diff options
Diffstat (limited to 'kernel')
54 files changed, 930 insertions, 579 deletions
diff --git a/kernel/async.c b/kernel/async.c index 2cbd3dd5940d..a893d6170944 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -84,20 +84,24 @@ static atomic_t entry_count; static async_cookie_t lowest_in_progress(struct async_domain *domain) { - struct list_head *pending; + struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); - if (domain) - pending = &domain->pending; - else - pending = &async_global_pending; + if (domain) { + if (!list_empty(&domain->pending)) + first = list_first_entry(&domain->pending, + struct async_entry, domain_list); + } else { + if (!list_empty(&async_global_pending)) + first = list_first_entry(&async_global_pending, + struct async_entry, global_list); + } - if (!list_empty(pending)) - ret = list_first_entry(pending, struct async_entry, - domain_list)->cookie; + if (first) + ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b1f66480135b..14750e7c5ee4 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array) { int i; - for (i = 0; i < array->map.max_entries; i++) + for (i = 0; i < array->map.max_entries; i++) { free_percpu(array->pptrs[i]); + cond_resched(); + } } static int bpf_array_alloc_percpu(struct bpf_array *array) @@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) return -ENOMEM; } array->pptrs[i] = ptr; + cond_resched(); } return 0; @@ -73,11 +76,11 @@ static int array_map_alloc_check(union bpf_attr *attr) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; - int numa_node = bpf_map_attr_numa_node(attr); + int ret, numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool unpriv = !capable(CAP_SYS_ADMIN); + u64 cost, array_size, mask64; struct bpf_array *array; - u64 array_size, mask64; elem_size = round_up(attr->value_size, 8); @@ -109,8 +112,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) max_entries * elem_size; /* make sure there is no u32 overflow later in round_up() */ - if (array_size >= U32_MAX - PAGE_SIZE) + cost = array_size; + if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); + if (percpu) { + cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-ENOMEM); + } + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); @@ -121,20 +135,13 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); + array->map.pages = cost; array->elem_size = elem_size; - if (!percpu) - goto out; - - array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); - - if (array_size >= U32_MAX - PAGE_SIZE || - bpf_array_alloc_percpu(array)) { + if (percpu && bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } -out: - array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; return &array->map; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5f35f93dcab2..d315b393abdd 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1576,25 +1576,41 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, __u32 __user *prog_ids, u32 cnt) { struct bpf_prog **prog; - u32 i = 0, id; - + unsigned long err = 0; + u32 i = 0, *ids; + bool nospc; + + /* users of this function are doing: + * cnt = bpf_prog_array_length(); + * if (cnt > 0) + * bpf_prog_array_copy_to_user(..., cnt); + * so below kcalloc doesn't need extra cnt > 0 check, but + * bpf_prog_array_length() releases rcu lock and + * prog array could have been swapped with empty or larger array, + * so always copy 'cnt' prog_ids to the user. + * In a rare race the user will see zero prog_ids + */ + ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); + if (!ids) + return -ENOMEM; rcu_read_lock(); prog = rcu_dereference(progs)->progs; for (; *prog; prog++) { if (*prog == &dummy_bpf_prog.prog) continue; - id = (*prog)->aux->id; - if (copy_to_user(prog_ids + i, &id, sizeof(id))) { - rcu_read_unlock(); - return -EFAULT; - } + ids[i] = (*prog)->aux->id; if (++i == cnt) { prog++; break; } } + nospc = !!(*prog); rcu_read_unlock(); - if (*prog) + err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); + kfree(ids); + if (err) + return -EFAULT; + if (nospc) return -ENOSPC; return 0; } diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index fbfdada6caee..a4bb0b34375a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -334,7 +334,7 @@ static int cpu_map_kthread_run(void *data) static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) { - gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; int numa, err; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 7b469d10d0e9..b4b5b81e7251 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -555,7 +555,10 @@ static void trie_free(struct bpf_map *map) struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; - raw_spin_lock(&trie->lock); + /* Wait for outstanding programs to complete + * update/lookup/delete/get_next_key and free the trie. + */ + synchronize_rcu(); /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent @@ -566,10 +569,9 @@ static void trie_free(struct bpf_map *map) slot = &trie->root; for (;;) { - node = rcu_dereference_protected(*slot, - lockdep_is_held(&trie->lock)); + node = rcu_dereference_protected(*slot, 1); if (!node) - goto unlock; + goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; @@ -587,8 +589,8 @@ static void trie_free(struct bpf_map *map) } } -unlock: - raw_spin_unlock(&trie->lock); +out: + kfree(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 0314d1783d77..a927e89dad6e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -86,9 +86,10 @@ struct smap_psock { struct work_struct tx_work; struct work_struct gc_work; + struct proto *sk_proto; + void (*save_close)(struct sock *sk, long timeout); void (*save_data_ready)(struct sock *sk); void (*save_write_space)(struct sock *sk); - void (*save_state_change)(struct sock *sk); }; static inline struct smap_psock *smap_psock_sk(const struct sock *sk) @@ -96,12 +97,102 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static struct proto tcp_bpf_proto; +static int bpf_tcp_init(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + return -EINVAL; + } + + if (unlikely(psock->sk_proto)) { + rcu_read_unlock(); + return -EBUSY; + } + + psock->save_close = sk->sk_prot->close; + psock->sk_proto = sk->sk_prot; + sk->sk_prot = &tcp_bpf_proto; + rcu_read_unlock(); + return 0; +} + +static void bpf_tcp_release(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + + if (likely(psock)) { + sk->sk_prot = psock->sk_proto; + psock->sk_proto = NULL; + } + rcu_read_unlock(); +} + +static void smap_release_sock(struct smap_psock *psock, struct sock *sock); + +static void bpf_tcp_close(struct sock *sk, long timeout) +{ + void (*close_fun)(struct sock *sk, long timeout); + struct smap_psock_map_entry *e, *tmp; + struct smap_psock *psock; + struct sock *osk; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + return sk->sk_prot->close(sk, timeout); + } + + /* The psock may be destroyed anytime after exiting the RCU critial + * section so by the time we use close_fun the psock may no longer + * be valid. However, bpf_tcp_close is called with the sock lock + * held so the close hook and sk are still valid. + */ + close_fun = psock->save_close; + + write_lock_bh(&sk->sk_callback_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + list_del(&e->list); + smap_release_sock(psock, sk); + } + } + write_unlock_bh(&sk->sk_callback_lock); + rcu_read_unlock(); + close_fun(sk, timeout); +} + enum __sk_action { __SK_DROP = 0, __SK_PASS, __SK_REDIRECT, }; +static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = { + .name = "bpf_tcp", + .uid = TCP_ULP_BPF, + .user_visible = false, + .owner = NULL, + .init = bpf_tcp_init, + .release = bpf_tcp_release, +}; + +static int bpf_tcp_ulp_register(void) +{ + tcp_bpf_proto = tcp_prot; + tcp_bpf_proto.close = bpf_tcp_close; + return tcp_register_ulp(&bpf_tcp_ulp_ops); +} + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); @@ -166,68 +257,6 @@ static void smap_report_sk_error(struct smap_psock *psock, int err) sk->sk_error_report(sk); } -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); - -/* Called with lock_sock(sk) held */ -static void smap_state_change(struct sock *sk) -{ - struct smap_psock_map_entry *e, *tmp; - struct smap_psock *psock; - struct socket_wq *wq; - struct sock *osk; - - rcu_read_lock(); - - /* Allowing transitions into an established syn_recv states allows - * for early binding sockets to a smap object before the connection - * is established. - */ - switch (sk->sk_state) { - case TCP_SYN_SENT: - case TCP_SYN_RECV: - case TCP_ESTABLISHED: - break; - case TCP_CLOSE_WAIT: - case TCP_CLOSING: - case TCP_LAST_ACK: - case TCP_FIN_WAIT1: - case TCP_FIN_WAIT2: - case TCP_LISTEN: - break; - case TCP_CLOSE: - /* Only release if the map entry is in fact the sock in - * question. There is a case where the operator deletes - * the sock from the map, but the TCP sock is closed before - * the psock is detached. Use cmpxchg to verify correct - * sock is removed. - */ - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - break; - write_lock_bh(&sk->sk_callback_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - osk = cmpxchg(e->entry, sk, NULL); - if (osk == sk) { - list_del(&e->list); - smap_release_sock(psock, sk); - } - } - write_unlock_bh(&sk->sk_callback_lock); - break; - default: - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - break; - smap_report_sk_error(psock, EPIPE); - break; - } - - wq = rcu_dereference(sk->sk_wq); - if (skwq_has_sleeper(wq)) - wake_up_interruptible_all(&wq->wait); - rcu_read_unlock(); -} - static void smap_read_sock_strparser(struct strparser *strp, struct sk_buff *skb) { @@ -322,10 +351,8 @@ static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) return; sk->sk_data_ready = psock->save_data_ready; sk->sk_write_space = psock->save_write_space; - sk->sk_state_change = psock->save_state_change; psock->save_data_ready = NULL; psock->save_write_space = NULL; - psock->save_state_change = NULL; strp_stop(&psock->strp); psock->strp_enabled = false; } @@ -350,6 +377,7 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock) if (psock->refcnt) return; + tcp_cleanup_ulp(sock); smap_stop_sock(psock, sock); clear_bit(SMAP_TX_RUNNING, &psock->state); rcu_assign_sk_user_data(sock, NULL); @@ -427,10 +455,8 @@ static void smap_start_sock(struct smap_psock *psock, struct sock *sk) return; psock->save_data_ready = sk->sk_data_ready; psock->save_write_space = sk->sk_write_space; - psock->save_state_change = sk->sk_state_change; sk->sk_data_ready = smap_data_ready; sk->sk_write_space = smap_write_space; - sk->sk_state_change = smap_state_change; psock->strp_enabled = true; } @@ -495,8 +521,8 @@ static struct smap_psock *smap_init_psock(struct sock *sock, static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; - int err = -EINVAL; u64 cost; + int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -509,6 +535,10 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (attr->value_size > KMALLOC_MAX_SIZE) return ERR_PTR(-E2BIG); + err = bpf_tcp_ulp_register(); + if (err && err != -EEXIST) + return ERR_PTR(err); + stab = kzalloc(sizeof(*stab), GFP_USER); if (!stab) return ERR_PTR(-ENOMEM); @@ -517,6 +547,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); + err = -EINVAL; if (cost >= U32_MAX - PAGE_SIZE) goto free_stab; @@ -590,11 +621,6 @@ static void sock_map_free(struct bpf_map *map) } rcu_read_unlock(); - if (stab->bpf_verdict) - bpf_prog_put(stab->bpf_verdict); - if (stab->bpf_parse) - bpf_prog_put(stab->bpf_parse); - sock_map_remove_complete(stab); } @@ -754,6 +780,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto out_progs; } + err = tcp_set_ulp_id(sock, TCP_ULP_BPF); + if (err) + goto out_progs; + set_bit(SMAP_TX_RUNNING, &psock->state); } @@ -866,6 +896,19 @@ static int sock_map_update_elem(struct bpf_map *map, return err; } +static void sock_map_release(struct bpf_map *map, struct file *map_file) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_prog *orig; + + orig = xchg(&stab->bpf_parse, NULL); + if (orig) + bpf_prog_put(orig); + orig = xchg(&stab->bpf_verdict, NULL); + if (orig) + bpf_prog_put(orig); +} + const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, @@ -873,6 +916,7 @@ const struct bpf_map_ops sock_map_ops = { .map_get_next_key = sock_map_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, + .map_release = sock_map_release, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f7efa7b4d825..b42037e6e81d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1254,9 +1254,9 @@ done: return retval; } -int current_cpuset_is_being_rebound(void) +bool current_cpuset_is_being_rebound(void) { - int ret; + bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; diff --git a/kernel/compat.c b/kernel/compat.c index d1cee656a7ed..3247fe761f60 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -355,7 +355,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - size_t retlen = min_t(size_t, len, cpumask_size()); + unsigned int retlen = min(len, cpumask_size()); if (compat_put_bitmap(user_mask_ptr, cpumask_bits(mask), retlen * 8)) ret = -EFAULT; diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config index 8d9643767142..108fecc20fc1 100644 --- a/kernel/configs/kvm_guest.config +++ b/kernel/configs/kvm_guest.config @@ -18,6 +18,7 @@ CONFIG_VIRTUALIZATION=y CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_KVM_GUEST=y +CONFIG_S390_GUEST=y CONFIG_VIRTIO=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BLK=y diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config index 7fa0c4ae6394..9bfdffc100da 100644 --- a/kernel/configs/tiny.config +++ b/kernel/configs/tiny.config @@ -10,3 +10,7 @@ CONFIG_OPTIMIZE_INLINING=y # CONFIG_SLAB is not set # CONFIG_SLUB is not set CONFIG_SLOB=y +CONFIG_CC_STACKPROTECTOR_NONE=y +# CONFIG_CC_STACKPROTECTOR_REGULAR is not set +# CONFIG_CC_STACKPROTECTOR_STRONG is not set +# CONFIG_CC_STACKPROTECTOR_AUTO is not set diff --git a/kernel/events/core.c b/kernel/events/core.c index f0549e79978b..96db9ae5d5af 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4524,7 +4524,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct ring_buffer *rb; - __poll_t events = POLLHUP; + __poll_t events = EPOLLHUP; poll_wait(file, &event->waitq, wait); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 141aa2ca8728..6c6b3c48db71 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -19,7 +19,7 @@ static void perf_output_wakeup(struct perf_output_handle *handle) { - atomic_set(&handle->rb->poll, POLLIN); + atomic_set(&handle->rb->poll, EPOLLIN); handle->event->pending_wakeup = 1; irq_work_queue(&handle->event->pending); diff --git a/kernel/extable.c b/kernel/extable.c index a17fdb63dc3e..6a5b61ebc66c 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -64,7 +64,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -static inline int init_kernel_text(unsigned long addr) +int init_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext) diff --git a/kernel/fork.c b/kernel/fork.c index 5e6cf0dd031c..e5d9d405ae4e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -283,8 +283,9 @@ static void free_thread_stack(struct task_struct *tsk) void thread_stack_cache_init(void) { - thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE, - THREAD_SIZE, 0, NULL); + 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 @@ -591,7 +592,7 @@ static void check_mm(struct mm_struct *mm) * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ -static void __mmdrop(struct mm_struct *mm) +void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); mm_free_pgd(mm); @@ -602,13 +603,7 @@ static void __mmdrop(struct mm_struct *mm) put_user_ns(mm->user_ns); free_mm(mm); } - -void mmdrop(struct mm_struct *mm) -{ - if (unlikely(atomic_dec_and_test(&mm->mm_count))) - __mmdrop(mm); -} -EXPORT_SYMBOL_GPL(mmdrop); +EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { @@ -693,6 +688,21 @@ static void set_max_threads(unsigned int max_threads_suggested) int arch_task_struct_size __read_mostly; #endif +static void task_struct_whitelist(unsigned long *offset, unsigned long *size) +{ + /* Fetch thread_struct whitelist for the architecture. */ + arch_thread_struct_whitelist(offset, size); + + /* + * Handle zero-sized whitelist or empty thread_struct, otherwise + * adjust offset to position of thread_struct in task_struct. + */ + if (unlikely(*size == 0)) + *offset = 0; + else + *offset += offsetof(struct task_struct, thread); +} + void __init fork_init(void) { int i; @@ -701,11 +711,14 @@ void __init fork_init(void) #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); + unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ - task_struct_cachep = kmem_cache_create("task_struct", + task_struct_whitelist(&useroffset, &usersize); + task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, - SLAB_PANIC|SLAB_ACCOUNT, NULL); + SLAB_PANIC|SLAB_ACCOUNT, + useroffset, usersize, NULL); #endif /* do the arch specific task caches init */ @@ -1568,6 +1581,10 @@ static __latent_entropy struct task_struct *copy_process( int retval; struct task_struct *p; + /* + * Don't allow sharing the root directory with processes in a different + * namespace + */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); @@ -2043,6 +2060,8 @@ long _do_fork(unsigned long clone_flags, int __user *child_tidptr, unsigned long tls) { + struct completion vfork; + struct pid *pid; struct task_struct *p; int trace = 0; long nr; @@ -2068,43 +2087,40 @@ long _do_fork(unsigned long clone_flags, p = copy_process(clone_flags, stack_start, stack_size, child_tidptr, NULL, trace, tls, NUMA_NO_NODE); add_latent_entropy(); + + if (IS_ERR(p)) + return PTR_ERR(p); + /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ - if (!IS_ERR(p)) { - struct completion vfork; - struct pid *pid; - - trace_sched_process_fork(current, p); - - pid = get_task_pid(p, PIDTYPE_PID); - nr = pid_vnr(pid); + trace_sched_process_fork(current, p); - if (clone_flags & CLONE_PARENT_SETTID) - put_user(nr, parent_tidptr); + pid = get_task_pid(p, PIDTYPE_PID); + nr = pid_vnr(pid); - if (clone_flags & CLONE_VFORK) { - p->vfork_done = &vfork; - init_completion(&vfork); - get_task_struct(p); - } + if (clone_flags & CLONE_PARENT_SETTID) + put_user(nr, parent_tidptr); - wake_up_new_task(p); + if (clone_flags & CLONE_VFORK) { + p->vfork_done = &vfork; + init_completion(&vfork); + get_task_struct(p); + } - /* forking complete and child started to run, tell ptracer */ - if (unlikely(trace)) - ptrace_event_pid(trace, pid); + wake_up_new_task(p); - if (clone_flags & CLONE_VFORK) { - if (!wait_for_vfork_done(p, &vfork)) - ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); - } + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event_pid(trace, pid); - put_pid(pid); - } else { - nr = PTR_ERR(p); + if (clone_flags & CLONE_VFORK) { + if (!wait_for_vfork_done(p, &vfork)) + ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } + + put_pid(pid); return nr; } @@ -2248,9 +2264,11 @@ void __init proc_caches_init(void) * maximum number of CPU's we can ever have. The cpumask_allocation * is at the end of the structure, exactly for that reason. */ - mm_cachep = kmem_cache_create("mm_struct", + mm_cachep = kmem_cache_create_usercopy("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, + offsetof(struct mm_struct, saved_auxv), + sizeof_field(struct mm_struct, saved_auxv), NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); diff --git a/kernel/futex.c b/kernel/futex.c index 7f719d110908..1f450e092c74 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -862,24 +862,6 @@ static void put_pi_state(struct futex_pi_state *pi_state) } } -/* - * Look up the task based on what TID userspace gave us. - * We dont trust it. - */ -static struct task_struct *futex_find_get_task(pid_t pid) -{ - struct task_struct *p; - - rcu_read_lock(); - p = find_task_by_vpid(pid); - if (p) - get_task_struct(p); - - rcu_read_unlock(); - - return p; -} - #ifdef CONFIG_FUTEX_PI /* @@ -1183,7 +1165,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, */ if (!pid) return -ESRCH; - p = futex_find_get_task(pid); + p = find_get_task_by_vpid(pid); if (!p) return -ESRCH; diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 4e8089b319ae..8c82ea26e837 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -71,7 +71,7 @@ unsigned long probe_irq_on(void) raw_spin_lock_irq(&desc->lock); if (!desc->action && irq_settings_can_probe(desc)) { desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; - if (irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE)) + if (irq_activate_and_startup(desc, IRQ_NORESEND)) desc->istate |= IRQS_PENDING; } raw_spin_unlock_irq(&desc->lock); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 043bfc35b353..c69357a43849 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -294,11 +294,11 @@ int irq_activate(struct irq_desc *desc) return 0; } -void irq_activate_and_startup(struct irq_desc *desc, bool resend) +int irq_activate_and_startup(struct irq_desc *desc, bool resend) { if (WARN_ON(irq_activate(desc))) - return; - irq_startup(desc, resend, IRQ_START_FORCE); + return 0; + return irq_startup(desc, resend, IRQ_START_FORCE); } static void __irq_disable(struct irq_desc *desc, bool mask); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ab19371eab9b..ca6afa267070 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -76,7 +76,7 @@ extern void __enable_irq(struct irq_desc *desc); #define IRQ_START_COND false extern int irq_activate(struct irq_desc *desc); -extern void irq_activate_and_startup(struct irq_desc *desc, bool resend); +extern int irq_activate_and_startup(struct irq_desc *desc, bool resend); extern int irq_startup(struct irq_desc *desc, bool resend, bool force); extern void irq_shutdown(struct irq_desc *desc); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e6a9c36470ee..82b8b18ee1eb 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1726,25 +1726,14 @@ static int irq_domain_debug_show(struct seq_file *m, void *p) irq_domain_debug_show_one(m, d, 0); return 0; } - -static int irq_domain_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_domain_debug_show, inode->i_private); -} - -static const struct file_operations dfs_domain_ops = { - .open = irq_domain_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(irq_domain_debug); static void debugfs_add_domain_dir(struct irq_domain *d) { if (!d->name || !domain_dir || d->debugfs_file) return; d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d, - &dfs_domain_ops); + &irq_domain_debug_fops); } static void debugfs_remove_domain_dir(struct irq_domain *d) @@ -1760,7 +1749,8 @@ void __init irq_domain_debugfs_init(struct dentry *root) if (!domain_dir) return; - debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops); + debugfs_create_file("default", 0444, domain_dir, NULL, + &irq_domain_debug_fops); mutex_lock(&irq_domain_mutex); list_for_each_entry(d, &irq_domain_list, link) debugfs_add_domain_dir(d); diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 5187dfe809ac..4c5770407031 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -16,6 +16,7 @@ struct cpumap { unsigned int available; unsigned int allocated; unsigned int managed; + bool initialized; bool online; unsigned long alloc_map[IRQ_MATRIX_SIZE]; unsigned long managed_map[IRQ_MATRIX_SIZE]; @@ -81,9 +82,11 @@ void irq_matrix_online(struct irq_matrix *m) BUG_ON(cm->online); - bitmap_zero(cm->alloc_map, m->matrix_bits); - cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc); - cm->allocated = 0; + if (!cm->initialized) { + cm->available = m->alloc_size; + cm->available -= cm->managed + m->systembits_inalloc; + cm->initialized = true; + } m->global_available += cm->available; cm->online = true; m->online_maps++; @@ -370,14 +373,16 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) return; - if (cm->online) { - clear_bit(bit, cm->alloc_map); - cm->allocated--; + clear_bit(bit, cm->alloc_map); + cm->allocated--; + + if (cm->online) m->total_allocated--; - if (!managed) { - cm->available++; + + if (!managed) { + cm->available++; + if (cm->online) m->global_available++; - } } trace_irq_matrix_free(bit, cpu, m, cm); } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index ef2a47e0eab6..6cdecc6f4c53 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -10,7 +10,6 @@ #include <linux/jiffies.h> #include <linux/irq.h> #include <linux/module.h> -#include <linux/kallsyms.h> #include <linux/interrupt.h> #include <linux/moduleparam.h> #include <linux/timer.h> diff --git a/kernel/jump_label.c b/kernel/jump_label.c index b4517095db6a..52a0a7af8640 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -366,12 +366,15 @@ static void __jump_label_update(struct static_key *key, { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { /* - * entry->code set to 0 invalidates module init text sections - * kernel_text_address() verifies we are not in core kernel - * init code, see jump_label_invalidate_module_init(). + * An entry->code of 0 indicates an entry which has been + * disabled because it was in an init text area. */ - if (entry->code && kernel_text_address(entry->code)) - arch_jump_label_transform(entry, jump_label_type(entry)); + if (entry->code) { + if (kernel_text_address(entry->code)) + arch_jump_label_transform(entry, jump_label_type(entry)); + else + WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code); + } } } @@ -417,6 +420,19 @@ void __init jump_label_init(void) cpus_read_unlock(); } +/* Disable any jump label entries in __init code */ +void __init jump_label_invalidate_init(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (init_kernel_text(iter->code)) + iter->code = 0; + } +} + #ifdef CONFIG_MODULES static enum jump_label_type jump_label_init_type(struct jump_entry *entry) @@ -633,6 +649,7 @@ static void jump_label_del_module(struct module *mod) } } +/* Disable any jump label entries in module init code */ static void jump_label_invalidate_module_init(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; diff --git a/kernel/kcov.c b/kernel/kcov.c index 7594c033d98a..2c16f1ab5e10 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -358,7 +358,8 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, */ if (kcov->mode != KCOV_MODE_INIT || !kcov->area) return -EINVAL; - if (kcov->t != NULL) + t = current; + if (kcov->t != NULL || t->kcov != NULL) return -EBUSY; if (arg == KCOV_TRACE_PC) kcov->mode = KCOV_MODE_TRACE_PC; @@ -370,7 +371,6 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, #endif else return -EINVAL; - t = current; /* Cache in task struct for performance. */ t->kcov_size = kcov->size; t->kcov_area = kcov->area; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index da2ccf142358..102160ff5c66 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -978,67 +978,90 @@ static int prepare_kprobe(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void arm_kprobe_ftrace(struct kprobe *p) +static int arm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); - WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); - kprobe_ftrace_enabled++; - if (kprobe_ftrace_enabled == 1) { + if (ret) { + pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; + } + + if (kprobe_ftrace_enabled == 0) { ret = register_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (ret) { + pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); + goto err_ftrace; + } } + + kprobe_ftrace_enabled++; + return ret; + +err_ftrace: + /* + * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a + * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental + * empty filter_hash which would undesirably trace all functions. + */ + ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); + return ret; } /* Caller must lock kprobe_mutex */ -static void disarm_kprobe_ftrace(struct kprobe *p) +static int disarm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; - kprobe_ftrace_enabled--; - if (kprobe_ftrace_enabled == 0) { + if (kprobe_ftrace_enabled == 1) { ret = unregister_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) + return ret; } + + kprobe_ftrace_enabled--; + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) do {} while (0) -#define disarm_kprobe_ftrace(p) do {} while (0) +#define arm_kprobe_ftrace(p) (-ENODEV) +#define disarm_kprobe_ftrace(p) (-ENODEV) #endif /* Arm a kprobe with text_mutex */ -static void arm_kprobe(struct kprobe *kp) +static int arm_kprobe(struct kprobe *kp) { - if (unlikely(kprobe_ftrace(kp))) { - arm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return arm_kprobe_ftrace(kp); + cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* Disarm a kprobe with text_mutex */ -static void disarm_kprobe(struct kprobe *kp, bool reopt) +static int disarm_kprobe(struct kprobe *kp, bool reopt) { - if (unlikely(kprobe_ftrace(kp))) { - disarm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* @@ -1362,9 +1385,15 @@ out: if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) + if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ - arm_kprobe(ap); + ret = arm_kprobe(ap); + if (ret) { + ap->flags |= KPROBE_FLAG_DISABLED; + list_del_rcu(&p->list); + synchronize_sched(); + } + } } return ret; } @@ -1573,8 +1602,14 @@ int register_kprobe(struct kprobe *p) hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arm_kprobe(p); + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { + ret = arm_kprobe(p); + if (ret) { + hlist_del_rcu(&p->hlist); + synchronize_sched(); + goto out; + } + } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); @@ -1608,11 +1643,12 @@ static int aggr_kprobe_disabled(struct kprobe *ap) static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; + int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) - return NULL; + return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ @@ -1626,8 +1662,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) * should have already been disarmed, so * skip unneed disarming process. */ - if (!kprobes_all_disarmed) - disarm_kprobe(orig_p, true); + if (!kprobes_all_disarmed) { + ret = disarm_kprobe(orig_p, true); + if (ret) { + p->flags &= ~KPROBE_FLAG_DISABLED; + return ERR_PTR(ret); + } + } orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -1644,8 +1685,8 @@ static int __unregister_kprobe_top(struct kprobe *p) /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); - if (ap == NULL) - return -EINVAL; + if (IS_ERR(ap)) + return PTR_ERR(ap); if (ap == p) /* @@ -2078,12 +2119,14 @@ static void kill_kprobe(struct kprobe *p) int disable_kprobe(struct kprobe *kp) { int ret = 0; + struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ - if (__disable_kprobe(kp) == NULL) - ret = -EINVAL; + p = __disable_kprobe(kp); + if (IS_ERR(p)) + ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; @@ -2116,7 +2159,9 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; - arm_kprobe(p); + ret = arm_kprobe(p); + if (ret) + p->flags |= KPROBE_FLAG_DISABLED; } out: mutex_unlock(&kprobe_mutex); @@ -2407,11 +2452,12 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -static void arm_all_kprobes(void) +static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); @@ -2428,46 +2474,74 @@ static void arm_all_kprobes(void) /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) - if (!kprobe_disabled(p)) - arm_kprobe(p); + /* Arm all kprobes on a best-effort basis */ + hlist_for_each_entry_rcu(p, head, hlist) { + if (!kprobe_disabled(p)) { + err = arm_kprobe(p); + if (err) { + errors++; + ret = err; + } + total++; + } + } } - printk(KERN_INFO "Kprobes globally enabled\n"); + if (errors) + pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); - return; + return ret; } -static void disarm_all_kprobes(void) +static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); - return; + return 0; } kprobes_all_disarmed = true; - printk(KERN_INFO "Kprobes globally disabled\n"); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; + /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry_rcu(p, head, hlist) { - if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - disarm_kprobe(p, false); + if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { + err = disarm_kprobe(p, false); + if (err) { + errors++; + ret = err; + } + total++; + } } } + + if (errors) + pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally disabled\n"); + mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); + + return ret; } /* @@ -2494,6 +2568,7 @@ static ssize_t write_enabled_file_bool(struct file *file, { char buf[32]; size_t buf_size; + int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -2504,17 +2579,20 @@ static ssize_t write_enabled_file_bool(struct file *file, case 'y': case 'Y': case '1': - arm_all_kprobes(); + ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': - disarm_all_kprobes(); + ret = disarm_all_kprobes(); break; default: return -EINVAL; } + if (ret) + return ret; + return count; } diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 38ece035039e..d880296245c5 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -379,6 +379,14 @@ queue: tail = encode_tail(smp_processor_id(), idx); node += idx; + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + node->locked = 0; node->next = NULL; pv_init_node(node); @@ -408,14 +416,15 @@ queue: */ if (old & _Q_TAIL_MASK) { prev = decode_tail(old); + /* - * The above xchg_tail() is also a load of @lock which - * generates, through decode_tail(), a pointer. The address - * dependency matches the RELEASE of xchg_tail() such that - * the subsequent access to @prev happens after. + * We must ensure that the stores to @node are observed before + * the write to prev->next. The address dependency from + * xchg_tail is not sufficient to ensure this because the read + * component of xchg_tail is unordered with respect to the + * initialisation of @node. */ - - WRITE_ONCE(prev->next, node); + smp_store_release(&prev->next, node); pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); diff --git a/kernel/memremap.c b/kernel/memremap.c index 403ab9cdb949..4849be5f9b3c 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -188,13 +188,6 @@ static RADIX_TREE(pgmap_radix, GFP_KERNEL); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT) -struct page_map { - struct resource res; - struct percpu_ref *ref; - struct dev_pagemap pgmap; - struct vmem_altmap altmap; -}; - static unsigned long order_at(struct resource *res, unsigned long pgoff) { unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff; @@ -248,34 +241,36 @@ int device_private_entry_fault(struct vm_area_struct *vma, EXPORT_SYMBOL(device_private_entry_fault); #endif /* CONFIG_DEVICE_PRIVATE */ -static void pgmap_radix_release(struct resource *res) +static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff) { unsigned long pgoff, order; mutex_lock(&pgmap_lock); - foreach_order_pgoff(res, order, pgoff) + foreach_order_pgoff(res, order, pgoff) { + if (pgoff >= end_pgoff) + break; radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff); + } mutex_unlock(&pgmap_lock); synchronize_rcu(); } -static unsigned long pfn_first(struct page_map *page_map) +static unsigned long pfn_first(struct dev_pagemap *pgmap) { - struct dev_pagemap *pgmap = &page_map->pgmap; - const struct resource *res = &page_map->res; - struct vmem_altmap *altmap = pgmap->altmap; + const struct resource *res = &pgmap->res; + struct vmem_altmap *altmap = &pgmap->altmap; unsigned long pfn; pfn = res->start >> PAGE_SHIFT; - if (altmap) + if (pgmap->altmap_valid) pfn += vmem_altmap_offset(altmap); return pfn; } -static unsigned long pfn_end(struct page_map *page_map) +static unsigned long pfn_end(struct dev_pagemap *pgmap) { - const struct resource *res = &page_map->res; + const struct resource *res = &pgmap->res; return (res->start + resource_size(res)) >> PAGE_SHIFT; } @@ -283,15 +278,15 @@ static unsigned long pfn_end(struct page_map *page_map) #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) -static void devm_memremap_pages_release(struct device *dev, void *data) +static void devm_memremap_pages_release(void *data) { - struct page_map *page_map = data; - struct resource *res = &page_map->res; + struct dev_pagemap *pgmap = data; + struct device *dev = pgmap->dev; + struct resource *res = &pgmap->res; resource_size_t align_start, align_size; - struct dev_pagemap *pgmap = &page_map->pgmap; unsigned long pfn; - for_each_device_pfn(pfn, page_map) + for_each_device_pfn(pfn, pgmap) put_page(pfn_to_page(pfn)); if (percpu_ref_tryget_live(pgmap->ref)) { @@ -301,56 +296,51 @@ static void devm_memremap_pages_release(struct device *dev, void *data) /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) + - align_start; mem_hotplug_begin(); - arch_remove_memory(align_start, align_size); + arch_remove_memory(align_start, align_size, pgmap->altmap_valid ? + &pgmap->altmap : NULL); mem_hotplug_done(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); - pgmap_radix_release(res); - dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, - "%s: failed to free all reserved pages\n", __func__); -} - -/* assumes rcu_read_lock() held at entry */ -struct dev_pagemap *find_dev_pagemap(resource_size_t phys) -{ - struct page_map *page_map; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys)); - return page_map ? &page_map->pgmap : NULL; + pgmap_radix_release(res, -1); + dev_WARN_ONCE(dev, pgmap->altmap.alloc, + "%s: failed to free all reserved pages\n", __func__); } /** * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res - * @res: "host memory" address range - * @ref: a live per-cpu reference count - * @altmap: optional descriptor for allocating the memmap from @res + * @pgmap: pointer to a struct dev_pgmap * * Notes: - * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time - * (or devm release event). The expected order of events is that @ref has + * 1/ At a minimum the res, ref and type members of @pgmap must be initialized + * by the caller before passing it to this function + * + * 2/ The altmap field may optionally be initialized, in which case altmap_valid + * must be set to true + * + * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages() + * time (or devm release event). The expected order of events is that ref has * been through percpu_ref_kill() before devm_memremap_pages_release(). The * wait for the completion of all references being dropped and * percpu_ref_exit() must occur after devm_memremap_pages_release(). * - * 2/ @res is expected to be a host memory range that could feasibly be + * 4/ res is expected to be a host memory range that could feasibly be * treated as a "System RAM" range, i.e. not a device mmio range, but * this is not enforced. */ -void *devm_memremap_pages(struct device *dev, struct resource *res, - struct percpu_ref *ref, struct vmem_altmap *altmap) +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { resource_size_t align_start, align_size, align_end; + struct vmem_altmap *altmap = pgmap->altmap_valid ? + &pgmap->altmap : NULL; unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; - struct dev_pagemap *pgmap; - struct page_map *page_map; int error, nid, is_ram, i = 0; + struct resource *res = &pgmap->res; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -367,47 +357,18 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (is_ram == REGION_INTERSECTS) return __va(res->start); - if (!ref) + if (!pgmap->ref) return ERR_PTR(-EINVAL); - page_map = devres_alloc_node(devm_memremap_pages_release, - sizeof(*page_map), GFP_KERNEL, dev_to_node(dev)); - if (!page_map) - return ERR_PTR(-ENOMEM); - pgmap = &page_map->pgmap; - - memcpy(&page_map->res, res, sizeof(*res)); - pgmap->dev = dev; - if (altmap) { - memcpy(&page_map->altmap, altmap, sizeof(*altmap)); - pgmap->altmap = &page_map->altmap; - } - pgmap->ref = ref; - pgmap->res = &page_map->res; - pgmap->type = MEMORY_DEVICE_HOST; - pgmap->page_fault = NULL; - pgmap->page_free = NULL; - pgmap->data = NULL; mutex_lock(&pgmap_lock); error = 0; align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { - struct dev_pagemap *dup; - - rcu_read_lock(); - dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff)); - rcu_read_unlock(); - if (dup) { - dev_err(dev, "%s: %pr collides with mapping for %s\n", - __func__, res, dev_name(dup->dev)); - error = -EBUSY; - break; - } error = __radix_tree_insert(&pgmap_radix, - PHYS_PFN(res->start) + pgoff, order, page_map); + PHYS_PFN(res->start) + pgoff, order, pgmap); if (error) { dev_err(dev, "%s: failed: %d\n", __func__, error); break; @@ -427,16 +388,16 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, goto err_pfn_remap; mem_hotplug_begin(); - error = arch_add_memory(nid, align_start, align_size, false); + error = arch_add_memory(nid, align_start, align_size, altmap, false); if (!error) move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT); + align_size >> PAGE_SHIFT, altmap); mem_hotplug_done(); if (error) goto err_add_memory; - for_each_device_pfn(pfn, page_map) { + for_each_device_pfn(pfn, pgmap) { struct page *page = pfn_to_page(pfn); /* @@ -447,19 +408,21 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, */ list_del(&page->lru); page->pgmap = pgmap; - percpu_ref_get(ref); + percpu_ref_get(pgmap->ref); if (!