diff options
Diffstat (limited to 'arch/loongarch/kernel')
58 files changed, 1768 insertions, 797 deletions
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index c9bfeda89e40..001924877772 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -5,12 +5,12 @@ OBJECT_FILES_NON_STANDARD_head.o := y -extra-y := vmlinux.lds +always-$(KBUILD_BUILTIN) := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ - traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ + traps.o irq.o idle.o process.o dma.o mem.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unwind.o + alternative.o kdebugfs.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o @@ -21,10 +21,10 @@ obj-$(CONFIG_CPU_HAS_LBT) += lbt.o obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o -CFLAGS_module.o += $(call cc-option,-Wno-override-init,) -CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,) -CFLAGS_traps.o += $(call cc-option,-Wno-override-init,) -CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,) +CFLAGS_module.o += $(call cc-disable-warning, override-init) +CFLAGS_syscall.o += $(call cc-disable-warning, override-init) +CFLAGS_traps.o += $(call cc-disable-warning, override-init) +CFLAGS_perf_event.o += $(call cc-disable-warning, override-init) ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE @@ -62,6 +62,7 @@ obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o obj-$(CONFIG_RELOCATABLE) += relocate.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_efi.o kexec_elf.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o diff --git a/arch/loongarch/kernel/Makefile.syscalls b/arch/loongarch/kernel/Makefile.syscalls new file mode 100644 index 000000000000..ab7d9baa2915 --- /dev/null +++ b/arch/loongarch/kernel/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +# No special ABIs on loongarch so far +syscall_abis_64 += diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 5cf59c617126..1367ca759468 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -9,6 +9,8 @@ #include <linux/init.h> #include <linux/acpi.h> +#include <linux/efi-bgrt.h> +#include <linux/export.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/memblock.h> @@ -58,38 +60,47 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) } #ifdef CONFIG_SMP -static int set_processor_mask(u32 id, u32 flags) +static int set_processor_mask(u32 id, u32 pass) { + int cpu = -1, cpuid = id; - 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 (num_processors >= NR_CPUS) { + pr_warn(PREFIX "nr_cpus limit of %i reached." + " processor 0x%x ignored.\n", NR_CPUS, cpuid); return -ENODEV; } + if (cpuid == loongson_sysconf.boot_cpu_id) cpu = 0; - else - cpu = cpumask_next_zero(-1, cpu_present_mask); - if (flags & ACPI_MADT_ENABLED) { + switch (pass) { + case 1: /* Pass 1 handle enabled processors */ + if (cpu < 0) + cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS); num_processors++; - set_cpu_possible(cpu, true); set_cpu_present(cpu, true); - __cpu_number_map[cpuid] = cpu; - __cpu_logical_map[cpu] = cpuid; - } else + break; + case 2: /* Pass 2 handle disabled processors */ + if (cpu < 0) + cpu = find_first_zero_bit(cpumask_bits(cpu_possible_mask), NR_CPUS); disabled_cpus++; + break; + default: + return cpu; + } + + set_cpu_possible(cpu, true); + __cpu_number_map[cpuid] = cpu; + __cpu_logical_map[cpu] = cpuid; return cpu; } #endif static int __init -acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long end) +acpi_parse_p1_processor(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_core_pic *processor = NULL; @@ -100,13 +111,30 @@ acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long en acpi_table_print_madt_entry(&header->common); #ifdef CONFIG_SMP acpi_core_pic[processor->core_id] = *processor; - set_processor_mask(processor->core_id, processor->flags); + if (processor->flags & ACPI_MADT_ENABLED) + set_processor_mask(processor->core_id, 1); #endif return 0; } static int __init +acpi_parse_p2_processor(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_core_pic *processor = NULL; + + processor = (struct acpi_madt_core_pic *)header; + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + +#ifdef CONFIG_SMP + if (!(processor->flags & ACPI_MADT_ENABLED)) + set_processor_mask(processor->core_id, 2); +#endif + + return 0; +} +static int __init acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long end) { static int core = 0; @@ -133,7 +161,10 @@ static void __init acpi_process_madt(void) } #endif acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC, - acpi_parse_processor, MAX_CORE_PIC); + acpi_parse_p1_processor, MAX_CORE_PIC); + + acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC, + acpi_parse_p2_processor, MAX_CORE_PIC); acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, acpi_parse_eio_master, MAX_IO_PICS); @@ -202,6 +233,9 @@ void __init acpi_boot_table_init(void) /* Do not enable ACPI SPCR console by default */ acpi_parse_spcr(earlycon_acpi_spcr_enable, false); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); + return; fdt_earlycon: @@ -211,34 +245,6 @@ fdt_earlycon: #ifdef CONFIG_ACPI_NUMA -static __init int setup_node(int pxm) -{ - return acpi_map_pxm_to_node(pxm); -} - -/* - * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for - * I/O localities since SRAT does not list them. I/O localities are - * not supported at this point. - */ -unsigned int numa_distance_cnt; - -static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit) -{ - return slit->locality_count; -} - -void __init numa_set_distance(int from, int to, int distance) -{ - if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - node_distances[from][to] = distance; -} - /* Callback for Proximity Domain -> CPUID mapping */ void __init acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) @@ -259,7 +265,41 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pxm |= (pa->proximity_domain_hi[1] << 16); pxm |= (pa->proximity_domain_hi[2] << 24); } - node = setup_node(pxm); + node = acpi_map_pxm_to_node(pxm); + if (node < 0) { + pr_err("SRAT: Too many proximity domains %x\n", pxm); + bad_srat(); + return; + } + + if (pa->apic_id >= CONFIG_NR_CPUS) { + pr_info("SRAT: PXM %u -> CPU 0x%02x -> Node %u skipped apicid that is too big\n", + pxm, pa->apic_id, node); + return; + } + + early_numa_add_cpu(pa->apic_id, node); + + set_cpuid_to_node(pa->apic_id, node); + node_set(node, numa_nodes_parsed); + pr_info("SRAT: PXM %u -> CPU 0x%02x -> Node %u\n", pxm, pa->apic_id, node); +} + +void __init +acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) +{ + int pxm, node; + + if (srat_disabled()) + return; + if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) { + bad_srat(); + return; + } + if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) + return; + pxm = pa->proximity_domain; + node = acpi_map_pxm_to_node(pxm); if (node < 0) { pr_err("SRAT: Too many proximity domains %x\n", pxm); bad_srat(); @@ -296,6 +336,10 @@ static int __ref acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) int nid; nid = acpi_get_node(handle); + + if (nid != NUMA_NO_NODE) + nid = early_cpu_to_node(cpu); + if (nid != NUMA_NO_NODE) { set_cpuid_to_node(physid, nid); node_set(nid, numa_nodes_parsed); @@ -310,12 +354,14 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu { int cpu; - cpu = set_processor_mask(physid, ACPI_MADT_ENABLED); - if (cpu < 0) { + cpu = cpu_number_map(physid); + if (cpu < 0 || cpu >= nr_cpu_ids) { pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); - return cpu; + return -ERANGE; } + num_processors++; + set_cpu_present(cpu, true); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c index 4ad13847e962..0e0c766df1e3 100644 --- a/arch/loongarch/kernel/alternative.c +++ b/arch/loongarch/kernel/alternative.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/export.h> #include <linux/mm.h> #include <linux/module.h> #include <asm/alternative.h> diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index bee9f7a3108f..3017c7157600 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -4,6 +4,8 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#define COMPILE_OFFSETS + #include <linux/types.h> #include <linux/sched.h> #include <linux/mm.h> @@ -14,6 +16,7 @@ #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/ftrace.h> +#include <vdso/datapage.h> static void __used output_ptreg_defines(void) { @@ -279,18 +282,6 @@ static void __used output_pbe_defines(void) } #endif -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __used output_fgraph_ret_regs_defines(void) -{ - COMMENT("LoongArch fgraph_ret_regs offsets."); - OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]); - OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]); - OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); - BLANK(); -} -#endif - static void __used output_kvm_defines(void) { COMMENT("KVM/LoongArch Specific offsets."); @@ -307,6 +298,7 @@ static void __used output_kvm_defines(void) OFFSET(KVM_ARCH_HSP, kvm_vcpu_arch, host_sp); OFFSET(KVM_ARCH_HTP, kvm_vcpu_arch, host_tp); OFFSET(KVM_ARCH_HPGD, kvm_vcpu_arch, host_pgd); + OFFSET(KVM_ARCH_KVMPGD, kvm_vcpu_arch, kvm_pgd); OFFSET(KVM_ARCH_HANDLE_EXIT, kvm_vcpu_arch, handle_exit); OFFSET(KVM_ARCH_HEENTRY, kvm_vcpu_arch, host_eentry); OFFSET(KVM_ARCH_GEENTRY, kvm_vcpu_arch, guest_eentry); @@ -321,3 +313,11 @@ static void __used output_kvm_defines(void) OFFSET(KVM_GPGD, kvm, arch.pgd); BLANK(); } + +static void __used output_vdso_defines(void) +{ + COMMENT("LoongArch vDSO offsets."); + + DEFINE(__VDSO_PAGES, VDSO_NR_PAGES); + BLANK(); +} diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index c7988f757281..8e231b0d2cd6 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -51,6 +51,12 @@ static void cache_cpumap_setup(unsigned int cpu) continue; sib_leaf = sib_cpu_ci->info_list + index; + /* SMT cores share all caches */ + if (cpus_are_siblings(i, cpu)) { + cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); + cpumask_set_cpu(i, &this_leaf->shared_cpu_map); + } + /* Node's cores share shared caches */ if (cache_leaves_are_shared(this_leaf, sib_leaf)) { cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); cpumask_set_cpu(i, &this_leaf->shared_cpu_map); diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 55320813ee08..a2060a24b39f 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -52,6 +52,48 @@ static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_loongarch *c) c->fpu_mask = ~(fcsr0 ^ fcsr1) & ~mask; } +/* simd = -1/0/128/256 */ +static unsigned int simd = -1U; + +static int __init cpu_setup_simd(char *str) +{ + get_option(&str, &simd); + pr_info("Set SIMD width = %u\n", simd); + + return 0; +} + +early_param("simd", cpu_setup_simd); + +static int __init cpu_final_simd(void) +{ + struct cpuinfo_loongarch *c = &cpu_data[0]; + + if (simd < 128) { + c->options &= ~LOONGARCH_CPU_LSX; + elf_hwcap &= ~HWCAP_LOONGARCH_LSX; + } + + if (simd < 256) { + c->options &= ~LOONGARCH_CPU_LASX; + elf_hwcap &= ~HWCAP_LOONGARCH_LASX; + } + + simd = 0; + + if (c->options & LOONGARCH_CPU_LSX) + simd = 128; + + if (c->options & LOONGARCH_CPU_LASX) + simd = 256; + + pr_info("Final SIMD width = %u\n", simd); + + return 0; +} + +arch_initcall(cpu_final_simd); + static inline void set_elf_platform(int cpu, const char *plat) { if (cpu == 0) @@ -91,12 +133,32 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) unsigned int config; unsigned long asid_mask; - c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | - LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; + c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_VINT; elf_hwcap = HWCAP_LOONGARCH_CPUCFG; config = read_cpucfg(LOONGARCH_CPUCFG1); + + switch (config & CPUCFG1_ISA) { + case 0: + set_isa(c, LOONGARCH_CPU_ISA_LA32R); + break; + case 1: + set_isa(c, LOONGARCH_CPU_ISA_LA32S); + break; + case 2: + set_isa(c, LOONGARCH_CPU_ISA_LA64); + break; + default: + pr_warn("Warning: unknown ISA level\n"); + } + + if (config & CPUCFG1_PAGING) + c->options |= LOONGARCH_CPU_TLB; + if (config & CPUCFG1_IOCSR) + c->options |= LOONGARCH_CPU_IOCSR; + if (config & CPUCFG1_MSGINT) + c->options |= LOONGARCH_CPU_MSGINT; if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; @@ -106,7 +168,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) elf_hwcap |= HWCAP_LOONGARCH_CRC32; } - config = read_cpucfg(LOONGARCH_CPUCFG2); if (config & CPUCFG2_LAM) { c->options |= LOONGARCH_CPU_LAM; @@ -117,13 +178,13 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) elf_hwcap |= HWCAP_LOONGARCH_FPU; } #ifdef CONFIG_CPU_HAS_LSX - if (config & CPUCFG2_LSX) { + if ((config & CPUCFG2_LSX) && (simd >= 128)) { c->options |= LOONGARCH_CPU_LSX; elf_hwcap |= HWCAP_LOONGARCH_LSX; } #endif #ifdef CONFIG_CPU_HAS_LASX - if (config & CPUCFG2_LASX) { + if ((config & CPUCFG2_LASX) && (simd >= 256)) { c->options |= LOONGARCH_CPU_LASX; elf_hwcap |= HWCAP_LOONGARCH_LASX; } @@ -140,6 +201,10 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_PTW; elf_hwcap |= HWCAP_LOONGARCH_PTW; } + if (config & CPUCFG2_LSPW) { + c->options |= LOONGARCH_CPU_LSPW; + elf_hwcap |= HWCAP_LOONGARCH_LSPW; + } if (config & CPUCFG2_LVZP) { c->options |= LOONGARCH_CPU_LVZ; elf_hwcap |= HWCAP_LOONGARCH_LVZ; @@ -163,26 +228,13 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) if (config & CPUCFG6_PMP) c->options |= LOONGARCH_CPU_PMP; - config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); - if (config & IOCSRF_CSRIPI) - c->options |= LOONGARCH_CPU_CSRIPI; - if (config & IOCSRF_EXTIOI) - c->options |= LOONGARCH_CPU_EXTIOI; - if (config & IOCSRF_FREQSCALE) - c->options |= LOONGARCH_CPU_SCALEFREQ; - if (config & IOCSRF_FLATMODE) - c->options |= LOONGARCH_CPU_FLATMODE; - if (config & IOCSRF_EIODECODE) - c->options |= LOONGARCH_CPU_EIODECODE; - if (config & IOCSRF_VM) - c->options |= LOONGARCH_CPU_HYPERVISOR; - config = csr_read32(LOONGARCH_CSR_ASID); config = (config & CSR_ASID_BIT) >> CSR_ASID_BIT_SHIFT; asid_mask = GENMASK(config - 1, 0); set_cpu_asid_mask(c, asid_mask); config = read_csr_prcfg1(); + c->timerbits = (config & CSR_CONF1_TMRBITS) >> CSR_CONF1_TMRBITS_SHIFT; c->ksave_mask = GENMASK((config & CSR_CONF1_KSNUM) - 1, 0); c->ksave_mask &= ~(EXC_KSAVE_MASK | PERCPU_KSAVE_MASK | KVM_KSAVE_MASK); @@ -209,6 +261,9 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) default: pr_warn("Warning: unknown TLB type\n"); } + + if (get_num_brps() + get_num_wrps()) + c->options |= LOONGARCH_CPU_WATCH; } #define MAX_NAME_LEN 32 @@ -219,52 +274,57 @@ static char cpu_full_name[MAX_NAME_LEN] = " - "; static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int cpu) { + uint32_t config; uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]); uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]); + const char *core_name = id_to_core_name(c->processor_id); - if (!