[PATCH 13/19] riscv: vector: Support xtheadvector save/restore

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Use alternatives to add support for xtheadvector vector save/restore
routines.

Signed-off-by: Charlie Jenkins <charlie@xxxxxxxxxxxx>
---
 arch/riscv/include/asm/csr.h           |   6 +
 arch/riscv/include/asm/vector.h        | 228 +++++++++++++++++++++++++--------
 arch/riscv/kernel/kernel_mode_vector.c |   4 +-
 arch/riscv/kernel/vector.c             |  22 +++-
 4 files changed, 203 insertions(+), 57 deletions(-)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index e5a35efd56e0..13657d096e7d 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -30,6 +30,12 @@
 #define SR_VS_CLEAN	_AC(0x00000400, UL)
 #define SR_VS_DIRTY	_AC(0x00000600, UL)
 
+#define SR_VS_THEAD		_AC(0x01800000, UL) /* xtheadvector Status */
+#define SR_VS_OFF_THEAD		_AC(0x00000000, UL)
+#define SR_VS_INITIAL_THEAD	_AC(0x00800000, UL)
+#define SR_VS_CLEAN_THEAD	_AC(0x01000000, UL)
+#define SR_VS_DIRTY_THEAD	_AC(0x01800000, UL)
+
 #define SR_XS		_AC(0x00018000, UL) /* Extension Status */
 #define SR_XS_OFF	_AC(0x00000000, UL)
 #define SR_XS_INITIAL	_AC(0x00008000, UL)
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 731dcd0ed4de..f6ca30dd7d86 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -18,6 +18,25 @@
 #include <asm/cpufeature.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
+#include <asm/xtheadvector.h>
+
+#define __riscv_v_vstate_or(_val, TYPE) ({				\
+	typeof(_val) _res = _val;					\
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) \
+		_res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD;	\
+	else								\
+		_res = (_res & ~SR_VS) | SR_VS_##TYPE;			\
+	_res;								\
+})
+
+#define __riscv_v_vstate_check(_val, TYPE) ({				\
+	bool _res;							\
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) \
+		_res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD;	\
+	else								\
+		_res = ((_val) & SR_VS) == SR_VS_##TYPE;		\
+	_res;								\
+})
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
@@ -42,37 +61,43 @@ static __always_inline bool has_vector(void)
 
 static inline void __riscv_v_vstate_clean(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN;
+	regs->status = __riscv_v_vstate_or(regs->status, CLEAN);
 }
 
 static inline void __riscv_v_vstate_dirty(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY;
+	regs->status = __riscv_v_vstate_or(regs->status, DIRTY);
 }
 
 static inline void riscv_v_vstate_off(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+	regs->status = __riscv_v_vstate_or(regs->status, OFF);
 }
 
 static inline void riscv_v_vstate_on(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL;
+	regs->status = __riscv_v_vstate_or(regs->status, INITIAL);
 }
 
 static inline bool riscv_v_vstate_query(struct pt_regs *regs)
 {
-	return (regs->status & SR_VS) != 0;
+	return !__riscv_v_vstate_check(regs->status, OFF);
 }
 
 static __always_inline void riscv_v_enable(void)
 {
-	csr_set(CSR_SSTATUS, SR_VS);
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR))
+		csr_set(CSR_SSTATUS, SR_VS_THEAD);
+	else
+		csr_set(CSR_SSTATUS, SR_VS);
 }
 
 static __always_inline void riscv_v_disable(void)
 {
-	csr_clear(CSR_SSTATUS, SR_VS);
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR))
+		csr_clear(CSR_SSTATUS, SR_VS_THEAD);
+	else
+		csr_clear(CSR_SSTATUS, SR_VS);
 }
 
 static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
@@ -81,10 +106,47 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
 		"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"
-		"csrr	%4, " __stringify(CSR_VLENB) "\n\t"
 		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
-		  "=r" (dest->vcsr), "=r" (dest->vlenb) : :);
+		"=r" (dest->vcsr) : :);
+
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) {
+		u32 tmp_vcsr;
+		bool restore_fpu = false;
+		unsigned long status = csr_read(CSR_SSTATUS);
+
+		/*
+		 * CSR_VCSR is defined as
+		 * [2:1] - vxrm[1:0]
+		 * [0] - vxsat
+		 * The earlier vector spec implemented by T-Head uses separate
+		 * registers for the same bit-elements, so just combine those
+		 * into the existing output field.
+		 *
+		 * Additionally T-Head cores need FS to be enabled when accessing
+		 * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions.
+		 * Though the cores do not implement the VXRM and VXSAT fields in the
+		 * FCSR CSR that vector-0.7.1 specifies.
+		 */
+		if ((status & SR_FS) == SR_FS_OFF) {
+			csr_set(CSR_SSTATUS, (status & ~SR_FS) | SR_FS_CLEAN);
+			restore_fpu = true;
+		}
+
+		asm volatile (
+			"csrr	%[tmp_vcsr], " __stringify(VCSR_VXRM) "\n\t"
+			"slliw	%[vcsr], %[tmp_vcsr], " __stringify(VCSR_VXRM_SHIFT) "\n\t"
+			"csrr	%[tmp_vcsr], " __stringify(VCSR_VXSAT) "\n\t"
+			"or	%[vcsr], %[vcsr], %[tmp_vcsr]\n\t"
+			: [vcsr] "=r" (dest->vcsr), [tmp_vcsr] "=&r" (tmp_vcsr));
+
+		if (restore_fpu)
+			csr_set(CSR_SSTATUS, status);
+	} else {
+		asm volatile (
+			"csrr	%[vcsr], " __stringify(CSR_VCSR) "\n\t"
+			"csrr	%[vlenb], " __stringify(CSR_VLENB) "\n\t"
+			: [vcsr] "=r" (dest->vcsr), [vlenb] "=r" (dest->vlenb));
+	}
 }
 
 static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src)
@@ -95,9 +157,37 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src
 		"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) :);
+		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl));
+
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) {
+		u32 tmp_vcsr;
+		bool restore_fpu = false;
+		unsigned long status = csr_read(CSR_SSTATUS);
+
+		/*
+		 * Similar to __vstate_csr_save above, restore values for the
+		 * separate VXRM and VXSAT CSRs from the vcsr variable.
+		 */
+		if ((status & SR_FS) == SR_FS_OFF) {
+			csr_set(CSR_SSTATUS, (status & ~SR_FS) | SR_FS_CLEAN);
+			restore_fpu = true;
+		}
+
+		asm volatile (
+			"srliw	%[tmp_vcsr], %[vcsr], " __stringify(VCSR_VXRM_SHIFT) "\n\t"
+			"andi	%[tmp_vcsr], %[tmp_vcsr], " __stringify(VCSR_VXRM_MASK) "\n\t"
+			"csrw	" __stringify(VCSR_VXRM) ", %[tmp_vcsr]\n\t"
+			"andi	%[tmp_vcsr], %[vcsr], " __stringify(VCSR_VXSAT_MASK) "\n\t"
+			"csrw	" __stringify(VCSR_VXSAT) ", %[tmp_vcsr]\n\t"
+			: [tmp_vcsr] "=&r" (tmp_vcsr) : [vcsr] "r" (src->vcsr));
+
+		if (restore_fpu)
+			csr_set(CSR_SSTATUS, status);
+	} else {
+		asm volatile (
+			"csrw	" __stringify(CSR_VCSR) ", %[vcsr]\n\t"
+			: : [vcsr] "r" (src->vcsr));
+	}
 }
 
 static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
@@ -107,19 +197,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 
 	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");
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) {
+		asm volatile (
+			"mv t0, %0\n\t"
+			THEAD_VSETVLI_T4X0E8M8D1
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			: : "r" (datap) : "memory", "t0", "t4");
+	} else {
+		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();
 }
 
@@ -129,55 +233,77 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 	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");
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) {
+		asm volatile (
+			"mv t0, %0\n\t"
+			THEAD_VSETVLI_T4X0E8M8D1
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			: : "r" (datap) : "memory", "t0", "t4");
+	} else {
+		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();
 }
 
 static inline void __riscv_v_vstate_discard(void)
 {
-	unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1);
+	unsigned long vtype_inval = 1UL << (BITS_PER_LONG - 1);
 
 	riscv_v_enable();
+	if (riscv_has_vendor_extension_unlikely(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR))
+		asm volatile (THEAD_VSETVLI_X0X0E8M8D1);
+	else
+		asm volatile (
+			".option push\n\t"
+			".option arch, +v\n\t"
+			"vsetvli	x0, x0, e8, m8, ta, ma\n\t"
+			".option pop\n\t");
+
 	asm volatile (
 		".option push\n\t"
 		".option arch, +v\n\t"
-		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
 		"vmv.v.i	v0, -1\n\t"
 		"vmv.v.i	v8, -1\n\t"
 		"vmv.v.i	v16, -1\n\t"
 		"vmv.v.i	v24, -1\n\t"
-		"vsetvl		%0, x0, %1\n\t"
+		"vsetvl		x0, x0, %0\n\t"
 		".option pop\n\t"
-		: "=&r" (vl) : "r" (vtype_inval) : "memory");
+		: : "r" (vtype_inval));
+
 	riscv_v_disable();
 }
 
 static inline void riscv_v_vstate_discard(struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) == SR_VS_OFF)
-		return;
-
-	__riscv_v_vstate_discard();
-	__riscv_v_vstate_dirty(regs);
+	if (riscv_v_vstate_query(regs)) {
+		__riscv_v_vstate_discard();
+		__riscv_v_vstate_dirty(regs);
+	}
 }
 
 static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 				       struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
+	if (__riscv_v_vstate_check(regs->status, DIRTY)) {
 		__riscv_v_vstate_save(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
@@ -186,7 +312,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 					  struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) != SR_VS_OFF) {
+	if (riscv_v_vstate_query(regs)) {
 		__riscv_v_vstate_restore(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
@@ -195,7 +321,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 static inline void riscv_v_vstate_set_restore(struct task_struct *task,
 					      struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) != SR_VS_OFF) {
+	if (riscv_v_vstate_query(regs)) {
 		set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
 		riscv_v_vstate_on(regs);
 	}
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 6afe80c7f03a..ad70fc581dbe 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -143,7 +143,7 @@ static int riscv_v_start_kernel_context(bool *is_nested)
 
 	/* Transfer the ownership of V from user to kernel, then save */
 	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
-	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+	if (__riscv_v_vstate_check(task_pt_regs(current)->status, DIRTY)) {
 		uvstate = &current->thread.vstate;
 		__riscv_v_vstate_save(uvstate, uvstate->datap);
 	}
@@ -160,7 +160,7 @@ asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
 		return;
 
 	depth = riscv_v_ctx_get_depth();
-	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+	if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY))
 		riscv_preempt_v_set_dirty();
 
 	riscv_v_ctx_depth_inc();
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 6727d1d3b8f2..d8ec2757cc2e 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -33,10 +33,24 @@ int riscv_v_setup_vsize(void)
 {
 	unsigned long this_vsize;
 
-	/* There are 32 vector registers with vlenb length. */
-	riscv_v_enable();
-	this_vsize = csr_read(CSR_VLENB) * 32;
-	riscv_v_disable();
+	/*
+	 * This is called before alternatives have been patched so can't use
+	 * riscv_has_vendor_extension_unlikely
+	 */
+	if (__riscv_isa_vendor_extension_available(NULL, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR)) {
+		/*
+		 * Although xtheadvector states that th.vlenb exists and
+		 * overlaps with the vector 1.0 extension overlaps, an illegal
+		 * instruction is raised if read. These systems all currently
+		 * have a fixed vector length of 128, so hardcode that value.
+		 */
+		this_vsize = 128;
+	} else {
+		/* There are 32 vector registers with vlenb length. */
+		riscv_v_enable();
+		this_vsize = csr_read(CSR_VLENB) * 32;
+		riscv_v_disable();
+	}
 
 	if (!riscv_v_vsize) {
 		riscv_v_vsize = this_vsize;

-- 
2.44.0





[Index of Archives]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite Forum]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux