summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c3
-rw-r--r--kernel/bpf/offload.c15
-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.c3
-rw-r--r--kernel/printk/printk.c3
-rw-r--r--kernel/sched/fair.c102
-rw-r--r--kernel/sched/wait.c2
-rw-r--r--kernel/trace/bpf_trace.c8
-rw-r--r--kernel/uid16.c1
-rw-r--r--kernel/workqueue.c33
19 files changed, 153 insertions, 77 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b9f8686a84cf..86b50aa26ee8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1447,7 +1447,8 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
rcu_read_lock();
prog = rcu_dereference(progs)->progs;
for (; *prog; prog++)
- cnt++;
+ if (*prog != &dummy_bpf_prog.prog)
+ cnt++;
rcu_read_unlock();
return cnt;
}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 68ec884440b7..8455b89d1bbf 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -1,3 +1,18 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/bug.h>
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 16beab4767e1..4df5b695bf0d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6639,6 +6639,7 @@ 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))
@@ -6649,7 +6650,7 @@ 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);
@@ -6661,6 +6662,8 @@ 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,
@@ -7987,11 +7990,11 @@ 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..670d8d7d8087 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4790,7 +4790,8 @@ void lockdep_invariant_state(bool force)
* Verify the former, enforce the latter.
*/
WARN_ON_ONCE(!force && current->lockdep_depth);
- invalidate_xhlock(&xhlock(current->xhlock_idx));
+ if (current->xhlocks)
+ invalidate_xhlock(&xhlock(current->xhlock_idx));
}
static int cross_lock(struct lockdep_map *lock)
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/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/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/bpf_trace.c b/kernel/trace/bpf_trace.c
index 27d1f4ffa3de..0ce99c379c30 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -759,6 +759,8 @@ const struct bpf_prog_ops perf_event_prog_ops = {
static DEFINE_MUTEX(bpf_event_mutex);
+#define BPF_TRACE_MAX_PROGS 64
+
int perf_event_attach_bpf_prog(struct perf_event *event,
struct bpf_prog *prog)
{
@@ -772,6 +774,12 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
goto unlock;
old_array = event->tp_event->prog_array;
+ if (old_array &&
+ bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) {
+ ret = -E2BIG;
+ goto unlock;
+ }
+
ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
if (ret < 0)
goto unlock;
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);
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-19 14:34:42 +0000