Merge tag 'riscv-for-linus-6.13-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-v updates from Palmer Dabbelt:

 - Support for pointer masking in userspace

 - Support for probing vector misaligned access performance

 - Support for qspinlock on systems with Zacas and Zabha

* tag 'riscv-for-linus-6.13-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (38 commits)
  RISC-V: Remove unnecessary include from compat.h
  riscv: Fix default misaligned access trap
  riscv: Add qspinlock support
  dt-bindings: riscv: Add Ziccrse ISA extension description
  riscv: Add ISA extension parsing for Ziccrse
  asm-generic: ticket-lock: Add separate ticket-lock.h
  asm-generic: ticket-lock: Reuse arch_spinlock_t of qspinlock
  riscv: Implement xchg8/16() using Zabha
  riscv: Implement arch_cmpxchg128() using Zacas
  riscv: Improve zacas fully-ordered cmpxchg()
  riscv: Implement cmpxchg8/16() using Zabha
  dt-bindings: riscv: Add Zabha ISA extension description
  riscv: Implement cmpxchg32/64() using Zacas
  riscv: Do not fail to build on byte/halfword operations with Zawrs
  riscv: Move cpufeature.h macros into their own header
  KVM: riscv: selftests: Add Smnpm and Ssnpm to get-reg-list test
  RISC-V: KVM: Allow Smnpm and Ssnpm extensions for guests
  riscv: hwprobe: Export the Supm ISA extension
  riscv: selftests: Add a pointer masking test
  riscv: Allow ptrace control of the tagged address ABI
  ...

37 files changed, 1247 insertions, 181 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index ff1e353b0d6f..cc63aef41e94 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -83,6 +83,7 @@ config RISCV
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if RISCV_M_MODE
@@ -116,6 +117,7 @@ config RISCV
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
@@ -507,6 +509,39 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+choice
+	prompt "RISC-V spinlock type"
+	default RISCV_COMBO_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU && NONPORTABLE
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  The queued spinlock implementation requires the forward progress
+	  guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or
+	  LR/SC with Ziccrse provide such guarantee.
+
+	  Select this if and only if Zabha or Ziccrse is available on your
+	  platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms
+	  without one of those extensions.
+
+	  If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks
+	  when supported and otherwise ticket spinlocks.
+
+config RISCV_COMBO_SPINLOCKS
+	bool "Using combo spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Embed both queued spinlock and ticket lock so that the spinlock
+	  implementation can be chosen at runtime.
+
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL
@@ -532,6 +567,17 @@ config RISCV_ISA_C
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_SUPM
+	bool "Supm extension for userspace pointer masking"
+	depends on 64BIT
+	default y
+	help
+	  Add support for pointer masking in userspace (Supm) when the
+	  underlying hardware extension (Smnpm or Ssnpm) is detected at boot.
+
+	  If this option is disabled, userspace will be unable to use
+	  the prctl(PR_{SET,GET}_TAGGED_ADDR_CTRL) API.
+
 config RISCV_ISA_SVNAPOT
 	bool "Svnapot extension support for supervisor mode NAPOT pages"
 	depends on 64BIT && MMU
@@ -633,6 +679,40 @@ config RISCV_ISA_ZAWRS
 	  use of these instructions in the kernel when the Zawrs extension is
 	  detected at boot.
 
+config TOOLCHAIN_HAS_ZABHA
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zabha)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zabha)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZABHA
+	bool "Zabha extension support for atomic byte/halfword operations"
+	depends on TOOLCHAIN_HAS_ZABHA
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zabha ISA-extension to implement kernel
+	  byte/halfword atomic memory operations when it is detected at boot.
+
+	  If you don't know what to do here, say Y.
+
+config TOOLCHAIN_HAS_ZACAS
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZACAS
+	bool "Zacas extension support for atomic CAS"
+	depends on TOOLCHAIN_HAS_ZACAS
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Enable the use of the Zacas ISA-extension to implement kernel atomic
+	  cmpxchg operations when it is detected at boot.
+
 	  If you don't know what to do here, say Y.
 
 config TOOLCHAIN_HAS_ZBB
@@ -786,10 +866,24 @@ config THREAD_SIZE_ORDER
 
 config RISCV_MISALIGNED
 	bool
+	help
+	  Embed support for detecting and emulating misaligned
+	  scalar or vector loads and stores.
+
+config RISCV_SCALAR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	help
 	  Embed support for emulating misaligned loads and stores.
 
+config RISCV_VECTOR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  Enable detecting support for vector misaligned loads and stores.
+
 choice
 	prompt "Unaligned Accesses Support"
 	default RISCV_PROBE_UNALIGNED_ACCESS
@@ -801,7 +895,7 @@ choice
 
 config RISCV_PROBE_UNALIGNED_ACCESS
 	bool "Probe for hardware unaligned access support"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  During boot, the kernel will run a series of tests to determine the
 	  speed of unaligned accesses. This probing will dynamically determine
@@ -812,7 +906,7 @@ config RISCV_PROBE_UNALIGNED_ACCESS
 
 config RISCV_EMULATED_UNALIGNED_ACCESS
 	bool "Emulate unaligned access where system support is missing"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  If unaligned memory accesses trap into the kernel as they are not
 	  supported by the system, the kernel will emulate the unaligned
@@ -841,6 +935,46 @@ config RISCV_EFFICIENT_UNALIGNED_ACCESS
 
 endchoice
 
+choice
+	prompt "Vector unaligned Accesses Support"
+	depends on RISCV_ISA_V
+	default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for vector unaligned accesses. This
+	  information is used by the kernel to perform optimizations. It is also
+	  exposed to user space via the hwprobe syscall. The hardware will be
+	  probed at boot by default.
+
+config RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	bool "Probe speed of vector unaligned accesses"
+	select RISCV_VECTOR_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of vector unaligned accesses if they are supported. This probing
+	  will dynamically determine the speed of vector unaligned accesses on
+	  the underlying system if they are supported.
+
+config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports slow vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow vector unaligned memory accesses. The
+	  kernel and userspace programs may not be able to run at all on systems
+	  that do not support unaligned memory accesses.
+
+config RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports fast vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports fast vector unaligned memory accesses. When
+	  enabled, this option improves the performance of the kernel on such
+	  systems. However, the kernel and userspace programs will run much more
+	  slowly, or will not be able to run at all, on systems that do not
+	  support efficient unaligned memory accesses.
+
+endchoice
+
 source "arch/riscv/Kconfig.vendor"
 
 endmenu # "Platform type"
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index d469db9f46f4..9fe1ee740dda 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -82,6 +82,12 @@ else
 riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei
 endif
 
+# Check if the toolchain supports Zacas
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas
+
+# Check if the toolchain supports Zabha
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZABHA) := $(riscv-march-y)_zabha
+
 # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
 # matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
 KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 1d5e13b148f2..b4a37345703e 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -167,6 +167,7 @@ CONFIG_PINCTRL_SOPHGO_CV1800B=y
 CONFIG_PINCTRL_SOPHGO_CV1812H=y
 CONFIG_PINCTRL_SOPHGO_SG2000=y
 CONFIG_PINCTRL_SOPHGO_SG2002=y
+CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_SIFIVE=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_SENSORS_SFCTEMP=m
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 1461af12da6e..de13d5a234f8 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -6,10 +6,12 @@ generic-y += early_ioremap.h
 generic-y += flat.h
 generic-y += kvm_para.h
 generic-y += mmzone.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
-generic-y += spinlock.h
 generic-y += spinlock_types.h
+generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
+generic-y += qspinlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ebbce134917c..4cadc56220fe 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -12,30 +12,43 @@
 #include <asm/fence.h>
 #include <asm/hwcap.h>
 #include <asm/insn-def.h>
-
-#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
-({									\
-	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
-	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-	       prepend							\
-	       "0:	lr.w %0, %2\n"					\
-	       "	and  %1, %0, %z4\n"				\
-	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
-	       "	bnez %1, 0b\n"					\
-	       append							\
-	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-	       : "rJ" (__newx), "rJ" (~__mask)				\
-	       : "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#include <asm/cpufeature-macros.h>
+
+#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
+			   swap_append, r, p, n)				\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) {		\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+			swap_append						\
+			: "=&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+				<< __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+		       prepend							\
+		       "0:	lr.w %0, %2\n"					\
+		       "	and  %1, %0, %z4\n"				\
+		       "	or   %1, %1, %z3\n"				\
+		       "	sc.w" sc_sfx " %1, %1, %2\n"			\
+		       "	bnez %1, 0b\n"					\
+		       sc_append						\
+		       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+		       : "rJ" (__newx), "rJ" (~__mask)				\
+		       : "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
@@ -58,8 +71,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
+		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
@@ -106,55 +124,90 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-
-#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n)	\
-({									\
-	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
-	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __oldx = (ulong)(o) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-		prepend							\
-		"0:	lr.w %0, %2\n"					\
-		"	and  %1, %0, %z5\n"				\
-		"	bne  %1, %z3, 1f\n"				\
-		"	and  %1, %0, %z6\n"				\
-		"	or   %1, %1, %z4\n"				\
-		"	sc.w" sc_sfx " %1, %1, %2\n"			\
-		"	bnez %1, 0b\n"					\
-		append							\
-		"1:\n"							\
-		: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-		: "rJ" ((long)__oldx), "rJ" (__newx),			\
-		  "rJ" (__mask), "rJ" (~__mask)				\
-		: "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#define __arch_cmpxchg_masked(sc_sfx, cas_sfx,					\
+			      sc_prepend, sc_append,				\
+			      cas_prepend, cas_append,				\
+			      r, p, o, n)					\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) &&		\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {		\
+		r = o;								\
+										\
+		__asm__ __volatile__ (						\
+			cas_prepend							\
+			"	amocas" cas_sfx " %0, %z2, %1\n"		\
+			cas_append							\
+			: "+&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+			       << __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __oldx = (ulong)(o) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+			sc_prepend							\
+			"0:	lr.w %0, %2\n"					\
+			"	and  %1, %0, %z5\n"				\
+			"	bne  %1, %z3, 1f\n"				\
+			"	and  %1, %0, %z6\n"				\
+			"	or   %1, %1, %z4\n"				\
+			"	sc.w" sc_sfx " %1, %1, %2\n"			\
+			"	bnez %1, 0b\n"					\
+			sc_append							\
+			"1:\n"							\
+			: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+			: "rJ" ((long)__oldx), "rJ" (__newx),			\
+			  "rJ" (__mask), "rJ" (~__mask)				\
+			: "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
-#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n)	\
+#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx,				\
+		       sc_prepend, sc_append,				\
+		       cas_prepend, cas_append,				\
+		       r, p, co, o, n)					\
 ({									\
-	register unsigned int __rc;					\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&			\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {	\
+		r = o;							\
 									\
-	__asm__ __volatile__ (						\
-		prepend							\
-		"0:	lr" lr_sfx " %0, %2\n"				\
-		"	bne  %0, %z3, 1f\n"				\
-		"	sc" sc_sfx " %1, %z4, %2\n"			\
-		"	bnez %1, 0b\n"					\
-		append							\
-		"1:\n"							\
-		: "=&r" (r), "=&r" (__rc), "+A" (*(p))			\
-		: "rJ" (co o), "rJ" (n)					\
-		: "memory");						\
+		__asm__ __volatile__ (					\
+			cas_prepend					\
+			"	amocas" cas_sfx " %0, %z2, %1\n"	\
+			cas_append					\
+			: "+&r" (r), "+A" (*(p))			\
+			: "rJ" (n)					\
+			: "memory");					\
+	} else {							\
+		register unsigned int __rc;				\
+									\
+		__asm__ __volatile__ (					\
+			sc_prepend					\
+			"0:	lr" lr_sfx " %0, %2\n"			\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc" sc_sfx " %1, %z4, %2\n"		\
+			"	bnez %1, 0b\n"				\
+			sc_append					\
+			"1:\n"						\
+			: "=&r" (r), "=&r" (__rc), "+A" (*(p))		\
+			: "rJ" (co o), "rJ" (n)				\
+			: "memory");					\
+	}								\
 })
 
-#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append)		\
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx,			\
+		      sc_prepend, sc_append,				\
+		      cas_prepend, cas_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __old = (old);				\
@@ -163,17 +216,28 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
+		break;							\
 	case 2:								\
-		__arch_cmpxchg_masked(sc_sfx, prepend, append,		\
-					__ret, __ptr, __old, __new);	\
+		__arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
 		break;							\
 	case 4:								\
-		__arch_cmpxchg(".w", ".w" sc_sfx, prepend, append,	\
-				__ret, __ptr, (long), __old, __new);	\
+		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, (long), __old, __new);	\
 		break;							\
 	case 8:								\
-		__arch_cmpxchg(".d", ".d" sc_sfx, prepend, append,	\
-				__ret, __ptr, /**/, __old, __new);	\
+		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -181,17 +245,40 @@
 	(__typeof__(*(__ptr)))__ret;					\
 })
 
+/*
+ * These macros are here to improve the readability of the arch_cmpxchg_XXX()
+ * macros.
+ */
+#define SC_SFX(x)	x
+#define CAS_SFX(x)	x
+#define SC_PREPEND(x)	x
+#define SC_APPEND(x)	x
+#define CAS_PREPEND(x)	x
+#define CAS_APPEND(x)	x
+
 #define arch_cmpxchg_relaxed(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(""),			\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_acquire(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER))
 
 #define arch_cmpxchg_release(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""),	\
+		      CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND(""))
 