(++i % 1024)) cond_resched(); } - devres_add(dev, page_map); + + devm_add_action(dev, devm_memremap_pages_release, pgmap); + return __va(res->start); err_add_memory: untrack_pfn(NULL, PHYS_PFN(align_start), align_size); err_pfn_remap: err_radix: - pgmap_radix_release(res); - devres_free(page_map); + pgmap_radix_release(res, pgoff); + devres_free(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); @@ -475,34 +438,39 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) altmap->alloc -= nr_pfns; } -struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +/** + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn + * @pfn: page frame number to lookup page_map + * @pgmap: optional known pgmap that already has a reference + * + * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap + * is non-NULL but does not cover @pfn the reference to it will be released. + */ +struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) { - /* - * 'memmap_start' is the virtual address for the first "struct - * page" in this range of the vmemmap array. In the case of - * CONFIG_SPARSEMEM_VMEMMAP a page_to_pfn conversion is simple - * pointer arithmetic, so we can perform this to_vmem_altmap() - * conversion without concern for the initialization state of - * the struct page fields. - */ - struct page *page = (struct page *) memmap_start; - struct dev_pagemap *pgmap; + resource_size_t phys = PFN_PHYS(pfn); /* - * Unconditionally retrieve a dev_pagemap associated with the - * given physical address, this is only for use in the - * arch_{add|remove}_memory() for setting up and tearing down - * the memmap. + * In the cached case we're already holding a live reference. */ + if (pgmap) { + if (phys >= pgmap->res.start && phys <= pgmap->res.end) + return pgmap; + put_dev_pagemap(pgmap); + } + + /* fall back to slow path lookup */ rcu_read_lock(); - pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page))); + pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys)); + if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + pgmap = NULL; rcu_read_unlock(); - return pgmap ? pgmap->altmap : NULL; + return pgmap; } #endif /* CONFIG_ZONE_DEVICE */ - #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) void put_zone_device_private_or_public_page(struct page *page) { diff --git a/kernel/module.c b/kernel/module.c index ccdf24c4949e..ad2d420024f6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3804,6 +3804,7 @@ static int load_module(struct load_info *info, const char __user *uargs, module_disable_nx(mod); ddebug_cleanup: + ftrace_release_mod(mod); dynamic_debug_remove(mod, info->debug); synchronize_sched(); kfree(mod->args); @@ -3823,12 +3824,6 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_sched(); mutex_unlock(&module_mutex); free_module: - /* - * Ftrace needs to clean up what it initialized. - * This does nothing if ftrace_module_init() wasn't called, - * but it must be called outside of module_mutex. - */ - ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); diff --git a/kernel/pid.c b/kernel/pid.c index 5d30c87e3c42..ed6c343fe50d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -343,6 +343,19 @@ struct task_struct *find_task_by_vpid(pid_t vnr) return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } +struct task_struct *find_get_task_by_vpid(pid_t nr) +{ + struct task_struct *task; + + rcu_read_lock(); + task = find_task_by_vpid(nr); + if (task) + get_task_struct(task); + rcu_read_unlock(); + + return task; +} + struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; diff --git a/kernel/power/power.h b/kernel/power/power.h index f29cd178df90..9e58bdc8a562 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -104,9 +104,6 @@ extern int in_suspend; extern dev_t swsusp_resume_device; extern sector_t swsusp_resume_block; -extern asmlinkage int swsusp_arch_suspend(void); -extern asmlinkage int swsusp_arch_resume(void); - extern int create_basic_memory_bitmaps(void); extern void free_basic_memory_bitmaps(void); extern int hibernate_preallocate_memory(void); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4d818642ac0e..f274fbef821d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -930,7 +930,7 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) __poll_t ret = 0; if (!user) - return POLLERR|POLLNVAL; + return EPOLLERR|EPOLLNVAL; poll_wait(file, &log_wait, wait); @@ -938,9 +938,9 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) if (user->seq < log_next_seq) { /* return error when data has vanished underneath us */ if (user->seq < log_first_seq) - ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI; + ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else - ret = POLLIN|POLLRDNORM; + ret = EPOLLIN|EPOLLRDNORM; } logbuf_unlock_irq(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 5e1d713c8e61..21fec73d45d4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1103,21 +1103,6 @@ int ptrace_request(struct task_struct *child, long request, return ret; } -static struct task_struct *ptrace_get_task_struct(pid_t pid) -{ - struct task_struct *child; - - rcu_read_lock(); - child = find_task_by_vpid(pid); - if (child) - get_task_struct(child); - rcu_read_unlock(); - - if (!child) - return ERR_PTR(-ESRCH); - return child; -} - #ifndef arch_ptrace_attach #define arch_ptrace_attach(child) do { } while (0) #endif @@ -1135,9 +1120,9 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out; } - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) { - ret = PTR_ERR(child); + child = find_get_task_by_vpid(pid); + if (!child) { + ret = -ESRCH; goto out; } @@ -1281,9 +1266,9 @@ COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, goto out; } - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) { - ret = PTR_ERR(child); + child = find_get_task_by_vpid(pid); + if (!child) { + ret = -ESRCH; goto out; } diff --git a/kernel/relay.c b/kernel/relay.c index 41280033a4c5..c955b10c973c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > UINT_MAX / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); @@ -611,7 +611,6 @@ free_bufs: kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); - kfree(chan); return NULL; } EXPORT_SYMBOL_GPL(relay_open); @@ -925,12 +924,12 @@ static __poll_t relay_file_poll(struct file *filp, poll_table *wait) struct rchan_buf *buf = filp->private_data; if (buf->finalized) - return POLLERR; + return EPOLLERR; if (filp->f_mode & FMODE_READ) { poll_wait(filp, &buf->read_wait, wait); if (!relay_buf_empty(buf)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } return mask; diff --git a/kernel/resource.c b/kernel/resource.c index 54ba6de3757c..e270b5048988 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1022,6 +1022,7 @@ static void __init __reserve_region_with_split(struct resource *root, struct resource *conflict; struct resource *res = alloc_resource(GFP_ATOMIC); struct resource *next_res = NULL; + int type = resource_type(root); if (!res) return; @@ -1029,7 +1030,7 @@ static void __init __reserve_region_with_split(struct resource *root, res->name = name; res->start = start; res->end = end; - res->flags = IORESOURCE_BUSY; + res->flags = type | IORESOURCE_BUSY; res->desc = IORES_DESC_NONE; while (1) { @@ -1064,7 +1065,7 @@ static void __init __reserve_region_with_split(struct resource *root, next_res->name = name; next_res->start = conflict->end + 1; next_res->end = end; - next_res->flags = IORESOURCE_BUSY; + next_res->flags = type | IORESOURCE_BUSY; next_res->desc = IORES_DESC_NONE; } } else { @@ -1478,7 +1479,7 @@ void __devm_release_region(struct device *dev, struct resource *parent, EXPORT_SYMBOL(__devm_release_region); /* - * Called from init/main.c to reserve IO ports. + * Reserve I/O ports or memory based on "reserve=" kernel parameter. */ #define MAXRESERVE 4 static int __init reserve_setup(char *str) @@ -1489,26 +1490,38 @@ static int __init reserve_setup(char *str) for (;;) { unsigned int io_start, io_num; int x = reserved; + struct resource *parent; - if (get_option (&str, &io_start) != 2) + if (get_option(&str, &io_start) != 2) break; - if (get_option (&str, &io_num) == 0) + if (get_option(&str, &io_num) == 0) break; if (x < MAXRESERVE) { struct resource *res = reserve + x; + + /* + * If the region starts below 0x10000, we assume it's + * I/O port space; otherwise assume it's memory. + */ + if (io_start < 0x10000) { + res->flags = IORESOURCE_IO; + parent = &ioport_resource; + } else { + res->flags = IORESOURCE_MEM; + parent = &iomem_resource; + } res->name = "reserved"; res->start = io_start; res->end = io_start + io_num - 1; - res->flags = IORESOURCE_BUSY; + res->flags |= IORESOURCE_BUSY; res->desc = IORES_DESC_NONE; res->child = NULL; - if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0) + if (request_resource(parent, res) == 0) reserved = x+1; } } return 1; } - __setup("reserve=", reserve_setup); /* @@ -1563,17 +1576,17 @@ static int strict_iomem_checks; /* * check if an address is reserved in the iomem resource tree - * returns 1 if reserved, 0 if not reserved. + * returns true if reserved, false if not reserved. */ -int iomem_is_exclusive(u64 addr) +bool iomem_is_exclusive(u64 addr) { struct resource *p = &iomem_resource; - int err = 0; + bool err = false; loff_t l; int size = PAGE_SIZE; if (!strict_iomem_checks) - return 0; + return false; addr = addr & PAGE_MASK; @@ -1596,7 +1609,7 @@ int iomem_is_exclusive(u64 addr) continue; if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM) || p->flags & IORESOURCE_EXCLUSIVE) { - err = 1; + err = true; break; } } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3da7a2444a91..e7c535eee0a6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1630,16 +1630,16 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) #ifdef