x86/fpu: Remove the thread::fpu pointer

As suggested by Oleg, remove the thread::fpu pointer, as we can
calculate it via x86_task_fpu() at compile-time.

This improves code generation a bit:

   kepler:~/tip> size vmlinux.before vmlinux.after
   text        data        bss        dec         hex        filename
   26475405    10435342    1740804    38651551    24dc69f    vmlinux.before
   26475339    10959630    1216516    38651485    24dc65d    vmlinux.after

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Chang S. Bae <chang.seok.bae@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20250409211127.3544993-5-mingo@kernel.org

Author: Ingo Molnar

arch/x86/include/asm/processor.h

@@ -514,12 +514,9 @@ struct thread_struct {
 
 	struct thread_shstk	shstk;
 #endif
-
-	/* Floating point and extended processor state */
-	struct fpu		*fpu;
 };
 
-#define x86_task_fpu(task) ((task)->thread.fpu)
+#define x86_task_fpu(task)	((struct fpu *)((void *)(task) + sizeof(*(task))))
 
 /*
  * X86 doesn't need any embedded-FPU-struct quirks:

arch/x86/kernel/fpu/core.c

@@ -600,13 +600,11 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	 * This is safe because task_struct size is a multiple of cacheline size.
 	 */
 	struct fpu *src_fpu = x86_task_fpu(current);
-	struct fpu *dst_fpu = (void *)dst + sizeof(*dst);
+	struct fpu *dst_fpu = x86_task_fpu(dst);
 
 	BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0);
 	BUG_ON(!src_fpu);
 
-	dst->thread.fpu = dst_fpu;
-
 	/* The new task's FPU state cannot be valid in the hardware. */
 	dst_fpu->last_cpu = -1;
 

arch/x86/kernel/fpu/init.c

@@ -76,7 +76,6 @@ static struct fpu x86_init_fpu __attribute__ ((aligned (64))) __read_mostly;
 static void __init fpu__init_system_early_generic(void)
 {
 	fpstate_reset(&x86_init_fpu);
-	current->thread.fpu = &x86_init_fpu;
 	set_thread_flag(TIF_NEED_FPU_LOAD);
 	x86_init_fpu.last_cpu = -1;
 

arch/x86/kernel/process.c

@@ -102,8 +102,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif
-	/* Drop the copied pointer to current's fpstate */
-	dst->thread.fpu = NULL;
 
 	return 0;
 }

arch/x86/kernel/vmlinux.lds.S

@@ -181,6 +181,10 @@ SECTIONS
 		/* equivalent to task_pt_regs(&init_task) */
 		__top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE;
 
+		__x86_init_fpu_begin = .;
+		. = __x86_init_fpu_begin + 128*PAGE_SIZE;
+		__x86_init_fpu_end = .;
+
 #ifdef CONFIG_X86_32
 		/* 32 bit has nosave before _edata */
 		NOSAVE_DATA