Merge tag 'riscv-for-linus-6.6-mw2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - The kernel now dynamically probes for misaligned access speed, as
   opposed to relying on a table of known implementations.

 - Support for non-coherent devices on systems using the Andes AX45MP
   core, including the RZ/Five SoCs.

 - Support for the V extension in ptrace(), again.

 - Support for KASLR.

 - Support for the BPF prog pack allocator in RISC-V.

 - A handful of bug fixes and cleanups.

* tag 'riscv-for-linus-6.6-mw2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (25 commits)
  soc: renesas: Kconfig: For ARCH_R9A07G043 select the required configs if dependencies are met
  riscv: Kconfig.errata: Add dependency for RISCV_SBI in ERRATA_ANDES config
  riscv: Kconfig.errata: Drop dependency for MMU in ERRATA_ANDES_CMO config
  riscv: Kconfig: Select DMA_DIRECT_REMAP only if MMU is enabled
  bpf, riscv: use prog pack allocator in the BPF JIT
  riscv: implement a memset like function for text
  riscv: extend patch_text_nosync() for multiple pages
  bpf: make bpf_prog_pack allocator portable
  riscv: libstub: Implement KASLR by using generic functions
  libstub: Fix compilation warning for rv32
  arm64: libstub: Move KASLR handling functions to kaslr.c
  riscv: Dump out kernel offset information on panic
  riscv: Introduce virtual kernel mapping KASLR
  RISC-V: Add ptrace support for vectors
  soc: renesas: Kconfig: Select the required configs for RZ/Five SoC
  cache: Add L2 cache management for Andes AX45MP RISC-V core
  dt-bindings: cache: andestech,ax45mp-cache: Add DT binding documentation for L2 cache controller
  riscv: mm: dma-noncoherent: nonstandard cache operations support
  riscv: errata: Add Andes alternative ports
  riscv: asm: vendorid_list: Add Andes Technology to the vendors list
  ...

35 files changed, 909 insertions, 82 deletions

diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index f482b994c608..bcd5622aa096 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -156,4 +156,6 @@ static inline void efi_capsule_flush_cache_range(void *addr, int size)
 
 efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f);
 
+void efi_icache_sync(unsigned long start, unsigned long end);
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 5138dce1a0b4..d607ab0f7c6d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -273,7 +273,14 @@ config RISCV_DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB
-	select DMA_DIRECT_REMAP
+	select DMA_DIRECT_REMAP if MMU
+
+config RISCV_NONSTANDARD_CACHE_OPS
+	bool
+	depends on RISCV_DMA_NONCOHERENT
+	help
+	  This enables function pointer support for non-standard noncoherent
+	  systems to handle cache management.
 
 config AS_HAS_INSN
 	def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero)
@@ -713,6 +720,25 @@ config RELOCATABLE
 
           If unsure, say N.
 
+config RANDOMIZE_BASE
+        bool "Randomize the address of the kernel image"
+        select RELOCATABLE
+        depends on MMU && 64BIT && !XIP_KERNEL
+        help
+          Randomizes the virtual address at which the kernel image is
+          loaded, as a security feature that deters exploit attempts
+          relying on knowledge of the location of kernel internals.
+
+          It is the bootloader's job to provide entropy, by passing a
+          random u64 value in /chosen/kaslr-seed at kernel entry.
+
+          When booting via the UEFI stub, it will invoke the firmware's
+          EFI_RNG_PROTOCOL implementation (if available) to supply entropy
+          to the kernel proper. In addition, it will randomise the physical
+          location of the kernel Image as well.
+
+          If unsure, say N.
+
 endmenu # "Kernel features"
 
 menu "Boot options"
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 0c8f4652cd82..566bcefeab50 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -1,5 +1,26 @@
 menu "CPU errata selection"
 
