summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/bpf/arraymap.c1
-rw-r--r--kernel/bpf/core.c24
-rw-r--r--kernel/bpf/stackmap.c3
-rw-r--r--kernel/bpf/syscall.c11
-rw-r--r--kernel/cgroup/cgroup.c4
-rw-r--r--kernel/cgroup/cpuset.c56
-rw-r--r--kernel/cred.c9
-rw-r--r--kernel/dma/debug.c36
-rw-r--r--kernel/dma/debug.h24
-rw-r--r--kernel/dma/mapping.c24
-rw-r--r--kernel/events/core.c34
-rw-r--r--kernel/module.c2
-rw-r--r--kernel/sched/core.c1
-rw-r--r--kernel/sched/debug.c8
-rw-r--r--kernel/sched/fair.c6
-rw-r--r--kernel/signal.c25
-rw-r--r--kernel/trace/ftrace.c4
-rw-r--r--kernel/trace/trace.c11
-rw-r--r--kernel/trace/trace_eprobe.c65
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/ucount.c49
-rw-r--r--kernel/workqueue.c18
23 files changed, 294 insertions, 125 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dd73a64f921..b1cb1dbf7417 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -657,7 +657,7 @@ static int audit_filter_rules(struct task_struct *tsk,
result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val);
break;
case AUDIT_SADDR_FAM:
- if (ctx->sockaddr)
+ if (ctx && ctx->sockaddr)
result = audit_comparator(ctx->sockaddr->ss_family,
f->op, f->val);
break;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 5e1ccfae916b..c7a5be3bf8be 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1071,6 +1071,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
INIT_WORK(&aux->work, prog_array_map_clear_deferred);
INIT_LIST_HEAD(&aux->poke_progs);
mutex_init(&aux->poke_mutex);
+ spin_lock_init(&aux->owner.lock);
map = array_map_alloc(attr);
if (IS_ERR(map)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b6c72af64d5d..327e3996eadb 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -525,6 +525,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
+long bpf_jit_limit_max __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -818,7 +819,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void)
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
- bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
PAGE_SIZE), LONG_MAX);
return 0;
}
@@ -1822,20 +1824,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ bool ret;
+
if (fp->kprobe_override)
return false;
- if (!array->aux->type) {
+ spin_lock(&array->aux->owner.lock);
+
+ if (!array->aux->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->aux->type = fp->type;
- array->aux->jited = fp->jited;
- return true;
+ array->aux->owner.type = fp->type;
+ array->aux->owner.jited = fp->jited;
+ ret = true;
+ } else {
+ ret = array->aux->owner.type == fp->type &&
+ array->aux->owner.jited == fp->jited;
}
-
- return array->aux->type == fp->type &&
- array->aux->jited == fp->jited;
+ spin_unlock(&array->aux->owner.lock);
+ return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 09a3fd97d329..6e75bbee39f0 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -63,7 +63,8 @@ static inline int stack_map_data_size(struct bpf_map *map)
static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
- u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
+ u64 elem_size = sizeof(struct stack_map_bucket) +
+ (u64)smap->map.value_size;
int err;
smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e12a217ead34..50f96ea4452a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -546,8 +546,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
- type = array->aux->type;
- jited = array->aux->jited;
+ spin_lock(&array->aux->owner.lock);
+ type = array->aux->owner.type;
+ jited = array->aux->owner.jited;
+ spin_unlock(&array->aux->owner.lock);
}
seq_printf(m,
@@ -1354,12 +1356,11 @@ int generic_map_update_batch(struct bpf_map *map,
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 value_size, cp, max_count;
- int ufd = attr->map_fd;
+ int ufd = attr->batch.map_fd;
void *key, *value;
struct fd f;
int err = 0;
- f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -1384,6 +1385,7 @@ int generic_map_update_batch(struct bpf_map *map,
return -ENOMEM;
}
+ f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
@@ -1403,6 +1405,7 @@ int generic_map_update_batch(struct bpf_map *map,
kvfree(value);
kvfree(key);
+ fdput(f);
return err;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 570b0c97392a..ea08f01d0111 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb)
* And don't kill the default root.