 #define arch_cmpxchg(ptr, o, n)						\
-	_arch_cmpxchg((ptr), (o), (n), ".rl", "", "	fence rw, rw\n")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(".rl"), CAS_SFX(".aqrl"),			\
+		      SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_local(ptr, o, n)					\
 	arch_cmpxchg_relaxed((ptr), (o), (n))
@@ -226,6 +313,44 @@
 	arch_cmpxchg_release((ptr), (o), (n));				\
 })
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS)
+
+#define system_has_cmpxchg128()        riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)
+
+union __u128_halves {
+	u128 full;
+	struct {
+		u64 low, high;
+	};
+};
+
+#define __arch_cmpxchg128(p, o, n, cas_sfx)					\
+({										\
+	__typeof__(*(p)) __o = (o);                                             \
+	union __u128_halves __hn = { .full = (n) };				\
+	union __u128_halves __ho = { .full = (__o) };				\
+	register unsigned long t1 asm ("t1") = __hn.low;			\
+	register unsigned long t2 asm ("t2") = __hn.high;			\
+	register unsigned long t3 asm ("t3") = __ho.low;			\
+	register unsigned long t4 asm ("t4") = __ho.high;			\
+										\
+	__asm__ __volatile__ (							\
+		 "       amocas.q" cas_sfx " %0, %z3, %2"			\
+		 : "+&r" (t3), "+&r" (t4), "+A" (*(p))				\
+		 : "rJ" (t1), "rJ" (t2)						\
+		 : "memory");							\
+										\
+		 ((u128)t4 << 64) | t3;						\
+})
+
+#define arch_cmpxchg128(ptr, o, n)						\
+	__arch_cmpxchg128((ptr), (o), (n), ".aqrl")
+
+#define arch_cmpxchg128_local(ptr, o, n)					\
+	__arch_cmpxchg128((ptr), (o), (n), "")
+
+#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */
+
 #ifdef CONFIG_RISCV_ISA_ZAWRS
 /*
  * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to
@@ -245,6 +370,11 @@ static __always_inline void __cmpwait(volatile void *ptr,
 		 : : : : no_zawrs);
 
 	switch (size) {
+	case 1:
+		fallthrough;
+	case 2:
+		/* RISC-V doesn't have lr instructions on byte and half-word. */
+		goto no_zawrs;
 	case 4:
 		asm volatile(
 		"	lr.w	%0, %1\n"
diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
index aa103530a5c8..6081327e55f5 100644
--- a/arch/riscv/include/asm/compat.h
+++ b/arch/riscv/include/asm/compat.h
@@ -9,7 +9,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/sched/task_stack.h>
 #include <asm-generic/compat.h>
 
 static inline int is_compat_task(void)
diff --git a/arch/riscv/include/asm/cpufeature-macros.h b/arch/riscv/include/asm/cpufeature-macros.h
new file mode 100644
index 000000000000..a8103edbf51f
--- /dev/null
+++ b/arch/riscv/include/asm/cpufeature-macros.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2022-2024 Rivos, Inc
+ */
+
+#ifndef _ASM_CPUFEATURE_MACROS_H
+#define _ASM_CPUFEATURE_MACROS_H
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+
+#define STANDARD_EXT		0
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
+							 const unsigned long ext)
+{
+	asm goto(ALTERNATIVE("j	%l[l_no]", "nop", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_no);
+
+	return true;
+l_no:
+	return false;
+}
+
+static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
+							   const unsigned long ext)
+{
+	asm goto(ALTERNATIVE("nop", "j	%l[l_yes]", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
+static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_likely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
+#endif /* _ASM_CPUFEATURE_MACROS_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 45f9c1171a48..4bd054c54c21 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -8,9 +8,12 @@
 
 #include <linux/bitmap.h>
 #include <linux/jump_label.h>
+#include <linux/workqueue.h>
+#include <linux/kconfig.h>
+#include <linux/percpu-defs.h>
+#include <linux/threads.h>
 #include <asm/hwcap.h>
-#include <asm/alternative-macros.h>
-#include <asm/errno.h>
+#include <asm/cpufeature-macros.h>
 
 /*
  * These are probed via a device_initcall(), via either the SBI or directly
@@ -31,7 +34,7 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
-void riscv_user_isa_enable(void);
+void __init riscv_user_isa_enable(void);
 
 #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
 	.name = #_name,									\
@@ -58,8 +61,9 @@ void riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
-#if defined(CONFIG_RISCV_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
+void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
 bool unaligned_ctl_available(void);
 DECLARE_PER_CPU(long, misaligned_access_speed);
@@ -70,6 +74,12 @@ static inline bool unaligned_ctl_available(void)
 }
 #endif
 
+bool check_vector_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_VECTOR_MISALIGNED)
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused);
+DECLARE_PER_CPU(long, vector_misaligned_access);
+#endif
+
 #if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
 DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 
@@ -103,61 +113,6 @@ extern const size_t riscv_isa_ext_count;
 extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
-
-#define STANDARD_EXT		0
-
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
-#define riscv_isa_extension_available(isa_bitmap, ext)	\
-	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
-
-static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
-							 const unsigned long ext)
-{
-	asm goto(ALTERNATIVE("j	%l[l_no]", "nop", %[vendor], %[ext], 1)
-	:
-	: [vendor] "i" (vendor), [ext] "i" (ext)
-	:
-	: l_no);
-
-	return true;
-l_no:
-	return false;
-}
-
-static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
-							   const unsigned long ext)
-{
-	asm goto(ALTERNATIVE("nop", "j	%l[l_yes]", %[vendor], %[ext], 1)
-	:
-	: [vendor] "i" (vendor), [ext] "i" (ext)
-	:
-	: l_yes);
-
-	return false;
-l_yes:
-	return true;
-}
-
-static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
-		return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
-
-	return __riscv_isa_extension_available(NULL, ext);
-}
-
-static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
-		return __riscv_has_extension_likely(STANDARD_EXT, ext);
-
-	return __riscv_isa_extension_available(NULL, ext);
-}
-
 static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
 {
 	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 25966995da04..fe5d4eb9adea 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -119,6 +119,10 @@
 
 /* HSTATUS flags */
 #ifdef CONFIG_64BIT
+#define HSTATUS_HUPMM		_AC(0x3000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_0	_AC(0x0000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_7	_AC(0x2000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_16	_AC(0x3000000000000, UL)
 #define HSTATUS_VSXL		_AC(0x300000000, UL)
 #define HSTATUS_VSXL_SHIFT	32
 #endif
@@ -195,6 +199,10 @@
 /* xENVCFG flags */
 #define ENVCFG_STCE			(_AC(1, ULL) << 63)
 #define ENVCFG_PBMTE			(_AC(1, ULL) << 62)
+#define ENVCFG_PMM			(_AC(0x3, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_0		(_AC(0x0, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_7		(_AC(0x2, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_16		(_AC(0x3, ULL) << 32)
 #define ENVCFG_CBZE			(_AC(1, UL) << 7)
 #define ENVCFG_CBCFE			(_AC(1, UL) << 6)
 #define ENVCFG_CBIE_SHIFT		4
@@ -216,6 +224,12 @@
 #define SMSTATEEN0_SSTATEEN0_SHIFT	63
 #define SMSTATEEN0_SSTATEEN0		(_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT)
 
