arm64/sve: Generalise vector length configuration prctl() for SME

In preparation for adding SME support update the bulk of the implementation
for the vector length configuration prctl() calls to be independent of
vector type.

Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: broonie

arch/arm64/include/asm/fpsimd.h

@@ -51,8 +51,8 @@ extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
-/* Maximum VL that SVE VL-agnostic software can transparently support */
-#define SVE_VL_ARCH_MAX 0x100
+/* Maximum VL that SVE/SME VL-agnostic software can transparently support */
+#define VL_ARCH_MAX 0x100
 
 /* Offset of FFR in the SVE register dump */
 static inline size_t sve_ffr_offset(int vl)
@@ -122,7 +122,7 @@ extern void fpsimd_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
-extern int sve_set_vector_length(struct task_struct *task,
+extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 				 unsigned long vl, unsigned long flags);
 
 extern int sve_set_current_vl(unsigned long arg);

arch/arm64/kernel/fpsimd.c

@@ -632,7 +632,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	__fpsimd_to_sve(sst, fst, vq);
 }
 
-int sve_set_vector_length(struct task_struct *task,
+int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 			  unsigned long vl, unsigned long flags)
 {
 	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
@@ -643,33 +643,35 @@ int sve_set_vector_length(struct task_struct *task,
 		return -EINVAL;
 
 	/*
-	 * Clamp to the maximum vector length that VL-agnostic SVE code can
-	 * work with.  A flag may be assigned in the future to allow setting
-	 * of larger vector lengths without confusing older software.
+	 * Clamp to the maximum vector length that VL-agnostic code
+	 * can work with.  A flag may be assigned in the future to
+	 * allow setting of larger vector lengths without confusing
+	 * older software.
 	 */
-	if (vl > SVE_VL_ARCH_MAX)
-		vl = SVE_VL_ARCH_MAX;
+	if (vl > VL_ARCH_MAX)
+		vl = VL_ARCH_MAX;
 
-	vl = find_supported_vector_length(ARM64_VEC_SVE, vl);
+	vl = find_supported_vector_length(type, vl);
 
 	if (flags & (PR_SVE_VL_INHERIT |
 		     PR_SVE_SET_VL_ONEXEC))
-		task_set_sve_vl_onexec(task, vl);
+		task_set_vl_onexec(task, type, vl);
 	else
 		/* Reset VL to system default on next exec: */
-		task_set_sve_vl_onexec(task, 0);
+		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_sve_vl(task))
+	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
-	 * non-SVE thread.
+	 * regular FPSIMD thread.  Since the vector length can only be changed
+	 * with a syscall we can't be in streaming mode while reconfiguring.
 	 */
 	if (task == current) {
 		get_cpu_fpsimd_context();
@@ -690,31 +692,32 @@ int sve_set_vector_length(struct task_struct *task,
 	 */
 	sve_free(task);
 
-	task_set_sve_vl(task, vl);
+	task_set_vl(task, type, vl);
 
 out:
-	update_tsk_thread_flag(task, TIF_SVE_VL_INHERIT,
+	update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
 			       flags & PR_SVE_VL_INHERIT);
 
 	return 0;
 }
 
 /*
  * Encode the current vector length and flags for return.
- * This is only required for prctl(): ptrace has separate fields
+ * This is only required for prctl(): ptrace has separate fields.
+ * SVE and SME use the same bits for _ONEXEC and _INHERIT.
  *
- * flags are as for sve_set_vector_length().
+ * flags are as for vec_set_vector_length().
  */
-static int sve_prctl_status(unsigned long flags)
+static int vec_prctl_status(enum vec_type type, unsigned long flags)
 {
 	int ret;
 
 	if (flags & PR_SVE_SET_VL_ONEXEC)
-		ret = task_get_sve_vl_onexec(current);
+		ret = task_get_vl_onexec(current, type);
 	else
-		ret = task_get_sve_vl(current);
+		ret = task_get_vl(current, type);
 
-	if (test_thread_flag(TIF_SVE_VL_INHERIT))
+	if (test_thread_flag(vec_vl_inherit_flag(type)))
 		ret |= PR_SVE_VL_INHERIT;
 
 	return ret;
@@ -732,11 +735,11 @@ int sve_set_current_vl(unsigned long arg)
 	if (!system_supports_sve() || is_compat_task())
 		return -EINVAL;
 
-	ret = sve_set_vector_length(current, vl, flags);
+	ret = vec_set_vector_length(current, ARM64_VEC_SVE, vl, flags);
 	if (ret)
 		return ret;
 
-	return sve_prctl_status(flags);
+	return vec_prctl_status(ARM64_VEC_SVE, flags);
 }
 
 /* PR_SVE_GET_VL */
@@ -745,7 +748,7 @@ int sve_get_current_vl(void)
 	if (!system_supports_sve() || is_compat_task())
 		return -EINVAL;
 
-	return sve_prctl_status(0);
+	return vec_prctl_status(ARM64_VEC_SVE, 0);
 }
 
 static void vec_probe_vqs(struct vl_info *info,

arch/arm64/kernel/ptrace.c

@@ -812,9 +812,9 @@ static int sve_set(struct task_struct *target,
 
 	/*
 	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
-	 * sve_set_vector_length(), which will also validate them for us:
+	 * vec_set_vector_length(), which will also validate them for us:
 	 */
-	ret = sve_set_vector_length(target, header.vl,
+	ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl,
 		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
 	if (ret)
 		goto out;

arch/arm64/kvm/reset.c

@@ -52,10 +52,10 @@ int kvm_arm_init_sve(void)
 		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
 		 * to be extended with multiple register slice support in
 		 * order to support vector lengths greater than
-		 * SVE_VL_ARCH_MAX:
+		 * VL_ARCH_MAX:
 		 */
-		if (WARN_ON(kvm_sve_max_vl > SVE_VL_ARCH_MAX))
-			kvm_sve_max_vl = SVE_VL_ARCH_MAX;
+		if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX))
+			kvm_sve_max_vl = VL_ARCH_MAX;
 
 		/*
 		 * Don't even try to make use of vector lengths that
@@ -103,7 +103,7 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
 	 * set_sve_vls().  Double-check here just to be sure:
 	 */
 	if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() ||
-		    vl > SVE_VL_ARCH_MAX))
+		    vl > VL_ARCH_MAX))
 		return -EIO;
 
 	buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL_ACCOUNT);