summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorAndrew Morton <akpm@linux-foundation.org>2023-06-30 08:37:44 -0700
committerAndrew Morton <akpm@linux-foundation.org>2023-06-30 08:37:44 -0700
commit0a30901b0732a59e038088d3de3e5611db1870d3 (patch)
tree1d194c6c9fa651e866cc8f6a508535eb482bb15c /kernel
parent814bc1de03ea4361101408e63a68e4b82aef22cb (diff)
parent6995e2de6891c724bfeb2db33d7b87775f913ad1 (diff)
Merge branch 'master' into mm-hotfixes-stable
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c20
-rw-r--r--kernel/bpf/map_in_map.c8
-rw-r--r--kernel/bpf/syscall.c14
-rw-r--r--kernel/bpf/verifier.c10
-rw-r--r--kernel/cgroup/cgroup-v1.c4
-rw-r--r--kernel/cgroup/cgroup.c37
-rw-r--r--kernel/cgroup/legacy_freezer.c8
-rw-r--r--kernel/exit.c5
-rw-r--r--kernel/fork.c15
-rw-r--r--kernel/module/decompress.c2
-rw-r--r--kernel/module/main.c4
-rw-r--r--kernel/signal.c8
-rw-r--r--kernel/time/tick-common.c13
-rw-r--r--kernel/time/tick-sched.c13
-rw-r--r--kernel/trace/bpf_trace.c12
-rw-r--r--kernel/trace/trace_events_user.c290
-rw-r--r--kernel/trace/trace_output.c2
-rw-r--r--kernel/trace/trace_probe.h2
-rw-r--r--kernel/vhost_task.c94
-rw-r--r--kernel/workqueue.c13
20 files changed, 391 insertions, 183 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 6b682b8e4b50..72b32b7cd9cd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -744,13 +744,12 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
return offset < btf->hdr.str_len;
}
-static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
+static bool __btf_name_char_ok(char c, bool first)
{
if ((first ? !isalpha(c) :
!isalnum(c)) &&
c != '_' &&
- ((c == '.' && !dot_ok) ||
- c != '.'))
+ c != '.')
return false;
return true;
}
@@ -767,20 +766,20 @@ static const char *btf_str_by_offset(const struct btf *btf, u32 offset)
return NULL;
}
-static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
+static bool __btf_name_valid(const struct btf *btf, u32 offset)
{
/* offset must be valid */
const char *src = btf_str_by_offset(btf, offset);
const char *src_limit;
- if (!__btf_name_char_ok(*src, true, dot_ok))
+ if (!__btf_name_char_ok(*src, true))
return false;
/* set a limit on identifier length */
src_limit = src + KSYM_NAME_LEN;
src++;
while (*src && src < src_limit) {
- if (!__btf_name_char_ok(*src, false, dot_ok))
+ if (!__btf_name_char_ok(*src, false))
return false;
src++;
}
@@ -788,17 +787,14 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
return !*src;
}
-/* Only C-style identifier is permitted. This can be relaxed if
- * necessary.
- */
static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
{
- return __btf_name_valid(btf, offset, false);
+ return __btf_name_valid(btf, offset);
}
static bool btf_name_valid_section(const struct btf *btf, u32 offset)
{
- return __btf_name_valid(btf, offset, true);
+ return __btf_name_valid(btf, offset);
}
static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
@@ -4422,7 +4418,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env,
}
if (!t->name_off ||
- !__btf_name_valid(env->btf, t->name_off, true)) {
+ !__btf_name_valid(env->btf, t->name_off)) {
btf_verifier_log_type(env, t, "Invalid name");
return -EINVAL;
}
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 2c5c64c2a53b..cd5eafaba97e 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -69,9 +69,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
if (inner_map->ops == &array_map_ops) {
+ struct bpf_array *inner_array_meta =
+ container_of(inner_map_meta, struct bpf_array, map);
+ struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map);
+
+ inner_array_meta->index_mask = inner_array->index_mask;
+ inner_array_meta->elem_size = inner_array->elem_size;
inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
- container_of(inner_map_meta, struct bpf_array, map)->index_mask =
- container_of(inner_map, struct bpf_array, map)->index_mask;
}
fdput(f);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 14f39c1e573e..f1c8733f76b8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2433,6 +2433,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
default:
return -EINVAL;
}
+ case BPF_PROG_TYPE_NETFILTER:
+ if (expected_attach_type == BPF_NETFILTER)
+ return 0;
+ return -EINVAL;
case BPF_PROG_TYPE_SYSCALL:
case BPF_PROG_TYPE_EXT:
if (expected_attach_type)
@@ -3436,6 +3440,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
return prog->enforce_expected_attach_type &&
prog->expected_attach_type != attach_type ?
