summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/hashtab.c2
-rw-r--r--kernel/cgroup/debug.c4
-rw-r--r--kernel/cgroup/stat.c8
-rw-r--r--kernel/cpu.c14
-rw-r--r--kernel/debug/kdb/kdb_io.c2
-rw-r--r--kernel/events/core.c7
-rw-r--r--kernel/exit.c8
-rw-r--r--kernel/futex.c4
-rw-r--r--kernel/groups.c5
-rw-r--r--kernel/irq/matrix.c4
-rw-r--r--kernel/kcov.c4
-rw-r--r--kernel/locking/lockdep.c651
-rw-r--r--kernel/locking/spinlock.c13
-rw-r--r--kernel/printk/printk.c3
-rw-r--r--kernel/sched/core.c22
-rw-r--r--kernel/sched/fair.c102
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/sched/wait.c2
-rw-r--r--kernel/trace/Kconfig1
-rw-r--r--kernel/trace/bpf_trace.c19
-rw-r--r--kernel/trace/ring_buffer.c6
-rw-r--r--kernel/trace/trace.c41
-rw-r--r--kernel/trace/trace_stack.c4
-rw-r--r--kernel/uid16.c1
-rw-r--r--kernel/workqueue.c33
25 files changed, 216 insertions, 752 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index e469e05c8e83..3905d4bc5b80 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -114,6 +114,7 @@ static void htab_free_elems(struct bpf_htab *htab)
pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
htab->map.key_size);
free_percpu(pptr);
+ cond_resched();
}
free_elems:
bpf_map_area_free(htab->elems);
@@ -159,6 +160,7 @@ static int prealloc_init(struct bpf_htab *htab)
goto free_elems;
htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
pptr);
+ cond_resched();
}
skip_percpu_elems:
diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c
index 5f780d8f6a9d..9caeda610249 100644
--- a/kernel/cgroup/debug.c
+++ b/kernel/cgroup/debug.c
@@ -50,7 +50,7 @@ static int current_css_set_read(struct seq_file *seq, void *v)
spin_lock_irq(&css_set_lock);
rcu_read_lock();
- cset = rcu_dereference(current->cgroups);
+ cset = task_css_set(current);
refcnt = refcount_read(&cset->refcount);
seq_printf(seq, "css_set %pK %d", cset, refcnt);
if (refcnt > cset->nr_tasks)
@@ -96,7 +96,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
spin_lock_irq(&css_set_lock);
rcu_read_lock();
- cset = rcu_dereference(current->cgroups);
+ cset = task_css_set(current);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c
index 133b465691d6..1e111dd455c4 100644
--- a/kernel/cgroup/stat.c
+++ b/kernel/cgroup/stat.c
@@ -296,8 +296,12 @@ int cgroup_stat_init(struct cgroup *cgrp)
}
/* ->updated_children list is self terminated */
- for_each_possible_cpu(cpu)
- cgroup_cpu_stat(cgrp, cpu)->updated_children = cgrp;
+ for_each_possible_cpu(cpu) {
+ struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu);
+
+ cstat->updated_children = cgrp;
+ u64_stats_init(&cstat->sync);
+ }
prev_cputime_init(&cgrp->stat.prev_cputime);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 04892a82f6ac..41376c3ac93b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -780,8 +780,8 @@ static int takedown_cpu(unsigned int cpu)
BUG_ON(cpu_online(cpu));
/*
- * The CPUHP_AP_SCHED_MIGRATE_DYING callback will have removed all
- * runnable tasks from the cpu, there's only the idle task left now
+ * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed
+ * all runnable tasks from the CPU, there's only the idle task left now
* that the migration thread is done doing the stop_machine thing.
*
* Wait for the stop thread to go away.
@@ -1289,11 +1289,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
.teardown.single = NULL,
.cant_stop = true,
},
- [CPUHP_AP_SMPCFD_DYING] = {
- .name = "smpcfd:dying",
- .startup.single = NULL,
- .teardown.single = smpcfd_dying_cpu,
- },
/*
* Handled on controll processor until the plugged processor manages
* this itself.
@@ -1335,6 +1330,11 @@ static struct cpuhp_step cpuhp_ap_states[] = {
.startup.single = NULL,
.teardown.single = rcutree_dying_cpu,
},
+ [CPUHP_AP_SMPCFD_DYING] = {
+ .name = "smpcfd:dying",
+ .startup.single = NULL,
+ .teardown.single = smpcfd_dying_cpu,
+ },
/* Entry state on starting. Interrupts enabled from here on. Transient
* state for synchronsization */
[CPUHP_AP_ONLINE] = {
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index e74be38245ad..ed5d34925ad0 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -350,7 +350,7 @@ poll_again:
}
kdb_printf("\n");
for (i = 0; i < count; i++) {
- if (kallsyms_symbol_next(p_tmp, i) < 0)
+ if (WARN_ON(!kallsyms_symbol_next(p_tmp, i)))
break;
kdb_printf("%s ", p_tmp);
*(p_tmp + len) = '\0';
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 34fda6aa4606..878d86c513d6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6642,6 +6642,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
struct perf_namespaces_event *namespaces_event = data;
struct perf_output_handle handle;
struct perf_sample_data sample;
+ u16 header_size = namespaces_event->event_id.header.size;
int ret;
if (!perf_event_namespaces_match(event))
@@ -6652,7 +6653,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
ret = perf_output_begin(&handle, event,
namespaces_event->event_id.header.size);
if (ret)
- return;
+ goto out;
namespaces_event->event_id.pid = perf_event_pid(event,
namespaces_event->task);
@@ -6664,6 +6665,8 @@ static void perf_event_namespaces_output(struct perf_event *event,
perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
+out:
+ namespaces_event->event_id.header.size = header_size;
}
static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
@@ -7990,11 +7993,11 @@ static void bpf_overflow_handler(struct perf_event *event,
{
struct bpf_perf_event_data_kern ctx = {
.data = data,
- .regs = regs,
.event = event,
};
int ret = 0;
+ ctx.regs = perf_arch_bpf_user_pt_regs(regs);
preempt_disable();
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
goto out;
diff --git a/kernel/exit.c b/kernel/exit.c
index 6b4298a41167..df0c91d5606c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1755,3 +1755,11 @@ Efault:
return -EFAULT;
}
#endif
+
+__weak void abort(void)
+{
+ BUG();
+
+ /* if that doesn't kill us, halt */
+ panic("Oops failed to kill thread");
+}
diff --git a/kernel/futex.c b/kernel/futex.c
index 76ed5921117a..57d0b3657e16 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1582,8 +1582,8 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
{
unsigned int op = (encoded_op & 0x70000000) >> 28;
unsigned int cmp = (encoded_op & 0x0f000000) >> 24;
- int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 12);
- int cmparg = sign_extend32(encoded_op & 0x00000fff, 12);
+ int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
+ int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
int oldval, ret;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
diff --git a/kernel/groups.c b/kernel/groups.c
