[RFC PATCH v2 21/41] arm64/sve: Enable SVE on demand for userspace

[Dave Martin]

This patch tracks whether a task has ever attempted to use the
Scalable Vector Extension.  If and only if SVE is in use by a task,
it will be enabled for userspace when scheduling the task in.  For
other tasks, SVE is disabled when scheduling in.

Signed-off-by: Dave Martin <Dave.Martin at arm.com>
---
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/kernel/entry.S            | 18 +++++++++++++++++-
 arch/arm64/kernel/fpsimd.c           | 28 ++++++++++++++++++++++++++++
 3 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 46c3b93..272c32d 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -91,6 +91,7 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
 #define TIF_SECCOMP		11
+#define TIF_SVE			17	/* Scalable Vector Extension in use */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 43512d4..a9ae051 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -524,6 +524,10 @@ el0_sync:
 	b.eq	el0_ia
 	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
 	b.eq	el0_fpsimd_acc
+#ifdef CONFIG_ARM64_SVE
+	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
+	b.eq	el0_sve_acc
+#endif
 	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
 	b.eq	el0_fpsimd_exc
 	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
@@ -622,9 +626,21 @@ el0_fpsimd_acc:
 	mov	x1, sp
 	bl	do_fpsimd_acc
 	b	ret_to_user
+#ifdef CONFIG_ARM64_SVE
+	/*
+	 * Scalable Vector Extension access
+	 */
+el0_sve_acc:
+	enable_dbg
+	ct_user_exit
+	mov	x0, x25
+	mov	x1, sp
+	bl	do_sve_acc
+	b	ret_to_user
+#endif
 el0_fpsimd_exc:
 	/*
-	 * Floating Point or Advanced SIMD exception
+	 * Floating Point, Advanced SIMD or SVE exception
 	 */
 	enable_dbg
 	ct_user_exit
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index f3006a6..749f4f0 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -149,6 +149,18 @@ static void sve_to_fpsimd(struct task_struct *task)
 	__sve_to_fpsimd(task, sve_vq_from_vl(vl));
 }
 
+void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+{
+	unsigned long tmp;
+
+	if (test_and_set_thread_flag(TIF_SVE))
+		BUG();
+
+	asm ("mrs %0, cpacr_el1" : "=r" (tmp));
+	asm volatile ("msr cpacr_el1, %0" :: "r" (tmp | (1 << 17)));
+	/* Serialised by exception return to user */
+}
+
 #else /* ! CONFIG_ARM64_SVE */
 
 /* Dummy declarations for usage protected with IS_ENABLED(CONFIG_ARM64_SVE): */
@@ -306,11 +318,27 @@ void fpsimd_restore_current_state(void)
 		return;
 	preempt_disable();
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		unsigned long tmp;
+		unsigned long flags;
+
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
 
 		task_fpsimd_load(current);
 		this_cpu_write(fpsimd_last_state, st);
 		st->cpu = smp_processor_id();
+
+		if (IS_ENABLED(CONFIG_ARM64_SVE)) {
+			/*
+			 * Flip SVE enable for userspace if it doesn't
+			 * match the current_task.
+			 */
+			asm ("mrs %0, cpacr_el1" : "=r" (tmp));
+			flags = current_thread_info()->flags;
+			if ((tmp ^ (unsigned long)flags) & (1 << 17)) {
+				tmp ^= 1 << 17;
+				asm volatile ("msr cpacr_el1, %0" :: "r" (tmp));
+			}
+		}
 	}
 	preempt_enable();
 }
-- 
2.1.4