-EINVAL : 0;
+ case BPF_PROG_TYPE_KPROBE:
+ if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+ attach_type != BPF_TRACE_KPROBE_MULTI)
+ return -EINVAL;
+ return 0;
default:
return 0;
}
@@ -4590,7 +4599,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
switch (prog->type) {
case BPF_PROG_TYPE_EXT:
+ break;
case BPF_PROG_TYPE_NETFILTER:
+ if (attr->link_create.attach_type != BPF_NETFILTER) {
+ ret = -EINVAL;
+ goto out;
+ }
break;
case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_TRACEPOINT:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5871aa78d01a..cf5f230360f5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3868,6 +3868,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
return err;
}
save_register_state(state, spi, reg, size);
+ /* Break the relation on a narrowing spill. */
+ if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
+ state->stack[spi].spilled_ptr.id = 0;
} else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) &&
insn->imm != 0 && env->bpf_capable) {
struct bpf_reg_state fake_reg = {};
@@ -17214,9 +17217,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
}
/* finally lock prog and jit images for all functions and
- * populate kallsysm
+ * populate kallsysm. Begin at the first subprogram, since
+ * bpf_prog_load will add the kallsyms for the main program.
*/
- for (i = 0; i < env->subprog_cnt; i++) {
+ for (i = 1; i < env->subprog_cnt; i++) {
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
@@ -17242,6 +17246,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->jited_len = func[0]->jited_len;
+ prog->aux->extable = func[0]->aux->extable;
+ prog->aux->num_exentries = func[0]->aux->num_exentries;
prog->aux->func = func;
prog->aux->func_cnt = env->subprog_cnt;
bpf_prog_jit_attempt_done(prog);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index aeef06c465ef..5407241dbb45 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -108,7 +108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
cgroup_lock();
- percpu_down_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_lock(true);
/* all tasks in @from are being moved, all csets are source */
spin_lock_irq(&css_set_lock);
@@ -144,7 +144,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
} while (task && !ret);
out_err:
cgroup_migrate_finish(&mgctx);
- percpu_up_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_unlock(true);
cgroup_unlock();
return ret;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..4d42f0cbc11e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1798,7 +1798,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
{
struct cgroup *dcgrp = &dst_root->cgrp;
struct cgroup_subsys *ss;
- int ssid, i, ret;
+ int ssid, ret;
u16 dfl_disable_ss_mask = 0;
lockdep_assert_held(&cgroup_mutex);
@@ -1842,7 +1842,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
struct cgroup_root *src_root = ss->root;
struct cgroup *scgrp = &src_root->cgrp;
struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
- struct css_set *cset;
+ struct css_set *cset, *cset_pos;
+ struct css_task_iter *it;
WARN_ON(!css || cgroup_css(dcgrp, ss));
@@ -1860,9 +1861,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
css->cgroup = dcgrp;
spin_lock_irq(&css_set_lock);
- hash_for_each(css_set_table, i, cset, hlist)
+ WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+ list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+ e_cset_node[ss->id]) {
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
+ /*
+ * all css_sets of scgrp together in same order to dcgrp,
+ * patch in-flight iterators to preserve correct iteration.
+ * since the iterator is always advanced right away and
+ * finished when it->cset_pos meets it->cset_head, so only
+ * update it->cset_head is enough here.
+ */
+ list_for_each_entry(it, &cset->task_iters, iters_node)
+ if (it->cset_head == &scgrp->e_csets[ss->id])
+ it->cset_head = &dcgrp->e_csets[ss->id];
+ }
spin_unlock_irq(&css_set_lock);
if (ss->css_rstat_flush) {
@@ -6486,19 +6500,18 @@ err:
static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
{
+ struct cgroup *cgrp = kargs->cgrp;
+ struct css_set *cset = kargs->cset;
+
cgroup_threadgroup_change_end(current);
- if (kargs->flags & CLONE_INTO_CGROUP) {
- struct cgroup *cgrp = kargs->cgrp;
- struct css_set *cset = kargs->cset;
+ if (cset) {
+ put_css_set(cset);
+ kargs->cset = NULL;
+ }
+ if (kargs->flags & CLONE_INTO_CGROUP) {
cgroup_unlock();
-
- if (cset) {
- put_css_set(cset);
- kargs->cset = NULL;
- }
-
if (cgrp) {
cgroup_put(cgrp);
kargs->cgrp = NULL;
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 936473203a6b..122dacb3a443 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -108,16 +108,18 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
struct freezer *freezer = css_freezer(css);
struct freezer *parent = parent_freezer(freezer);
+ cpus_read_lock();
mutex_lock(&freezer_mutex);
freezer->state |= CGROUP_FREEZER_ONLINE;
if (parent && (parent->state & CGROUP_FREEZING)) {
freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
