diff options
Diffstat (limited to 'kernel/fork.c')
| -rw-r--r-- | kernel/fork.c | 149 |
1 files changed, 111 insertions, 38 deletions
diff --git a/kernel/fork.c b/kernel/fork.c index f0b58479534f..fbe9dfcd8680 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -77,7 +77,6 @@ #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/magic.h> -#include <linux/sched/mm.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> @@ -91,6 +90,7 @@ #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> +#include <linux/stackleak.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -163,10 +163,6 @@ static inline void free_task_struct(struct task_struct *tsk) } #endif -void __weak arch_release_thread_stack(unsigned long *stack) -{ -} - #ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* @@ -220,12 +216,18 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) memset(s->addr, 0, THREAD_SIZE); tsk->stack_vm_area = s; + tsk->stack = s->addr; return s->addr; } + /* + * Allocated stacks are cached and later reused by new threads, + * so memcg accounting is performed manually on assigning/releasing + * stacks to tasks. Drop __GFP_ACCOUNT. + */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, - THREADINFO_GFP, + THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); @@ -234,8 +236,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ - if (stack) + if (stack) { tsk->stack_vm_area = find_vm_area(stack); + tsk->stack = stack; + } return stack; #else struct page *page = alloc_pages_node(node, THREADINFO_GFP, @@ -248,9 +252,19 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK - if (task_stack_vm_area(tsk)) { + struct vm_struct *vm = task_stack_vm_area(tsk); + + if (vm) { int i; + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + -(int)(PAGE_SIZE / 1024)); + + memcg_kmem_uncharge(vm->pages[i], 0); + } + for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) @@ -272,7 +286,10 @@ static struct kmem_cache *thread_stack_cache; static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); + unsigned long *stack; + stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); + tsk->stack = stack; + return stack; } static void free_thread_stack(struct task_struct *tsk) @@ -351,10 +368,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account) NR_KERNEL_STACK_KB, PAGE_SIZE / 1024 * account); } - - /* All stack pages belong to the same memcg. */ - mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); } else { /* * All stack pages are in the same zone and belong to the @@ -370,13 +383,41 @@ static void account_kernel_stack(struct task_struct *tsk, int account) } } +static int memcg_charge_kernel_stack(struct task_struct *tsk) +{ +#ifdef CONFIG_VMAP_STACK + struct vm_struct *vm = task_stack_vm_area(tsk); + int ret; + + if (vm) { + int i; + + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + /* + * If memcg_kmem_charge() fails, page->mem_cgroup + * pointer is NULL, and both memcg_kmem_uncharge() + * and mod_memcg_page_state() in free_thread_stack() + * will ignore this page. So it's safe. + */ + ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0); + if (ret) + return ret; + + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + PAGE_SIZE / 1024); + } + } +#endif + return 0; +} + static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(tsk->state != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ account_kernel_stack(tsk, -1); - arch_release_thread_stack(tsk->stack); free_thread_stack(tsk); tsk->stack = NULL; #ifdef CONFIG_VMAP_STACK @@ -387,7 +428,7 @@ static void release_task_stack(struct task_struct *tsk) #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { - if (atomic_dec_and_test(&tsk->stack_refcount)) + if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif @@ -405,7 +446,7 @@ void free_task(struct task_struct *tsk) * If the task had a separate stack allocation, it should be gone * by now. */ - WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0); + WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); @@ -668,14 +709,14 @@ static inline void free_signal_struct(struct signal_struct *sig) static inline void put_signal_struct(struct signal_struct *sig) { - if (atomic_dec_and_test(&sig->sigcnt)) + if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); - WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); cgroup_free(tsk); @@ -698,15 +739,16 @@ void __init __weak arch_task_cache_init(void) { } static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; + unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ - if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64) + if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else - threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, + threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) @@ -773,6 +815,7 @@ void __init fork_init(void) #endif lockdep_init_task(&init_task); + uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, @@ -794,7 +837,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; unsigned long *stack; - struct vm_struct *stack_vm_area; + struct vm_struct *stack_vm_area __maybe_unused; int err; if (node == NUMA_NO_NODE) @@ -807,6 +850,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!stack) goto free_tsk; + if (memcg_charge_kernel_stack(tsk)) + goto free_stack; + stack_vm_area = task_stack_vm_area(tsk); err = arch_dup_task_struct(tsk, orig); @@ -821,7 +867,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->stack_vm_area = stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK - atomic_set(&tsk->stack_refcount, 1); + refcount_set(&tsk->stack_refcount, 1); #endif if (err) @@ -850,7 +896,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) * One for us, one for whoever does the "release_task()" (usually * parent) */ - atomic_set(&tsk->usage, 2); + refcount_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif @@ -935,7 +981,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; - mm->pinned_vm = 0; + atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); @@ -1253,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) complete_vfork_done(tsk); } -/* - * Allocate a new mm structure and copy contents from the - * mm structure of the passed in task structure. +/** + * dup_mm() - duplicates an existing mm structure + * @tsk: the task_struct with which the new mm will be associated. + * @oldmm: the mm to duplicate. + * + * Allocates a new mm structure and duplicates the provided @oldmm structure + * content into it. + * + * Return: the duplicated mm or NULL on failure. */ -static struct mm_struct *dup_mm(struct task_struct *tsk) +static struct mm_struct *dup_mm(struct task_struct *tsk, + struct mm_struct *oldmm) { - struct mm_struct *mm, *oldmm = current->mm; + struct mm_struct *mm; int err; mm = allocate_mm(); @@ -1326,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) } retval = -ENOMEM; - mm = dup_mm(tsk); + mm = dup_mm(tsk, current->mm); if (!mm) goto fail_nomem; @@ -1417,7 +1470,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { - atomic_inc(¤t->sighand->count); + refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); @@ -1425,7 +1478,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) if (!sig) return -ENOMEM; - atomic_set(&sig->count, 1); + refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); @@ -1434,7 +1487,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_sighand(struct sighand_struct *sighand) { - if (atomic_dec_and_test(&sighand->count)) { + if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it @@ -1481,7 +1534,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->nr_threads = 1; atomic_set(&sig->live, 1); - atomic_set(&sig->sigcnt, 1); + refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); @@ -1779,13 +1832,15 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cpu_timers_init(p); - p->start_time = ktime_get_ns(); - p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); @@ -1879,6 +1934,8 @@ static __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; + stackleak_task_init(p); + if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { @@ -1950,6 +2007,17 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_free_pid; /* + * From this point on we must avoid any synchronous user-space + * communication until we take the tasklist-lock. In particular, we do + * not want user-space to be able to predict the process start-time by + * stalling fork(2) after we recorded the start_time but before it is + * visible to the system. + */ + + p->start_time = ktime_get_ns(); + p->real_start_time = ktime_get_boot_ns(); + + /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ @@ -2021,7 +2089,7 @@ static __latent_entropy struct task_struct *copy_process( } else { current->signal->nr_threads++; atomic_inc(¤t->signal->live); - atomic_inc(¤t->signal->sigcnt); + refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); @@ -2126,6 +2194,11 @@ struct task_struct *fork_idle(int cpu) return task; } +struct mm_struct *copy_init_mm(void) +{ + return dup_mm(NULL, &init_mm); +} + /* * Ok, this is the main fork-routine. * @@ -2378,7 +2451,7 @@ static int check_unshare_flags(unsigned long unshare_flags) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { - if (atomic_read(¤t->sighand->count) > 1) + if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { |