[PATCH -next v13 08/19] riscv: Introduce struct/helpers to save/restore per-task Vector state

[Andy Chiu <andy.chiu@sifive.com>]

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

Add vector state context struct to be added later in thread_struct. And
prepare low-level helper functions to save/restore vector contexts.

This include Vector Regfile and CSRs holding dynamic configuration state
(vstart, vl, vtype, vcsr). The Vec Register width could be implementation
defined, but same for all processes, so that is saved separately.

This is not yet wired into final thread_struct - will be done when
__switch_to actually starts doing this in later patches.

Given the variable (and potentially large) size of regfile, they are
saved in dynamically allocated memory, pointed to by datap pointer in
__riscv_v_state.

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>
Signed-off-by: Vineet Gupta <vineetg@rivosinc.com>
[vineetg: merged bits from 2 different patches]
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
[andy.chiu: use inline asm to save/restore context, remove asm vaiant]
---
 arch/riscv/include/asm/vector.h      | 84 ++++++++++++++++++++++++++++
 arch/riscv/include/uapi/asm/ptrace.h | 17 ++++++
 2 files changed, 101 insertions(+)

diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 16cb4a1c1230..842a859609b5 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -12,6 +12,9 @@
 
 #include <asm/hwcap.h>
 #include <asm/csr.h>
+#include <asm/asm.h>
+
+#define CSR_STR(x) __ASM_STR(x)
 
 extern unsigned long riscv_vsize;
 
@@ -20,6 +23,26 @@ static __always_inline bool has_vector(void)
 	return static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_VECTOR]);
 }
 
+static inline void __vstate_clean(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~(SR_VS)) | SR_VS_CLEAN;
+}
+
+static inline void vstate_off(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+}
+
+static inline void vstate_on(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~(SR_VS)) | SR_VS_INITIAL;
+}
+
+static inline bool vstate_query(struct pt_regs *regs)
+{
+	return (regs->status & SR_VS) != 0;
+}
+
 static __always_inline void rvv_enable(void)
 {
 	csr_set(CSR_SSTATUS, SR_VS);
@@ -30,10 +53,71 @@ static __always_inline void rvv_disable(void)
 	csr_clear(CSR_SSTATUS, SR_VS);
 }
 
+static __always_inline void __vstate_csr_save(struct __riscv_v_state *dest)
+{
+	asm volatile (
+		"csrr	%0, " CSR_STR(CSR_VSTART) "\n\t"
+		"csrr	%1, " CSR_STR(CSR_VTYPE) "\n\t"
+		"csrr	%2, " CSR_STR(CSR_VL) "\n\t"
+		"csrr	%3, " CSR_STR(CSR_VCSR) "\n\t"
+		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
+		  "=r" (dest->vcsr) : :);
+}
+
+static __always_inline void __vstate_csr_restore(struct __riscv_v_state *src)
+{
+	asm volatile (
+		"vsetvl	 x0, %2, %1\n\t"
+		"csrw	" CSR_STR(CSR_VSTART) ", %0\n\t"
+		"csrw	" CSR_STR(CSR_VCSR) ", %3\n\t"
+		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl),
+		    "r" (src->vcsr) :);
+}
+
+static inline void __vstate_save(struct __riscv_v_state *save_to, void *datap)
+{
+	rvv_enable();
+	__vstate_csr_save(save_to);
+	asm volatile (
+		"vsetvli	t4, x0, e8, m8, ta, ma\n\t"
+		"vse8.v		v0, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vse8.v		v8, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vse8.v		v16, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vse8.v		v24, (%0)\n\t"
+		: : "r" (datap) : "t4", "memory");
+	rvv_disable();
+}
+
+static inline void __vstate_restore(struct __riscv_v_state *restore_from,
+				    void *datap)
+{
+	rvv_enable();
+	asm volatile (
+		"vsetvli	t4, x0, e8, m8, ta, ma\n\t"
+		"vle8.v		v0, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vle8.v		v8, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vle8.v		v16, (%0)\n\t"
+		"add		%0, %0, t4\n\t"
+		"vle8.v		v24, (%0)\n\t"
+		: : "r" (datap) : "t4");
+	__vstate_csr_restore(restore_from);
+	rvv_disable();
+}
+
 #else /* ! CONFIG_RISCV_ISA_V  */
 
+struct pt_regs;
+
 static __always_inline bool has_vector(void) { return false; }
+static inline bool vstate_query(struct pt_regs *regs) { return false; }
 #define riscv_vsize (0)
+#define vstate_off(regs)		do {} while (0)
+#define vstate_on(regs)			do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 882547f6bd5c..6ee1ca2edfa7 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -77,6 +77,23 @@ union __riscv_fp_state {
 	struct __riscv_q_ext_state q;
 };
 
+struct __riscv_v_state {
+	unsigned long vstart;
+	unsigned long vl;
+	unsigned long vtype;
+	unsigned long vcsr;
+	void *datap;
+	/*
+	 * In signal handler, datap will be set a correct user stack offset
+	 * and vector registers will be copied to the address of datap
+	 * pointer.
+	 *
+	 * In ptrace syscall, datap will be set to zero and the vector
+	 * registers will be copied to the address right after this
+	 * structure.
+	 */
+};
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_ASM_RISCV_PTRACE_H */
-- 
2.17.1