Merge tag 'riscv-for-linus-6.14-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - The PH1520 pinctrl and dwmac drivers are enabeled in defconfig

 - A redundant AQRL barrier has been removed from the futex cmpxchg
   implementation

 - Support for the T-Head vector extensions, which includes exposing
   these extensions to userspace on systems that implement them

 - Some more page table information is now printed on die() and systems
   that cause PA overflows

* tag 'riscv-for-linus-6.14-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: add a warning when physical memory address overflows
  riscv/mm/fault: add show_pte() before die()
  riscv: Add ghostwrite vulnerability
  selftests: riscv: Support xtheadvector in vector tests
  selftests: riscv: Fix vector tests
  riscv: hwprobe: Document thead vendor extensions and xtheadvector extension
  riscv: hwprobe: Add thead vendor extension probing
  riscv: vector: Support xtheadvector save/restore
  riscv: Add xtheadvector instruction definitions
  riscv: csr: Add CSR encodings for CSR_VXRM/CSR_VXSAT
  RISC-V: define the elements of the VCSR vector CSR
  riscv: vector: Use vlenb from DT for thead
  riscv: Add thead and xtheadvector as a vendor extension
  riscv: dts: allwinner: Add xtheadvector to the D1/D1s devicetree
  dt-bindings: cpus: add a thead vlen register length property
  dt-bindings: riscv: Add xtheadvector ISA extension description
  RISC-V: Mark riscv_v_init() as __init
  riscv: defconfig: drop RT_GROUP_SCHED=y
  riscv/futex: Optimize atomic cmpxchg
  riscv: defconfig: enable pinctrl and dwmac support for TH1520

Documentation/arch/riscv/hwprobe.rst

@@ -293,3 +293,13 @@ The following keys are defined:
 
   * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are
     not supported at all and will generate a misaligned address fault.
+
+* :c:macro:`RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0`: A bitmask containing the
+  thead vendor extensions that are compatible with the
+  :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: base system behavior.
+
+  * T-HEAD
+
+    * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR`: The xtheadvector vendor
+        extension is supported in the T-Head ISA extensions spec starting from
+	commit a18c801634 ("Add T-Head VECTOR vendor extension. ").

Documentation/devicetree/bindings/riscv/cpus.yaml

@@ -26,6 +26,18 @@ description: |
 allOf:
   - $ref: /schemas/cpu.yaml#
   - $ref: extensions.yaml
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - thead,c906
+                - thead,c910
+                - thead,c920
+    then:
+      properties:
+        thead,vlenb: false
 
 properties:
   compatible:
@@ -96,6 +108,13 @@ properties:
     description:
       The blocksize in bytes for the Zicboz cache operations.
 
+  thead,vlenb:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      VLEN/8, the vector register length in bytes. This property is required on
+      thead systems where the vector register length is not identical on all harts, or
+      the vlenb CSR is not available.
+
   # RISC-V has multiple properties for cache op block sizes as the sizes
   # differ between individual CBO extensions
   cache-op-block-size: false

Documentation/devicetree/bindings/riscv/extensions.yaml

@@ -621,6 +621,10 @@ properties:
             latency, as ratified in commit 56ed795 ("Update
             riscv-crypto-spec-vector.adoc") of riscv-crypto.
 
+        # vendor extensions, each extension sorted alphanumerically under the
+        # vendor they belong to. Vendors are sorted alphanumerically as well.
+
+        # Andes
         - const: xandespmu
           description:
             The Andes Technology performance monitor extension for counter overflow
@@ -628,6 +632,12 @@ properties:
             Registers in the AX45MP datasheet.
             https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf
 
