1 files changed, 165 insertions, 211 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 8370d55f0353..c37f02d7194e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -119,7 +119,7 @@
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
 
-static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
 
 __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
 #ifdef CONFIG_ARM64_SVE
@@ -180,12 +180,12 @@ static inline void set_sve_default_vl(int val)
 	set_default_vl(ARM64_VEC_SVE, val);
 }
 
-static void __percpu *efi_sve_state;
+static u8 *efi_sve_state;
 
 #else /* ! CONFIG_ARM64_SVE */
 
 /* Dummy declaration for code that will be optimised out: */
-extern void __percpu *efi_sve_state;
+extern u8 *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
@@ -359,20 +359,15 @@ static void task_fpsimd_load(void)
 	WARN_ON(preemptible());
 	WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
 
-	if (system_supports_fpmr())
-		write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
-
 	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
 		case FP_STATE_FPSIMD:
 			/* Stop tracking SVE for this task until next use. */
-			if (test_and_clear_thread_flag(TIF_SVE))
-				sve_user_disable();
+			clear_thread_flag(TIF_SVE);
 			break;
 		case FP_STATE_SVE:
-			if (!thread_sm_enabled(&current->thread) &&
-			    !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE)))
-				sve_user_enable();
+			if (!thread_sm_enabled(&current->thread))
+				WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE));
 
 			if (test_thread_flag(TIF_SVE))
 				sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
@@ -413,6 +408,9 @@ static void task_fpsimd_load(void)
 			restore_ffr = system_supports_fa64();
 	}
 
+	if (system_supports_fpmr())
+		write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
+
 	if (restore_sve_regs) {
 		WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
 		sve_load_state(sve_pffr(&current->thread),
@@ -453,12 +451,15 @@ static void fpsimd_save_user_state(void)
 		*(last->fpmr) = read_sysreg_s(SYS_FPMR);
 
 	/*
-	 * If a task is in a syscall the ABI allows us to only
-	 * preserve the state shared with FPSIMD so don't bother
-	 * saving the full SVE state in that case.
+	 * Save SVE state if it is live.
+	 *
+	 * The syscall ABI discards live SVE state at syscall entry. When
+	 * entering a syscall, fpsimd_syscall_enter() sets to_save to
+	 * FP_STATE_FPSIMD to allow the SVE state to be lazily discarded until
+	 * either new SVE state is loaded+bound or fpsimd_syscall_exit() is
+	 * called prior to a return to userspace.
 	 */
-	if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) &&
-	     !in_syscall(current_pt_regs())) ||
+	if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE)) ||
 	    last->to_save == FP_STATE_SVE) {
 		save_sve_regs = true;
 		save_ffr = true;
@@ -651,7 +652,7 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
  * task->thread.uw.fpsimd_state must be up to date before calling this
  * function.
  */
-static void fpsimd_to_sve(struct task_struct *task)
+static inline void fpsimd_to_sve(struct task_struct *task)
 {
 	unsigned int vq;
 	void *sst = task->thread.sve_state;
@@ -675,7 +676,7 @@ static void fpsimd_to_sve(struct task_struct *task)
  * bytes of allocated kernel memory.
  * task->thread.sve_state must be up to date before calling this function.
  */
-static void sve_to_fpsimd(struct task_struct *task)
+static inline void sve_to_fpsimd(struct task_struct *task)
 {
 	unsigned int vq, vl;
 	void const *sst = task->thread.sve_state;
@@ -694,44 +695,39 @@ static void sve_to_fpsimd(struct task_struct *task)
 	}
 }
 
-void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
+static inline void __fpsimd_zero_vregs(struct user_fpsimd_state *fpsimd)
 {
-	write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
-		       SYS_SCTLR_EL1);
+	memset(&fpsimd->vregs, 0, sizeof(fpsimd->vregs));
 }
 
-#ifdef CONFIG_ARM64_SVE
 /*
- * Call __sve_free() directly only if you know task can't be scheduled
- * or preempted.
+ * Simulate the effects of an SMSTOP SM instruction.
  */
-static void __sve_free(struct task_struct *task)
+void task_smstop_sm(struct task_struct *task)
 {
-	kfree(task->thread.sve_state);
-	task->thread.sve_state = NULL;
-}
+	if (!thread_sm_enabled(&task->thread))
+		return;
 
