// SPDX-License-Identifier: GPL-2.0-only/* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h>#include <linux/slab.h>#include <linux/sched/autogroup.h>#include <linux/sched/mm.h>#include <linux/sched/user.h>#include <linux/sched/numa_balancing.h>#include <linux/sched/stat.h>#include <linux/sched/task.h>#include <linux/sched/task_stack.h>#include <linux/sched/cputime.h>#include <linux/sched/ext.h>#include <linux/seq_file.h>#include <linux/rtmutex.h>#include <linux/init.h>#include <linux/unistd.h>#include <linux/module.h>#include <linux/vmalloc.h>#include <linux/completion.h>#include <linux/personality.h>#include <linux/mempolicy.h>#include <linux/sem.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/iocontext.h>#include <linux/key.h>#include <linux/kmsan.h>#include <linux/binfmts.h>#include <linux/mman.h>#include <linux/mmu_notifier.h>#include <linux/fs.h>#include <linux/mm.h>#include <linux/mm_inline.h>#include <linux/memblock.h>#include <linux/nsproxy.h>#include <linux/ns/ns_common_types.h>#include <linux/capability.h>#include <linux/cpu.h>#include <linux/cgroup.h>#include <linux/security.h>#include <linux/hugetlb.h>#include <linux/seccomp.h>#include <linux/swap.h>#include <linux/syscalls.h>#include <linux/syscall_user_dispatch.h>#include <linux/jiffies.h>#include <linux/futex.h>#include <linux/compat.h>#include <linux/kthread.h>#include <linux/task_io_accounting_ops.h>#include <linux/rcupdate.h>#include <linux/ptrace.h>#include <linux/mount.h>#include <linux/audit.h>#include <linux/memcontrol.h>#include <linux/ftrace.h>#include <linux/proc_fs.h>#include <linux/profile.h>#include <linux/rmap.h>#include <linux/ksm.h>#include <linux/acct.h>#include <linux/userfaultfd_k.h>#include <linux/tsacct_kern.h>#include <linux/cn_proc.h>#include <linux/freezer.h>#include <linux/delayacct.h>#include <linux/taskstats_kern.h>#include <linux/tty.h>#include <linux/fs_struct.h>#include <linux/magic.h>#include <linux/perf_event.h>#include <linux/posix-timers.h>#include <linux/user-return-notifier.h>#include <linux/oom.h>#include <linux/khugepaged.h>#include <linux/signalfd.h>#include <linux/uprobes.h>#include <linux/aio.h>#include <linux/compiler.h>#include <linux/sysctl.h>#include <linux/kcov.h>#include <linux/livepatch.h>#include <linux/thread_info.h>#include <linux/kstack_erase.h>#include <linux/kasan.h>#include <linux/randomize_kstack.h>#include <linux/scs.h>#include <linux/io_uring.h>#include <linux/io_uring_types.h>#include <linux/bpf.h>#include <linux/stackprotector.h>#include <linux/user_events.h>#include <linux/iommu.h>#include <linux/rseq.h>#include <uapi/linux/pidfd.h>#include <linux/pidfs.h>#include <linux/tick.h>#include <linux/unwind_deferred.h>#include <linux/pgalloc.h>#include <linux/uaccess.h> #include <asm/mmu_context.h>#include <asm/cacheflush.h>#include <asm/tlbflush.h> /* For dup_mmap(). */#include "../mm/internal.h" #include <trace/events/sched.h> #define CREATE_TRACE_POINTS#include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */#define MIN_THREADS 20 /* * Maximum number of threads */#define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */unsigned long total_forks; /* Handle normal Linux uptimes. */int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES),}; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCUint lockdep_tasklist_lock_is_held(void){ return lockdep_is_held(&tasklist_lock);}EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);#endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void){ int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total;} void __weak arch_release_task_struct(struct task_struct *tsk){} static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node){ return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);} static inline void free_task_struct(struct task_struct *tsk){ kmem_cache_free(task_struct_cachep, tsk);} #ifdef CONFIG_VMAP_STACK/* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */#define NR_CACHED_STACKS 2static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);/* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */#define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO | __GFP_SKIP_KASAN) struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area;}; static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node){ struct vm_struct *vm_area; unsigned int i; /* * If the node has memory, we are guaranteed the stacks are backed by local pages. * Otherwise the pages are arbitrary. * * Note that depending on cpuset it is possible we will get migrated to a different * node immediately after allocating here, so this does *not* guarantee locality for * arbitrary callers. */ scoped_guard(preempt) { if (node != NUMA_NO_NODE && numa_node_id() != node) return NULL; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (vm_area) return vm_area; } } return NULL;} static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area){ unsigned int i; int nid; /* * Don't cache stacks if any of the pages don't match the local domain, unless * there is no local memory to begin with. * * Note that lack of local memory does not automatically mean it makes no difference * performance-wise which other domain backs the stack. In this case we are merely * trying to avoid constantly going to vmalloc. */ scoped_guard(preempt) { nid = numa_node_id(); if (node_state(nid, N_MEMORY)) { for (i = 0; i < vm_area->nr_pages; i++) { struct page *page = vm_area->pages[i]; if (page_to_nid(page) != nid) return false; } } for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) return true; } } return false;} static void thread_stack_free_rcu(struct rcu_head *rh){ struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr);} static void thread_stack_delayed_free(struct task_struct *tsk){ struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu);} static int free_vm_stack_cache(unsigned int cpu){ struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0;} static int memcg_charge_kernel_stack(struct vm_struct *vm_area){ int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0;err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); return ret;} static int alloc_thread_stack_node(struct task_struct *tsk, int node){ struct vm_struct *vm_area; void *stack; vm_area = alloc_thread_stack_node_from_cache(tsk, node); if (vm_area) { if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } /* Reset stack metadata. */ if (!kasan_hw_tags_enabled()) kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ clear_pages(vm_area->addr, vm_area->nr_pages); tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm_area; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0;} static void free_thread_stack(struct task_struct *tsk){ if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL;} #else /* !CONFIG_VMAP_STACK */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */#if THREAD_SIZE >= PAGE_SIZE static void thread_stack_free_rcu(struct rcu_head *rh){ __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER);} static void thread_stack_delayed_free(struct task_struct *tsk){ struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu);} static int alloc_thread_stack_node(struct task_struct *tsk, int node){ struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM;} static void free_thread_stack(struct task_struct *tsk){ thread_stack_delayed_free(tsk); tsk->stack = NULL;} #else /* !(THREAD_SIZE >= PAGE_SIZE) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh){ kmem_cache_free(thread_stack_cache, rh);} static void thread_stack_delayed_free(struct task_struct *tsk){ struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu);} static int alloc_thread_stack_node(struct task_struct *tsk, int node){ unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM;} static void free_thread_stack(struct task_struct *tsk){ thread_stack_delayed_free(tsk); tsk->stack = NULL;} void thread_stack_cache_init(void){ thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL);} #endif /* THREAD_SIZE >= PAGE_SIZE */#endif /* CONFIG_VMAP_STACK */ /* SLAB cache for signal_struct structures (tsk->signal) */static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */struct kmem_cache *fs_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account){ if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); }}Lines 1–500 of 3383. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/ns/ns_common_types.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/kstack_erase.h> #include <linux/kasan.h> #include <linux/randomize_kstack.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <linux/unwind_deferred.h> #include <linux/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> /* For dup_mmap(). */ #include "../mm/internal.h" #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); /* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */ #define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO | __GFP_SKIP_KASAN) struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node) { struct vm_struct *vm_area; unsigned int i; /* * If the node has memory, we are guaranteed the stacks are backed by local pages. * Otherwise the pages are arbitrary. * * Note that depending on cpuset it is possible we will get migrated to a different * node immediately after allocating here, so this does *not* guarantee locality for * arbitrary callers. */ scoped_guard(preempt) { if (node != NUMA_NO_NODE && numa_node_id() != node) return NULL; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (vm_area) return vm_area; } } return NULL; } static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area) { unsigned int i; int nid; /* * Don't cache stacks if any of the pages don't match the local domain, unless * there is no local memory to begin with. * * Note that lack of local memory does not automatically mean it makes no difference * performance-wise which other domain backs the stack. In this case we are merely * trying to avoid constantly going to vmalloc. */ scoped_guard(preempt) { nid = numa_node_id(); if (node_state(nid, N_MEMORY)) { for (i = 0; i < vm_area->nr_pages; i++) { struct page *page = vm_area->pages[i]; if (page_to_nid(page) != nid) return false; } } for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) return true; } } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm_area) { int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; vm_area = alloc_thread_stack_node_from_cache(tsk, node); if (vm_area) { if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } /* Reset stack metadata. */ if (!kasan_hw_tags_enabled()) kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ clear_pages(vm_area->addr, vm_area->nr_pages); tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm_area; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } #else /* !CONFIG_VMAP_STACK */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ #if THREAD_SIZE >= PAGE_SIZE static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } #else /* !(THREAD_SIZE >= PAGE_SIZE) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } #endif /* THREAD_SIZE >= PAGE_SIZE */ #endif /* CONFIG_VMAP_STACK */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } }