@@ -26,6 +26,8 @@ void kernel_vector_begin(void);
void kernel_vector_end(void);
void get_cpu_vector_context(void);
void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
static inline u32 riscv_v_flags(void)
{
@@ -227,6 +229,8 @@ static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
#define __switch_to_vector(__prev, __next) do {} while (0)
#define riscv_v_vstate_off(regs) do {} while (0)
#define riscv_v_vstate_on(regs) do {} while (0)
+#define riscv_v_thread_free(tsk) do {} while (0)
+#define riscv_v_setup_ctx_cache() do {} while (0)
#endif /* CONFIG_RISCV_ISA_V */
@@ -179,7 +179,7 @@ void arch_release_task_struct(struct task_struct *tsk)
{
/* Free the vector context of datap. */
if (has_vector())
- kfree(tsk->thread.vstate.datap);
+ riscv_v_thread_free(tsk);
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -228,3 +228,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
p->thread.sp = (unsigned long)childregs; /* kernel sp */
return 0;
}
+
+void __init arch_task_cache_init(void)
+{
+ riscv_v_setup_ctx_cache();
+}
@@ -21,6 +21,7 @@
#include <asm/bug.h>
static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
unsigned long riscv_v_vsize __read_mostly;
EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +48,13 @@ int riscv_v_setup_vsize(void)
return 0;
}
+void __init riscv_v_setup_ctx_cache(void)
+{
+ riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+ riscv_v_vsize, 16, SLAB_PANIC,
+ 0, riscv_v_vsize, NULL);
+}
+
static bool insn_is_vector(u32 insn_buf)
{
u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -84,7 +92,7 @@ static int riscv_v_thread_zalloc(void)
{
void *datap;
- datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+ datap = kmem_cache_zalloc(riscv_v_user_cachep, GFP_KERNEL);
if (!datap)
return -ENOMEM;
@@ -94,6 +102,12 @@ static int riscv_v_thread_zalloc(void)
return 0;
}
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+ if (tsk->thread.vstate.datap)
+ kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+}
+
#define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
#define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
#define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
The allocation size of thread.vstate.datap is always riscv_v_vsize. So it is possbile to use kmem_cache_* to manage the allocation. This gives users more information regarding allocation of vector context via /proc/slabinfo. And it potentially reduces the latency of the first-use trap because of the allocation caches. Signed-off-by: Andy Chiu <andy.chiu@sifive.com> --- Changelog v6: - new patch since v6 --- arch/riscv/include/asm/vector.h | 4 ++++ arch/riscv/kernel/process.c | 7 ++++++- arch/riscv/kernel/vector.c | 16 +++++++++++++++- 3 files changed, 25 insertions(+), 2 deletions(-)