- static_branch_inc(&freezer_active);
+ static_branch_inc_cpuslocked(&freezer_active);
}
mutex_unlock(&freezer_mutex);
+ cpus_read_unlock();
return 0;
}
@@ -132,14 +134,16 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
{
struct freezer *freezer = css_freezer(css);
+ cpus_read_lock();
mutex_lock(&freezer_mutex);
if (freezer->state & CGROUP_FREEZING)
- static_branch_dec(&freezer_active);
+ static_branch_dec_cpuslocked(&freezer_active);
freezer->state = 0;
mutex_unlock(&freezer_mutex);
+ cpus_read_unlock();
}
static void freezer_css_free(struct cgroup_subsys_state *css)
diff --git a/kernel/exit.c b/kernel/exit.c
index 34b90e2e7cf7..edb50b4c9972 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk)
tsk->flags |= PF_POSTCOREDUMP;
core_state = tsk->signal->core_state;
spin_unlock_irq(&tsk->sighand->siglock);
- if (core_state) {
+
+ /* The vhost_worker does not particpate in coredumps */
+ if (core_state &&
+ ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) {
struct core_thread self;
self.task = current;
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..41c964104b58 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -627,6 +627,7 @@ void free_task(struct task_struct *tsk)
arch_release_task_struct(tsk);
if (tsk->flags & PF_KTHREAD)
free_kthread_struct(tsk);
+ bpf_task_storage_free(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -979,7 +980,6 @@ void __put_task_struct(struct task_struct *tsk)
cgroup_free(tsk);
task_numa_free(tsk, true);
security_task_free(tsk);
- bpf_task_storage_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
@@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process(
p->flags &= ~PF_KTHREAD;
if (args->kthread)
p->flags |= PF_KTHREAD;
- if (args->user_worker)
- p->flags |= PF_USER_WORKER;
- if (args->io_thread) {
+ if (args->user_worker) {
/*
- * Mark us an IO worker, and block any signal that isn't
+ * Mark us a user worker, and block any signal that isn't
* fatal or STOP
*/
- p->flags |= PF_IO_WORKER;
+ p->flags |= PF_USER_WORKER;
siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
}
+ if (args->io_thread)
+ p->flags |= PF_IO_WORKER;
if (args->name)
strscpy_pad(p->comm, args->name, sizeof(p->comm));
@@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process(
if (retval)
goto bad_fork_cleanup_io;
- if (args->ignore_signals)
- ignore_signals(p);
-
stackleak_task_init(p);
if (pid != &init_struct_pid) {
diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c
index e97232b125eb..8a5d6d63b06c 100644
--- a/kernel/module/decompress.c
+++ b/kernel/module/decompress.c
@@ -257,7 +257,7 @@ static ssize_t module_zstd_decompress(struct load_info *info,
do {
struct page *page = module_get_next_page(info);
- if (!IS_ERR(page)) {
+ if (IS_ERR(page)) {
retval = PTR_ERR(page);
goto out;
}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 044aa2c9e3cb..4e2cf784cf8c 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
MOD_RODATA,
MOD_RO_AFTER_INIT,
MOD_DATA,
- MOD_INVALID, /* This is needed to match the masks array */
+ MOD_DATA,
};
static const int init_m_to_mem_type[] = {
MOD_INIT_TEXT,
MOD_INIT_RODATA,
MOD_INVALID,
MOD_INIT_DATA,
- MOD_INVALID, /* This is needed to match the masks array */
+ MOD_INIT_DATA,
};
for (m = 0; m < ARRAY_SIZE(masks); ++m) {
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f6330f0e9ca..2547fa73bde5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p)
while_each_thread(p, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
- count++;
+ /* Don't require de_thread to wait for the vhost_worker */
+ if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
+ count++;
/* Don't bother with already dead threads */
if (t->exit_state)
@@ -2861,11 +2863,11 @@ relock:
}
/*
- * PF_IO_WORKER threads will catch and exit on fatal signals
+ * PF_USER_WORKER threads will catch and exit on fatal signals
* themselves. They have cleanup that must be performed, so
* we cannot call do_exit() on their behalf.
*/
- if (current->flags & PF_IO_WORKER)
+ if (current->flags & PF_USER_WORKER)
goto out;
/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 65b8658da829..e9138cd7a0f5 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -218,19 +218,8 @@ static void tick_setup_device(struct tick_device *td,
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- ktime_t next_p;
- u32 rem;
-
tick_do_timer_cpu = cpu;
-
- next_p = ktime_get();
- div_u64_rem(next_p, TICK_NSEC, &rem);
- if (rem) {
- next_p -= rem;
- next_p += TICK_NSEC;
- }
-
- tick_next_period = next_p;
+ tick_next_period = ktime_get();
#ifdef CONFIG_NO_HZ_FULL
/*
* The boot CPU may be nohz_full, in which case set
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 52254679ec48..42c0be3080bd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -161,8 +161,19 @@ static ktime_t tick_init_jiffy_update(void)
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
/* Did we start the jiffies update yet ? */
- if (last_jiffies_update == 0)
+ if (last_jiffies_update == 0) {
+ u32 rem;
+
+ /*
+ * Ensure that the tick is aligned to a multiple of
+ * TICK_NSEC.