*/
if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
- !percpu_ref_is_dying(&root->cgrp.self.refcnt))
+ !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+ cgroup_bpf_offline(&root->cgrp);
percpu_ref_kill(&root->cgrp.self.refcnt);
+ }
cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index df1ccf4558f8..2a9695ccb65f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -311,17 +311,19 @@ static struct cpuset top_cpuset = {
if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
/*
- * There are two global locks guarding cpuset structures - cpuset_mutex and
+ * There are two global locks guarding cpuset structures - cpuset_rwsem and
* callback_lock. We also require taking task_lock() when dereferencing a
* task's cpuset pointer. See "The task_lock() exception", at the end of this
- * comment.
+ * comment. The cpuset code uses only cpuset_rwsem write lock. Other
+ * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to
+ * prevent change to cpuset structures.
*
* A task must hold both locks to modify cpusets. If a task holds
- * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it
+ * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it
* is the only task able to also acquire callback_lock and be able to
* modify cpusets. It can perform various checks on the cpuset structure
* first, knowing nothing will change. It can also allocate memory while
- * just holding cpuset_mutex. While it is performing these checks, various
+ * just holding cpuset_rwsem. While it is performing these checks, various
* callback routines can briefly acquire callback_lock to query cpusets.
* Once it is ready to make the changes, it takes callback_lock, blocking
* everyone else.
@@ -393,7 +395,7 @@ static inline bool is_in_v2_mode(void)
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void guarantee_online_cpus(struct task_struct *tsk,
struct cpumask *pmask)
@@ -435,7 +437,7 @@ out_unlock:
* One way or another, we guarantee to return some non-empty subset
* of node_states[N_MEMORY].
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
{
@@ -447,7 +449,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
/*
* update task's spread flag if cpuset's page/slab spread flag is set
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void cpuset_update_task_spread_flag(struct cpuset *cs,
struct task_struct *tsk)
@@ -468,7 +470,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
*
* One cpuset is a subset of another if all its allowed CPUs and
* Memory Nodes are a subset of the other, and its exclusive flags
- * are only set if the other's are set. Call holding cpuset_mutex.
+ * are only set if the other's are set. Call holding cpuset_rwsem.
*/
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
@@ -577,7 +579,7 @@ static inline void free_cpuset(struct cpuset *cs)
* If we replaced the flag and mask values of the current cpuset
* (cur) with those values in the trial cpuset (trial), would
* our various subset and exclusive rules still be valid? Presumes
- * cpuset_mutex held.
+ * cpuset_rwsem held.
*
* 'cur' is the address of an actual, in-use cpuset. Operations
* such as list traversal that depend on the actual address of the
@@ -700,7 +702,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
rcu_read_unlock();
}
-/* Must be called with cpuset_mutex held. */
+/* Must be called with cpuset_rwsem held. */
static inline int nr_cpusets(void)
{
/* jump label reference count + the top-level cpuset */
@@ -726,7 +728,7 @@ static inline int nr_cpusets(void)
* domains when operating in the severe memory shortage situations
* that could cause allocation failures below.
*
- * Must be called with cpuset_mutex held.
+ * Must be called with cpuset_rwsem held.
*
* The three key local variables below are:
* cp - cpuset pointer, used (together with pos_css) to perform a
@@ -1005,7 +1007,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
* 'cpus' is removed, then call this routine to rebuild the
* scheduler's dynamic sched domains.
*
- * Call with cpuset_mutex held. Takes cpus_read_lock().
+ * Call with cpuset_rwsem held. Takes cpus_read_lock().
*/
static void rebuild_sched_domains_locked(void)
{
@@ -1078,7 +1080,7 @@ void rebuild_sched_domains(void)
* @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
*
* Iterate through each task of @cs updating its cpus_allowed to the
- * effective cpuset's. As this function is called with cpuset_mutex held,
+ * effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_cpumask(struct cpuset *cs)
@@ -1347,7 +1349,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
*
* On legacy hierarchy, effective_cpus will be the same with cpu_allowed.
*
- * Called with cpuset_mutex held
+ * Called with cpuset_rwsem held
*/
static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
{
@@ -1704,12 +1706,12 @@ static void *cpuset_being_rebound;
* @cs: the cpuset in which each task's mems_allowed mask needs to be changed
*
* Iterate through each task of @cs updating its mems_allowed to the
- * effective cpuset's. As this function is called with cpuset_mutex held,
+ * effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_nodemask(struct cpuset *cs)
{
- static nodemask_t newmems; /* protected by cpuset_mutex */
+ static nodemask_t newmems; /* protected by cpuset_rwsem */
struct css_task_iter it;
struct task_struct *task;
@@ -1722,7 +1724,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
* take while holding tasklist_lock. Forks can happen - the
* mpol_dup() cpuset_being_rebound check will catch such forks,
* and rebind their vma mempolicies too. Because we still hold
- * the global cpuset_mutex, we know that no other rebind effort
+ * the global cpuset_rwsem, we know that no other rebind effort
* will be contending for the global variable cpuset_being_rebound.
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
@@ -1768,7 +1770,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
*
* On legacy hierarchy, effective_mems will be the same with mems_allowed.
*
- * Called with cpuset_mutex held
+ * Called with cpuset_rwsem held
*/
static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
{
@@ -1821,7 +1823,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
* mempolicies and if the cpuset is marked 'memory_migrate',
* migrate the tasks pages to the new memory.
*
- * Call with cpuset_mutex held. May take callback_lock during call.
+ * Call with cpuset_rwsem held. May take callback_lock during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
* lock each such tasks mm->mmap_lock, scan its vma's and rebind
* their mempolicies to the cpusets new mems_allowed.
@@ -1911,7 +1913,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
* @cs: the cpuset in which each task's spread flags needs to be changed
*
* Iterate through each task of @cs updating its spread flags. As this
- * function is called with cpuset_mutex held, cpuset membership stays
+ * function is called with cpuset_rwsem held, cpuset membership stays
* stable.
*/
static void update_tasks_flags(struct cpuset *cs)
@@ -1931,7 +1933,7 @@ static void update_tasks_flags(struct cpuset *cs)
* cs: the cpuset to update
* turning_on: whether the flag is being set or cleared
*
- * Call with cpuset_mutex held.
+ * Call with cpuset_rwsem held.
*/
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
@@ -1980,7 +1982,7 @@ out:
* cs: the cpuset to update
* new_prs: new partition root state
*
- * Call with cpuset_mutex held.
+ * Call with cpuset_rwsem held.
*/
static int update_prstate(struct cpuset *cs, int new_prs)
{
@@ -2167,7 +2169,7 @@ static int fmeter_getrate(struct fmeter *fmp)
static struct cpuset *cpuset_attach_old_cs;
-/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
+/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */
static int cpuset_can_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
@@ -2219,7 +2221,7 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
}
/*
- * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach()
+ * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach()
* but we can't allocate it dynamically there. Define it global and
* allocate from cpuset_init().
*/
@@ -2227,7 +2229,7 @@ static cpumask_var_t cpus_attach;
static void cpuset_attach(struct cgroup_taskset *tset)
{
- /* static buf protected by cpuset_mutex */
+ /* static buf protected by cpuset_rwsem */
static nodemask_t cpuset_attach_nodemask_to;
struct task_struct *task;
struct task_struct *leader;
@@ -2417,7 +2419,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
* operation like this one can lead to a deadlock through kernfs
* active_ref protection. Let's break the protection. Losing the
* protection is okay as we check whether @cs is online after
- * grabbing cpuset_mutex anyway. This only happens on the legacy
+ * grabbing cpuset_rwsem anyway. This only happens on the legacy
* hierarchies.