-static void sve_free(struct task_struct *task)
-{
-	WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+	__fpsimd_zero_vregs(&task->thread.uw.fpsimd_state);
+	task->thread.uw.fpsimd_state.fpsr = 0x0800009f;
+	if (system_supports_fpmr())
+		task->thread.uw.fpmr = 0;
 
-	__sve_free(task);
+	task->thread.svcr &= ~SVCR_SM_MASK;
+	task->thread.fp_type = FP_STATE_FPSIMD;
 }
 
-/*
- * Return how many bytes of memory are required to store the full SVE
- * state for task, given task's currently configured vector length.
- */
-size_t sve_state_size(struct task_struct const *task)
+void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
 {
-	unsigned int vl = 0;
-
-	if (system_supports_sve())
-		vl = task_get_sve_vl(task);
-	if (system_supports_sme())
-		vl = max(vl, task_get_sme_vl(task));
+	write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
+		       SYS_SCTLR_EL1);
+}
 
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+#ifdef CONFIG_ARM64_SVE
+static void sve_free(struct task_struct *task)
+{
+	kfree(task->thread.sve_state);
+	task->thread.sve_state = NULL;
 }
 
 /*
@@ -758,69 +754,34 @@ void sve_alloc(struct task_struct *task, bool flush)
 		kzalloc(sve_state_size(task), GFP_KERNEL);
 }
 
-
-/*
- * Force the FPSIMD state shared with SVE to be updated in the SVE state
- * even if the SVE state is the current active state.
- *
- * This should only be called by ptrace.  task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- */
-void fpsimd_force_sync_to_sve(struct task_struct *task)
-{
-	fpsimd_to_sve(task);
-}
-
-/*
- * Ensure that task->thread.sve_state is up to date with respect to
- * the user task, irrespective of when SVE is in use or not.
- *
- * This should only be called by ptrace.  task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- */
-void fpsimd_sync_to_sve(struct task_struct *task)
-{
-	if (!test_tsk_thread_flag(task, TIF_SVE) &&
-	    !thread_sm_enabled(&task->thread))
-		fpsimd_to_sve(task);
-}
-
 /*
- * Ensure that task->thread.uw.fpsimd_state is up to date with respect to
- * the user task, irrespective of whether SVE is in use or not.
+ * Ensure that task->thread.uw.fpsimd_state is up to date with respect to the
+ * task's currently effective FPSIMD/SVE state.
  *
- * This should only be called by ptrace.  task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
+ * The task's FPSIMD/SVE/SME state must not be subject to concurrent
+ * manipulation.
  */
-void sve_sync_to_fpsimd(struct task_struct *task)
+void fpsimd_sync_from_effective_state(struct task_struct *task)
 {
 	if (task->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(task);
 }
 
 /*
- * Ensure that task->thread.sve_state is up to date with respect to
- * the task->thread.uw.fpsimd_state.
+ * Ensure that the task's currently effective FPSIMD/SVE state is up to date
+ * with respect to task->thread.uw.fpsimd_state, zeroing any effective
+ * non-FPSIMD (S)SVE state.
  *
- * This should only be called by ptrace to merge new FPSIMD register
- * values into a task for which SVE is currently active.
- * task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- * task->thread.uw.fpsimd_state must already have been initialised with
- * the new FPSIMD register values to be merged in.
+ * The task's FPSIMD/SVE/SME state must not be subject to concurrent
+ * manipulation.
  */
-void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
+void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task)
 {
 	unsigned int vq;
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 
-	if (!test_tsk_thread_flag(task, TIF_SVE) &&
-	    !thread_sm_enabled(&task->thread))
+	if (task->thread.fp_type != FP_STATE_SVE)
 		return;
 
 	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -829,10 +790,73 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	__fpsimd_to_sve(sst, fst, vq);
 }
 
