[v6, 01/10] riscv: Add support for kernel mode vector

[Andy Chiu]

From: Greentime Hu <greentime.hu at sifive.com>

Add kernel_vector_begin() and kernel_vector_end() function declarations
and corresponding definitions in kernel_mode_vector.c

These are needed to wrap uses of vector in kernel mode.

Co-developed-by: Vincent Chen <vincent.chen at sifive.com>
Signed-off-by: Vincent Chen <vincent.chen at sifive.com>
Signed-off-by: Greentime Hu <greentime.hu at sifive.com>
Signed-off-by: Andy Chiu <andy.chiu at sifive.com>
---
Changelog v6:
 - Use 8 bits to track non-preemptible vector context to provide better
   WARN coverage.
Changelog v4:
 - Use kernel_v_flags and helpers to track vector context.
Changelog v3:
 - Reorder patch 1 to patch 3 to make use of
   {get,put}_cpu_vector_context later.
 - Export {get,put}_cpu_vector_context.
 - Save V context after disabling preemption. (Guo)
 - Fix a build fail. (Conor)
 - Remove irqs_disabled() check as it is not needed, fix styling. (Björn)
Changelog v2:
 - 's/kernel_rvv/kernel_vector' and return void in kernel_vector_begin
   (Conor)
 - export may_use_simd to include/asm/simd.h
---
 arch/riscv/include/asm/processor.h     | 17 ++++-
 arch/riscv/include/asm/simd.h          | 42 ++++++++++++
 arch/riscv/include/asm/vector.h        | 21 ++++++
 arch/riscv/kernel/Makefile             |  1 +
 arch/riscv/kernel/kernel_mode_vector.c | 95 ++++++++++++++++++++++++++
 arch/riscv/kernel/process.c            |  2 +-
 6 files changed, 176 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/include/asm/simd.h
 create mode 100644 arch/riscv/kernel/kernel_mode_vector.c

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda54..15781e2232e0 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -73,6 +73,20 @@
 struct task_struct;
 struct pt_regs;
 
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ *  - bit 0-7 indicates whether the in-kernel Vector context is active. The
+ *    activation of this state disables the preemption. On a non-RT kernel, it
+ *    also disable bh. Currently only 0 and 1 are valid value for this field.
+ *    Other values are reserved for future uses.
+ */
+
+#define RISCV_KERNEL_MODE_V_MASK	0xff
+
+#define RISCV_KERNEL_MODE_V	0x1
+
 /* CPU-specific state of a task */
 struct thread_struct {
 	/* Callee-saved registers */
@@ -81,7 +95,8 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
-	unsigned long vstate_ctrl;
+	u32 riscv_v_flags;
+	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
 };
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 000000000000..269752bfa2cc
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel at linaro.org>
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - whether it is allowable at this time to issue vector
+ *                instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	/*
+	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled.
+	 */
+	return !in_hardirq() && !in_nmi() && !(riscv_v_ctx_cnt() & RISCV_KERNEL_MODE_V_MASK);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+	return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 87aaef656257..6254830c0668 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -22,6 +22,27 @@
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+
+static inline void riscv_v_ctx_cnt_add(u32 offset)
+{
+	current->thread.riscv_v_flags += offset;
+	barrier();
+}
+
+static inline void riscv_v_ctx_cnt_sub(u32 offset)
+{
+	barrier();
+	current->thread.riscv_v_flags -= offset;
+}
+
+static inline u32 riscv_v_ctx_cnt(void)
+{
+	return READ_ONCE(current->thread.riscv_v_flags);
+}
 
 static __always_inline bool has_vector(void)
 {
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index fee22a3d1b53..8c58595696b3 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 000000000000..105147c7d2da
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas at arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel at linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/simd.h>
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+	preempt_disable();
+
+	WARN_ON((riscv_v_ctx_cnt() & RISCV_KERNEL_MODE_V_MASK) != 0);
+	riscv_v_ctx_cnt_add(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+	WARN_ON((riscv_v_ctx_cnt() & RISCV_KERNEL_MODE_V_MASK) != RISCV_KERNEL_MODE_V);
+	riscv_v_ctx_cnt_sub(RISCV_KERNEL_MODE_V);
+
+	preempt_enable();
+}
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	get_cpu_vector_context();
+
+	riscv_v_vstate_save(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_vstate_restore(current, task_pt_regs(current));
+
+	riscv_v_disable();
+
+	put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a129..5c4dcf518684 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -187,7 +187,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *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;
 }
 
@@ -221,6 +220,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
-- 
2.17.1