Re: [RFC PATCH v8 21/21] riscv: Turn has_vector into a static key if VECTOR=y

From: Jisheng Zhang
Date: Wed Sep 15 2021 - 10:31:34 EST

On Thu, 9 Sep 2021 01:45:33 +0800
Greentime Hu <greentime.hu@xxxxxxxxxx> wrote:

> Just like fpu, we can use static key for has_vector.
> The has_vector check sits at hot code path: switch_to(). Currently,
> has_vector is a bool variable if VECTOR=y, switch_to() checks it each time,
> we can optimize out this check by turning the has_vector into a static key.
>

has_vector is newly introduced in this patch set so I believe this patch can
be folded into has_vector introducing patch, I.E patch 6


> Signed-off-by: Greentime Hu <greentime.hu@xxxxxxxxxx>
> ---
> arch/riscv/include/asm/switch_to.h | 10 +++++++---
> arch/riscv/kernel/cpufeature.c | 4 ++--
> arch/riscv/kernel/kernel_mode_vector.c | 4 ++--
> arch/riscv/kernel/process.c | 8 ++++----
> arch/riscv/kernel/signal.c | 6 +++---
> 5 files changed, 18 insertions(+), 14 deletions(-)
>
> diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
> index b48c9c974564..576204217e0f 100644
> --- a/arch/riscv/include/asm/switch_to.h
> +++ b/arch/riscv/include/asm/switch_to.h
> @@ -71,7 +71,11 @@ static __always_inline bool has_fpu(void) { return false; }
> #endif
>
> #ifdef CONFIG_VECTOR
> -extern bool has_vector;
> +extern struct static_key_false cpu_hwcap_vector;
> +static __always_inline bool has_vector(void)
> +{
> + return static_branch_likely(&cpu_hwcap_vector);
> +}
> extern unsigned long riscv_vsize;
> extern void __vstate_save(struct __riscv_v_state *save_to, void *datap);
> extern void __vstate_restore(struct __riscv_v_state *restore_from, void *datap);
> @@ -120,7 +124,7 @@ static inline void __switch_to_vector(struct task_struct *prev,
> }
>
> #else
> -#define has_vector false
> +static __always_inline bool has_vector(void) { return false; }
> #define riscv_vsize (0)
> #define vstate_save(task, regs) do { } while (0)
> #define vstate_restore(task, regs) do { } while (0)
> @@ -136,7 +140,7 @@ do { \
> struct task_struct *__next = (next); \
> if (has_fpu()) \
> __switch_to_fpu(__prev, __next); \
> - if (has_vector) \
> + if (has_vector()) \
> __switch_to_vector(__prev, __next); \
> ((last) = __switch_to(__prev, __next)); \
> } while (0)
> diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
> index af984f875f60..0139ec20adce 100644
> --- a/arch/riscv/kernel/cpufeature.c
> +++ b/arch/riscv/kernel/cpufeature.c
> @@ -23,7 +23,7 @@ __ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu);
> #endif
> #ifdef CONFIG_VECTOR
> #include <asm/vector.h>
> -bool has_vector __read_mostly;
> +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_vector);
> unsigned long riscv_vsize __read_mostly;
> #endif
>
> @@ -157,7 +157,7 @@ void __init riscv_fill_hwcap(void)
>
> #ifdef CONFIG_VECTOR
> if (elf_hwcap & COMPAT_HWCAP_ISA_V) {
> - has_vector = true;
> + static_branch_enable(&cpu_hwcap_vector);
> /* There are 32 vector registers with vlenb length. */
> rvv_enable();
> riscv_vsize = csr_read(CSR_VLENB) * 32;
> diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
> index 0d990bd8b8dd..0d08954c30af 100644
> --- a/arch/riscv/kernel/kernel_mode_vector.c
> +++ b/arch/riscv/kernel/kernel_mode_vector.c
> @@ -110,7 +110,7 @@ static void vector_flush_cpu_state(void)
> */
> void kernel_rvv_begin(void)
> {
> - if (WARN_ON(!has_vector))
> + if (WARN_ON(!has_vector()))
> return;
>
> WARN_ON(!may_use_vector());
> @@ -140,7 +140,7 @@ EXPORT_SYMBOL(kernel_rvv_begin);
> */
> void kernel_rvv_end(void)
> {
> - if (WARN_ON(!has_vector))
> + if (WARN_ON(!has_vector()))
> return;
>
> /* Invalidate vector regs */
> diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
> index 05ff5f934e7e..62540815ba1c 100644
> --- a/arch/riscv/kernel/process.c
> +++ b/arch/riscv/kernel/process.c
> @@ -96,7 +96,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
> fstate_restore(current, regs);
> }
>
> - if (has_vector) {
> + if (has_vector()) {
> struct __riscv_v_state *vstate = &(current->thread.vstate);
>
> /* Enable vector and allocate memory for vector registers. */
> @@ -141,11 +141,11 @@ void flush_thread(void)
> int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
> {
> fstate_save(src, task_pt_regs(src));
> - if (has_vector)
> + if (has_vector())
> /* To make sure every dirty vector context is saved. */
> vstate_save(src, task_pt_regs(src));
> *dst = *src;
> - if (has_vector) {
> + if (has_vector()) {
> /* Copy vector context to the forked task from parent. */
> if ((task_pt_regs(src)->status & SR_VS) != SR_VS_OFF) {
> dst->thread.vstate.datap = kzalloc(riscv_vsize, GFP_KERNEL);
> @@ -164,7 +164,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
> void arch_release_task_struct(struct task_struct *tsk)
> {
> /* Free the vector context of datap. */
> - if (has_vector)
> + if (has_vector())
> kfree(tsk->thread.vstate.datap);
> }
>
> diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
> index d30a3b588156..6a19b4b7b206 100644
> --- a/arch/riscv/kernel/signal.c
> +++ b/arch/riscv/kernel/signal.c
> @@ -192,7 +192,7 @@ static long restore_sigcontext(struct pt_regs *regs,
> goto invalid;
> goto done;
> case RVV_MAGIC:
> - if (!has_vector)
> + if (!has_vector())
> goto invalid;
> if (size != rvv_sc_size)
> goto invalid;
> @@ -221,7 +221,7 @@ static size_t cal_rt_frame_size(void)
>
> frame_size = sizeof(*frame);
>
> - if (has_vector)
> + if (has_vector())
> total_context_size += rvv_sc_size;
> /* Preserved a __riscv_ctx_hdr for END signal context header. */
> total_context_size += sizeof(struct __riscv_ctx_hdr);
> @@ -288,7 +288,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
> if (has_fpu())
> err |= save_fp_state(regs, &sc->sc_fpregs);
> /* Save the vector state. */
> - if (has_vector)
> + if (has_vector())
> err |= save_v_state(regs, &sc_reserved_free_ptr);
>
> /* Put END __riscv_ctx_hdr at the end. */