+static int change_live_vector_length(struct task_struct *task,
+				     enum vec_type type,
+				     unsigned long vl)
+{
+	unsigned int sve_vl = task_get_sve_vl(task);
+	unsigned int sme_vl = task_get_sme_vl(task);
+	void *sve_state = NULL, *sme_state = NULL;
+
+	if (type == ARM64_VEC_SME)
+		sme_vl = vl;
+	else
+		sve_vl = vl;
+
+	/*
+	 * Allocate the new sve_state and sme_state before freeing the old
+	 * copies so that allocation failure can be handled without needing to
+	 * mutate the task's state in any way.
+	 *
+	 * Changes to the SVE vector length must not discard live ZA state or
+	 * clear PSTATE.ZA, as userspace code which is unaware of the AAPCS64
+	 * ZA lazy saving scheme may attempt to change the SVE vector length
+	 * while unsaved/dormant ZA state exists.
+	 */
+	sve_state = kzalloc(__sve_state_size(sve_vl, sme_vl), GFP_KERNEL);
+	if (!sve_state)
+		goto out_mem;
+
+	if (type == ARM64_VEC_SME) {
+		sme_state = kzalloc(__sme_state_size(sme_vl), GFP_KERNEL);
+		if (!sme_state)
+			goto out_mem;
+	}
+
+	if (task == current)
+		fpsimd_save_and_flush_current_state();
+	else
+		fpsimd_flush_task_state(task);
+
+	/*
+	 * Always preserve PSTATE.SM and the effective FPSIMD state, zeroing
+	 * other SVE state.
+	 */
+	fpsimd_sync_from_effective_state(task);
+	task_set_vl(task, type, vl);
+	kfree(task->thread.sve_state);
+	task->thread.sve_state = sve_state;
+	fpsimd_sync_to_effective_state_zeropad(task);
+
+	if (type == ARM64_VEC_SME) {
+		task->thread.svcr &= ~SVCR_ZA_MASK;
+		kfree(task->thread.sme_state);
+		task->thread.sme_state = sme_state;
+	}
+
+	return 0;
+
+out_mem:
+	kfree(sve_state);
+	kfree(sme_state);
+	return -ENOMEM;
+}
+
 int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 			  unsigned long vl, unsigned long flags)
 {
-	bool free_sme = false;
+	bool onexec = flags & PR_SVE_SET_VL_ONEXEC;
+	bool inherit = flags & PR_SVE_VL_INHERIT;
 
 	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
 				     PR_SVE_SET_VL_ONEXEC))
@@ -852,71 +876,17 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 
 	vl = find_supported_vector_length(type, vl);
 
-	if (flags & (PR_SVE_VL_INHERIT |
-		     PR_SVE_SET_VL_ONEXEC))
+	if (!onexec && vl != task_get_vl(task, type)) {
+		if (change_live_vector_length(task, type, vl))
+			return -ENOMEM;
+	}
+
+	if (onexec || inherit)
 		task_set_vl_onexec(task, type, vl);
 	else
 		/* Reset VL to system default on next exec: */
 		task_set_vl_onexec(task, type, 0);
 
-	/* Only actually set the VL if not deferred: */
-	if (flags & PR_SVE_SET_VL_ONEXEC)
-		goto out;
-
-	if (vl == task_get_vl(task, type))
-		goto out;
-
-	/*
-	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
-	 * write any live register state back to task_struct, and convert to a
-	 * regular FPSIMD thread.
-	 */
-	if (task == current) {
-		get_cpu_fpsimd_context();
-
-		fpsimd_save_user_state();
-	}
-
-	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
-	    thread_sm_enabled(&task->thread)) {
-		sve_to_fpsimd(task);
-		task->thread.fp_type = FP_STATE_FPSIMD;
-	}
-
-	if (system_supports_sme()) {
-		if (type == ARM64_VEC_SME ||
-		    !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) {
-			/*
-			 * We are changing the SME VL or weren't using
-			 * SME anyway, discard the state and force a
-			 * reallocation.
-			 */
-			task->thread.svcr &= ~(SVCR_SM_MASK |
-					       SVCR_ZA_MASK);
-			clear_tsk_thread_flag(task, TIF_SME);
-			free_sme = true;
-		}
-	}
-
-	if (task == current)
-		put_cpu_fpsimd_context();
-
-	task_set_vl(task, type, vl);
-
-	/*
-	 * Free the changed states if they are not in use, SME will be
-	 * reallocated to the correct size on next use and we just
-	 * allocate SVE now in case it is needed for use in streaming
-	 * mode.
-	 */
-	sve_free(task);
-	sve_alloc(task, true);
-
-	if (free_sme)
-		sme_free(task);
-
-out:
 	update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
 			       flags & PR_SVE_VL_INHERIT);
 
