summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_tree.c63
-rw-r--r--kernel/bpf/bpf_lru_list.c9
-rw-r--r--kernel/bpf/bpf_lru_list.h1
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/verifier.c5
-rw-r--r--kernel/cgroup/legacy_freezer.c3
-rw-r--r--kernel/events/core.c116
-rw-r--r--kernel/exit.c17
-rw-r--r--kernel/futex/core.c14
-rw-r--r--kernel/irq/chip.c8
-rw-r--r--kernel/irq/cpuhotplug.c7
-rw-r--r--kernel/irq/irq_sim.c2
-rw-r--r--kernel/kexec_handover.c29
-rw-r--r--kernel/rcu/tree.c4
-rw-r--r--kernel/sched/core.c4
-rw-r--r--kernel/sched/ext.c17
-rw-r--r--kernel/sched/ext.h2
-rw-r--r--kernel/trace/trace_functions_graph.c6
-rw-r--r--kernel/workqueue.c3
19 files changed, 193 insertions, 119 deletions
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f2f38903b2fe..b0eae2a3c895 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule)
return 0;
}
-static int compare_root(struct vfsmount *mnt, void *arg)
-{
- return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
- (unsigned long)arg;
-}
-
void audit_trim_trees(void)
{
struct list_head cursor;
@@ -683,8 +677,9 @@ void audit_trim_trees(void)
while (cursor.next != &tree_list) {
struct audit_tree *tree;
struct path path;
- struct vfsmount *root_mnt;
struct audit_node *node;
+ struct path *paths;
+ struct path array[16];
int err;
tree = container_of(cursor.next, struct audit_tree, list);
@@ -696,9 +691,9 @@ void audit_trim_trees(void)
if (err)
goto skip_it;
- root_mnt = collect_mounts(&path);
+ paths = collect_paths(&path, array, 16);
path_put(&path);
- if (IS_ERR(root_mnt))
+ if (IS_ERR(paths))
goto skip_it;
spin_lock(&hash_lock);
@@ -706,14 +701,17 @@ void audit_trim_trees(void)
struct audit_chunk *chunk = find_chunk(node);
/* this could be NULL if the watch is dying else where... */
node->index |= 1U<<31;
- if (iterate_mounts(compare_root,
- (void *)(chunk->key),
- root_mnt))
- node->index &= ~(1U<<31);
+ for (struct path *p = paths; p->dentry; p++) {
+ struct inode *inode = p->dentry->d_inode;
+ if (inode_to_key(inode) == chunk->key) {
+ node->index &= ~(1U<<31);
+ break;
+ }
+ }
}
spin_unlock(&hash_lock);
trim_marked(tree);
- drop_collected_mounts(root_mnt);
+ drop_collected_paths(paths, array);
skip_it:
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree)
put_tree(tree);
}
-static int tag_mount(struct vfsmount *mnt, void *arg)
+static int tag_mounts(struct path *paths, struct audit_tree *tree)
{
- return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+ for (struct path *p = paths; p->dentry; p++) {
+ int err = tag_chunk(p->dentry->d_inode, tree);
+ if (err)
+ return err;
+ }
+ return 0;
}
/*
@@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
{
struct audit_tree *seed = rule->tree, *tree;
struct path path;
- struct vfsmount *mnt;
+ struct path array[16];
+ struct path *paths;
int err;
rule->tree = NULL;
@@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule)
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
- mnt = collect_mounts(&path);
+ paths = collect_paths(&path, array, 16);
path_put(&path);
- if (IS_ERR(mnt)) {
- err = PTR_ERR(mnt);
+ if (IS_ERR(paths)) {
+ err = PTR_ERR(paths);
goto Err;
}
get_tree(tree);
- err = iterate_mounts(tag_mount, tree, mnt);
- drop_collected_mounts(mnt);
+ err = tag_mounts(paths, tree);
+ drop_collected_paths(paths, array);
if (!err) {
struct audit_node *node;
@@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new)
struct list_head cursor, barrier;
int failed = 0;
struct path path1, path2;
- struct vfsmount *tagged;
+ struct path array[16];
+ struct path *paths;
int err;
err = kern_path(new, 0, &path2);
if (err)
return err;
- tagged = collect_mounts(&path2);
+ paths = collect_paths(&path2, array, 16);
path_put(&path2);
- if (IS_ERR(tagged))
- return PTR_ERR(tagged);
+ if (IS_ERR(paths))
+ return PTR_ERR(paths);
err = kern_path(old, 0, &path1);
if (err) {
- drop_collected_mounts(tagged);
+ drop_collected_paths(paths, array);
return err;
}
@@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new)
continue;
}
- failed = iterate_mounts(tag_mount, tree, tagged);