+        # T-HEAD
+        - const: xtheadvector
+          description:
+            The T-HEAD specific 0.7.1 vector implementation as written in
+            https://github.com/T-head-Semi/thead-extension-spec/blob/95358cb2cca9489361c61d335e03d3134b14133f/xtheadvector.adoc.
+
     allOf:
       # Zcb depends on Zca
       - if:

arch/riscv/Kconfig.errata

@@ -119,4 +119,15 @@ config ERRATA_THEAD_PMU
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD_GHOSTWRITE
+	bool "Apply T-Head Ghostwrite errata"
+	depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR
+	default y
+	help
+	  The T-Head C9xx cores have a vulnerability in the xtheadvector
+	  instruction set. When this errata is enabled, the CPUs will be probed
+	  to determine if they are vulnerable and disable xtheadvector.
+
+	  If you don't know what to do here, say "Y".
+
 endmenu # "CPU errata selection"

arch/riscv/Kconfig.vendor

@@ -16,4 +16,30 @@ config RISCV_ISA_VENDOR_EXT_ANDES
 	  If you don't know what to do here, say Y.
 endmenu
 
+menu "T-Head"
+config RISCV_ISA_VENDOR_EXT_THEAD
+	bool "T-Head vendor extension support"
+	select RISCV_ISA_VENDOR_EXT
+	default y
+	help
+	  Say N here to disable detection of and support for all T-Head vendor
+	  extensions. Without this option enabled, T-Head vendor extensions will
+	  not be detected at boot and their presence not reported to userspace.
+
+	  If you don't know what to do here, say Y.
+
+config RISCV_ISA_XTHEADVECTOR
+	bool "xtheadvector extension support"
+	depends on RISCV_ISA_VENDOR_EXT_THEAD
+	depends on RISCV_ISA_V
+	depends on FPU
+	default y
+	help
+	  Say N here if you want to disable all xtheadvector related procedures
+	  in the kernel. This will disable vector for any T-Head board that
+	  contains xtheadvector rather than the standard vector.
+
+	  If you don't know what to do here, say Y.
+endmenu
+
 endmenu

arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi

@@ -27,7 +27,8 @@
 			riscv,isa = "rv64imafdc";
 			riscv,isa-base = "rv64i";
 			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
-					       "zifencei", "zihpm";
+					       "zifencei", "zihpm", "xtheadvector";
+			thead,vlenb = <128>;
 			#cooling-cells = <2>;
 
 			cpu0_intc: interrupt-controller {

arch/riscv/configs/defconfig

@@ -10,7 +10,6 @@ CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y

arch/riscv/errata/thead/errata.c

@@ -10,6 +10,7 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 #include <asm/alternative.h>
+#include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/dma-noncoherent.h>
@@ -142,6 +143,31 @@ static bool errata_probe_pmu(unsigned int stage,
 	return true;
 }
 
+static bool errata_probe_ghostwrite(unsigned int stage,
+				    unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE))
+		return false;
+
+	/*
+	 * target-c9xx cores report arch_id and impid as 0
+	 *
+	 * While ghostwrite may not affect all c9xx cores that implement
+	 * xtheadvector, there is no futher granularity than c9xx. Assume
+	 * vulnerable for this entire class of processors when xtheadvector is
+	 * enabled.
+	 */
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage != RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	ghostwrite_set_vulnerable();
+
+	return true;
+}
+
 static u32 thead_errata_probe(unsigned int stage,
 			      unsigned long archid, unsigned long impid)
 {
@@ -155,6 +181,8 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pmu(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
 
+	errata_probe_ghostwrite(stage, archid, impid);
+
 	return cpu_req_errata;
 }
 

arch/riscv/include/asm/bugs.h

@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface for managing mitigations for riscv vulnerabilities.
+ *
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#ifndef __ASM_BUGS_H
+#define __ASM_BUGS_H
+
+/* Watch out, ordering is important here. */
+enum mitigation_state {
+	UNAFFECTED,
+	MITIGATED,
+	VULNERABLE,
+};
+
+void ghostwrite_set_vulnerable(void);
+bool ghostwrite_enable_mitigation(void);
+enum mitigation_state ghostwrite_get_state(void);
+
+#endif /* __ASM_BUGS_H */

arch/riscv/include/asm/cpufeature.h

@@ -34,6 +34,8 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
+extern u32 thead_vlenb_of;
+
 void __init riscv_user_isa_enable(void);
 
 #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\

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)
@@ -315,6 +321,15 @@
 #define CSR_STIMECMP		0x14D
 #define CSR_STIMECMPH		0x15D
 