__cpu_full_name[cpu]) - __cpu_full_name[cpu] = cpu_full_name; - - *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); - *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); - - switch (c->processor_id & PRID_SERIES_MASK) { - case PRID_SERIES_LA132: + switch (BIT(fls(c->isa_level) - 1)) { + case LOONGARCH_CPU_ISA_LA32R: + case LOONGARCH_CPU_ISA_LA32S: c->cputype = CPU_LOONGSON32; - set_isa(c, LOONGARCH_CPU_ISA_LA32S); __cpu_family[cpu] = "Loongson-32bit"; - pr_info("32-bit Loongson Processor probed (LA132 Core)\n"); - break; - case PRID_SERIES_LA264: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA264 Core)\n"); break; - case PRID_SERIES_LA364: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA364 Core)\n"); - break; - case PRID_SERIES_LA464: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA464 Core)\n"); - break; - case PRID_SERIES_LA664: + case LOONGARCH_CPU_ISA_LA64: c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA664 Core)\n"); break; - default: /* Default to 64 bit */ - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (Unknown Core)\n"); } + + pr_info("%s Processor probed (%s Core)\n", __cpu_family[cpu], core_name); + + if (!cpu_has_iocsr) { + __cpu_full_name[cpu] = "Unknown"; + return; + } + + *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); + *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); + + if (!__cpu_full_name[cpu]) { + if (((char *)vendor)[0] == 0) + __cpu_full_name[cpu] = "Unknown"; + else + __cpu_full_name[cpu] = cpu_full_name; + } + + config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); + if (config & IOCSRF_CSRIPI) + c->options |= LOONGARCH_CPU_CSRIPI; + if (config & IOCSRF_EXTIOI) + c->options |= LOONGARCH_CPU_EXTIOI; + if (config & IOCSRF_FREQSCALE) + c->options |= LOONGARCH_CPU_SCALEFREQ; + if (config & IOCSRF_FLATMODE) + c->options |= LOONGARCH_CPU_FLATMODE; + if (config & IOCSRF_EIODECODE) + c->options |= LOONGARCH_CPU_EIODECODE; + if (config & IOCSRF_AVEC) + c->options |= LOONGARCH_CPU_AVECINT; + if (config & IOCSRF_REDIRECT) + c->options |= LOONGARCH_CPU_REDIRECTINT; + if (config & IOCSRF_VM) + c->options |= LOONGARCH_CPU_HYPERVISOR; } #ifdef CONFIG_64BIT diff --git a/arch/loongarch/kernel/efi-header.S b/arch/loongarch/kernel/efi-header.S index 5f23b85d78ca..ba0bdbf86aa8 100644 --- a/arch/loongarch/kernel/efi-header.S +++ b/arch/loongarch/kernel/efi-header.S @@ -7,7 +7,7 @@ #include <linux/sizes.h> .macro __EFI_PE_HEADER - .long PE_MAGIC + .long IMAGE_NT_SIGNATURE .Lcoff_header: .short IMAGE_FILE_MACHINE_LOONGARCH64 /* Machine */ .short .Lsection_count /* NumberOfSections */ @@ -20,7 +20,7 @@ IMAGE_FILE_LINE_NUMS_STRIPPED /* Characteristics */ .Loptional_header: - .short PE_OPT_MAGIC_PE32PLUS /* PE32+ format */ + .short IMAGE_NT_OPTIONAL_HDR64_MAGIC /* PE32+ format */ .byte 0x02 /* MajorLinkerVersion */ .byte 0x14 /* MinorLinkerVersion */ .long __inittext_end - .Lefi_header_end /* SizeOfCode */ diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 000825406c1f..860a3bc030e0 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -66,6 +66,12 @@ void __init efi_runtime_init(void) set_bit(EFI_RUNTIME_SERVICES, &efi.flags); } +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES) && + (acpi_gbl_reduced_hardware || acpi_no_s5); +} + unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) @@ -89,7 +95,7 @@ static void __init init_screen_info(void) memset(si, 0, sizeof(*si)); early_memunmap(si, sizeof(*si)); - memblock_reserve(screen_info.lfb_base, screen_info.lfb_size); + memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size); } void __init efi_init(void) @@ -138,6 +144,18 @@ void __init efi_init(void) if (efi_memmap_init_early(&data) < 0) panic("Unable to map EFI memory map.\n"); + /* + * Reserve the physical memory region occupied by the EFI + * memory map table (header + descriptors). This is crucial + * for kdump, as the kdump kernel relies on this original + * memmap passed by the bootloader. Without reservation, + * this region could be overwritten by the primary kernel. + * Also, set the EFI_PRESERVE_BS_REGIONS flag to indicate that + * critical boot services code/data regions like this are preserved. + */ + memblock_reserve((phys_addr_t)boot_memmap, sizeof(*tbl) + data.size); + set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags); + early_memunmap(tbl, sizeof(*tbl)); } diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c index 0fa81ced28dc..3d98c6aa00db 100644 --- a/arch/loongarch/kernel/elf.c +++ b/arch/loongarch/kernel/elf.c @@ -6,7 +6,6 @@ #include <linux/binfmts.h> #include <linux/elf.h> -#include <linux/export.h> #include <linux/sched.h> #include <asm/cpu-features.h> diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index 48e7e34e355e..47e1db9a1ce4 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -73,28 +73,29 @@ SYM_CODE_START(handle_syscall) move a0, sp bl do_syscall + STACKLEAK_ERASE RESTORE_ALL_AND_RET SYM_CODE_END(handle_syscall) _ASM_NOKPROBE(handle_syscall) -SYM_CODE_START(ret_from_fork) +SYM_CODE_START(ret_from_fork_asm) UNWIND_HINT_REGS - bl schedule_tail # a0 = struct task_struct *prev - move a0, sp - bl syscall_exit_to_user_mode + move a1, sp + bl ret_from_fork + STACKLEAK_ERASE RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_asm) -SYM_CODE_START(ret_from_kernel_thread) +SYM_CODE_START(ret_from_kernel_thread_asm) UNWIND_HINT_REGS - bl schedule_tail # a0 = struct task_struct *prev - move a0, s1 - jirl ra, s0, 0 - move a0, sp - bl syscall_exit_to_user_mode + move a1, sp + move a2, s0 + move a3, s1 + bl ret_from_kernel_thread + STACKLEAK_ERASE RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET -SYM_CODE_END(ret_from_kernel_thread) +SYM_CODE_END(ret_from_kernel_thread_asm) diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 2f1f5b08638f..23bd5ae2212c 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -39,16 +39,19 @@ void __init init_environ(void) static int __init init_cpu_fullname(void) { - struct device_node *root; int cpu, ret; - char *model; + char *cpuname; + const char *model; + struct device_node *root; /* Parsing cpuname from DTS model property */ root = of_find_node_by_path("/"); - ret = of_property_read_string(root, "model", (const char **)&model); + ret = of_property_read_string(root, "model", &model); + if (ret == 0) { + cpuname = kstrdup(model, GFP_KERNEL); + loongson_sysconf.cpuname = strsep(&cpuname, " "); + } of_node_put(root); - if (ret == 0) - loongson_sysconf.cpuname = strsep(&model, " "); if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) { for (cpu = 0; cpu < NR_CPUS; cpu++) @@ -68,6 +71,8 @@ static int __init fdt_cpu_clk_init(void) return -ENODEV; clk = of_clk_get(np, 0); + of_node_put(np); + if (IS_ERR(clk)) return -ENODEV; @@ -81,7 +86,7 @@ late_initcall(fdt_cpu_clk_init); static ssize_t boardinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, + return sysfs_emit(buf, "BIOS Information\n" "Vendor\t\t\t: %s\n" "Version\t\t\t: %s\n" @@ -104,6 +109,8 @@ static int __init boardinfo_init(void) struct kobject *loongson_kobj; loongson_kobj = kobject_create_and_add("loongson", firmware_kobj); + if (!loongson_kobj) + return -ENOMEM; return sysfs_create_file(loongson_kobj, &boardinfo_attr.attr); } diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index 69a85f2479fb..28caf416ae36 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -458,6 +458,7 @@ SYM_FUNC_START(_save_fp_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_save_fp_context) +EXPORT_SYMBOL_GPL(_save_fp_context) /* * a0: fpregs @@ -471,6 +472,7 @@ SYM_FUNC_START(_restore_fp_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_restore_fp_context) +EXPORT_SYMBOL_GPL(_restore_fp_context) /* * a0: fpregs @@ -484,6 +486,7 @@ SYM_FUNC_START(_save_lsx_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_save_lsx_context) +EXPORT_SYMBOL_GPL(_save_lsx_context) /* * a0: fpregs @@ -497,6 +500,7 @@ SYM_FUNC_START(_restore_lsx_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_restore_lsx_context) +EXPORT_SYMBOL_GPL(_restore_lsx_context) /* * a0: fpregs @@ -510,6 +514,7 @@ SYM_FUNC_START(_save_lasx_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_save_lasx_context) +EXPORT_SYMBOL_GPL(_save_lasx_context) /* * a0: fpregs @@ -523,6 +528,7 @@ SYM_FUNC_START(_restore_lasx_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_restore_lasx_context) +EXPORT_SYMBOL_GPL(_restore_lasx_context) .L_fpu_fault: li.w a0, -EFAULT # failure @@ -530,6 +536,10 @@ SYM_FUNC_END(_restore_lasx_context) #ifdef CONFIG_CPU_HAS_LBT STACK_FRAME_NON_STANDARD _restore_fp +#ifdef CONFIG_CPU_HAS_LSX STACK_FRAME_NON_STANDARD _restore_lsx +#endif +#ifdef CONFIG_CPU_HAS_LASX STACK_FRAME_NON_STANDARD _restore_lasx #endif +#endif diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index bff058317062..d5d81d74034c 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -85,14 +85,13 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod * dealing with an out-of-range condition, we can assume it * is due to a module being loaded far away from the kernel. * - * NOTE: __module_text_address() must be called with preemption - * disabled, but we can rely on ftrace_lock to ensure that 'mod' + * NOTE: __module_text_address() must be called within a RCU read + * section, but we can rely on ftrace_lock to ensure that 'mod' * retains its validity throughout the remainder of this code. */ if (!mod) { - preempt_disable(); - mod = __module_text_address(pc); - preempt_enable(); + scoped_guard(rcu) + mod = __module_text_address(pc); } if (WARN_ON(!mod)) @@ -241,10 +240,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent) void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - struct pt_regs *regs = &fregs->regs; + struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *parent = (unsigned long *)®s->regs[1]; + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; - prepare_ftrace_return(ip, (unsigned long *)parent); + if (!function_graph_enter_regs(old, ip, 0, parent, fregs)) + *parent = return_hooker; } #else static int ftrace_modify_graph_caller(bool enable) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 86d5d90ebefe..733a7665e434 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -16,30 +16,35 @@ #include <asm/stackframe.h> #include <asm/thread_info.h> + .section .cpuidle.text, "ax" .align 5 SYM_FUNC_START(__arch_cpu_idle) - /* start of rollback region */ - LONG_L t0, tp, TI_FLAGS - nop - andi t0, t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop + /* start of idle interrupt region */ + ori t0, zero, CSR_CRMD_IE + /* idle instruction needs irq enabled */ + csrxchg t0, t0, LOONGARCH_CSR_CRMD + /* + * If an interrupt lands here; between enabling interrupts above and + * going idle on the next instruction, we must *NOT* go idle since the + * interrupt could have set TIF_NEED_RESCHED or caused an timer to need + * reprogramming. Fall through -- see handle_vint() below -- and have + * the idle loop take care of things. + */ idle 0 - /* end of rollback region */ -1: jr ra + /* end of idle interrupt region */ +idle_exit: + jr ra SYM_FUNC_END(__arch_cpu_idle) + .previous SYM_CODE_START(handle_vint) UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL - la_abs t1, __arch_cpu_idle + la_abs t1, idle_exit LONG_L t0, sp, PT_ERA - /* 32 byte rollback region */ - ori t0, t0, 0x1f - xori t0, t0, 0x1f + /* 3 instructions idle interrupt region */ + ori t0, t0, 0b1100 bne t0, t1, 1f LONG_S t0, sp, PT_ERA 1: move a0, sp diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 4677ea8fa8e9..e3865e92a917 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -20,7 +20,7 @@ __HEAD _head: - .word MZ_MAGIC /* "MZ", MS-DOS header */ + .word IMAGE_DOS_SIGNATURE /* "MZ", MS-DOS header */ .org 0x8 .dword _kernel_entry /* Kernel entry point (physical address) */ .dword _kernel_asize /* Kernel image effective size */ @@ -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..c35f9bf38033 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -51,7 +51,13 @@ int hw_breakpoint_slots(int type) READ_WB_REG_CASE(OFF, 4, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 5, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - READ_WB_REG_CASE(OFF, 7, REG, T, VAL); + READ_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 13, REG, T, VAL); #define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL) \ WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL); \ @@ -61,7 +67,13 @@ int hw_breakpoint_slots(int type) WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); + WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 13, REG, T, VAL); static u64 read_wb_reg(int reg, int n, int t) { @@ -221,7 +233,7 @@ 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/idle.c b/arch/loongarch/kernel/idle.c index 0b5dd2faeb90..54b247d8cdb6 100644 --- a/arch/loongarch/kernel/idle.c +++ b/arch/loongarch/kernel/idle.c @@ -11,7 +11,6 @@ void __cpuidle arch_cpu_idle(void) { - raw_local_irq_enable(); - __arch_cpu_idle(); /* idle instruction needs irq enabled */ + __arch_cpu_idle(); raw_local_irq_disable(); } diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 3050329556d1..bf037f0c6b26 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -4,6 +4,8 @@ */ #include <linux/sizes.h> #include <linux/uaccess.h> +#include <linux/set_memory.h> +#include <linux/stop_machine.h> #include <asm/cacheflush.h> #include <asm/inst.h> @@ -139,6 +141,9 @@ bool insns_not_supported(union loongarch_instruction insn) case amswapw_op ... ammindbdu_op: pr_notice("atomic memory access instructions are not supported\n"); return true; + case scq_op: + pr_notice("sc.q instruction is not supported\n"); + return true; } switch (insn.reg2i14_format.opcode) { @@ -150,6 +155,15 @@ bool insns_not_supported(union loongarch_instruction insn) return true; } + switch (insn.reg2_format.opcode) { + case llacqw_op: + case llacqd_op: + case screlw_op: + case screld_op: + pr_notice("llacq and screl instructions are not supported\n"); + return true; + } + switch (insn.reg1i21_format.opcode) { case bceqz_op: pr_notice("bceqz and bcnez instructions are not supported\n"); @@ -218,6 +232,50 @@ int larch_insn_patch_text(void *addr, u32 insn) return ret; } +struct insn_copy { + void *dst; + void *src; + size_t len; + unsigned int cpu; +}; + +static int text_copy_cb(void *data) +{ + int ret = 0; + struct insn_copy *copy = data; + + if (smp_processor_id() == copy->cpu) { + ret = copy_to_kernel_nofault(copy->dst, copy->src, copy->len); + if (ret) + pr_err("%s: operation failed\n", __func__); + } + + flush_icache_range((unsigned long)copy->dst, (unsigned long)copy->dst + copy->len); + + return ret; +} + +int larch_insn_text_copy(void *dst, void *src, size_t len) +{ + int ret = 0; + size_t start, end; + struct insn_copy copy = { + .dst = dst, + .src = src, + .len = len, + .cpu = smp_processor_id(), + }; + + start = round_down((size_t)dst, PAGE_SIZE); + end = round_up((size_t)dst + len, PAGE_SIZE); + + set_memory_rw(start, (end - start) / PAGE_SIZE); + ret = stop_machine(text_copy_cb, ©, cpu_online_mask); + set_memory_rox(start, (end - start) / PAGE_SIZE); + + return ret; +} + u32 larch_insn_gen_nop(void) { return INSN_NOP; @@ -323,6 +381,34 @@ u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) return insn.word; } +u32 larch_insn_gen_beq(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) +{ + union loongarch_instruction insn; + + if ((imm & 3) || imm < -SZ_128K || imm >= SZ_128K) { + pr_warn("The generated beq instruction is out of range.\n"); + return INSN_BREAK; + } + + emit_beq(&insn, rj, rd, imm >> 2); + + return insn.word; +} + +u32 larch_insn_gen_bne(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) +{ + union loongarch_instruction insn; + + if ((imm & 3) || imm < -SZ_128K || imm >= SZ_128K) { + pr_warn("The generated bne instruction is out of range.\n"); + return INSN_BREAK; + } + + emit_bne(&insn, rj, rd, imm >> 2); + + return insn.word; +} + u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) { union loongarch_instruction insn; @@ -332,7 +418,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) return INSN_BREAK; } - emit_jirl(&insn, rj, rd, imm >> 2); + emit_jirl(&insn, rd, rj, imm >> 2); return insn.word; } diff --git a/arch/loongarch/kernel/io.c b/arch/loongarch/kernel/io.c deleted file mode 100644 index cb85bda5a6ad..000000000000 --- a/arch/loongarch/kernel/io.c +++ /dev/null @@ -1,94 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#include <linux/export.h> -#include <linux/types.h> -#include <linux/io.h> - -/* - * Copy data from IO memory space to "real" memory space. - */ -void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) -{ - while (count && !IS_ALIGNED((unsigned long)from, 8)) { - *(u8 *)to = __raw_readb(from); - from++; - to++; - count--; - } - - while (count >= 8) { - *(u64 *)to = __raw_readq(from); - from += 8; - to += 8; - count -= 8; - } - - while (count) { - *(u8 *)to = __raw_readb(from); - from++; - to++; - count--; - } -} -EXPORT_SYMBOL(__memcpy_fromio); - -/* - * Copy data from "real" memory space to IO memory space. - */ -void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count) -{ - while (count && !IS_ALIGNED((unsigned long)to, 8)) { - __raw_writeb(*(u8 *)from, to); - from++; - to++; - count--; - } - - while (count >= 8) { - __raw_writeq(*(u64 *)from, to); - from += 8; - to += 8; - count -= 8; - } - - while (count) { - __raw_writeb(*(u8 *)from, to); - from++; - to++; - count--; - } -} -EXPORT_SYMBOL(__memcpy_toio); - -/* - * "memset" on IO memory space. - */ -void __memset_io(volatile void __iomem *dst, int c, size_t count) -{ - u64 qc = (u8)c; - - qc |= qc << 8; - qc |= qc << 16; - qc |= qc << 32; - - while (count && !IS_ALIGNED((unsigned long)dst, 8)) { - __raw_writeb(c, dst); - dst++; - count--; - } - - while (count >= 8) { - __raw_writeq(qc, dst); - dst += 8; - count -= 8; - } - - while (count) { - __raw_writeb(c, dst); - dst++; - count--; - } -} -EXPORT_SYMBOL(__memset_io); diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index f4991c03514f..80946cafaec1 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -87,6 +87,18 @@ static void __init init_vec_parent_group(void) acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse); } +int __init arch_probe_nr_irqs(void) +{ + int nr_io_pics = bitmap_weight(loongson_sysconf.cores_io_master, NR_CPUS); + + if (!cpu_has_avecint) + irq_set_nr_irqs(64 + NR_VECTORS * nr_io_pics); + else + irq_set_nr_irqs(64 + NR_VECTORS * (nr_cpu_ids + nr_io_pics)); + + return NR_IRQS_LEGACY; +} + void __init init_IRQ(void) { int i; @@ -102,9 +114,6 @@ void __init init_IRQ(void) mp_ops.init_ipi(); #endif - for (i = 0; i < NR_IRQS; i++) - irq_set_noprobe(i); - for_each_possible_cpu(i) { page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order); diff --git a/arch/loongarch/kernel/kdebugfs.c b/arch/loongarch/kernel/kdebugfs.c new file mode 100644 index 000000000000..80cf64772399 --- /dev/null +++ b/arch/loongarch/kernel/kdebugfs.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/export.h> +#include <linux/debugfs.h> +#include <linux/kstrtox.h> +#include <asm/loongarch.h> + +struct dentry *arch_debugfs_dir; +EXPORT_SYMBOL(arch_debugfs_dir); + +static int sfb_state, tso_state; + +static void set_sfb_state(void *info) +{ + int val = *(int *)info << CSR_STFILL_SHIFT; + + csr_xchg32(val, CSR_STFILL, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t sfb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[32]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %x\nCurrent State: %x\n", sfb_state, state); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t sfb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: + on_each_cpu(set_sfb_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations sfb_fops = { + .read = sfb_read, + .write = sfb_write, + .open = simple_open, + .llseek = default_llseek +}; + +#define LDSTORDER_NLD_NST 0x0 /* 000 = No Load No Store */ +#define LDSTORDER_ALD_NST 0x1 /* 001 = All Load No Store */ +#define LDSTORDER_SLD_NST 0x3 /* 011 = Same Load No Store */ +#define LDSTORDER_NLD_AST 0x4 /* 100 = No Load All Store */ +#define LDSTORDER_ALD_AST 0x5 /* 101 = All Load All Store */ +#define LDSTORDER_SLD_AST 0x7 /* 111 = Same Load All Store */ + +static char *tso_hints[] = { + "No Load No Store", + "All Load No Store", + "Invalid Config", + "Same Load No Store", + "No Load All Store", + "All Load All Store", + "Invalid Config", + "Same Load All Store" +}; + +static void set_tso_state(void *info) +{ + int val = *(int *)info << CSR_LDSTORDER_SHIFT; + + csr_xchg32(val, CSR_LDSTORDER_MASK, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t tso_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[240]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %d (%s)\n" + "Current State: %d (%s)\n\n" + "Available States:\n" + "0 (%s)\t" "1 (%s)\t" "3 (%s)\n" + "4 (%s)\t" "5 (%s)\t" "7 (%s)\n", + tso_state, tso_hints[tso_state], state, tso_hints[state], + tso_hints[0], tso_hints[1], tso_hints[3], tso_hints[4], tso_hints[5], tso_hints[7]); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t tso_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: case 3: + case 4: case 5: case 7: + on_each_cpu(set_tso_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations tso_fops = { + .read = tso_read, + .write = tso_write, + .open = simple_open, + .llseek = default_llseek +}; + +static int __init arch_kdebugfs_init(void) +{ + unsigned int config = read_cpucfg(LOONGARCH_CPUCFG3); + + arch_debugfs_dir = debugfs_create_dir("loongarch", NULL); + + if (config & CPUCFG3_SFB) { + debugfs_create_file("sfb_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &sfb_state, &sfb_fops); + sfb_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + } + + if (config & (CPUCFG3_ALDORDER_CAP | CPUCFG3_ASTORDER_CAP)) { + debugfs_create_file("tso_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &tso_state, &tso_fops); + tso_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + } + + return 0; +} +postcore_initcall(arch_kdebugfs_init); diff --git a/arch/loongarch/kernel/kexec_efi.c b/arch/loongarch/kernel/kexec_efi.c new file mode 100644 index 000000000000..5ee78ebb1546 --- /dev/null +++ b/arch/loongarch/kernel/kexec_efi.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Load EFI vmlinux file for the kexec_file_load syscall. + * + * Author: Youling Tang <tangyouling@kylinos.cn> + * Copyright (C) 2025 KylinSoft Corporation. + */ + +#define pr_fmt(fmt) "kexec_file(EFI): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <asm/byteorder.h> +#include <asm/cpufeature.h> +#include <asm/image.h> + +static int efi_kexec_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct loongarch_image_header *h = (const struct loongarch_image_header *)kernel_buf; + + if (!h || (kernel_len < sizeof(*h))) { + kexec_dprintk("No LoongArch image header.\n"); + return -EINVAL; + } + + if (!loongarch_header_check_dos_sig(h)) { + kexec_dprintk("No LoongArch PE image header.\n"); + return -EINVAL; + } + + return 0; +} + +static void *efi_kexec_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + int ret; + unsigned long text_offset, kernel_segment_number; + struct kexec_buf kbuf = {}; + struct kexec_segment *kernel_segment; + struct loongarch_image_header *h; + + h = (struct loongarch_image_header *)kernel; + if (!h->kernel_asize) + return ERR_PTR(-EINVAL); + + /* + * Load the kernel + * FIXME: Non-relocatable kernel rejected for kexec_file (require CONFIG_RELOCATABLE) + */ + kbuf.image = image; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = le64_to_cpu(h->kernel_asize); + text_offset = le64_to_cpu(h->text_offset); + kbuf.buf_min = text_offset; + kbuf.buf_align = SZ_2M; + + kernel_segment_number = image->nr_segments; + + /* + * The location of the kernel segment may make it impossible to + * satisfy the other segment requirements, so we try repeatedly + * to find a location that will work. + */ + while ((ret = kexec_add_buffer(&kbuf)) == 0) { + /* Try to load additional data */ + kernel_segment = &image->segment[kernel_segment_number]; + ret = load_other_segments(image, kernel_segment->mem, + kernel_segment->memsz, initrd, + initrd_len, cmdline, cmdline_len); + if (!ret) + break; + + /* + * We couldn't find space for the other segments; erase the + * kernel segment and try the next available hole. + */ + image->nr_segments -= 1; + kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + } + + if (ret < 0) { + pr_err("Could not find any suitable kernel location!"); + return ERR_PTR(ret); + } + + kernel_segment = &image->segment[kernel_segment_number]; + + /* Make sure the second kernel jumps to the correct "kernel_entry" */ + image->start = kernel_segment->mem + h->kernel_entry - text_offset; + + kexec_dprintk("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); + + return NULL; +} + +const struct kexec_file_ops kexec_efi_ops = { + .probe = efi_kexec_probe, + .load = efi_kexec_load, +}; diff --git a/arch/loongarch/kernel/kexec_elf.c b/arch/loongarch/kernel/kexec_elf.c new file mode 100644 index 000000000000..1b6b64744c7f --- /dev/null +++ b/arch/loongarch/kernel/kexec_elf.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Author: Youling Tang <tangyouling@kylinos.cn> + * Copyright (C) 2025 KylinSoft Corporation. + */ + +#define pr_fmt(fmt) "kexec_file(ELF): " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <asm/setup.h> + +#define elf_kexec_probe kexec_elf_probe + +static int _elf_kexec_load(struct kimage *image, + struct elfhdr *ehdr, struct kexec_elf_info *elf_info, + struct kexec_buf *kbuf, unsigned long *text_offset) +{ + int i, ret = -1; + + /* Read in the PT_LOAD segments. */ + for (i = 0; i < ehdr->e_phnum; i++) { + size_t size; + const struct elf_phdr *phdr; + + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf->buffer = (void *)elf_info->buffer + phdr->p_offset; + kbuf->bufsz = size; + kbuf->buf_align = phdr->p_align; + *text_offset = __pa(phdr->p_paddr); + kbuf->buf_min = *text_offset; + kbuf->memsz = ALIGN(phdr->p_memsz, SZ_64K); + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(kbuf); + if (ret < 0) + break; + } + + return ret; +} + +static void *elf_kexec_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + int ret; + unsigned long text_offset, kernel_segment_number; + struct elfhdr ehdr; + struct kexec_buf kbuf = {}; + struct kexec_elf_info elf_info; + struct kexec_segment *kernel_segment; + + ret = kexec_build_elf_info(kernel, kernel_len, &ehdr, &elf_info); + if (ret < 0) + return ERR_PTR(ret); + + /* + * Load the kernel + * FIXME: Non-relocatable kernel rejected for kexec_file (require CONFIG_RELOCATABLE) + */ + kbuf.image = image; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kernel_segment_number = image->nr_segments; + + ret = _elf_kexec_load(image, &ehdr, &elf_info, &kbuf, &text_offset); + if (ret < 0) + goto out; + + /* Load additional data */ + kernel_segment = &image->segment[kernel_segment_number]; + ret = load_other_segments(image, kernel_segment->mem, kernel_segment->memsz, + initrd, initrd_len, cmdline, cmdline_len); + if (ret < 0) + goto out; + + /* Make sure the second kernel jumps to the correct "kernel_entry". */ + image->start = kernel_segment->mem + __pa(ehdr.e_entry) - text_offset; + + kexec_dprintk("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); + +out: + kexec_free_elf_info(&elf_info); + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops kexec_elf_ops = { + .probe = elf_kexec_probe, + .load = elf_kexec_load, +}; diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c index ec5b28e570c9..141b49bd989c 100644 --- a/arch/loongarch/kernel/kfpu.c +++ b/arch/loongarch/kernel/kfpu.c @@ -4,6 +4,7 @@ */ #include <linux/cpu.h> +#include <linux/export.h> #include <linux/init.h> #include <asm/fpu.h> #include <asm/smp.h> @@ -18,11 +19,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN; static DEFINE_PER_CPU(bool, in_kernel_fpu); static DEFINE_PER_CPU(unsigned int, euen_current); +static inline void fpregs_lock(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_bh_disable(); +} + +static inline void fpregs_unlock(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_bh_enable(); +} + void kernel_fpu_begin(void) { unsigned int *euen_curr; - preempt_disable(); + if (!irqs_disabled()) + fpregs_lock(); WARN_ON(this_cpu_read(in_kernel_fpu)); @@ -73,7 +91,8 @@ void kernel_fpu_end(void) this_cpu_write(in_kernel_fpu, false); - preempt_enable(); + if (!irqs_disabled()) + fpregs_unlock(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); diff --git a/arch/loongarch/kernel/kgdb.c b/arch/loongarch/kernel/kgdb.c index 445c452d72a7..7be5b4c0c900 100644 --- a/arch/loongarch/kernel/kgdb.c +++ b/arch/loongarch/kernel/kgdb.c @@ -8,6 +8,7 @@ #include <linux/hw_breakpoint.h> #include <linux/kdebug.h> #include <linux/kgdb.h> +#include <linux/objtool.h> #include <linux/processor.h> #include <linux/ptrace.h> #include <linux/sched.h> @@ -224,13 +225,13 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) regs->csr_era = pc; } -void arch_kgdb_breakpoint(void) +noinline void arch_kgdb_breakpoint(void) { __asm__ __volatile__ ( \ ".globl kgdb_breakinst\n\t" \ - "nop\n" \ "kgdb_breakinst:\tbreak 2\n\t"); /* BRK_KDB = 2 */ } +STACK_FRAME_NON_STANDARD(arch_kgdb_breakpoint); /* * Calls linux_debug_hook before the kernel dies. If KGDB is enabled, 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/lbt.S b/arch/loongarch/kernel/lbt.S index 001f061d226a..71678912d24c 100644 --- a/arch/loongarch/kernel/lbt.S +++ b/arch/loongarch/kernel/lbt.S @@ -90,6 +90,7 @@ SYM_FUNC_START(_save_lbt_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_save_lbt_context) +EXPORT_SYMBOL_GPL(_save_lbt_context) /* * a0: scr @@ -110,6 +111,7 @@ SYM_FUNC_START(_restore_lbt_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_restore_lbt_context) +EXPORT_SYMBOL_GPL(_restore_lbt_context) /* * a0: ftop @@ -120,6 +122,7 @@ SYM_FUNC_START(_save_ftop_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_save_ftop_context) +EXPORT_SYMBOL_GPL(_save_ftop_context) /* * a0: ftop @@ -150,6 +153,7 @@ SYM_FUNC_START(_restore_ftop_context) li.w a0, 0 # success jr ra SYM_FUNC_END(_restore_ftop_context) +EXPORT_SYMBOL_GPL(_restore_ftop_context) .L_lbt_fault: li.w a0, -EFAULT # failure diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c index 8ae641dc53bb..d7fafda1d541 100644 --- a/arch/loongarch/kernel/machine_kexec.c +++ b/arch/loongarch/kernel/machine_kexec.c @@ -39,49 +39,37 @@ static unsigned long systable_ptr; static unsigned long start_addr; static unsigned long first_ind_entry; -static void kexec_image_info(const struct kimage *kimage) -{ - unsigned long i; - - pr_debug("kexec kimage info:\n"); - pr_debug("\ttype: %d\n", kimage->type); - pr_debug("\tstart: %lx\n", kimage->start); - pr_debug("\thead: %lx\n", kimage->head); - pr_debug("\tnr_segments: %lu\n", kimage->nr_segments); - - for (i = 0; i < kimage->nr_segments; i++) { - pr_debug("\t segment[%lu]: %016lx - %016lx", i, - kimage->segment[i].mem, - kimage->segment[i].mem + kimage->segment[i].memsz); - pr_debug("\t\t0x%lx bytes, %lu pages\n", - (unsigned long)kimage->segment[i].memsz, - (unsigned long)kimage->segment[i].memsz / PAGE_SIZE); - } -} - int machine_kexec_prepare(struct kimage *kimage) { int i; char *bootloader = "kexec"; void *cmdline_ptr = (void *)KEXEC_CMDLINE_ADDR; - kexec_image_info(kimage); - kimage->arch.efi_boot = fw_arg0; kimage->arch.systable_ptr = fw_arg2; - /* Find the command line */ - for (i = 0; i < kimage->nr_segments; i++) { - if (!strncmp(bootloader, (char __user *)kimage->segment[i].buf, strlen(bootloader))) { - if (!copy_from_user(cmdline_ptr, kimage->segment[i].buf, COMMAND_LINE_SIZE)) - kimage->arch.cmdline_ptr = (unsigned long)cmdline_ptr; - break; + if (kimage->file_mode == 1) { + /* + * kimage->cmdline_buf will be released in kexec_file_load, so copy + * to the KEXEC_CMDLINE_ADDR safe area. + */ + memcpy((void *)KEXEC_CMDLINE_ADDR, (void *)kimage->arch.cmdline_ptr, + strlen((char *)kimage->arch.cmdline_ptr) + 1); + kimage->arch.cmdline_ptr = (unsigned long)KEXEC_CMDLINE_ADDR; + } else { + /* Find the command line */ + for (i = 0; i < kimage->nr_segments; i++) { + if (!strncmp(bootloader, (char __user *)kimage->segment[i].buf, strlen(bootloader))) { + if (!copy_from_user(cmdline_ptr, kimage->segment[i].buf, COMMAND_LINE_SIZE)) + kimage->arch.cmdline_ptr = (unsigned long)cmdline_ptr; + break; + } } - } - if (!kimage->arch.cmdline_ptr) { - pr_err("Command line not included in the provided image\n"); - return -EINVAL; + if (!kimage->arch.cmdline_ptr) { + pr_err("Command line not included in the provided image\n"); + return -EINVAL; + } } /* kexec/kdump need a safe page to save reboot_code_buffer */ @@ -126,14 +114,14 @@ void kexec_reboot(void) /* All secondary cpus go to kexec_smp_wait */ if (smp_processor_id() > 0) { relocated_kexec_smp_wait(NULL); - unreachable(); + BUG(); } #endif do_kexec = (void *)reboot_code_buffer; do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry); - unreachable(); + BUG(); } @@ -249,6 +237,7 @@ void machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_SMP crash_smp_send_stop(); #endif + machine_kexec_mask_interrupts(); cpumask_set_cpu(crashing_cpu, &cpus_in_crash); pr_info("Starting crashdump kernel...\n"); @@ -286,10 +275,12 @@ void machine_kexec(struct kimage *image) /* We do not want to be bothered. */ local_irq_disable(); + machine_kexec_mask_interrupts(); - pr_notice("EFI boot flag 0x%lx\n", efi_boot); - pr_notice("Command line at 0x%lx\n", cmdline_ptr); - pr_notice("System table at 0x%lx\n", systable_ptr); + pr_notice("EFI boot flag: 0x%lx\n", efi_boot); + pr_notice("Command line addr: 0x%lx\n", cmdline_ptr); + pr_notice("Command line string: %s\n", (char *)cmdline_ptr); + pr_notice("System table addr: 0x%lx\n", systable_ptr); pr_notice("We will call new kernel at 0x%lx\n", start_addr); pr_notice("Bye ...\n"); diff --git a/arch/loongarch/kernel/machine_kexec_file.c b/arch/loongarch/kernel/machine_kexec_file.c new file mode 100644 index 000000000000..fb57026f5f25 --- /dev/null +++ b/arch/loongarch/kernel/machine_kexec_file.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kexec_file for LoongArch + * + * Author: Youling Tang <tangyouling@kylinos.cn> + * Copyright (C) 2025 KylinSoft Corporation. + * + * Most code is derived from LoongArch port of kexec-tools + */ + +#define pr_fmt(fmt) "kexec_file: " fmt + +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/memblock.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/vmalloc.h> +#include <asm/bootinfo.h> + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_efi_ops, + &kexec_elf_ops, + NULL +}; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +/* Add the "kexec_file" command line parameter to command line. */ +static void cmdline_add_loader(unsigned long *cmdline_tmplen, char *modified_cmdline) +{ + int loader_strlen; + + loader_strlen = sprintf(modified_cmdline + (*cmdline_tmplen), "kexec_file "); + *cmdline_tmplen += loader_strlen; +} + +/* Add the "initrd=start,size" command line parameter to command line. */ +static void cmdline_add_initrd(struct kimage *image, unsigned long *cmdline_tmplen, + char *modified_cmdline, unsigned long initrd) +{ + int initrd_strlen; + + initrd_strlen = sprintf(modified_cmdline + (*cmdline_tmplen), "initrd=0x%lx,0x%lx ", + initrd, image->initrd_buf_len); + *cmdline_tmplen += initrd_strlen; +} + +#ifdef CONFIG_CRASH_DUMP + +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + int ret, nr_ranges; + uint64_t i; + phys_addr_t start, end; + struct crash_mem *cmem; + + nr_ranges = 2; /* for exclusion of crashkernel region */ + for_each_mem_range(i, &start, &end) + nr_ranges++; + + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + for_each_mem_range(i, &start, &end) { + cmem->ranges[cmem->nr_ranges].start = start; + cmem->ranges[cmem->nr_ranges].end = end - 1; + cmem->nr_ranges++; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + if (ret < 0) + goto out; + + if (crashk_low_res.end) { + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret < 0) + goto out; + } + + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + +out: + kfree(cmem); + return ret; +} + +/* + * Add the "mem=size@start" command line parameter to command line, indicating the + * memory region the new kernel can use to boot into. + */ +static void cmdline_add_mem(unsigned long *cmdline_tmplen, char *modified_cmdline) +{ + int mem_strlen = 0; + + mem_strlen = sprintf(modified_cmdline + (*cmdline_tmplen), "mem=0x%llx@0x%llx ", + crashk_res.end - crashk_res.start + 1, crashk_res.start); + *cmdline_tmplen += mem_strlen; + + if (crashk_low_res.end) { + mem_strlen = sprintf(modified_cmdline + (*cmdline_tmplen), "mem=0x%llx@0x%llx ", + crashk_low_res.end - crashk_low_res.start + 1, crashk_low_res.start); + *cmdline_tmplen += mem_strlen; + } +} + +/* Add the "elfcorehdr=size@start" command line parameter to command line. */ +static void cmdline_add_elfcorehdr(struct kimage *image, unsigned long *cmdline_tmplen, + char *modified_cmdline, unsigned long elfcorehdr_sz) +{ + int elfcorehdr_strlen = 0; + + elfcorehdr_strlen = sprintf(modified_cmdline + (*cmdline_tmplen), "elfcorehdr=0x%lx@0x%lx ", + elfcorehdr_sz, image->elf_load_addr); + *cmdline_tmplen += elfcorehdr_strlen; +} + +#endif + +/* + * Try to add the initrd to the image. If it is not possible to find valid + * locations, this function will undo changes to the image and return non zero. + */ +int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, unsigned long kernel_size, + char *initrd, unsigned long initrd_len, char *cmdline, unsigned long cmdline_len) +{ + int ret = 0; + unsigned long cmdline_tmplen = 0; + unsigned long initrd_load_addr = 0; + unsigned long orig_segments = image->nr_segments; + char *modified_cmdline = NULL; + struct kexec_buf kbuf = {}; + + kbuf.image = image; + /* Don't allocate anything below the kernel */ + kbuf.buf_min = kernel_load_addr + kernel_size; + + modified_cmdline = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!modified_cmdline) + return -EINVAL; + + cmdline_add_loader(&cmdline_tmplen, modified_cmdline); + /* Ensure it's null terminated */ + modified_cmdline[COMMAND_LINE_SIZE - 1] = '\0'; + +#ifdef CONFIG_CRASH_DUMP + /* Load elf core header */ + if (image->type == KEXEC_TYPE_CRASH) { + void *headers; + unsigned long headers_sz; + + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret < 0) { + pr_err("Preparing elf core header failed\n"); + goto out_err; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = SZ_64K; /* largest supported page size */ + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret < 0) { + vfree(headers); + goto out_err; + } + image->elf_headers = headers; + image->elf_load_addr = kbuf.mem; + image->elf_headers_sz = headers_sz; + + kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + + /* Add the mem=size@start parameter to the command line */ + cmdline_add_mem(&cmdline_tmplen, modified_cmdline); + + /* Add the elfcorehdr=size@start parameter to the command line */ + cmdline_add_elfcorehdr(image, &cmdline_tmplen, modified_cmdline, headers_sz); + } +#endif + + /* Load initrd */ + if (initrd) { + kbuf.buffer = initrd; + kbuf.bufsz = initrd_len; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = initrd_len; + kbuf.buf_align = 0; + /* within 1GB-aligned window of up to 32GB in size */ + kbuf.buf_max = round_down(kernel_load_addr, SZ_1G) + (unsigned long)SZ_1G * 32; + kbuf.top_down = false; + + ret = kexec_add_buffer(&kbuf); + if (ret < 0) + goto out_err; + initrd_load_addr = kbuf.mem; + + kexec_dprintk("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, kbuf.bufsz, kbuf.memsz); + + /* Add the initrd=start,size parameter to the command line */ + cmdline_add_initrd(image, &cmdline_tmplen, modified_cmdline, initrd_load_addr); + } + + if (cmdline_len + cmdline_tmplen > COMMAND_LINE_SIZE) { + pr_err("Appending command line exceeds COMMAND_LINE_SIZE\n"); + ret = -EINVAL; + goto