summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/memalloc.c44
-rw-r--r--kernel/bpf/mprog.c13
-rw-r--r--kernel/bpf/syscall.c21
-rw-r--r--kernel/bpf/tcx.c8
-rw-r--r--kernel/bpf/verifier.c14
-rw-r--r--kernel/cgroup/cgroup-v1.c5
-rw-r--r--kernel/power/snapshot.c4
-rw-r--r--kernel/printk/printk.c8
-rw-r--r--kernel/sched/cpufreq_schedutil.c3
-rw-r--r--kernel/sched/fair.c89
-rw-r--r--kernel/workqueue.c24
11 files changed, 154 insertions, 79 deletions
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index cf1941516643..d93ddac283d4 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -965,37 +965,31 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
return !ret ? NULL : ret + LLIST_NODE_SZ;
}
-/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
static __init int bpf_mem_cache_adjust_size(void)
{
- unsigned int size, index;
+ unsigned int size;
- /* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
- * up-to 256-bytes.
+ /* Adjusting the indexes in size_index() according to the object_size
+ * of underlying slab cache, so bpf_mem_alloc() will select a
+ * bpf_mem_cache with unit_size equal to the object_size of
+ * the underlying slab cache.
+ *
+ * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
+ * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
*/
- size = KMALLOC_MIN_SIZE;
- if (size <= 192)
- index = size_index[(size - 1) / 8];
- else
- index = fls(size - 1) - 1;
- for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
- size_index[(size - 1) / 8] = index;
+ for (size = 192; size >= 8; size -= 8) {
+ unsigned int kmalloc_size, index;
- /* The minimal alignment is 64-bytes, so disable 96-bytes cache and
- * use 128-bytes cache instead.
- */
- if (KMALLOC_MIN_SIZE >= 64) {
- index = size_index[(128 - 1) / 8];
- for (size = 64 + 8; size <= 96; size += 8)
- size_index[(size - 1) / 8] = index;
- }
+ kmalloc_size = kmalloc_size_roundup(size);
+ if (kmalloc_size == size)
+ continue;
- /* The minimal alignment is 128-bytes, so disable 192-bytes cache and
- * use 256-bytes cache instead.
- */
- if (KMALLOC_MIN_SIZE >= 128) {
- index = fls(256 - 1) - 1;
- for (size = 128 + 8; size <= 192; size += 8)
+ if (kmalloc_size <= 192)
+ index = size_index[(kmalloc_size - 1) / 8];
+ else
+ index = fls(kmalloc_size - 1) - 1;
+ /* Only overwrite if necessary */
+ if (size_index[(size - 1) / 8] != index)
size_index[(size - 1) / 8] = index;
}
diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
index 32d2c4829eb8..1394168062e8 100644
--- a/kernel/bpf/mprog.c
+++ b/kernel/bpf/mprog.c
@@ -253,6 +253,9 @@ int bpf_mprog_attach(struct bpf_mprog_entry *entry,
goto out;
}
idx = tidx;
+ } else if (bpf_mprog_total(entry) == bpf_mprog_max()) {
+ ret = -ERANGE;
+ goto out;
}
if (flags & BPF_F_BEFORE) {
tidx = bpf_mprog_pos_before(entry, &rtuple);
@@ -398,14 +401,16 @@ int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
struct bpf_mprog_cp *cp;
struct bpf_prog *prog;
const u32 flags = 0;
+ u32 id, count = 0;
+ u64 revision = 1;
int i, ret = 0;
- u32 id, count;
- u64 revision;
if (attr->query.query_flags || attr->query.attach_flags)
return -EINVAL;
- revision = bpf_mprog_revision(entry);
- count = bpf_mprog_total(entry);
+ if (entry) {
+ revision = bpf_mprog_revision(entry);
+ count = bpf_mprog_total(entry);
+ }
if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
return -EFAULT;
if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index eb01c31ed591..d77b2f8b9364 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3796,7 +3796,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- u32 mask;
int ret;
if (CHECK_ATTR(BPF_PROG_ATTACH))
@@ -3805,10 +3804,16 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = attach_type_to_prog_type(attr->attach_type);
if (ptype == BPF_PROG_TYPE_UNSPEC)
return -EINVAL;
- mask = bpf_mprog_supported(ptype) ?
- BPF_F_ATTACH_MASK_MPROG : BPF_F_ATTACH_MASK_BASE;
- if (attr->attach_flags & ~mask)
- return -EINVAL;
+ if (bpf_mprog_supported(ptype)) {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+ return -EINVAL;
+ } else {
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
+ return -EINVAL;
+ if (attr->relative_fd ||
+ attr->expected_revision)
+ return -EINVAL;
+ }
prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
if (IS_ERR(prog))
@@ -3878,6 +3883,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
}
+ } else if (attr->attach_flags ||
+ attr->relative_fd ||
+ attr->expected_revision) {
+ return -EINVAL;
}
switch (ptype) {
@@ -3913,7 +3922,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
return ret;
}
-#define BPF_PROG_QUERY_LAST_FIELD query.link_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.revision
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
index 13f0b5dc8262..1338a13a8b64 100644
--- a/kernel/bpf/tcx.c
+++ b/kernel/bpf/tcx.c
@@ -123,7 +123,6 @@ int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
{
bool ingress = attr->query.attach_type == BPF_TCX_INGRESS;
struct net *net = current->nsproxy->net_ns;
- struct bpf_mprog_entry *entry;
struct net_device *dev;
int ret;
@@ -133,12 +132,7 @@ int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
ret = -ENODEV;
goto out;
}
- entry = tcx_entry_fetch(dev, ingress);
- if (!entry) {
- ret = -ENOENT;
- goto out;
- }
- ret = bpf_mprog_query(attr, uattr, entry);
+ ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress));
out:
rtnl_unlock();
return ret;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb78212fa5b2..873ade146f3d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4047,11 +4047,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bitmap_from_u64(mask, bt_reg_mask(bt));
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
- if (reg->type != SCALAR_VALUE) {
- bt_clear_reg(bt, i);
- continue;
- }
- reg->precise = true;
+ bt_clear_reg(bt, i);
+ if (reg->type == SCALAR_VALUE)
+ reg->precise = true;
}
return 0;
}
@@ -14481,7 +14479,7 @@ static int check_return_code(struct bpf_verifier_env *env)
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
- struct tnum range = tnum_range(0, 1);
+ struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
struct bpf_func_state *frame = env->cur_state->frame[0];
@@ -14529,8 +14527,8 @@ static int check_return_code(struct bpf_verifier_env *env)
return -EINVAL;
}
- if (!tnum_in(tnum_const(0), reg->var_off)) {
- verbose_invalid_scalar(env, reg, &range, "async callback", "R0");
+ if (!tnum_in(const_0, reg->var_off)) {
+ verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
return -EINVAL;
}
return 0;
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index c487ffef6652..76db6c67e39a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -360,10 +360,9 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
}
css_task_iter_end(&it);
length = n;
- /* now sort & (if procs) strip out duplicates */
+ /* now sort & strip out duplicates (tgids or recycled thread PIDs) */
sort(array, length, sizeof(pid_t), cmppid, NULL);
- if (type == CGROUP_FILE_PROCS)
- length = pidlist_uniq(array, length);
+ length = pidlist_uniq(array, length);
l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 87e9f7e2bdc0..0f12e0a97e43 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -2647,7 +2647,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm,
memory_bm_free(bm, PG_UNSAFE_KEEP);
/* Make a copy of zero_bm so it can be created in safe pages */
- error = memory_bm_create(&tmp, GFP_ATOMIC, PG_ANY);
+ error = memory_bm_create(&tmp, GFP_ATOMIC, PG_SAFE);
if (error)
goto Free;
@@ -2660,7 +2660,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm,
goto Free;
duplicate_memory_bitmap(zero_bm, &tmp);
- memory_bm_free(&tmp, PG_UNSAFE_KEEP);
+ memory_bm_free(&tmp, PG_UNSAFE_CLEAR);
/* At this point zero_bm is in safe pages and it can be used for restoring. */
if (nr_highmem > 0) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 7e0b4dd02398..0b3af1529778 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3740,12 +3740,18 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
seq = prb_next_seq(prb);
+ /* Flush the consoles so that records up to @seq are printed. */
+ console_lock();
+ console_unlock();
+
for (;;) {
diff = 0;
/*
* Hold the console_lock to guarantee safe access to
- * console->seq.
+ * console->seq. Releasing console_lock flushes more
+ * records in case @seq is still not printed on all
+ * usable consoles.
*/
console_lock();
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..458d359f5991 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
* Except when the rq is capped by uclamp_max.
*/
if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
- sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+ sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+ !sg_policy->need_freq_update) {
next_f = sg_policy->next_freq;
/* Restore cached freq as next_freq has changed */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cb225921bbca..061a30a8925a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -664,6 +664,10 @@ void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
}
+/*
+ * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * For this to be so, the result of this function must have a left bias.
+ */
u64 avg_vruntime(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
@@ -677,8 +681,12 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
load += weight;
}
- if (load)
+ if (load) {
+ /* sign flips effective floor / ceil */
+ if (avg < 0)
+ avg -= (load - 1);
avg = div_s64(avg, load);
+ }
return cfs_rq->min_vruntime + avg;
}
@@ -864,14 +872,16 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
*
* Which allows an EDF like search on (sub)trees.
*/
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
{
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
+ struct sched_entity *best_left = NULL;
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
+ best = curr;
/*
* Once selected, run a task until it either becomes non-eligible or
@@ -892,33 +902,75 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
}
/*
- * If this entity has an earlier deadline than the previous
- * best, take this one. If it also has the earliest deadline
- * of its subtree, we're done.
