x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86

Don't burden architectures without dynamic task_struct sizing
with the overhead of dynamic sizing.

Also optimize the x86 code a bit by caching task_struct_size.

Acked-and-Tested-by: Dave Hansen <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Brian Gerst <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Denys Vlasenko <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Oleg Nesterov <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

arch/Kconfig

···
 config ARCH_THREAD_INFO_ALLOCATOR
 	bool
 
+# Select if arch wants to size task_struct dynamically via arch_task_struct_size:
+config ARCH_WANTS_DYNAMIC_TASK_STRUCT
+	bool
+
 config HAVE_REGS_AND_STACK_ACCESS_API
 	bool
 	help

arch/x86/Kconfig

···
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
 	select ARCH_WANT_OPTIONAL_GPIOLIB

arch/x86/kernel/fpu/init.c

···
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 
+#include <linux/sched.h>
+
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
  * we are using:
···
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
-#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER)	\
-	BUILD_BUG_ON((sizeof(TYPE) -			\
-			offsetof(TYPE, MEMBER) -	\
-			sizeof(((TYPE *)0)->MEMBER)) > 	\
-			0)				\
+/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
+	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
 
 /*
- * We append the 'struct fpu' to the task_struct.
+ * We append the 'struct fpu' to the task_struct:
  */
-int __weak arch_task_struct_size(void)
+static void __init fpu__init_task_struct_size(void)
 {
 	int task_size = sizeof(struct task_struct);
 
···
 	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
 	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
 
-	return task_size;
+	arch_task_struct_size = task_size;
 }
 
 /*
···
 	fpu__init_system_generic();
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate();
+	fpu__init_task_struct_size();
 
 	fpu__init_system_ctx_switch();
 }

arch/x86/kernel/process.c

···
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst, src, arch_task_struct_size());
+	memcpy(dst, src, arch_task_struct_size);
 
 	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }

fs/proc/kcore.c

···
 			     roundup(sizeof(CORE_STR), 4)) +
 			roundup(sizeof(struct elf_prstatus), 4) +
 			roundup(sizeof(struct elf_prpsinfo), 4) +
-			roundup(arch_task_struct_size(), 4);
+			roundup(arch_task_struct_size, 4);
 	*elf_buflen = PAGE_ALIGN(*elf_buflen);
 	return size + *elf_buflen;
 }
···
 	/* set up the task structure */
 	notes[2].name	= CORE_STR;
 	notes[2].type	= NT_TASKSTRUCT;
-	notes[2].datasz	= arch_task_struct_size();
+	notes[2].datasz	= arch_task_struct_size;
 	notes[2].data	= current;
 
 	nhdr->p_filesz	+= notesize(&notes[2]);

include/linux/sched.h

···
  */
 };
 
-extern int arch_task_struct_size(void);
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+extern int arch_task_struct_size __read_mostly;
+#else
+# define arch_task_struct_size (sizeof(struct task_struct))
+#endif
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)

kernel/fork.c

···
 	max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
 }
 
-int __weak arch_task_struct_size(void)
-{
-	return sizeof(struct task_struct);
-}
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+/* Initialized by the architecture: */
+int arch_task_struct_size __read_mostly;
+#endif
 
 void __init fork_init(void)
 {
-	int task_struct_size = arch_task_struct_size();
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
 #endif
 	/* create a slab on which task_structs can be allocated */
 	task_struct_cachep =
-		kmem_cache_create("task_struct", task_struct_size,
+		kmem_cache_create("task_struct", arch_task_struct_size,
 			ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
 #endif