x86/fpu: Convert task_struct::thread.fpu accesses to use x86_task_fpu()

This will make the removal of the task_struct::thread.fpu array
easier.

No change in functionality - code generated before and after this
commit is identical on x86-defconfig:

kepler:~/tip> diff -up vmlinux.before.asm vmlinux.after.asm
kepler:~/tip>

Signed-off-by: Ingo Molnar <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: Brian Gerst <[e-mail]>
Cc: Chang S. Bae <[e-mail]>
Cc: H. Peter Anvin <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Oleg Nesterov <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/x86/include/asm/fpu/sched.h

···
 {
 	if (cpu_feature_enabled(X86_FEATURE_FPU) &&
 	    !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
-		struct fpu *old_fpu = &old->thread.fpu;
+		struct fpu *old_fpu = x86_task_fpu(old);
 
 		save_fpregs_to_fpstate(old_fpu);
 		/*

arch/x86/kernel/fpu/context.h

···
 /* Internal helper for switch_fpu_return() and signal frame setup */
 static inline void fpregs_restore_userregs(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int cpu = smp_processor_id();
 
 	if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER)))
···
 		 * If PKRU is enabled, then the PKRU value is already
 		 * correct because it was either set in switch_to() or in
 		 * flush_thread(). So it is excluded because it might be
-		 * not up to date in current->thread.fpu.xsave state.
+		 * not up to date in current->thread.fpu->xsave state.
 		 *
 		 * XFD state is handled in restore_fpregs_from_fpstate().
 		 */

arch/x86/kernel/fpu/core.c

···
 		return;
 
 	spin_lock_irq(&current->sighand->siglock);
-	fpuperm = &current->group_leader->thread.fpu.guest_perm;
+	fpuperm = &x86_task_fpu(current->group_leader)->guest_perm;
 	perm = fpuperm->__state_perm;
 
 	/* First fpstate allocation locks down permissions. */
···
  */
 void fpu_sync_guest_vmexit_xfd_state(void)
 {
-	struct fpstate *fps = current->thread.fpu.fpstate;
+	struct fpstate *fps = x86_task_fpu(current)->fpstate;
 
 	lockdep_assert_irqs_disabled();
 	if (fpu_state_size_dynamic()) {
···
 int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 {
 	struct fpstate *guest_fps = guest_fpu->fpstate;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *cur_fps = fpu->fpstate;
 
 	fpregs_lock();
···
 	if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) &&
 	    !test_thread_flag(TIF_NEED_FPU_LOAD)) {
 		set_thread_flag(TIF_NEED_FPU_LOAD);
-		save_fpregs_to_fpstate(&current->thread.fpu);
+		save_fpregs_to_fpstate(x86_task_fpu(current));
 	}
 	__cpu_invalidate_fpregs_state();
 
···
  */
 void fpu_sync_fpstate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu);
+	WARN_ON_FPU(fpu != x86_task_fpu(current));
 
 	fpregs_lock();
 	trace_x86_fpu_before_save(fpu);
···
 static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 {
 	if (fpu_state_size_dynamic()) {
-		struct fpu *src_fpu = &current->group_leader->thread.fpu;
+		struct fpu *src_fpu = x86_task_fpu(current->group_leader);
 
 		spin_lock_irq(&current->sighand->siglock);
 		/* Fork also inherits the permissions of the parent */
···
 	if (!ssp)
 		return 0;
 
-	xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave,
+	xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave,
 				XFEATURE_CET_USER);
 
 	/*
···
 int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	      unsigned long ssp)
 {
-	struct fpu *src_fpu = &current->thread.fpu;
-	struct fpu *dst_fpu = &dst->thread.fpu;
+	struct fpu *src_fpu = x86_task_fpu(current);
+	struct fpu *dst_fpu = x86_task_fpu(dst);
 
 	/* The new task's FPU state cannot be valid in the hardware. */
 	dst_fpu->last_cpu = -1;
···
 {
 	preempt_disable();
 
-	if (fpu == &current->thread.fpu) {
+	if (fpu == x86_task_fpu(current)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
···
  */
 static void fpu_reset_fpregs(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	fpregs_lock();
 	__fpu_invalidate_fpregs_state(fpu);
···
  */
 void fpu__clear_user_states(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu);
+	WARN_ON_FPU(fpu != x86_task_fpu(current));
 
 	fpregs_lock();
 	if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
···
 
 void fpu_flush_thread(void)
 {
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 	fpu_reset_fpregs();
 }
 /*
···
  */
 void fpregs_assert_state_consistent(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		return;
···
 
 void fpregs_mark_activate(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	fpregs_activate(fpu);
 	fpu->last_cpu = smp_processor_id();

arch/x86/kernel/fpu/init.c

···
 	/* Flush out any pending x87 state: */
 #ifdef CONFIG_MATH_EMULATION
 	if (!boot_cpu_has(X86_FEATURE_FPU))
-		fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+		fpstate_init_soft(&x86_task_fpu(current)->fpstate->regs.soft);
 	else
 #endif
 		asm volatile ("fninit");
···
 	 * Subtract off the static size of the register state.
 	 * It potentially has a bunch of padding.
 	 */
-	task_size -= sizeof(current->thread.fpu.__fpstate.regs);
+	task_size -= sizeof(union fpregs_state);
 
 	/*
 	 * Add back the dynamically-calculated register state
···
 	fpu_kernel_cfg.default_size = size;
 	fpu_user_cfg.max_size = size;
 	fpu_user_cfg.default_size = size;
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 }
 
 /*
···
  */
 void __init fpu__init_system(void)
 {
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 	fpu__init_system_early_generic();
 
 	/*

arch/x86/kernel/fpu/regset.c

···
  */
 static void sync_fpstate(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu)
+	if (fpu == x86_task_fpu(current))
 		fpu_sync_fpstate(fpu);
 }
 
···
 	 * Only stopped child tasks can be used to modify the FPU
 	 * state in the fpstate buffer:
 	 */
-	WARN_ON_FPU(fpu == &current->thread.fpu);
+	WARN_ON_FPU(fpu == x86_task_fpu(current));
 
 	__fpu_invalidate_fpregs_state(fpu);
 }
···
 int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 		struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 
 	if (!cpu_feature_enabled(X86_FEATURE_FXSR))
 		return -ENODEV;
···
 		unsigned int pos, unsigned int count,
 		const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct fxregs_state newstate;
 	int ret;
 
···
 	if (!cpu_feature_enabled(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
-	sync_fpstate(&target->thread.fpu);
+	sync_fpstate(x86_task_fpu(target));
 
 	copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE);
 	return 0;
···
 		  unsigned int pos, unsigned int count,
 		  const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct xregs_state *tmpbuf = NULL;
 	int ret;
 
···
 int ssp_get(struct task_struct *target, const struct user_regset *regset,
 	    struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct cet_user_state *cetregs;
 
 	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
···
 	    unsigned int pos, unsigned int count,
 	    const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct xregs_state *xsave = &fpu->fpstate->regs.xsave;
 	struct cet_user_state *cetregs;
 	unsigned long user_ssp;
···
 void
 convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 {
-	__convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave);
+	__convert_from_fxsr(env, tsk, &x86_task_fpu(tsk)->fpstate->regs.fxsave);
 }
 
 void convert_to_fxsr(struct fxregs_state *fxsave,
···
 int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	       struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct user_i387_ia32_struct env;
 	struct fxregs_state fxsave, *fx;
 
···
 	       unsigned int pos, unsigned int count,
 	       const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct user_i387_ia32_struct env;
 	int ret;
 

arch/x86/kernel/fpu/signal.c

···
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + current->thread.fpu.fpstate->user_size)))
+	if (__get_user(magic2, (__u32 __user *)(fpstate + x86_task_fpu(current)->fpstate->user_size)))
 		return false;
 
 	if (likely(magic2 == FP_XSTATE_MAGIC2))
 		return true;
 setfx:
-	trace_x86_fpu_xstate_check_failed(&current->thread.fpu);
+	trace_x86_fpu_xstate_check_failed(x86_task_fpu(current));
 
 	/* Set the parameters for fx only state */
 	fx_sw->magic1 = 0;
···
 static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
 {
 	if (use_fxsr()) {
-		struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave;
+		struct xregs_state *xsave = &x86_task_fpu(tsk)->fpstate->regs.xsave;
 		struct user_i387_ia32_struct env;
 		struct _fpstate_32 __user *fp = buf;
 
 		fpregs_lock();
 		if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-			fxsave(&tsk->thread.fpu.fpstate->regs.fxsave);
+			fxsave(&x86_task_fpu(tsk)->fpstate->regs.fxsave);
 		fpregs_unlock();
 
 		convert_from_fxsr(&env, tsk);
···
 bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru)
 {
 	struct task_struct *tsk = current;
-	struct fpstate *fpstate = tsk->thread.fpu.fpstate;
+	struct fpstate *fpstate = x86_task_fpu(tsk)->fpstate;
 	bool ia32_fxstate = (buf != buf_fx);
 	int ret;
 
···
  */
 static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int ret;
 
 	/* Restore enabled features only. */
···
 			      bool ia32_fxstate)
 {
 	struct task_struct *tsk = current;
-	struct fpu *fpu = &tsk->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(tsk);
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
···
  */
 bool fpu__restore_sig(void __user *buf, int ia32_frame)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	void __user *buf_fx = buf;
 	bool ia32_fxstate = false;
 	bool success = false;
···
 fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
 		     unsigned long *buf_fx, unsigned long *size)
 {
-	unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate);
+	unsigned long frame_size = xstate_sigframe_size(x86_task_fpu(current)->fpstate);
 
 	*buf_fx = sp = round_down(sp - frame_size, 64);
 	if (ia32_frame && use_fxsr()) {

arch/x86/kernel/fpu/xstate.c

···
 	 */
 	init_fpstate.xfd = 0;
 
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 }
 
 /*
···
 		goto out_disable;
 
