summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c14
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/bpf/verifier.c21
-rw-r--r--kernel/cgroup/cgroup-internal.h3
-rw-r--r--kernel/cgroup/cgroup.c66
-rw-r--r--kernel/cgroup/cpuset.c1
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/futex.c5
-rw-r--r--kernel/kmod.c25
-rw-r--r--kernel/pid.c3
-rw-r--r--kernel/power/snapshot.c2
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/signal.c17
-rw-r--r--kernel/time/timer.c2
-rw-r--r--kernel/trace/bpf_trace.c34
-rw-r--r--kernel/watchdog.c1
-rw-r--r--kernel/watchdog_hld.c59
-rw-r--r--kernel/workqueue.c30
18 files changed, 224 insertions, 67 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 62d686d96581..9eb8b3511636 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -66,7 +66,7 @@ static struct fsnotify_group *audit_watch_group;
/* fsnotify events we care about. */
#define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
- FS_MOVE_SELF | FS_EVENT_ON_CHILD)
+ FS_MOVE_SELF | FS_EVENT_ON_CHILD | FS_UNMOUNT)
static void audit_free_parent(struct audit_parent *parent)
{
@@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule)
list_del(&krule->rlist);
if (list_empty(&watch->rules)) {
+ /*
+ * audit_remove_watch() drops our reference to 'parent' which
+ * can get freed. Grab our own reference to be safe.
+ */
+ audit_get_parent(parent);
audit_remove_watch(watch);
-
- if (list_empty(&parent->watches)) {
- audit_get_parent(parent);
+ if (list_empty(&parent->watches))
fsnotify_destroy_mark(&parent->mark, audit_watch_group);
- audit_put_parent(parent);
- }
+ audit_put_parent(parent);
}
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 045646da97cc..6c772adabad2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1289,7 +1289,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info_len = min_t(u32, sizeof(info), info_len);
if (copy_from_user(&info, uinfo, info_len))
- return err;
+ return -EFAULT;
info.type = prog->type;
info.id = prog->aux->id;
@@ -1312,7 +1312,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
ulen = info.xlated_prog_len;
- info.xlated_prog_len = bpf_prog_size(prog->len);
+ info.xlated_prog_len = bpf_prog_insn_size(prog);
if (info.xlated_prog_len && ulen) {
uinsns = u64_to_user_ptr(info.xlated_prog_insns);
ulen = min_t(u32, info.xlated_prog_len, ulen);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index af9e84a4944e..664d93972373 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1865,10 +1865,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
* do our normal operations to the register, we need to set the values
* to the min/max since they are undefined.
*/
- if (min_val == BPF_REGISTER_MIN_RANGE)
- dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- if (max_val == BPF_REGISTER_MAX_RANGE)
- dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+ if (opcode != BPF_SUB) {
+ if (min_val == BPF_REGISTER_MIN_RANGE)
+ dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+ if (max_val == BPF_REGISTER_MAX_RANGE)
+ dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+ }
switch (opcode) {
case BPF_ADD:
@@ -1879,10 +1881,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_SUB:
+ /* If one of our values was at the end of our ranges, then the
+ * _opposite_ value in the dst_reg goes to the end of our range.
+ */
+ if (min_val == BPF_REGISTER_MIN_RANGE)
+ dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+ if (max_val == BPF_REGISTER_MAX_RANGE)
+ dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
- dst_reg->min_value -= min_val;
+ dst_reg->min_value -= max_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
- dst_reg->max_value -= max_val;
+ dst_reg->max_value -= min_val;
dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_MUL:
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 793565c05742..8b4c3c2f2509 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -33,6 +33,9 @@ struct cgroup_taskset {
struct list_head src_csets;
struct list_head dst_csets;
+ /* the number of tasks in the set */
+ int nr_tasks;
+
/* the subsys currently being processed */
int ssid;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 620794a20a33..df2e0f14a95d 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2006,6 +2006,8 @@ static void cgroup_migrate_add_task(struct task_struct *task,
if (!cset->mg_src_cgrp)
return;
+ mgctx->tset.nr_tasks++;
+
list_move_tail(&task->cg_list, &cset->mg_tasks);
if (list_empty(&cset->mg_node))
list_add_tail(&cset->mg_node,
@@ -2094,21 +2096,19 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
struct css_set *cset, *tmp_cset;
int ssid, failed_ssid, ret;
- /* methods shouldn't be called if no task is actually migrating */
- if (list_empty(&tset->src_csets))
- return 0;
-
/* check that we can legitimately attach to the cgroup */
- do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
- if (ss->can_attach) {
- tset->ssid = ssid;
- ret = ss->can_attach(tset);
- if (ret) {
- failed_ssid = ssid;
- goto out_cancel_attach;
+ if (tset->nr_tasks) {
+ do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+ if (ss->can_attach) {
+ tset->ssid = ssid;
+ ret = ss->can_attach(tset);
+ if (ret) {
+ failed_ssid = ssid;
+ goto out_cancel_attach;
+ }
}
- }
- } while_each_subsys_mask();
+ } while_each_subsys_mask();
+ }
/*
* Now that we're guaranteed success, proceed to move all tasks to
@@ -2137,25 +2137,29 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
*/
tset->csets = &tset->dst_csets;
- do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
- if (ss->attach) {
- tset->ssid = ssid;
- ss->attach(tset);
- }
- } while_each_subsys_mask();
+ if (tset->nr_tasks) {
+ do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+ if (ss->attach) {
+ tset->ssid = ssid;
+ ss->attach(tset);
+ }
+ } while_each_subsys_mask();
+ }
ret = 0;
goto out_release_tset;
out_cancel_attach:
- do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
- if (ssid == failed_ssid)
- break;
- if (ss->cancel_attach) {
- tset->ssid = ssid;
- ss->cancel_attach(tset);
- }
- } while_each_subsys_mask();
+ if (tset->nr_tasks) {
+ do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+ if (ssid == failed_ssid)
+ break;
+ if (ss->cancel_attach) {
+ tset->ssid = ssid;
+ ss->cancel_attach(tset);
+ }
+ } while_each_subsys_mask();
+ }
out_release_tset:
spin_lock_irq(&css_set_lock);
list_splice_init(&tset->dst_csets, &tset->src_csets);
@@ -2997,11 +3001,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
cgrp->subtree_control &= ~disable;
ret = cgroup_apply_control(cgrp);
-
cgroup_finalize_control(cgrp, ret);
+ if (ret)
+ goto out_unlock;
kernfs_activate(cgrp->kn);
- ret = 0;
out_unlock:
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
@@ -4669,6 +4673,10 @@ int __init cgroup_init(void)
if (ss->bind)
ss->bind(init_css_set.subsys[ssid]);
+
+ mutex_lock(&cgroup_mutex);
+ css_populate_dir(init_css_set.subsys[ssid]);
+ mutex_unlock(&cgroup_mutex);
}
/* init_css_set.subsys[] has been updated, re-hash */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ca8376e5008c..8d5151688504 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -63,6 +63,7 @@
#include <linux/cgroup.h>
#include <linux/wait.h>
+DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
/* See "Frequency meter" comments, below. */
diff --git a/kernel/fork.c b/kernel/fork.c
index 17921b0390b4..e075b7780421 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -807,7 +807,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm_init_aio(mm);
mm_init_owner(mm, p);
mmu_notifier_mm_init(mm);
- clear_tlb_flush_pending(mm);
+ init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
diff --git a/kernel/futex.c b/kernel/futex.c
index 16dbe4c93895..f50b434756c1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -670,13 +670,14 @@ again:
* this reference was taken by ihold under the page lock
* pinning the inode in place so i_lock was unnecessary. The
* only way for this check to fail is if the inode was
- * truncated in parallel so warn for now if this happens.
+ * truncated in parallel which is almost certainly an
+ * application bug. In such a case, just retry.
*
* We are not calling into get_futex_key_refs() in file-backed
* cases, therefore a successful atomic_inc return below will
* guarantee that get_futex_key() will still imply smp_mb(); (B).
*/
- if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+ if (!atomic_inc_not_zero(&inode->i_count)) {
rcu_read_unlock();
put_page(page);
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 6d016c5d97c8..2f37acde640b 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -71,6 +71,18 @@ static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);
/*
+ * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads
+ * running at the same time without returning. When this happens we
+ * believe you've somehow ended up with a recursive module dependency
+ * creating a loop.
+ *
+ * We have no option but to fail.
+ *
+ * Userspace should proactively try to detect and prevent these.
+ */
+#define MAX_KMOD_ALL_BUSY_TIMEOUT 5
+
+/*
modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
@@ -167,8 +179,17 @@ int __request_module(bool wait, const char *fmt, ...)
pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...",
atomic_read(&kmod_concurrent_max),
MAX_KMOD_CONCURRENT, module_name);
- wait_event_interruptible(kmod_wq,
- atomic_dec_if_positive(&kmod_concurrent_max) >= 0);
+ ret = wait_event_killable_timeout(kmod_wq,
+ atomic_dec_if_positive(&kmod_concurrent_max) >= 0,
+ MAX_KMOD_ALL_BUSY_TIMEOUT * HZ);
+ if (!ret) {
+ pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now",
+ module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT);
+ return -ETIME;
+ } else if (ret == -ERESTARTSYS) {
+ pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name);
+ return ret;
+ }
}
trace_module_request(module_name, wait, _RET_IP_);
diff --git a/kernel/pid.c b/kernel/pid.c
index 731c4e528f4e..c69c30d827e5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -575,13 +575,10 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
*/
void __init pidhash_init(void)
{
- unsigned int pidhash_size;
-
pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
HASH_EARLY | HASH_SMALL | HASH_ZERO,
&pidhash_shift, NULL,
0, 4096);
- pidhash_size = 1U << pidhash_shift;
}
void __init pidmap_init(void)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 222317721c5a..0972a8e09d08 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1650,7 +1650,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
{
unsigned long size;
- size = global_page_state(NR_SLAB_RECLAIMABLE)
+ size = global_node_page_state(NR_SLAB_RECLAIMABLE)
+ global_node_page_state(NR_ACTIVE_ANON)
+ global_node_page_state(NR_INACTIVE_ANON)
+ global_node_page_state(NR_ACTIVE_FILE)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 17c667b427b4..0869b20fba81 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2069,7 +2069,7 @@ out:
/**
* try_to_wake_up_local - try to wake up a local task with rq lock held
* @p: the thread to be awakened
- * @cookie: context's cookie for pinning
+ * @rf: request-queue flags for pinning
*
* Put @p on the run-queue if it's not already there. The caller must
* ensure that this_rq() is locked, @p is bound to this_rq() and not
diff --git a/kernel/signal.c b/kernel/signal.c
index caed9133ae52..ed804a470dcd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1194,7 +1194,11 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
recalc_sigpending_and_wake(t);
}
}
- if (action->sa.sa_handler == SIG_DFL)
+ /*
+ * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
+ * debugging to leave init killable.
+ */
+ if (action->sa.sa_handler == SIG_DFL && !t->ptrace)
t->signal->flags &= ~SIGNAL_UNKILLABLE;
ret = specific_send_sig_info(sig, info, t);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
@@ -3303,12 +3307,15 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
{
+#ifdef __BIG_ENDIAN
sigset_t set;
- int err = do_sigpending(&set, sizeof(old_sigset_t));
- if (err == 0)
- if (copy_to_user(set32, &set, sizeof(old_sigset_t)))
- err = -EFAULT;
+ int err = do_sigpending(&set, sizeof(set.sig[0]));
+ if (!err)
+ err = put_user(set.sig[0], set32);
return err;
+#else
+ return sys_rt_sigpending((sigset_t __user *)set32, sizeof(*set32));
+#endif
}
#endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 71ce3f4eead3..8f5d1bf18854 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1495,7 +1495,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
base->is_idle = false;
} else {
if (!is_max_delta)
- expires = basem + (nextevt - basej) * TICK_NSEC;
+ expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle:
*/
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 37385193a608..dc498b605d5d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -204,10 +204,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
fmt_cnt++;
}
- return __trace_printk(1/* fake ip will not be printed */, fmt,
- mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
- mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
- mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT() __BPF_ARG3_TP()
+#define __BPF_TP(...) \
+ __trace_printk(1 /* Fake ip will not be printed. */, \
+ fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...) \
+ ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_TP(arg1, ##__VA_ARGS__) \
+ : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_TP((long)arg1, ##__VA_ARGS__) \
+ : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...) \
+ ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \
+ : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \
+ : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...) \
+ ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \
+ ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \
+ : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \
+ ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \
+ : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+ return __BPF_TP_EMIT();
}
static const struct bpf_func_proto bpf_trace_printk_proto = {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 06d3389bca0d..f5d52024f6b7 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -240,6 +240,7 @@ static void set_sample_period(void)
* hardlockup detector generates a warning
*/
sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5);
+ watchdog_update_hrtimer_threshold(sample_period);
}
/* Commands for resetting the watchdog */
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 295a0d84934c..3a09ea1b1d3d 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -37,6 +37,62 @@ void arch_touch_nmi_watchdog(void)
}
EXPORT_SYMBOL(arch_touch_nmi_watchdog);
+#ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP
+static DEFINE_PER_CPU(ktime_t, last_timestamp);
+static DEFINE_PER_CPU(unsigned int, nmi_rearmed);
+static ktime_t watchdog_hrtimer_sample_threshold __read_mostly;
+
+void watchdog_update_hrtimer_threshold(u64 period)
+{
+ /*
+ * The hrtimer runs with a period of (watchdog_threshold * 2) / 5
+ *
+ * So it runs effectively with 2.5 times the rate of the NMI
+ * watchdog. That means the hrtimer should fire 2-3 times before
+ * the NMI watchdog expires. The NMI watchdog on x86 is based on
+ * unhalted CPU cycles, so if Turbo-Mode is enabled the CPU cycles
+ * might run way faster than expected and the NMI fires in a
+ * smaller period than the one deduced from the nominal CPU
+ * frequency. Depending on the Turbo-Mode factor this might be fast
+ * enough to get the NMI period smaller than the hrtimer watchdog
+ * period and trigger false positives.
+ *
+ * The sample threshold is used to check in the NMI handler whether
+ * the minimum time between two NMI samples has elapsed. That
+ * prevents false positives.
+ *
+ * Set this to 4/5 of the actual watchdog threshold period so the
+ * hrtimer is guaranteed to fire at least once within the real
+ * watchdog threshold.
+ */
+ watchdog_hrtimer_sample_threshold = period * 2;
+}
+
+static bool watchdog_check_timestamp(void)
+{
+ ktime_t delta, now = ktime_get_mono_fast_ns();
+
+ delta = now - __this_cpu_read(last_timestamp);
+ if (delta < watchdog_hrtimer_sample_threshold) {
+ /*
+ * If ktime is jiffies based, a stalled timer would prevent
+ * jiffies from being incremented and the filter would look
+ * at a stale timestamp and never trigger.
+ */
+ if (__this_cpu_inc_return(nmi_rearmed) < 10)
+ return false;
+ }
+ __this_cpu_write(nmi_rearmed, 0);
+ __this_cpu_write(last_timestamp, now);
+ return true;
+}
+#else
+static inline bool watchdog_check_timestamp(void)
+{
+ return true;
+}
+#endif
+
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
@@ -61,6 +117,9 @@ static void watchdog_overflow_callback(struct perf_event *event,
return;
}
+ if (!watchdog_check_timestamp())
+ return;
+
/* check for a hardlockup
* This is done by making sure our timer interrupt
* is incrementing. The timer interrupt should have
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a86688fabc55..ca937b0c3a96 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3577,6 +3577,13 @@ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
/* yeap, return possible CPUs in @node that @attrs wants */
cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
+
+ if (cpumask_empty(cpumask)) {
+ pr_warn_once("WARNING: workqueue cpumask: online intersect > "
+ "possible intersect\n");
+ return false;
+ }
+
return !cpumask_equal(cpumask, attrs->cpumask);
use_dfl:
@@ -3744,8 +3751,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
return -EINVAL;
/* creating multiple pwqs breaks ordering guarantee */
- if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
- return -EINVAL;
+ if (!list_empty(&wq->pwqs)) {
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+ return -EINVAL;
+
+ wq->flags &= ~__WQ_ORDERED;
+ }
ctx = apply_wqattrs_prepare(wq, attrs);
if (!ctx)
@@ -3929,6 +3940,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
+ /*
+ * Unbound && max_active == 1 used to imply ordered, which is no
+ * longer the case on NUMA machines due to per-node pools. While
+ * alloc_ordered_workqueue() is the right way to create an ordered
+ * workqueue, keep the previous behavior to avoid subtle breakages
+ * on NUMA.
+ */
+ if ((flags & WQ_UNBOUND) && max_active == 1)
+ flags |= __WQ_ORDERED;
+
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
flags |= WQ_UNBOUND;
@@ -4119,13 +4140,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
struct pool_workqueue *pwq;
/* disallow meddling with max_active for ordered workqueues */
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return;
max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
mutex_lock(&wq->mutex);
+ wq->flags &= ~__WQ_ORDERED;
wq->saved_max_active = max_active;
for_each_pwq(pwq, wq)
@@ -5253,7 +5275,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
* attributes breaks ordering guarantee. Disallow exposing ordered
* workqueues.
*/
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return -EINVAL;
wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-24 03:57:27 +0100