[PATCH v12 08/17] riscv: Add task switch support for vector

From: Chris Stillson
Date: Wed Sep 21 2022 - 17:50:09 EST


From: Greentime Hu <greentime.hu@xxxxxxxxxx>

This patch adds task switch support for vector. It supports partial lazy
save and restore mechanism. It also supports all lengths of vlen.

[guoren@xxxxxxxxxxxxxxxxx: First available porting to support vector
context switching]
[nick.knight@xxxxxxxxxx: Rewrite vector.S to support dynamic vlen, xlen and
code refine]
[vincent.chen@xxxxxxxxxx: Fix the might_sleep issue in vstate_save,
vstate_restore]
[andrew@xxxxxxxxxx: Optimize task switch codes of vector]
[ruinland.tsai@xxxxxxxxxx: Fix the arch_release_task_struct free wrong
datap issue]

Suggested-by: Andrew Waterman <andrew@xxxxxxxxxx>
Co-developed-by: Nick Knight <nick.knight@xxxxxxxxxx>
Signed-off-by: Nick Knight <nick.knight@xxxxxxxxxx>
Co-developed-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Co-developed-by: Vincent Chen <vincent.chen@xxxxxxxxxx>
Signed-off-by: Vincent Chen <vincent.chen@xxxxxxxxxx>
Co-developed-by: Ruinland Tsai <ruinland.tsai@xxxxxxxxxx>
Signed-off-by: Ruinland Tsai <ruinland.tsai@xxxxxxxxxx>
Signed-off-by: Greentime Hu <greentime.hu@xxxxxxxxxx>
Reported-by: kernel test robot <lkp@xxxxxxxxx>
Reported-by: kernel test robot <lkp@xxxxxxxxx>
---
arch/riscv/include/asm/switch_to.h | 66 ++++++++++++++++++++++++++++++
arch/riscv/kernel/Makefile | 1 +
arch/riscv/kernel/process.c | 43 +++++++++++++++++++
3 files changed, 110 insertions(+)

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index df1aa589b7fd..527951c033d4 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -7,11 +7,13 @@
#define _ASM_RISCV_SWITCH_TO_H

#include <linux/jump_label.h>
+#include <linux/slab.h>
#include <linux/sched/task_stack.h>
#include <asm/hwcap.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/csr.h>
+#include <asm/asm-offsets.h>

#ifdef CONFIG_FPU
extern void __fstate_save(struct task_struct *save_to);
@@ -68,6 +70,68 @@ static __always_inline bool has_fpu(void) { return false; }
#define __switch_to_fpu(__prev, __next) do { } while (0)
#endif

+#ifdef CONFIG_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);
+
+static inline void __vstate_clean(struct pt_regs *regs)
+{
+ regs->status = (regs->status & ~(SR_VS)) | SR_VS_CLEAN;
+}
+
+static inline void vstate_off(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+}
+
+static inline void vstate_save(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->status & SR_VS) == SR_VS_DIRTY) {
+ struct __riscv_v_state *vstate = &(task->thread.vstate);
+
+ __vstate_save(vstate, vstate->datap);
+ __vstate_clean(regs);
+ }
+}
+
+static inline void vstate_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if ((regs->status & SR_VS) != SR_VS_OFF) {
+ struct __riscv_v_state *vstate = &(task->thread.vstate);
+
+ __vstate_restore(vstate, vstate->datap);
+ __vstate_clean(regs);
+ }
+}
+
+static inline void __switch_to_vector(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct pt_regs *regs;
+
+ regs = task_pt_regs(prev);
+ if (unlikely(regs->status & SR_SD))
+ vstate_save(prev, regs);
+ vstate_restore(next, task_pt_regs(next));
+}
+
+#else
+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)
+#define __switch_to_vector(__prev, __next) do { } while (0)
+#endif
+
extern struct task_struct *__switch_to(struct task_struct *,
struct task_struct *);

@@ -77,6 +141,8 @@ do { \
struct task_struct *__next = (next); \
if (has_fpu()) \
__switch_to_fpu(__prev, __next); \
+ if (has_vector()) \
+ __switch_to_vector(__prev, __next); \
((last) = __switch_to(__prev, __next)); \
} while (0)

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 33bb60a354cd..35752fb6d145 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/

obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o
obj-$(CONFIG_FPU) += fpu.o
+obj-$(CONFIG_VECTOR) += vector.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SMP) += cpu_ops.o
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index ceb9ebab6558..e88a37fc77ed 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -124,6 +124,25 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
*/
fstate_restore(current, regs);
}
+
+ if (has_vector()) {
+ struct __riscv_v_state *vstate = &(current->thread.vstate);
+
+ /* Enable vector and allocate memory for vector registers. */
+ if (!vstate->datap) {
+ vstate->datap = kzalloc(riscv_vsize, GFP_KERNEL);
+ if (WARN_ON(!vstate->datap))
+ return;
+ }
+ regs->status |= SR_VS_INITIAL;
+
+ /*
+ * Restore the initial value to the vector register
+ * before starting the user program.
+ */
+ vstate_restore(current, regs);
+ }
+
regs->epc = pc;
regs->sp = sp;

@@ -148,15 +167,29 @@ void flush_thread(void)
fstate_off(current, task_pt_regs(current));
memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
#endif
+#ifdef CONFIG_VECTOR
+ /* Reset vector state */
+ vstate_off(current, task_pt_regs(current));
+ memset(&current->thread.vstate, 0, RISCV_V_STATE_DATAP);
+#endif
}

int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
fstate_save(src, task_pt_regs(src));
*dst = *src;
+ dst->thread.vstate.datap = NULL;
+
return 0;
}

+void arch_release_task_struct(struct task_struct *tsk)
+{
+ /* Free the vector context of datap. */
+ if (has_vector() && tsk->thread.vstate.datap)
+ kfree(tsk->thread.vstate.datap);
+}
+
int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
{
unsigned long clone_flags = args->flags;
@@ -175,7 +208,17 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
p->thread.ra = (unsigned long)ret_from_kernel_thread;
p->thread.s[0] = (unsigned long)args->fn;
p->thread.s[1] = (unsigned long)args->fn_arg;
+ p->thread.vstate.datap = NULL;
} else {
+ /* Allocate the datap for the user process if datap is NULL */
+ if (has_vector() && !p->thread.vstate.datap) {
+ void *datap = kzalloc(riscv_vsize, GFP_KERNEL);
+ /* Failed to allocate memory. */
+ if (!datap)
+ return -ENOMEM;
+ p->thread.vstate.datap = datap;
+ memset(&p->thread.vstate, 0, RISCV_V_STATE_DATAP);
+ }
*childregs = *(current_pt_regs());
if (usp) /* User fork */
childregs->sp = usp;
--
2.25.1