+ failed = tag_mounts(paths, tree);
if (failed) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new)
list_del(&cursor);
mutex_unlock(&audit_filter_mutex);
path_put(&path1);
- drop_collected_mounts(tagged);
+ drop_collected_paths(paths, array);
return failed;
}
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
index 3dabdd137d10..2d6e1c98d8ad 100644
--- a/kernel/bpf/bpf_lru_list.c
+++ b/kernel/bpf/bpf_lru_list.c
@@ -337,12 +337,12 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru,
list) {
__bpf_lru_node_move_to_free(l, node, local_free_list(loc_l),
BPF_LRU_LOCAL_LIST_T_FREE);
- if (++nfree == LOCAL_FREE_TARGET)
+ if (++nfree == lru->target_free)
break;
}
- if (nfree < LOCAL_FREE_TARGET)
- __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree,
+ if (nfree < lru->target_free)
+ __bpf_lru_list_shrink(lru, l, lru->target_free - nfree,
local_free_list(loc_l),
BPF_LRU_LOCAL_LIST_T_FREE);
@@ -577,6 +577,9 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,
list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
buf += elem_size;
}
+
+ lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2,
+ 1, LOCAL_FREE_TARGET);
}
static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf,
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index cbd8d3720c2b..fe2661a58ea9 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -58,6 +58,7 @@ struct bpf_lru {
del_from_htab_func del_from_htab;
void *del_arg;
unsigned int hash_offset;
+ unsigned int target_free;
unsigned int nr_scans;
bool percpu;
};
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9122c39870bf..f4885514f007 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -2134,7 +2134,7 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a7d6e0c5928b..169845710c7e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7027,8 +7027,7 @@ BTF_TYPE_SAFE_TRUSTED(struct file) {
struct inode *f_inode;
};
-BTF_TYPE_SAFE_TRUSTED(struct dentry) {
- /* no negative dentry-s in places where bpf can see it */
+BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) {
struct inode *d_inode;
};
@@ -7066,7 +7065,6 @@ static bool type_is_trusted(struct bpf_verifier_env *env,
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file));
- BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted");
}
@@ -7076,6 +7074,7 @@ static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
const char *field_name, u32 btf_id)
{
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
+ BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
"__safe_trusted_or_null");
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 039d1eb2f215..507b8f19a262 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -188,13 +188,12 @@ static void freezer_attach(struct cgroup_taskset *tset)
if (!(freezer->state & CGROUP_FREEZING)) {
__thaw_task(task);
} else {
- freeze_task(task);
-
/* clear FROZEN and propagate upwards */
while (freezer && (freezer->state & CGROUP_FROZEN)) {
freezer->state &= ~CGROUP_FROZEN;
freezer = parent_freezer(freezer);
}
+ freeze_task(task);
}
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f34c99f8ce8f..1f746469fda5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,19 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
__perf_ctx_unlock(&cpuctx->ctx);
}
+typedef struct {
+ struct perf_cpu_context *cpuctx;
+ struct perf_event_context *ctx;
+} class_perf_ctx_lock_t;
+
+static inline void class_perf_ctx_lock_destructor(class_perf_ctx_lock_t *_T)
+{ perf_ctx_unlock(_T->cpuctx, _T->ctx); }
+
+static inline class_perf_ctx_lock_t
+class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{ perf_ctx_lock(cpuctx, ctx); return (class_perf_ctx_lock_t){ cpuctx, ctx }; }
+
#define TASK_TOMBSTONE ((void *)-1L)
static bool is_kernel_event(struct perf_event *event)
@@ -944,7 +957,13 @@ static void perf_cgroup_switch(struct task_struct *task)
if (READ_ONCE(cpuctx->cgrp) == cgrp)
return;
- perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+ guard(perf_ctx_lock)(cpuctx, cpuctx->task_ctx);
+ /*
+ * Re-check, could've raced vs perf_remove_from_context().
+ */
+ if (READ_ONCE(cpuctx->cgrp) == NULL)
+ return;
+
perf_ctx_disable(&cpuctx->ctx, true);
ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +981,6 @@ static void perf_cgroup_switch(struct task_struct *task)
ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
perf_ctx_enable(&cpuctx->ctx, true);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
static int perf_cgroup_ensure_storage(struct perf_event *event,
@@ -2120,18 +2138,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
if (event->group_leader == event)
del_event_from_groups(event, ctx);
- /*
- * If event was in error state, then keep it
- * that way, otherwise bogus counts will be
- * returned on read(). The only way to get out
- * of error state is by explicit re-enabling
- * of the event
- */
- if (event->state > PERF_EVENT_STATE_OFF) {
- perf_cgroup_event_disable(event, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_OFF);
- }
-
ctx->generation++;
event->pmu_ctx->nr_events--;
}
@@ -2149,8 +2155,9 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
}
static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
- struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+ struct perf_event_context *ctx,
+ enum perf_event_state state);
static void perf_put_aux_event(struct perf_event *event)
{
@@ -2183,8 +2190,7 @@ static void perf_put_aux_event(struct perf_event *event)
* state so that we don't try to schedule it again. Note
* that perf_event_enable() will clear the ERROR status.
*/
- event_sched_out(iter, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+ __event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
}
}
@@ -2242,18 +2248,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
&event->pmu_ctx->flexible_active;
}
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
- event_sched_out(event, event->ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
static void perf_group_detach(struct perf_event *event)
{
struct perf_event *leader = event->group_leader;
@@ -2289,8 +2283,15 @@ static void perf_group_detach(struct perf_event *event)
*/
list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
+ /*
+ * Events that have PERF_EV_CAP_SIBLING require being part of
+ * a group and cannot exist on their own, schedule them out
+ * and move them into the ERROR state. Also see
+ * _perf_event_enable(), it will not be able to recover this
+ * ERROR state.
+ */
if (sibling->event_caps & PERF_EV_CAP_SIBLING)
- perf_remove_sibling_event(sibling);
+ __event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
sibling->group_leader = sibling;
list_del_init(&sibling->sibling_list);
@@ -2493,11 +2494,14 @@ __perf_remove_from_context(struct perf_event *event,
state = PERF_EVENT_STATE_EXIT;
if (flags & DETACH_REVOKE)
state = PERF_EVENT_STATE_REVOKED;
- if (flags & DETACH_DEAD) {
- event->pending_disable = 1;
+ if (flags & DETACH_DEAD)
state = PERF_EVENT_STATE_DEAD;
- }
+
event_sched_out(event, ctx);
+
+ if (event->state > PERF_EVENT_STATE_OFF)
+ perf_cgroup_event_disable(event, ctx);
+
perf_event_set_state(event, min(event->state, state));
if (flags & DETACH_GROUP)
@@ -2562,6 +2566,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
event_function_call(event, __perf_remove_from_context, (void *)flags);
}
+static void __event_disable(struct perf_event *event,
+ struct perf_event_context *ctx,
+ enum perf_event_state state)
+{
+ event_sched_out(event, ctx);
+ perf_cgroup_event_disable(event, ctx);
+ perf_event_set_state(event, state);
+}
+
/*
* Cross CPU call to disable a performance event
*/
@@ -2576,13 +2589,18 @@ static void __perf_event_disable(struct perf_event *event,
perf_pmu_disable(event->pmu_ctx->pmu);
ctx_time_update_event(ctx, event);
+ /*
+ * When disabling a group leader, the whole group becomes ineligible
+ * to run, so schedule out the full group.
+ */
if (event == event->group_leader)
group_sched_out(event, ctx);
- else
- event_sched_out(event, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_OFF);
- perf_cgroup_event_disable(event, ctx);
+ /*
+ * But only mark the leader OFF; the siblings will remain
+ * INACTIVE.
+ */
+ __event_disable(event, ctx, PERF_EVENT_STATE_OFF);
perf_pmu_enable(event->pmu_ctx->pmu);
}
@@ -2656,8 +2674,8 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
static void perf_event_throttle(struct perf_event *event)
{
- event->pmu->stop(event, 0);
event->hw.interrupts = MAX_INTERRUPTS;
+ event->pmu->stop(event, 0);
if (event == event->group_leader)
perf_log_throttle(event, 0);
}
@@ -7439,6 +7457,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
if (!regs)
return 0;
+ /* No mm, no stack, no dump. */
+ if (!current->mm)
+ return 0;
+
/*
* Check if we fit in with the requested stack size into the:
* - TASK_SIZE
@@ -8150,6 +8172,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
const u32 max_stack = event->attr.sample_max_stack;
struct perf_callchain_entry *callchain;
+ if (!current->mm)
+ user = false;
+
if (!kernel && !user)
return &__empty_callchain;
@@ -11749,7 +11774,12 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- if (is_sampling_event(event)) {
+ /*
+ * The throttle can be triggered in the hrtimer handler.
+ * The HRTIMER_NORESTART should be used to stop the timer,
+ * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+ */
+ if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
local64_set(&hwc->period_left, ktime_to_ns(remaining));
@@ -11804,7 +11834,8 @@ static void cpu_clock_event_start(struct perf_event *event, int flags)
static void cpu_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
- cpu_clock_event_update(event);
+ if (flags & PERF_EF_UPDATE)
+ cpu_clock_event_update(event);
}
static int cpu_clock_event_add(struct perf_event *event, int flags)
@@ -11882,7 +11913,8 @@ static void task_clock_event_start(struct perf_event *event, int flags)
static void task_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
- task_clock_event_update(event, event->ctx->time);
+ if (flags & PERF_EF_UPDATE)
+ task_clock_event_update(event, event->ctx->time);
}
static int task_clock_event_add(struct perf_event *event, int flags)
diff --git a/kernel/exit.c b/kernel/exit.c
index bd743900354c..bb184a67ac73 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -940,6 +940,15 @@ void __noreturn do_exit(long code)
taskstats_exit(tsk, group_dead);
trace_sched_process_exit(tsk, group_dead);
+ /*
+ * Since sampling can touch ->mm, make sure to stop everything before we
+ * tear it down.
+ *
+ * Also flushes inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ */
+ perf_event_exit_task(tsk);
+
exit_mm();
if (group_dead)
@@ -955,14 +964,6 @@ void __noreturn do_exit(long code)
exit_task_work(tsk);
exit_thread(tsk);
- /*
- * Flush inherited counters to the parent - before the parent
- * gets woken up by child-exit notifications.
- *
- * because of cgroup mode, must be called before cgroup_exit()
- */
- perf_event_exit_task(tsk);
-
sched_autogroup_exit_task(tsk);
cgroup_exit(tsk);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 565f9717c6ca..90d53fb0ee9e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -583,8 +583,8 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
if (futex_get_value(&node, naddr))
return -EFAULT;
- if (node != FUTEX_NO_NODE &&
- (node >= MAX_NUMNODES || !node_possible(node)))
+ if ((node != FUTEX_NO_NODE) &&
+ ((unsigned int)node >= MAX_NUMNODES || !node_possible(node)))
return -EINVAL;
}
@@ -1629,6 +1629,16 @@ again:
mm->futex_phash_new = NULL;
if (fph) {
+ if (cur && (!cur->hash_mask || cur->immutable)) {
+ /*
+ * If two threads simultaneously request the global
+ * hash then the first one performs the switch,
+ * the second one returns here.
+ */
+ free = fph;
+ mm->futex_phash_new = new;
+ return -EBUSY;
+ }
if (cur && !new) {
/*
* If we have an existing hash, but do not yet have
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b0e0a7332993..2b274007e8ba 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -205,6 +205,14 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
void irq_startup_managed(struct irq_desc *desc)
{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+
+ /*
+ * Clear managed-shutdown flag, so we don't repeat managed-startup for
+ * multiple hotplugs, and cause imbalanced disable depth.
+ */
+ irqd_clr_managed_shutdown(d);
+
/*
* Only start it up when the disable depth is 1, so that a disable,
* hotunplug, hotplug sequence does not end up enabling it during
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index f07529ae4895..755346ea9819 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -210,13 +210,6 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
!irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
return;
- /*
- * Don't restore suspended interrupts here when a system comes back
- * from S3. They are reenabled via resume_device_irqs().
- */
- if (desc->istate & IRQS_SUSPENDED)
- return;
-
if (irqd_is_managed_and_shutdown(data))
irq_startup_managed(desc);
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 1a3d483548e2..ae4c9cbd1b4b 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -202,7 +202,7 @@ struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode,
void *data)
{
struct irq_sim_work_ctx *work_ctx __free(kfree) =
- kmalloc(sizeof(*work_ctx), GFP_KERNEL);
+ kzalloc(sizeof(*work_ctx), GFP_KERNEL);
if (!work_ctx)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 69b953551677..5a21dbe17950 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -164,11 +164,21 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
}
/* almost as free_reserved_page(), just don't free the page */
-static void kho_restore_page(struct page *page)
+static void kho_restore_page(struct page *page, unsigned int order)
{
- ClearPageReserved(page);
- init_page_count(page);
- adjust_managed_page_count(page, 1);
+ unsigned int nr_pages = (1 << order);
+
+ /* Head page gets refcount of 1. */
+ set_page_count(page, 1);
+
+ /* For higher order folios, tail pages get a page count of zero. */
+ for (unsigned int i = 1; i < nr_pages; i++)
+ set_page_count(page + i, 0);
+
+ if (order > 0)
+ prep_compound_page(page, order);
+
+ adjust_managed_page_count(page, nr_pages);
}
/**
@@ -186,15 +196,10 @@ struct folio *kho_restore_folio(phys_addr_t phys)
return NULL;
order = page->private;
- if (order) {
- if (order > MAX_PAGE_ORDER)
- return NULL;
-
- prep_compound_page(page, order);
- } else {
- kho_restore_page(page);
- }
+ if (order > MAX_PAGE_ORDER)
+ return NULL;
+ kho_restore_page(page, order);
return page_folio(page);
}
EXPORT_SYMBOL_GPL(kho_restore_folio);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e8a4b720d7d2..14d4499c6fc3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3072,6 +3072,10 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
/* Misaligned rcu_head! */
WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
+ /* Avoid NULL dereference if callback is NULL. */
+ if (WARN_ON_ONCE(!func))
+ return;
+
if (debug_rcu_head_queue(head)) {
/*
* Probable double call_rcu(), so leak the callback.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dce50fa57471..8988d38d46a3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8545,7 +8545,7 @@ void __init sched_init(void)
init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_EXT_GROUP_SCHED
- root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+ scx_tg_init(&root_task_group);
#endif /* CONFIG_EXT_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -8985,7 +8985,7 @@ struct task_group *sched_create_group(struct task_group *parent)
if (!alloc_rt_sched_group(tg, parent))
goto err;
- scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+ scx_tg_init(tg);
alloc_uclamp_sched_group(tg, parent);
return tg;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2c41c78be61e..b498d867ba21 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4092,6 +4092,11 @@ bool scx_can_stop_tick(struct rq *rq)
DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
+void scx_tg_init(struct task_group *tg)
+{
+ tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
int scx_tg_online(struct task_group *tg)
{
struct scx_sched *sch = scx_root;
@@ -4241,12 +4246,12 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
percpu_down_read(&scx_cgroup_rwsem);
- if (scx_cgroup_enabled && tg->scx_weight != weight) {
- if (SCX_HAS_OP(sch, cgroup_set_weight))
- SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
- tg_cgrp(tg), weight);
- tg->scx_weight = weight;
- }
+ if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+ tg->scx_weight != weight)
+ SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+ tg_cgrp(tg), weight);
+
+ tg->scx_weight = weight;
percpu_up_read(&scx_cgroup_rwsem);
}
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 6e5072f57771..a75835c23f15 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -79,6 +79,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
#ifdef CONFIG_CGROUP_SCHED
#ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
int scx_tg_online(struct task_group *tg);
void scx_tg_offline(struct task_group *tg);
int scx_cgroup_can_attach(struct cgroup_taskset *tset);
@@ -88,6 +89,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
void scx_group_set_idle(struct task_group *tg, bool idle);
#else /* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
static inline int scx_tg_online(struct task_group *tg) { return 0; }
static inline void scx_tg_offline(struct task_group *tg) {}
static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9234e2c39abf..14d74a7491b8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -455,10 +455,16 @@ static int graph_trace_init(struct trace_array *tr)
return 0;
}
+static struct tracer graph_trace;
+
static int ftrace_graph_trace_args(struct trace_array *tr, int set)
{
trace_func_graph_ent_t entry;
+ /* Do nothing if the current tracer is not this tracer */
+ if (tr->current_trace != &graph_trace)
+ return 0;
+
if (set)
entry = trace_graph_entry_args;
else
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 97f37b5bae66..9f9148075828 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7767,7 +7767,8 @@ void __init workqueue_init_early(void)
restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
-
+ cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask,
+ housekeeping_cpumask(HK_TYPE_DOMAIN));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs();
generated by cgit (git 2.34.1) at 2025-06-26 07:42:22 +0000