summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c8
-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/crash_core.c17
-rw-r--r--kernel/dma/swiotlb.c31
-rw-r--r--kernel/events/core.c39
-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/cpupri.c1
-rw-r--r--kernel/sched/fair.c90
-rw-r--r--kernel/trace/fprobe.c6
-rw-r--r--kernel/trace/ring_buffer.c3
-rw-r--r--kernel/trace/trace_events.c1
-rw-r--r--kernel/trace/trace_events_user.c58
-rw-r--r--kernel/trace/trace_kprobe.c63
-rw-r--r--kernel/trace/trace_probe.h1
-rw-r--r--kernel/workqueue.c33
22 files changed, 357 insertions, 114 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 21d2fa815e78..6f0d6fb6523f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2212,7 +2212,7 @@ __audit_reusename(const __user char *uptr)
if (!n->name)
continue;
if (n->name->uptr == uptr) {
- n->name->refcnt++;
+ atomic_inc(&n->name->refcnt);
return n->name;
}
}
@@ -2241,7 +2241,7 @@ void __audit_getname(struct filename *name)
n->name = name;
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
static inline int audit_copy_fcaps(struct audit_names *name,
@@ -2373,7 +2373,7 @@ out_alloc:
return;
if (name) {
n->name = name;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
out:
@@ -2500,7 +2500,7 @@ void __audit_inode_child(struct inode *parent,
if (found_parent) {
found_child->name = found_parent->name;
found_child->name_len = AUDIT_NAME_FULL;
- found_child->name->refcnt++;
+ atomic_inc(&found_child->name->refcnt);
}
}
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/crash_core.c b/kernel/crash_core.c
index 03a7932cde0a..2f675ef045d4 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -740,6 +740,17 @@ subsys_initcall(crash_notes_memory_init);
#define pr_fmt(fmt) "crash hp: " fmt
/*
+ * Different than kexec/kdump loading/unloading/jumping/shrinking which
+ * usually rarely happen, there will be many crash hotplug events notified
+ * during one short period, e.g one memory board is hot added and memory
+ * regions are online. So mutex lock __crash_hotplug_lock is used to
+ * serialize the crash hotplug handling specifically.
+ */
+DEFINE_MUTEX(__crash_hotplug_lock);
+#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
+#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
+
+/*
* This routine utilized when the crash_hotplug sysfs node is read.
* It reflects the kernel's ability/permission to update the crash
* elfcorehdr directly.
@@ -748,9 +759,11 @@ int crash_check_update_elfcorehdr(void)
{
int rc = 0;
+ crash_hotplug_lock();
/* Obtain lock while reading crash information */
if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
return 0;
}
if (kexec_crash_image) {
@@ -761,6 +774,7 @@ int crash_check_update_elfcorehdr(void)
}
/* Release lock now that update complete */
kexec_unlock();
+ crash_hotplug_unlock();
return rc;
}
@@ -783,9 +797,11 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
{
struct kimage *image;
+ crash_hotplug_lock();
/* Obtain lock while changing crash information */
if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
return;
}
@@ -852,6 +868,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
out:
/* Release lock now that update complete */
kexec_unlock();
+ crash_hotplug_unlock();
}
static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 394494a6b1f3..01637677736f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -399,14 +399,13 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
}
mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
- default_nareas), SMP_CACHE_BYTES);
+ nareas), SMP_CACHE_BYTES);
if (!mem->areas) {
pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
return;
}
- swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false,
- default_nareas);
+ swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas);
add_mem_pool(&io_tlb_default_mem, mem);
if (flags & SWIOTLB_VERBOSE)
@@ -729,9 +728,6 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
}
add_mem_pool(mem, pool);
-
- /* Pairs with smp_rmb() in is_swiotlb_buffer(). */
- smp_wmb();
}
/**
@@ -1152,9 +1148,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
found:
- dev->dma_uses_io_tlb = true;
- /* Pairs with smp_rmb() in is_swiotlb_buffer() */
- smp_wmb();
+ WRITE_ONCE(dev->dma_uses_io_tlb, true);
+
+ /*
+ * The general barrier orders reads and writes against a presumed store
+ * of the SWIOTLB buffer address by a device driver (to a driver private
+ * data structure). It serves two purposes.
+ *
+ * First, the store to dev->dma_uses_io_tlb must be ordered before the
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be passed to another CPU before updating dev->dma_uses_io_tlb.
+ *
+ * Second, the load from mem->pools must be ordered before the same
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be observed by another CPU before an update of the RCU list
+ * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy
+ * atomicity).
