Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

24 files changed, 519 insertions, 313 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 604d6bf7e4..81d94a8ee1 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -39,7 +39,6 @@ extra-y += vmlinux.lds
 obj-y	+= head.o
 obj-y	+= soc.o
 obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o
-obj-y	+= copy-unaligned.o
 obj-y	+= cpu.o
 obj-y	+= cpufeature.o
 obj-y	+= entry.o
@@ -64,6 +63,9 @@ obj-y	+= tests/
 obj-$(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_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
@@ -94,7 +96,7 @@ obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KEXEC_CORE)	+= kexec_relocate.o crash_save_regs.o machine_kexec.o
 obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
-obj-$(CONFIG_CRASH_CORE)	+= crash_core.o
+obj-$(CONFIG_VMCORE_INFO)	+= vmcore_info.o
 
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 319a1da035..0128b161bf 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -43,7 +43,7 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 
 	switch (cpu_mfr_info->vendor_id) {
 #ifdef CONFIG_ERRATA_ANDES
-	case ANDESTECH_VENDOR_ID:
+	case ANDES_VENDOR_ID:
 		cpu_mfr_info->patch_func = andes_errata_patch_func;
 		break;
 #endif
diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index 6ec9dbd729..64bdd3e1ab 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -75,3 +75,56 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 
 	return report_cfi_failure(regs, regs->epc, &target, type);
 }
+
+#ifdef CONFIG_CFI_CLANG
+struct bpf_insn;
+
+/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
+extern unsigned int __bpf_prog_runX(const void *ctx,
+				    const struct bpf_insn *insn);
+
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+__ADDRESSABLE(__bpf_prog_runX);
+
+/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
+asm (
+"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
+"	.type	cfi_bpf_hash,@object				\n"
+"	.globl	cfi_bpf_hash					\n"
+"	.p2align	2, 0x0					\n"
+"cfi_bpf_hash:							\n"
+"	.word	__kcfi_typeid___bpf_prog_runX			\n"
+"	.size	cfi_bpf_hash, 4					\n"
+"	.popsection						\n"
+);
+
+/* Must match bpf_callback_t */
+extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
+
+__ADDRESSABLE(__bpf_callback_fn);
+
+/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
+asm (
+"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
+"	.type	cfi_bpf_subprog_hash,@object			\n"
+"	.globl	cfi_bpf_subprog_hash				\n"
+"	.p2align	2, 0x0					\n"
+"cfi_bpf_subprog_hash:						\n"
+"	.word	__kcfi_typeid___bpf_callback_fn			\n"
+"	.size	cfi_bpf_subprog_hash, 4				\n"
+"	.popsection						\n"
+);
+
+u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	if (get_kernel_nofault(hash, func - cfi_get_offset()))
+		return 0;
+
+	return hash;
+}
+#endif
diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile
index 62fa393b2e..3df4cb788c 100644
--- a/arch/riscv/kernel/compat_vdso/Makefile
+++ b/arch/riscv/kernel/compat_vdso/Makefile
@@ -74,5 +74,5 @@ quiet_cmd_compat_vdsold = VDSOLD  $@
                    rm $@.tmp
 
 # actual build commands
-quiet_cmd_compat_vdsoas = VDSOAS $@
+quiet_cmd_compat_vdsoas = VDSOAS  $@
       cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $<
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index d11d6320fb..c1f3655238 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -139,6 +139,34 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 	return -1;
 }
 
+unsigned long __init riscv_get_marchid(void)
+{
+	struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo);
+
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid();
+#elif IS_ENABLED(CONFIG_RISCV_M_MODE)
+	ci->marchid = csr_read(CSR_MARCHID);
+#else
+	ci->marchid = 0;
+#endif
+	return ci->marchid;
+}
+
+unsigned long __init riscv_get_mvendorid(void)
+{
+	struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo);
+
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid();
+#elif IS_ENABLED(CONFIG_RISCV_M_MODE)
+	ci->mvendorid = csr_read(CSR_MVENDORID);
+#else
+	ci->mvendorid = 0;
+#endif
+	return ci->mvendorid;
+}
+
 DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 
 unsigned long riscv_cached_mvendorid(unsigned int cpu_id)
@@ -170,12 +198,16 @@ static int riscv_cpuinfo_starting(unsigned int cpu)
 	struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo);
 
 #if IS_ENABLED(CONFIG_RISCV_SBI)
-	ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid();
-	ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid();
+	if (!ci->mvendorid)
+		ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid();
+	if (!ci->marchid)
+		ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid();
 	ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid();
 #elif IS_ENABLED(CONFIG_RISCV_M_MODE)
-	ci->mvendorid = csr_read(CSR_MVENDORID);
-	ci->marchid = csr_read(CSR_MARCHID);
+	if (!ci->mvendorid)
+		ci->mvendorid = csr_read(CSR_MVENDORID);
+	if (!ci->marchid)
+		ci->marchid = csr_read(CSR_MARCHID);
 	ci->mimpid = csr_read(CSR_MIMPID);
 #else
 	ci->mvendorid = 0;
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 1cc7df740e..e6fbaaf549 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	/* Make sure tidle is updated */
 	smp_mb();
 	bdata->task_ptr = tidle;
-	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	bdata->stack_ptr = task_pt_regs(tidle);
 	/* Make sure boot data is updated */
 	smp_mb();
 	hsm_data = __pa(bdata);
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index 613872b0a2..24869eb889 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 
 	/* Make sure tidle is updated */
 	smp_mb();
-	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
-		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle));
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 79a5a35fab..5ef48cb20e 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -11,7 +11,6 @@
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
-#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -21,21 +20,13 @@
 #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/sbi.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_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
-#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
-
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -44,11 +35,6 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 /* Per-cpu ISA extensions. */
 struct riscv_isainfo hart_isa[NR_CPUS];
 
-/* Performance information */
-DEFINE_PER_CPU(long, misaligned_access_speed);
-
-static cpumask_t fast_misaligned_access;
-
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -318,6 +304,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_EXT_XANDESPMU),
 };
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
@@ -503,6 +490,8 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 	struct acpi_table_header *rhct;
 	acpi_status status;
 	unsigned int cpu;
+	u64 boot_vendorid;
+	u64 boot_archid;
 
 	if (!acpi_disabled) {
 		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
@@ -510,6 +499,9 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 			return;
 	}
 
+	boot_vendorid = riscv_get_mvendorid();
+	boot_archid = riscv_get_marchid();
+
 	for_each_possible_cpu(cpu) {
 		struct riscv_isainfo *isainfo = &hart_isa[cpu];
 		unsigned long this_hwcap = 0;
@@ -557,8 +549,7 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 		 * CPU cores with the ratified spec will contain non-zero
 		 * marchid.
 		 */
-		if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID &&
-		    riscv_cached_marchid(cpu) == 0x0) {
+		if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) {
 			this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v];
 			clear_bit(RISCV_ISA_EXT_v, isainfo->isa);
 		}
@@ -612,7 +603,7 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 
 			if (ext->subset_ext_size) {
 				for (int j = 0; j < ext->subset_ext_size; j++) {
-					if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+					if (riscv_isa_extension_check(ext->subset_ext_ids[j]))
 						set_bit(ext->subset_ext_ids[j], isainfo->isa);
 				}
 			}
@@ -731,247 +722,6 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-static int check_unaligned_access(void *param)
-{
-	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 = param;
-	void *dst;
-	void *src;
-	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
-
-	if (check_unaligned_access_emulated(cpu))
-		return 0;
-
-	/* 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);
-
-		return 0;
-	}
-
-	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;
-
-	/*
-	 * Set the value of fast_misaligned_access of a CPU. These operations
-	 * are atomic to avoid race conditions.
-	 */
-	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
-		cpumask_set_cpu(cpu, &fast_misaligned_access);
-	else
-		cpumask_clear_cpu(cpu, &fast_misaligned_access);
-
-	return 0;
-}
-
-static void check_unaligned_access_nonboot_cpu(void *param)
-{
-	unsigned int cpu = smp_processor_id();
-	struct page **pages = param;
-
-	if (smp_processor_id() != 0)
-		check_unaligned_access(pages[cpu]);
-}
-
-DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
-static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
-{
-	if (cpumask_weight(mask) == weight)
-		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
-	else
-		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
-}
-
-static void set_unaligned_access_static_branches_except_cpu(int cpu)
-{
-	/*
-	 * Same as set_unaligned_access_static_branches, except excludes the
-	 * given CPU from the result. When a CPU is hotplugged into an offline
-	 * state, this function is called before the CPU is set to offline in
-	 * the cpumask, and thus the CPU needs to be explicitly excluded.
-	 */
-
-	cpumask_t fast_except_me;
-
-	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &fast_except_me);
-
-	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
-}
-
-static void set_unaligned_access_static_branches(void)
-{
-	/*
-	 * This will be called after check_unaligned_access_all_cpus so the
-	 * result of unaligned access speed for all CPUs will be available.
-	 *
-	 * To avoid the number of online cpus changing between reading
-	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
-	 * held before calling this function.
-	 */
-
-	cpumask_t fast_and_online;
-
-	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
-
-	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
-}
-
-static int lock_and_set_unaligned_access_static_branch(void)
-{
-	cpus_read_lock();
-	set_unaligned_access_static_branches();
-	cpus_read_unlock();
-
-	return 0;
-}
-
-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_UNKNOWN)
-		goto exit;
-
-	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);
-
-exit:
-	set_unaligned_access_static_branches();
-
-	return 0;
-}
-
-static int riscv_offline_cpu(unsigned int cpu)
-{
-	set_unaligned_access_static_branches_except_cpu(cpu);
-
-	return 0;
-}
-
-/* Measure unaligned access on all CPUs present at boot in parallel. */
-static int check_unaligned_access_all_cpus(void)
-{
-	unsigned int cpu;
-	unsigned int cpu_count = num_possible_cpus();
-	struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
-				     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:
-	unaligned_emulation_finish();
-	for_each_cpu(cpu, cpu_online_mask) {
-		if (bufs[cpu])
-			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
-	}
-
-	kfree(bufs);
-	return 0;
-}
-
-arch_initcall(check_unaligned_access_all_cpus);
-
 void riscv_user_isa_enable(void)
 {
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index 5bd1ec3341..54260c16f9 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -117,6 +117,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 	return ret;
 }
 
+#ifdef CONFIG_CRASH_DUMP
 static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 {
 	unsigned int *nr_ranges = arg;
@@ -189,6 +190,7 @@ static char *setup_kdump_cmdline(struct kimage *image, char *cmdline,
 	cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0';
 	return cmdline_ptr;
 }
+#endif
 
 static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 			    unsigned long kernel_len, char *initrd,
@@ -196,12 +198,11 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 			    unsigned long cmdline_len)
 {
 	int ret;
+	void *fdt;
 	unsigned long old_kernel_pbase = ULONG_MAX;
 	unsigned long new_kernel_pbase = 0UL;
 	unsigned long initrd_pbase = 0UL;
-	unsigned long headers_sz;
 	unsigned long kernel_start;
-	void *fdt, *headers;
 	struct elfhdr ehdr;
 	struct kexec_buf kbuf;
 	struct kexec_elf_info elf_info;
@@ -227,8 +228,11 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 	kbuf.buf_min = new_kernel_pbase + kernel_len;
 	kbuf.buf_max = ULONG_MAX;
 
+#ifdef CONFIG_CRASH_DUMP
 	/* Add elfcorehdr */
 	if (image->type == KEXEC_TYPE_CRASH) {
+		void *headers;
+		unsigned long headers_sz;
 		ret = prepare_elf_headers(&headers, &headers_sz);
 		if (ret) {
 			pr_err("Preparing elf core header failed\n");
@@ -264,6 +268,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		}
 		cmdline = modified_cmdline;
 	}
+#endif
 
 #ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY
 	/* Add purgatory to the image */
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 9d1a305d55..68a24cf948 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -111,6 +111,7 @@ SYM_CODE_START(handle_exception)
 1:
 	tail do_trap_unknown
 SYM_CODE_END(handle_exception)
+ASM_NOKPROBE(handle_exception)
 
 /*
  * The ret_from_exception must be called with interrupt disabled. Here is the
@@ -184,6 +185,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	sret
 #endif
 SYM_CODE_END(ret_from_exception)
+ASM_NOKPROBE(ret_from_exception)
 
 #ifdef CONFIG_VMAP_STACK
 SYM_CODE_START_LOCAL(handle_kernel_stack_overflow)
@@ -219,6 +221,7 @@ SYM_CODE_START_LOCAL(handle_kernel_stack_overflow)
 	move a0, sp
 	tail handle_bad_stack
 SYM_CODE_END(handle_kernel_stack_overflow)
+ASM_NOKPROBE(handle_kernel_stack_overflow)
 #endif
 
 SYM_CODE_START(ret_from_fork)
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index d7ec69ac69..3a42f62879 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -50,8 +50,8 @@
 
 SYM_TYPED_FUNC_START(ftrace_stub)
 #ifdef CONFIG_DYNAMIC_FTRACE
-       .global MCOUNT_NAME
-       .set    MCOUNT_NAME, ftrace_stub
+       .global _mcount
+       .set    _mcount, ftrace_stub
 #endif
 	ret
 SYM_FUNC_END(ftrace_stub)
@@ -80,7 +80,7 @@ SYM_FUNC_END(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-SYM_FUNC_START(MCOUNT_NAME)
+SYM_FUNC_START(_mcount)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
@@ -126,6 +126,6 @@ SYM_FUNC_START(MCOUNT_NAME)
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-SYM_FUNC_END(MCOUNT_NAME)
+SYM_FUNC_END(_mcount)
 #endif
-EXPORT_SYMBOL(MCOUNT_NAME)
+EXPORT_SYMBOL(_mcount)
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index 07915dc927..b75f150b92 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -9,6 +9,9 @@ KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
 		   -fno-asynchronous-unwind-tables -fno-unwind-tables \
 		   $(call cc-option,-fno-addrsig)
 
+# Disable LTO
+KBUILD_CFLAGS	:= $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS))
+
 KBUILD_CFLAGS	+= -mcmodel=medany
 
 CFLAGS_cmdline_early.o += -D__NO_FORTIFY
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
index 7142ec42e8..a69dfa610a 100644
--- a/arch/riscv/kernel/probes/ftrace.c
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -11,6 +11,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
+	if (unlikely(kprobe_ftrace_disabled))
+		return;
+
 	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index e8515aa9d8..92731ff8c7 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -377,14 +377,14 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 	return ret;
 }
+#else
+static const struct user_regset_view compat_riscv_user_native_view = {};
 #endif /* CONFIG_COMPAT */
 
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
-#ifdef CONFIG_COMPAT
-	if (test_tsk_thread_flag(task, TIF_32BIT))
+	if (is_compat_thread(&task->thread_info))
 		return &compat_riscv_user_native_view;
 	else
-#endif
 		return &riscv_user_native_view;
 }
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 519b6bd946..4b3c50da48 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -26,9 +26,8 @@
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
-#include <asm/cpufeature.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
@@ -42,10 +41,6 @@
 
 static DECLARE_COMPLETION(cpu_running);
 
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
@@ -239,9 +234,10 @@ asmlinkage __visible void smp_callin(void)
 	riscv_user_isa_enable();
 
 	/*
-	 * Remote TLB flushes are ignored while the CPU is offline, so emit
-	 * a local TLB flush right now just in case.
+	 * Remote cache and TLB flushes are ignored while the CPU is offline,
+	 * so flush them both right now just in case.
 	 */
+	local_flush_icache_all();
 	local_flush_tlb_all();
 	complete(&cpu_running);
 	/*
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 64a9c093ae..528ec7cc9a 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -18,6 +18,16 @@
 
 extern asmlinkage void ret_from_exception(void);
 
+static inline int fp_is_valid(unsigned long fp, unsigned long sp)
+{
+	unsigned long low, high;
+
+	low = sp + sizeof(struct stackframe);
+	high = ALIGN(sp, THREAD_SIZE);
+
+	return !(fp < low || fp > high || fp & 0x07);
+}
+
 void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			     bool (*fn)(void *, unsigned long), void *arg)
 {
@@ -41,21 +51,19 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 	}
 
 	for (;;) {
-		unsigned long low, high;
 		struct stackframe *frame;
 
 		if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc))))
 			break;
 
-		/* Validate frame pointer */
-		low = sp + sizeof(struct stackframe);
-		high = ALIGN(sp, THREAD_SIZE);
-		if (unlikely(fp < low || fp > high || fp & 0x7))
+		if (unlikely(!fp_is_valid(fp, sp)))
 			break;
+
 		/* Unwind stack frame */
 		frame = (struct stackframe *)fp - 1;
 		sp = fp;
-		if (regs && (regs->epc == pc) && (frame->fp & 0x7)) {
+		if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) {
+			/* We hit function where ra is not saved on the stack */
 			fp = frame->ra;
 			pc = regs->ra;
 		} else {
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 299795341e..8a327b485b 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -132,4 +132,53 @@ static int __init sbi_system_suspend_init(void)
 }
 
 arch_initcall(sbi_system_suspend_init);
+
+static int sbi_suspend_finisher(unsigned long suspend_type,
+				unsigned long resume_addr,
+				unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_SUSPEND,
+			suspend_type, resume_addr, opaque, 0, 0, 0);
+
+	return (ret.error) ? sbi_err_map_linux_errno(ret.error) : 0;
+}
+
+int riscv_sbi_hart_suspend(u32 state)
+{
+	if (state & SBI_HSM_SUSP_NON_RET_BIT)
+		return cpu_suspend(state, sbi_suspend_finisher);
+	else
+		return sbi_suspend_finisher(state, 0, 0);
+}
+
+bool riscv_sbi_suspend_state_is_valid(u32 state)
+{
+	if (state > SBI_HSM_SUSPEND_RET_DEFAULT &&
+	    state < SBI_HSM_SUSPEND_RET_PLATFORM)
+		return false;
+
+	if (state > SBI_HSM_SUSPEND_NON_RET_DEFAULT &&
+	    state < SBI_HSM_SUSPEND_NON_RET_PLATFORM)
+		return false;
+
+	return true;
+}
+
+bool riscv_sbi_hsm_is_supported(void)
+{
+	/*
+	 * The SBI HSM suspend function is only available when:
+	 * 1) SBI version is 0.3 or higher
+	 * 2) SBI HSM extension is available
+	 */
+	if (sbi_spec_version < sbi_mk_version(0, 3) ||
+	    !sbi_probe_extension(SBI_EXT_HSM)) {
+		pr_info("HSM suspend not available\n");
+		return false;
+	}
+
+	return true;
+}
 #endif /* CONFIG_RISCV_SBI */
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index a7c56b41ef..8cae41a502 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -147,6 +147,7 @@ static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
 	return (pair.value & ext);
 }
 
+#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
 	int cpu;
@@ -169,6 +170,18 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 
 	return perf;
 }
+#else
+static u64 hwprobe_misaligned(const struct cpumask *cpus)
+{
+	if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_FAST;
+
+	if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available())
+		return RISCV_HWPROBE_MISALIGNED_EMULATED;
+
+	return RISCV_HWPROBE_MISALIGNED_SLOW;
+}
+#endif
 
 static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 			     const struct cpumask *cpus)
diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug
index 5dba64e8e9..78cea5d2c2 100644
--- a/arch/riscv/kernel/tests/Kconfig.debug
+++ b/arch/riscv/kernel/tests/Kconfig.debug
@@ -6,7 +6,7 @@ config AS_HAS_ULEB128
 
 menuconfig RUNTIME_KERNEL_TESTING_MENU
        bool "arch/riscv/kernel runtime Testing"
-       def_bool y
+       default y
        help
          Enable riscv kernel runtime testing.
 
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 142f5f5168..05a16b1f0a 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -6,6 +6,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/randomize_kstack.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/signal.h>
@@ -310,7 +311,8 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs)
 	}
 }
 
-asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs)
+asmlinkage __visible __trap_section  __no_stack_protector
+void do_trap_ecall_u(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		long syscall = regs->a7;
@@ -322,10 +324,23 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs)
 
 		syscall = syscall_enter_from_user_mode(regs, syscall);
 
+		add_random_kstack_offset();
+
 		if (syscall >= 0 && syscall < NR_syscalls)
 			syscall_handler(regs, syscall);
 		else if (syscall != -1)
 			regs->a0 = -ENOSYS;
+		/*
+		 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+		 * so the maximum stack offset is 1k bytes (10 bits).
+		 *
+		 * The actual entropy will be further reduced by the compiler when
+		 * applying stack alignment constraints: 16-byte (i.e. 4-bit) aligned
+		 * for RV32I or RV64I.
+		 *
+		 * The resulting 6 bits of entropy is seen in SP[9:4].
+		 */
+		choose_random_kstack_offset(get_random_u16());
 
 		syscall_exit_to_user_mode(regs);
 	} else {
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index c2ed4e689b..2adb7c3e4d 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -413,7 +413,9 @@ int handle_misaligned_load(struct pt_regs *regs)
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
 
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
 	*this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED;
+#endif
 
 	if (!unaligned_enabled)
 		return -1;
@@ -596,7 +598,7 @@ int handle_misaligned_store(struct pt_regs *regs)
 	return 0;
 }
 
-bool check_unaligned_access_emulated(int cpu)
+static bool check_unaligned_access_emulated(int cpu)
 {
 	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
 	unsigned long tmp_var, tmp_val;
@@ -623,7 +625,7 @@ bool check_unaligned_access_emulated(int cpu)
 	return misaligned_emu_detected;
 }
 
-void unaligned_emulation_finish(void)
+bool check_unaligned_access_emulated_all_cpus(void)
 {
 	int cpu;
 
@@ -632,13 +634,12 @@ void unaligned_emulation_finish(void)
 	 * accesses emulated since tasks requesting such control can run on any
 	 * CPU.
 	 */
-	for_each_online_cpu(cpu) {
-		if (per_cpu(misaligned_access_speed, cpu) !=
-					RISCV_HWPROBE_MISALIGNED_EMULATED) {
-			return;
-		}
-	}
+	for_each_online_cpu(cpu)
+		if (!check_unaligned_access_emulated(cpu))
+			return false;
+
 	unaligned_ctl = true;
+	return true;
 }
 
 bool unaligned_ctl_available(void)
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
new file mode 100644
index 0000000000..a9a6bcb02a
--- /dev/null
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2024 Rivos Inc.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/jump_label.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+
+#include "copy-unaligned.h"
+
+#define MISALIGNED_ACCESS_JIFFIES_LG2 1
+#define MISALIGNED_BUFFER_SIZE 0x4000
+#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);
+
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
+static cpumask_t fast_misaligned_access;
+static int check_unaligned_access(void *param)
+{
+	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 = param;
+	void *dst;
+	void *src;
+	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+		return 0;
+
+	/* 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);
+
+		return 0;
+	}
+
+	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;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
+	return 0;
+}
+
+static void check_unaligned_access_nonboot_cpu(void *param)
+{
+	unsigned int cpu = smp_processor_id();
+	struct page **pages = param;
+
+	if (smp_processor_id() != 0)
+		check_unaligned_access(pages[cpu]);
+}
+
+DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_unaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_unaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+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_UNKNOWN)
+		goto exit;
+
+	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);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(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;
+}
+
+static int check_unaligned_access_all_cpus(void)
+{
+	bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+
+	if (!all_cpus_emulated)
+		return check_unaligned_access_speed_all_cpus();
+
+	return 0;
+}
+#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
+static int check_unaligned_access_all_cpus(void)
+{
+	check_unaligned_access_emulated_all_cpus();
+
+	return 0;
+}
+#endif
+
+arch_initcall(check_unaligned_access_all_cpus);
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 2cf76218a5..98315b9825 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -30,14 +30,8 @@ enum rv_vdso_map {
 
 #define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
 
-/*
- * The vDSO data page.
- */
-static union {
-	struct vdso_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
 struct __vdso_info {
 	const char *name;
diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/vmcore_info.c
index 8706736fd4..6d7a22522d 100644
--- a/arch/riscv/kernel/crash_core.c
+++ b/arch/riscv/kernel/vmcore_info.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
 #include <linux/pagemap.h>
 
 void arch_crash_save_vmcoreinfo(void)
@@ -8,7 +8,6 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_NUMBER(phys_ram_base);
 
 	vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET);
-	vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END);
 #ifdef CONFIG_MMU
 	VMCOREINFO_NUMBER(VA_BITS);