out_err; + } + + memcpy(modified_cmdline + cmdline_tmplen, cmdline, cmdline_len); + cmdline = modified_cmdline; + image->arch.cmdline_ptr = (unsigned long)cmdline; + + return 0; + +out_err: + image->nr_segments = orig_segments; + kfree(modified_cmdline); + return ret; +} diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index 3015896016a0..b6850503e061 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller) SYM_FUNC_END(ftrace_graph_caller) SYM_FUNC_START(return_to_handler) - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + /* Save return value regs */ + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler @@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler) /* Restore the real parent address: a0 -> ra */ move ra, a0 - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + /* Restore return value regs */ + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE + jr ra SYM_FUNC_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index 0c65cf09110c..d6b474ad1d5e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -140,19 +140,19 @@ SYM_CODE_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED /* Save return value regs */ - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler move ra, a0 /* Restore return value regs */ - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE jr ra SYM_CODE_END(return_to_handler) diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index aed901c57fb4..8ab1ffedc52c 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -13,7 +13,7 @@ void __init memblock_init(void) { u32 mem_type; - u64 mem_start, mem_end, mem_size; + u64 mem_start, mem_size; efi_memory_desc_t *md; /* Parse memory information */ @@ -21,7 +21,6 @@ void __init memblock_init(void) mem_type = md->type; mem_start = md->phys_addr; mem_size = md->num_pages << EFI_PAGE_SHIFT; - mem_end = mem_start + mem_size; switch (mem_type) { case EFI_LOADER_CODE: @@ -31,8 +30,6 @@ void __init memblock_init(void) case EFI_PERSISTENT_MEMORY: case EFI_CONVENTIONAL_MEMORY: memblock_add(mem_start, mem_size); - if (max_low_pfn < (mem_end >> PAGE_SHIFT)) - max_low_pfn = mem_end >> PAGE_SHIFT; break; case EFI_PAL_CODE: case EFI_UNUSABLE_MEMORY: @@ -49,6 +46,8 @@ void __init memblock_init(void) } } + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); memblock_set_current_limit(PFN_PHYS(max_low_pfn)); /* Reserve the first 2MB */ diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index e2f30ff9afde..a43ba7f9f987 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/moduleloader.h> #include <linux/ftrace.h> +#include <linux/sort.h> Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) { @@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v return (Elf_Addr)&plt[nr]; } -static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) -{ - return x->r_info == y->r_info && x->r_addend == y->r_addend; -} +#define cmp_3way(a, b) ((a) < (b) ? -1 : (a) > (b)) -static bool duplicate_rela(const Elf_Rela *rela, int idx) +static int compare_rela(const void *x, const void *y) { - int i; + int ret; + const Elf_Rela *rela_x = x, *rela_y = y; - for (i = 0; i < idx; i++) { - if (is_rela_equal(&rela[i], &rela[idx])) - return true; - } + ret = cmp_3way(rela_x->r_info, rela_y->r_info); + if (ret == 0) + ret = cmp_3way(rela_x->r_addend, rela_y->r_addend); - return false; + return ret; } static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts, unsigned int *gots) { - unsigned int i, type; + unsigned int i; + + sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL); for (i = 0; i < num; i++) { - type = ELF_R_TYPE(relas[i].r_info); - switch (type) { + if (i && !compare_rela(&relas[i-1], &relas[i])) + continue; + + switch (ELF_R_TYPE(relas[i].r_info)) { case R_LARCH_SOP_PUSH_PLT_PCREL: case R_LARCH_B26: - if (!duplicate_rela(relas, i)) - (*plts)++; + (*plts)++; break; case R_LARCH_GOT_PC_HI20: - if (!duplicate_rela(relas, i)) - (*gots)++; + (*gots)++; break; default: break; /* Do nothing. */ diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 8fe21f868f72..8b89898e20df 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -11,6 +11,7 @@ #include <linux/mmzone.h> #include <linux/export.h> #include <linux/nodemask.h> +#include <linux/numa_memblks.h> #include <linux/swap.h> #include <linux/memblock.h> #include <linux/pfn.h> @@ -27,13 +28,6 @@ #include <asm/time.h> int numa_off; -struct pglist_data *node_data[MAX_NUMNODES]; -unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES]; - -EXPORT_SYMBOL(node_data); -EXPORT_SYMBOL(node_distances); - -static struct numa_meminfo numa_meminfo; cpumask_t cpus_on_node[MAX_NUMNODES]; cpumask_t phys_cpus_on_node[MAX_NUMNODES]; EXPORT_SYMBOL(cpus_on_node); @@ -46,8 +40,6 @@ s16 __cpuid_to_node[CONFIG_NR_CPUS] = { }; EXPORT_SYMBOL(__cpuid_to_node); -nodemask_t numa_nodes_parsed __initdata; - #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); @@ -148,66 +140,6 @@ void numa_remove_cpu(unsigned int cpu) cpumask_clear_cpu(cpu, &cpus_on_node[nid]); } -static int __init numa_add_memblk_to(int nid, u64 start, u64 end, - struct numa_meminfo *mi) -{ - /* ignore zero length blks */ - if (start == end) - return 0; - - /* whine about and ignore invalid blks */ - if (start > end || nid < 0 || nid >= MAX_NUMNODES) { - pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - return 0; - } - - if (mi->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("NUMA: too many memblk ranges\n"); - return -EINVAL; - } - - mi->blk[mi->nr_blks].start = PFN_ALIGN(start); - mi->blk[mi->nr_blks].end = PFN_ALIGN(end - PAGE_SIZE + 1); - mi->blk[mi->nr_blks].nid = nid; - mi->nr_blks++; - return 0; -} - -/** - * numa_add_memblk - Add one numa_memblk to numa_meminfo - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * Add a new memblk to the default numa_meminfo. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - return numa_add_memblk_to(nid, start, end, &numa_meminfo); -} - -static void __init alloc_node_data(int nid) -{ - void *nd; - unsigned long nd_pa; - size_t nd_sz = roundup(sizeof(pg_data_t), PAGE_SIZE); - - nd_pa = memblock_phys_alloc_try_nid(nd_sz, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu Byte for node_data (initial node: %d)\n", nd_sz, nid); - return; - } - - nd = __va(nd_pa); - - node_data[nid] = nd; - memset(nd, 0, sizeof(pg_data_t)); -} - static void __init node_mem_init(unsigned int node) { unsigned long start_pfn, end_pfn; @@ -226,54 +158,9 @@ static void __init node_mem_init(unsigned int node) #ifdef CONFIG_ACPI_NUMA -static void __init add_node_intersection(u32 node, u64 start, u64 size, u32 type) -{ - static unsigned long num_physpages; - - num_physpages += (size >> PAGE_SHIFT); - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", - node, type, start, size); - pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", - start >> PAGE_SHIFT, (start + size) >> PAGE_SHIFT, num_physpages); - memblock_set_node(start, size, &memblock.memory, node); -} - -/* - * add_numamem_region - * - * Add a uasable memory region described by BIOS. The - * routine gets each intersection between BIOS's region - * and node's region, and adds them into node's memblock - * pool. - * - */ -static void __init add_numamem_region(u64 start, u64 end, u32 type) -{ - u32 i; - u64 ofs = start; - - if (start >= end) { - pr_debug("Invalid region: %016llx-%016llx\n", start, end); - return; - } - - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = &numa_meminfo.blk[i]; - - if (ofs > mb->end) - continue; - - if (end > mb->end) { - add_node_intersection(mb->nid, ofs, mb->end - ofs, type); - ofs = mb->end; - } else { - add_node_intersection(mb->nid, ofs, end - ofs, type); - break; - } - } -} +static unsigned long num_physpages; -static void __init init_node_memblock(void) +static void __init info_node_memblock(void) { u32 mem_type; u64 mem_end, mem_start, mem_size; @@ -293,12 +180,20 @@ static void __init init_node_memblock(void) case EFI_BOOT_SERVICES_DATA: case EFI_PERSISTENT_MEMORY: case EFI_CONVENTIONAL_MEMORY: - add_numamem_region(mem_start, mem_end, mem_type); + num_physpages += (mem_size >> PAGE_SHIFT); + pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", + (u32)pa_to_nid(mem_start), mem_type, mem_start, mem_size); + pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", + mem_start >> PAGE_SHIFT, mem_end >> PAGE_SHIFT, num_physpages); break; case EFI_PAL_CODE: case EFI_UNUSABLE_MEMORY: case EFI_ACPI_RECLAIM_MEMORY: - add_numamem_region(mem_start, mem_end, mem_type); + num_physpages += (mem_size >> PAGE_SHIFT); + pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", + (u32)pa_to_nid(mem_start), mem_type, mem_start, mem_size); + pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", + mem_start >> PAGE_SHIFT, mem_end >> PAGE_SHIFT, num_physpages); fallthrough; case EFI_RESERVED_TYPE: case EFI_RUNTIME_SERVICES_CODE: @@ -312,24 +207,6 @@ static void __init init_node_memblock(void) } } -static void __init numa_default_distance(void) -{ - int row, col; - - for (row = 0; row < MAX_NUMNODES; row++) - for (col = 0; col < MAX_NUMNODES; col++) { - if (col == row) - node_distances[row][col] = LOCAL_DISTANCE; - else - /* We assume that one node per package here! - * - * A SLIT should be used for multiple nodes - * per package to override default setting. - */ - node_distances[row][col] = REMOTE_DISTANCE; - } -} - /* * fake_numa_init() - For Non-ACPI systems * Return: 0 on success, -errno on failure. @@ -354,22 +231,16 @@ int __init init_numa_memory(void) for (i = 0; i < NR_CPUS; i++) set_cpuid_to_node(i, NUMA_NO_NODE); - numa_default_distance(); - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - /* Parse SRAT and SLIT if provided by firmware. */ - ret = acpi_disabled ? fake_numa_init() : acpi_numa_init(); + if (!acpi_disabled) + ret = numa_memblks_init(acpi_numa_init, false); + else + ret = numa_memblks_init(fake_numa_init, false); + if (ret < 0) return ret; - node_possible_map = numa_nodes_parsed; - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - init_node_memblock(); + info_node_memblock(); if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; @@ -377,7 +248,8 @@ int __init init_numa_memory(void) node_mem_init(node); node_set_online(node); } - max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); setup_nr_node_ids(); loongson_sysconf.nr_nodes = nr_node_ids; @@ -388,32 +260,6 @@ int __init init_numa_memory(void) #endif -void __init paging_init(void) -{ - unsigned int node; - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - - for_each_online_node(node) { - unsigned long start_pfn, end_pfn; - - get_pfn_range_for_nid(node, &start_pfn, &end_pfn); - - if (end_pfn > max_low_pfn) - max_low_pfn = end_pfn; - } -#ifdef CONFIG_ZONE_DMA32 - zones_size[ZONE_DMA32] = MAX_DMA32_PFN; -#endif - zones_size[ZONE_NORMAL] = max_low_pfn; - free_area_init(zones_size); -} - -void __init mem_init(void) -{ - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - memblock_free_all(); -} - int pcibus_to_node(struct pci_bus *bus) { return dev_to_node(&bus->dev); diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index 1633ed4f692f..b1b51f920b23 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -1,14 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 -#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> #include <linux/static_call.h> #include <asm/paravirt.h> +static int has_steal_clock; struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; +static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); +DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key); static u64 native_steal_clock(int cpu) { @@ -17,12 +21,47 @@ static u64 native_steal_clock(int cpu) DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); +static bool steal_acc = true; + +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} +early_param("no-steal-acc", parse_no_stealacc); + +static u64 paravt_steal_clock(int cpu) +{ + int version; + u64 steal; + struct kvm_steal_time *src; + + src = &per_cpu(steal_time, cpu); + do { + + version = src->version; + virt_rmb(); /* Make sure that the version is read before the steal */ + steal = src->steal; + virt_rmb(); /* Make sure that the steal is read before the next version */ + + } while ((version & 1) || (version != src->version)); + + return steal; +} + #ifdef CONFIG_SMP +static struct smp_ops native_ops; + static void pv_send_ipi_single(int cpu, unsigned int action) { int min, old; irq_cpustat_t *info = &per_cpu(irq_stat, cpu); + if (unlikely(action == ACTION_BOOT_CPU)) { + native_ops.send_ipi_single(cpu, action); + return; + } + old = atomic_fetch_or(BIT(action), &info->message); if (old) return; @@ -42,6 +81,11 @@ static void pv_send_ipi_mask(const struct cpumask *mask, unsigned int action) if (cpumask_empty(mask)) return; + if (unlikely(action == ACTION_BOOT_CPU)) { + native_ops.send_ipi_mask(mask, action); + return; + } + action = BIT(action); for_each_cpu(i, mask) { info = &per_cpu(irq_stat, i); @@ -97,6 +141,16 @@ 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]++; + } + + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + info->ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } @@ -104,6 +158,8 @@ static void pv_init_ipi(void) { int r, swi; + /* Init native ipi irq for ACTION_BOOT_CPU */ + native_ops.init_ipi(); swi = get_percpu_irq(INT_SWI0); if (swi < 0) panic("SWI0 IRQ mapping failed\n"); @@ -114,11 +170,14 @@ static void pv_init_ipi(void) } #endif -static bool kvm_para_available(void) +bool kvm_para_available(void) { int config; static int hypervisor_type; + if (!cpu_has_hypervisor) + return false; + if (!hypervisor_type) { config = read_cpucfg(CPUCFG_KVM_SIG); if (!memcmp(&config, KVM_SIGNATURE, 4)) @@ -128,20 +187,26 @@ static bool kvm_para_available(void) return hypervisor_type == HYPERVISOR_KVM; } -int __init pv_ipi_init(void) +unsigned int kvm_arch_para_features(void) { - int feature; + static unsigned int feature; - if (!cpu_has_hypervisor) - return 0; if (!kvm_para_available()) return 0; - feature = read_cpucfg(CPUCFG_KVM_FEATURE); - if (!(feature & KVM_FEATURE_IPI)) + if (!feature) + feature = read_cpucfg(CPUCFG_KVM_FEATURE); + + return feature; +} + +int __init pv_ipi_init(void) +{ + if (!kvm_para_has_feature(KVM_FEATURE_IPI)) return 0; #ifdef CONFIG_SMP + native_ops = mp_ops; mp_ops.init_ipi = pv_init_ipi; mp_ops.send_ipi_single = pv_send_ipi_single; mp_ops.send_ipi_mask = pv_send_ipi_mask; @@ -149,3 +214,121 @@ int __init pv_ipi_init(void) return 0; } + +static int pv_enable_steal_time(void) +{ + int cpu = smp_processor_id(); + unsigned long addr; + struct kvm_steal_time *st; + + if (!has_steal_clock) + return -EPERM; + + st = &per_cpu(steal_time, cpu); + addr = per_cpu_ptr_to_phys(st); + + /* The whole structure kvm_steal_time should be in one page */ + if (PFN_DOWN(addr) != PFN_DOWN(addr + sizeof(*st))) { + pr_warn("Illegal PV steal time addr %lx\n", addr); + return -EFAULT; + } + + addr |= KVM_STEAL_PHYS_VALID; + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), addr); + + return 0; +} + +static void pv_disable_steal_time(void) +{ + if (has_steal_clock) + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), 0); +} + +#ifdef CONFIG_SMP +static int pv_time_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_enable_steal_time(); + local_irq_restore(flags); + + return 0; +} + +static int pv_time_cpu_down_prepare(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_disable_steal_time(); + local_irq_restore(flags); + + return 0; +} +#endif + +static void pv_cpu_reboot(void *unused) +{ + pv_disable_steal_time(); +} + +static int pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) +{ + on_each_cpu(pv_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block pv_reboot_nb = { + .notifier_call = pv_reboot_notify, +}; + +int __init pv_time_init(void) +{ + int r; + + if (!kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) + return 0; + + has_steal_clock = 1; + r = pv_enable_steal_time(); + if (r < 0) { + has_steal_clock = 0; + return 0; + } + register_reboot_notifier(&pv_reboot_nb); + +#ifdef CONFIG_SMP + r = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "loongarch/pv_time:online", + pv_time_cpu_online, pv_time_cpu_down_prepare); + if (r < 0) { + has_steal_clock = 0; + pr_err("Failed to install cpu hotplug callbacks\n"); + return r; + } +#endif + + static_call_update(pv_steal_clock, paravt_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); +#endif + + pr_info("Using paravirt steal-time\n"); + + return 0; +} + +int __init pv_spinlock_init(void) +{ + if (!cpu_has_hypervisor) + return 0; + + static_branch_enable(&virt_spin_lock_key); + + return 0; +} diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index f86a4b838dd7..9d257c8519c9 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -479,8 +479,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc, int idx, if (!loongarch_pmu_event_set_period(event, hwc, idx)) return; - if (perf_event_overflow(event, data, regs)) - loongarch_pmu_disable_event(idx); + perf_event_overflow(event, data, regs); } static irqreturn_t pmu_handle_irq(int irq, void *dev) @@ -846,13 +845,14 @@ static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config static int __init init_hw_perf_events(void) { - int counters; + int bits, counters; if (!cpu_has_pmp) return -ENODEV; pr_info("Performance counters: "); - counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> 4) + 1; + bits = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMBITS) >> CPUCFG6_PMBITS_SHIFT) + 1; + counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT) + 1; loongarch_pmu.num_counters = counters; loongarch_pmu.max_period = (1ULL << 63) - 1; @@ -868,7 +868,7 @@ static int __init init_hw_perf_events(void) on_each_cpu(reset_counters, NULL, 1); pr_cont("%s PMU enabled, %d %d-bit counters available to each CPU.\n", - loongarch_pmu.name, counters, 64); + loongarch_pmu.name, counters, bits); perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 0d33cbc47e51..63d2b7e7e844 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -13,27 +13,13 @@ #include <asm/processor.h> #include <asm/time.h> -/* - * No lock; only written during early bootup by CPU 0. - */ -static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain); - -int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb) -{ - return raw_notifier_chain_register(&proc_cpuinfo_chain, nb); -} - -int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v) -{ - return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v); -} - static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; + unsigned int isa = cpu_data[n].isa_level; + unsigned int prid = cpu_data[n].processor_id; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; - struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args; #ifdef CONFIG_SMP if (!cpu_online(n)) @@ -52,6 +38,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "global_id\t\t: %d\n", cpu_data[n].global_id); seq_printf(m, "CPU Family\t\t: %s\n", __cpu_family[n]); seq_printf(m, "Model Name\t\t: %s\n", __cpu_full_name[n]); + seq_printf(m, "PRID\t\t\t: %s (%08x)\n", id_to_core_name(prid), prid); seq_printf(m, "CPU Revision\t\t: 0x%02x\n", version); seq_printf(m, "FPU Revision\t\t: 0x%02x\n", fp_version); seq_printf(m, "CPU MHz\t\t\t: %llu.%02llu\n", @@ -64,9 +51,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) cpu_pabits + 1, cpu_vabits + 1); seq_printf(m, "ISA\t\t\t:"); - if (cpu_has_loongarch32) - seq_printf(m, " loongarch32"); - if (cpu_has_loongarch64) + if (isa & LOONGARCH_CPU_ISA_LA32R) + seq_printf(m, " loongarch32r"); + if (isa & LOONGARCH_CPU_ISA_LA32S) + seq_printf(m, " loongarch32s"); + if (isa & LOONGARCH_CPU_ISA_LA64) seq_printf(m, " loongarch64"); seq_printf(m, "\n"); @@ -81,26 +70,20 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_complex) seq_printf(m, " complex"); if (cpu_has_crypto) seq_printf(m, " crypto"); if (cpu_has_ptw) seq_printf(m, " ptw"); + if (cpu_has_lspw) seq_printf(m, " lspw"); if (cpu_has_lvz) seq_printf(m, " lvz"); if (cpu_has_lbt_x86) seq_printf(m, " lbt_x86"); if (cpu_has_lbt_arm) seq_printf(m, " lbt_arm"); if (cpu_has_lbt_mips) seq_printf(m, " lbt_mips"); seq_printf(m, "\n"); - seq_printf(m, "Hardware Watchpoint\t: %s", - cpu_has_watch ? "yes, " : "no\n"); + seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch)); if (cpu_has_watch) { - seq_printf(m, "iwatch count: %d, dwatch count: %d\n", + seq_printf(m, ", iwatch count: %d, dwatch count: %d", cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count); } - proc_cpuinfo_notifier_args.m = m; - proc_cpuinfo_notifier_args.n = n; - - raw_notifier_call_chain(&proc_cpuinfo_chain, 0, - &proc_cpuinfo_notifier_args); - - seq_printf(m, "\n"); + seq_printf(m, "\n\n"); return 0; } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index f2ff8b5d591e..efd9edf65603 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -13,6 +13,7 @@ #include <linux/cpu.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/entry-common.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -34,6 +35,7 @@ #include <linux/nmi.h> #include <asm/asm.h> +#include <asm/asm-prototypes.h> #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/elf.h> @@ -47,6 +49,7 @@ #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/reg.h> +#include <asm/switch_to.h> #include <asm/unwind.h> #include <asm/vdso.h> @@ -63,8 +66,9 @@ EXPORT_SYMBOL(__stack_chk_guard); unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -asmlinkage void ret_from_fork(void); -asmlinkage void ret_from_kernel_thread(void); +asmlinkage void restore_and_ret(void); +asmlinkage void ret_from_fork_asm(void); +asmlinkage void ret_from_kernel_thread_asm(void); void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -138,6 +142,23 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } +asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev, + struct pt_regs *regs) +{ + schedule_tail(prev); + syscall_exit_to_user_mode(regs); +} + +asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev, + struct pt_regs *regs, + int (*fn)(void *), + void *fn_arg) +{ + schedule_tail(prev); + fn(fn_arg); + syscall_exit_to_user_mode(regs); +} + /* * Copy architecture-specific thread state */ @@ -146,7 +167,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) unsigned long childksp; unsigned long tls = args->tls; unsigned long usp = args->stack; - unsigned long clone_flags = args->flags; + u64 clone_flags = args->flags; struct pt_regs *childregs, *regs = current_pt_regs(); childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE; @@ -165,8 +186,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.reg03 = childksp; p->thread.reg23 = (unsigned long)args->fn; p->thread.reg24 = (unsigned long)args->fn_arg; - p->thread.reg01 = (unsigned long)ret_from_kernel_thread; - p->thread.sched_ra = (unsigned long)ret_from_kernel_thread; + p->thread.reg01 = (unsigned long)ret_from_kernel_thread_asm; + p->thread.sched_ra = (unsigned long)ret_from_kernel_thread_asm; memset(childregs, 0, sizeof(struct pt_regs)); childregs->csr_euen = p->thread.csr_euen; childregs->csr_crmd = p->thread.csr_crmd; @@ -182,8 +203,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->regs[3] = usp; p->thread.reg03 = (unsigned long) childregs; - p->thread.reg01 = (unsigned long) ret_from_fork; - p->thread.sched_ra = (unsigned long) ret_from_fork; + p->thread.reg01 = (unsigned long) ret_from_fork_asm; + p->thread.sched_ra = (unsigned long) ret_from_fork_asm; /* * New tasks lose permission to use the fpu. This accelerates context @@ -293,13 +314,15 @@ unsigned long stack_top(void) { unsigned long top = TASK_SIZE & PAGE_MASK; - /* Space for the VDSO & data page */ - top -= PAGE_ALIGN(current->thread.vdso->size); - top -= VVAR_SIZE; + if (current->thread.vdso) { + /* Space for the VDSO & data page */ + top -= PAGE_ALIGN(current->thread.vdso->size); + top -= VVAR_SIZE; - /* Space to randomize the VDSO base */ - if (current->flags & PF_RANDOMIZE) - top -= VDSO_RANDOMIZE_SIZE; + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + } return top; } diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index 200109de1971..8edd0954e55a 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); @@ -717,7 +720,7 @@ static int hw_break_set(struct task_struct *target, unsigned int note_type = regset->core_note_type; /* Resource info */ - offset = offsetof(struct user_watch_state, dbg_regs); + offset = offsetof(struct user_watch_state_v2, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, mask, ctrl) registers */ @@ -861,7 +864,7 @@ enum loongarch_regset { static const struct user_regset loongarch64_regsets[] = { [REGSET_GPR] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(elf_greg_t), .align = sizeof(elf_greg_t), @@ -869,7 +872,7 @@ static const struct user_regset loongarch64_regsets[] = { .set = gpr_set, }, [REGSET_FPR] = { - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(elf_fpreg_t), .align = sizeof(elf_fpreg_t), @@ -877,7 +880,7 @@ static const struct user_regset loongarch64_regsets[] = { .set = fpr_set, }, [REGSET_CPUCFG] = { - .core_note_type = NT_LOONGARCH_CPUCFG, + USER_REGSET_NOTE_TYPE(LOONGARCH_CPUCFG), .n = 64, .size = sizeof(u32), .align = sizeof(u32), @@ -886,7 +889,7 @@ static const struct user_regset loongarch64_regsets[] = { }, #ifdef CONFIG_CPU_HAS_LSX [REGSET_LSX] = { - .core_note_type = NT_LOONGARCH_LSX, + USER_REGSET_NOTE_TYPE(LOONGARCH_LSX), .n = NUM_FPU_REGS, .size = 16, .align = 16, @@ -896,7 +899,7 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_CPU_HAS_LASX [REGSET_LASX] = { - .core_note_type = NT_LOONGARCH_LASX, + USER_REGSET_NOTE_TYPE(LOONGARCH_LASX), .n = NUM_FPU_REGS, .size = 32, .align = 32, @@ -906,7 +909,7 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_CPU_HAS_LBT [REGSET_LBT] = { - .core_note_type = NT_LOONGARCH_LBT, + USER_REGSET_NOTE_TYPE(LOONGARCH_LBT), .n = 5, .size = sizeof(u64), .align = sizeof(u64), @@ -916,16 +919,16 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { - .core_note_type = NT_LOONGARCH_HW_BREAK, - .n = sizeof(struct user_watch_state) / sizeof(u32), + USER_REGSET_NOTE_TYPE(LOONGARCH_HW_BREAK), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { - .core_note_type = NT_LOONGARCH_HW_WATCH, - .n = sizeof(struct user_watch_state) / sizeof(u32), + USER_REGSET_NOTE_TYPE(LOONGARCH_HW_WATCH), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 1acfa704c8d0..b5e2312a2fca 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 +140,36 @@ 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 + + str = strstr(boot_command_line, "kexec_file"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return true; + return false; } @@ -170,7 +217,7 @@ 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 +229,7 @@ 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/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index 84e6de2fd973..8b5140ac9ea1 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -109,4 +109,4 @@ SYM_CODE_END(kexec_smp_wait) relocate_new_kernel_end: .section ".data" -SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel) +SYM_DATA(relocate_new_kernel_size, .quad relocate_new_kernel_end - relocate_new_kernel) diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 1ef8c6383535..de8fa5a8a825 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -33,7 +33,7 @@ void machine_halt(void) console_flush_on_panic(CONSOLE_FLUSH_PENDING); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -53,7 +53,7 @@ void machine_power_off(void) #endif while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -74,6 +74,6 @@ void machine_restart(char *command) acpi_reboot(); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 3d048f1be143..25a87378e48e 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -55,6 +55,7 @@ #define SMBIOS_FREQHIGH_OFFSET 0x17 #define SMBIOS_FREQLOW_MASK 0xFF #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 +#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25 #define LOONGSON_EFI_ENABLE (1 << 3) unsigned long fw_arg0, fw_arg1, fw_arg2; @@ -125,7 +126,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm) cpu_clock_freq = freq_temp * 1000000; loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]); - loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET); + loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); pr_info("CpuClock = %llu\n", cpu_clock_freq); } @@ -190,6 +191,16 @@ static int __init early_parse_mem(char *p) return -EINVAL; } + start = 0; + size = memparse(p, &p); + if (*p == '@') /* Every mem=... should contain '@' */ + start = memparse(p + 1, &p); + else { /* Only one mem=... is allowed if no '@' */ + usermem = 1; + memblock_enforce_memory_limit(size); + return 0; + } + /* * If a user specifies memory size, we * blow away any automatically generated @@ -200,14 +211,6 @@ static int __init early_parse_mem(char *p) memblock_remove(memblock_start_of_DRAM(), memblock_end_of_DRAM() - memblock_start_of_DRAM()); } - start = 0; - size = memparse(p, &p); - if (*p == '@') - start = memparse(p + 1, &p); - else { - pr_err("Invalid format!\n"); - return -EINVAL; - } if (!IS_ENABLED(CONFIG_NUMA)) memblock_add(start, size); @@ -258,18 +261,17 @@ static void __init arch_reserve_crashkernel(void) int ret; unsigned long long low_size = 0; unsigned long long crash_base, crash_size; - char *cmdline = boot_command_line; bool high = false; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; - ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), - &crash_size, &crash_base, &low_size, &high); + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + &crash_size, &crash_base, &low_size, NULL, &high); if (ret) return; - reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high); + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); } static void __init fdt_setup(void) @@ -290,10 +292,8 @@ static void __init fdt_setup(void) if (!fdt_pointer || fdt_check_header(fdt_pointer)) return; - early_init_dt_scan(fdt_pointer); + early_init_dt_scan(fdt_pointer, __pa(fdt_pointer)); early_init_fdt_reserve_self(); - - max_low_pfn = PFN_PHYS(memblock_end_of_DRAM()); #endif } @@ -353,6 +353,7 @@ void __init platform_init(void) #ifdef CONFIG_ACPI acpi_table_upgrade(); + acpi_gbl_use_global_lock = false; acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif @@ -386,6 +387,10 @@ static void __init check_kernel_sections_mem(void) */ static void __init arch_mem_init(char **cmdline_p) { + /* Recalculate max_low_pfn for "mem=xxx" */ + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); + if (usermem) pr_info("User-defined physical RAM map overwrite\n"); @@ -430,7 +435,7 @@ static void __init resource_init(void) num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); - standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES); + standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES); for_each_mem_region(region) { res = &standard_resources[i++]; @@ -576,8 +581,10 @@ 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); } @@ -601,6 +608,8 @@ void __init setup_arch(char **cmdline_p) arch_mem_init(cmdline_p); resource_init(); + jump_label_init(); /* Initialise the static keys for paravirtualization */ + #ifdef CONFIG_SMP plat_smp_setup(); prefill_possible_map(); diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index 7a555b600171..c9f7ca778364 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -51,27 +51,6 @@ #define lock_lbt_owner() ({ preempt_disable(); pagefault_disable(); }) #define unlock_lbt_owner() ({ pagefault_enable(); preempt_enable(); }) -/* Assembly functions to move context to/from the FPU */ -extern asmlinkage int -_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr); -extern asmlinkage int -_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr); -extern asmlinkage int -_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); -extern asmlinkage int -_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); -extern asmlinkage int -_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); -extern asmlinkage int -_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr); - -#ifdef CONFIG_CPU_HAS_LBT -extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags); -extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags); -extern asmlinkage int _save_ftop_context(void __user *ftop); -extern asmlinkage int _restore_ftop_context(void __user *ftop); -#endif - struct rt_sigframe { struct siginfo rs_info; struct ucontext rs_uctx; @@ -698,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, for (i = 1; i < 32; i++) err |= __put_user(regs->regs[i], &sc->sc_regs[i]); +#ifdef CONFIG_CPU_HAS_LBT + if (extctx->lbt.addr) + err |= protected_save_lbt_context(extctx); +#endif + if (extctx->lasx.addr) err |= protected_save_lasx_context(extctx); else if (extctx->lsx.addr) @@ -705,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, else if (extctx->fpu.addr) err |= protected_save_fpu_context(extctx); -#ifdef CONFIG_CPU_HAS_LBT - if (extctx->lbt.addr) - err |= protected_save_lbt_context(extctx); -#endif - /* Set the "end" magic */ info = (struct sctx_info *)extctx->end.addr; err |= __put_user(0, &info->magic); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 1436d2465939..8b2fcb3fb874 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -13,11 +13,13 @@ #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> #include <linux/threads.h> #include <linux/export.h> +#include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/time.h> #include <linux/tracepoint.h> @@ -44,6 +46,10 @@ EXPORT_SYMBOL(__cpu_logical_map); cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_sibling_map); +/* Representing the last level cache shared map of each logical CPU */ +cpumask_t cpu_llc_shared_map[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(cpu_llc_shared_map); + /* Representing the core map of multi-core chips of each logical CPU */ cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); @@ -61,6 +67,9 @@ EXPORT_SYMBOL(cpu_foreign_map); /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; +/* representing cpus for which llc shared maps can be computed */ +static cpumask_t cpu_llc_shared_setup_map; + /* representing cpus for which core maps can be computed */ static cpumask_t cpu_core_setup_map; @@ -70,6 +79,8 @@ 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", + [IPI_CLEAR_VECTOR] = "Clear vector interrupts", }; void show_ipi_list(struct seq_file *p, int prec) @@ -79,7 +90,7 @@ void show_ipi_list(struct seq_file *p, int prec) for (i = 0; i < NR_IPI; i++) { seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : ""); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).ipi_irqs[i]); + seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, cpu).ipi_irqs[i], 10); seq_printf(p, " LoongArch %d %s\n", i + 1, ipi_types[i]); } } @@ -98,6 +109,34 @@ static inline void set_cpu_core_map(int cpu) } } +static inline void set_cpu_llc_shared_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_llc_shared_setup_map); + + for_each_cpu(i, &cpu_llc_shared_setup_map) { + if (cpu_to_node(cpu) == cpu_to_node(i)) { + cpumask_set_cpu(i, &cpu_llc_shared_map[cpu]); + cpumask_set_cpu(cpu, &cpu_llc_shared_map[i]); + } + } +} + +static inline void clear_cpu_llc_shared_map(int cpu) +{ + int i; + + for_each_cpu(i, &cpu_llc_shared_setup_map) { + if (cpu_to_node(cpu) == cpu_to_node(i)) { + cpumask_clear_cpu(i, &cpu_llc_shared_map[cpu]); + cpumask_clear_cpu(cpu, &cpu_llc_shared_map[i]); + } + } + + cpumask_clear_cpu(cpu, &cpu_llc_shared_setup_map); +} + static inline void set_cpu_sibling_map(int cpu) { int i; @@ -217,6 +256,13 @@ 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 +280,16 @@ 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]++; + } + + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } @@ -271,11 +327,10 @@ 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); @@ -283,7 +338,7 @@ static void __init fdt_smp_setup(void) __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; - early_numa_add_cpu(cpu, 0); + early_numa_add_cpu(cpuid, 0); set_cpuid_to_node(cpuid, 0); } @@ -312,11 +367,11 @@ void __init loongson_prepare_cpus(unsigned int max_cpus) int i = 0; parse_acpi_topology(); + cpu_data[0].global_id = cpu_logical_map(0); for (i = 0; i < loongson_sysconf.nr_cpus; i++) { set_cpu_present(i, true); csr_mail_send(0, __cpu_logical_map[i], 0); - cpu_data[i].global_id = __cpu_logical_map[i]; } per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -361,6 +416,7 @@ void loongson_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; cpu_data[cpu].core = pptt_enabled ? cpu_data[cpu].core : cpu_logical_map(cpu) % loongson_sysconf.cores_per_package; + cpu_data[cpu].global_id = cpu_logical_map(cpu); } void loongson_smp_finish(void) @@ -385,6 +441,7 @@ int loongson_cpu_disable(void) #endif set_cpu_online(cpu, false); clear_cpu_sibling_map(cpu); + clear_cpu_llc_shared_map(cpu); calculate_cpu_foreign_map(); local_irq_save(flags); irq_migrate_all_off_this_cpu(); @@ -403,7 +460,7 @@ void loongson_cpu_die(unsigned int cpu) mb(); } -void __noreturn arch_cpu_idle_dead(void) +static void __noreturn idle_play_dead(void) { register uint64_t addr; register void (*init_fn)(void); @@ -427,6 +484,50 @@ void __noreturn arch_cpu_idle_dead(void) BUG(); } +#ifdef CONFIG_HIBERNATION +static void __noreturn poll_play_dead(void) +{ + register uint64_t addr; + register void (*init_fn)(void); + + idle_task_exit(); + __this_cpu_write(cpu_state, CPU_DEAD); + + __smp_mb(); + do { + __asm__ __volatile__("nop\n\t"); + addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); + } while (addr == 0); + + init_fn = (void *)TO_CACHE(addr); + iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); + + init_fn(); + BUG(); +} +#endif + +static void (*play_dead)(void) = idle_play_dead; + +void __noreturn arch_cpu_idle_dead(void) +{ + play_dead(); + BUG(); /* play_dead() doesn't return */ +} + +#ifdef CONFIG_HIBERNATION +int hibernate_resume_nonboot_cpu_disable(void) +{ + int ret; + + play_dead = poll_play_dead; + ret = suspend_disable_secondary_cpus(); + play_dead = idle_play_dead; + + return ret; +} +#endif + #endif /* @@ -434,28 +535,32 @@ void __noreturn arch_cpu_idle_dead(void) */ #ifdef CONFIG_PM -static int loongson_ipi_suspend(void) +static int loongson_ipi_suspend(void *data) { return 0; } -static void loongson_ipi_resume(void) +static void loongson_ipi_resume(void *data) { iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN); } -static struct syscore_ops loongson_ipi_syscore_ops = { +static const struct syscore_ops loongson_ipi_syscore_ops = { .resume = loongson_ipi_resume, .suspend = loongson_ipi_suspend, }; +static struct syscore loongson_ipi_syscore = { + .ops = &loongson_ipi_syscore_ops, +}; + /* * Enable boot cpu ipi before enabling nonboot cpus * during syscore_resume. */ static int __init ipi_pm_init(void) { - register_syscore_ops(&loongson_ipi_syscore_ops); + register_syscore(&loongson_ipi_syscore); return 0; } @@ -463,7 +568,7 @@ core_initcall(ipi_pm_init); #endif /* Preload SMP state for boot cpu */ -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { unsigned int cpu, node, rr_node; @@ -496,6 +601,8 @@ void smp_prepare_boot_cpu(void) rr_node = next_node_in(rr_node, node_online_map); } } + + pv_spinlock_init(); } /* called from main before smp_init() */ @@ -505,6 +612,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) current_thread_info()->cpu = 0; loongson_prepare_cpus(max_cpus); set_cpu_sibling_map(0); + set_cpu_llc_shared_map(0); set_cpu_core_map(0); calculate_cpu_foreign_map(); #ifndef CONFIG_HOTPLUG_CPU @@ -546,6 +654,7 @@ asmlinkage void start_secondary(void) loongson_init_secondary(); set_cpu_sibling_map(cpu); + set_cpu_llc_shared_map(cpu); set_cpu_core_map(cpu); notify_cpu_starting(cpu); diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c index 9a038d1070d7..387dc4d3c486 100644 --- a/arch/loongarch/kernel/stacktrace.c +++ b/arch/loongarch/kernel/stacktrace.c @@ -51,12 +51,13 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (task == current) { regs->regs[3] = (unsigned long)__builtin_frame_address(0); regs->csr_era = (unsigned long)__builtin_return_address(0); + regs->regs[22] = 0; } else { regs->regs[3] = thread_saved_fp(task); regs->csr_era = thread_saved_ra(task); + regs->regs[22] = task->thread.reg22; } regs->regs[1] = 0; - regs->regs[22] = 0; for (unwind_start(&state, task, regs); !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 31dd8199b245..9c23cb7e432f 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -12,7 +12,7 @@ /* * task_struct *__switch_to(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, void *sched_ra, void *sched_cfa) */ .align 5 SYM_FUNC_START(__switch_to) diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index 8801611143ab..168bd97540f8 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -9,17 +9,21 @@ #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> #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, offset) @@ -32,13 +36,13 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, void *sys_call_table[__NR_syscalls] = { [0 ... __NR_syscalls - 1] = sys_ni_syscall, -#include <asm/unistd.h> +#include <asm/syscall_table_64.h> }; 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; @@ -54,11 +58,24 @@ 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); } diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index fd5354f9be7c..6fb92cc1a4c9 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -5,6 +5,7 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/clockchips.h> +#include <linux/cpuhotplug.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -15,6 +16,7 @@ #include <asm/cpu-features.h> #include <asm/loongarch.h> +#include <asm/paravirt.h> #include <asm/time.h> u64 cpu_clock_freq; @@ -101,7 +103,22 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev return 0; } -static unsigned long __init get_loops_per_jiffy(void) +static int arch_timer_starting(unsigned int cpu) +{ + set_csr_ecfg(ECFGF_TIMER); + + return 0; +} + +static int arch_timer_dying(unsigned int cpu) +{ + /* Clear Timer Interrupt */ + write_csr_tintclear(CSR_TINTCLR_TI); + + return 0; +} + +static unsigned long get_loops_per_jiffy(void) { unsigned long lpj = (unsigned long)const_clock_freq; @@ -110,7 +127,7 @@ static unsigned long __init get_loops_per_jiffy(void) return lpj; } -static long init_offset __nosavedata; +static long init_offset; void save_counter(void) { @@ -126,8 +143,12 @@ void sync_counter(void) int constant_clockevent_init(void) { unsigned int cpu = smp_processor_id(); - unsigned long min_delta = 0x600; - unsigned long max_delta = (1UL << 48) - 1; +#ifdef CONFIG_PREEMPT_RT + unsigned long min_delta = 100; +#else + unsigned long min_delta = 1000; +#endif + unsigned long max_delta = GENMASK_ULL(boot_cpu_data.timerbits, 0); struct clock_event_device *cd; static int irq = 0, timer_irq_installed = 0; @@ -167,6 +188,10 @@ int constant_clockevent_init(void) lpj_fine = get_loops_per_jiffy(); pr_info("Constant clock event device register\n"); + cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, + "clockevents/loongarch/timer:starting", + arch_timer_starting, arch_timer_dying); + return 0; } @@ -214,4 +239,5 @@ void __init time_init(void) constant_clockevent_init(); constant_clocksource_init(); + pv_time_init(); } diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index f9f4eb00c92e..da5926fead4a 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/kexec.h> #include <linux/module.h> +#include <linux/export.h> #include <linux/extable.h> #include <linux/mm.h> #include <linux/sched/mm.h> @@ -553,8 +554,12 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs) die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); #else + bool pie = regs_irqs_disabled(regs); unsigned int *pc; + if (!pie) + local_irq_enable(); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); /* @@ -579,6 +584,8 @@ sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); out: + if (!pie) + local_irq_disable(); #endif irqentry_exit(regs, state); } @@ -592,29 +599,37 @@ int is_valid_bugaddr(unsigned long addr) static void bug_handler(struct pt_regs *regs) { + if (user_mode(regs)) { + force_sig(SIGTRAP); + return; + } + switch (report_bug(regs->csr_era, regs)) { case BUG_TRAP_TYPE_BUG: - case BUG_TRAP_TYPE_NONE: - die_if_kernel("Oops - BUG", regs); - force_sig(SIGTRAP); + die("Oops - BUG", regs); break; case BUG_TRAP_TYPE_WARN: /* Skip the BUG instruction and continue */ regs->csr_era += LOONGARCH_INSN_SIZE; break; + + default: + if (!fixup_exception(regs)) + die("Oops - BUG", regs); } } asmlinkage void noinstr do_bce(struct pt_regs *regs) { bool user = user_mode(regs); + bool pie = regs_irqs_disabled(regs); unsigned long era = exception_era(regs); u64 badv = 0, lower = 0, upper = ULONG_MAX; union loongarch_instruction insn; irqentry_state_t state = irqentry_enter(regs); - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_enable(); current->thread.trap_nr = read_csr_excode(); @@ -680,7 +695,7 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs) force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper); out: - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_disable(); irqentry_exit(regs, state); @@ -698,11 +713,12 @@ bad_era: asmlinkage void noinstr do_bp(struct pt_regs *regs) { bool user = user_mode(regs); + bool pie = regs_irqs_disabled(regs); unsigned int opcode, bcode; unsigned long era = exception_era(regs); irqentry_state_t state = irqentry_enter(regs); - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_enable(); if (__get_inst(&opcode, (u32 *)era, user)) @@ -768,7 +784,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) } out: - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_disable(); irqentry_exit(regs, state); @@ -1003,6 +1019,7 @@ static void init_restore_lbt(void) asmlinkage void noinstr do_lbt(struct pt_regs *regs) { + bool pie = regs_irqs_disabled(regs); irqentry_state_t state = irqentry_enter(regs); /* @@ -1012,7 +1029,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs) * (including the user using 'MOVGR2GCSR' to turn on TM, which * will not trigger the BTE), we need to check PRMD first. */ - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_enable(); if (!cpu_has_lbt) { @@ -1026,7 +1043,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs) preempt_enable(); out: - if (regs->csr_prmd & CSR_PRMD_PIE) + if (!pie) local_irq_disable(); irqentry_exit(regs, state); @@ -1114,8 +1131,8 @@ static void configure_exception_vector(void) tlbrentry = (unsigned long)exception_handlers + 80*VECSIZE; csr_write64(eentry, LOONGARCH_CSR_EENTRY); - csr_write64(eentry, LOONGARCH_CSR_MERRENTRY); - csr_write64(tlbrentry, LOONGARCH_CSR_TLBRENTRY); + csr_write64(__pa(eentry), LOONGARCH_CSR_MERRENTRY); + csr_write64(__pa(tlbrentry), LOONGARCH_CSR_TLBRENTRY); } void per_cpu_trap_init(int cpu) diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c index 3abf163dda05..487be604b96a 100644 --- a/arch/loongarch/kernel/unaligned.c +++ b/arch/loongarch/kernel/unaligned.c @@ -482,14 +482,10 @@ sigbus: #ifdef CONFIG_DEBUG_FS static int __init debugfs_unaligned(void) { - struct dentry *d; - - d = debugfs_create_dir("loongarch", NULL); - debugfs_create_u32("unaligned_instructions_user", - S_IRUGO, d, &unaligned_instructions_user); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_user); debugfs_create_u32("unaligned_instructions_kernel", - S_IRUGO, d, &unaligned_instructions_kernel); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_kernel); return 0; } diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c index 98379b7d4147..08d7951b2f60 100644 --- a/arch/loongarch/kernel/unwind_guess.c +++ b/arch/loongarch/kernel/unwind_guess.c @@ -3,6 +3,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include <asm/unwind.h> +#include <linux/export.h> unsigned long unwind_get_return_address(struct unwind_state *state) { diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c index b25722876331..0d5fa64a2225 100644 --- a/arch/loongarch/kernel/unwind_orc.c +++ b/arch/loongarch/kernel/unwind_orc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/objtool.h> +#include <linux/export.h> #include <linux/module.h> +#include <linux/objtool.h> #include <linux/sort.h> #include <asm/exception.h> #include <asm/orc_header.h> @@ -399,7 +400,7 @@ bool unwind_next_frame(struct unwind_state *state) return false; /* Don't let modules unload while we're reading their ORC data. */ - preempt_disable(); + guard(rcu)(); if (is_entry_func(state->pc)) goto end; @@ -507,21 +508,19 @@ bool unwind_next_frame(struct unwind_state *state) state->pc = bt_address(pc); if (!state->pc) { - pr_err("cannot find unwind pc at %pK\n", (void *)pc); + pr_err("cannot find unwind pc at %p\n", (void *)pc); goto err; } if (!__kernel_text_address(state->pc)) goto err; - preempt_enable(); return true; err: state->error = true; end: - preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; } diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 929ae240280a..729e775bd40d 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -3,6 +3,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include <linux/cpumask.h> +#include <linux/export.h> #include <linux/ftrace.h> #include <linux/kallsyms.h> diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c index 87abc7137b73..6022eb0f71db 100644 --- a/arch/loongarch/kernel/uprobes.c +++ b/arch/loongarch/kernel/uprobes.c @@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) utask->autask.saved_trap_nr = current->thread.trap_nr; current->thread.trap_nr = UPROBE_TRAP_NR; instruction_pointer_set(regs, utask->xol_vaddr); - user_enable_single_step(current); return 0; } @@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); current->thread.trap_nr = utask->autask.saved_trap_nr; - - if (auprobe->simulate) - instruction_pointer_set(regs, auprobe->resume_era); - else - instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE); - - user_disable_single_step(current); + instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE); return 0; } @@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.trap_nr = utask->autask.saved_trap_nr; instruction_pointer_set(regs, utask->vaddr); - user_disable_single_step(current); } bool arch_uprobe_xol_was_trapped(struct task_struct *t) @@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) insn.word = auprobe->insn[0]; arch_simulate_insn(insn, regs); - auprobe->resume_era = regs->csr_era; return true; } diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 90dfccb41c14..dee1a15d7f4c 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -14,8 +14,7 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> -#include <linux/time_namespace.h> -#include <linux/timekeeper_internal.h> +#include <linux/vdso_datastore.h> #include <asm/page.h> #include <asm/vdso.h> @@ -26,18 +25,6 @@ extern char vdso_start[], vdso_end[]; -/* Kernel-provided data used by the VDSO. */ -static union vdso_data_store generic_vdso_data __page_aligned_data; - -static union { - u8 page[LOONGARCH_VDSO_DATA_SIZE]; - struct loongarch_vdso_data vdata; -} loongarch_vdso_data __page_aligned_data; - -static struct page *vdso_pages[] = { NULL }; -struct vdso_data *vdso_data = generic_vdso_data.data; -struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { current->mm->context.vdso = (void *)(new_vma->vm_start); @@ -45,55 +32,12 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc return 0; } -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf) -{ - unsigned long pfn; - struct page *timens_page = find_timens_vvar_page(vma); - - switch (vmf->pgoff) { - case VVAR_GENERIC_PAGE_OFFSET: - if (!timens_page) - pfn = sym_to_pfn(vdso_data); - else - pfn = page_to_pfn(timens_page); - break; -#ifdef CONFIG_TIME_NS - case VVAR_TIMENS_PAGE_OFFSET: - /* - * If a task belongs to a time namespace then a namespace specific - * VVAR is mapped with the VVAR_GENERIC_PAGE_OFFSET and the real - * VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET offset. - * See also the comment near timens_setup_vdso_data(). - */ - if (!timens_page) - return VM_FAULT_SIGBUS; - else - pfn = sym_to_pfn(vdso_data); - break; -#endif /* CONFIG_TIME_NS */ - case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END: - pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START; - break; - default: - return VM_FAULT_SIGBUS; - } - - return vmf_insert_pfn(vma, vmf->address, pfn); -} - struct loongarch_vdso_info vdso_info = { .vdso = vdso_start, - .size = PAGE_SIZE, .code_mapping = { .name = "[vdso]", - .pages = vdso_pages, .mremap = vdso_mremap, }, - .data_mapping = { - .name = "[vvar]", - .fault = vvar_fault, - }, .offset_sigreturn = vdso_offset_sigreturn, }; @@ -102,10 +46,16 @@ static int __init init_vdso(void) unsigned long i, cpu, pfn; BUG_ON(!PAGE_ALIGNED(vdso_info.vdso)); - BUG_ON(!PAGE_ALIGNED(vdso_info.size)); for_each_possible_cpu(cpu) - vdso_pdata[cpu].node = cpu_to_node(cpu); + vdso_k_arch_data->pdata[cpu].node = cpu_to_node(cpu); + + vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start); + vdso_info.code_mapping.pages = + kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL); + + if (!vdso_info.code_mapping.pages) + return -ENOMEM; pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso)); for (i = 0; i < vdso_info.size / PAGE_SIZE; i++) @@ -115,37 +65,6 @@ static int __init init_vdso(void) } subsys_initcall(init_vdso); -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)(vvar_page); -} - -/* - * The vvar mapping contains data for a specific time namespace, so when a - * task changes namespace we must unmap its vvar data for the old namespace. - * Subsequent faults will map in data for the new namespace. - * - * For more details see timens_setup_vdso_data(). - */ -int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) -{ - struct mm_struct *mm = task->mm; - struct vm_area_struct *vma; - - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vdso_info.data_mapping)) - zap_vma_pages(vma); - } - mmap_read_unlock(mm); - - return 0; -} -#endif - static unsigned long vdso_base(void) { unsigned long base = STACK_TOP; @@ -181,9 +100,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) goto out; } - vma = _install_special_mapping(mm, data_addr, VVAR_SIZE, - VM_READ | VM_MAYREAD | VM_PFNMAP, - &info->data_mapping); + vma = vdso_install_vvar_mapping(mm, data_addr); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; @@ -191,7 +108,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vdso_addr = data_addr + VVAR_SIZE; vma = _install_special_mapping(mm, vdso_addr, info->size, - VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + VM_READ | VM_EXEC | + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | + VM_SEALED_SYSMAP, &info->code_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); 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 |