+ */
+ div_u64_rem(tick_next_period, TICK_NSEC, &rem);
+ if (rem)
+ tick_next_period += TICK_NSEC - rem;
+
last_jiffies_update = tick_next_period;
+ }
period = last_jiffies_update;
write_seqcount_end(&jiffies_seq);
raw_spin_unlock(&jiffies_lock);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9a050e36dc6c..1f4b07da327a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -900,13 +900,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
{
+ struct path copy;
long len;
char *p;
if (!sz)
return 0;
- p = d_path(path, buf, sz);
+ /*
+ * The path pointer is verified as trusted and safe to use,
+ * but let's double check it's valid anyway to workaround
+ * potentially broken verifier.
+ */
+ len = copy_from_kernel_nofault(&copy, path, sizeof(*path));
+ if (len < 0)
+ return len;
+
+ p = d_path(&copy, buf, sz);
if (IS_ERR(p)) {
len = PTR_ERR(p);
} else {
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index dbb14705d0d3..8df0550415e7 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -50,6 +50,18 @@
#define EVENT_STATUS_OTHER BIT(7)
/*
+ * User register flags are not allowed yet, keep them here until we are
+ * ready to expose them out to the user ABI.
+ */
+enum user_reg_flag {
+ /* Event will not delete upon last reference closing */
+ USER_EVENT_REG_PERSIST = 1U << 0,
+
+ /* This value or above is currently non-ABI */
+ USER_EVENT_REG_MAX = 1U << 1,
+};
+
+/*
* Stores the system name, tables, and locks for a group of events. This
* allows isolation for events by various means.
*/
@@ -85,8 +97,10 @@ struct user_event {
struct hlist_node node;
struct list_head fields;
struct list_head validators;
+ struct work_struct put_work;
refcount_t refcnt;
int min_size;
+ int reg_flags;
char status;
};
@@ -165,76 +179,151 @@ typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
static int user_event_parse(struct user_event_group *group, char *name,
char *args, char *flags,
- struct user_event **newuser);
+ struct user_event **newuser, int reg_flags);
static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
static void user_event_mm_put(struct user_event_mm *mm);
+static int destroy_user_event(struct user_event *user);
static u32 user_event_key(char *name)
{
return jhash(name, strlen(name), 0);
}
-static void user_event_group_destroy(struct user_event_group *group)
+static struct user_event *user_event_get(struct user_event *user)
{
- kfree(group->system_name);
- kfree(group);
+ refcount_inc(&user->refcnt);
+
+ return user;
}
-static char *user_event_group_system_name(struct user_namespace *user_ns)
+static void delayed_destroy_user_event(struct work_struct *work)
{
- char *system_name;
- int len = sizeof(USER_EVENTS_SYSTEM) + 1;
+ struct user_event *user = container_of(
+ work, struct user_event, put_work);
- if (user_ns != &init_user_ns) {
+ mutex_lock(&event_mutex);
+
+ if (!refcount_dec_and_test(&user->refcnt))
+ goto out;
+
+ if (destroy_user_event(user)) {
/*
- * Unexpected at this point:
- * We only currently support init_user_ns.
- * When we enable more, this will trigger a failure so log.
+ * The only reason this would fail here is if we cannot
+ * update the visibility of the event. In this case the
+ * event stays in the hashtable, waiting for someone to
+ * attempt to delete it later.
*/
- pr_warn("user_events: Namespace other than init_user_ns!\n");
- return NULL;
+ pr_warn("user_events: Unable to delete event\n");
+ refcount_set(&user->refcnt, 1);
}
+out:
+ mutex_unlock(&event_mutex);
+}
- system_name = kmalloc(len, GFP_KERNEL);
+static void user_event_put(struct user_event *user, bool locked)
+{
+ bool delete;
- if (!system_name)
- return NULL;
+ if (unlikely(!user))
+ return;
- snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM);
+ /*
+ * When the event is not enabled for auto-delete there will always
+ * be at least 1 reference to the event. During the event creation
+ * we initially set the refcnt to 2 to achieve this. In those cases
+ * the caller must acquire event_mutex and after decrement check if
+ * the refcnt is 1, meaning this is the last reference. When auto
+ * delete is enabled, there will only be 1 ref, IE: refcnt will be
+ * only set to 1 during creation to allow the below checks to go
+ * through upon the last put. The last put must always be done with
+ * the event mutex held.
+ */
+ if (!locked) {
+ lockdep_assert_not_held(&event_mutex);
+ delete = refcount_dec_and_mutex_lock(&user->refcnt, &event_mutex);
+ } else {
+ lockdep_assert_held(&event_mutex);
+ delete = refcount_dec_and_test(&user->refcnt);
+ }
- return system_name;
+ if (!delete)
+ return;
+
+ /*
+ * We now have the event_mutex in all cases, which ensures that
+ * no new references will be taken until event_mutex is released.
+ * New references come through find_user_event(), which requires
+ * the event_mutex to be held.
+ */
+
+ if (user->reg_flags & USER_EVENT_REG_PERSIST) {
+ /* We should not get here when persist flag is set */
+ pr_alert("BUG: Auto-delete engaged on persistent event\n");
+ goto out;
+ }
+
+ /*
+ * Unfortunately we have to attempt the actual destroy in a work
+ * queue. This is because not all cases handle a trace_event_call
+ * being removed within the class->reg() operation for unregister.
+ */
+ INIT_WORK(&user->put_work, delayed_destroy_user_event);
+
+ /*
+ * Since the event is still in the hashtable, we have to re-inc
+ * the ref count to 1. This count will be decremented and checked
+ * in the work queue to ensure it's still the last ref. This is
+ * needed because a user-process could register the same event in
+ * between the time of event_mutex release and the work queue
+ * running the delayed destroy. If we removed the item now from
+ * the hashtable, this would result in a timing window where a
+ * user process would fail a register because the trace_event_call
+ * register would fail in the tracing layers.
+ */
+ refcount_set(&user->refcnt, 1);
+
+ if (WARN_ON_ONCE(!schedule_work(&user->put_work))) {
+ /*
+ * If we fail we must wait for an admin to attempt delete or
+ * another register/close of the event, whichever is first.
+ */
+ pr_warn("user_events: Unable to queue delayed destroy\n");
+ }
+out:
+ /* Ensure if we didn't have event_mutex before we unlock it */
+ if (!locked)
+ mutex_unlock(&event_mutex);
}
-static inline struct user_event_group
-*user_event_group_from_user_ns(struct user_namespace *user_ns)
+static void user_event_group_destroy(struct user_event_group *group)
{
- if (user_ns == &init_user_ns)
- return init_group;
-
- return NULL;
+ kfree(group->system_name);
+ kfree(group);
}
-static struct user_event_group *current_user_event_group(void)
+static char *user_event_group_system_name(void)
{
- struct user_namespace *user_ns = current_user_ns();
- struct user_event_group *group = NULL;
+ char *system_name;
+ int len = sizeof(USER_EVENTS_SYSTEM) + 1;
- while (user_ns) {
- group = user_event_group_from_user_ns(user_ns);
+ system_name = kmalloc(len, GFP_KERNEL);
- if (group)
- break;
+ if (!system_name)
+ return NULL;
- user_ns = user_ns->parent;
- }
+ snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM);
- return group;
+ return system_name;
}
-static struct user_event_group
-*user_event_group_create(struct user_namespace *user_ns)
+static struct user_event_group *current_user_event_group(void)
+{
+ return init_group;
+}
+
+static struct user_event_group *user_event_group_create(void)
{
struct user_event_group *group;
@@ -243,7 +332,7 @@ static struct user_event_group
if (!group)
return NULL;
- group->system_name = user_event_group_system_name(user_ns);
+ group->system_name = user_event_group_system_name();
if (!group->system_name)
goto error;
@@ -259,12 +348,13 @@ error:
return NULL;
};
-static void user_event_enabler_destroy(struct user_event_enabler *enabler)
+static void user_event_enabler_destroy(struct user_event_enabler *enabler,
+ bool locked)
{
list_del_rcu(&enabler->mm_enablers_link);
/* No longer tracking the event via the enabler */
- refcount_dec(&enabler->event->refcnt);
+ user_event_put(enabler->event, locked);
kfree(enabler);
}
@@ -326,7 +416,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work)
/* User asked for enabler to be removed during fault */
if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) {
- user_event_enabler_destroy(enabler);
+ user_event_enabler_destroy(enabler, true);
goto out;
}
@@ -501,14 +591,12 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig,
if (!enabler)
return false;
- enabler->event = orig->event;
+ enabler->event = user_event_get(orig->event);
enabler->addr = orig->addr;
/* Only dup part of value (ignore future flags, etc) */
enabler->values = orig->values & ENABLE_VAL_DUP_MASK;
- refcount_inc(&enabler->event->refcnt);
-
/* Enablers not exposed yet, RCU not required */
list_add(&enabler->mm_enablers_link, &mm->enablers);
@@ -625,7 +713,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm)
struct user_event_enabler *enabler, *next;
list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link)
- user_event_enabler_destroy(enabler);
+ user_event_enabler_destroy(enabler, false);
mmdrop(mm->mm);
kfree(mm);
@@ -780,7 +868,7 @@ retry:
* exit or run exec(), which includes forks and clones.