@@ -1131,15 +1101,15 @@ static void __init sve_efi_setup(void)
 	if (!sve_vl_valid(max_vl))
 		goto fail;
 
-	efi_sve_state = __alloc_percpu(
-		SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
+	efi_sve_state = kmalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)),
+				GFP_KERNEL);
 	if (!efi_sve_state)
 		goto fail;
 
 	return;
 
 fail:
-	panic("Cannot allocate percpu memory for EFI SVE save/restore");
+	panic("Cannot allocate memory for EFI SVE save/restore");
 }
 
 void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1212,7 +1182,7 @@ void __init sve_setup(void)
  */
 void fpsimd_release_task(struct task_struct *dead_task)
 {
-	__sve_free(dead_task);
+	sve_free(dead_task);
 	sme_free(dead_task);
 }
 
@@ -1436,7 +1406,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 	 * If this not a trap due to SME being disabled then something
 	 * is being used in the wrong mode, report as SIGILL.
 	 */
-	if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+	if (ESR_ELx_SME_ISS_SMTC(esr) != ESR_ELx_SME_ISS_SMTC_SME_DISABLED) {
 		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
 		return;
 	}
@@ -1460,6 +1430,8 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		sme_set_vq(vq_minus_one);
 
 		fpsimd_bind_task_to_cpu();
+	} else {
+		fpsimd_flush_task_state(current);
 	}
 
 	put_cpu_fpsimd_context();
@@ -1573,8 +1545,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 		fpsimd_save_user_state();
 
 	if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
-		fpsimd_load_kernel_state(next);
 		fpsimd_flush_cpu_state();
+		fpsimd_load_kernel_state(next);
 	} else {
 		/*
 		 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
@@ -1661,6 +1633,9 @@ void fpsimd_flush_thread(void)
 		current->thread.svcr = 0;
 	}
 
+	if (system_supports_fpmr())
+		current->thread.uw.fpmr = 0;
+
 	current->thread.fp_type = FP_STATE_FPSIMD;
 
 	put_cpu_fpsimd_context();
@@ -1683,18 +1658,6 @@ void fpsimd_preserve_current_state(void)
 }
 
 /*
- * Like fpsimd_preserve_current_state(), but ensure that
- * current->thread.uw.fpsimd_state is updated so that it can be copied to
- * the signal frame.
- */
-void fpsimd_signal_preserve_current_state(void)
-{
-	fpsimd_preserve_current_state();
-	if (current->thread.fp_type == FP_STATE_SVE)
-		sve_to_fpsimd(current);
-}
-
-/*
  * Associate current's FPSIMD context with this cpu
  * The caller must have ownership of the cpu FPSIMD context before calling
  * this function.
@@ -1786,30 +1749,14 @@ void fpsimd_restore_current_state(void)
 	put_cpu_fpsimd_context();
 }
 
-/*
- * Load an updated userland FPSIMD state for 'current' from memory and set the
- * flag that indicates that the FPSIMD register contents are the most recent
- * FPSIMD state of 'current'. This is used by the signal code to restore the
- * register state when returning from a signal handler in FPSIMD only cases,
- * any SVE context will be discarded.
- */
 void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 {
 	if (WARN_ON(!system_supports_fpsimd()))
 		return;
 
-	get_cpu_fpsimd_context();
-
 	current->thread.uw.fpsimd_state = *state;
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		fpsimd_to_sve(current);
-
-	task_fpsimd_load();
-	fpsimd_bind_task_to_cpu();
-
-	clear_thread_flag(TIF_FOREIGN_FPSTATE);
-
-	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1839,6 +1786,17 @@ void fpsimd_flush_task_state(struct task_struct *t)
 	barrier();
 }
 
+void fpsimd_save_and_flush_current_state(void)
+{
+	if (!system_supports_fpsimd())
+		return;
+
+	get_cpu_fpsimd_context();
+	fpsimd_save_user_state();
+	fpsimd_flush_task_state(current);
+	put_cpu_fpsimd_context();
+}
+
 /*
  * Save the FPSIMD state to memory and invalidate cpu view.
  * This function must be called with preemption disabled.
@@ -1948,10 +1906,10 @@ EXPORT_SYMBOL_GPL(kernel_neon_end);
 
 #ifdef CONFIG_EFI
 
-static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
-static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
-static DEFINE_PER_CPU(bool, efi_sve_state_used);
-static DEFINE_PER_CPU(bool, efi_sm_state);
+static struct user_fpsimd_state efi_fpsimd_state;
+static bool efi_fpsimd_state_used;
+static bool efi_sve_state_used;
+static bool efi_sm_state;
 
 /*
  * EFI runtime services support functions
@@ -1984,18 +1942,16 @@ void __efi_fpsimd_begin(void)
 		 * If !efi_sve_state, SVE can't be in use yet and doesn't need
 		 * preserving:
 		 */
-		if (system_supports_sve() && likely(efi_sve_state)) {
-			char *sve_state = this_cpu_ptr(efi_sve_state);
+		if (system_supports_sve() && efi_sve_state != NULL) {
 			bool ffr = true;
 			u64 svcr;
 
-			__this_cpu_write(efi_sve_state_used, true);
+			efi_sve_state_used = true;
 
 			if (system_supports_sme()) {
 				svcr = read_sysreg_s(SYS_SVCR);
 
-				__this_cpu_write(efi_sm_state,
-						 svcr & SVCR_SM_MASK);
+				efi_sm_state = svcr & SVCR_SM_MASK;
 
 				/*
 				 * Unless we have FA64 FFR does not
@@ -2005,19 +1961,18 @@ void __efi_fpsimd_begin(void)
 					ffr = !(svcr & SVCR_SM_MASK);
 			}
 
-			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
-				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       ffr);
+			sve_save_state(efi_sve_state + sve_ffr_offset(sve_max_vl()),
+				       &efi_fpsimd_state.fpsr, ffr);
 
 			if (system_supports_sme())
 				sysreg_clear_set_s(SYS_SVCR,
 						   SVCR_SM_MASK, 0);
 
 		} else {
-			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+			fpsimd_save_state(&efi_fpsimd_state);
 		}
 
-		__this_cpu_write(efi_fpsimd_state_used, true);
+		efi_fpsimd_state_used = true;
 	}
 }
 
@@ -2029,12 +1984,10 @@ void __efi_fpsimd_end(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
+	if (!efi_fpsimd_state_used) {
 		kernel_neon_end();
 	} else {
-		if (system_supports_sve() &&
-		    likely(__this_cpu_read(efi_sve_state_used))) {
-			char const *sve_state = this_cpu_ptr(efi_sve_state);
+		if (system_supports_sve() && efi_sve_state_used) {
 			bool ffr = true;
 
 			/*
@@ -2043,7 +1996,7 @@ void __efi_fpsimd_end(void)
 			 * streaming mode.
 			 */
 			if (system_supports_sme()) {
-				if (__this_cpu_read(efi_sm_state)) {
+				if (efi_sm_state) {
 					sysreg_clear_set_s(SYS_SVCR,
 							   0,
 							   SVCR_SM_MASK);
@@ -2057,14 +2010,15 @@ void __efi_fpsimd_end(void)
 				}
 			}
 
-			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
-				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       ffr);
+			sve_load_state(efi_sve_state + sve_ffr_offset(sve_max_vl()),
+				       &efi_fpsimd_state.fpsr, ffr);
 
-			__this_cpu_write(efi_sve_state_used, false);
+			efi_sve_state_used = false;
 		} else {
-			fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
+			fpsimd_load_state(&efi_fpsimd_state);
 		}
+
+		efi_fpsimd_state_used = false;
 	}
 }