riscv: Introduce struct/helpers to save/restore per-task Vector state

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_ext_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>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20230605110724.21391-10-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/include/asm/vector.h

@@ -11,8 +11,10 @@
 
 #ifdef CONFIG_RISCV_ISA_V
 
+#include <linux/stringify.h>
 #include <asm/hwcap.h>
 #include <asm/csr.h>
+#include <asm/asm.h>
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
@@ -22,6 +24,26 @@ static __always_inline bool has_vector(void)
 	return riscv_has_extension_unlikely(RISCV_ISA_EXT_v);
 }
 
+static inline void __riscv_v_vstate_clean(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN;
+}
+
+static inline void riscv_v_vstate_off(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+}
+
+static inline void riscv_v_vstate_on(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL;
+}
+
+static inline bool riscv_v_vstate_query(struct pt_regs *regs)
+{
+	return (regs->status & SR_VS) != 0;
+}
+
 static __always_inline void riscv_v_enable(void)
 {
 	csr_set(CSR_SSTATUS, SR_VS);
@@ -32,13 +54,86 @@ static __always_inline void riscv_v_disable(void)
 	csr_clear(CSR_SSTATUS, SR_VS);
 }
 
+static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
+{
+	asm volatile (
+		"csrr	%0, " __stringify(CSR_VSTART) "\n\t"
+		"csrr	%1, " __stringify(CSR_VTYPE) "\n\t"
+		"csrr	%2, " __stringify(CSR_VL) "\n\t"
+		"csrr	%3, " __stringify(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_ext_state *src)
+{
+	asm volatile (
+		".option push\n\t"
+		".option arch, +v\n\t"
+		"vsetvl	 x0, %2, %1\n\t"
+		".option pop\n\t"
+		"csrw	" __stringify(CSR_VSTART) ", %0\n\t"
+		"csrw	" __stringify(CSR_VCSR) ", %3\n\t"
+		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl),
+		    "r" (src->vcsr) :);
+}
+
+static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
+					 void *datap)
+{
+	unsigned long vl;
+
+	riscv_v_enable();
+	__vstate_csr_save(save_to);
+	asm volatile (
+		".option push\n\t"
+		".option arch, +v\n\t"
+		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+		"vse8.v		v0, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vse8.v		v8, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vse8.v		v16, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vse8.v		v24, (%1)\n\t"
+		".option pop\n\t"
+		: "=&r" (vl) : "r" (datap) : "memory");
+	riscv_v_disable();
+}
+
+static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_from,
+					    void *datap)
+{
+	unsigned long vl;
+
+	riscv_v_enable();
+	asm volatile (
+		".option push\n\t"
+		".option arch, +v\n\t"
+		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+		"vle8.v		v0, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vle8.v		v8, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vle8.v		v16, (%1)\n\t"
+		"add		%1, %1, %0\n\t"
+		"vle8.v		v24, (%1)\n\t"
+		".option pop\n\t"
+		: "=&r" (vl) : "r" (datap) : "memory");
+	__vstate_csr_restore(restore_from);
+	riscv_v_disable();
+}
+
 #else /* ! CONFIG_RISCV_ISA_V  */
 
 struct pt_regs;
 
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 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_vstate_off(regs)		do {} while (0)
+#define riscv_v_vstate_on(regs)			do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 

arch/riscv/include/uapi/asm/ptrace.h

@@ -77,6 +77,23 @@ union __riscv_fp_state {
 	struct __riscv_q_ext_state q;
 };
 
+struct __riscv_v_ext_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 */