+/* mseccfg bits */
+#define MSECCFG_PMM			ENVCFG_PMM
+#define MSECCFG_PMM_PMLEN_0		ENVCFG_PMM_PMLEN_0
+#define MSECCFG_PMM_PMLEN_7		ENVCFG_PMM_PMLEN_7
+#define MSECCFG_PMM_PMLEN_16		ENVCFG_PMM_PMLEN_16
+
 /* symbolic CSR names: */
 #define CSR_CYCLE		0xc00
 #define CSR_TIME		0xc01
@@ -382,6 +396,8 @@
 #define CSR_MIP			0x344
 #define CSR_PMPCFG0		0x3a0
 #define CSR_PMPADDR0		0x3b0
+#define CSR_MSECCFG		0x747
+#define CSR_MSECCFGH		0x757
 #define CSR_MVENDORID		0xf11
 #define CSR_MARCHID		0xf12
 #define CSR_MIMPID		0xf13
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 2293e535f865..b28ccc6cdeea 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -33,6 +33,7 @@ static inline int handle_misaligned_load(struct pt_regs *regs)
 {
 	return -1;
 }
+
 static inline int handle_misaligned_store(struct pt_regs *regs)
 {
 	return -1;
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 46d9de54179e..08d2a5697466 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -93,6 +93,11 @@
 #define RISCV_ISA_EXT_ZCMOP		84
 #define RISCV_ISA_EXT_ZAWRS		85
 #define RISCV_ISA_EXT_SVVPTC		86
+#define RISCV_ISA_EXT_SMMPM		87
+#define RISCV_ISA_EXT_SMNPM		88
+#define RISCV_ISA_EXT_SSNPM		89
+#define RISCV_ISA_EXT_ZABHA		90
+#define RISCV_ISA_EXT_ZICCRSE		91
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
@@ -101,8 +106,10 @@
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
+#define RISCV_ISA_EXT_SUPM		RISCV_ISA_EXT_SMNPM
 #else
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SSAIA
+#define RISCV_ISA_EXT_SUPM		RISCV_ISA_EXT_SSNPM
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index ffb9484531af..1ce1df6d0ff3 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 9
+#define RISCV_HWPROBE_MAX_KEY 10
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index c9e03e9da3dc..1cc90465d75b 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -26,8 +26,15 @@ typedef struct {
 	unsigned long exec_fdpic_loadmap;
 	unsigned long interp_fdpic_loadmap;
 #endif
+	unsigned long flags;
+#ifdef CONFIG_RISCV_ISA_SUPM
+	u8 pmlen;
+#endif
 } mm_context_t;
 
+/* Lock the pointer masking mode because this mm is multithreaded */
+#define MM_CONTEXT_LOCK_PMLEN	0
+
 #define cntx2asid(cntx)		((cntx) & SATP_ASID_MASK)
 #define cntx2version(cntx)	((cntx) & ~SATP_ASID_MASK)
 
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index 7030837adc1a..8c4bc49a3a0f 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -20,6 +20,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 static inline void activate_mm(struct mm_struct *prev,
 			       struct mm_struct *next)
 {
+#ifdef CONFIG_RISCV_ISA_SUPM
+	next->context.pmlen = 0;
+#endif
 	switch_mm(prev, next, NULL);
 }
 
@@ -30,11 +33,21 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_MMU
 	atomic_long_set(&mm->context.id, 0);
 #endif
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+		clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags);
 	return 0;
 }
 
 DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+	return -1UL >> mm->context.pmlen;
+}
+#endif
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index efa1b3519b23..5f56eb9d114a 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -102,6 +102,7 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
+	unsigned long envcfg;
 	u32 riscv_v_flags;
 	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
@@ -177,6 +178,14 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 #define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2)	riscv_set_icache_flush_ctx(arg1, arg2)
 extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread);
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..e5121b89acea
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_RISCV_SPINLOCK_H
+#define __ASM_RISCV_SPINLOCK_H
+
+#ifdef CONFIG_RISCV_COMBO_SPINLOCKS
+#define _Q_PENDING_LOOPS	(1 << 9)
+
+#define __no_arch_spinlock_redefine
+#include <asm/ticket_spinlock.h>
+#include <asm/qspinlock.h>
+#include <asm/jump_label.h>
+
+/*
+ * TODO: Use an alternative instead of a static key when we are able to parse
+ * the extensions string earlier in the boot process.
+ */
+DECLARE_STATIC_KEY_TRUE(qspinlock_key);
+
+#define SPINLOCK_BASE_DECLARE(op, type, type_lock)			\
+static __always_inline type arch_spin_##op(type_lock lock)		\
+{									\
+	if (static_branch_unlikely(&qspinlock_key))			\
+		return queued_spin_##op(lock);				\
+	return ticket_spin_##op(lock);					\
+}
+
+SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t)
+
+#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS)
+
+#include <asm/qspinlock.h>
+
+#else
+
+#include <asm/ticket_spinlock.h>
+
+#endif
+
+#include <asm/qrwlock.h>
+
+#endif /* __ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 7594df37cc9f..94e33216b2d9 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -70,6 +70,24 @@ static __always_inline bool has_fpu(void) { return false; }
 #define __switch_to_fpu(__prev, __next) do { } while (0)
 #endif
 
+static inline void envcfg_update_bits(struct task_struct *task,
+				      unsigned long mask, unsigned long val)
+{
+	unsigned long envcfg;
+
+	envcfg = (task->thread.envcfg & ~mask) | val;
+	task->thread.envcfg = envcfg;
+	if (task == current)
+		csr_write(CSR_ENVCFG, envcfg);
+}
+
+static inline void __switch_to_envcfg(struct task_struct *next)
+{
+	asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0",
+				  0, RISCV_ISA_EXT_XLINUXENVCFG, 1)
+			:: "r" (next->thread.envcfg) : "memory");
+}
+
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
@@ -103,6 +121,7 @@ do {							\
 		__switch_to_vector(__prev, __next);	\
 	if (switch_to_should_flush_icache(__next))	\
 		local_flush_icache_all();		\
+	__switch_to_envcfg(__next);			\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 72ec1d9bd3f3..fee56b0c8058 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -9,8 +9,41 @@
 #define _ASM_RISCV_UACCESS_H
 