CONFIG_SMP if (cpu == rq->cpu) { - schedstat_inc(rq->ttwu_local); - schedstat_inc(p->se.statistics.nr_wakeups_local); + __schedstat_inc(rq->ttwu_local); + __schedstat_inc(p->se.statistics.nr_wakeups_local); } else { struct sched_domain *sd; - schedstat_inc(p->se.statistics.nr_wakeups_remote); + __schedstat_inc(p->se.statistics.nr_wakeups_remote); rcu_read_lock(); for_each_domain(rq->cpu, sd) { if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd->ttwu_wake_remote); + __schedstat_inc(sd->ttwu_wake_remote); break; } } @@ -1647,14 +1647,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } if (wake_flags & WF_MIGRATED) - schedstat_inc(p->se.statistics.nr_wakeups_migrate); + __schedstat_inc(p->se.statistics.nr_wakeups_migrate); #endif /* CONFIG_SMP */ - schedstat_inc(rq->ttwu_count); - schedstat_inc(p->se.statistics.nr_wakeups); + __schedstat_inc(rq->ttwu_count); + __schedstat_inc(p->se.statistics.nr_wakeups); if (wake_flags & WF_SYNC) - schedstat_inc(p->se.statistics.nr_wakeups_sync); + __schedstat_inc(p->se.statistics.nr_wakeups_sync); } static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) @@ -2461,6 +2461,7 @@ void wake_up_new_task(struct task_struct *p) * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, * as we're not fully set-up yet. */ + p->recent_used_cpu = task_cpu(p); __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); @@ -2600,19 +2601,31 @@ static inline void finish_task(struct task_struct *prev) #endif } -static inline void finish_lock_switch(struct rq *rq) +static inline void +prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf) { + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + rq_unpin_lock(rq, rf); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = current; + rq->lock.owner = next; #endif +} + +static inline void finish_lock_switch(struct rq *rq) +{ /* * If we are tracking spinlock dependencies then we have to * fix up the runqueue lock - which gets 'carried over' from * prev into current: */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - raw_spin_unlock_irq(&rq->lock); } @@ -2698,23 +2711,27 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state; vtime_task_switch(prev); perf_event_task_sched_in(prev, current); - /* - * The membarrier system call requires a full memory barrier - * after storing to rq->curr, before going back to user-space. - * - * TODO: This smp_mb__after_unlock_lock can go away if PPC end - * up adding a full barrier to switch_mm(), or we should figure - * out if a smp_mb__after_unlock_lock is really the proper API - * to use. - */ - smp_mb__after_unlock_lock(); finish_task(prev); finish_lock_switch(rq); finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); - if (mm) + /* + * When switching through a kernel thread, the loop in + * membarrier_{private,global}_expedited() may have observed that + * kernel thread and not issued an IPI. It is therefore possible to + * schedule between user->kernel->user threads without passing though + * switch_mm(). Membarrier requires a barrier after storing to + * rq->curr, before returning to userspace, so provide them here: + * + * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. + */ + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); + } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); @@ -2818,6 +2835,13 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); + /* + * If mm is non-NULL, we pass through switch_mm(). If mm is + * NULL, we will pass through mmdrop() in finish_task_switch(). + * Both of these contain the full memory barrier required by + * membarrier after storing to rq->curr, before returning to + * user-space. + */ if (!mm) { next->active_mm = oldmm; mmgrab(oldmm); @@ -2832,14 +2856,7 @@ context_switch(struct rq *rq, struct task_struct *prev, rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - /* - * Since the runqueue lock will be released by the next - * task (which is an invalid locking op but in the case - * of the scheduler it's an obvious special-case), so we - * do an early lockdep release here: - */ - rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + prepare_lock_switch(rq, next, rf); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); @@ -3354,6 +3371,9 @@ static void __sched notrace __schedule(bool preempt) * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). + * + * The membarrier system call requires a full memory barrier + * after coming from user-space, before storing to rq->curr. */ rq_lock(rq, &rf); smp_mb__after_spinlock(); @@ -3401,17 +3421,16 @@ static void __sched notrace __schedule(bool preempt) /* * The membarrier system call requires each architecture * to have a full memory barrier after updating - * rq->curr, before returning to user-space. For TSO - * (e.g. x86), the architecture must provide its own - * barrier in switch_mm(). For weakly ordered machines - * for which spin_unlock() acts as a full memory - * barrier, finish_lock_switch() in common code takes - * care of this barrier. For weakly ordered machines for - * which spin_unlock() acts as a RELEASE barrier (only - * arm64 and PowerPC), arm64 has a full barrier in - * switch_to(), and PowerPC has - * smp_mb__after_unlock_lock() before - * finish_lock_switch(). + * rq->curr, before returning to user-space. + * + * Here are the schemes providing that barrier on the + * various architectures: + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. + * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - finish_lock_switch() for weakly-ordered + * architectures where spin_unlock is a full barrier, + * - switch_to() for arm64 (weakly-ordered, spin_unlock + * is a RELEASE barrier), */ ++*switch_count; @@ -4853,7 +4872,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - size_t retlen = min_t(size_t, len, cpumask_size()); + unsigned int retlen = min(len, cpumask_size()); if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index dd062a1c8cf0..7936f548e071 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -19,8 +19,6 @@ #include "sched.h" -#define SUGOV_KTHREAD_PRIORITY 50 - struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 9bb0e0c412ec..9df09782025c 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1153,6 +1153,7 @@ static void update_curr_dl(struct rq *rq) struct sched_dl_entity *dl_se = &curr->dl; u64 delta_exec, scaled_delta_exec; int cpu = cpu_of(rq); + u64 now; if (!dl_task(curr) || !on_dl_rq(dl_se)) return; @@ -1165,7 +1166,8 @@ static void update_curr_dl(struct rq *rq) * natural solution, but the full ramifications of this * approach need further study. */ - delta_exec = rq_clock_task(rq) - curr->se.exec_start; + now = rq_clock_task(rq); + delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) { if (unlikely(dl_se->dl_yielded)) goto throttle; @@ -1178,7 +1180,7 @@ static void update_curr_dl(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq_clock_task(rq); + curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7b6535987500..5eb3ffc9be84 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -871,7 +871,7 @@ update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) likely(wait_start > prev_wait_start)) wait_start -= prev_wait_start; - schedstat_set(se->statistics.wait_start, wait_start); + __schedstat_set(se->statistics.wait_start, wait_start); } static inline void @@ -893,17 +893,17 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) * time stamp can be adjusted to accumulate wait time * prior to migration. */ - schedstat_set(se->statistics.wait_start, delta); + __schedstat_set(se->statistics.wait_start, delta); return; } trace_sched_stat_wait(p, delta); } - schedstat_set(se->statistics.wait_max, + __schedstat_set(se->statistics.wait_max, max(schedstat_val(se->statistics.wait_max), delta)); - schedstat_inc(se->statistics.wait_count); - schedstat_add(se->statistics.wait_sum, delta); - schedstat_set(se->statistics.wait_start, 0); + __schedstat_inc(se->statistics.wait_count); + __schedstat_add(se->statistics.wait_sum, delta); + __schedstat_set(se->statistics.wait_start, 0); } static inline void @@ -928,10 +928,10 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) delta = 0; if (unlikely(delta > schedstat_val(se->statistics.sleep_max))) - schedstat_set(se->statistics.sleep_max, delta); + __schedstat_set(se->statistics.sleep_max, delta); - schedstat_set(se->statistics.sleep_start, 0); - schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(se->statistics.sleep_start, 0); + __schedstat_add(se->statistics.sum_sleep_runtime, delta); if (tsk) { account_scheduler_latency(tsk, delta >> 10, 1); @@ -945,15 +945,15 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) delta = 0; if (unlikely(delta > schedstat_val(se->statistics.block_max))) - schedstat_set(se->statistics.block_max, delta); + __schedstat_set(se->statistics.block_max, delta); - schedstat_set(se->statistics.block_start, 0); - schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(se->statistics.block_start, 0); + __schedstat_add(se->statistics.sum_sleep_runtime, delta); if (tsk) { if (tsk->in_iowait) { - schedstat_add(se->statistics.iowait_sum, delta); - schedstat_inc(se->statistics.iowait_count); + __schedstat_add(se->statistics.iowait_sum, delta); + __schedstat_inc(se->statistics.iowait_count); trace_sched_stat_iowait(tsk, delta); } @@ -1012,10 +1012,10 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) struct task_struct *tsk = task_of(se); if (tsk->state & TASK_INTERRUPTIBLE) - schedstat_set(se->statistics.sleep_start, + __schedstat_set(se->statistics.sleep_start, rq_clock(rq_of(cfs_rq))); if (tsk->state & TASK_UNINTERRUPTIBLE) - schedstat_set(se->statistics.block_start, + __schedstat_set(se->statistics.block_start, rq_clock(rq_of(cfs_rq))); } } @@ -5692,27 +5692,31 @@ static int wake_wide(struct task_struct *p) * scheduling latency of the CPUs. This seems to work * for the overloaded case. */ - -static bool -wake_affine_idle(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +static int +wake_affine_idle(int this_cpu, int prev_cpu, int sync) { /* * If this_cpu is idle, it implies the wakeup is from interrupt * context. Only allow the move if cache is shared. Otherwise an * interrupt intensive workload could force all tasks onto one * node depending on the IO topology or IRQ affinity settings. + * + * If the prev_cpu is idle and cache affine then avoid a migration. + * There is no guarantee that the cache hot data from an interrupt + * is more important than cache hot data on the prev_cpu and from + * a cpufreq perspective, it's better to have higher utilisation + * on one CPU. */ if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) - return true; + return idle_cpu(prev_cpu) ? prev_cpu : this_cpu; if (sync && cpu_rq(this_cpu)->nr_running == 1) - return true; + return this_cpu; - return false; + return nr_cpumask_bits; } -static bool +static int wake_affine_weight(struct sched_domain *sd, struct task_struct *p, int this_cpu, int prev_cpu, int sync) { @@ -5726,7 +5730,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, unsigned long current_load = task_h_load(current); if (current_load > this_eff_load) - return true; + return this_cpu; this_eff_load -= current_load; } @@ -5743,28 +5747,28 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; prev_eff_load *= capacity_of(this_cpu); - return this_eff_load <= prev_eff_load; + return this_eff_load <= prev_eff_load ? this_cpu : nr_cpumask_bits; } static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine = false; + int target = nr_cpumask_bits; - if (sched_feat(WA_IDLE) && !affine) - affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_IDLE)) + target = wake_affine_idle(this_cpu, prev_cpu, sync); - if (sched_feat(WA_WEIGHT) && !affine) - affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits) + target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); - if (affine) { - schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); - } + if (target == nr_cpumask_bits) + return prev_cpu; - return affine; + schedstat_inc(sd->ttwu_move_affine); + schedstat_inc(p->se.statistics.nr_wakeups_affine); + return target; } static inline unsigned long task_util(struct task_struct *p); @@ -6193,7 +6197,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; - int i; + int i, recent_used_cpu; if (idle_cpu(target)) return target; @@ -6204,6 +6208,21 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev)) return prev; + /* Check a recently used CPU as a potential idle candidate */ + recent_used_cpu = p->recent_used_cpu; + if (recent_used_cpu != prev && + recent_used_cpu != target && + cpus_share_cache(recent_used_cpu, target) && + idle_cpu(recent_used_cpu) && + cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { + /* + * Replace recent_used_cpu with prev as it is a potential + * candidate for the next wake. + */ + p->recent_used_cpu = prev; + return recent_used_cpu; + } + sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; @@ -6357,8 +6376,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (cpu == prev_cpu) goto pick_cpu; - if (wake_affine(affine_sd, p, prev_cpu, sync)) - new_cpu = cpu; + new_cpu = wake_affine(affine_sd, p, prev_cpu, sync); } if (sd && !(sd_flag & SD_BALANCE_FORK)) { @@ -6372,9 +6390,12 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (!sd) { pick_cpu: - if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ + if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); + if (want_affine) + current->recent_used_cpu = cpu; + } } else { new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 9bcbacba82a8..5d0762633639 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -26,24 +26,110 @@ * Bitmask made from a "or" of all commands within enum membarrier_cmd, * except MEMBARRIER_CMD_QUERY. */ +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + (MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE) +#else +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0 +#endif + #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ + | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static int membarrier_private_expedited(void) +static int membarrier_global_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; - if (!(atomic_read(¤t->mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) - return -EPERM; + if (num_online_cpus() == 1) + return 0; + + /* + * Matches memory barriers around rq->curr modification in + * scheduler. + */ + smp_mb(); /* system call entry is not a mb. */ + + /* + * Expedited membarrier commands guarantee that they won't + * block, hence the GFP_NOWAIT allocation flag and fallback + * implementation. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) { + /* Fallback for OOM. */ + fallback = true; + } + + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct task_struct *p; + + /* + * Skipping the current CPU is OK even through we can be + * migrated at any point. The current CPU, at the point + * where we read raw_smp_processor_id(), is ensured to + * be in program order with respect to the caller + * thread. Therefore, we can skip this CPU from the + * iteration. + */ + if (cpu == raw_smp_processor_id()) + continue; + rcu_read_lock(); + p = task_rcu_dereference(&cpu_rq(cpu)->curr); + if (p && p->mm && (atomic_read(&p->mm->membarrier_state) & + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) { + if (!fallback) + __cpumask_set_cpu(cpu, tmpmask); + else + smp_call_function_single(cpu, ipi_mb, NULL, 1); + } + rcu_read_unlock(); + } + if (!fallback) { + preempt_disable(); + smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + preempt_enable(); + free_cpumask_var(tmpmask); + } + cpus_read_unlock(); + + /* + * Memory barrier on the caller thread _after_ we finished + * waiting for the last IPI. Matches memory barriers around + * rq->curr modification in scheduler. + */ + smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static int membarrier_private_expedited(int flags) +{ + int cpu; + bool fallback = false; + cpumask_var_t tmpmask; + + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) + return -EPERM; + } else { + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + } if (num_online_cpus() == 1) return 0; @@ -105,21 +191,69 @@ static int membarrier_private_expedited(void) return 0; } -static void membarrier_register_private_expedited(void) +static int membarrier_register_global_expedited(void) { struct task_struct *p = current; struct mm_struct *mm = p->mm; + if (atomic_read(&mm->membarrier_state) & + MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY) + return 0; + atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED, &mm->membarrier_state); + if (atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1) { + /* + * For single mm user, single threaded process, we can + * simply issue a memory barrier after setting + * MEMBARRIER_STATE_GLOBAL_EXPEDITED to guarantee that + * no memory access following registration is reordered + * before registration. + */ + smp_mb(); + } else { + /* + * For multi-mm user threads, we need to ensure all + * future scheduler executions will observe the new + * thread flag state for this mm. + */ + synchronize_sched(); + } + atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY, + &mm->membarrier_state); + return 0; +} + +static int membarrier_register_private_expedited(int flags) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + int state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY; + + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY; + } + /* * We need to consider threads belonging to different thread * groups, which use the same mm. (CLONE_VM but not * CLONE_THREAD). */ - if (atomic_read(&mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) - return; - atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, - &mm->membarrier_state); + if (atomic_read(&mm->membarrier_state) & state) + return 0; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED, &mm->membarrier_state); + if (flags & MEMBARRIER_FLAG_SYNC_CORE) + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE, + &mm->membarrier_state); + if (!(atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1)) { + /* + * Ensure all future scheduler executions will observe the + * new thread flag state for this process. + */ + synchronize_sched(); + } + atomic_or(state, &mm->membarrier_state); + return 0; } /** @@ -159,21 +293,28 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) int cmd_mask = MEMBARRIER_CMD_BITMASK; if (tick_nohz_full_enabled()) - cmd_mask &= ~MEMBARRIER_CMD_SHARED; + cmd_mask &= ~MEMBARRIER_CMD_GLOBAL; return cmd_mask; } - case MEMBARRIER_CMD_SHARED: - /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + case MEMBARRIER_CMD_GLOBAL: + /* MEMBARRIER_CMD_GLOBAL is not compatible with nohz_full. */ if (tick_nohz_full_enabled()) return -EINVAL; if (num_online_cpus() > 1) synchronize_sched(); return 0; + case MEMBARRIER_CMD_GLOBAL_EXPEDITED: + return membarrier_global_expedited(); + case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED: + return membarrier_register_global_expedited(); case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - return membarrier_private_expedited(); + return membarrier_private_expedited(0); case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: - membarrier_register_private_expedited(); - return 0; + return membarrier_register_private_expedited(0); + case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); default: return -EINVAL; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 862a513adca3..aad49451584e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -951,11 +951,13 @@ static void update_curr_rt(struct rq *rq) struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; u64 delta_exec; + u64 now; if (curr->sched_class != &rt_sched_class) return; - delta_exec = rq_clock_task(rq) - curr->se.exec_start; + now = rq_clock_task(rq); + delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; @@ -968,7 +970,7 @@ static void update_curr_rt(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq_clock_task(rq); + curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); @@ -1907,9 +1909,8 @@ static void push_rt_tasks(struct rq *rq) * the rt_loop_next will cause the iterator to perform another scan. * */ -static int rto_next_cpu(struct rq *rq) +static int rto_next_cpu(struct root_domain *rd) { - struct root_domain *rd = rq->rd; int