*/
if (!*write_result) {
- refcount_inc(&enabler->event->refcnt);
+ user_event_get(user);
list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers);
}
@@ -803,7 +891,12 @@ out:
static __always_inline __must_check
bool user_event_last_ref(struct user_event *user)
{
- return refcount_read(&user->refcnt) == 1;
+ int last = 0;
+
+ if (user->reg_flags & USER_EVENT_REG_PERSIST)
+ last = 1;
+
+ return refcount_read(&user->refcnt) == last;
}
static __always_inline __must_check
@@ -842,7 +935,8 @@ static struct list_head *user_event_get_fields(struct trace_event_call *call)
* Upon success user_event has its ref count increased by 1.
*/
static int user_event_parse_cmd(struct user_event_group *group,
- char *raw_command, struct user_event **newuser)
+ char *raw_command, struct user_event **newuser,
+ int reg_flags)
{
char *name = raw_command;
char *args = strpbrk(name, " ");
@@ -856,7 +950,7 @@ static int user_event_parse_cmd(struct user_event_group *group,
if (flags)
*flags++ = '\0';
- return user_event_parse(group, name, args, flags, newuser);
+ return user_event_parse(group, name, args, flags, newuser, reg_flags);
}
static int user_field_array_size(const char *type)
@@ -1367,10 +1461,8 @@ static struct user_event *find_user_event(struct user_event_group *group,
*outkey = key;
hash_for_each_possible(group->register_table, user, node, key)
- if (!strcmp(EVENT_NAME(user), name)) {
- refcount_inc(&user->refcnt);
- return user;
- }
+ if (!strcmp(EVENT_NAME(user), name))
+ return user_event_get(user);
return NULL;
}
@@ -1432,7 +1524,7 @@ static void user_event_ftrace(struct user_event *user, struct iov_iter *i,
if (unlikely(!entry))
return;
- if (unlikely(!copy_nofault(entry + 1, i->count, i)))
+ if (unlikely(i->count != 0 && !copy_nofault(entry + 1, i->count, i)))
goto discard;
if (!list_empty(&user->validators) &&
@@ -1473,7 +1565,7 @@ static void user_event_perf(struct user_event *user, struct iov_iter *i,
perf_fetch_caller_regs(regs);
- if (unlikely(!copy_nofault(perf_entry + 1, i->count, i)))
+ if (unlikely(i->count != 0 && !copy_nofault(perf_entry + 1, i->count, i)))
goto discard;
if (!list_empty(&user->validators) &&
@@ -1584,12 +1676,12 @@ static int user_event_reg(struct trace_event_call *call,
return ret;
inc:
- refcount_inc(&user->refcnt);
+ user_event_get(user);
update_enable_bit_for(user);
return 0;
dec:
update_enable_bit_for(user);
- refcount_dec(&user->refcnt);
+ user_event_put(user, true);
return 0;
}
@@ -1620,10 +1712,11 @@ static int user_event_create(const char *raw_command)
mutex_lock(&group->reg_mutex);
- ret = user_event_parse_cmd(group, name, &user);
+ /* Dyn events persist, otherwise they would cleanup immediately */
+ ret = user_event_parse_cmd(group, name, &user, USER_EVENT_REG_PERSIST);
if (!ret)
- refcount_dec(&user->refcnt);
+ user_event_put(user, false);
mutex_unlock(&group->reg_mutex);
@@ -1745,6 +1838,8 @@ static bool user_event_match(const char *system, const char *event,
if (match && argc > 0)
match = user_fields_match(user, argc, argv);
+ else if (match && argc == 0)
+ match = list_empty(&user->fields);
return match;
}
@@ -1781,11 +1876,17 @@ static int user_event_trace_register(struct user_event *user)
*/
static int user_event_parse(struct user_event_group *group, char *name,
char *args, char *flags,
- struct user_event **newuser)
+ struct user_event **newuser, int reg_flags)
{
int ret;
u32 key;
struct user_event *user;
+ int argc = 0;
+ char **argv;
+
+ /* User register flags are not ready yet */
+ if (reg_flags != 0 || flags != NULL)
+ return -EINVAL;
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
@@ -1793,13 +1894,35 @@ static int user_event_parse(struct user_event_group *group, char *name,
mutex_unlock(&event_mutex);
if (user) {
- *newuser = user;
- /*
- * Name is allocated by caller, free it since it already exists.
- * Caller only worries about failure cases for freeing.
- */
- kfree(name);
+ if (args) {
+ argv = argv_split(GFP_KERNEL, args, &argc);
+ if (!argv) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ ret = user_fields_match(user, argc, (const char **)argv);
+ argv_free(argv);
+
+ } else
+ ret = list_empty(&user->fields);
+
+ if (ret) {
+ *newuser = user;
+ /*
+ * Name is allocated by caller, free it since it already exists.
+ * Caller only worries about failure cases for freeing.