+ * Now we heap search eligible trees for the best (min_)deadline
*/
- if (!best || deadline_gt(deadline, best, se)) {
+ if (!best || deadline_gt(deadline, best, se))
best = se;
- if (best->deadline == best->min_deadline)
- break;
- }
/*
- * If the earlest deadline in this subtree is in the fully
- * eligible left half of our space, go there.
+ * Every se in a left branch is eligible, keep track of the
+ * branch with the best min_deadline
*/
+ if (node->rb_left) {
+ struct sched_entity *left = __node_2_se(node->rb_left);
+
+ if (!best_left || deadline_gt(min_deadline, best_left, left))
+ best_left = left;
+
+ /*
+ * min_deadline is in the left branch. rb_left and all
+ * descendants are eligible, so immediately switch to the second
+ * loop.
+ */
+ if (left->min_deadline == se->min_deadline)
+ break;
+ }
+
+ /* min_deadline is at this node, no need to look right */
+ if (se->deadline == se->min_deadline)
+ break;
+
+ /* else min_deadline is in the right branch. */
+ node = node->rb_right;
+ }
+
+ /*
+ * We ran into an eligible node which is itself the best.
+ * (Or nr_running == 0 and both are NULL)
+ */
+ if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
+ return best;
+
+ /*
+ * Now best_left and all of its children are eligible, and we are just
+ * looking for deadline == min_deadline
+ */
+ node = &best_left->run_node;
+ while (node) {
+ struct sched_entity *se = __node_2_se(node);
+
+ /* min_deadline is the current node */
+ if (se->deadline == se->min_deadline)
+ return se;
+
+ /* min_deadline is in the left branch */
if (node->rb_left &&
__node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
node = node->rb_left;
continue;
}
+ /* else min_deadline is in the right branch */
node = node->rb_right;
}
+ return NULL;
+}
- if (!best || (curr && deadline_gt(deadline, best, curr)))
- best = curr;
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
+{
+ struct sched_entity *se = __pick_eevdf(cfs_rq);
- if (unlikely(!best)) {
+ if (!se) {
struct sched_entity *left = __pick_first_entity(cfs_rq);
if (left) {
pr_err("EEVDF scheduling fail, picking leftmost\n");
@@ -926,7 +978,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
}
}
- return best;
+ return se;
}
#ifdef CONFIG_SCHED_DEBUG
@@ -3605,6 +3657,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
*/
deadline = div_s64(deadline * old_weight, weight);
se->deadline = se->vruntime + deadline;
+ min_deadline_cb_propagate(&se->run_node, NULL);
}
#ifdef CONFIG_SMP
@@ -4919,10 +4972,12 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
- u64 vslice = calc_delta_fair(se->slice, se);
- u64 vruntime = avg_vruntime(cfs_rq);
+ u64 vslice, vruntime = avg_vruntime(cfs_rq);
s64 lag = 0;
+ se->slice = sysctl_sched_base_slice;
+ vslice = calc_delta_fair(se->slice, se);
+
/*
* Due to how V is constructed as the weighted average of entities,
* adding tasks with positive lag, or removing tasks with negative lag
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b9f053a5a5f0..a3522b70218d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2166,7 +2166,7 @@ static struct worker *create_worker(struct worker_pool *pool)
{
struct worker *worker;
int id;
- char id_buf[16];
+ char id_buf[23];
/* ID is needed to determine kthread name */
id = ida_alloc(&pool->worker_ida, GFP_KERNEL);
@@ -4600,12 +4600,22 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
}
cpus_read_unlock();
+ /* for unbound pwq, flush the pwq_release_worker ensures that the
+ * pwq_release_workfn() completes before calling kfree(wq).
+ */
+ if (ret)
+ kthread_flush_worker(pwq_release_worker);
+
return ret;
enomem:
if (wq->cpu_pwq) {
- for_each_possible_cpu(cpu)
- kfree(*per_cpu_ptr(wq->cpu_pwq, cpu));
+ for_each_possible_cpu(cpu) {
+ struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu);
+
+ if (pwq)
+ kmem_cache_free(pwq_cache, pwq);
+ }
free_percpu(wq->cpu_pwq);
wq->cpu_pwq = NULL;
}
@@ -5782,9 +5792,13 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
list_for_each_entry(wq, &workqueues, list) {
if (!(wq->flags & WQ_UNBOUND))
continue;
+
/* creating multiple pwqs breaks ordering guarantee */
- if (wq->flags & __WQ_ORDERED)
- continue;
+ if (!list_empty(&wq->pwqs)) {
+ if (wq->flags & __WQ_ORDERED_EXPLICIT)
+ continue;
+ wq->flags &= ~__WQ_ORDERED;
+ }
ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask);
if (IS_ERR(ctx)) {
generated by cgit (git 2.34.1) at 2025-12-16 03:39:24 +0000