 #include <asm/asm-extable.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>		/* for TASK_SIZE */
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr)
+{
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) {
+		u8 pmlen = mm->context.pmlen;
+
+		/* Virtual addresses are sign-extended; physical addresses are zero-extended. */
+		if (IS_ENABLED(CONFIG_MMU))
+			return (long)(addr << pmlen) >> pmlen;
+		else
+			return (addr << pmlen) >> pmlen;
+	}
+
+	return addr;
+}
+
+#define untagged_addr(addr) ({							\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	(__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr);	\
+})
+
+#define untagged_addr_remote(mm, addr) ({					\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	mmap_assert_locked(mm);							\
+	(__force __typeof__(addr))__untagged_addr_remote(mm, __addr);		\
+})
+
+#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size))
+#else
+#define untagged_addr(addr) (addr)
+#endif
+
 /*
  * User space memory access functions
  */
@@ -130,7 +163,7 @@ do {								\
  */
 #define __get_user(x, ptr)					\
 ({								\
-	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);	\
+	const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	long __gu_err = 0;					\
 								\
 	__chk_user_ptr(__gu_ptr);				\
@@ -246,7 +279,7 @@ do {								\
  */
 #define __put_user(x, ptr)					\
 ({								\
-	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	__typeof__(*__gu_ptr) __val = (x);			\
 	long __pu_err = 0;					\
 								\
@@ -293,13 +326,13 @@ unsigned long __must_check __asm_copy_from_user(void *to,
 static inline unsigned long
 raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	return __asm_copy_from_user(to, from, n);
+	return __asm_copy_from_user(to, untagged_addr(from), n);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	return __asm_copy_to_user(to, from, n);
+	return __asm_copy_to_user(untagged_addr(to), from, n);
 }
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
@@ -314,7 +347,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	might_fault();
 	return access_ok(to, n) ?
-		__clear_user(to, n) : n;
+		__clear_user(untagged_addr(to), n) : n;
 }
 
 #define __get_kernel_nofault(dst, src, type, err_label)			\
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index be7d309cca8a..c7c023afbacd 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -21,6 +21,7 @@
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
+bool insn_is_vector(u32 insn_buf);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
 void kernel_vector_begin(void);
 void kernel_vector_end(void);
@@ -268,6 +269,7 @@ 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 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; }
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 1e153cda57db..3af142b99f77 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -72,6 +72,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZCF		(1ULL << 46)
 #define		RISCV_HWPROBE_EXT_ZCMOP		(1ULL << 47)
 #define		RISCV_HWPROBE_EXT_ZAWRS		(1ULL << 48)
+#define		RISCV_HWPROBE_EXT_SUPM		(1ULL << 49)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -88,6 +89,11 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW		2
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED	4
+#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF	10
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN		0
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW		2
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index e97db3296456..4f24201376b1 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -175,6 +175,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZCF,
 	KVM_RISCV_ISA_EXT_ZCMOP,
 	KVM_RISCV_ISA_EXT_ZAWRS,
+	KVM_RISCV_ISA_EXT_SMNPM,
+	KVM_RISCV_ISA_EXT_SSNPM,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 69dc8aaab3fb..063d1faf5a53 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -75,7 +75,8 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
-obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
+obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)		+= copy-unaligned.o
+obj-$(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)	+= vec-copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h
index e3d70d35b708..85d4d11450cb 100644
--- a/arch/riscv/kernel/copy-unaligned.h
+++ b/arch/riscv/kernel/copy-unaligned.h
@@ -10,4 +10,9 @@
 void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size);
 void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size);
 
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+void __riscv_copy_vec_words_unaligned(void *dst, const void *src, size_t size);
+void __riscv_copy_vec_bytes_unaligned(void *dst, const void *src, size_t size);
+#endif
+
 #endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 826f46b21f2e..467c5c735bf5 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -29,6 +29,8 @@
 
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
+static bool any_cpu_has_zicboz;
+
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -99,6 +101,7 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 		pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n");
 		return -EINVAL;
 	}
+	any_cpu_has_zicboz = true;
 	return 0;
 }
 
@@ -315,6 +318,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 					  riscv_ext_zicbom_validate),
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts,
 					  riscv_ext_zicboz_validate),
+	__RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
@@ -323,6 +327,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zimop, RISCV_ISA_EXT_ZIMOP),
+	__RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
 	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
 	__RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
@@ -375,9 +380,12 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
 	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
+	__RISCV_ISA_EXT_DATA(smmpm, RISCV_ISA_EXT_SMMPM),
+	__RISCV_ISA_EXT_SUPERSET(smnpm, RISCV_ISA_EXT_SMNPM, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_SUPERSET(ssnpm, RISCV_ISA_EXT_SSNPM, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
@@ -918,10 +926,12 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-void riscv_user_isa_enable(void)
+void __init riscv_user_isa_enable(void)
 {
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
-		csr_set(CSR_ENVCFG, ENVCFG_CBZE);
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ))
+		current->thread.envcfg |= ENVCFG_CBZE;
+	else if (any_cpu_has_zicboz)
+		pr_warn("Zicboz disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index 327cf527dd7e..f74f6b60e347 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -170,7 +170,7 @@ SYM_FUNC_END(__fstate_restore)
 	__access_func(f31)
 
 
-#ifdef CONFIG_RISCV_MISALIGNED
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
 
 /*
  * Disable compressed instructions set to keep a constant offset between FP
@@ -224,4 +224,4 @@ SYM_FUNC_START(get_f64_reg)
 	fp_access_epilogue
 SYM_FUNC_END(get_f64_reg)
 
-#endif /* CONFIG_RISCV_MISALIGNED */
+#endif /* CONFIG_RISCV_SCALAR_MISALIGNED */
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index e3142d8a6e28..58b6482c2bf6 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/bitfield.h>
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -180,6 +181,10 @@ void flush_thread(void)
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
 	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		envcfg_update_bits(current, ENVCFG_PMM, ENVCFG_PMM_PMLEN_0);
+#endif
 }
 
 void arch_release_task_struct(struct task_struct *tsk)
@@ -208,6 +213,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
+	/* Ensure all threads in this mm have the same pointer masking mode. */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM) && p->mm && (clone_flags & CLONE_VM))
+		set_bit(MM_CONTEXT_LOCK_PMLEN, &p->mm->context.flags);
+
 	memset(&p->thread.s, 0, sizeof(p->thread.s));
 
 	/* p->thread holds context to be restored by __switch_to() */
@@ -242,3 +251,148 @@ void __init arch_task_cache_init(void)
 {
 	riscv_v_setup_ctx_cache();
 }
+
+#ifdef CONFIG_RISCV_ISA_SUPM
+enum {
+	PMLEN_0 = 0,
+	PMLEN_7 = 7,
+	PMLEN_16 = 16,
+};
+
+static bool have_user_pmlen_7;
+static bool have_user_pmlen_16;
+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
+{
+	unsigned long valid_mask = PR_PMLEN_MASK | PR_TAGGED_ADDR_ENABLE;
+	struct thread_info *ti = task_thread_info(task);
+	struct mm_struct *mm = task->mm;
+	unsigned long pmm;
+	u8 pmlen;
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	if (arg & ~valid_mask)
+		return -EINVAL;
+
+	/*
+	 * Prefer the smallest PMLEN that satisfies the user's request,
+	 * in case choosing a larger PMLEN has a performance impact.
+	 */
+	pmlen = FIELD_GET(PR_PMLEN_MASK, arg);
+	if (pmlen == PMLEN_0) {
+		pmm = ENVCFG_PMM_PMLEN_0;
+	} else if (pmlen <= PMLEN_7 && have_user_pmlen_7) {
+		pmlen = PMLEN_7;
+		pmm = ENVCFG_PMM_PMLEN_7;
+	} else if (pmlen <= PMLEN_16 && have_user_pmlen_16) {
+		pmlen = PMLEN_16;
+		pmm = ENVCFG_PMM_PMLEN_16;
+	} else {
+		return -EINVAL;
+	}
+
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled, if pointer masking
+	 * is disabled for userspace.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen))
+		return -EINVAL;
+
+	if (!(arg & PR_TAGGED_ADDR_ENABLE))
+		pmlen = PMLEN_0;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	if (test_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags) && mm->context.pmlen != pmlen) {
+		mmap_write_unlock(mm);
+		return -EBUSY;
+	}
+
+	envcfg_update_bits(task, ENVCFG_PMM, pmm);
+	mm->context.pmlen = pmlen;
+
+	mmap_write_unlock(mm);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(struct task_struct *task)
+{
+	struct thread_info *ti = task_thread_info(task);
+	long ret = 0;
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	/*
+	 * The mm context's pmlen is set only when the tagged address ABI is
+	 * enabled, so the effective PMLEN must be extracted from envcfg.PMM.
+	 */
+	switch (task->thread.envcfg & ENVCFG_PMM) {
+	case ENVCFG_PMM_PMLEN_7:
+		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7);
+		break;
+	case ENVCFG_PMM_PMLEN_16:
+		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_16);
+		break;
+	}
+
+	if (task->mm->context.pmlen)
+		ret |= PR_TAGGED_ADDR_ENABLE;
+
+	return ret;
+}
+
+static bool try_to_set_pmm(unsigned long value)
+{
+	csr_set(CSR_ENVCFG, value);
+	return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return 0;
+
+	/*
+	 * envcfg.PMM is a WARL field. Detect which values are supported.
+	 * Assume the supported PMLEN values are the same on all harts.
+	 */
+	csr_clear(CSR_ENVCFG, ENVCFG_PMM);
+	have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7);
+	have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16);
+
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+
+	return 0;
+}
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_RISCV_ISA_SUPM */
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 92731ff8c79a..ea67e9fb7a58 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -28,6 +28,9 @@ enum riscv_regset {
 #ifdef CONFIG_RISCV_ISA_V
 	REGSET_V,
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	REGSET_TAGGED_ADDR_CTRL,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -152,6 +155,35 @@ static int riscv_vr_set(struct task_struct *target,
 }
 #endif
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+static int tagged_addr_ctrl_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	long ctrl = get_tagged_addr_ctrl(target);
+
+	if (IS_ERR_VALUE(ctrl))
+		return ctrl;
+
+	return membuf_write(&to, &ctrl, sizeof(ctrl));
+}
+
+static int tagged_addr_ctrl_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	long ctrl;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
+	if (ret)
+		return ret;
+
+	return set_tagged_addr_ctrl(target, ctrl);
+}
+#endif
+
 static const struct user_regset riscv_user_regset[] = {
 	[REGSET_X] = {
 		.core_note_type = NT_PRSTATUS,
@@ -182,6 +214,16 @@ static const struct user_regset riscv_user_regset[] = {
 		.set = riscv_vr_set,
 	},
 #endif
+#ifdef CONFIG_RISCV_ISA_SUPM
+	[REGSET_TAGGED_ADDR_CTRL] = {
+		.core_note_type = NT_RISCV_TAGGED_ADDR_CTRL,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.regset_get = tagged_addr_ctrl_get,
+		.set = tagged_addr_ctrl_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 26c886db4fb3..016b48fcd6f2 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -244,6 +244,42 @@ static void __init parse_dtb(void)
 #endif
 }
 
+#if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
+DEFINE_STATIC_KEY_TRUE(qspinlock_key);
+EXPORT_SYMBOL(qspinlock_key);
+#endif
+
+static void __init riscv_spinlock_init(void)
+{
+	char *using_ext = NULL;
+
+	if (IS_ENABLED(CONFIG_RISCV_TICKET_SPINLOCKS)) {
+		pr_info("Ticket spinlock: enabled\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&
+	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&
+	    riscv_isa_extension_available(NULL, ZABHA) &&
+	    riscv_isa_extension_available(NULL, ZACAS)) {
+		using_ext = "using Zabha";
+	} else if (riscv_isa_extension_available(NULL, ZICCRSE)) {
+		using_ext = "using Ziccrse";
+	}
+#if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
+	else {
+		static_branch_disable(&qspinlock_key);
+		pr_info("Ticket spinlock: enabled\n");
+		return;
+	}
+#endif
+
+	if (!using_ext)
+		pr_err("Queued spinlock without Zabha or Ziccrse");
+	else
+		pr_info("Queued spinlock %s: enabled\n", using_ext);
+}
+
 extern void __init init_rt_signal_env(void);
 
 void __init setup_arch(char **cmdline_p)
@@ -297,6 +333,7 @@ void __init setup_arch(char **cmdline_p)
 	riscv_set_dma_cache_alignment();
 
 	riscv_user_isa_enable();
+	riscv_spinlock_init();
 }
 
 bool arch_cpu_is_hotpluggable(int cpu)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 0f8f1c95ac38..e36d20205bd7 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -233,8 +233,6 @@ asmlinkage __visible void smp_callin(void)
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, true);
 
-	riscv_user_isa_enable();
-
 	/*
 	 * Remote cache and TLB flushes are ignored while the CPU is offline,
 	 * so flush them both right now just in case.
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index c8cec0cc5833..9a8a0dc035b2 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -14,7 +14,7 @@
 
 void suspend_save_csrs(struct suspend_context *context)
 {
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG))
 		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
 	context->ie = csr_read(CSR_IE);
@@ -37,7 +37,7 @@ void suspend_save_csrs(struct suspend_context *context)
 void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, 0);
-	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG))
 		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
 	csr_write(CSR_IE, context->ie);
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 711a31f27c3d..cb93adfffc48 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -150,6 +150,9 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZFH);
 			EXT_KEY(ZFHMIN);
 		}
+
+		if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+			EXT_KEY(SUPM);
 #undef EXT_KEY
 	}
 
@@ -201,6 +204,43 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 }
 #endif
 
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	/* Return if supported or not even if speed wasn't probed */
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(vector_misaligned_access, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
+	return perf;
+}
+#else
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+
+	if (IS_ENABLED(CONFIG_RISCV_SLOW_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+
+	return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+}
+#endif
+
 static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 			     const struct cpumask *cpus)
 {
@@ -229,6 +269,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF:
+		pair->value = hwprobe_vec_misaligned(cpus);
+		break;
+
 	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
 		pair->value = 0;
 		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 1b9867136b61..7cc108aed74e 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -16,6 +16,7 @@
 #include <asm/entry-common.h>
 #include <asm/hwprobe.h>
 #include <asm/cpufeature.h>
+#include <asm/vector.h>
 
 #define INSN_MATCH_LB			0x3
 #define INSN_MASK_LB			0x707f
@@ -320,12 +321,37 @@ union reg_data {
 	u64 data_u64;
 };
 