index e357bc800111..daae2f2dc6d4 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -86,11 +86,12 @@ static int gid_cmp(const void *_a, const void *_b)
return gid_gt(a, b) - gid_lt(a, b);
}
-static void groups_sort(struct group_info *group_info)
+void groups_sort(struct group_info *group_info)
{
sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid),
gid_cmp, NULL);
}
+EXPORT_SYMBOL(groups_sort);
/* a simple bsearch */
int groups_search(const struct group_info *group_info, kgid_t grp)
@@ -122,7 +123,6 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
void set_groups(struct cred *new, struct group_info *group_info)
{
put_group_info(new->group_info);
- groups_sort(group_info);
get_group_info(group_info);
new->group_info = group_info;
}
@@ -206,6 +206,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
return retval;
}
+ groups_sort(group_info);
retval = set_current_groups(group_info);
put_group_info(group_info);
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 7df2480005f8..0ba0dd8863a7 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -384,7 +384,9 @@ unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown)
{
struct cpumap *cm = this_cpu_ptr(m->maps);
- return (m->global_available - cpudown) ? cm->available : 0;
+ if (!cpudown)
+ return m->global_available;
+ return m->global_available - cm->available;
}
/**
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 15f33faf4013..7594c033d98a 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -157,7 +157,7 @@ void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2)
}
EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2);
-void notrace __sanitizer_cov_trace_cmp4(u16 arg1, u16 arg2)
+void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2)
{
write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_);
}
@@ -183,7 +183,7 @@ void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2)
}
EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2);
-void notrace __sanitizer_cov_trace_const_cmp4(u16 arg1, u16 arg2)
+void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2)
{
write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2,
_RET_IP_);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 9776da8db180..5fa1324a4f29 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -57,10 +57,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/lock.h>
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-#include <linux/slab.h>
-#endif
-
#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
module_param(prove_locking, int, 0644);
@@ -75,19 +71,6 @@ module_param(lock_stat, int, 0644);
#define lock_stat 0
#endif
-#ifdef CONFIG_BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
-static int crossrelease_fullstack = 1;
-#else
-static int crossrelease_fullstack;
-#endif
-static int __init allow_crossrelease_fullstack(char *str)
-{
- crossrelease_fullstack = 1;
- return 0;
-}
-
-early_param("crossrelease_fullstack", allow_crossrelease_fullstack);
-
/*
* lockdep_lock: protects the lockdep graph, the hashes and the
* class/list/hash allocators.
@@ -740,18 +723,6 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL);
}
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-static void cross_init(struct lockdep_map *lock, int cross);
-static int cross_lock(struct lockdep_map *lock);
-static int lock_acquire_crosslock(struct held_lock *hlock);
-static int lock_release_crosslock(struct lockdep_map *lock);
-#else
-static inline void cross_init(struct lockdep_map *lock, int cross) {}
-static inline int cross_lock(struct lockdep_map *lock) { return 0; }
-static inline int lock_acquire_crosslock(struct held_lock *hlock) { return 2; }
-static inline int lock_release_crosslock(struct lockdep_map *lock) { return 2; }
-#endif
-
/*
* Register a lock's class in the hash-table, if the class is not present
* yet. Otherwise we look it up. We cache the result in the lock object
@@ -1151,41 +1122,22 @@ print_circular_lock_scenario(struct held_lock *src,
printk(KERN_CONT "\n\n");
}
- if (cross_lock(tgt->instance)) {
- printk(" Possible unsafe locking scenario by crosslock:\n\n");
- printk(" CPU0 CPU1\n");
- printk(" ---- ----\n");
- printk(" lock(");
- __print_lock_name(parent);
- printk(KERN_CONT ");\n");
- printk(" lock(");
- __print_lock_name(target);
- printk(KERN_CONT ");\n");
- printk(" lock(");
- __print_lock_name(source);
- printk(KERN_CONT ");\n");
- printk(" unlock(");
- __print_lock_name(target);
- printk(KERN_CONT ");\n");
- printk("\n *** DEADLOCK ***\n\n");
- } else {
- printk(" Possible unsafe locking scenario:\n\n");
- printk(" CPU0 CPU1\n");
- printk(" ---- ----\n");
- printk(" lock(");
- __print_lock_name(target);
- printk(KERN_CONT ");\n");
- printk(" lock(");
- __print_lock_name(parent);
- printk(KERN_CONT ");\n");
- printk(" lock(");
- __print_lock_name(target);
- printk(KERN_CONT ");\n");
- printk(" lock(");
- __print_lock_name(source);
- printk(KERN_CONT ");\n");
- printk("\n *** DEADLOCK ***\n\n");
- }
+ printk(" Possible unsafe locking scenario:\n\n");
+ printk(" CPU0 CPU1\n");
+ printk(" ---- ----\n");
+ printk(" lock(");
+ __print_lock_name(target);
+ printk(KERN_CONT ");\n");
+ printk(" lock(");
+ __print_lock_name(parent);
+ printk(KERN_CONT ");\n");
+ printk(" lock(");
+ __print_lock_name(target);
+ printk(KERN_CONT ");\n");
+ printk(" lock(");
+ __print_lock_name(source);
+ printk(KERN_CONT ");\n");
+ printk("\n *** DEADLOCK ***\n\n");
}
/*
@@ -1211,10 +1163,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
curr->comm, task_pid_nr(curr));
print_lock(check_src);
- if (cross_lock(check_tgt->instance))
- pr_warn("\nbut now in release context of a crosslock acquired at the following:\n");
- else
- pr_warn("\nbut task is already holding lock:\n");
+ pr_warn("\nbut task is already holding lock:\n");
print_lock(check_tgt);
pr_warn("\nwhich lock already depends on the new lock.\n\n");
@@ -1244,9 +1193,7 @@ static noinline int print_circular_bug(struct lock_list *this,
if (!debug_locks_off_graph_unlock() || debug_locks_silent)
return 0;
- if (cross_lock(check_tgt->instance))
- this->trace = *trace;
- else if (!save_trace(&this->trace))
+ if (!save_trace(&this->trace))
return 0;
depth = get_lock_depth(target);
@@ -1850,9 +1797,6 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
if (nest)
return 2;
- if (cross_lock(prev->instance))
- continue;
-
return print_deadlock_bug(curr, prev, next);
}
return 1;
@@ -2018,31 +1962,26 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
for (;;) {
int distance = curr->lockdep_depth - depth + 1;
hlock = curr->held_locks + depth - 1;
+
/*
- * Only non-crosslock entries get new dependencies added.
- * Crosslock entries will be added by commit later:
+ * Only non-recursive-read entries get new dependencies
+ * added:
*/
- if (!cross_lock(hlock->instance)) {
+ if (hlock->read != 2 && hlock->check) {
+ int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace);
+ if (!ret)
+ return 0;
+
/*
- * Only non-recursive-read entries get new dependencies
- * added:
+ * Stop after the first non-trylock entry,
+ * as non-trylock entries have added their
+ * own direct dependencies already, so this
+ * lock is connected to them indirectly:
*/
- if (hlock->read != 2 && hlock->check) {
- int ret = check_prev_add(curr, hlock, next,
- distance, &trace, save_trace);
- if (!ret)
- return 0;
-
- /*
- * Stop after the first non-trylock entry,
- * as non-trylock entries have added their
- * own direct dependencies already, so this
- * lock is connected to them indirectly:
- */
- if (!hlock->trylock)
- break;
- }
+ if (!hlock->trylock)
+ break;
}
+
depth--;
/*
* End of lock-stack?
@@ -3292,21 +3231,10 @@ static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
- cross_init(lock, 0);
__lockdep_init_map(lock, name, key, subclass);
}
EXPORT_SYMBOL_GPL(lockdep_init_map);
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-void lockdep_init_map_crosslock(struct lockdep_map *lock, const char *name,
- struct lock_class_key *key, int subclass)
-{
- cross_init(lock, 1);
- __lockdep_init_map(lock, name, key, subclass);
-}
-EXPORT_SYMBOL_GPL(lockdep_init_map_crosslock);
-#endif
-
struct lock_class_key __lockdep_no_validate__;
EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
@@ -3362,7 +3290,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int chain_head = 0;
int class_idx;
u64 chain_key;
- int ret;
if (unlikely(!debug_locks))
return 0;
@@ -3411,8 +3338,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
class_idx = class - lock_classes + 1;
- /* TODO: nest_lock is not implemented for crosslock yet. */
- if (depth && !cross_lock(lock)) {
+ if (depth) {
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
if (hlock->references) {
@@ -3500,14 +3426,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (!validate_chain(curr, lock, hlock, chain_head, chain_key))
return 0;
- ret = lock_acquire_crosslock(hlock);
- /*
- * 2 means normal acquire operations are needed. Otherwise, it's
- * ok just to return with '0:fail, 1:success'.
- */
- if (ret != 2)
- return ret;
-
curr->curr_chain_key = chain_key;
curr->lockdep_depth++;
check_chain_key(curr);
@@ -3745,19 +3663,11 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
struct task_struct *curr = current;
struct held_lock *hlock;
unsigned int depth;
- int ret, i;
+ int i;
if (unlikely(!debug_locks))
return 0;
- ret = lock_release_crosslock(lock);
- /*
- * 2 means normal release operations are needed. Otherwise, it's
- * ok just to return with '0:fail, 1:success'.
- */
- if (ret != 2)
- return ret;
-
depth = curr->lockdep_depth;
/*
* So we're all set to release this lock.. wait what lock? We don't
@@ -4675,494 +4585,3 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
dump_stack();
}
EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious);
-
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-
-/*
- * Crossrelease works by recording a lock history for each thread and
- * connecting those historic locks that were taken after the
- * wait_for_completion() in the complete() context.
- *
- * Task-A Task-B
- *
- * mutex_lock(&A);
- * mutex_unlock(&A);
- *
- * wait_for_completion(&C);
- * lock_acquire_crosslock();
- * atomic_inc_return(&cross_gen_id);
- * |
- * | mutex_lock(&B);
- * | mutex_unlock(&B);
- * |
- * | complete(&C);
- * `-- lock_commit_crosslock();
- *
- * Which will then add a dependency between B and C.
- */
-
-#define xhlock(i) (current->xhlocks[(i) % MAX_XHLOCKS_NR])
-
-/*
- * Whenever a crosslock is held, cross_gen_id will be increased.
- */
-static atomic_t cross_gen_id; /* Can be wrapped */
-
-/*
- * Make an entry of the ring buffer invalid.
- */
-static inline void invalidate_xhlock(struct hist_lock *xhlock)
-{
- /*
- * Normally, xhlock->hlock.instance must be !NULL.
- */
- xhlock->hlock.instance = NULL;
-}
-
-/*
- * Lock history stacks; we have 2 nested lock history stacks:
- *
- * HARD(IRQ)
- * SOFT(IRQ)
- *
- * The thing is that once we complete a HARD/SOFT IRQ the future task locks
- * should not depend on any of the locks observed while running the IRQ. So
- * what we do is rewind the history buffer and erase all our knowledge of that
- * temporal event.
