riscv: misaligned: request misaligned exception from SBI

Now that the kernel can handle misaligned accesses in S-mode, request
misaligned access exception delegation from SBI. This uses the FWFT SBI
extension defined in SBI version 3.0.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20250523101932.1594077-7-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>

Author: clementleger

arch/riscv/include/asm/cpufeature.h

@@ -67,8 +67,9 @@ void __init riscv_user_isa_enable(void);
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
 bool __init check_unaligned_access_emulated_all_cpus(void);
+void unaligned_access_init(void);
+int cpu_online_unaligned_access_init(unsigned int cpu);
 #if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
-void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
 bool unaligned_ctl_available(void);
 DECLARE_PER_CPU(long, misaligned_access_speed);

arch/riscv/kernel/traps_misaligned.c

@@ -16,6 +16,7 @@
 #include <asm/entry-common.h>
 #include <asm/hwprobe.h>
 #include <asm/cpufeature.h>
+#include <asm/sbi.h>
 #include <asm/vector.h>
 
 #define INSN_MATCH_LB			0x3
@@ -646,7 +647,7 @@ bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 
 static bool unaligned_ctl __read_mostly;
 
-void check_unaligned_access_emulated(struct work_struct *work __always_unused)
+static void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 {
 	int cpu = smp_processor_id();
 	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
@@ -657,6 +658,13 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 	__asm__ __volatile__ (
 		"       "REG_L" %[tmp], 1(%[ptr])\n"
 		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
+}
+
+static int cpu_online_check_unaligned_access_emulated(unsigned int cpu)
+{
+	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
+
+	check_unaligned_access_emulated(NULL);
 
 	/*
 	 * If unaligned_ctl is already set, this means that we detected that all
@@ -665,9 +673,10 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 	 */
 	if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) {
 		pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n");
-		while (true)
-			cpu_relax();
+		return -EINVAL;
 	}
+
+	return 0;
 }
 
 bool __init check_unaligned_access_emulated_all_cpus(void)
@@ -699,4 +708,60 @@ bool __init check_unaligned_access_emulated_all_cpus(void)
 {
 	return false;
 }
+static int cpu_online_check_unaligned_access_emulated(unsigned int cpu)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_RISCV_SBI
+
+static bool misaligned_traps_delegated;
+
+static int cpu_online_sbi_unaligned_setup(unsigned int cpu)
+{
+	if (sbi_fwft_set(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0) &&
+	    misaligned_traps_delegated) {
+		pr_crit("Misaligned trap delegation non homogeneous (expected delegated)");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void __init unaligned_access_init(void)
+{
+	int ret;
+
+	ret = sbi_fwft_set_online_cpus(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0);
+	if (ret)
+		return;
+
+	misaligned_traps_delegated = true;
+	pr_info("SBI misaligned access exception delegation ok\n");
+	/*
+	 * Note that we don't have to take any specific action here, if
+	 * the delegation is successful, then
+	 * check_unaligned_access_emulated() will verify that indeed the
+	 * platform traps on misaligned accesses.
+	 */
+}
+#else
+void __init unaligned_access_init(void) {}
+
+static int cpu_online_sbi_unaligned_setup(unsigned int cpu __always_unused)
+{
+	return 0;
+}
 #endif
+
+int cpu_online_unaligned_access_init(unsigned int cpu)
+{
+	int ret;
+
+	ret = cpu_online_sbi_unaligned_setup(cpu);
+	if (ret)
+		return ret;
+
+	return cpu_online_check_unaligned_access_emulated(cpu);
+}

arch/riscv/kernel/unaligned_access_speed.c

@@ -236,6 +236,11 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
 
 static int riscv_online_cpu(unsigned int cpu)
 {
+	int ret = cpu_online_unaligned_access_init(cpu);
+
+	if (ret)
+		return ret;
+
 	/* We are already set since the last check */
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
 		goto exit;
@@ -248,7 +253,6 @@ static int riscv_online_cpu(unsigned int cpu)
 	{
 		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");
@@ -439,6 +443,8 @@ static int __init check_unaligned_access_all_cpus(void)
 {
 	int cpu;
 
+	unaligned_access_init();
+
 	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);