+ *
+ * See also the comment in is_swiotlb_buffer().
+ */
+ smp_mb();
*retpool = pool;
return index;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c72a41f11af..d0663b9324e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1954,6 +1954,7 @@ static void perf_group_attach(struct perf_event *event)
list_add_tail(&event->sibling_list, &group_leader->sibling_list);
group_leader->nr_siblings++;
+ group_leader->group_generation++;
perf_event__header_size(group_leader);
@@ -2144,6 +2145,7 @@ static void perf_group_detach(struct perf_event *event)
if (leader != event) {
list_del_init(&event->sibling_list);
event->group_leader->nr_siblings--;
+ event->group_leader->group_generation++;
goto out;
}
@@ -5440,7 +5442,7 @@ static int __perf_read_group_add(struct perf_event *leader,
u64 read_format, u64 *values)
{
struct perf_event_context *ctx = leader->ctx;
- struct perf_event *sub;
+ struct perf_event *sub, *parent;
unsigned long flags;
int n = 1; /* skip @nr */
int ret;
@@ -5450,6 +5452,33 @@ static int __perf_read_group_add(struct perf_event *leader,
return ret;
raw_spin_lock_irqsave(&ctx->lock, flags);
+ /*
+ * Verify the grouping between the parent and child (inherited)
+ * events is still in tact.
+ *
+ * Specifically:
+ * - leader->ctx->lock pins leader->sibling_list
+ * - parent->child_mutex pins parent->child_list
+ * - parent->ctx->mutex pins parent->sibling_list
+ *
+ * Because parent->ctx != leader->ctx (and child_list nests inside
+ * ctx->mutex), group destruction is not atomic between children, also
+ * see perf_event_release_kernel(). Additionally, parent can grow the
+ * group.
+ *
+ * Therefore it is possible to have parent and child groups in a
+ * different configuration and summing over such a beast makes no sense
+ * what so ever.
+ *
+ * Reject this.
+ */
+ parent = leader->parent;
+ if (parent &&
+ (parent->group_generation != leader->group_generation ||
+ parent->nr_siblings != leader->nr_siblings)) {
+ ret = -ECHILD;
+ goto unlock;
+ }
/*
* Since we co-schedule groups, {enabled,running} times of siblings
@@ -5483,8 +5512,9 @@ static int __perf_read_group_add(struct perf_event *leader,
values[n++] = atomic64_read(&sub->lost_samples);
}
+unlock:
raw_spin_unlock_irqrestore(&ctx->lock, flags);
- return 0;
+ return ret;
}
static int perf_read_group(struct perf_event *event,
@@ -5503,10 +5533,6 @@ static int perf_read_group(struct perf_event *event,
values[0] = 1 + leader->nr_siblings;
- /*
- * By locking the child_mutex of the leader we effectively
- * lock the child list of all siblings.. XXX explain how.
- */
mutex_lock(&leader->child_mutex);
ret = __perf_read_group_add(leader, read_format, values);
@@ -13346,6 +13372,7 @@ static int inherit_group(struct perf_event *parent_event,
!perf_get_aux_event(child_ctr, leader))
return -EINVAL;
}
+ leader->group_generation = parent_event->group_generation;
return 0;
}
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/cpupri.c b/kernel/sched/cpupri.c
index a286e726eb4b..42c40cfdf836 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
+ cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
/*
* We have to ensure that we have at least one bit
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cb225921bbca..df348aa55d3c 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 +3657,8 @@ 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;
+ if (se != cfs_rq->curr)
+ min_deadline_cb_propagate(&se->run_node, NULL);
}
#ifdef CONFIG_SMP
@@ -4919,10 +4973,12 @@ 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/trace/fprobe.c b/kernel/trace/fprobe.c
index 3b21f4063258..881f90f0cbcf 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -189,7 +189,7 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
{
int i, size;
- if (num < 0)
+ if (num <= 0)
return -EINVAL;
if (!fp->exit_handler) {
@@ -202,8 +202,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
size = fp->nr_maxactive;
else
size = num * num_possible_cpus() * 2;
- if (size < 0)
- return -E2BIG;
+ if (size <= 0)
+ return -EINVAL;
fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
if (!fp->rethook)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 28daf0ce95c5..515cafdb18d9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1137,6 +1137,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
if (full) {
poll_wait(filp, &work->full_waiters, poll_table);
work->full_waiters_pending = true;
+ if (!cpu_buffer->shortest_full ||
+ cpu_buffer->shortest_full > full)
+ cpu_buffer->shortest_full = full;
} else {
poll_wait(filp, &work->waiters, poll_table);
work->waiters_pending = true;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 91951d038ba4..f49d6ddb6342 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2770,6 +2770,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
update_event_fields(call, map[i]);
}
}
+ cond_resched();
}
up_write(&trace_event_sem);
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 6f046650e527..b87f41187c6a 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -127,8 +127,13 @@ struct user_event_enabler {
/* Bit 7 is for freeing status of enablement */
#define ENABLE_VAL_FREEING_BIT 7
-/* Only duplicate the bit value */
-#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK
+/* Bit 8 is for marking 32-bit on 64-bit */
+#define ENABLE_VAL_32_ON_64_BIT 8
+
+#define ENABLE_VAL_COMPAT_MASK (1 << ENABLE_VAL_32_ON_64_BIT)
+
+/* Only duplicate the bit and compat values */
+#define ENABLE_VAL_DUP_MASK (ENABLE_VAL_BIT_MASK | ENABLE_VAL_COMPAT_MASK)
#define ENABLE_BITOPS(e) (&(e)->values)
@@ -174,6 +179,30 @@ struct user_event_validator {
int flags;
};
+static inline void align_addr_bit(unsigned long *addr, int *bit,
+ unsigned long *flags)
+{
+ if (IS_ALIGNED(*addr, sizeof(long))) {
+#ifdef __BIG_ENDIAN
+ /* 32 bit on BE 64 bit requires a 32 bit offset when aligned. */
+ if (test_bit(ENABLE_VAL_32_ON_64_BIT, flags))
+ *bit += 32;
+#endif
+ return;
+ }
+
+ *addr = ALIGN_DOWN(*addr, sizeof(long));
+
+ /*
+ * We only support 32 and 64 bit values. The only time we need
+ * to align is a 32 bit value on a 64 bit kernel, which on LE
+ * is always 32 bits, and on BE requires no change when unaligned.
+ */
+#ifdef __LITTLE_ENDIAN
+ *bit += 32;
+#endif
+}
+
typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted);
@@ -482,6 +511,7 @@ static int user_event_enabler_write(struct user_event_mm *mm,
unsigned long *ptr;
struct page *page;
void *kaddr;
+ int bit = ENABLE_BIT(enabler);
int ret;
lockdep_assert_held(&event_mutex);
@@ -497,6 +527,8 @@ static int user_event_enabler_write(struct user_event_mm *mm,
test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))))
return -EBUSY;
+ align_addr_bit(&uaddr, &bit, ENABLE_BITOPS(enabler));
+
ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
&page, NULL);
@@ -515,9 +547,9 @@ static int user_event_enabler_write(struct user_event_mm *mm,
/* Update bit atomically, user tracers must be atomic as well */
if (enabler->event && enabler->event->status)
- set_bit(ENABLE_BIT(enabler), ptr);
+ set_bit(bit, ptr);
else
- clear_bit(ENABLE_BIT(enabler), ptr);
+ clear_bit(bit, ptr);
kunmap_local(kaddr);
unpin_user_pages_dirty_lock(&page, 1, true);
@@ -849,6 +881,12 @@ static struct user_event_enabler
enabler->event = user;
enabler->addr = uaddr;
enabler->values = reg->enable_bit;
+
+#if BITS_PER_LONG >= 64
+ if (reg->enable_size == 4)
+ set_bit(ENABLE_VAL_32_ON_64_BIT, ENABLE_BITOPS(enabler));
+#endif
+
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -2377,7 +2415,8 @@ static long user_unreg_get(struct user_unreg __user *ureg,
}
static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
- unsigned long uaddr, unsigned char bit)
+ unsigned long uaddr, unsigned char bit,
+ unsigned long flags)
{
struct user_event_enabler enabler;
int result;
@@ -2385,7 +2424,7 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
memset(&enabler, 0, sizeof(enabler));
enabler.addr = uaddr;
- enabler.values = bit;
+ enabler.values = bit | flags;
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -2415,6 +2454,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
struct user_event_mm *mm = current->user_event_mm;
struct user_event_enabler *enabler, *next;
struct user_unreg reg;
+ unsigned long flags;
long ret;
ret = user_unreg_get(ureg, &reg);
@@ -2425,6 +2465,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
if (!mm)
return -ENOENT;
+ flags = 0;
ret = -ENOENT;
/*
@@ -2441,6 +2482,9 @@ static long user_events_ioctl_unreg(unsigned long uarg)
ENABLE_BIT(enabler) == reg.disable_bit) {