+config ERRATA_ANDES
+	bool "Andes AX45MP errata"
+	depends on RISCV_ALTERNATIVE && RISCV_SBI
+	help
+	  All Andes errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all Andes errata. Please say "Y"
+	  here if your platform uses Andes CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_ANDES_CMO
+	bool "Apply Andes cache management errata"
+	depends on ERRATA_ANDES && ARCH_R9A07G043
+	select RISCV_DMA_NONCOHERENT
+	default y
+	help
+	  This will apply the cache management errata to handle the
+	  non-standard handling on non-coherent operations on Andes cores.
+
+	  If you don't know what to do here, say "Y".
+
 config ERRATA_SIFIVE
 	bool "SiFive errata"
 	depends on RISCV_ALTERNATIVE
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 7b2637c8c332..8a2739485123 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -2,5 +2,6 @@ ifdef CONFIG_RELOCATABLE
 KBUILD_CFLAGS += -fno-pie
 endif
 
+obj-$(CONFIG_ERRATA_ANDES) += andes/
 obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
 obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile
new file mode 100644
index 000000000000..2d644e19caef
--- /dev/null
+++ b/arch/riscv/errata/andes/Makefile
@@ -0,0 +1 @@
+obj-y += errata.o
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
new file mode 100644
index 000000000000..197db68cc8da
--- /dev/null
+++ b/arch/riscv/errata/andes/errata.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Erratas to be applied for Andes CPU cores
+ *
+ *  Copyright (C) 2023 Renesas Electronics Corporation.
+ *
+ * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+ */
+
+#include <linux/memory.h>
+#include <linux/module.h>
+
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/patch.h>
+#include <asm/processor.h>
+#include <asm/sbi.h>
+#include <asm/vendorid_list.h>
+
+#define ANDESTECH_AX45MP_MARCHID	0x8000000000008a45UL
+#define ANDESTECH_AX45MP_MIMPID		0x500UL
+#define ANDESTECH_SBI_EXT_ANDES		0x0900031E
+
+#define ANDES_SBI_EXT_IOCP_SW_WORKAROUND	1
+
+static long ax45mp_iocp_sw_workaround(void)
+{
+	struct sbiret ret;
+
+	/*
+	 * ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI EXT checks if the IOCP is missing and
+	 * cache is controllable only then CMO will be applied to the platform.
+	 */
+	ret = sbi_ecall(ANDESTECH_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND,
+			0, 0, 0, 0, 0, 0);
+
+	return ret.error ? 0 : ret.value;
+}
+
+static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO))
+		return false;
+
+	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
+		return false;
+
+	if (!ax45mp_iocp_sw_workaround())
+		return false;
+
+	/* Set this just to make core cbo code happy */
+	riscv_cbom_block_size = 1;
+	riscv_noncoherent_supported();
+
+	return true;
+}
+
+void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+					      unsigned long archid, unsigned long impid,
+					      unsigned int stage)
+{
+	errata_probe_iocp(stage, archid, impid);
+
+	/* we have nothing to patch here ATM so just return back */
+}
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index be84b14f0118..0554ed4bf087 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -120,11 +120,3 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		local_flush_icache_all();
 }
-
-void thead_feature_probe_func(unsigned int cpu,
-			      unsigned long archid,
-			      unsigned long impid)
-{
-	if ((archid == 0) && (impid == 0))
-		per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_FAST;
-}
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 6a41537826a7..3c2b59b25017 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -30,7 +30,6 @@
 #define ALT_OLD_PTR(a)			__ALT_PTR(a, old_offset)
 #define ALT_ALT_PTR(a)			__ALT_PTR(a, alt_offset)
 
-void probe_vendor_features(unsigned int cpu);
 void __init apply_boot_alternatives(void);
 void __init apply_early_boot_alternatives(void);
 void apply_module_alternatives(void *start, size_t length);
@@ -46,6 +45,9 @@ struct alt_entry {
 	u32 patch_id;		/* The patch ID (erratum ID or cpufeature ID) */
 };
 
+void andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage);
 void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			      unsigned long archid, unsigned long impid,
 			      unsigned int stage);
@@ -53,15 +55,11 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			     unsigned long archid, unsigned long impid,
 			     unsigned int stage);
 
-void thead_feature_probe_func(unsigned int cpu, unsigned long archid,
-			      unsigned long impid);
-
 void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
 				 unsigned int stage);
 
 #else /* CONFIG_RISCV_ALTERNATIVE */
 
-static inline void probe_vendor_features(unsigned int cpu) { }
 static inline void apply_boot_alternatives(void) { }
 static inline void apply_early_boot_alternatives(void) { }
 static inline void apply_module_alternatives(void *start, size_t length) { }
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 23fed53b8815..d0345bd659c9 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -30,4 +30,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
+void check_unaligned_access(int cpu);
+
 #endif
diff --git a/arch/riscv/include/asm/dma-noncoherent.h b/arch/riscv/include/asm/dma-noncoherent.h
new file mode 100644
index 000000000000..312cfa0858fb
--- /dev/null
+++ b/arch/riscv/include/asm/dma-noncoherent.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#ifndef __ASM_DMA_NONCOHERENT_H
+#define __ASM_DMA_NONCOHERENT_H
+
+#include <linux/dma-direct.h>
+
+/*
+ * struct riscv_nonstd_cache_ops - Structure for non-standard CMO function pointers
+ *
+ * @wback: Function pointer for cache writeback
+ * @inv: Function pointer for invalidating cache
+ * @wback_inv: Function pointer for flushing the cache (writeback + invalidating)
+ */
+struct riscv_nonstd_cache_ops {
+	void (*wback)(phys_addr_t paddr, size_t size);
+	void (*inv)(phys_addr_t paddr, size_t size);
+	void (*wback_inv)(phys_addr_t paddr, size_t size);
+};
+
+extern struct riscv_nonstd_cache_ops noncoherent_cache_ops;
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops);
+
+#endif	/* __ASM_DMA_NONCOHERENT_H */
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index 8a6a128ec57f..46a355913b27 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -45,4 +45,6 @@ void arch_efi_call_virt_teardown(void);
 
 unsigned long stext_offset(void);
 
+void efi_icache_sync(unsigned long start, unsigned long end);
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index fb1a810f3d8c..e2ecd01bfac7 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -11,6 +11,11 @@
 #include <asm/hwcap.h>
 #include <asm/vendorid_list.h>
 
+#ifdef CONFIG_ERRATA_ANDES
+#define ERRATA_ANDESTECH_NO_IOCP	0
+#define ERRATA_ANDESTECH_NUMBER		1
+#endif
+
 #ifdef CONFIG_ERRATA_SIFIVE
 #define	ERRATA_SIFIVE_CIP_453 0
 #define	ERRATA_SIFIVE_CIP_1200 1
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index b55ba20903ec..5488ecc337b6 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -106,6 +106,7 @@ typedef struct page *pgtable_t;
 struct kernel_mapping {
 	unsigned long page_offset;
 	unsigned long virt_addr;
+	unsigned long virt_offset;
 	uintptr_t phys_addr;
 	uintptr_t size;
 	/* Offset between linear mapping virtual address and kernel load address */
@@ -185,6 +186,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 
 #define sym_to_pfn(x)           __phys_to_pfn(__pa_symbol(x))
 
+unsigned long kaslr_offset(void);
+
 #endif /* __ASSEMBLY__ */
 
 #define virt_addr_valid(vaddr)	({						\
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h
index 63c98833d510..e88b52d39eac 100644
--- a/arch/riscv/include/asm/patch.h
+++ b/arch/riscv/include/asm/patch.h
@@ -7,6 +7,7 @@
 #define _ASM_RISCV_PATCH_H
 
 int patch_text_nosync(void *addr, const void *insns, size_t len);
+int patch_text_set_nosync(void *addr, u8 c, size_t len);
 int patch_text(void *addr, u32 *insns, int ninsns);
 
 extern int riscv_patch_in_stop_machine;
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index cb89af3f0704..e55407ace0c3 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -5,6 +5,7 @@
 #ifndef ASM_VENDOR_LIST_H
 #define ASM_VENDOR_LIST_H
 
+#define ANDESTECH_VENDOR_ID	0x31e
 #define SIFIVE_VENDOR_ID	0x489
 #define THEAD_VENDOR_ID		0x5b7
 
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 6d2d9afaabea..a38268b19c3d 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -108,13 +108,18 @@ struct __riscv_v_ext_state {
 	 * In signal handler, datap will be set a correct user stack offset
 	 * and vector registers will be copied to the address of datap
 	 * pointer.
-	 *
-	 * In ptrace syscall, datap will be set to zero and the vector
-	 * registers will be copied to the address right after this
-	 * structure.
 	 */
 };
 