+ */
+ kfree(name);
+ } else {
+ ret = -EADDRINUSE;
+ goto error;
+ }
+
return 0;
+error:
+ user_event_put(user, false);
+ return ret;
}
user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
@@ -1852,8 +1975,15 @@ static int user_event_parse(struct user_event_group *group, char *name,
if (ret)
goto put_user_lock;
- /* Ensure we track self ref and caller ref (2) */
- refcount_set(&user->refcnt, 2);
+ user->reg_flags = reg_flags;
+
+ if (user->reg_flags & USER_EVENT_REG_PERSIST) {
+ /* Ensure we track self ref and caller ref (2) */
+ refcount_set(&user->refcnt, 2);
+ } else {
+ /* Ensure we track only caller ref (1) */
+ refcount_set(&user->refcnt, 1);
+ }
dyn_event_init(&user->devent, &user_event_dops);
dyn_event_add(&user->devent, &user->call);
@@ -1885,7 +2015,7 @@ static int delete_user_event(struct user_event_group *group, char *name)
if (!user)
return -ENOENT;
- refcount_dec(&user->refcnt);
+ user_event_put(user, true);
if (!user_event_last_ref(user))
return -EBUSY;
@@ -2044,9 +2174,7 @@ static int user_events_ref_add(struct user_event_file_info *info,
for (i = 0; i < count; ++i)
new_refs->events[i] = refs->events[i];
- new_refs->events[i] = user;
-
- refcount_inc(&user->refcnt);
+ new_refs->events[i] = user_event_get(user);
rcu_assign_pointer(info->refs, new_refs);
@@ -2077,8 +2205,8 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg)
if (ret)
return ret;
- /* Ensure no flags, since we don't support any yet */
- if (kreg->flags != 0)
+ /* Ensure only valid flags */
+ if (kreg->flags & ~(USER_EVENT_REG_MAX-1))
return -EINVAL;
/* Ensure supported size */
@@ -2150,7 +2278,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info,
return ret;
}
- ret = user_event_parse_cmd(info->group, name, &user);
+ ret = user_event_parse_cmd(info->group, name, &user, reg.flags);
if (ret) {
kfree(name);
@@ -2160,7 +2288,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info,
ret = user_events_ref_add(info, user);
/* No longer need parse ref, ref_add either worked or not */
- refcount_dec(&user->refcnt);
+ user_event_put(user, false);
/* Positive number is index and valid */
if (ret < 0)
@@ -2309,7 +2437,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler));
if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))
- user_event_enabler_destroy(enabler);
+ user_event_enabler_destroy(enabler, true);
/* Removed at least one */
ret = 0;
@@ -2367,7 +2495,6 @@ static int user_events_release(struct inode *node, struct file *file)
struct user_event_file_info *info = file->private_data;
struct user_event_group *group;
struct user_event_refs *refs;
- struct user_event *user;
int i;
if (!info)
@@ -2391,12 +2518,9 @@ static int user_events_release(struct inode *node, struct file *file)
* The underlying user_events are ref counted, and cannot be freed.
* After this decrement, the user_events may be freed elsewhere.
*/
- for (i = 0; i < refs->count; ++i) {
- user = refs->events[i];
+ for (i = 0; i < refs->count; ++i)
+ user_event_put(refs->events[i], false);
- if (user)
- refcount_dec(&user->refcnt);
- }
out:
file->private_data = NULL;
@@ -2577,7 +2701,7 @@ static int __init trace_events_user_init(void)
if (!fault_cache)
return -ENOMEM;
- init_group = user_event_group_create(&init_user_ns);
+ init_group = user_event_group_create();
if (!init_group) {
kmem_cache_destroy(fault_cache);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 15f05faaae44..1e33f367783e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -847,7 +847,7 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c
int ret;
void *pos;
- list_for_each_entry(field, head, link) {
+ list_for_each_entry_reverse(field, head, link) {
trace_seq_printf(&iter->seq, " %s=", field->name);
if (field->offset + field->size > iter->ent_size) {
trace_seq_puts(&iter->seq, "<OVERFLOW>");
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index ef8ed3b65d05..6a4ecfb1da43 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -308,7 +308,7 @@ trace_probe_primary_from_call(struct trace_event_call *call)
{
struct trace_probe_event *tpe = trace_probe_event_from_call(call);
- return list_first_entry(&tpe->probes, struct trace_probe, list);
+ return list_first_entry_or_null(&tpe->probes, struct trace_probe, list);
}
static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp)
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index b7cbd66f889e..da35e5b7f047 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -12,58 +12,90 @@ enum vhost_task_flags {
VHOST_TASK_FLAGS_STOP,
};
+struct vhost_task {
+ bool (*fn)(void *data);
+ void *data;
+ struct completion exited;
+ unsigned long flags;
+ struct task_struct *task;
+};
+
static int vhost_task_fn(void *data)
{
struct vhost_task *vtsk = data;
- int ret;
+ bool dead = false;
+
+ for (;;) {
+ bool did_work;
+
+ if (!dead && signal_pending(current)) {
+ struct ksignal ksig;
+ /*
+ * Calling get_signal will block in SIGSTOP,
+ * or clear fatal_signal_pending, but remember
+ * what was set.
