[RFC PATCH v7 09/21] riscv: Add task switch support for vector

From: Greentime Hu
Date: Thu Sep 10 2020 - 04:18:53 EST

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@xxxxxxxxx: Fix the might_sleep issue in vstate_save,
vstate_restore]
Signed-off-by: Nick Knight <nick.knight@xxxxxxxxxx>
Signed-off-by: Greentime Hu <greentime.hu@xxxxxxxxxx>
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Signed-off-by: Vincent Chen <vincent.chen@xxxxxxxxxx>
---
arch/riscv/include/asm/switch_to.h | 65 +++++++++++++++++++++++
arch/riscv/kernel/Makefile | 1 +
arch/riscv/kernel/process.c | 40 ++++++++++++++
arch/riscv/kernel/vector.S | 84 ++++++++++++++++++++++++++++++
4 files changed, 190 insertions(+)
create mode 100644 arch/riscv/kernel/vector.S

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index b9234e7178d0..2afd0124701a 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -6,10 +6,12 @@
#ifndef _ASM_RISCV_SWITCH_TO_H
#define _ASM_RISCV_SWITCH_TO_H

+#include <linux/slab.h>
#include <linux/sched/task_stack.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);
@@ -63,6 +65,67 @@ extern bool has_fpu;
#define __switch_to_fpu(__prev, __next) do { } while (0)
#endif

+#ifdef CONFIG_VECTOR
+extern bool has_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);
+
+ /* Allocate space for vector registers. */
+ if (!vstate->datap) {
+ vstate->datap = kzalloc(riscv_vsize, GFP_ATOMIC);
+ vstate->size = riscv_vsize;
+ }
+ __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
+#define has_vector false
+#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 *);

@@ -72,6 +135,8 @@ 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 dc93710f0b2f..3a166c21ea49 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -33,6 +33,7 @@ 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 2b97c493427c..fb485c9bceee 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -82,6 +82,16 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
*/
fstate_restore(current, regs);
}
+
+ if (has_vector) {
+ 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;
set_fs(USER_DS);
@@ -98,15 +108,45 @@ 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, sizeof(current->thread.vstate));
+#endif
}

int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
fstate_save(src, task_pt_regs(src));
+ if (has_vector)
+ /* To make sure every dirty vector context is saved. */
+ vstate_save(src, task_pt_regs(src));
*dst = *src;
+ if (has_vector) {
+ /* Copy vector context to the forked task from parent. */
+ if ((task_pt_regs(src)->status & SR_VS) != SR_VS_OFF) {
+ unsigned long size = src->thread.vstate.size;
+
+ dst->thread.vstate.datap = kzalloc(size, GFP_KERNEL);
+ /* Failed to allocate memory. */
+ if (!dst->thread.vstate.datap)
+ return -ENOMEM;
+ /* Copy the src vector context to dst. */
+ memcpy(dst->thread.vstate.datap,
+ src->thread.vstate.datap, size);
+ }
+ }
+
return 0;
}

+void arch_release_task_struct(struct task_struct *tsk)
+{
+ /* Free the vector context of datap. */
+ if (has_vector)
+ kfree(tsk->thread.vstate.datap);
+}
+
int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
struct task_struct *p, unsigned long tls)
{
diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S
new file mode 100644
index 000000000000..4c880b1c32aa
--- /dev/null
+++ b/arch/riscv/kernel/vector.S
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2019 Alibaba Group Holding Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/asm-offsets.h>
+
+#define vstatep a0
+#define datap a1
+#define x_vstart t0
+#define x_vtype t1
+#define x_vl t2
+#define x_vcsr t3
+#define incr t4
+#define m_one t5
+#define status t6
+
+ENTRY(__vstate_save)
+ li status, SR_VS
+ csrs sstatus, status
+
+ csrr x_vstart, CSR_VSTART
+ csrr x_vtype, CSR_VTYPE
+ csrr x_vl, CSR_VL
+ csrr x_vcsr, CSR_VCSR
+ li m_one, -1
+ vsetvli incr, m_one, e8, m8
+ vse8.v v0, (datap)
+ add datap, datap, incr
+ vse8.v v8, (datap)
+ add datap, datap, incr
+ vse8.v v16, (datap)
+ add datap, datap, incr
+ vse8.v v24, (datap)
+
+ REG_S x_vstart, RISCV_V_STATE_VSTART(vstatep)
+ REG_S x_vtype, RISCV_V_STATE_VTYPE(vstatep)
+ REG_S x_vl, RISCV_V_STATE_VL(vstatep)
+ REG_S x_vcsr, RISCV_V_STATE_VCSR(vstatep)
+
+ csrc sstatus, status
+ ret
+ENDPROC(__vstate_save)
+
+ENTRY(__vstate_restore)
+ li status, SR_VS
+ csrs sstatus, status
+
+ li m_one, -1
+ vsetvli incr, m_one, e8, m8
+ vle8.v v0, (datap)
+ add datap, datap, incr
+ vle8.v v8, (datap)
+ add datap, datap, incr
+ vle8.v v16, (datap)
+ add datap, datap, incr
+ vle8.v v24, (datap)
+
+ REG_L x_vstart, RISCV_V_STATE_VSTART(vstatep)
+ REG_L x_vtype, RISCV_V_STATE_VTYPE(vstatep)
+ REG_L x_vl, RISCV_V_STATE_VL(vstatep)
+ REG_L x_vcsr, RISCV_V_STATE_VCSR(vstatep)
+ vsetvl x0, x_vl, x_vtype
+ csrw CSR_VSTART, x_vstart
+ csrw CSR_VCSR, x_vcsr
+
+ csrc sstatus, status
+ ret
+ENDPROC(__vstate_restore)
--
2.28.0