- */
-
-void crossrelease_hist_start(enum xhlock_context_t c)
-{
- struct task_struct *cur = current;
-
- if (!cur->xhlocks)
- return;
-
- cur->xhlock_idx_hist[c] = cur->xhlock_idx;
- cur->hist_id_save[c] = cur->hist_id;
-}
-
-void crossrelease_hist_end(enum xhlock_context_t c)
-{
- struct task_struct *cur = current;
-
- if (cur->xhlocks) {
- unsigned int idx = cur->xhlock_idx_hist[c];
- struct hist_lock *h = &xhlock(idx);
-
- cur->xhlock_idx = idx;
-
- /* Check if the ring was overwritten. */
- if (h->hist_id != cur->hist_id_save[c])
- invalidate_xhlock(h);
- }
-}
-
-/*
- * lockdep_invariant_state() is used to annotate independence inside a task, to
- * make one task look like multiple independent 'tasks'.
- *
- * Take for instance workqueues; each work is independent of the last. The
- * completion of a future work does not depend on the completion of a past work
- * (in general). Therefore we must not carry that (lock) dependency across
- * works.
- *
- * This is true for many things; pretty much all kthreads fall into this
- * pattern, where they have an invariant state and future completions do not
- * depend on past completions. Its just that since they all have the 'same'
- * form -- the kthread does the same over and over -- it doesn't typically
- * matter.
- *
- * The same is true for system-calls, once a system call is completed (we've
- * returned to userspace) the next system call does not depend on the lock
- * history of the previous system call.
- *
- * They key property for independence, this invariant state, is that it must be
- * a point where we hold no locks and have no history. Because if we were to
- * hold locks, the restore at _end() would not necessarily recover it's history
- * entry. Similarly, independence per-definition means it does not depend on
- * prior state.
- */
-void lockdep_invariant_state(bool force)
-{
- /*
- * We call this at an invariant point, no current state, no history.
- * Verify the former, enforce the latter.
- */
- WARN_ON_ONCE(!force && current->lockdep_depth);
- invalidate_xhlock(&xhlock(current->xhlock_idx));
-}
-
-static int cross_lock(struct lockdep_map *lock)
-{
- return lock ? lock->cross : 0;
-}
-
-/*
- * This is needed to decide the relationship between wrapable variables.
- */
-static inline int before(unsigned int a, unsigned int b)
-{
- return (int)(a - b) < 0;
-}
-
-static inline struct lock_class *xhlock_class(struct hist_lock *xhlock)
-{
- return hlock_class(&xhlock->hlock);
-}
-
-static inline struct lock_class *xlock_class(struct cross_lock *xlock)
-{
- return hlock_class(&xlock->hlock);
-}
-
-/*
- * Should we check a dependency with previous one?
- */
-static inline int depend_before(struct held_lock *hlock)
-{
- return hlock->read != 2 && hlock->check && !hlock->trylock;
-}
-
-/*
- * Should we check a dependency with next one?
- */
-static inline int depend_after(struct held_lock *hlock)
-{
- return hlock->read != 2 && hlock->check;
-}
-
-/*
- * Check if the xhlock is valid, which would be false if,
- *
- * 1. Has not used after initializaion yet.
- * 2. Got invalidated.
- *
- * Remind hist_lock is implemented as a ring buffer.
- */
-static inline int xhlock_valid(struct hist_lock *xhlock)
-{
- /*
- * xhlock->hlock.instance must be !NULL.
- */
- return !!xhlock->hlock.instance;
-}
-
-/*
- * Record a hist_lock entry.
- *
- * Irq disable is only required.
- */
-static void add_xhlock(struct held_lock *hlock)
-{
- unsigned int idx = ++current->xhlock_idx;
- struct hist_lock *xhlock = &xhlock(idx);
-
-#ifdef CONFIG_DEBUG_LOCKDEP
- /*
- * This can be done locklessly because they are all task-local
- * state, we must however ensure IRQs are disabled.
- */
- WARN_ON_ONCE(!irqs_disabled());
-#endif
-
- /* Initialize hist_lock's members */
- xhlock->hlock = *hlock;
- xhlock->hist_id = ++current->hist_id;
-
- xhlock->trace.nr_entries = 0;
- xhlock->trace.max_entries = MAX_XHLOCK_TRACE_ENTRIES;
- xhlock->trace.entries = xhlock->trace_entries;
-
- if (crossrelease_fullstack) {
- xhlock->trace.skip = 3;
- save_stack_trace(&xhlock->trace);
- } else {
- xhlock->trace.nr_entries = 1;
- xhlock->trace.entries[0] = hlock->acquire_ip;
- }
-}
-
-static inline int same_context_xhlock(struct hist_lock *xhlock)
-{
- return xhlock->hlock.irq_context == task_irq_context(current);
-}
-
-/*
- * This should be lockless as far as possible because this would be
- * called very frequently.
- */
-static void check_add_xhlock(struct held_lock *hlock)
-{
- /*
- * Record a hist_lock, only in case that acquisitions ahead
- * could depend on the held_lock. For example, if the held_lock
- * is trylock then acquisitions ahead never depends on that.
- * In that case, we don't need to record it. Just return.
- */
- if (!current->xhlocks || !depend_before(hlock))
- return;
-
- add_xhlock(hlock);
-}
-
-/*
- * For crosslock.
- */
-static int add_xlock(struct held_lock *hlock)
-{
- struct cross_lock *xlock;
- unsigned int gen_id;
-
- if (!graph_lock())
- return 0;
-
- xlock = &((struct lockdep_map_cross *)hlock->instance)->xlock;
-
- /*
- * When acquisitions for a crosslock are overlapped, we use
- * nr_acquire to perform commit for them, based on cross_gen_id
- * of the first acquisition, which allows to add additional
- * dependencies.
- *
- * Moreover, when no acquisition of a crosslock is in progress,
- * we should not perform commit because the lock might not exist
- * any more, which might cause incorrect memory access. So we
- * have to track the number of acquisitions of a crosslock.
- *
- * depend_after() is necessary to initialize only the first
- * valid xlock so that the xlock can be used on its commit.
- */
- if (xlock->nr_acquire++ && depend_after(&xlock->hlock))
- goto unlock;
-
- gen_id = (unsigned int)atomic_inc_return(&cross_gen_id);
- xlock->hlock = *hlock;
- xlock->hlock.gen_id = gen_id;
-unlock:
- graph_unlock();
- return 1;
-}
-
-/*
- * Called for both normal and crosslock acquires. Normal locks will be
- * pushed on the hist_lock queue. Cross locks will record state and
- * stop regular lock_acquire() to avoid being placed on the held_lock
- * stack.
- *
- * Return: 0 - failure;
- * 1 - crosslock, done;
- * 2 - normal lock, continue to held_lock[] ops.
- */
-static int lock_acquire_crosslock(struct held_lock *hlock)
-{
- /*
- * CONTEXT 1 CONTEXT 2
- * --------- ---------
- * lock A (cross)
- * X = atomic_inc_return(&cross_gen_id)
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- * Y = atomic_read_acquire(&cross_gen_id)
- * lock B
- *
- * atomic_read_acquire() is for ordering between A and B,
- * IOW, A happens before B, when CONTEXT 2 see Y >= X.
- *
- * Pairs with atomic_inc_return() in add_xlock().
- */
- hlock->gen_id = (unsigned int)atomic_read_acquire(&cross_gen_id);
-
- if (cross_lock(hlock->instance))
- return add_xlock(hlock);
-
- check_add_xhlock(hlock);
- return 2;
-}
-
-static int copy_trace(struct stack_trace *trace)
-{
- unsigned long *buf = stack_trace + nr_stack_trace_entries;
- unsigned int max_nr = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
- unsigned int nr = min(max_nr, trace->nr_entries);
-
- trace->nr_entries = nr;
- memcpy(buf, trace->entries, nr * sizeof(trace->entries[0]));
- trace->entries = buf;
- nr_stack_trace_entries += nr;
-
- if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
- if (!debug_locks_off_graph_unlock())
- return 0;
-
- print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!");
- dump_stack();
-
- return 0;
- }
-
- return 1;
-}
-
-static int commit_xhlock(struct cross_lock *xlock, struct hist_lock *xhlock)
-{
- unsigned int xid, pid;
- u64 chain_key;
-
- xid = xlock_class(xlock) - lock_classes;
- chain_key = iterate_chain_key((u64)0, xid);
- pid = xhlock_class(xhlock) - lock_classes;
- chain_key = iterate_chain_key(chain_key, pid);
-
- if (lookup_chain_cache(chain_key))
- return 1;
-
- if (!add_chain_cache_classes(xid, pid, xhlock->hlock.irq_context,
- chain_key))
- return 0;
-
- if (!check_prev_add(current, &xlock->hlock, &xhlock->hlock, 1,
- &xhlock->trace, copy_trace))
- return 0;
-
- return 1;
-}
-
-static void commit_xhlocks(struct cross_lock *xlock)
-{
- unsigned int cur = current->xhlock_idx;
- unsigned int prev_hist_id = xhlock(cur).hist_id;
- unsigned int i;
-
- if (!graph_lock())
- return;
-
- if (xlock->nr_acquire) {
- for (i = 0; i < MAX_XHLOCKS_NR; i++) {
- struct hist_lock *xhlock = &xhlock(cur - i);
-
- if (!xhlock_valid(xhlock))
- break;
-
- if (before(xhlock->hlock.gen_id, xlock->hlock.gen_id))
- break;
-
- if (!same_context_xhlock(xhlock))
- break;
-
- /*
- * Filter out the cases where the ring buffer was
- * overwritten and the current entry has a bigger
- * hist_id than the previous one, which is impossible
- * otherwise:
- */
- if (unlikely(before(prev_hist_id, xhlock->hist_id)))
- break;
-
- prev_hist_id = xhlock->hist_id;
-
- /*
- * commit_xhlock() returns 0 with graph_lock already
- * released if fail.
- */
- if (!commit_xhlock(xlock, xhlock))
- return;
- }
- }
-
- graph_unlock();
-}
-
-void lock_commit_crosslock(struct lockdep_map *lock)
-{
- struct cross_lock *xlock;
- unsigned long flags;
-
- if (unlikely(!debug_locks || current->lockdep_recursion))
- return;
-
- if (!current->xhlocks)
- return;
-
- /*
- * Do commit hist_locks with the cross_lock, only in case that
- * the cross_lock could depend on acquisitions after that.
- *
- * For example, if the cross_lock does not have the 'check' flag
- * then we don't need to check dependencies and commit for that.
- * Just skip it. In that case, of course, the cross_lock does
- * not depend on acquisitions ahead, either.
- *
- * WARNING: Don't do that in add_xlock() in advance. When an
- * acquisition context is different from the commit context,
- * invalid(skipped) cross_lock might be accessed.
- */
- if (!depend_after(&((struct lockdep_map_cross *)lock)->xlock.hlock))
- return;
-
- raw_local_irq_save(flags);
- check_flags(flags);
- current->lockdep_recursion = 1;
- xlock = &((struct lockdep_map_cross *)lock)->xlock;
- commit_xhlocks(xlock);
- current->lockdep_recursion = 0;
- raw_local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(lock_commit_crosslock);
-
-/*
- * Return: 0 - failure;
- * 1 - crosslock, done;
- * 2 - normal lock, continue to held_lock[] ops.
- */
-static int lock_release_crosslock(struct lockdep_map *lock)
-{
- if (cross_lock(lock)) {
- if (!graph_lock())
- return 0;
- ((struct lockdep_map_cross *)lock)->xlock.nr_acquire--;
- graph_unlock();
- return 1;
- }
- return 2;
-}
-
-static void cross_init(struct lockdep_map *lock, int cross)
-{
- if (cross)
- ((struct lockdep_map_cross *)lock)->xlock.nr_acquire = 0;
-
- lock->cross = cross;
-
- /*
- * Crossrelease assumes that the ring buffer size of xhlocks
- * is aligned with power of 2. So force it on build.
- */
- BUILD_BUG_ON(MAX_XHLOCKS_NR & (MAX_XHLOCKS_NR - 1));
-}
-
-void lockdep_init_task(struct task_struct *task)
-{
- int i;
-
- task->xhlock_idx = UINT_MAX;
- task->hist_id = 0;
-
- for (i = 0; i < XHLOCK_CTX_NR; i++) {
- task->xhlock_idx_hist[i] = UINT_MAX;
- task->hist_id_save[i] = 0;
- }
-
- task->xhlocks = kzalloc(sizeof(struct hist_lock) * MAX_XHLOCKS_NR,
- GFP_KERNEL);
-}
-
-void lockdep_free_task(struct task_struct *task)
-{
- if (task->xhlocks) {
- void *tmp = task->xhlocks;
- /* Diable crossrelease for current */
- task->xhlocks = NULL;
- kfree(tmp);
- }
-}
-#endif
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 1fd1a7543cdd..936f3d14dd6b 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -66,12 +66,8 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock) \
break; \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- while ((lock)->break_lock) \
- arch_##op##_relax(&lock->raw_lock); \
+ arch_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
} \
\
unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
@@ -86,12 +82,9 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
local_irq_restore(flags); \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- while ((lock)->break_lock) \
- arch_##op##_relax(&lock->raw_lock); \
+ arch_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
+ \
return flags; \
} \
\
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 5d81206a572d..b9006617710f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3141,9 +3141,6 @@ void dump_stack_print_info(const char *log_lvl)
void show_regs_print_info(const char *log_lvl)
{
dump_stack_print_info(log_lvl);
-
- printk("%stask: %p task.stack: %p\n",
- log_lvl, current, task_stack_page(current));
}
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 75554f366fd3..644fa2e3d993 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5097,17 +5097,6 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
return ret;
}
-/**
- * sys_sched_rr_get_interval - return the default timeslice of a process.
- * @pid: pid of the process.
- * @interval: userspace pointer to the timeslice value.
- *
- * this syscall writes the default timeslice value of a given process
- * into the user-space timespec buffer. A value of '0' means infinity.
- *
- * Return: On success, 0 and the timeslice is in @interval. Otherwise,
- * an error code.
- */
static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
{
struct task_struct *p;
@@ -5144,6 +5133,17 @@ out_unlock:
return retval;
}
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
+ */
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
struct timespec __user *, interval)
{
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4037e19bbca2..2fe3aa853e4d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3413,9 +3413,9 @@ void set_task_rq_fair(struct sched_entity *se,
* _IFF_ we look at the pure running and runnable sums. Because they
* represent the very same entity, just at different points in the hierarchy.
*
- *
- * Per the above update_tg_cfs_util() is trivial (and still 'wrong') and
- * simply copies the running sum over.
+ * Per the above update_tg_cfs_util() is trivial and simply copies the running
+ * sum over (but still wrong, because the group entity and group rq do not have
+ * their PELT windows aligned).
*
* However, update_tg_cfs_runnable() is more complex. So we have:
*
@@ -3424,11 +3424,11 @@ void set_task_rq_fair(struct sched_entity *se,
* And since, like util, the runnable part should be directly transferable,
* the following would _appear_ to be the straight forward approach:
*
- * grq->avg.load_avg = grq->load.weight * grq->avg.running_avg (3)
+ * grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg (3)
*
* And per (1) we have:
*
- * ge->avg.running_avg == grq->avg.running_avg
+ * ge->avg.runnable_avg == grq->avg.runnable_avg
*
* Which gives:
*
@@ -3447,27 +3447,28 @@ void set_task_rq_fair(struct sched_entity *se,
* to (shortly) return to us. This only works by keeping the weights as
* integral part of the sum. We therefore cannot decompose as per (3).
*
- * OK, so what then?
+ * Another reason this doesn't work is that runnable isn't a 0-sum entity.
+ * Imagine a rq with 2 tasks that each are runnable 2/3 of the time. Then the
+ * rq itself is runnable anywhere between 2/3 and 1 depending on how the
+ * runnable section of these tasks overlap (or not). If they were to perfectly
+ * align the rq as a whole would be runnable 2/3 of the time. If however we
+ * always have at least 1 runnable task, the rq as a whole is always runnable.
*
+ * So we'll have to approximate.. :/
*
- * Another way to look at things is:
+ * Given the constraint:
*
- * grq->avg.load_avg = \Sum se->avg.load_avg
+ * ge->avg.running_sum <= ge->avg.runnable_sum <= LOAD_AVG_MAX
*
- * Therefore, per (2):
+ * We can construct a rule that adds runnable to a rq by assuming minimal
+ * overlap.
*
- * grq->avg.load_avg = \Sum se->load.weight * se->avg.runnable_avg
+ * On removal, we'll assume each task is equally runnable; which yields:
*
- * And the very thing we're propagating is a change in that sum (someone
- * joined/left). So we can easily know the runnable change, which would be, per
- * (2) the already tracked se->load_avg divided by the corresponding
- * se->weight.
+ * grq->avg.runnable_sum = grq->avg.load_sum / grq->load.weight
*
- * Basically (4) but in differential form:
+ * XXX: only do this for the part of runnable > running ?
*
- * d(runnable_avg) += se->avg.load_avg / se->load.weight
- * (5)
- * ge->avg.load_avg += ge->load.weight * d(runnable_avg)
*/
static inline void
@@ -3479,6 +3480,14 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
if (!delta)
return;
+ /*
+ * The relation between sum and avg is:
+ *
+ * LOAD_AVG_MAX - 1024 + sa->period_contrib
+ *
+ * however, the PELT windows are not aligned between grq and gse.
+ */
+
/* Set new sched_entity's utilization */
se->avg.util_avg = gcfs_rq->avg.util_avg;
se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
@@ -3491,33 +3500,68 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
static inline void
update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
- long runnable_sum = gcfs_rq->prop_runnable_sum;
- long runnable_load_avg, load_avg;
- s64 runnable_load_sum, load_sum;
+ long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
+ unsigned long runnable_load_avg, load_avg;
+ u64 runnable_load_sum, load_sum = 0;
+ s64 delta_sum;
if (!runnable_sum)
return;
gcfs_rq->prop_runnable_sum = 0;
+ if (runnable_sum >= 0) {
+ /*
+ * Add runnable; clip at LOAD_AVG_MAX. Reflects that until
+ * the CPU is saturated running == runnable.
