summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_fsnotify.c1
-rw-r--r--kernel/bpf/core.c8
-rw-r--r--kernel/bpf/verifier.c1
-rw-r--r--kernel/cgroup/cgroup.c37
-rw-r--r--kernel/dma/swiotlb.c3
-rw-r--r--kernel/events/core.c45
-rw-r--r--kernel/kexec_file.c34
-rw-r--r--kernel/kprobes.c13
-rw-r--r--kernel/power/user.c13
-rw-r--r--kernel/profile.c7
-rw-r--r--kernel/sched/core.c11
-rw-r--r--kernel/sched/deadline.c131
-rw-r--r--kernel/sched/rt.c15
-rw-r--r--kernel/signal.c8
-rw-r--r--kernel/sys_ni.c1
-rw-r--r--kernel/trace/ftrace.c10
-rw-r--r--kernel/trace/trace_events.c1
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/trace/trace_probe.c4
-rw-r--r--kernel/watchdog.c21
-rw-r--r--kernel/workqueue.c6
21 files changed, 225 insertions, 147 deletions
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index fba78047f..57404292c 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -111,6 +111,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
if (ret < 0) {
+ audit_mark->path = NULL;
fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4e5b5ae05..cbbd0168f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -66,11 +66,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
{
u8 *ptr = NULL;
- if (k >= SKF_NET_OFF)
+ if (k >= SKF_NET_OFF) {
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
- else if (k >= SKF_LL_OFF)
+ } else if (k >= SKF_LL_OFF) {
+ if (unlikely(!skb_mac_header_was_set(skb)))
+ return NULL;
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
+ }
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 30ac8ee82..694ee0b1f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3496,6 +3496,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
coerce_reg_to_size(dst_reg, 4);
}
+ __update_reg_bounds(dst_reg);
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
return 0;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4e8284d8c..a892a99eb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -677,7 +677,8 @@ struct css_set init_css_set = {
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
.threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
- .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+ .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
/*
@@ -1151,7 +1152,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
INIT_LIST_HEAD(&cset->threaded_csets);
INIT_HLIST_NODE(&cset->hlist);
INIT_LIST_HEAD(&cset->cgrp_links);
- INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_src_preload_node);
+ INIT_LIST_HEAD(&cset->mg_dst_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
/* Copy the set of subsystem state objects generated in
@@ -2455,21 +2457,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
*/
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
- LIST_HEAD(preloaded);
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
- list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
- list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+ mg_src_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_src_preload_node);
+ put_css_set_locked(cset);
+ }
- list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+ mg_dst_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
- list_del_init(&cset->mg_preload_node);
+ list_del_init(&cset->mg_dst_preload_node);
put_css_set_locked(cset);
}
@@ -2511,7 +2519,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
- if (!list_empty(&src_cset->mg_preload_node))
+ if (!list_empty(&src_cset->mg_src_preload_node))
return;
WARN_ON(src_cset->mg_src_cgrp);
@@ -2522,7 +2530,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
src_cset->mg_src_cgrp = src_cgrp;
src_cset->mg_dst_cgrp = dst_cgrp;
get_css_set(src_cset);
- list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+ list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
}
/**
@@ -2547,7 +2555,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
/* look up the dst cset for each src cset and link it to src */
list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
- mg_preload_node) {
+ mg_src_preload_node) {
struct css_set *dst_cset;
struct cgroup_subsys *ss;
int ssid;
@@ -2566,7 +2574,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
src_cset->mg_dst_cgrp = NULL;
- list_del_init(&src_cset->mg_preload_node);
+ list_del_init(&src_cset->mg_src_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
@@ -2574,8 +2582,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
src_cset->mg_dst_cset = dst_cset;
- if (list_empty(&dst_cset->mg_preload_node))
- list_add_tail(&dst_cset->mg_preload_node,
+ if (list_empty(&dst_cset->mg_dst_preload_node))
+ list_add_tail(&dst_cset->mg_dst_preload_node,
&mgctx->preloaded_dst_csets);
else
put_css_set(dst_cset);
@@ -2809,7 +2817,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
goto out_finish;
spin_lock_irq(&css_set_lock);
- list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+ list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+ mg_src_preload_node) {
struct task_struct *task, *ntask;
/* all tasks in src_csets need to be migrated */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8b1360772..b1e2ce2f9 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -594,7 +594,8 @@ found:
* unconditional bounce may prevent leaking swiotlb content (i.e.