 	/* Reset the state for the current task */
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 
 	/*
 	 * Update info used for ptrace frames; use standard-format size and no
···
 	}
 
 	if (fpu_state_size_dynamic())
-		wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+		wrmsrl(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
 }
 
 /*
···
 void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 			     enum xstate_copy_mode copy_mode)
 {
-	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
-				  tsk->thread.fpu.fpstate->user_xfeatures,
+	__copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+				  x86_task_fpu(tsk)->fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }
 
···
 int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+	return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru);
 }
 
 static bool validate_independent_components(u64 mask)
···
 	  * The XFD MSR does not match fpstate->xfd. That's invalid when
 	  * the passed in fpstate is current's fpstate.
 	  */
-	if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+	if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd)
 		return false;
 
 	/*
···
 static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 			   unsigned int usize, struct fpu_guest *guest_fpu)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *curfps, *newfps = NULL;
 	unsigned int fpsize;
 	bool in_use;
···
 	 * AVX512.
 	 */
 	bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	u64 mask;
···
 		return -EPERM;
 	}
 
-	fpu = &current->group_leader->thread.fpu;
+	fpu = x86_task_fpu(current->group_leader);
 	perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
 	ksize = perm->__state_size;
 	usize = perm->__user_state_size;
···
  */
 static void avx512_status(struct seq_file *m, struct task_struct *task)
 {
-	unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+	unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
 	long delta;
 
 	if (!timestamp) {

arch/x86/kernel/fpu/xstate.h

···
 
 static inline u64 xstate_get_group_perm(bool guest)
 {
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 
 	/* Pairs with WRITE_ONCE() in xstate_request_perm() */
···
 	 * internally, e.g. PKRU. That's user space ABI and also required
 	 * to allow the signal handler to modify PKRU.
 	 */
-	struct fpstate *fpstate = current->thread.fpu.fpstate;
+	struct fpstate *fpstate = x86_task_fpu(current)->fpstate;
 	u64 mask = fpstate->user_xfeatures;
 	u32 lmask;
 	u32 hmask;
···
 	u32 hmask = mask >> 32;
 	int err;
 
-	xfd_validate_state(current->thread.fpu.fpstate, mask, true);
+	xfd_validate_state(x86_task_fpu(current)->fpstate, mask, true);
 
 	stac();
 	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);

arch/x86/kernel/process.c

···
 	dst->thread.vm86 = NULL;
 #endif
 	/* Drop the copied pointer to current's fpstate */
-	dst->thread.fpu.fpstate = NULL;
+	x86_task_fpu(dst)->fpstate = NULL;
 
 	return 0;
 }
···
 void arch_release_task_struct(struct task_struct *tsk)
 {
 	if (fpu_state_size_dynamic())
-		fpstate_free(&tsk->thread.fpu);
+		fpstate_free(x86_task_fpu(tsk));
 }
 #endif
 
···
 void exit_thread(struct task_struct *tsk)
 {
 	struct thread_struct *t = &tsk->thread;
-	struct fpu *fpu = &t->fpu;
+	struct fpu *fpu = x86_task_fpu(tsk);
 
 	if (test_thread_flag(TIF_IO_BITMAP))
 		io_bitmap_exit(tsk);

arch/x86/kernel/signal.c

···
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	if (v8086_mode(regs))
 		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
···
 	if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
 		return true;
 
-	fsize += current->group_leader->thread.fpu.perm.__user_state_size;
+	fsize += x86_task_fpu(current->group_leader)->perm.__user_state_size;
 	if (likely(ss_size > fsize))
 		return true;
 
 	if (strict_sigaltstack_size)
 		return ss_size > fsize;
 
-	mask = current->group_leader->thread.fpu.perm.__state_perm;
+	mask = x86_task_fpu(current->group_leader)->perm.__state_perm;
 	if (mask & XFEATURE_MASK_USER_DYNAMIC)
 		return ss_size > fsize;
 

arch/x86/kernel/traps.c

···
 static void math_error(struct pt_regs *regs, int trapnr)
 {
 	struct task_struct *task = current;
-	struct fpu *fpu = &task->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(task);
 	int si_code;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";

arch/x86/math-emu/fpu_aux.c

···
 
 void finit(void)
 {
-	fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+	fpstate_init_soft(&x86_task_fpu(current)->fpstate->regs.soft);
 }
 
 /*

arch/x86/math-emu/fpu_entry.c

···
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
···
 		    const struct user_regset *regset,
 		    struct membuf to)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	const void *space = s387->st_space;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;
 

arch/x86/math-emu/fpu_system.h

···
 	return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
 }
 
-#define I387			(&current->thread.fpu.fpstate->regs)
+#define I387			(&x86_task_fpu(current)->fpstate->regs)
 #define FPU_info		(I387->soft.info)
 
 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))

arch/x86/mm/extable.c

···
 
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
- * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * here because the FPU state of a task using the FPU (struct fpu::fpstate)
  * should always be valid.  However, past bugs have allowed userspace to set
  * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
  * These caused XRSTOR to fail when switching to the task, leaking the FPU