x86/fpu: Make task_struct::thread constant size

Turn thread.fpu into a pointer. Since most FPU code internals work by passing
around the FPU pointer already, the code generation impact is small.

This allows us to remove the old kludge of task_struct being variable size:

  struct task_struct {

       ...
       /*
        * New fields for task_struct should be added above here, so that
        * they are included in the randomized portion of task_struct.
        */
       randomized_struct_fields_end

       /* CPU-specific state of this task: */
       struct thread_struct            thread;

       /*
        * WARNING: on x86, 'thread_struct' contains a variable-sized
        * structure.  It *MUST* be at the end of 'task_struct'.
        *
        * Do not put anything below here!
        */
  };

... which creates a number of problems, such as requiring thread_struct to be
the last member of the struct - not allowing it to be struct-randomized, etc.

But the primary motivation is to allow the decoupling of task_struct from
hardware details (<asm/processor.h> in particular), and to eventually allow
the per-task infrastructure:

   DECLARE_PER_TASK(type, name);
   ...
   per_task(current, name) = val;

... which requires task_struct to be a constant size struct.

The fpu_thread_struct_whitelist() quirk to hardened usercopy can be removed,
now that the FPU structure is not embedded in the task struct anymore, which
reduces text footprint a bit.

Fixed-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>
Link: https://lore.kernel.org/r/20250409211127.3544993-4-mingo@kernel.org

1 files changed, 10 insertions, 7 deletions

diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index ad5cb2943d37..848ea79886ba 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -71,8 +71,15 @@ static bool __init fpu__probe_without_cpuid(void)
 	return fsw == 0 && (fcw & 0x103f) == 0x003f;
 }
 
+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;
+
 	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
 	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
 		if (fpu__probe_without_cpuid())
@@ -150,6 +157,8 @@ static void __init fpu__init_task_struct_size(void)
 {
 	int task_size = sizeof(struct task_struct);
 
+	task_size += sizeof(struct fpu);
+
 	/*
 	 * Subtract off the static size of the register state.
 	 * It potentially has a bunch of padding.
@@ -164,14 +173,9 @@ static void __init fpu__init_task_struct_size(void)
 
 	/*
 	 * We dynamically size 'struct fpu', so we require that
-	 * it be at the end of 'thread_struct' and that
-	 * 'thread_struct' be at the end of 'task_struct'.  If
-	 * you hit a compile error here, check the structure to
-	 * see if something got added to the end.
+	 * 'state' be at the end of 'it:
 	 */
 	CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate);
-	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
-	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
 
 	arch_task_struct_size = task_size;
 }
@@ -213,7 +217,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  */
 void __init fpu__init_system(void)
 {
-	fpstate_reset(x86_task_fpu(current));
 	fpu__init_system_early_generic();
 
 	/*