22 files changed, 433 insertions, 196 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 8d186bfced45..f7480c9c6f8d 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
-CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index e89455a6a0e5..16490755304e 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -36,7 +36,6 @@ void asm_offsets(void)
 	OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
 
 	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
-	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
 	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 40ac72e407b6..2054f6c4b0ae 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -32,6 +32,7 @@
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
 static bool any_cpu_has_zicboz;
+static bool any_cpu_has_zicbom;
 
 unsigned long elf_hwcap __read_mostly;
 
@@ -53,9 +54,7 @@ u32 thead_vlenb_of;
  */
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
 {
-	if (!isa_bitmap)
-		return riscv_isa[0];
-	return isa_bitmap[0];
+	return !isa_bitmap ? riscv_isa[0] : isa_bitmap[0];
 }
 EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
 
@@ -76,10 +75,19 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned i
 	if (bit >= RISCV_ISA_EXT_MAX)
 		return false;
 
-	return test_bit(bit, bmap) ? true : false;
+	return test_bit(bit, bmap);
 }
 EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
 
+static int riscv_ext_f_depends(const struct riscv_isa_ext_data *data,
+			       const unsigned long *isa_bitmap)
+{
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_f))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
 static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data,
 				     const unsigned long *isa_bitmap)
 {
@@ -91,6 +99,8 @@ static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data,
 		pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n");
 		return -EINVAL;
 	}
+
+	any_cpu_has_zicbom = true;
 	return 0;
 }
 
@@ -109,6 +119,82 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static int riscv_ext_f_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	/*
+	 * Due to extension ordering, d is checked before f, so no deferral
+	 * is required.
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d)) {
+		pr_warn_once("This kernel does not support systems with F but not D\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int riscv_ext_d_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_x_validate(const struct riscv_isa_ext_data *data,
+				       const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_float_validate(const struct riscv_isa_ext_data *data,
+					   const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	/*
+	 * The kernel doesn't support systems that don't implement both of
+	 * F and D, so if any of the vector extensions that do floating point
+	 * are to be usable, both floating point extensions need to be usable.
+	 *
+	 * Since this function validates vector only, and v/Zve* are probed
+	 * after f/d, there's no need for a deferral here.
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_crypto_validate(const struct riscv_isa_ext_data *data,
+					    const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	/*
+	 * It isn't the kernel's job to check that the binding is correct, so
+	 * it should be enough to check that any of the vector extensions are
+	 * enabled, which in-turn means that vector is usable in this kernel
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32X))
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 static int riscv_ext_zca_depends(const struct riscv_isa_ext_data *data,
 				 const unsigned long *isa_bitmap)
 {
@@ -140,6 +226,28 @@ static int riscv_ext_zcf_validate(const struct riscv_isa_ext_data *data,
 	return -EPROBE_DEFER;
 }
 
+static int riscv_vector_f_validate(const struct riscv_isa_ext_data *data,
+				   const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32F))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
+static int riscv_ext_zvfbfwma_validate(const struct riscv_isa_ext_data *data,
+				       const unsigned long *isa_bitmap)
+{
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZFBFMIN) &&
+	    __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVFBFMIN))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
 static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data,
 				    const unsigned long *isa_bitmap)
 {
@@ -150,6 +258,11 @@ static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static const unsigned int riscv_a_exts[] = {
+	RISCV_ISA_EXT_ZAAMO,
+	RISCV_ISA_EXT_ZALRSC,
+};
+
 static const unsigned int riscv_zk_bundled_exts[] = {
 	RISCV_ISA_EXT_ZBKB,
 	RISCV_ISA_EXT_ZBKC,
@@ -321,17 +434,15 @@ static const unsigned int riscv_c_exts[] = {
 const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i),
 	__RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m),
-	__RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a),
-	__RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f),
-	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
+	__RISCV_ISA_EXT_SUPERSET(a, RISCV_ISA_EXT_a, riscv_a_exts),
+	__RISCV_ISA_EXT_DATA_VALIDATE(f, RISCV_ISA_EXT_f, riscv_ext_f_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(d, RISCV_ISA_EXT_d, riscv_ext_d_validate),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_SUPERSET(c, RISCV_ISA_EXT_c, riscv_c_exts),
-	__RISCV_ISA_EXT_SUPERSET(v, RISCV_ISA_EXT_v, riscv_v_exts),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(v, RISCV_ISA_EXT_v, riscv_v_exts, riscv_ext_vector_float_validate),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
-	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts,
-					  riscv_ext_zicbom_validate),
-	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts,
-					  riscv_ext_zicboz_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, 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),
@@ -341,10 +452,13 @@ 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(zaamo, RISCV_ISA_EXT_ZAAMO),
 	__RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
 	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zalrsc, RISCV_ISA_EXT_ZALRSC),
 	__RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
 	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA),
@@ -370,29 +484,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
 	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
 	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
-	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
-	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
-	__RISCV_ISA_EXT_SUPERSET(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts),
-	__RISCV_ISA_EXT_DATA(zve32x, RISCV_ISA_EXT_ZVE32X),
-	__RISCV_ISA_EXT_SUPERSET(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts),
-	__RISCV_ISA_EXT_SUPERSET(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts),
-	__RISCV_ISA_EXT_SUPERSET(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvbc, RISCV_ISA_EXT_ZVBC, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zve32x, RISCV_ISA_EXT_ZVE32X, riscv_ext_vector_x_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts, riscv_ext_vector_x_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, riscv_ext_zvfbfwma_validate),
 	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
 	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
-	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
-	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
-	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
-	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
-	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
-	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
-	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
-	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
-	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
-	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkb, RISCV_ISA_EXT_ZVKB, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkg, RISCV_ISA_EXT_ZVKG, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkn, riscv_zvkn_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvknc, riscv_zvknc_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkned, RISCV_ISA_EXT_ZVKNED, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkng, riscv_zvkng_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvknha, RISCV_ISA_EXT_ZVKNHA, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvknhb, RISCV_ISA_EXT_ZVKNHB, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvks, riscv_zvks_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksc, riscv_zvksc_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvksed, RISCV_ISA_EXT_ZVKSED, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvksh, RISCV_ISA_EXT_ZVKSH, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksg, riscv_zvksg_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkt, RISCV_ISA_EXT_ZVKT, riscv_ext_vector_crypto_validate),
 	__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),
@@ -960,16 +1076,6 @@ void __init riscv_fill_hwcap(void)
 		riscv_v_setup_vsize();
 	}
 
-	if (elf_hwcap & COMPAT_HWCAP_ISA_V) {
-		/*
-		 * ISA string in device tree might have 'v' flag, but
-		 * CONFIG_RISCV_ISA_V is disabled in kernel.
-		 * Clear V flag in elf_hwcap if CONFIG_RISCV_ISA_V is disabled.
-		 */
-		if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
-			elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
-	}
-
 	memset(print_str, 0, sizeof(print_str));
 	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
 		if (riscv_isa[0] & BIT_MASK(i))
@@ -1001,6 +1107,11 @@ void __init riscv_user_isa_enable(void)
 		current->thread.envcfg |= ENVCFG_CBZE;
 	else if (any_cpu_has_zicboz)
 		pr_warn("Zicboz disabled as it is unavailable on some harts\n");
+
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOM))
+		current->thread.envcfg |= ENVCFG_CBCFE;
+	else if (any_cpu_has_zicbom)
+		pr_warn("Zicbom disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index 3c37661801f9..e783a72d051f 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -468,6 +468,9 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		case R_RISCV_ALIGN:
 		case R_RISCV_RELAX:
 			break;
+		case R_RISCV_64:
+			*(u64 *)loc = val;
+			break;
 		default:
 			pr_err("Unknown rela relocation: %d\n", r_type);
 			return -ENOEXEC;
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 3524db5e4fa0..674dcdfae7a1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -36,7 +36,7 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 				     unsigned int *expected)
 {
 	unsigned int replaced[2];
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	/* we expect nops at the hook position */
 	if (!expected)
@@ -68,7 +68,7 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 				bool enable, bool ra)
 {
 	unsigned int call[2];
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	if (ra)
 		make_call_ra(hook_pos, target, call);
@@ -97,7 +97,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	if (patch_insn_write((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
index 654ed159c830..b4c1a6a3fbd2 100644
--- a/arch/riscv/kernel/jump_label.c
+++ b/arch/riscv/kernel/jump_label.c
@@ -11,8 +11,8 @@
 #include <asm/bug.h>
 #include <asm/cacheflush.h>
 #include <asm/text-patching.h>
+#include <asm/insn-def.h>
 
-#define RISCV_INSN_NOP 0x00000013U
 #define RISCV_INSN_JAL 0x0000006fU
 
 bool arch_jump_label_transform_queue(struct jump_entry *entry,
@@ -33,7 +33,7 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 			(((u32)offset & GENMASK(10,  1)) << (21 -  1)) |
 			(((u32)offset & GENMASK(20, 20)) << (31 - 20));
 	} else {
-		insn = RISCV_INSN_NOP;
+		insn = RISCV_INSN_NOP4;
 	}
 
 	if (early_boot_irqs_disabled) {
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index 2e0266ae6bd7..9f3db3503dab 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
 	regs->epc = pc;
 }
 
+noinline void arch_kgdb_breakpoint(void)
+{
+	asm(".global kgdb_compiled_break\n"
+	    "kgdb_compiled_break: ebreak\n");
+}
+
 void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
 				char *remcom_out_buffer)
 {
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 068168046e0e..da4a4000e57e 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -12,8 +12,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
 
-#define ABI_SIZE_ON_STACK	80
-
 	.text
 
 	.macro SAVE_ABI_STATE
@@ -28,12 +26,12 @@
 	 * register if a0 was not saved.
 	 */
 	.macro SAVE_RET_ABI_STATE
-	addi	sp, sp, -ABI_SIZE_ON_STACK
-	REG_S	ra, 1*SZREG(sp)
-	REG_S	s0, 8*SZREG(sp)
-	REG_S	a0, 10*SZREG(sp)
-	REG_S	a1, 11*SZREG(sp)
-	addi	s0, sp, ABI_SIZE_ON_STACK
+	addi	sp, sp, -FREGS_SIZE_ON_STACK
+	REG_S	ra, FREGS_RA(sp)
+	REG_S	s0, FREGS_S0(sp)
+	REG_S	a0, FREGS_A0(sp)
+	REG_S	a1, FREGS_A1(sp)
+	addi	s0, sp, FREGS_SIZE_ON_STACK
 	.endm
 
 	.macro RESTORE_ABI_STATE
@@ -43,11 +41,11 @@
 	.endm
 
 	.macro RESTORE_RET_ABI_STATE
-	REG_L	ra, 1*SZREG(sp)
-	REG_L	s0, 8*SZREG(sp)
-	REG_L	a0, 10*SZREG(sp)
-	REG_L	a1, 11*SZREG(sp)
-	addi	sp, sp, ABI_SIZE_ON_STACK
+	REG_L	ra, FREGS_RA(sp)
+	REG_L	s0, FREGS_S0(sp)
+	REG_L	a0, FREGS_A0(sp)
+	REG_L	a1, FREGS_A1(sp)
+	addi	sp, sp, FREGS_SIZE_ON_STACK
 	.endm
 
 SYM_TYPED_FUNC_START(ftrace_stub)
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index e264e59e596e..91d0b355ceef 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -73,16 +73,17 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int type, i;
-
-	for (i = 0; i < num; i++) {
-		type = ELF_RISCV_R_TYPE(relas[i].r_info);
-		if (type == R_RISCV_CALL_PLT) {
+	for (int i = 0; i < num; i++) {
+		switch (ELF_R_TYPE(relas[i].r_info)) {
+		case R_RISCV_CALL_PLT:
+		case R_RISCV_PLT32:
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
-		} else if (type == R_RISCV_GOT_HI20) {
+			break;
+		case R_RISCV_GOT_HI20:
 			if (!duplicate_rela(relas, i))
 				(*gots)++;
+			break;
 		}
 	}
 }
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 47d0ebeec93c..7f6147c18033 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me,
 		kfree(bucket_iter);
 	}
 
-	kfree(*relocation_hashtable);
+	kvfree(*relocation_hashtable);
 }
 
 static int add_relocation_to_accumulate(struct module *me, int type,
@@ -752,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 
 	hashtable_size <<= should_double_size;
 
-	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(**relocation_hashtable),
-					      GFP_KERNEL);
+	/* Number of relocations may be large, so kvmalloc it */
+	*relocation_hashtable = kvmalloc_array(hashtable_size,
+					       sizeof(**relocation_hashtable),
+					       GFP_KERNEL);
 	if (!*relocation_hashtable)
 		return 0;
 
@@ -859,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 				}
 
 				j++;
-				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+				if (j == num_relocations)
 					j = 0;
 
 			} while (j_idx != j);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8beaf77..cc15f7ca6cc1 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 	/* Initialize the slot */
 	void *kaddr = kmap_atomic(page);
 	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+	unsigned long start = (unsigned long)dst;
 
 	memcpy(dst, src, len);
 
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
 	}
 
+	flush_icache_range(start, start + len);
 	kunmap_atomic(kaddr);
-
-	/*
-	 * We probably need flush_icache_user_page() but it needs vma.
-	 * This should work on most of architectures by default. If
-	 * architecture needs to do something different it can define
-	 * its own version of the function.
-	 */
-	flush_dcache_page(page);
 }
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 4fe45daa6281..f7c9a1caa83e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -66,6 +66,9 @@ static struct resource bss_res = { .name = "Kernel bss", };
 static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
 #endif
 
+static int num_standard_resources;
+static struct resource *standard_resources;
+
 static int __init add_resource(struct resource *parent,
 				struct resource *res)
 {
@@ -139,7 +142,7 @@ static void __init init_resources(void)
 	struct resource *res = NULL;
 	struct resource *mem_res = NULL;
 	size_t mem_res_sz = 0;
-	int num_resources = 0, res_idx = 0;
+	int num_resources = 0, res_idx = 0, non_resv_res = 0;
 	int ret = 0;
 
 	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
@@ -193,6 +196,7 @@ static void __init init_resources(void)
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
 		res = &mem_res[res_idx--];
+		non_resv_res++;
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";
@@ -210,6 +214,9 @@ static void __init init_resources(void)
 			goto error;
 	}
 
+	num_standard_resources = non_resv_res;
+	standard_resources = &mem_res[res_idx + 1];
+
 	/* Clean-up any unused pre-allocated resources */
 	if (res_idx >= 0)
 		memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
@@ -221,6 +228,33 @@ static void __init init_resources(void)
 	memblock_free(mem_res, mem_res_sz);
 }
 
+static int __init reserve_memblock_reserved_regions(void)
+{
+	u64 i, j;
+
+	for (i = 0; i < num_standard_resources; i++) {
+		struct resource *mem = &standard_resources[i];
+		phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+		if (!memblock_is_region_reserved(mem->start, mem_size))
+			continue;
+
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
+			resource_size_t start, end;
+
+			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+			end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+			if (start > mem->end || end < mem->start)
+				continue;
+
+			reserve_region_with_split(mem, start, end, "Reserved");
+		}
+	}
+
+	return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
 
 static void __init parse_dtb(void)
 {
@@ -235,11 +269,6 @@ static void __init parse_dtb(void)
 	} else {
 		pr_err("No DTB passed to the kernel\n");
 	}
-
-#ifdef CONFIG_CMDLINE_FORCE
-	strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-	pr_info("Forcing kernel command line to: %s\n", boot_command_line);
-#endif
 }
 
 #if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index d58b5e751286..e650dec44817 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -48,6 +48,8 @@ EXPORT_SYMBOL_GPL(__cpuid_to_hartid_map);
 void __init smp_setup_processor_id(void)
 {
 	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+
+	pr_info("Booting Linux on hartid %lu\n", boot_cpu_hartid);
 }
 
 static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index e36d20205bd7..601a321e0f17 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -231,6 +231,10 @@ asmlinkage __visible void smp_callin(void)
 	riscv_ipi_enable();
 
 	numa_add_cpu(curr_cpuid);
+
+	pr_debug("CPU%u: Booted secondary hartid %lu\n", curr_cpuid,
+		cpuid_to_hartid_map(curr_cpuid));
+
 	set_cpu_online(curr_cpuid, true);
 
 	/*
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index d4355c770c36..3fe9e6edef8f 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -74,7 +74,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 						   &frame->ra);
 			if (pc >= (unsigned long)handle_exception &&
 			    pc < (unsigned long)&ret_from_exception_end) {
-				if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))
+				if (unlikely(!fn(arg, pc)))
 					break;
 
 				pc = ((struct pt_regs *)sp)->epc;
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 9a8a0dc035b2..24b3f57d467f 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -30,6 +30,13 @@ void suspend_save_csrs(struct suspend_context *context)
 	 */
 
 #ifdef CONFIG_MMU
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) {
+		context->stimecmp = csr_read(CSR_STIMECMP);
+#if __riscv_xlen < 64
+		context->stimecmph = csr_read(CSR_STIMECMPH);
+#endif
+	}
+
 	context->satp = csr_read(CSR_SATP);
 #endif
 }
@@ -43,6 +50,13 @@ void suspend_restore_csrs(struct suspend_context *context)
 	csr_write(CSR_IE, context->ie);
 
 #ifdef CONFIG_MMU
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) {
+		csr_write(CSR_STIMECMP, context->stimecmp);
+#if __riscv_xlen < 64
+		csr_write(CSR_STIMECMPH, context->stimecmph);
+#endif
+	}
+
 	csr_write(CSR_SATP, context->satp);
 #endif
 }
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 04a4e5495512..249aec8594a9 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -95,7 +95,9 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		 * regardless of the kernel's configuration, as no other checks, besides
 		 * presence in the hart_isa bitmap, are made.
 		 */
+		EXT_KEY(ZAAMO);
 		EXT_KEY(ZACAS);
+		EXT_KEY(ZALRSC);
 		EXT_KEY(ZAWRS);
 		EXT_KEY(ZBA);
 		EXT_KEY(ZBB);
@@ -107,10 +109,13 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZCA);
 		EXT_KEY(ZCB);
 		EXT_KEY(ZCMOP);
+		EXT_KEY(ZICBOM);
 		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZICNTR);
 		EXT_KEY(ZICOND);
 		EXT_KEY(ZIHINTNTL);
 		EXT_KEY(ZIHINTPAUSE);
+		EXT_KEY(ZIHPM);
 		EXT_KEY(ZIMOP);
 		EXT_KEY(ZKND);
 		EXT_KEY(ZKNE);
@@ -132,6 +137,8 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZVE64D);
 			EXT_KEY(ZVE64F);
 			EXT_KEY(ZVE64X);
+			EXT_KEY(ZVFBFMIN);
+			EXT_KEY(ZVFBFWMA);
 			EXT_KEY(ZVFH);
 			EXT_KEY(ZVFHMIN);
 			EXT_KEY(ZVKB);
@@ -148,6 +155,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZCD);
 			EXT_KEY(ZCF);
 			EXT_KEY(ZFA);
+			EXT_KEY(ZFBFMIN);
 			EXT_KEY(ZFH);
 			EXT_KEY(ZFHMIN);
 		}
@@ -161,7 +169,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	pair->value &= ~missing;
 }
 
-static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
 {
 	struct riscv_hwprobe pair;
 
@@ -279,6 +287,11 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
 			pair->value = riscv_cboz_block_size;
 		break;
+	case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM))
+			pair->value = riscv_cbom_block_size;
+		break;
 	case RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS:
 		pair->value = user_max_virt_addr();
 		break;
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 7cc108aed74e..4354c87c0376 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -605,16 +605,10 @@ void check_vector_unaligned_access_emulated(struct work_struct *work __always_un
 	kernel_vector_end();
 }
 
-bool check_vector_unaligned_access_emulated_all_cpus(void)
+bool __init 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)
@@ -625,7 +619,7 @@ bool check_vector_unaligned_access_emulated_all_cpus(void)
 	return true;
 }
 #else
-bool check_vector_unaligned_access_emulated_all_cpus(void)
+bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 {
 	return false;
 }
@@ -659,7 +653,7 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 	}
 }
 
-bool check_unaligned_access_emulated_all_cpus(void)
+bool __init check_unaligned_access_emulated_all_cpus(void)
 {
 	int cpu;
 
@@ -684,7 +678,7 @@ bool unaligned_ctl_available(void)
 	return unaligned_ctl;
 }
 #else
-bool check_unaligned_access_emulated_all_cpus(void)
+bool __init check_unaligned_access_emulated_all_cpus(void)
 {
 	return false;
 }
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 91f189cf1611..b8ba13819d05 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -24,8 +24,12 @@
 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 long unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
+static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
 static cpumask_t fast_misaligned_access;
+
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
 static int check_unaligned_access(void *param)
 {
 	int cpu = smp_processor_id();
@@ -121,7 +125,7 @@ static int check_unaligned_access(void *param)
 	return 0;
 }
 
-static void check_unaligned_access_nonboot_cpu(void *param)
+static void __init check_unaligned_access_nonboot_cpu(void *param)
 {
 	unsigned int cpu = smp_processor_id();
 	struct page **pages = param;
@@ -130,6 +134,50 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static void __init check_unaligned_access_speed_all_cpus(void)
+{
+	unsigned int cpu;
+	unsigned int cpu_count = num_possible_cpus();
+	struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL);
+
+	if (!bufs) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return;
+	}
+
+	/*
+	 * Allocate separate buffers for each CPU so there's no fighting over
+	 * cache lines.
+	 */
+	for_each_cpu(cpu, cpu_online_mask) {
+		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!bufs[cpu]) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			goto out;
+		}
+	}
+
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
+
+out:
+	for_each_cpu(cpu, cpu_online_mask) {
+		if (bufs[cpu])
+			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
+	}
+
+	kfree(bufs);
+}
+#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
+static void __init check_unaligned_access_speed_all_cpus(void)
+{
+}
+#endif
+
 DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 
 static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
@@ -175,7 +223,7 @@ static void set_unaligned_access_static_branches(void)
 	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
 }
 
-static int lock_and_set_unaligned_access_static_branch(void)
+static int __init lock_and_set_unaligned_access_static_branch(void)
 {
 	cpus_read_lock();
 	set_unaligned_access_static_branches();
@@ -188,21 +236,29 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
 
 static int riscv_online_cpu(unsigned int cpu)
 {
-	static struct page *buf;
-
 	/* We are already set since the last check */
-	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		goto exit;
+	} else if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
 		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");
-		return -ENOMEM;
 	}
 
-	check_unaligned_access(buf);
-	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
+	{
+		static struct page *buf;
+
+		check_unaligned_access_emulated(NULL);
+		buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!buf) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			return -ENOMEM;
+		}
+
+		check_unaligned_access(buf);
+		__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+	}
+#endif
 
 exit:
 	set_unaligned_access_static_branches();
@@ -217,59 +273,6 @@ static int riscv_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-/* Measure unaligned access speed on all CPUs present at boot in parallel. */
-static int check_unaligned_access_speed_all_cpus(void)
-{
-	unsigned int cpu;
-	unsigned int cpu_count = num_possible_cpus();
-	struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL);
-
-	if (!bufs) {
-		pr_warn("Allocation failure, not measuring misaligned performance\n");
-		return 0;
-	}
-
-	/*
-	 * Allocate separate buffers for each CPU so there's no fighting over
-	 * cache lines.
-	 */
-	for_each_cpu(cpu, cpu_online_mask) {
-		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
-		if (!bufs[cpu]) {
-			pr_warn("Allocation failure, not measuring misaligned performance\n");
-			goto out;
-		}
-	}
-
-	/* Check everybody except 0, who stays behind to tend jiffies. */
-	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
-
-	/* Check core 0. */
-	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
-
-	/*
-	 * 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, riscv_offline_cpu);
-
-out:
-	for_each_cpu(cpu, cpu_online_mask) {
-		if (bufs[cpu])
-			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
-	}
-
-	kfree(bufs);
-	return 0;
-}
-#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
-static int check_unaligned_access_speed_all_cpus(void)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
 static void check_vector_unaligned_access(struct work_struct *work __always_unused)
 {
@@ -349,7 +352,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus
 		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n",
 			cpu);
 
-		return;
+		goto free;
 	}
 
 	if (word_cycles < byte_cycles)
@@ -363,57 +366,119 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus
 		(speed ==  RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow");
 
 	per_cpu(vector_misaligned_access, cpu) = speed;
+
+free:
+	__free_pages(page, MISALIGNED_BUFFER_ORDER);
+}
+
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	schedule_on_each_cpu(check_vector_unaligned_access);
+
+	return 0;
+}
+#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
+static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	return 0;
 }
+#endif
 
 static int riscv_online_cpu_vec(unsigned int cpu)
 {
-	if (!has_vector())
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
 		return 0;
+	}
 
-	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED)
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
 		return 0;
 
 	check_vector_unaligned_access_emulated(NULL);
 	check_vector_unaligned_access(NULL);
+#endif
+
 	return 0;
 }
 
-/* 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)
-{
-	schedule_on_each_cpu(check_vector_unaligned_access);
+static const char * const speed_str[] __initconst = { NULL, NULL, "slow", "fast", "unsupported" };
 
-	/*
-	 * 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);
+static int __init set_unaligned_scalar_speed_param(char *str)
+{
+	if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_FAST]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED;
+	else
+		return -EINVAL;
 
-	return 0;
+	return 1;
 }
-#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
-static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+__setup("unaligned_scalar_speed=", set_unaligned_scalar_speed_param);
+
+static int __init set_unaligned_vector_speed_param(char *str)
 {
-	return 0;
+	if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_FAST]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+	else
+		return -EINVAL;
+
+	return 1;
 }
-#endif
+__setup("unaligned_vector_speed=", set_unaligned_vector_speed_param);
 
-static int check_unaligned_access_all_cpus(void)
+static int __init check_unaligned_access_all_cpus(void)
 {
-	bool all_cpus_emulated, all_cpus_vec_unsupported;
+	int cpu;
+
+	if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n",
+			speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param);
+		for_each_online_cpu(cpu)
+			per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
+	} else if (!check_unaligned_access_emulated_all_cpus()) {
+		check_unaligned_access_speed_all_cpus();
+	}
+
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		if (!has_vector() &&
+		    unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) {
+			pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n",
+				speed_str[unaligned_vector_speed_param]);
+		} else {
+			pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n",
+				speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param);
+		}
+	}
 
-	all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
-	all_cpus_vec_unsupported = check_vector_unaligned_access_emulated_all_cpus();
+	if (!has_vector())
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
-	if (!all_cpus_vec_unsupported &&
-	    IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		for_each_online_cpu(cpu)
+			per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
+	} else if (!check_vector_unaligned_access_emulated_all_cpus() &&
+		   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();
+	/*
+	 * 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, riscv_offline_cpu);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu_vec, NULL);
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S
index d16f19f1b3b6..7ce4de6f6e69 100644
--- a/arch/riscv/kernel/vec-copy-unaligned.S
+++ b/arch/riscv/kernel/vec-copy-unaligned.S
@@ -11,7 +11,7 @@
 
 #define WORD_SEW CONCATENATE(e, WORD_EEW)
 #define VEC_L CONCATENATE(vle, WORD_EEW).v
-#define VEC_S CONCATENATE(vle, WORD_EEW).v
+#define VEC_S CONCATENATE(vse, 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. */
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
index a31ff84740eb..9feb7f67a0a3 100644
--- a/arch/riscv/kernel/vendor_extensions.c
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -61,6 +61,6 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig
 	if (bit >= RISCV_ISA_VENDOR_EXT_MAX)
 		return false;
 
-	return test_bit(bit, bmap->isa) ? true : false;
+	return test_bit(bit, bmap->isa);
 }
 EXPORT_SYMBOL_GPL(__riscv_isa_vendor_extension_available);
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 002ca58dd998..61bd5ba6680a 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -97,6 +97,9 @@ SECTIONS
 	{
 		EXIT_DATA
 	}
+
+	RUNTIME_CONST_VARIABLES
+
 	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	.rel.dyn : {