* kernel memory) to user-space.
*/
- swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+ if (orig_addr)
+ swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
return tlb_addr;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 88dd1398a..ba66ea3ca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5719,10 +5719,10 @@ again:
if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
/*
- * Raced against perf_mmap_close() through
- * perf_event_set_output(). Try again, hope for better
- * luck.
+ * Raced against perf_mmap_close(); remove the
+ * event and try again.
*/
+ ring_buffer_attach(event, NULL);
mutex_unlock(&event->mmap_mutex);
goto again;
}
@@ -10396,14 +10396,25 @@ err_size:
goto out;
}
+static void mutex_lock_double(struct mutex *a, struct mutex *b)
+{
+ if (b < a)
+ swap(a, b);
+
+ mutex_lock(a);
+ mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
+}
+
static int
perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
{
struct ring_buffer *rb = NULL;
int ret = -EINVAL;
- if (!output_event)
+ if (!output_event) {
+ mutex_lock(&event->mmap_mutex);
goto set;
+ }
/* don't allow circular references */
if (event == output_event)
@@ -10441,8 +10452,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
event->pmu != output_event->pmu)
goto out;
+ /*
+ * Hold both mmap_mutex to serialize against perf_mmap_close(). Since
+ * output_event is already on rb->event_list, and the list iteration
+ * restarts after every removal, it is guaranteed this new event is
+ * observed *OR* if output_event is already removed, it's guaranteed we
+ * observe !rb->mmap_count.
+ */
+ mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex);
set:
- mutex_lock(&event->mmap_mutex);
/* Can't redirect output if we've got an active mmap() */
if (atomic_read(&event->mmap_count))
goto unlock;
@@ -10452,6 +10470,12 @@ set:
rb = ring_buffer_get(output_event);
if (!rb)
goto unlock;
+
+ /* did we race against perf_mmap_close() */
+ if (!atomic_read(&rb->mmap_count)) {
+ ring_buffer_put(rb);
+ goto unlock;
+ }
}
ring_buffer_attach(event, rb);
@@ -10459,20 +10483,13 @@ set:
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);
+ if (output_event)
+ mutex_unlock(&output_event->mmap_mutex);
out:
return ret;
}
-static void mutex_lock_double(struct mutex *a, struct mutex *b)
-{
- if (b < a)
- swap(a, b);
-
- mutex_lock(a);
- mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
-}
-
static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
{
bool nmi_safe = false;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 89d41c0a1..ab1934a2b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -111,40 +111,6 @@ int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
#endif
/*
- * arch_kexec_apply_relocations_add - apply relocations of type RELA
- * @pi: Purgatory to be relocated.
- * @section: Section relocations applying to.
- * @relsec: Section containing RELAs.
- * @symtab: Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section,
- const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
- pr_err("RELA relocation unsupported.\n");
- return -ENOEXEC;
-}
-
-/*
- * arch_kexec_apply_relocations - apply relocations of type REL
- * @pi: Purgatory to be relocated.
- * @section: Section relocations applying to.
- * @relsec: Section containing RELs.
- * @symtab: Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section,
- const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
- pr_err("REL relocation unsupported.\n");
- return -ENOEXEC;
-}
-
-/*
* Free up memory used by kernel, initrd, and command line. This is temporary
* memory allocation which is not needed any more after these buffers have
* been loaded into separate segments and have been copied elsewhere.