-static bool unaligned_ctl __read_mostly;
-
 /* sysctl hooks */
 int unaligned_enabled __read_mostly = 1;	/* Enabled by default */
 
-int handle_misaligned_load(struct pt_regs *regs)
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+static int handle_vector_misaligned_load(struct pt_regs *regs)
+{
+	unsigned long epc = regs->epc;
+	unsigned long insn;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
+
+	/* Only return 0 when in check_vector_unaligned_access_emulated */
+	if (*this_cpu_ptr(&vector_misaligned_access) == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		*this_cpu_ptr(&vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+		regs->epc = epc + INSN_LEN(insn);
+		return 0;
+	}
+
+	/* If vector instruction we don't emulate it yet */
+	regs->epc = epc;
+	return -1;
+}
+#else
+static int handle_vector_misaligned_load(struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
+
+static int handle_scalar_misaligned_load(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
@@ -433,7 +459,7 @@ int handle_misaligned_load(struct pt_regs *regs)
 	return 0;
 }
 
-int handle_misaligned_store(struct pt_regs *regs)
+static int handle_scalar_misaligned_store(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
@@ -524,11 +550,96 @@ int handle_misaligned_store(struct pt_regs *regs)
 	return 0;
 }
 
-static bool check_unaligned_access_emulated(int cpu)
+int handle_misaligned_load(struct pt_regs *regs)
+{
+	unsigned long epc = regs->epc;
+	unsigned long insn;
+
+	if (IS_ENABLED(CONFIG_RISCV_VECTOR_MISALIGNED)) {
+		if (get_insn(regs, epc, &insn))
+			return -1;
+
+		if (insn_is_vector(insn))
+			return handle_vector_misaligned_load(regs);
+	}
+
+	if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED))
+		return handle_scalar_misaligned_load(regs);
+
+	return -1;
+}
+
+int handle_misaligned_store(struct pt_regs *regs)
 {
+	if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED))
+		return handle_scalar_misaligned_store(regs);
+
+	return -1;
+}
+
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused)
+{
+	long *mas_ptr = this_cpu_ptr(&vector_misaligned_access);
+	unsigned long tmp_var;
+
+	*mas_ptr = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
+	kernel_vector_begin();
+	/*
+	 * In pre-13.0.0 versions of GCC, vector registers cannot appear in
+	 * the clobber list. This inline asm clobbers v0, but since we do not
+	 * currently build the kernel with V enabled, the v0 clobber arg is not
+	 * needed (as the compiler will not emit vector code itself). If the kernel
+	 * is changed to build with V enabled, the clobber arg will need to be
+	 * added here.
+	 */
+	__asm__ __volatile__ (
+		".balign 4\n\t"
+		".option push\n\t"
+		".option arch, +zve32x\n\t"
+		"       vsetivli zero, 1, e16, m1, ta, ma\n\t"	// Vectors of 16b
+		"       vle16.v v0, (%[ptr])\n\t"		// Load bytes
+		".option pop\n\t"
+		: : [ptr] "r" ((u8 *)&tmp_var + 1));
+	kernel_vector_end();
+}
+
+bool check_vector_unaligned_access_emulated_all_cpus(void)
+{
+	int cpu;
+
+	if (!has_vector()) {
+		for_each_online_cpu(cpu)
+			per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+		return false;
+	}
+
+	schedule_on_each_cpu(check_vector_unaligned_access_emulated);
+
+	for_each_online_cpu(cpu)
+		if (per_cpu(vector_misaligned_access, cpu)
+		    == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
+			return false;
+
+	return true;
+}
+#else
+bool check_vector_unaligned_access_emulated_all_cpus(void)
+{
+	return false;
+}
+#endif
+
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
+
+static bool unaligned_ctl __read_mostly;
+
+void check_unaligned_access_emulated(struct work_struct *work __always_unused)
+{
+	int cpu = smp_processor_id();
 	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
 	unsigned long tmp_var, tmp_val;
-	bool misaligned_emu_detected;
 
 	*mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 
@@ -536,19 +647,16 @@ static bool check_unaligned_access_emulated(int cpu)
 		"       "REG_L" %[tmp], 1(%[ptr])\n"
 		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
 
-	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED);
 	/*
 	 * If unaligned_ctl is already set, this means that we detected that all
 	 * CPUS uses emulated misaligned access at boot time. If that changed
 	 * when hotplugging the new cpu, this is something we don't handle.
 	 */
-	if (unlikely(unaligned_ctl && !misaligned_emu_detected)) {
+	if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) {
 		pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n");
 		while (true)
 			cpu_relax();
 	}
-
-	return misaligned_emu_detected;
 }
 
 bool check_unaligned_access_emulated_all_cpus(void)
@@ -560,8 +668,11 @@ bool check_unaligned_access_emulated_all_cpus(void)
 	 * accesses emulated since tasks requesting such control can run on any
 	 * CPU.
 	 */
+	schedule_on_each_cpu(check_unaligned_access_emulated);
+
 	for_each_online_cpu(cpu)
-		if (!check_unaligned_access_emulated(cpu))
+		if (per_cpu(misaligned_access_speed, cpu)
+		    != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED)
 			return false;
 
 	unaligned_ctl = true;
@@ -572,3 +683,9 @@ bool unaligned_ctl_available(void)
 {
 	return unaligned_ctl;
 }
+#else
+bool check_unaligned_access_emulated_all_cpus(void)
+{
+	return false;
+}
+#endif
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 160628a2116d..91f189cf1611 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -6,11 +6,13 @@
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/jump_label.h>
+#include <linux/kthread.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/types.h>
 #include <asm/cpufeature.h>
 #include <asm/hwprobe.h>
+#include <asm/vector.h>
 
 #include "copy-unaligned.h"
 
@@ -19,7 +21,8 @@
 #define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
 #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
 
-DEFINE_PER_CPU(long, misaligned_access_speed);
+DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
+DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
 #ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
 static cpumask_t fast_misaligned_access;
@@ -191,6 +194,7 @@ static int riscv_online_cpu(unsigned int cpu)
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
 		goto exit;
 
+	check_unaligned_access_emulated(NULL);
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
 		pr_warn("Allocation failure, not measuring misaligned performance\n");
@@ -259,23 +263,159 @@ out:
 	kfree(bufs);
 	return 0;
 }
+#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
+static int check_unaligned_access_speed_all_cpus(void)
+{
+	return 0;
+}
+#endif
 
-static int check_unaligned_access_all_cpus(void)
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+static void check_vector_unaligned_access(struct work_struct *work __always_unused)
 {
-	bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+	int cpu = smp_processor_id();
+	u64 start_cycles, end_cycles;
+	u64 word_cycles;
+	u64 byte_cycles;
+	int ratio;
+	unsigned long start_jiffies, now;
+	struct page *page;
+	void *dst;
+	void *src;
+	long speed = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
 