+ *
+ * This thread won't actually exit until all
+ * of the file descriptors are closed, and
+ * the release function is called.
+ */
+ dead = get_signal(&ksig);
+ if (dead)
+ clear_thread_flag(TIF_SIGPENDING);
+ }
+
+ /* mb paired w/ vhost_task_stop */
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) {
+ __set_current_state(TASK_RUNNING);
+ break;
+ }
+
+ did_work = vtsk->fn(vtsk->data);
+ if (!did_work)
+ schedule();
+ }
- ret = vtsk->fn(vtsk->data);
complete(&vtsk->exited);
- do_exit(ret);
+ do_exit(0);
}
/**
+ * vhost_task_wake - wakeup the vhost_task
+ * @vtsk: vhost_task to wake
+ *
+ * wake up the vhost_task worker thread
+ */
+void vhost_task_wake(struct vhost_task *vtsk)
+{
+ wake_up_process(vtsk->task);
+}
+EXPORT_SYMBOL_GPL(vhost_task_wake);
+
+/**
* vhost_task_stop - stop a vhost_task
* @vtsk: vhost_task to stop
*
- * Callers must call vhost_task_should_stop and return from their worker
- * function when it returns true;
+ * vhost_task_fn ensures the worker thread exits after
+ * VHOST_TASK_FLAGS_SOP becomes true.
*/
void vhost_task_stop(struct vhost_task *vtsk)
{
- pid_t pid = vtsk->task->pid;
-
set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
- wake_up_process(vtsk->task);
+ vhost_task_wake(vtsk);
/*
* Make sure vhost_task_fn is no longer accessing the vhost_task before
- * freeing it below. If userspace crashed or exited without closing,
- * then the vhost_task->task could already be marked dead so
- * kernel_wait will return early.
+ * freeing it below.
*/
wait_for_completion(&vtsk->exited);
- /*
- * If we are just closing/removing a device and the parent process is
- * not exiting then reap the task.
- */
- kernel_wait4(pid, NULL, __WCLONE, NULL);
kfree(vtsk);
}
EXPORT_SYMBOL_GPL(vhost_task_stop);
/**
- * vhost_task_should_stop - should the vhost task return from the work function
- * @vtsk: vhost_task to stop
- */
-bool vhost_task_should_stop(struct vhost_task *vtsk)
-{
- return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags);
-}
-EXPORT_SYMBOL_GPL(vhost_task_should_stop);
-
-/**
- * vhost_task_create - create a copy of a process to be used by the kernel
- * @fn: thread stack
+ * vhost_task_create - create a copy of a task to be used by the kernel
+ * @fn: vhost worker function
* @arg: data to be passed to fn
* @name: the thread's name
*
@@ -71,17 +103,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop);
* failure. The returned task is inactive, and the caller must fire it up
* through vhost_task_start().
*/
-struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg,
+struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg,
const char *name)
{
struct kernel_clone_args args = {
- .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM,
+ .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM |
+ CLONE_THREAD | CLONE_SIGHAND,
.exit_signal = 0,
.fn = vhost_task_fn,
.name = name,
.user_worker = 1,
.no_files = 1,
- .ignore_signals = 1,
};
struct vhost_task *vtsk;
struct task_struct *tsk;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4666a1a92a31..c913e333cce8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -705,12 +705,17 @@ static void clear_work_data(struct work_struct *work)
set_work_data(work, WORK_STRUCT_NO_POOL, 0);
}
+static inline struct pool_workqueue *work_struct_pwq(unsigned long data)
+{
+ return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK);
+}
+
static struct pool_workqueue *get_work_pwq(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
- return (void *)(data & WORK_STRUCT_WQ_DATA_MASK);
+ return work_struct_pwq(data);
else
return NULL;
}
@@ -738,8 +743,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work)
assert_rcu_or_pool_mutex();
if (data & WORK_STRUCT_PWQ)
- return ((struct pool_workqueue *)
- (data & WORK_STRUCT_WQ_DATA_MASK))->pool;
+ return work_struct_pwq(data)->pool;
pool_id = data >> WORK_OFFQ_POOL_SHIFT;
if (pool_id == WORK_OFFQ_POOL_NONE)
@@ -760,8 +764,7 @@ static int get_work_pool_id(struct work_struct *work)
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
- return ((struct pool_workqueue *)
- (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id;
+ return work_struct_pwq(data)->pool->id;
return data >> WORK_OFFQ_POOL_SHIFT;
}