*/
css_get(&cs->css);
@@ -3672,7 +3674,7 @@ void __cpuset_memory_pressure_bump(void)
* - Used for /proc/<pid>/cpuset.
* - No need to task_lock(tsk) on this tsk->cpuset reference, as it
* doesn't really matter if tsk->cpuset changes after we read it,
- * and we take cpuset_mutex, keeping cpuset_attach() from changing it
+ * and we take cpuset_rwsem, keeping cpuset_attach() from changing it
* anyway.
*/
int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
diff --git a/kernel/cred.c b/kernel/cred.c
index f784e08c2fbd..1ae0b4948a5a 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -225,8 +225,6 @@ struct cred *cred_alloc_blank(void)
#ifdef CONFIG_DEBUG_CREDENTIALS
new->magic = CRED_MAGIC;
#endif
- new->ucounts = get_ucounts(&init_ucounts);
-
if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
@@ -501,7 +499,7 @@ int commit_creds(struct cred *new)
inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
rcu_assign_pointer(task->real_cred, new);
rcu_assign_pointer(task->cred, new);
- if (new->user != old->user)
+ if (new->user != old->user || new->user_ns != old->user_ns)
dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
alter_cred_subscribers(old, -2);
@@ -669,7 +667,7 @@ int set_cred_ucounts(struct cred *new)
{
struct task_struct *task = current;
const struct cred *old = task->real_cred;
- struct ucounts *old_ucounts = new->ucounts;
+ struct ucounts *new_ucounts, *old_ucounts = new->ucounts;
if (new->user == old->user && new->user_ns == old->user_ns)
return 0;
@@ -681,9 +679,10 @@ int set_cred_ucounts(struct cred *new)
if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid))
return 0;
- if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid)))
+ if (!(new_ucounts = alloc_ucounts(new->user_ns, new->euid)))
return -EAGAIN;
+ new->ucounts = new_ucounts;
if (old_ucounts)
put_ucounts(old_ucounts);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 95445bd6eb72..7a14ca29c377 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -552,7 +552,7 @@ static void active_cacheline_remove(struct dma_debug_entry *entry)
* Wrapper function for adding an entry to the hash.
* This function takes care of locking itself.
*/
-static void add_dma_entry(struct dma_debug_entry *entry)
+static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
{
struct hash_bucket *bucket;
unsigned long flags;
@@ -566,7 +566,7 @@ static void add_dma_entry(struct dma_debug_entry *entry)
if (rc == -ENOMEM) {
pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
global_disable = true;
- } else if (rc == -EEXIST) {
+ } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
err_printk(entry->dev, entry,
"cacheline tracking EEXIST, overlapping mappings aren't supported\n");
}
@@ -1191,7 +1191,8 @@ void debug_dma_map_single(struct device *dev, const void *addr,
EXPORT_SYMBOL(debug_dma_map_single);
void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
- size_t size, int direction, dma_addr_t dma_addr)
+ size_t size, int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1222,7 +1223,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
check_for_illegal_area(dev, addr, size);
}
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
@@ -1280,7 +1281,8 @@ void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
}
void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction)
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
struct scatterlist *s;
@@ -1289,6 +1291,12 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
if (unlikely(dma_debug_disabled()))
return;
+ for_each_sg(sg, s, nents, i) {
+ check_for_stack(dev, sg_page(s), s->offset);
+ if (!PageHighMem(sg_page(s)))
+ check_for_illegal_area(dev, sg_virt(s), s->length);
+ }
+
for_each_sg(sg, s, mapped_ents, i) {
entry = dma_entry_alloc();
if (!entry)
@@ -1304,15 +1312,9 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
entry->sg_call_ents = nents;
entry->sg_mapped_ents = mapped_ents;
- check_for_stack(dev, sg_page(s), s->offset);
-
- if (!PageHighMem(sg_page(s))) {
- check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
- }
-
check_sg_segment(dev, s);
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
}
@@ -1368,7 +1370,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
}
void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt)
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1398,7 +1401,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size,
else
entry->pfn = page_to_pfn(virt_to_page(virt));
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_free_coherent(struct device *dev, size_t size,
@@ -1429,7 +1432,8 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
}
void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
- int direction, dma_addr_t dma_addr)
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1449,7 +1453,7 @@ void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
entry->direction = direction;
entry->map_err_type = MAP_ERR_NOT_CHECKED;
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index 83643b3010b2..f525197d3cae 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -11,26 +11,30 @@
#ifdef CONFIG_DMA_API_DEBUG
extern void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
- int direction, dma_addr_t dma_addr);
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs);
extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, int direction);
extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction);
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs);
extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, int dir);
extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt);
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs);
extern void debug_dma_free_coherent(struct device *dev, size_t size,
void *virt, dma_addr_t addr);
extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
size_t size, int direction,
- dma_addr_t dma_addr);
+ dma_addr_t dma_addr,
+ unsigned long attrs);
extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
size_t size, int direction);
@@ -53,7 +57,8 @@ extern void debug_dma_sync_sg_for_device(struct device *dev,
#else /* CONFIG_DMA_API_DEBUG */
static inline void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
- int direction, dma_addr_t dma_addr)
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
}
@@ -63,7 +68,8 @@ static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
}
static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction)
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs)
{
}
@@ -74,7 +80,8 @@ static inline void debug_dma_unmap_sg(struct device *dev,
}
static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt)
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs)
{
}
@@ -85,7 +92,8 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size,
static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
size_t size, int direction,
- dma_addr_t dma_addr)
+ dma_addr_t dma_addr,
+ unsigned long attrs)
{
}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 06fec5547e7c..8349a9f2c345 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -156,7 +156,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
else
addr = ops->map_page(dev, page, offset, size, dir, attrs);
- debug_dma_map_page(dev, page, offset, size, dir, addr);
+ debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
return addr;
}
@@ -195,7 +195,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
ents = ops->map_sg(dev, sg, nents, dir, attrs);
if (ents > 0)
- debug_dma_map_sg(dev, sg, nents, ents, dir);
+ debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
ents != -EIO))
return -EIO;
@@ -249,12 +249,12 @@ EXPORT_SYMBOL(dma_map_sg_attrs);
* Returns 0 on success or a negative error code on error. The following
* error codes are supported with the given meaning:
*
- * -EINVAL - An invalid argument, unaligned access or other error
- * in usage. Will not succeed if retried.
- * -ENOMEM - Insufficient resources (like memory or IOVA space) to
- * complete the mapping. Should succeed if retried later.
- * -EIO - Legacy error code with an unknown meaning. eg. this is
- * returned if a lower level call returned DMA_MAPPING_ERROR.
+ * -EINVAL An invalid argument, unaligned access or other error
+ * in usage. Will not succeed if retried.
+ * -ENOMEM Insufficient resources (like memory or IOVA space) to
+ * complete the mapping. Should succeed if retried later.
+ * -EIO Legacy error code with an unknown meaning. eg. this is
+ * returned if a lower level call returned DMA_MAPPING_ERROR.