next; int cpu; @@ -1985,19 +1986,24 @@ static void tell_cpu_to_push(struct rq *rq) * Otherwise it is finishing up and an ipi needs to be sent. */ if (rq->rd->rto_cpu < 0) - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rq->rd); raw_spin_unlock(&rq->rd->rto_lock); rto_start_unlock(&rq->rd->rto_loop_start); - if (cpu >= 0) + if (cpu >= 0) { + /* Make sure the rd does not get freed while pushing */ + sched_get_rd(rq->rd); irq_work_queue_on(&rq->rd->rto_push_work, cpu); + } } /* Called from hardirq context */ void rto_push_irq_work_func(struct irq_work *work) { + struct root_domain *rd = + container_of(work, struct root_domain, rto_push_work); struct rq *rq; int cpu; @@ -2013,18 +2019,20 @@ void rto_push_irq_work_func(struct irq_work *work) raw_spin_unlock(&rq->lock); } - raw_spin_lock(&rq->rd->rto_lock); + raw_spin_lock(&rd->rto_lock); /* Pass the IPI to the next rt overloaded queue */ - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rd); - raw_spin_unlock(&rq->rd->rto_lock); + raw_spin_unlock(&rd->rto_lock); - if (cpu < 0) + if (cpu < 0) { + sched_put_rd(rd); return; + } /* Try the next RT overloaded CPU */ - irq_work_queue_on(&rq->rd->rto_push_work, cpu); + irq_work_queue_on(&rd->rto_push_work, cpu); } #endif /* HAVE_RT_PUSH_IPI */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2e95505e23c6..fb5fc458547f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -691,6 +691,8 @@ extern struct mutex sched_domains_mutex; extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); +extern void sched_get_rd(struct root_domain *rd); +extern void sched_put_rd(struct root_domain *rd); #ifdef HAVE_RT_PUSH_IPI extern void rto_push_irq_work_func(struct irq_work *work); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baf500d12b7c..8e7b58de61e7 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -31,8 +31,11 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) rq->rq_sched_info.run_delay += delta; } #define schedstat_enabled() static_branch_unlikely(&sched_schedstats) +#define __schedstat_inc(var) do { var++; } while (0) #define schedstat_inc(var) do { if (schedstat_enabled()) { var++; } } while (0) +#define __schedstat_add(var, amt) do { var += (amt); } while (0) #define schedstat_add(var, amt) do { if (schedstat_enabled()) { var += (amt); } } while (0) +#define __schedstat_set(var, val) do { var = (val); } while (0) #define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) #define schedstat_val(var) (var) #define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0) @@ -48,8 +51,11 @@ static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} #define schedstat_enabled() 0 +#define __schedstat_inc(var) do { } while (0) #define schedstat_inc(var) do { } while (0) +#define __schedstat_add(var, amt) do { } while (0) #define schedstat_add(var, amt) do { } while (0) +#define __schedstat_set(var, val) do { } while (0) #define schedstat_set(var, val) do { } while (0) #define schedstat_val(var) 0 #define schedstat_val_or_zero(var) 0 diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 034cbed7f88b..519b024f4e94 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -259,6 +259,19 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd) call_rcu_sched(&old_rd->rcu, free_rootdomain); } +void sched_get_rd(struct root_domain *rd) +{ + atomic_inc(&rd->refcount); +} + +void sched_put_rd(struct root_domain *rd) +{ + if (!atomic_dec_and_test(&rd->refcount)) + return; + + call_rcu_sched(&rd->rcu, free_rootdomain); +} + static int init_rootdomain(struct root_domain *rd) { if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 940fa408a288..dc77548167ef 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1076,14 +1076,16 @@ long seccomp_get_metadata(struct task_struct *task, size = min_t(unsigned long, size, sizeof(kmd)); - if (copy_from_user(&kmd, data, size)) + if (size < sizeof(kmd.filter_off)) + return -EINVAL; + + if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off))) return -EFAULT; filter = get_nth_filter(task, kmd.filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); - memset(&kmd, 0, sizeof(kmd)); if (filter->log) kmd.flags |= SECCOMP_FILTER_FLAG_LOG; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2fb4e27c636a..f98f28c12020 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -218,6 +218,8 @@ static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, static int proc_dostring_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ @@ -1812,8 +1814,7 @@ static struct ctl_table fs_table[] = { .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, - .proc_handler = &pipe_proc_fn, - .extra1 = &pipe_min_size, + .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", @@ -2615,29 +2616,17 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, do_proc_douintvec_minmax_conv, ¶m); } -struct do_proc_dopipe_max_size_conv_param { - unsigned int *min; -}; - static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { - struct do_proc_dopipe_max_size_conv_param *param = data; - if (write) { unsigned int val; - if (*lvalp > UINT_MAX) - return -EINVAL; - val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; - if (param->min && *param->min > val) - return -ERANGE; - *valp = val; } else { unsigned int val = *valp; @@ -2647,14 +2636,11 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, return 0; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - struct do_proc_dopipe_max_size_conv_param param = { - .min = (unsigned int *) table->extra1, - }; return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, ¶m); + do_proc_dopipe_max_size_conv, NULL); } static void validate_coredump_safety(void) @@ -3160,12 +3146,6 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3209,7 +3189,6 @@ EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL_GPL(proc_douintvec_minmax); -EXPORT_SYMBOL_GPL(proc_dopipe_max_size); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4559e914452b..4e62a4a8fa91 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -194,11 +194,7 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) { struct task_struct *tsk; - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk) - get_task_struct(tsk); - rcu_read_unlock(); + tsk = find_get_task_by_vpid(pid); if (!tsk) return -ESRCH; fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ae0c8a411fe7..23788100e214 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -37,7 +37,6 @@ #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> -#include <linux/kallsyms.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/seq_file.h> diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 94ad46d50b56..fe56c4e06c51 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -74,7 +74,7 @@ static __poll_t posix_clock_poll(struct file *fp, poll_table *wait) __poll_t result = 0; if (!clk) - return POLLERR; + return EPOLLERR; if (clk->ops.poll) result = clk->ops.poll(clk, fp, wait); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fc2838ac8b78..c0a9e310d715 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -872,6 +872,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; + if (query.ids_len > BPF_TRACE_MAX_PROGS) + return -E2BIG; mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dabd9d167d42..eac9ce2c57a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4456,7 +4456,6 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, func_g.type = filter_parse_regex(glob, strlen(glob), &func_g.search, ¬); func_g.len = strlen(func_g.search); - func_g.search = glob; /* we do not support '!' for function probes */ if (WARN_ON(not)) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ca6930e0d25e..dcf1c4dd3efe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -627,7 +627,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. * - * Returns POLLIN | POLLRDNORM if data exists in the buffers, + * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers, * zero otherwise. */ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, @@ -665,7 +665,7 @@ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 56608538a4ad..20a2300ae4e8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5623,13 +5623,13 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (tr->trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, filp, poll_table); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 61e7f0678d33..a764aec3c9a1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -400,7 +400,6 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) for (i = 0; i < len; i++) { if (buff[i] == '*') { if (!i) { - *search = buff + 1; type = MATCH_END_ONLY; } else if (i == len - 1) { if (type == MATCH_END_ONLY) @@ -410,14 +409,14 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) buff[i] = 0; break; } else { /* pattern continues, use full glob */ - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } else if (strchr("[?\\", buff[i])) { - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } + if (buff[0] == '*') + *search = buff + 1; return type; } diff --git a/kernel/user.c b/kernel/user.c index 9a20acce460d..36288d840675 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -101,6 +101,7 @@ struct user_struct root_user = { .sigpending = ATOMIC_INIT(0), .locked_shm = 0, .uid = GLOBAL_ROOT_UID, + .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* @@ -191,6 +192,8 @@ struct user_struct *alloc_uid(kuid_t uid) new->uid = uid; atomic_set(&new->__count, 1); + ratelimit_state_init(&new->ratelimit, HZ, 100); + ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 017044c26233..bb9a519cbf50 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4180,6 +4180,22 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** + * current_work - retrieve %current task's work struct + * + * Determine if %current task is a workqueue worker and what it's working on. + * Useful to find out the context that the %current task is running in. + * + * Return: work struct if %current task is a workqueue worker, %NULL otherwise. + */ +struct work_struct *current_work(void) +{ + struct worker *worker = current_wq_worker(); + + return worker ? worker->current_work : NULL; +} +EXPORT_SYMBOL(current_work); + +/** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from |