+/* xtheadvector symbolic CSR names */
+#define CSR_VXSAT		0x9
+#define CSR_VXRM		0xa
+
+/* xtheadvector CSR masks */
+#define CSR_VXRM_MASK		3
+#define CSR_VXRM_SHIFT		1
+#define CSR_VXSAT_MASK		1
+
 /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */
 #define CSR_SISELECT		0x150
 #define CSR_SIREG		0x151

arch/riscv/include/asm/errata_list.h

@@ -25,7 +25,8 @@
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_MAE 0
 #define	ERRATA_THEAD_PMU 1
-#define	ERRATA_THEAD_NUMBER 2
+#define	ERRATA_THEAD_GHOSTWRITE 2
+#define	ERRATA_THEAD_NUMBER 3
 #endif
 
 #ifdef __ASSEMBLY__

arch/riscv/include/asm/futex.h

@@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 	__enable_user_access();
 	__asm__ __volatile__ (
-	"1:	lr.w.aqrl %[v],%[u]			\n"
+	"1:	lr.w %[v],%[u]			        \n"
 	"	bne %[v],%z[ov],3f			\n"
 	"2:	sc.w.aqrl %[t],%z[nv],%[u]		\n"
 	"	bnez %[t],1b				\n"

arch/riscv/include/asm/hwprobe.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
  */
 
 #ifndef _ASM_HWPROBE_H
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 10
+#define RISCV_HWPROBE_MAX_KEY 11
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
@@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 key)
 	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
 	case RISCV_HWPROBE_KEY_IMA_EXT_0:
 	case RISCV_HWPROBE_KEY_CPUPERF_0:
+	case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0:
 		return true;
 	}
 

arch/riscv/include/asm/switch_to.h

@@ -117,7 +117,7 @@ do {							\
 	__set_prev_cpu(__prev->thread);			\
 	if (has_fpu())					\
 		__switch_to_fpu(__prev, __next);	\
-	if (has_vector())					\
+	if (has_vector() || has_xtheadvector())		\
 		__switch_to_vector(__prev, __next);	\
 	if (switch_to_should_flush_icache(__next))	\
 		local_flush_icache_all();		\

arch/riscv/include/asm/vector.h

@@ -18,6 +18,27 @@
 #include <asm/cpufeature.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
+#include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/thead.h>
+
+#define __riscv_v_vstate_or(_val, TYPE) ({				\
+	typeof(_val) _res = _val;					\
+	if (has_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 (has_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);
@@ -41,39 +62,62 @@ static __always_inline bool has_vector(void)
 	return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X);
 }
 
+static __always_inline bool has_xtheadvector_no_alternatives(void)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+		return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR);
+	else
+		return false;
+}
+
+static __always_inline bool has_xtheadvector(void)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+		return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID,
+							   RISCV_ISA_VENDOR_EXT_XTHEADVECTOR);
+	else
+		return false;
+}
+
 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 (has_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 (has_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)
@@ -82,10 +126,36 @@ 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 (has_xtheadvector()) {
+		unsigned long status;
+
+		/*
+		 * 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.
+		 */
+		status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+		dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT;
+
+		dest->vlenb = riscv_v_vsize / 32;
+
+		if ((status & SR_FS) != SR_FS_DIRTY)
+			csr_write(CSR_STATUS, status);
+	} else {
+		dest->vcsr = csr_read(CSR_VCSR);
+		dest->vlenb = csr_read(CSR_VLENB);
+	}
 }
 
 static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src)
@@ -96,9 +166,25 @@ 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 (has_xtheadvector()) {
+		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.
+		 */
+		status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+
+		csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK);
+		csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK);
+
+		if ((status & SR_FS) != SR_FS_DIRTY)
+			csr_write(CSR_STATUS, status);
+	} else {
+		csr_write(CSR_VCSR, src->vcsr);
+	}
 }
 
 static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
@@ -108,19 +194,33 @@ 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, +zve32x\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 (has_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, +zve32x\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();
 }
 