*/
int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
enum dma_data_direction dir, unsigned long attrs)
@@ -305,7 +305,7 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
else if (ops->map_resource)
addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
- debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+ debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs);
return addr;
}
EXPORT_SYMBOL(dma_map_resource);
@@ -510,7 +510,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
else
return NULL;
- debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+ debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, attrs);
return cpu_addr;
}
EXPORT_SYMBOL(dma_alloc_attrs);
@@ -566,7 +566,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp);
if (page)
- debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+ debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
return page;
}
EXPORT_SYMBOL_GPL(dma_alloc_pages);
@@ -644,7 +644,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
if (sgt) {
sgt->nents = 1;
- debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir);
+ debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
}
return sgt;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 20367196fa9a..ef29882c9dc4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
return 0;
}
+static inline bool event_update_userpage(struct perf_event *event)
+{
+ if (likely(!atomic_read(&event->mmap_count)))
+ return false;
+
+ perf_event_update_time(event);
+ perf_set_shadow_time(event, event->ctx);
+ perf_event_update_userpage(event);
+
+ return true;
+}
+
+static inline void group_update_userpage(struct perf_event *group_event)
+{
+ struct perf_event *event;
+
+ if (!event_update_userpage(group_event))
+ return;
+
+ for_each_sibling_event(event, group_event)
+ event_update_userpage(event);
+}
+
static int merge_sched_in(struct perf_event *event, void *data)
{
struct perf_event_context *ctx = event->ctx;
@@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data)
}
if (event->state == PERF_EVENT_STATE_INACTIVE) {
+ *can_add_hw = 0;
if (event->attr.pinned) {
perf_cgroup_event_disable(event, ctx);
perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+ } else {
+ ctx->rotate_necessary = 1;
+ perf_mux_hrtimer_restart(cpuctx);
+ group_update_userpage(event);
}
-
- *can_add_hw = 0;
- ctx->rotate_necessary = 1;
- perf_mux_hrtimer_restart(cpuctx);
}
return 0;
@@ -6324,6 +6348,8 @@ accounting:
ring_buffer_attach(event, rb);
+ perf_event_update_time(event);
+ perf_set_shadow_time(event, event->ctx);
perf_event_init_userpage(event);
perf_event_update_userpage(event);
} else {
diff --git a/kernel/module.c b/kernel/module.c
index 40ec9a030eec..5c26a76e800b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4489,8 +4489,10 @@ static void cfi_init(struct module *mod)
/* Fix init/exit functions to point to the CFI jump table */
if (init)
mod->init = *init;
+#ifdef CONFIG_MODULE_UNLOAD
if (exit)
mod->exit = *exit;
+#endif
cfi_module_add(mod, module_addr_min);
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1bba4128a3e6..f21714ea3db8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8795,6 +8795,7 @@ void idle_task_exit(void)
finish_arch_post_lock_switch();
}
+ scs_task_reset(current);
/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 49716228efb4..17a653b67006 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
char buf[16];
+ unsigned int scaling;
if (cnt > 15)
cnt = 15;
if (copy_from_user(&buf, ubuf, cnt))
return -EFAULT;
+ buf[cnt] = '\0';
- if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling))
+ if (kstrtouint(buf, 10, &scaling))
return -EINVAL;
+ if (scaling >= SCHED_TUNABLESCALING_END)
+ return -EINVAL;
+
+ sysctl_sched_tunable_scaling = scaling;
if (sched_update_scaling())
return -EINVAL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ff69f245b939..f6a05d9b5443 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
/* update hierarchical throttle state */
walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
- if (!cfs_rq->load.weight)
+ /* Nothing to run but something to decay (on_list)? Complete the branch */
+ if (!cfs_rq->load.weight) {
+ if (cfs_rq->on_list)
+ goto unthrottle_throttle;
return;
+ }
task_delta = cfs_rq->h_nr_running;
idle_task_delta = cfs_rq->idle_h_nr_running;
diff --git a/kernel/signal.c b/kernel/signal.c
index 952741f6d0f9..487bf4f5dadf 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -426,22 +426,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
*/
rcu_read_lock();
ucounts = task_ucounts(t);
- sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
- switch (sigpending) {
- case 1:
- if (likely(get_ucounts(ucounts)))
- break;
- fallthrough;
- case LONG_MAX:
- /*
- * we need to decrease the ucount in the userns tree on any
- * failure to avoid counts leaking.
- */
- dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
- rcu_read_unlock();
- return NULL;
- }
+ sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
rcu_read_unlock();
+ if (!sigpending)
+ return NULL;
if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
@@ -450,8 +438,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
}
if (unlikely(q == NULL)) {
- if (dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1))
- put_ucounts(ucounts);
+ dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
} else {
INIT_LIST_HEAD(&q->list);
q->flags = sigqueue_flags;
@@ -464,8 +451,8 @@ static void __sigqueue_free(struct sigqueue *q)
{
if (q->flags & SIGQUEUE_PREALLOC)
return;
- if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) {
- put_ucounts(q->ucounts);
+ if (q->ucounts) {
+ dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING);
q->ucounts = NULL;
}
kmem_cache_free(sigqueue_cachep, q);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7efbc8aaf7f6..635fbdc9d589 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6977,7 +6977,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op;
int bit;
- bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
+ bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START);
if (bit < 0)
return;
@@ -7052,7 +7052,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
{
int bit;
- bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
+ bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START);
if (bit < 0)
return;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7896d30d90f7..bc677cd64224 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1744,16 +1744,15 @@ void latency_fsnotify(struct trace_array *tr)
irq_work_queue(&tr->fsnotify_irqwork);
}
-/*
- * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
- * defined(CONFIG_FSNOTIFY)
- */
-#else
+#elif defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) \
+ || defined(CONFIG_OSNOISE_TRACER)
#define trace_create_maxlat_file(tr, d_tracer) \
trace_create_file("tracing_max_latency", 0644, d_tracer, \
&tr->max_latency, &tracing_max_lat_fops)
+#else
+#define trace_create_maxlat_file(tr, d_tracer) do { } while (0)
#endif
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -9473,9 +9472,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
create_trace_options_dir(tr);
-#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
trace_create_maxlat_file(tr, d_tracer);
-#endif
if (ftrace_create_function_files(tr, d_tracer))
MEM_FAIL(1, "Could not allocate function filter files");
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 3044b762cbd7..5c5f208c15d3 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -119,10 +119,58 @@ static bool eprobe_dyn_event_match(const char *system, const char *event,
int argc, const char **argv, struct dyn_event *ev)
{
struct trace_eprobe *ep = to_trace_eprobe(ev);
+ const char *slash;
- return strcmp(trace_probe_name(&ep->tp), event) == 0 &&
- (!system || strcmp(trace_probe_group_name(&ep->tp), system) == 0) &&
- trace_probe_match_command_args(&ep->tp, argc, argv);
+ /*
+ * We match the following:
+ * event only - match all eprobes with event name
+ * system and event only - match all system/event probes
+ *
+ * The below has the above satisfied with more arguments:
+ *
+ * attached system/event - If the arg has the system and event
+ * the probe is attached to, match
+ * probes with the attachment.
+ *
+ * If any more args are given, then it requires a full match.
+ */
+
+ /*
+ * If system exists, but this probe is not part of that system
+ * do not match.
+ */
+ if (system && strcmp(trace_probe_group_name(&ep->tp), system) != 0)
+ return false;
+
+ /* Must match the event name */
+ if (strcmp(trace_probe_name(&ep->tp), event) != 0)
+ return false;
+
+ /* No arguments match all */
+ if (argc < 1)
+ return true;
+
+ /* First argument is the system/event the probe is attached to */
+
+ slash = strchr(argv[0], '/');
+ if (!slash)
+ slash = strchr(argv[0], '.');
+ if (!slash)
+ return false;
+
+ if (strncmp(ep->event_system, argv[0], slash - argv[0]))
+ return false;
+ if (strcmp(ep->event_name, slash + 1))
+ return false;
+
+ argc--;
+ argv++;
+
+ /* If there are no other args, then match */
+ if (argc < 1)
+ return true;
+
+ return trace_probe_match_command_args(&ep->tp, argc, argv);
}
static struct dyn_event_operations eprobe_dyn_event_ops = {
@@ -632,6 +680,13 @@ static int disable_eprobe(struct trace_eprobe *ep,
trace_event_trigger_enable_disable(file, 0);
update_cond_flag(file);
+
+ /* Make sure nothing is using the edata or trigger */
+ tracepoint_synchronize_unregister();
+
+ kfree(edata);
+ kfree(trigger);
+
return 0;
}
@@ -849,8 +904,8 @@ static int __trace_eprobe_create(int argc, const char *argv[])
if (IS_ERR(ep)) {
ret = PTR_ERR(ep);
- /* This must return -ENOMEM, else there is a bug */
- WARN_ON_ONCE(ret != -ENOMEM);
+ /* This must return -ENOMEM or misssing event, else there is a bug */
+ WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV);
ep = NULL;
goto error;
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index a6061a69aa84..f01e442716e2 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2506,7 +2506,7 @@ find_synthetic_field_var(struct hist_trigger_data *target_hist_data,
* events. However, for convenience, users are allowed to directly
* specify an event field in an action, which will be automatically
* converted into a variable on their behalf.
