@@ -170,8 +170,8 @@ static inline void riscv_v_vstate_discard(struct pt_regs *regs)
if ((regs->status & SR_VS) == SR_VS_OFF)
return;
- __riscv_v_vstate_discard();
- __riscv_v_vstate_dirty(regs);
+ set_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
+ riscv_v_vstate_on(regs);
}
static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
@@ -186,7 +186,9 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
struct pt_regs *regs)
{
- if ((regs->status & SR_VS) != SR_VS_OFF) {
+ if ((regs->status & SR_VS) == SR_VS_INITIAL) {
+ __riscv_v_vstate_discard();
+ } else if ((regs->status & SR_VS) != SR_VS_OFF) {
__riscv_v_vstate_restore(vstate, vstate->datap);
__riscv_v_vstate_clean(regs);
}
@@ -197,7 +199,7 @@ static inline void riscv_v_vstate_set_restore(struct task_struct *task,
{
if ((regs->status & SR_VS) != SR_VS_OFF) {
set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
- riscv_v_vstate_on(regs);
+ __riscv_v_vstate_clean(regs);
}
}
The purpose of riscv_v_vstate_discard() is to invalidate v context at entries of syscalls. So users happen to use v after a syscall without re-configuring would see a failure. It was achieved by setting vector registers and CSRs to -1 and marking the context busy. However, this results in redundant saving of v-context if the process is scheduled out in a syscall. Moreover, restoring the invalidated context from memory is a costly operation. In fact, all can be prevented if we can delay vstate_discard before returning back to the user space. To be more specific, the kernel can mark v-context as INITIAL and set the restore flag at syscall entries. This is the indication for the vstate_restore, so it awares that the vstate has to be invalidated before returning back to the user space. After applying this patch, the context switch performance has improved 6.78% on vector enabled lmbench running on a FPGA with VLEN=512. The result was obtained by averaging the output from the following command. $ lat_ctx 2 Before the patch: 599.8357692 After the patch: 559.1748148 Signed-off-by: Andy Chiu <andy.chiu@sifive.com> --- arch/riscv/include/asm/vector.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) --- base-commit: 60a6707f582ebbdfb6b378f45d7bf929106a1cd5 change-id: 20240628-dev-vstate_discard-5784652968a3 Best regards,