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 993b84cc1..b2f01e61f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1566,7 +1566,9 @@ static int check_kprobe_address_safe(struct kprobe *p,
preempt_disable();
/* Ensure it is not in reserved area nor out of text */
- if (!kernel_text_address((unsigned long) p->addr) ||
+ if (!(core_kernel_text((unsigned long) p->addr) ||
+ is_module_text_address((unsigned long) p->addr)) ||
+ in_gate_area_no_mm((unsigned long) p->addr) ||
within_kprobe_blacklist((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr) ||
find_bug((unsigned long)p->addr)) {
@@ -1708,11 +1710,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
/* Try to disarm and disable this/parent probe */
if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
/*
- * If kprobes_all_disarmed is set, orig_p
- * should have already been disarmed, so
- * skip unneed disarming process.
+ * Don't be lazy here. Even if 'kprobes_all_disarmed'
+ * is false, 'orig_p' might not have been armed yet.
+ * Note arm_all_kprobes() __tries__ to arm all kprobes
+ * on the best effort basis.
*/
- if (!kprobes_all_disarmed) {
+ if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
ret = disarm_kprobe(orig_p, true);
if (ret) {
p->flags &= ~KPROBE_FLAG_DISABLED;
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 2d8b60a3c..6a11154b3 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -29,6 +29,7 @@
#include "power.h"
+static bool need_wait;
#define SNAPSHOT_MINOR 231
@@ -82,7 +83,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
* Resuming. We may need to wait for the image device to
* appear.
*/
- wait_for_device_probe();
+ need_wait = true;
data->swap = -1;
data->mode = O_WRONLY;
@@ -174,6 +175,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
ssize_t res;
loff_t pg_offp = *offp & ~PAGE_MASK;
+ if (need_wait) {
+ wait_for_device_probe();
+ need_wait = false;
+ }
+
lock_system_sleep();
data = filp->private_data;
@@ -209,6 +215,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
loff_t size;
sector_t offset;
+ if (need_wait) {
+ wait_for_device_probe();
+ need_wait = false;
+ }
+
if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC)
return -ENOTTY;
if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR)
diff --git a/kernel/profile.c b/kernel/profile.c
index efa58f63d..7fc621404 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -108,6 +108,13 @@ int __ref profile_init(void)
/* only text is profiled */
prof_len = (_etext - _stext) >> prof_shift;
+
+ if (!prof_len) {
+ pr_warn("profiling shift: %u too large\n", prof_shift);
+ prof_on = 0;
+ return -EINVAL;
+ }
+
buffer_bytes = prof_len*sizeof(atomic_t);
if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 32af895bd..a03464249 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3869,20 +3869,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_prio(pi_task->prio) &&
dl_entity_preempt(&pi_task->dl, &p->dl))) {
- p->dl.dl_boosted = 1;
+ p->dl.pi_se = pi_task->dl.pi_se;
queue_flag |= ENQUEUE_REPLENISH;
- } else
- p->dl.dl_boosted = 0;
+ } else {
+ p->dl.pi_se = &p->dl;
+ }
p->sched_class = &dl_sched_class;
} else if (rt_prio(prio)) {
if (dl_prio(oldprio))
- p->dl.dl_boosted = 0;
+ p->dl.pi_se = &p->dl;
if (oldprio < prio)
queue_flag |= ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
- p->dl.dl_boosted = 0;
+ p->dl.pi_se = &p->dl;
if (rt_prio(oldprio))
p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index beec5081a..29ed5d8d3 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
return !RB_EMPTY_NODE(&dl_se->rb_node);
}
+#ifdef CONFIG_RT_MUTEXES
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+ return dl_se->pi_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+ return pi_of(dl_se) != dl_se;
+}
+#else
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+ return dl_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_SMP
static inline struct dl_bw *dl_bw_of(int i)
{
@@ -657,7 +679,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
- WARN_ON(dl_se->dl_boosted);
+ WARN_ON(is_dl_boosted(dl_se));
WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
/*
@@ -695,21 +717,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
* could happen are, typically, a entity voluntarily trying to overcome its
* runtime, or it just underestimated it during sched_setattr().
*/
-static void replenish_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
- BUG_ON(pi_se->dl_runtime <= 0);
+ BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
/*
* This could be the case for a !-dl task that is boosted.
* Just go with full inherited parameters.
*/
if (dl_se->dl_deadline == 0) {
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
if (dl_se->dl_yielded && dl_se->runtime > 0)
@@ -722,8 +743,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
* arbitrary large.
*/
while (dl_se->runtime <= 0) {
- dl_se->deadline += pi_se->dl_period;
- dl_se->runtime += pi_se->dl_runtime;
+ dl_se->deadline += pi_of(dl_se)->dl_period;
+ dl_se->runtime += pi_of(dl_se)->dl_runtime;
}
/*
@@ -737,8 +758,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
*/
if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
printk_deferred_once("sched: DL replenish lagged too much\n");
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
if (dl_se->dl_yielded)
@@ -771,8 +792,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
* task with deadline equal to period this is the same of using
* dl_period instead of dl_deadline in the equation above.
*/
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
{
u64 left, right;
@@ -794,9 +814,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
- (pi_se->dl_runtime >> DL_SCALE);
+ (pi_of(dl_se)->dl_runtime >> DL_SCALE);
return dl_time_before(right, left);
}
@@ -881,24 +901,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
* Please refer to the comments update_dl_revised_wakeup() function to find
* more about the Revised CBS rule.
*/
-static void update_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
- dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+ dl_entity_overflow(dl_se, rq_clock(rq))) {
if (unlikely(!dl_is_implicit(dl_se) &&
!dl_time_before(dl_se->deadline, rq_clock(rq)) &&
- !dl_se->dl_boosted)){
+ !is_dl_boosted(dl_se))) {
update_dl_revised_wakeup(dl_se, rq);
return;
}
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
}
@@ -997,7 +1016,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
* The task might have been boosted by someone else and might be in the
* boosting/deboosting path, its not throttled.
*/
- if (dl_se->dl_boosted)
+ if (is_dl_boosted(dl_se))
goto unlock;
/*
@@ -1025,7 +1044,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
* but do not enqueue -- wait for our wakeup to do that.
*/
if (!task_on_rq_queued(p)) {
- replenish_dl_entity(dl_se, dl_se);
+ replenish_dl_entity(dl_se);
goto unlock;
}
@@ -1115,7 +1134,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
- if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
return;
dl_se->dl_throttled = 1;
if (dl_se->runtime > 0)
@@ -1246,7 +1265,7 @@ throttle:
dl_se->dl_overrun = 1;
__dequeue_task_dl(rq, curr, 0);
- if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
if (!is_leftmost(curr, &rq->dl))
@@ -1440,8 +1459,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
}
static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
{
BUG_ON(on_dl_rq(dl_se));
@@ -1452,9 +1470,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
*/
if (flags & ENQUEUE_WAKEUP) {
task_contending(dl_se, flags);
- update_dl_entity(dl_se, pi_se);
+ update_dl_entity(dl_se);
} else if (flags & ENQUEUE_REPLENISH) {
- replenish_dl_entity(dl_se, pi_se);
+ replenish_dl_entity(dl_se);
} else if ((flags & ENQUEUE_RESTORE) &&
dl_time_before(dl_se->deadline,
rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
@@ -1471,28 +1489,40 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
- struct task_struct *pi_task = rt_mutex_get_top_task(p);
- struct sched_dl_entity *pi_se = &p->dl;
-
- /*
- * Use the scheduling parameters of the top pi-waiter task if:
- * - we have a top pi-waiter which is a SCHED_DEADLINE task AND
- * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is
- * smaller than our deadline OR we are a !SCHED_DEADLINE task getting
- * boosted due to a SCHED_DEADLINE pi-waiter).
- * Otherwise we keep our runtime and deadline.
- */
- if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
- pi_se = &pi_task->dl;
+ if (is_dl_boosted(&p->dl)) {
+ /*
+ * Because of delays in the detection of the overrun of a
+ * thread's runtime, it might be the case that a thread
+ * goes to sleep in a rt mutex with negative runtime. As
+ * a consequence, the thread will be throttled.
+ *
+ * While waiting for the mutex, this thread can also be
+ * boosted via PI, resulting in a thread that is throttled
+ * and boosted at the same time.
+ *
+ * In this case, the boost overrides the throttle.
+ */
+ if (p->dl.dl_throttled) {
+ /*
+ * The replenish timer needs to be canceled. No
+ * problem if it fires concurrently: boosted threads
+ * are ignored in dl_task_timer().
+ */
+ hrtimer_try_to_cancel(&p->dl.dl_timer);
+ p->dl.dl_throttled = 0;
+ }
} else if (!dl_prio(p->normal_prio)) {
/*
- * Special case in which we have a !SCHED_DEADLINE task
- * that is going to be deboosted, but exceeds its
- * runtime while doing so. No point in replenishing
- * it, as it's going to return back to its original
- * scheduling class after this.
+ * Special case in which we have a !SCHED_DEADLINE task that is going
+ * to be deboosted, but exceeds its runtime while doing so. No point in
+ * replenishing it, as it's going to return back to its original
+ * scheduling class after this. If it has been throttled, we need to
+ * clear the flag, otherwise the task may wake up as throttled after
+ * being boosted again with no means to replenish the runtime and clear
+ * the throttle.
*/
- BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+ p->dl.dl_throttled = 0;
+ BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
return;
}
@@ -1529,7 +1559,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
return;
}
- enqueue_dl_entity(&p->dl, pi_se, flags);
+ enqueue_dl_entity(&p->dl, flags);
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
@@ -2691,11 +2721,14 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_bw = 0;
dl_se->dl_density = 0;
- dl_se->dl_boosted = 0;
dl_se->dl_throttled = 0;
dl_se->dl_yielded = 0;
dl_se->dl_non_contending = 0;
dl_se->dl_overrun = 0;
+
+#ifdef CONFIG_RT_MUTEXES
+ dl_se->pi_se = dl_se;
+#endif
}
bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 70e8cd395..9c6c3572b 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -434,7 +434,7 @@ static inline void rt_queue_push_tasks(struct rq *rq)
#endif /* CONFIG_SMP */
static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
-static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
+static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count);
static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
@@ -516,7 +516,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
rt_se = rt_rq->tg->rt_se[cpu];
if (!rt_se) {
- dequeue_top_rt_rq(rt_rq);
+ dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
}
@@ -602,7 +602,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
- dequeue_top_rt_rq(rt_rq);
+ dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
}
static inline int rt_rq_throttled(struct rt_rq *rt_rq)
@@ -1001,7 +1001,7 @@ static void update_curr_rt(struct rq *rq)
}
static void
-dequeue_top_rt_rq(struct rt_rq *rt_rq)
+dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count)
{
struct rq *rq = rq_of_rt_rq(rt_rq);
@@ -1012,7 +1012,7 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
BUG_ON(!rq->nr_running);
- sub_nr_running(rq, rt_rq->rt_nr_running);
+ sub_nr_running(rq, count);
rt_rq->rt_queued = 0;
}
@@ -1291,18 +1291,21 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag
static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
{
struct sched_rt_entity *back = NULL;
+ unsigned int rt_nr_running;
for_each_sched_rt_entity(rt_se) {
rt_se->back = back;
back = rt_se;
}
- dequeue_top_rt_rq(rt_rq_of_se(back));
+ rt_nr_running = rt_rq_of_se(back)->rt_nr_running;
for (rt_se = back; rt_se; rt_se = rt_se->back) {
if (on_rt_rq(rt_se))
__dequeue_rt_entity(rt_se, flags);
}
+
+ dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running);
}
static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
diff --git a/kernel/signal.c b/kernel/signal.c
index 4cc3f3ba1..c79b87ac1 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1825,12 +1825,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
bool autoreap = false;
u64 utime, stime;
- BUG_ON(sig == -1);
+ WARN_ON_ONCE(sig == -1);
- /* do_notify_parent_cldstop should have been called instead. */
- BUG_ON(task_is_stopped_or_traced(tsk));
+ /* do_notify_parent_cldstop should have been called instead. */
+ WARN_ON_ONCE(task_is_stopped_or_traced(tsk));
- BUG_ON(!tsk->ptrace &&
+ WARN_ON_ONCE(!tsk->ptrace &&
(tsk->group_leader != tsk || !thread_group_empty(tsk)));
if (sig != SIGCHLD) {
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index df556175b..acd7e1221 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -257,6 +257,7 @@ COND_SYSCALL_COMPAT(keyctl);
/* mm/fadvise.c */
COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
/* mm/, CONFIG_MMU only */
COND_SYSCALL(swapon);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 998d14148..d2272fff2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2748,6 +2748,16 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
ftrace_startup_enable(command);
+ /*
+ * If ftrace is in an undefined state, we just remove ops from list
+ * to prevent the NULL pointer, instead of totally rolling it back and
+ * free trampoline, because those actions could cause further damage.
+ */
+ if (unlikely(ftrace_disabled)) {
+ __unregister_ftrace_function(ops);
+ return -ENODEV;
+ }
+
ops->flags &= ~FTRACE_OPS_FL_ADDING;
return 0;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 1ca64a929..d2f9146d1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -173,6 +173,7 @@ static int trace_define_generic_fields(void)
__generic_field(int, CPU, FILTER_CPU);
__generic_field(int, cpu, FILTER_CPU);
+ __generic_field(int, common_cpu, FILTER_CPU);
__generic_field(char *, COMM, FILTER_COMM);
__generic_field(char *, comm, FILTER_COMM);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index e25bc917e..48f85dab9 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4266,6 +4266,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
s = kstrdup(field_str, GFP_KERNEL);
if (!s) {
+ kfree(hist_data->attrs->var_defs.name[n_vars]);
+ hist_data->attrs->var_defs.name[n_vars] = NULL;
ret = -ENOMEM;
goto free;
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index e99c3ce7a..d85ee1778 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -361,7 +361,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
}
} else
ret = -EINVAL;
- } else if (strcmp(arg, "comm") == 0) {
+ } else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
if (strcmp(t->name, "string") != 0 &&
strcmp(t->name, "string_size") != 0)
return -EINVAL;
@@ -544,7 +544,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
* The default type of $comm should be "string", and it can't be
* dereferenced.
*/
- if (!t && strcmp(arg, "$comm") == 0)
+ if (!t && (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0))
t = "string";
parg->type = find_fetch_type(t, ftbl);
if (!parg->type) {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6d60701dc..44096c4f4 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -561,7 +561,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
return 0;
}
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
@@ -581,6 +581,13 @@ static void lockup_detector_reconfigure(void)
__lockup_detector_cleanup();
}
+void lockup_detector_reconfigure(void)
+{
+ mutex_lock(&watchdog_mutex);
+ __lockup_detector_reconfigure();
+ mutex_unlock(&watchdog_mutex);
+}
+
/*
* Create the watchdog thread infrastructure and configure the detector(s).
*
@@ -601,13 +608,13 @@ static __init void lockup_detector_setup(void)
return;
mutex_lock(&watchdog_mutex);
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
softlockup_initialized = true;
mutex_unlock(&watchdog_mutex);
}
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
@@ -615,9 +622,13 @@ static void lockup_detector_reconfigure(void)
watchdog_nmi_start();
cpus_read_unlock();
}
+void lockup_detector_reconfigure(void)
+{
+ __lockup_detector_reconfigure();
+}
static inline void lockup_detector_setup(void)
{
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
}
#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
@@ -657,7 +668,7 @@ static void proc_watchdog_update(void)
{
/* Remove impossible cpus to keep sysctl output clean. */
cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
}
/*
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b1bb6cb58..4ea2f7fd2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2917,10 +2917,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
if (WARN_ON(!work->func))
return false;
- if (!from_cancel) {
- lock_map_acquire(&work->lockdep_map);
- lock_map_release(&work->lockdep_map);
- }
+ lock_map_acquire(&work->lockdep_map);
+ lock_map_release(&work->lockdep_map);
if (start_flush_work(work, &barr, from_cancel)) {
wait_for_completion(&barr.done);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 13:11:10 +0000