+struct __riscv_v_regset_state {
+	unsigned long vstart;
+	unsigned long vl;
+	unsigned long vtype;
+	unsigned long vcsr;
+	unsigned long vlenb;
+	char vreg[];
+};
+
 /*
  * According to spec: The number of bits in a single vector register,
  * VLEN >= ELEN, which must be a power of 2, and must be no greater than
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 6ac56af42f4a..95cf25d48405 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -38,6 +38,7 @@ extra-y += vmlinux.lds
 obj-y	+= head.o
 obj-y	+= soc.o
 obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o
+obj-y	+= copy-unaligned.o
 obj-y	+= cpu.o
 obj-y	+= cpufeature.o
 obj-y	+= entry.o
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 6b75788c18e6..319a1da0358b 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -27,8 +27,6 @@ struct cpu_manufacturer_info_t {
 	void (*patch_func)(struct alt_entry *begin, struct alt_entry *end,
 				  unsigned long archid, unsigned long impid,
 				  unsigned int stage);
-	void (*feature_probe_func)(unsigned int cpu, unsigned long archid,
-				   unsigned long impid);
 };
 
 static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info)
@@ -43,8 +41,12 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 	cpu_mfr_info->imp_id = sbi_get_mimpid();
 #endif
 
-	cpu_mfr_info->feature_probe_func = NULL;
 	switch (cpu_mfr_info->vendor_id) {
+#ifdef CONFIG_ERRATA_ANDES
+	case ANDESTECH_VENDOR_ID:
+		cpu_mfr_info->patch_func = andes_errata_patch_func;
+		break;
+#endif
 #ifdef CONFIG_ERRATA_SIFIVE
 	case SIFIVE_VENDOR_ID:
 		cpu_mfr_info->patch_func = sifive_errata_patch_func;
@@ -53,7 +55,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 #ifdef CONFIG_ERRATA_THEAD
 	case THEAD_VENDOR_ID:
 		cpu_mfr_info->patch_func = thead_errata_patch_func;
-		cpu_mfr_info->feature_probe_func = thead_feature_probe_func;
 		break;
 #endif
 	default:
@@ -143,20 +144,6 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len,
 	}
 }
 
-/* Called on each CPU as it starts */
-void probe_vendor_features(unsigned int cpu)
-{
-	struct cpu_manufacturer_info_t cpu_mfr_info;
-
-	riscv_fill_cpu_mfr_info(&cpu_mfr_info);
-	if (!cpu_mfr_info.feature_probe_func)
-		return;
-
-	cpu_mfr_info.feature_probe_func(cpu,
-					cpu_mfr_info.arch_id,
-					cpu_mfr_info.imp_id);
-}
-
 /*
  * This is called very early in the boot process (directly after we run
  * a feature detect on the boot CPU). No need to worry about other CPUs
@@ -211,7 +198,6 @@ void __init apply_boot_alternatives(void)
 	/* If called on non-boot cpu things could go wrong */
 	WARN_ON(smp_processor_id() != 0);
 
-	probe_vendor_features(0);
 	_apply_alternatives((struct alt_entry *)__alt_start,
 			    (struct alt_entry *)__alt_end,
 			    RISCV_ALTERNATIVES_BOOT);
diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S
new file mode 100644
index 000000000000..cfdecfbaad62
--- /dev/null
+++ b/arch/riscv/kernel/copy-unaligned.S
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2023 Rivos Inc. */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+	.text
+
+/* void __riscv_copy_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 8 * SZREG */
+ENTRY(__riscv_copy_words_unaligned)
+	andi  a4, a2, ~((8*SZREG)-1)
+	beqz  a4, 2f
+	add   a3, a1, a4
+1:
+	REG_L a4,       0(a1)
+	REG_L a5,   SZREG(a1)
+	REG_L a6, 2*SZREG(a1)
+	REG_L a7, 3*SZREG(a1)
+	REG_L t0, 4*SZREG(a1)
+	REG_L t1, 5*SZREG(a1)
+	REG_L t2, 6*SZREG(a1)
+	REG_L t3, 7*SZREG(a1)
+	REG_S a4,       0(a0)
+	REG_S a5,   SZREG(a0)
+	REG_S a6, 2*SZREG(a0)
+	REG_S a7, 3*SZREG(a0)
+	REG_S t0, 4*SZREG(a0)
+	REG_S t1, 5*SZREG(a0)
+	REG_S t2, 6*SZREG(a0)
+	REG_S t3, 7*SZREG(a0)
+	addi  a0, a0, 8*SZREG
+	addi  a1, a1, 8*SZREG
+	bltu  a1, a3, 1b
+
+2:
+	ret
+END(__riscv_copy_words_unaligned)
+
+/* void __riscv_copy_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 */
+ENTRY(__riscv_copy_bytes_unaligned)
+	andi a4, a2, ~(8-1)
+	beqz a4, 2f
+	add  a3, a1, a4
+1:
+	lb   a4, 0(a1)
+	lb   a5, 1(a1)
+	lb   a6, 2(a1)
+	lb   a7, 3(a1)
+	lb   t0, 4(a1)
+	lb   t1, 5(a1)
+	lb   t2, 6(a1)
+	lb   t3, 7(a1)
+	sb   a4, 0(a0)
+	sb   a5, 1(a0)
+	sb   a6, 2(a0)
+	sb   a7, 3(a0)
+	sb   t0, 4(a0)
+	sb   t1, 5(a0)
+	sb   t2, 6(a0)
+	sb   t3, 7(a0)
+	addi a0, a0, 8
+	addi a1, a1, 8
+	bltu a1, a3, 1b
+
+2:
+	ret
+END(__riscv_copy_bytes_unaligned)
diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h
new file mode 100644
index 000000000000..e3d70d35b708
--- /dev/null
+++ b/arch/riscv/kernel/copy-unaligned.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos, Inc.
+ */
+#ifndef __RISCV_KERNEL_COPY_UNALIGNED_H
+#define __RISCV_KERNEL_COPY_UNALIGNED_H
+
+#include <linux/types.h>
+
+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);
+
+#endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index ef7b4fd9e876..1cfbba65d11a 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -18,12 +18,19 @@
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwcap.h>
+#include <asm/hwprobe.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/vector.h>
 
+#include "copy-unaligned.h"
+
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
+#define MISALIGNED_ACCESS_JIFFIES_LG2 1
+#define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
+
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -549,6 +556,103 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
+void check_unaligned_access(int cpu)
+{
+	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_SLOW;
+
+	page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
+	if (!page) {
+		pr_warn("Can't alloc pages to measure memcpy performance");
+		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. */
+	__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	preempt_disable();
+	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_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_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();
+		mb();
+		__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < byte_cycles)
+			byte_cycles = end_cycles - start_cycles;
+	}
+
+	preempt_enable();
+
+	/* Don't divide by zero. */
+	if (!word_cycles || !byte_cycles) {
+		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
+			cpu);
+
+		goto out;
+	}
+
+	if (word_cycles < byte_cycles)
+		speed = RISCV_HWPROBE_MISALIGNED_FAST;
+
+	ratio = div_u64((byte_cycles * 100), word_cycles);
+	pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
+		cpu,
+		ratio / 100,
+		ratio % 100,
+		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
+
+	per_cpu(misaligned_access_speed, cpu) = speed;
+
+out:
+	__free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+}
+
+static int check_unaligned_access_boot_cpu(void)
+{
+	check_unaligned_access(0);
+	return 0;
+}
+
+arch_initcall(check_unaligned_access_boot_cpu);
+
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
  * Alternative patch sites consider 48 bits when determining when to patch
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
index 15616155008c..ea1a10355ce9 100644
--- a/arch/riscv/kernel/image-vars.h
+++ b/arch/riscv/kernel/image-vars.h
@@ -27,6 +27,7 @@ __efistub__start		= _start;
 __efistub__start_kernel		= _start_kernel;
 __efistub__end			= _end;
 __efistub__edata		= _edata;
+__efistub___init_text_end	= __init_text_end;
 __efistub_screen_info		= screen_info;
 
 #endif
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 575e71d6c8ae..13ee7bf589a1 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/stop_machine.h>
 #include <asm/kprobes.h>
@@ -53,13 +54,52 @@ static void patch_unmap(int fixmap)