diff options
Diffstat (limited to 'kernel/fork.c')
-rw-r--r-- | kernel/fork.c | 183 |
1 files changed, 124 insertions, 59 deletions
diff --git a/kernel/fork.c b/kernel/fork.c index 7161ebe67cbb..c6e26e433445 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -58,6 +58,7 @@ #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> +#include <linux/kaiser.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> @@ -75,6 +76,8 @@ #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> +#include <linux/kcov.h> +#include <linux/cpufreq_times.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -147,18 +150,18 @@ static inline void free_task_struct(struct task_struct *tsk) } #endif -void __weak arch_release_thread_info(struct thread_info *ti) +void __weak arch_release_thread_stack(unsigned long *stack) { } -#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR +#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, @@ -167,29 +170,32 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, return page ? page_address(page) : NULL; } -static inline void free_thread_info(struct thread_info *ti) +static inline void free_thread_stack(unsigned long *stack) { - free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); + struct page *page = virt_to_page(stack); + + kaiser_unmap_thread_stack(stack); + __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else -static struct kmem_cache *thread_info_cache; +static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node); + return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_thread_info(struct thread_info *ti) +static void free_thread_stack(unsigned long *stack) { - kmem_cache_free(thread_info_cache, ti); + kmem_cache_free(thread_stack_cache, stack); } -void thread_info_cache_init(void) +void thread_stack_cache_init(void) { - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); + BUG_ON(thread_stack_cache == NULL); } # endif #endif @@ -212,18 +218,19 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -static void account_kernel_stack(struct thread_info *ti, int account) +static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(ti)); + struct zone *zone = page_zone(virt_to_page(stack)); mod_zone_page_state(zone, NR_KERNEL_STACK, account); } void free_task(struct task_struct *tsk) { + cpufreq_task_times_exit(tsk); account_kernel_stack(tsk->stack, -1); - arch_release_thread_info(tsk->stack); - free_thread_info(tsk->stack); + arch_release_thread_stack(tsk->stack); + free_thread_stack(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); @@ -331,26 +338,31 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } -static struct task_struct *dup_task_struct(struct task_struct *orig) +static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; - struct thread_info *ti; - int node = tsk_fork_get_node(orig); + unsigned long *stack; int err; + if (node == NUMA_NO_NODE) + node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; - ti = alloc_thread_info_node(tsk, node); - if (!ti) + stack = alloc_thread_stack_node(tsk, node); + if (!stack) goto free_tsk; err = arch_dup_task_struct(tsk, orig); if (err) - goto free_ti; + goto free_stack; + + tsk->stack = stack; - tsk->stack = ti; + err = kaiser_map_thread_stack(tsk->stack); + if (err) + goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under @@ -367,7 +379,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR - tsk->stack_canary = get_random_int(); + tsk->stack_canary = get_random_long(); #endif /* @@ -382,12 +394,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - account_kernel_stack(ti, 1); + account_kernel_stack(stack, 1); + + kcov_task_init(tsk); return tsk; -free_ti: - free_thread_info(ti); +free_stack: + free_thread_stack(stack); free_tsk: free_task_struct(tsk); return NULL; @@ -585,7 +599,8 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } -static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, + struct user_namespace *user_ns) { mm->mmap = NULL; mm->mm_rb = RB_ROOT; @@ -625,6 +640,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) if (init_new_context(p, mm)) goto fail_nocontext; + mm->user_ns = get_user_ns(user_ns); return mm; fail_nocontext: @@ -670,7 +686,7 @@ struct mm_struct *mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - return mm_init(mm, current); + return mm_init(mm, current, current_user_ns()); } /* @@ -685,10 +701,31 @@ void __mmdrop(struct mm_struct *mm) destroy_context(mm); mmu_notifier_mm_destroy(mm); check_mm(mm); + put_user_ns(mm->user_ns); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); +static inline void __mmput(struct mm_struct *mm) +{ + VM_BUG_ON(atomic_read(&mm->mm_users)); + + uprobe_clear_state(mm); + exit_aio(mm); + ksm_exit(mm); + khugepaged_exit(mm); /* must run before exit_mmap */ + exit_mmap(mm); + set_mm_exe_file(mm, NULL); + if (!list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } + if (mm->binfmt) + module_put(mm->binfmt->module); + mmdrop(mm); +} + /* * Decrement the use count and release all resources for an mm. */ @@ -696,24 +733,24 @@ void mmput(struct mm_struct *mm) { might_sleep(); + if (atomic_dec_and_test(&mm->mm_users)) + __mmput(mm); +} +EXPORT_SYMBOL_GPL(mmput); + +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ if (atomic_dec_and_test(&mm->mm_users)) { - uprobe_clear_state(mm); - exit_aio(mm); - ksm_exit(mm); - khugepaged_exit(mm); /* must run before exit_mmap */ - exit_mmap(mm); - set_mm_exe_file(mm, NULL); - if (!list_empty(&mm->mmlist)) { - spin_lock(&mmlist_lock); - list_del(&mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (mm->binfmt) - module_put(mm->binfmt->module); - mmdrop(mm); + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); } } -EXPORT_SYMBOL_GPL(mmput); /** * set_mm_exe_file - change a reference to the mm's executable file @@ -942,7 +979,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk) memcpy(mm, oldmm, sizeof(*mm)); - if (!mm_init(mm, tsk)) + if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); @@ -1099,7 +1136,9 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) return -ENOMEM; atomic_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); return 0; } @@ -1267,7 +1306,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, int __user *child_tidptr, struct pid *pid, int trace, - unsigned long tls) + unsigned long tls, + int node) { int retval; struct task_struct *p; @@ -1320,10 +1360,24 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; retval = -ENOMEM; - p = dup_task_struct(current); + p = dup_task_struct(current, node); if (!p) goto fork_out; + cpufreq_task_times_init(p); + + /* + * This _must_ happen before we call free_task(), i.e. before we jump + * to any of the bad_fork_* labels. This is to avoid freeing + * p->set_child_tid which is (ab)used as a kthread's data pointer for + * kernel threads (PF_KTHREAD). + */ + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; + /* + * Clear TID on mm_release()? + */ + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; + ftrace_graph_init_task(p); rt_mutex_init_task(p); @@ -1386,8 +1440,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - p->start_time = ktime_get_ns(); - p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; cgroup_fork(p); @@ -1485,11 +1537,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, } } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; - /* - * Clear TID on mm_release()? - */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1553,6 +1600,17 @@ static struct task_struct *copy_process(unsigned long clone_flags, 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! */ @@ -1585,11 +1643,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ recalc_sigpending(); if (signal_pending(current)) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cancel_cgroup; } + if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) { + retval = -ENOMEM; + goto bad_fork_cancel_cgroup; + } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -1640,6 +1700,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, return p; bad_fork_cancel_cgroup: + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, cgrp_ss_priv); bad_fork_free_pid: threadgroup_change_end(current); @@ -1696,7 +1758,8 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1741,7 +1804,7 @@ long _do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace, tls); + child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1750,6 +1813,8 @@ long _do_fork(unsigned long clone_flags, struct completion vfork; struct pid *pid; + cpufreq_task_times_alloc(p); + trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); |