1 files changed, 12 insertions, 25 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 520b681a07bb..91e44ac7150f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -679,7 +679,7 @@ static void fpsimd_to_sve(struct task_struct *task)
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 
-	if (!system_supports_sve())
+	if (!system_supports_sve() && !system_supports_sme())
 		return;
 
 	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -705,7 +705,7 @@ static void sve_to_fpsimd(struct task_struct *task)
 	unsigned int i;
 	__uint128_t const *p;
 
-	if (!system_supports_sve())
+	if (!system_supports_sve() && !system_supports_sme())
 		return;
 
 	vl = thread_get_cur_vl(&task->thread);
@@ -835,7 +835,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	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))
+	if (!test_tsk_thread_flag(task, TIF_SVE) &&
+	    !thread_sm_enabled(&task->thread))
 		return;
 
 	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -909,7 +910,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 			 */
 			task->thread.svcr &= ~(SVCR_SM_MASK |
 					       SVCR_ZA_MASK);
-			clear_thread_flag(TIF_SME);
+			clear_tsk_thread_flag(task, TIF_SME);
 			free_sme = true;
 		}
 	}
@@ -1178,9 +1179,6 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_zcr_features(void)
 {
-	u64 zcr;
-	unsigned int vq_max;
-
 	/*
 	 * Set the maximum possible VL, and write zeroes to all other
 	 * bits to see if they stick.
@@ -1188,12 +1186,8 @@ u64 read_zcr_features(void)
 	sve_kernel_enable(NULL);
 	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
 
-	zcr = read_sysreg_s(SYS_ZCR_EL1);
-	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
-	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return zcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sve_get_vl()) - 1;
 }
 
 void __init sve_setup(void)
@@ -1284,9 +1278,9 @@ void fpsimd_release_task(struct task_struct *dead_task)
  * the interest of testability and predictability, the architecture
  * guarantees that when ZA is enabled it will be zeroed.
  */
-void sme_alloc(struct task_struct *task)
+void sme_alloc(struct task_struct *task, bool flush)
 {
-	if (task->thread.sme_state) {
+	if (task->thread.sme_state && flush) {
 		memset(task->thread.sme_state, 0, sme_state_size(task));
 		return;
 	}
@@ -1348,9 +1342,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_smcr_features(void)
 {
-	u64 smcr;
-	unsigned int vq_max;
-
 	sme_kernel_enable(NULL);
 
 	/*
@@ -1359,12 +1350,8 @@ u64 read_smcr_features(void)
 	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
 		       SYS_SMCR_EL1);
 
-	smcr = read_sysreg_s(SYS_SMCR_EL1);
-	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
-	vq_max = sve_vq_from_vl(sme_get_vl());
-	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return smcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sme_get_vl()) - 1;
 }
 
 void __init sme_setup(void)
@@ -1514,7 +1501,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 	}
 
 	sve_alloc(current, false);
-	sme_alloc(current);
+	sme_alloc(current, true);
 	if (!current->thread.sve_state || !current->thread.sme_state) {
 		force_sig(SIGKILL);
 		return;