riscv: sched: defer restoring Vector context for user

User will use its Vector registers only after the kernel really returns
to the userspace. So we can delay restoring Vector registers as long as
we are still running in kernel mode. So, add a thread flag to indicates
the need of restoring Vector and do the restore at the last
arch-specific exit-to-user hook. This save the context restoring cost
when we switch over multiple processes that run V in kernel mode. For
example, if the kernel performs a context swicth from A->B->C, and
returns to C's userspace, then there is no need to restore B's
V-register.

Besides, this also prevents us from repeatedly restoring V context when
executing kernel-mode Vector multiple times.

The cost of this is that we must disable preemption and mark vector as
busy during vstate_{save,restore}. Because then the V context will not
get restored back immediately when a trap-causing context switch happens
in the middle of vstate_{save,restore}.

Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240115055929.4736-5-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

5 files changed, 12 insertions, 4 deletions

diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 2fc145edae3d..8422c881f452 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -117,7 +117,7 @@ void kernel_vector_end(void)
 	if (WARN_ON(!has_vector()))
 		return;
 
-	riscv_v_vstate_restore(current, task_pt_regs(current));
+	riscv_v_vstate_set_restore(current, task_pt_regs(current));
 
 	riscv_v_disable();
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4a1275db1146..36993f408de4 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -171,6 +171,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 }
 
@@ -187,6 +188,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de16a..7b93bcbdf9fa 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
+	if (target == current) {
+		get_cpu_vector_context();
 		riscv_v_vstate_save(current, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b2608..aca4a12c8416 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,7 +86,10 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
+	get_cpu_vector_context();
 	riscv_v_vstate_save(current, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
@@ -134,7 +137,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	if (unlikely(err))
 		return err;
 
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 
 	return err;
 }
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b6292487e..66e8c6ab09d2 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -167,7 +167,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }