[-next,v16,09/20] riscv: Add task switch support for vector

Commit Message

Andy Chiu March 23, 2023, 2:59 p.m. UTC

From: Greentime Hu <[e-mail]>

This patch adds task switch support for vector. It also supports all
lengths of vlen.

Suggested-by: Andrew Waterman <[e-mail]>
Co-developed-by: Nick Knight <[e-mail]>
Signed-off-by: Nick Knight <[e-mail]>
Co-developed-by: Guo Ren <[e-mail]>
Signed-off-by: Guo Ren <[e-mail]>
Co-developed-by: Vincent Chen <[e-mail]>
Signed-off-by: Vincent Chen <[e-mail]>
Co-developed-by: Ruinland Tsai <[e-mail]>
Signed-off-by: Ruinland Tsai <[e-mail]>
Signed-off-by: Greentime Hu <[e-mail]>
Signed-off-by: Vineet Gupta <[e-mail]>
Signed-off-by: Andy Chiu <[e-mail]>
Reviewed-by: Conor Dooley <[e-mail]>
Reviewed-by: Björn Töpel <[e-mail]>
---
 arch/riscv/include/asm/processor.h   |  1 +
 arch/riscv/include/asm/switch_to.h   |  3 +++
 arch/riscv/include/asm/thread_info.h |  3 +++
 arch/riscv/include/asm/vector.h      | 38 ++++++++++++++++++++++++++++
 arch/riscv/kernel/process.c          | 18 +++++++++++++
 5 files changed, 63 insertions(+)

Patch

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 94a0590c6971..f0ddf691ac5e 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -39,6 +39,7 @@  struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
+	struct __riscv_v_ext_state vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 4b96b13dee27..a727be723c56 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -8,6 +8,7 @@ 
 
 #include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
+#include <asm/vector.h>
 #include <asm/hwcap.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
@@ -78,6 +79,8 @@  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/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index f704c8dd57e0..9e28c0199030 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -80,6 +80,9 @@  struct thread_info {
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
+void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index cb60637443be..4161352d6ea8 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -11,6 +11,9 @@ 
 #ifdef CONFIG_RISCV_ISA_V
 
 #include <linux/stringify.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm/ptrace.h>
 #include <asm/hwcap.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
@@ -123,6 +126,38 @@  static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 	riscv_v_disable();
 }
 
+static inline void riscv_v_vstate_save(struct task_struct *task,
+				       struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
+		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
+
+		__riscv_v_vstate_save(vstate, vstate->datap);
+		__riscv_v_vstate_clean(regs);
+	}
+}
+
+static inline void riscv_v_vstate_restore(struct task_struct *task,
+					  struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) != SR_VS_OFF) {
+		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
+
+		__riscv_v_vstate_restore(vstate, vstate->datap);
+		__riscv_v_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);
+	riscv_v_vstate_save(prev, regs);
+	riscv_v_vstate_restore(next, task_pt_regs(next));
+}
+
 #else /* ! CONFIG_RISCV_ISA_V  */
 
 struct pt_regs;
@@ -131,6 +166,9 @@  static __always_inline bool has_vector(void) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 #define riscv_v_vsize (0)
 #define riscv_v_setup_vsize()			do {} while (0)
+#define riscv_v_vstate_save(task, regs)		do {} while (0)
+#define riscv_v_vstate_restore(task, regs)	do {} while (0)
+#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)
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 774ffde386ab..44ca0be58ce7 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -24,6 +24,7 @@ 
 #include <asm/switch_to.h>
 #include <asm/thread_info.h>
 #include <asm/cpuidle.h>
+#include <asm/vector.h>
 
 register unsigned long gp_in_global __asm__("gp");
 
@@ -147,12 +148,28 @@  void flush_thread(void)
 	fstate_off(current, task_pt_regs(current));
 	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
 #endif
+#ifdef CONFIG_RISCV_ISA_V
+	/* Reset vector state */
+	riscv_v_vstate_off(task_pt_regs(current));
+	kfree(current->thread.vstate.datap);
+	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+#endif
+}
+
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	/* Free the vector context of datap. */
+	if (has_vector())
+		kfree(tsk->thread.vstate.datap);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	fstate_save(src, task_pt_regs(src));
 	*dst = *src;
+	/* clear entire V context, including datap for a new task */
+	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+
 	return 0;
 }
 
@@ -185,6 +202,7 @@  int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.ra = (unsigned long)ret_from_fork;
 	}
+	riscv_v_vstate_off(childregs);
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }