Merge tag 'riscv-for-linus-6.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

 - reintroduce the text patching global icache flush

 - fix syscall entry code to correctly initialize a0, which manifested
   as a strace bug

 - XIP kernels now map the entire kernel, which fixes boot under at
   least DEBUG_VIRTUAL=y

 - initialize all nodes in the acpi_early_node_map initializer

 - fix OOB access in the Andes vendor extension probing code

 - A new key for scalar misaligned access performance in hwprobe, which
   correctly treat the values as an enum (as opposed to a bitmap)

* tag 'riscv-for-linus-6.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: Fix out-of-bounds when accessing Andes per hart vendor extension array
  RISC-V: hwprobe: Add SCALAR to misaligned perf defines
  RISC-V: hwprobe: Add MISALIGNED_PERF key
  RISC-V: ACPI: NUMA: initialize all values of acpi_early_node_map to NUMA_NO_NODE
  riscv: change XIP's kernel_map.size to be size of the entire kernel
  riscv: entry: always initialize regs->a0 to -ENOSYS
  riscv: Re-introduce global icache flush in patch_text_XXX()

10 files changed, 32 insertions, 21 deletions

diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index ef01c182af2b..ffb9484531af 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 8
+#define RISCV_HWPROBE_MAX_KEY 9
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index b706c8e47b02..1e153cda57db 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -82,6 +82,12 @@ struct riscv_hwprobe {
 #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 #define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS	7
 #define RISCV_HWPROBE_KEY_TIME_CSR_FREQ	8
+#define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF	9
+#define		RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN		0
+#define		RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED	1
+#define		RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW		2
+#define		RISCV_HWPROBE_MISALIGNED_SCALAR_FAST		3
+#define		RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED	4
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c
index 0231482d6946..ff95aeebee3e 100644
--- a/arch/riscv/kernel/acpi_numa.c
+++ b/arch/riscv/kernel/acpi_numa.c
@@ -28,7 +28,7 @@
 
 #include <asm/numa.h>
 
-static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
+static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE };
 
 int __init acpi_numa_get_nid(unsigned int cpu)
 {
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 69e5796fc51f..34ef522f07a8 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -205,6 +205,8 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len)
 	int ret;
 
 	ret = patch_insn_set(addr, c, len);
+	if (!ret)
+		flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len);
 
 	return ret;
 }
@@ -239,6 +241,8 @@ int patch_text_nosync(void *addr, const void *insns, size_t len)
 	int ret;
 
 	ret = patch_insn_write(addr, insns, len);
+	if (!ret)
+		flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len);
 
 	return ret;
 }
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 8d1b5c35d2a7..cea0ca2bf2a2 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -178,13 +178,13 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 			perf = this_perf;
 
 		if (perf != this_perf) {
-			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+			perf = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 			break;
 		}
 	}
 
 	if (perf == -1ULL)
-		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+		return RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 
 	return perf;
 }
@@ -192,12 +192,12 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
 	if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS))
-		return RISCV_HWPROBE_MISALIGNED_FAST;
+		return RISCV_HWPROBE_MISALIGNED_SCALAR_FAST;
 
 	if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available())
-		return RISCV_HWPROBE_MISALIGNED_EMULATED;
+		return RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED;
 
-	return RISCV_HWPROBE_MISALIGNED_SLOW;
+	return RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
 }
 #endif
 
@@ -225,6 +225,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		break;
 
 	case RISCV_HWPROBE_KEY_CPUPERF_0:
+	case RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF:
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 05a16b1f0aee..51ebfd23e007 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
 
 		regs->epc += 4;
 		regs->orig_a0 = regs->a0;
+		regs->a0 = -ENOSYS;
 
 		riscv_v_vstate_discard(regs);
 
@@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
 
 		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).
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index b62d5a2f4541..192cd5603e95 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -338,7 +338,7 @@ 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;
+	*this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED;
 #endif
 
 	if (!unaligned_enabled)
@@ -532,13 +532,13 @@ static bool check_unaligned_access_emulated(int cpu)
 	unsigned long tmp_var, tmp_val;
 	bool misaligned_emu_detected;
 
-	*mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+	*mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 
 	__asm__ __volatile__ (
 		"       "REG_L" %[tmp], 1(%[ptr])\n"
 		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
 
-	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED);
+	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED);
 	/*
 	 * If unaligned_ctl is already set, this means that we detected that all
 	 * CPUS uses emulated misaligned access at boot time. If that changed
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index a9a6bcb02acf..160628a2116d 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -34,9 +34,9 @@ static int check_unaligned_access(void *param)
 	struct page *page = param;
 	void *dst;
 	void *src;
-	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+	long speed = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
 
-	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
 		return 0;
 
 	/* Make an unaligned destination buffer. */
@@ -95,14 +95,14 @@ static int check_unaligned_access(void *param)
 	}
 
 	if (word_cycles < byte_cycles)
-		speed = RISCV_HWPROBE_MISALIGNED_FAST;
+		speed = RISCV_HWPROBE_MISALIGNED_SCALAR_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");
+		(speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
 
@@ -110,7 +110,7 @@ static int check_unaligned_access(void *param)
 	 * Set the value of fast_misaligned_access of a CPU. These operations
 	 * are atomic to avoid race conditions.
 	 */
-	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+	if (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST)
 		cpumask_set_cpu(cpu, &fast_misaligned_access);
 	else
 		cpumask_clear_cpu(cpu, &fast_misaligned_access);
@@ -188,7 +188,7 @@ 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)
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
 		goto exit;
 
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
index b6c1e7b5d34b..a8126d118341 100644
--- a/arch/riscv/kernel/vendor_extensions.c
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -38,7 +38,7 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig
 	#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES
 	case ANDES_VENDOR_ID:
 		bmap = &riscv_isa_vendor_ext_list_andes.all_harts_isa_bitmap;
-		cpu_bmap = &riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap[cpu];
+		cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap;
 		break;
 	#endif
 	default:
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8b698d9609e7..eb0649a61b4c 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -927,7 +927,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir,
 				   PMD_SIZE, PAGE_KERNEL_EXEC);
 
 	/* Map the data in RAM */
-	end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
+	end_va = kernel_map.virt_addr + kernel_map.size;
 	for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
 		create_pgd_mapping(pgdir, va,
 				   kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
@@ -1096,7 +1096,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	phys_ram_base = CONFIG_PHYS_RAM_BASE;
 	kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
-	kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
+	kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start);
 
 	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
 #else