set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler));
+ /* We must keep compat flags for the clear */
+ flags |= enabler->values & ENABLE_VAL_COMPAT_MASK;
+
if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))
user_event_enabler_destroy(enabler, true);
@@ -2454,7 +2498,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
/* Ensure bit is now cleared for user, regardless of event status */
if (!ret)
ret = user_event_mm_clear_bit(mm, reg.disable_addr,
- reg.disable_bit);
+ reg.disable_bit, flags);
return ret;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 3d7a180a8427..a8fef6ab0872 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -705,6 +705,25 @@ static struct notifier_block trace_kprobe_module_nb = {
.priority = 1 /* Invoked after kprobe module callback */
};
+static int count_symbols(void *data, unsigned long unused)
+{
+ unsigned int *count = data;
+
+ (*count)++;
+
+ return 0;
+}
+
+static unsigned int number_of_same_symbols(char *func_name)
+{
+ unsigned int count;
+
+ count = 0;
+ kallsyms_on_each_match_symbol(count_symbols, func_name, &count);
+
+ return count;
+}
+
static int __trace_kprobe_create(int argc, const char *argv[])
{
/*
@@ -836,6 +855,31 @@ static int __trace_kprobe_create(int argc, const char *argv[])
}
}
+ if (symbol && !strchr(symbol, ':')) {
+ unsigned int count;
+
+ count = number_of_same_symbols(symbol);
+ if (count > 1) {
+ /*
+ * Users should use ADDR to remove the ambiguity of
+ * using KSYM only.
+ */
+ trace_probe_log_err(0, NON_UNIQ_SYMBOL);
+ ret = -EADDRNOTAVAIL;
+
+ goto error;
+ } else if (count == 0) {
+ /*
+ * We can return ENOENT earlier than when register the
+ * kprobe.
+ */
+ trace_probe_log_err(0, BAD_PROBE_ADDR);
+ ret = -ENOENT;
+
+ goto error;
+ }
+ }
+
trace_probe_log_set_index(0);
if (event) {
ret = traceprobe_parse_event_name(&event, &group, gbuf,
@@ -1695,6 +1739,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk)
}
#ifdef CONFIG_PERF_EVENTS
+
/* create a trace_kprobe, but don't add it to global lists */
struct trace_event_call *
create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
@@ -1705,6 +1750,24 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
int ret;
char *event;
+ if (func) {
+ unsigned int count;
+
+ count = number_of_same_symbols(func);
+ if (count > 1)
+ /*
+ * Users should use addr to remove the ambiguity of
+ * using func only.
+ */
+ return ERR_PTR(-EADDRNOTAVAIL);
+ else if (count == 0)
+ /*
+ * We can return ENOENT earlier than when register the
+ * kprobe.
+ */
+ return ERR_PTR(-ENOENT);
+ }
+
/*
* local trace_kprobes are not added to dyn_event, so they are never
* searched in find_trace_kprobe(). Therefore, there is no concern of
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 02b432ae7513..850d9ecb6765 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -450,6 +450,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_MAXACT, "Invalid maxactive number"), \
C(MAXACT_TOO_BIG, "Maxactive is too big"), \
C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \
+ C(NON_UNIQ_SYMBOL, "The symbol is not unique"), \
C(BAD_RETPROBE, "Retprobe address must be an function entry"), \
C(NO_TRACEPOINT, "Tracepoint is not found"), \
C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c85825e17df8..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)) {
@@ -6535,9 +6549,6 @@ void __init workqueue_init_early(void)
BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE));
- wq_update_pod_attrs_buf = alloc_workqueue_attrs();
- BUG_ON(!wq_update_pod_attrs_buf);
-
pt->nr_pods = 1;
cpumask_copy(pt->pod_cpus[0], cpu_possible_mask);
pt->pod_node[0] = NUMA_NO_NODE;
@@ -6605,13 +6616,13 @@ static void __init wq_cpu_intensive_thresh_init(void)
unsigned long thresh;
unsigned long bogo;
+ pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
+ BUG_ON(IS_ERR(pwq_release_worker));
+
/* if the user set it to a specific value, keep it */
if (wq_cpu_intensive_thresh_us != ULONG_MAX)
return;
- pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
- BUG_ON(IS_ERR(pwq_release_worker));
-
/*
* The default of 10ms is derived from the fact that most modern (as of
* 2023) processors can do a lot in 10ms and that it's just below what
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-20 02:18:14 +0100