-	if (!all_cpus_emulated)
-		return check_unaligned_access_speed_all_cpus();
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
+		return;
+
+	page = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+	if (!page) {
+		pr_warn("Allocation failure, not measuring vector misaligned performance\n");
+		return;
+	}
+
+	/* Make an unaligned destination buffer. */
+	dst = (void *)((unsigned long)page_address(page) | 0x1);
+	/* Unalign src as well, but differently (off by 1 + 2 = 3). */
+	src = dst + (MISALIGNED_BUFFER_SIZE / 2);
+	src += 2;
+	word_cycles = -1ULL;
+
+	/* Do a warmup. */
+	kernel_vector_begin();
+	__riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
 
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	/*
+	 * For a fixed amount of time, repeatedly try the function, and take
+	 * the best time in cycles as the measurement.
+	 */
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < word_cycles)
+			word_cycles = end_cycles - start_cycles;
+	}
+
+	byte_cycles = -1ULL;
+	__riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < byte_cycles)
+			byte_cycles = end_cycles - start_cycles;
+	}
+
+	kernel_vector_end();
+
+	/* Don't divide by zero. */
+	if (!word_cycles || !byte_cycles) {
+		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n",
+			cpu);
+
+		return;
+	}
+
+	if (word_cycles < byte_cycles)
+		speed = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+
+	ratio = div_u64((byte_cycles * 100), word_cycles);
+	pr_info("cpu%d: Ratio of vector byte access time to vector unaligned word access is %d.%02d, unaligned accesses are %s\n",
+		cpu,
+		ratio / 100,
+		ratio % 100,
+		(speed ==  RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow");
+
+	per_cpu(vector_misaligned_access, cpu) = speed;
+}
+
+static int riscv_online_cpu_vec(unsigned int cpu)
+{
+	if (!has_vector())
+		return 0;
+
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED)
+		return 0;
+
+	check_vector_unaligned_access_emulated(NULL);
+	check_vector_unaligned_access(NULL);
 	return 0;
 }
-#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
-static int check_unaligned_access_all_cpus(void)
+
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
 {
-	check_unaligned_access_emulated_all_cpus();
+	schedule_on_each_cpu(check_vector_unaligned_access);
+
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu_vec, NULL);
 
 	return 0;
 }
+#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	return 0;
+}
 #endif
 
+static int check_unaligned_access_all_cpus(void)
+{
+	bool all_cpus_emulated, all_cpus_vec_unsupported;
+
+	all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+	all_cpus_vec_unsupported = check_vector_unaligned_access_emulated_all_cpus();
+
+	if (!all_cpus_vec_unsupported &&
+	    IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+		kthread_run(vec_check_unaligned_access_speed_all_cpus,
+			    NULL, "vec_check_unaligned_access_speed_all_cpus");
+	}
+
+	if (!all_cpus_emulated)
+		return check_unaligned_access_speed_all_cpus();
+
+	return 0;
+}
+
 arch_initcall(check_unaligned_access_all_cpus);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 3f1c4b2d0b06..9a1b555e8733 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -45,7 +45,7 @@ $(obj)/vdso.o: $(obj)/vdso.so
 
 # link rule for the .so file, .lds has to be first
 $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
-	$(call if_changed,vdsold)
+	$(call if_changed,vdsold_and_check)
 LDFLAGS_vdso.so.dbg = -shared -soname=linux-vdso.so.1 \
 	--build-id=sha1 --hash-style=both --eh-frame-hdr
 
@@ -65,7 +65,8 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 # actual build commands
 # The DSO images are built using a special linker script
 # Make sure only to export the intended __vdso_xxx symbol offsets.
-quiet_cmd_vdsold = VDSOLD  $@
-      cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+quiet_cmd_vdsold_and_check = VDSOLD  $@
+      cmd_vdsold_and_check = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
                    $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
-                   rm $@.tmp
+                   rm $@.tmp && \
+                   $(cmd_vdso_check)
diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S
new file mode 100644
index 000000000000..d16f19f1b3b6
--- /dev/null
+++ b/arch/riscv/kernel/vec-copy-unaligned.S
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2024 Rivos Inc. */
+
+#include <linux/args.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+	.text
+
+#define WORD_EEW 32
+
+#define WORD_SEW CONCATENATE(e, WORD_EEW)
+#define VEC_L CONCATENATE(vle, WORD_EEW).v
+#define VEC_S CONCATENATE(vle, WORD_EEW).v
+
+/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using word loads and stores. */
+/* Note: The size is truncated to a multiple of WORD_EEW */
+SYM_FUNC_START(__riscv_copy_vec_words_unaligned)
+	andi  a4, a2, ~(WORD_EEW-1)
+	beqz  a4, 2f
+	add   a3, a1, a4
+	.option push
+	.option arch, +zve32x
+1:
+	vsetivli t0, 8, WORD_SEW, m8, ta, ma
+	VEC_L v0, (a1)
+	VEC_S v0, (a0)
+	addi  a0, a0, WORD_EEW
+	addi  a1, a1, WORD_EEW
+	bltu  a1, a3, 1b
+
+2:
+	.option pop
+	ret
+SYM_FUNC_END(__riscv_copy_vec_words_unaligned)
+
+/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */
+/* Performs a memcpy without aligning buffers, using only byte accesses. */
+/* Note: The size is truncated to a multiple of 8 */
+SYM_FUNC_START(__riscv_copy_vec_bytes_unaligned)
+	andi a4, a2, ~(8-1)
+	beqz a4, 2f
+	add  a3, a1, a4
+	.option push
+	.option arch, +zve32x
+1:
+	vsetivli t0, 8, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vse8.v v0, (a0)
+	addi a0, a0, 8
+	addi a1, a1, 8
+	bltu a1, a3, 1b
+
+2:
+	.option pop
+	ret
+SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned)
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 682b3feee451..821818886fab 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -66,7 +66,7 @@ void __init riscv_v_setup_ctx_cache(void)
 #endif
 }
 
-static bool insn_is_vector(u32 insn_buf)
+bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
 	u32 width, csr;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index b319c4c13c54..5b68490ad9b7 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -34,9 +34,11 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	[KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m,
 	[KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v,
 	/* Multi letter extensions (alphabetically sorted) */
+	[KVM_RISCV_ISA_EXT_SMNPM] = RISCV_ISA_EXT_SSNPM,
 	KVM_ISA_EXT_ARR(SMSTATEEN),
 	KVM_ISA_EXT_ARR(SSAIA),
 	KVM_ISA_EXT_ARR(SSCOFPMF),
+	KVM_ISA_EXT_ARR(SSNPM),
 	KVM_ISA_EXT_ARR(SSTC),
 	KVM_ISA_EXT_ARR(SVINVAL),
 	KVM_ISA_EXT_ARR(SVNAPOT),
@@ -127,8 +129,10 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_C:
 	case KVM_RISCV_ISA_EXT_I:
 	case KVM_RISCV_ISA_EXT_M:
+	case KVM_RISCV_ISA_EXT_SMNPM:
 	/* There is not architectural config bit to disable sscofpmf completely */
 	case KVM_RISCV_ISA_EXT_SSCOFPMF:
+	case KVM_RISCV_ISA_EXT_SSNPM:
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT: