Merge tag 'loongarch-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Define __ARCH_WANT_NEW_STAT in unistd.h

 - Always enumerate MADT and setup logical-physical CPU mapping

 - Add irq_work support via self IPIs

 - Add RANDOMIZE_KSTACK_OFFSET support

 - Add ARCH_HAS_PTE_DEVMAP support

 - Add ARCH_HAS_DEBUG_VM_PGTABLE support

 - Add writecombine support for DMW-based ioremap()

 - Add architectural preparation for CPUFreq

 - Add ACPI standard hardware register based S3 support

 - Add support for relocating the kernel with RELR relocation

 - Some bug fixes and other small changes

* tag 'loongarch-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  LoongArch: Make the users of larch_insn_gen_break() constant
  LoongArch: Check TIF_LOAD_WATCH to enable user space watchpoint
  LoongArch: Use rustc option -Zdirect-access-external-data
  LoongArch: Add support for relocating the kernel with RELR relocation
  LoongArch: Remove a redundant checking in relocator
  LoongArch: Use correct API to map cmdline in relocate_kernel()
  LoongArch: Automatically disable KASLR for hibernation
  LoongArch: Add ACPI standard hardware register based S3 support
  LoongArch: Add architectural preparation for CPUFreq
  LoongArch: Add writecombine support for DMW-based ioremap()
  LoongArch: Add ARCH_HAS_DEBUG_VM_PGTABLE support
  LoongArch: Add ARCH_HAS_PTE_DEVMAP support
  LoongArch: Add RANDOMIZE_KSTACK_OFFSET support
  LoongArch: Add irq_work support via self IPIs
  LoongArch: Always enumerate MADT and setup logical-physical CPU mapping
  LoongArch: Define __ARCH_WANT_NEW_STAT in unistd.h

12 files changed, 128 insertions, 30 deletions

diff --git a/arch/loongarch/kernel/Makefile.syscalls b/arch/loongarch/kernel/Makefile.syscalls
index ab7d9baa2915..523bb411a3bc 100644
--- a/arch/loongarch/kernel/Makefile.syscalls
+++ b/arch/loongarch/kernel/Makefile.syscalls
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-# No special ABIs on loongarch so far
-syscall_abis_64 +=
+syscall_abis_64 += newstat
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 5cf59c617126..929a497c987e 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -57,15 +57,22 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		return ioremap_cache(phys, size);
 }
 
+static int cpu_enumerated = 0;
+
 #ifdef CONFIG_SMP
 static int set_processor_mask(u32 id, u32 flags)
 {
-
+	int nr_cpus;
 	int cpu, cpuid = id;
 
-	if (num_processors >= nr_cpu_ids) {
-		pr_warn(PREFIX "nr_cpus/possible_cpus limit of %i reached."
-			" processor 0x%x ignored.\n", nr_cpu_ids, cpuid);
+	if (!cpu_enumerated)
+		nr_cpus = NR_CPUS;
+	else
+		nr_cpus = nr_cpu_ids;
+
+	if (num_processors >= nr_cpus) {
+		pr_warn(PREFIX "nr_cpus limit of %i reached."
+			" processor 0x%x ignored.\n", nr_cpus, cpuid);
 
 		return -ENODEV;
 
@@ -73,11 +80,13 @@ static int set_processor_mask(u32 id, u32 flags)
 	if (cpuid == loongson_sysconf.boot_cpu_id)
 		cpu = 0;
 	else
-		cpu = cpumask_next_zero(-1, cpu_present_mask);
+		cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
+
+	if (!cpu_enumerated)
+		set_cpu_possible(cpu, true);
 
 	if (flags & ACPI_MADT_ENABLED) {
 		num_processors++;
-		set_cpu_possible(cpu, true);
 		set_cpu_present(cpu, true);
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
@@ -138,6 +147,7 @@ static void __init acpi_process_madt(void)
 	acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC,
 			acpi_parse_eio_master, MAX_IO_PICS);
 
+	cpu_enumerated = 1;
 	loongson_sysconf.nr_cpus = num_processors;
 }
 
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 4677ea8fa8e9..506a99a5bbc7 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -44,11 +44,7 @@ SYM_DATA(kernel_fsize, .long _kernel_fsize);
 SYM_CODE_START(kernel_entry)			# kernel entry point
 
 	/* Config direct window and set PG */
-	li.d		t0, CSR_DMW0_INIT	# UC, PLV0, 0x8000 xxxx xxxx xxxx
-	csrwr		t0, LOONGARCH_CSR_DMWIN0
-	li.d		t0, CSR_DMW1_INIT	# CA, PLV0, 0x9000 xxxx xxxx xxxx
-	csrwr		t0, LOONGARCH_CSR_DMWIN1
-
+	SETUP_DMWINS	t0
 	JUMP_VIRT_ADDR	t0, t1
 
 	/* Enable PG */
@@ -124,11 +120,8 @@ SYM_CODE_END(kernel_entry)
  * function after setting up the stack and tp registers.
  */
 SYM_CODE_START(smpboot_entry)
-	li.d		t0, CSR_DMW0_INIT	# UC, PLV0
-	csrwr		t0, LOONGARCH_CSR_DMWIN0
-	li.d		t0, CSR_DMW1_INIT	# CA, PLV0
-	csrwr		t0, LOONGARCH_CSR_DMWIN1
 
+	SETUP_DMWINS	t0
 	JUMP_VIRT_ADDR	t0, t1
 
 #ifdef CONFIG_PAGE_SIZE_4KB
diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c
index 621ad7634df7..a6e4b605bfa8 100644
--- a/arch/loongarch/kernel/hw_breakpoint.c
+++ b/arch/loongarch/kernel/hw_breakpoint.c
@@ -221,7 +221,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
 		}
 		enable = csr_read64(LOONGARCH_CSR_CRMD);
 		csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD);
-		if (bp->hw.target)
+		if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH))
 			regs->csr_prmd |= CSR_PRMD_PWE;
 		break;
 	case HW_BREAKPOINT_UNINSTALL:
diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c
index 17b040bd6067..8ba391cfabb0 100644
--- a/arch/loongarch/kernel/kprobes.c
+++ b/arch/loongarch/kernel/kprobes.c
@@ -4,8 +4,8 @@
 #include <linux/preempt.h>
 #include <asm/break.h>
 
-#define KPROBE_BP_INSN		larch_insn_gen_break(BRK_KPROBE_BP)
-#define KPROBE_SSTEPBP_INSN	larch_insn_gen_break(BRK_KPROBE_SSTEPBP)
+#define KPROBE_BP_INSN		__emit_break(BRK_KPROBE_BP)
+#define KPROBE_SSTEPBP_INSN	__emit_break(BRK_KPROBE_SSTEPBP)
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe);
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index 9abe8b71aa48..9c9b75b76f62 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -2,6 +2,7 @@
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/irq_work.h>
 #include <linux/jump_label.h>
 #include <linux/kvm_para.h>
 #include <linux/reboot.h>
@@ -128,6 +129,11 @@ static irqreturn_t pv_ipi_interrupt(int irq, void *dev)
 		info->ipi_irqs[IPI_CALL_FUNCTION]++;
 	}
 
+	if (action & SMP_IRQ_WORK) {
+		irq_work_run();
+		info->ipi_irqs[IPI_IRQ_WORK]++;
+	}
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index 200109de1971..19dc6eff45cc 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -589,6 +589,7 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 	struct perf_event *bp;
 	struct perf_event_attr attr;
 	struct arch_hw_breakpoint_ctrl ctrl;
+	struct thread_info *ti = task_thread_info(tsk);
 
 	bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx);
 	if (IS_ERR(bp))
@@ -613,8 +614,10 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 		if (err)
 			return err;
 		attr.disabled = 0;
+		set_ti_thread_flag(ti, TIF_LOAD_WATCH);
 	} else {
 		attr.disabled = 1;
+		clear_ti_thread_flag(ti, TIF_LOAD_WATCH);
 	}
 
 	return modify_user_hw_breakpoint(bp, &attr);
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 1acfa704c8d0..50c469067f3a 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -13,6 +13,7 @@
 #include <asm/bootinfo.h>
 #include <asm/early_ioremap.h>
 #include <asm/inst.h>
+#include <asm/io.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 
@@ -34,11 +35,27 @@ static inline void __init relocate_relative(void)
 		if (rela->r_info != R_LARCH_RELATIVE)
 			continue;
 
-		if (relocated_addr >= VMLINUX_LOAD_ADDRESS)
-			relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr);
-
+		relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr);
 		*(Elf64_Addr *)RELOCATED(addr) = relocated_addr;
 	}
+
+#ifdef CONFIG_RELR
+	u64 *addr = NULL;
+	u64 *relr = (u64 *)&__relr_dyn_begin;
+	u64 *relr_end = (u64 *)&__relr_dyn_end;
+
+	for ( ; relr < relr_end; relr++) {
+		if ((*relr & 1) == 0) {
+			addr = (u64 *)(*relr + reloc_offset);
+			*addr++ += reloc_offset;
+		} else {
+			for (u64 *p = addr, r = *relr >> 1; r; p++, r >>= 1)
+				if (r & 1)
+					*p += reloc_offset;
+			addr += 63;
+		}
+	}
+#endif
 }
 
 static inline void __init relocate_absolute(long random_offset)
@@ -123,6 +140,32 @@ static inline __init bool kaslr_disabled(void)
 	if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' '))
 		return true;
 
+#ifdef CONFIG_HIBERNATION
+	str = strstr(builtin_cmdline, "nohibernate");
+	if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' '))
+		return false;
+
+	str = strstr(boot_command_line, "nohibernate");
+	if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' '))
+		return false;
+
+	str = strstr(builtin_cmdline, "noresume");
+	if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' '))
+		return false;
+
+	str = strstr(boot_command_line, "noresume");
+	if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' '))
+		return false;
+
+	str = strstr(builtin_cmdline, "resume=");
+	if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' '))
+		return true;
+
+	str = strstr(boot_command_line, "resume=");
+	if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' '))
+		return true;
+#endif
+
 	return false;
 }
 
@@ -170,7 +213,7 @@ unsigned long __init relocate_kernel(void)
 	unsigned long kernel_length;
 	unsigned long random_offset = 0;
 	void *location_new = _text; /* Default to original kernel start */
-	char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
+	char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
 
 	strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE);
 
@@ -182,6 +225,7 @@ unsigned long __init relocate_kernel(void)
 		random_offset = (unsigned long)location_new - (unsigned long)(_text);
 #endif
 	reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS;
+	early_memunmap(cmdline, COMMAND_LINE_SIZE);
 
 	if (random_offset) {
 		kernel_length = (long)(_end) - (long)(_text);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 3d048f1be143..0f0740f0be27 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -576,8 +576,10 @@ static void __init prefill_possible_map(void)
 
 	for (i = 0; i < possible; i++)
 		set_cpu_possible(i, true);
-	for (; i < NR_CPUS; i++)
+	for (; i < NR_CPUS; i++) {
+		set_cpu_present(i, false);
 		set_cpu_possible(i, false);
+	}
 
 	set_nr_cpu_ids(possible);
 }
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 1436d2465939..ca405ab86aae 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -13,6 +13,7 @@
 #include <linux/cpumask.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq_work.h>
 #include <linux/profile.h>
 #include <linux/seq_file.h>
 #include <linux/smp.h>
@@ -70,6 +71,7 @@ static DEFINE_PER_CPU(int, cpu_state);
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	[IPI_RESCHEDULE] = "Rescheduling interrupts",
 	[IPI_CALL_FUNCTION] = "Function call interrupts",
+	[IPI_IRQ_WORK] = "IRQ work interrupts",
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -217,6 +219,13 @@ void arch_smp_send_reschedule(int cpu)
 }
 EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	mp_ops.send_ipi_single(smp_processor_id(), ACTION_IRQ_WORK);
+}
+#endif
+
 static irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 {
 	unsigned int action;
@@ -234,6 +243,11 @@ static irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 		per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++;
 	}
 
+	if (action & SMP_IRQ_WORK) {
+		irq_work_run();
+		per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++;
+	}
+
 	return IRQ_HANDLED;
 }
 
@@ -271,11 +285,10 @@ static void __init fdt_smp_setup(void)
 		if (cpuid >= nr_cpu_ids)
 			continue;
 
-		if (cpuid == loongson_sysconf.boot_cpu_id) {
+		if (cpuid == loongson_sysconf.boot_cpu_id)
 			cpu = 0;
-		} else {
-			cpu = cpumask_next_zero(-1, cpu_present_mask);
-		}
+		else
+			cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
 
 		num_processors++;
 		set_cpu_possible(cpu, true);
diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c
index ec17cd5163b7..ba5d0930a74f 100644
--- a/arch/loongarch/kernel/syscall.c
+++ b/arch/loongarch/kernel/syscall.c
@@ -9,11 +9,14 @@
 #include <linux/entry-common.h>
 #include <linux/errno.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
+#include <linux/randomize_kstack.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 
 #include <asm/asm.h>
 #include <asm/exception.h>
+#include <asm/loongarch.h>
 #include <asm/signal.h>
 #include <asm/switch_to.h>
 #include <asm-generic/syscalls.h>
@@ -39,7 +42,7 @@ void *sys_call_table[__NR_syscalls] = {
 typedef long (*sys_call_fn)(unsigned long, unsigned long,
 	unsigned long, unsigned long, unsigned long, unsigned long);
 
-void noinstr do_syscall(struct pt_regs *regs)
+void noinstr __no_stack_protector do_syscall(struct pt_regs *regs)
 {
 	unsigned long nr;
 	sys_call_fn syscall_fn;
@@ -55,11 +58,28 @@ void noinstr do_syscall(struct pt_regs *regs)
 
 	nr = syscall_enter_from_user_mode(regs, nr);
 
+	add_random_kstack_offset();
+
 	if (nr < NR_syscalls) {
 		syscall_fn = sys_call_table[nr];
 		regs->regs[4] = syscall_fn(regs->orig_a0, regs->regs[5], regs->regs[6],
 					   regs->regs[7], regs->regs[8], regs->regs[9]);
 	}
 
+	/*
+	 * This value will get limited by KSTACK_OFFSET_MAX(), which is 10
+	 * bits. The actual entropy will be further reduced by the compiler
+	 * when applying stack alignment constraints: 16-bytes (i.e. 4-bits)
+	 * aligned, which will remove the 4 low bits from any entropy chosen
+	 * here.
+	 *
+	 * The resulting 6 bits of entropy is seen in SP[9:4].
+	 */
+	choose_random_kstack_offset(drdtime());
+
 	syscall_exit_to_user_mode(regs);
 }
+
+#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
+STACK_FRAME_NON_STANDARD(do_syscall);
+#endif
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index 3c7595342730..08ea921cdec1 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -113,6 +113,14 @@ SECTIONS
 		__rela_dyn_end = .;
 	}
 
+#ifdef CONFIG_RELR
+	.relr.dyn : ALIGN(8) {
+		__relr_dyn_begin = .;
+		 *(.relr.dyn)
+		__relr_dyn_end = .;
+	}
+#endif
+
 	.data.rel : { *(.data.rel*) }
 
 #ifdef CONFIG_RELOCATABLE