diff options
Diffstat (limited to 'arch/loongarch/kernel')
-rw-r--r-- | arch/loongarch/kernel/acpi.c | 52 | ||||
-rw-r--r-- | arch/loongarch/kernel/efi-header.S | 4 | ||||
-rw-r--r-- | arch/loongarch/kernel/entry.S | 25 | ||||
-rw-r--r-- | arch/loongarch/kernel/head.S | 2 | ||||
-rw-r--r-- | arch/loongarch/kernel/numa.c | 108 | ||||
-rw-r--r-- | arch/loongarch/kernel/perf_event.c | 3 | ||||
-rw-r--r-- | arch/loongarch/kernel/process.c | 33 | ||||
-rw-r--r-- | arch/loongarch/kernel/smp.c | 38 | ||||
-rw-r--r-- | arch/loongarch/kernel/vdso.c | 4 |
9 files changed, 132 insertions, 137 deletions
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 1120ac2824f6..a54cd6fd3796 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -244,22 +244,6 @@ fdt_earlycon: #ifdef CONFIG_ACPI_NUMA -static __init int setup_node(int pxm) -{ - return acpi_map_pxm_to_node(pxm); -} - -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) @@ -280,7 +264,41 @@ 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(); 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/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/head.S b/arch/loongarch/kernel/head.S index 506a99a5bbc7..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 */ diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 30a72fd528c0..d6e73e8f9c0b 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> @@ -27,10 +28,6 @@ #include <asm/time.h> int numa_off; -unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES]; -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); @@ -43,8 +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); @@ -145,48 +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 node_mem_init(unsigned int node) { unsigned long start_pfn, end_pfn; @@ -205,18 +158,6 @@ 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 * @@ -228,28 +169,21 @@ static void __init add_node_intersection(u32 node, u64 start, u64 size, u32 type */ static void __init add_numamem_region(u64 start, u64 end, u32 type) { - u32 i; - u64 ofs = start; + u32 node = pa_to_nid(start); + u64 size = end - start; + static unsigned long num_physpages; 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; - } - } + 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, end >> PAGE_SHIFT, num_physpages); + memblock_set_node(start, size, &memblock.memory, node); } static void __init init_node_memblock(void) @@ -291,24 +225,6 @@ 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. @@ -333,11 +249,11 @@ int __init init_numa_memory(void) for (i = 0; i < NR_CPUS; i++) set_cpuid_to_node(i, NUMA_NO_NODE); - numa_default_distance(); + numa_reset_distance(); nodes_clear(numa_nodes_parsed); nodes_clear(node_possible_map); nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); + WARN_ON(memblock_clear_hotplug(0, PHYS_ADDR_MAX)); /* Parse SRAT and SLIT if provided by firmware. */ ret = acpi_disabled ? fake_numa_init() : acpi_numa_init(); diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index f86a4b838dd7..8ad098703488 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) diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 6e58f65455c7..3582f591bab2 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 */ @@ -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 diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 4b24589c0b56..46036d98da75 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -46,6 +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); @@ -63,6 +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; @@ -102,6 +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; @@ -406,6 +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(); @@ -572,6 +608,7 @@ 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 @@ -613,6 +650,7 @@ 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/vdso.c b/arch/loongarch/kernel/vdso.c index 10cf1608c7b3..7b888d9085a0 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -105,7 +105,9 @@ 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); |