+ */
+ runnable_sum += se->avg.load_sum;
+ runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX);
+ } else {
+ /*
+ * Estimate the new unweighted runnable_sum of the gcfs_rq by
+ * assuming all tasks are equally runnable.
+ */
+ if (scale_load_down(gcfs_rq->load.weight)) {
+ load_sum = div_s64(gcfs_rq->avg.load_sum,
+ scale_load_down(gcfs_rq->load.weight));
+ }
+
+ /* But make sure to not inflate se's runnable */
+ runnable_sum = min(se->avg.load_sum, load_sum);
+ }
+
+ /*
+ * runnable_sum can't be lower than running_sum
+ * As running sum is scale with cpu capacity wehreas the runnable sum
+ * is not we rescale running_sum 1st
+ */
+ running_sum = se->avg.util_sum /
+ arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+ runnable_sum = max(runnable_sum, running_sum);
+
load_sum = (s64)se_weight(se) * runnable_sum;
load_avg = div_s64(load_sum, LOAD_AVG_MAX);
- add_positive(&se->avg.load_sum, runnable_sum);
- add_positive(&se->avg.load_avg, load_avg);
+ delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
+ delta_avg = load_avg - se->avg.load_avg;
- add_positive(&cfs_rq->avg.load_avg, load_avg);
- add_positive(&cfs_rq->avg.load_sum, load_sum);
+ se->avg.load_sum = runnable_sum;
+ se->avg.load_avg = load_avg;
+ add_positive(&cfs_rq->avg.load_avg, delta_avg);
+ add_positive(&cfs_rq->avg.load_sum, delta_sum);
runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
+ delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum;
+ delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
- add_positive(&se->avg.runnable_load_sum, runnable_sum);
- add_positive(&se->avg.runnable_load_avg, runnable_load_avg);
+ se->avg.runnable_load_sum = runnable_sum;
+ se->avg.runnable_load_avg = runnable_load_avg;
if (se->on_rq) {
- add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg);
- add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum);
+ add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
+ add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
}
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4056c19ca3f0..665ace2fc558 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2034,8 +2034,9 @@ static void pull_rt_task(struct rq *this_rq)
bool resched = false;
struct task_struct *p;
struct rq *src_rq;
+ int rt_overload_count = rt_overloaded(this_rq);
- if (likely(!rt_overloaded(this_rq)))
+ if (likely(!rt_overload_count))
return;
/*
@@ -2044,6 +2045,11 @@ static void pull_rt_task(struct rq *this_rq)
*/
smp_rmb();
+ /* If we are the only overloaded CPU do nothing */
+ if (rt_overload_count == 1 &&
+ cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask))
+ return;
+
#ifdef HAVE_RT_PUSH_IPI
if (sched_feat(RT_PUSH_IPI)) {
tell_cpu_to_push(this_rq);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 98feab7933c7..929ecb7d6b78 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -27,7 +27,7 @@ void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq
wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&wq_head->lock, flags);
- __add_wait_queue_entry_tail(wq_head, wq_entry);
+ __add_wait_queue(wq_head, wq_entry);
spin_unlock_irqrestore(&wq_head->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 3e6fd580fe7f..ae3a2d519e50 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -164,6 +164,7 @@ config PREEMPTIRQ_EVENTS
bool "Enable trace events for preempt and irq disable/enable"
select TRACE_IRQFLAGS
depends on DEBUG_PREEMPT || !PROVE_LOCKING
+ depends on TRACING
default n
help
Enable tracing of disable and enable events for preemption and irqs.
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c5dd60cc0751..f6d2327ecb59 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -365,14 +365,13 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
.arg4_type = ARG_CONST_SIZE,
};
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
static __always_inline u64
__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
- u64 flags, struct perf_raw_record *raw)
+ u64 flags, struct perf_sample_data *sd)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
- struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd);
unsigned int cpu = smp_processor_id();
u64 index = flags & BPF_F_INDEX_MASK;
struct bpf_event_entry *ee;
@@ -395,8 +394,6 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
if (unlikely(event->oncpu != cpu))
return -EOPNOTSUPP;
- perf_sample_data_init(sd, 0, 0);
- sd->raw = raw;
perf_event_output(event, sd, regs);
return 0;
}
@@ -404,6 +401,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
u64, flags, void *, data, u64, size)
{
+ struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
struct perf_raw_record raw = {
.frag = {
.size = size,
@@ -414,7 +412,10 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
return -EINVAL;
- return __bpf_perf_event_output(regs, map, flags, &raw);
+ perf_sample_data_init(sd, 0, 0);
+ sd->raw = &raw;
+
+ return __bpf_perf_event_output(regs, map, flags, sd);
}
static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -429,10 +430,12 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
};
static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
+ struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd);
struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
struct perf_raw_frag frag = {
.copy = ctx_copy,
@@ -450,8 +453,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
};
perf_fetch_caller_regs(regs);
+ perf_sample_data_init(sd, 0, 0);
+ sd->raw = &raw;
- return __bpf_perf_event_output(regs, map, flags, &raw);
+ return __bpf_perf_event_output(regs, map, flags, sd);
}
BPF_CALL_0(bpf_get_current_task)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 91874a95060d..c87766c1c204 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1799,12 +1799,6 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
}
EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
-static __always_inline void *
-__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
-{
- return bpage->data + index;
-}
-
static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
{
return bpage->page->data + index;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 73e67b68c53b..59518b8126d0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -362,7 +362,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct
}
/**
- * trace_pid_filter_add_remove - Add or remove a task from a pid_list
+ * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list
* @pid_list: The list to modify
* @self: The current task for fork or NULL for exit
* @task: The task to add or remove
@@ -925,7 +925,7 @@ static void tracing_snapshot_instance(struct trace_array *tr)
}
/**
- * trace_snapshot - take a snapshot of the current buffer.
+ * tracing_snapshot - take a snapshot of the current buffer.
*
* This causes a swap between the snapshot buffer and the current live
* tracing buffer. You can use this to take snapshots of the live
@@ -1004,9 +1004,9 @@ int tracing_alloc_snapshot(void)
EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
/**
- * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
+ * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer.
*
- * This is similar to trace_snapshot(), but it will allocate the
+ * This is similar to tracing_snapshot(), but it will allocate the
* snapshot buffer if it isn't already allocated. Use this only
* where it is safe to sleep, as the allocation may sleep.
*
@@ -1303,7 +1303,7 @@ unsigned long __read_mostly tracing_thresh;
/*
* Copy the new maximum trace into the separate maximum-trace
* structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ * for later retrieval via /sys/kernel/tracing/tracing_max_latency)
*/
static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
@@ -2415,7 +2415,7 @@ trace_process_export(struct trace_export *export,
entry = ring_buffer_event_data(event);
size = ring_buffer_event_length(event);
- export->write(entry, size);
+ export->write(export, entry, size);
}
static DEFINE_MUTEX(ftrace_export_lock);
@@ -4178,37 +4178,30 @@ static const struct file_operations show_traces_fops = {
.llseek = seq_lseek,
};
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
static ssize_t
tracing_cpumask_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct trace_array *tr = file_inode(filp)->i_private;
+ char *mask_str;
int len;
- mutex_lock(&tracing_cpumask_update_lock);
+ len = snprintf(NULL, 0, "%*pb\n",
+ cpumask_pr_args(tr->tracing_cpumask)) + 1;
+ mask_str = kmalloc(len, GFP_KERNEL);
+ if (!mask_str)
+ return -ENOMEM;
- len = snprintf(mask_str, count, "%*pb\n",
+ len = snprintf(mask_str, len, "%*pb\n",
cpumask_pr_args(tr->tracing_cpumask));
if (len >= count) {
count = -EINVAL;
goto out_err;
}
- count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+ count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
out_err:
- mutex_unlock(&tracing_cpumask_update_lock);
+ kfree(mask_str);
return count;
}
@@ -4228,8 +4221,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (err)
goto err_unlock;
- mutex_lock(&tracing_cpumask_update_lock);
-
local_irq_disable();
arch_spin_lock(&tr->max_lock);
for_each_tracing_cpu(cpu) {
@@ -4252,8 +4243,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
local_irq_enable();
cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
- mutex_unlock(&tracing_cpumask_update_lock);
free_cpumask_var(tracing_cpumask_new);
return count;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 734accc02418..3c7bfc4bf5e9 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -209,6 +209,10 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
if (__this_cpu_read(disable_stack_tracer) != 1)
goto out;
+ /* If rcu is not watching, then save stack trace can fail */
+ if (!rcu_is_watching())
+ goto out;
+
ip += MCOUNT_INSN_SIZE;
check_stack(ip, &stack);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index ce74a4901d2b..ef1da2a5f9bd 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -192,6 +192,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
return retval;
}
+ groups_sort(group_info);
retval = set_current_groups(group_info);
put_group_info(group_info);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8fdb710bfdd7..43d18cb46308 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -38,7 +38,6 @@
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
-#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
@@ -48,6 +47,7 @@
#include <linux/nodemask.h>
#include <linux/moduleparam.h>
#include <linux/uaccess.h>
+#include <linux/sched/isolation.h>
#include "workqueue_internal.h"
@@ -1634,7 +1634,7 @@ static void worker_enter_idle(struct worker *worker)
mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
/*
- * Sanity check nr_running. Because wq_unbind_fn() releases
+ * Sanity check nr_running. Because unbind_workers() releases
* pool->lock between setting %WORKER_UNBOUND and zapping
* nr_running, the warning may trigger spuriously. Check iff
* unbind is not in progress.
@@ -4510,9 +4510,8 @@ void show_workqueue_state(void)
* cpu comes back online.
*/
-static void wq_unbind_fn(struct work_struct *work)
+static void unbind_workers(int cpu)
{
- int cpu = smp_processor_id();
struct worker_pool *pool;
struct worker *worker;
@@ -4589,16 +4588,6 @@ static void rebind_workers(struct worker_pool *pool)
spin_lock_irq(&pool->lock);
- /*
- * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED
- * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is
- * being reworked and this can go away in time.
- */
- if (!(pool->flags & POOL_DISASSOCIATED)) {
- spin_unlock_irq(&pool->lock);
- return;
- }
-
pool->flags &= ~POOL_DISASSOCIATED;
for_each_pool_worker(worker, pool) {
@@ -4709,12 +4698,13 @@ int workqueue_online_cpu(unsigned int cpu)
int workqueue_offline_cpu(unsigned int cpu)
{
- struct work_struct unbind_work;
struct workqueue_struct *wq;
/* unbinding per-cpu workers should happen on the local CPU */
- INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
- queue_work_on(cpu, system_highpri_wq, &unbind_work);
+ if (WARN_ON(cpu != smp_processor_id()))
+ return -1;
+
+ unbind_workers(cpu);
/* update NUMA affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
@@ -4722,9 +4712,6 @@ int workqueue_offline_cpu(unsigned int cpu)
wq_update_unbound_numa(wq, cpu, false);
mutex_unlock(&wq_pool_mutex);
- /* wait for per-cpu unbinding to finish */
- flush_work(&unbind_work);
- destroy_work_on_stack(&unbind_work);
return 0;
}
@@ -4957,6 +4944,10 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL))
return -ENOMEM;
+ /*
+ * Not excluding isolated cpus on purpose.
+ * If the user wishes to include them, we allow that.
+ */
cpumask_and(cpumask, cpumask, cpu_possible_mask);
if (!cpumask_empty(cpumask)) {
apply_wqattrs_lock();
@@ -5555,7 +5546,7 @@ int __init workqueue_init_early(void)
WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
- cpumask_copy(wq_unbound_cpumask, cpu_possible_mask);
+ cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_DOMAIN));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
OpenPOWER on IntegriCloud