-
+ *
* If a user specifies a field on an event that isn't the event the
* histogram currently being defined (the target event histogram), the
* only way that can be accomplished is if a new hist trigger is
diff --git a/kernel/ucount.c b/kernel/ucount.c
index bb51849e6375..eb03f3c68375 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -284,6 +284,55 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
return (new == 0);
}
+static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
+ struct ucounts *last, enum ucount_type type)
+{
+ struct ucounts *iter, *next;
+ for (iter = ucounts; iter != last; iter = next) {
+ long dec = atomic_long_add_return(-1, &iter->ucount[type]);
+ WARN_ON_ONCE(dec < 0);
+ next = iter->ns->ucounts;
+ if (dec == 0)
+ put_ucounts(iter);
+ }
+}
+
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
+{
+ do_dec_rlimit_put_ucounts(ucounts, NULL, type);
+}
+
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
+{
+ /* Caller must hold a reference to ucounts */
+ struct ucounts *iter;
+ long dec, ret = 0;
+
+ for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+ long max = READ_ONCE(iter->ns->ucount_max[type]);
+ long new = atomic_long_add_return(1, &iter->ucount[type]);
+ if (new < 0 || new > max)
+ goto unwind;
+ if (iter == ucounts)
+ ret = new;
+ /*
+ * Grab an extra ucount reference for the caller when
+ * the rlimit count was previously 0.
+ */
+ if (new != 1)
+ continue;
+ if (!get_ucounts(iter))
+ goto dec_unwind;
+ }
+ return ret;
+dec_unwind:
+ dec = atomic_long_add_return(-1, &iter->ucount[type]);
+ WARN_ON_ONCE(dec < 0);
+unwind:
+ do_dec_rlimit_put_ucounts(ucounts, iter, type);
+ return 0;
+}
+
bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
{
struct ucounts *iter;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 33a6b4a2443d..1b3eb1e9531f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4830,8 +4830,16 @@ void show_workqueue_state(void)
for_each_pwq(pwq, wq) {
raw_spin_lock_irqsave(&pwq->pool->lock, flags);
- if (pwq->nr_active || !list_empty(&pwq->inactive_works))
+ if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
+ /*
+ * Defer printing to avoid deadlocks in console
+ * drivers that queue work while holding locks
+ * also taken in their write paths.
+ */
+ printk_deferred_enter();
show_pwq(pwq);
+ printk_deferred_exit();
+ }
raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
/*
* We could be printing a lot from atomic context, e.g.
@@ -4849,7 +4857,12 @@ void show_workqueue_state(void)
raw_spin_lock_irqsave(&pool->lock, flags);
if (pool->nr_workers == pool->nr_idle)
goto next_pool;
-
+ /*
+ * Defer printing to avoid deadlocks in console drivers that
+ * queue work while holding locks also taken in their write
+ * paths.
+ */
+ printk_deferred_enter();
pr_info("pool %d:", pool->id);
pr_cont_pool_info(pool);
pr_cont(" hung=%us workers=%d",
@@ -4864,6 +4877,7 @@ void show_workqueue_state(void)
first = false;
}
pr_cont("\n");
+ printk_deferred_exit();
next_pool:
raw_spin_unlock_irqrestore(&pool->lock, flags);
/*