riscv: Add task switch support for vector

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

[guoren@linux.alibaba.com: First available porting to support vector
context switching]
[nick.knight@sifive.com: Rewrite vector.S to support dynamic vlen, xlen and
code refine]
[vincent.chen@sifive.com: Fix the might_sleep issue in vstate_save,
vstate_restore]
[andrew@sifive.com: Optimize task switch codes of vector]

Suggested-by: Andrew Waterman <andrew@sifive.com>
Co-developed-by: Nick Knight <nick.knight@sifive.com>
Signed-off-by: Nick Knight <nick.knight@sifive.com>
Co-developed-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Co-developed-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>

arch/riscv/include/asm/switch_to.h

@@ -7,10 +7,12 @@
 #define _ASM_RISCV_SWITCH_TO_H
 
 #include <linux/jump_label.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);
@@ -68,6 +70,67 @@ 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 +140,8 @@ 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)
 

arch/riscv/kernel/Makefile

@@ -40,6 +40,7 @@ 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

arch/riscv/kernel/process.c

@@ -95,6 +95,25 @@ 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;
 }
@@ -110,15 +129,45 @@ 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 and keep datap pointer. */
+	vstate_off(current, task_pt_regs(current));
+	memset(&current->thread.vstate, 0, RISCV_V_STATE_DATAP);
+	if (current->thread.vstate.datap)
+		memset(current->thread.vstate.datap, 0, riscv_vsize);
+#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) {
+			dst->thread.vstate.datap = kzalloc(riscv_vsize, 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, riscv_vsize);
+		}
+	}
+
 	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)
 {

arch/riscv/kernel/vector.S

@@ -0,0 +1,81 @@
+/* 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 status   t5
+
+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
+	vsetvli incr, x0, 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
+
+	vsetvli incr, x0, 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)