@@ -130,19 +230,33 @@ 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, +zve32x\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 (has_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, +zve32x\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();
 }
@@ -152,33 +266,41 @@ static inline void __riscv_v_vstate_discard(void)
 	unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1);
 
 	riscv_v_enable();
+	if (has_xtheadvector())
+		asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4");
+	else
+		asm volatile (
+			".option push\n\t"
+			".option arch, +zve32x\n\t"
+			"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+			".option pop\n\t": "=&r" (vl));
+
 	asm volatile (
 		".option push\n\t"
 		".option arch, +zve32x\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"
 		".option pop\n\t"
-		: "=&r" (vl) : "r" (vtype_inval) : "memory");
+		: "=&r" (vl) : "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);
 	}
@@ -187,7 +309,7 @@ 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);
 	}
@@ -196,7 +318,7 @@ 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);
 	}
@@ -270,6 +392,8 @@ struct pt_regs;
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 static __always_inline bool has_vector(void) { return false; }
 static __always_inline bool insn_is_vector(u32 insn_buf) { return false; }
+static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; }
+static __always_inline bool has_xtheadvector(void) { return false; }
 static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }

arch/riscv/include/asm/vendor_extensions/thead.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+/*
+ * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX.
+ */
+#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR		0
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead;
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void disable_xtheadvector(void);
+#else
+static inline void disable_xtheadvector(void) { }
+#endif
+
+/* Extension specific helpers */
+
+/*
+ * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older
+ * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for
+ * vsetvli	t4, x0, e8, m8, d1
+ */
+#define THEAD_VSETVLI_T4X0E8M8D1	".long	0x00307ed7\n\t"
+
+/*
+ * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same
+ * encoding as the standard vse8.v and vle8.v, compilers seem to optimize
+ * the call resulting in a different encoding and then using a value for
+ * the "mop" field that is not part of vector-0.7.1
+ * So encode specific variants for vstate_save and _restore.
+ */
+#define THEAD_VSB_V_V0T0		".long	0x02028027\n\t"
+#define THEAD_VSB_V_V8T0		".long	0x02028427\n\t"
+#define THEAD_VSB_V_V16T0		".long	0x02028827\n\t"
+#define THEAD_VSB_V_V24T0		".long	0x02028c27\n\t"
+#define THEAD_VLB_V_V0T0		".long	0x012028007\n\t"
+#define THEAD_VLB_V_V8T0		".long	0x012028407\n\t"
+#define THEAD_VLB_V_V16T0		".long	0x012028807\n\t"
+#define THEAD_VLB_V_V24T0		".long	0x012028c07\n\t"
+
+#endif

arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+
+#include <linux/cpumask.h>
+
+#include <uapi/asm/hwprobe.h>
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus);
+#else
+static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair,
+						  const struct cpumask *cpus)
+{
+	pair->value = 0;
+}
+#endif
+
+#endif

arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h

@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_RISCV_SYS_HWPROBE_H
+#define _ASM_RISCV_SYS_HWPROBE_H
+
+#include <asm/cpufeature.h>
+
+#define VENDOR_EXT_KEY(ext)								\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \
+			pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext;			\
+		else									\
+			missing |= RISCV_HWPROBE_VENDOR_EXT_##ext;			\
+	} while (false)
+
+/*
+ * Loop through and record extensions that 1) anyone has, and 2) anyone
+ * doesn't have.
+ *
+ * _extension_checks is an arbitrary C block to set the values of pair->value
+ * and missing. It should be filled with VENDOR_EXT_KEY expressions.
+ */
+#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks)	\
+	do {											\
+		int cpu;									\
+		u64 missing = 0;								\
+		for_each_cpu(cpu, (cpus)) {							\
+			struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu];	\
+			_extension_checks							\
+		}										\
+		(pair)->value &= ~missing;							\
+	} while (false)										\
+
+#endif /* _ASM_RISCV_SYS_HWPROBE_H */

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

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
  */
 
 #ifndef _UAPI_ASM_HWPROBE_H
@@ -94,6 +94,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW		2
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
+#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0	11
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */