summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/hashtab.c6
-rw-r--r--kernel/bpf/map_in_map.c8
-rw-r--r--kernel/bpf/offload.c2
-rw-r--r--kernel/bpf/syscall.c9
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/cgroup/cgroup-v1.c4
-rw-r--r--kernel/cgroup/cgroup.c37
-rw-r--r--kernel/cgroup/legacy_freezer.c8
-rw-r--r--kernel/exit.c5
-rw-r--r--kernel/fork.c15
-rw-r--r--kernel/irq/msi.c4
-rw-r--r--kernel/kexec_file.c14
-rw-r--r--kernel/locking/lockdep.c28
-rw-r--r--kernel/module/decompress.c2
-rw-r--r--kernel/module/main.c4
-rw-r--r--kernel/module/stats.c4
-rw-r--r--kernel/signal.c8
-rw-r--r--kernel/time/tick-common.c13
-rw-r--r--kernel/time/tick-sched.c13
-rw-r--r--kernel/trace/bpf_trace.c12
-rw-r--r--kernel/trace/fprobe.c73
-rw-r--r--kernel/trace/rethook.c4
-rw-r--r--kernel/trace/trace.c44
-rw-r--r--kernel/trace/trace_events.c2
-rw-r--r--kernel/trace/trace_events_hist.c39
-rw-r--r--kernel/trace/trace_events_user.c400
-rw-r--r--kernel/trace/trace_osnoise.c2
-rw-r--r--kernel/trace/trace_output.c2
-rw-r--r--kernel/trace/trace_probe.h2
-rw-r--r--kernel/trace/trace_selftest.c10
-rw-r--r--kernel/vhost_task.c94
31 files changed, 615 insertions, 255 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 00c253b84bf5..9901efee4339 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1215,7 +1215,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
ret = htab_lock_bucket(htab, b, hash, &flags);
if (ret)
- return ret;
+ goto err_lock_bucket;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1236,6 +1236,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
err:
htab_unlock_bucket(htab, b, hash, flags);
+err_lock_bucket:
if (ret)
htab_lru_push_free(htab, l_new);
else if (l_old)
@@ -1338,7 +1339,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
ret = htab_lock_bucket(htab, b, hash, &flags);
if (ret)
- return ret;
+ goto err_lock_bucket;
l_old = lookup_elem_raw(head, hash, key, key_size);
@@ -1361,6 +1362,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
ret = 0;
err:
htab_unlock_bucket(htab, b, hash, flags);
+err_lock_bucket:
if (l_new)
bpf_lru_push_free(&htab->lru, &l_new->lru_node);
return ret;
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 2c5c64c2a53b..cd5eafaba97e 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -69,9 +69,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
if (inner_map->ops == &array_map_ops) {
+ struct bpf_array *inner_array_meta =
+ container_of(inner_map_meta, struct bpf_array, map);
+ struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map);
+
+ inner_array_meta->index_mask = inner_array->index_mask;
+ inner_array_meta->elem_size = inner_array->elem_size;
inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
- container_of(inner_map_meta, struct bpf_array, map)->index_mask =
- container_of(inner_map, struct bpf_array, map)->index_mask;
}
fdput(f);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index d9c9f45e3529..8a26cd8814c1 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -859,4 +859,4 @@ static int __init bpf_offload_init(void)
return rhashtable_init(&offdevs, &offdevs_params);
}
-late_initcall(bpf_offload_init);
+core_initcall(bpf_offload_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 14f39c1e573e..0c21d0d8efe4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2433,6 +2433,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
default:
return -EINVAL;
}
+ case BPF_PROG_TYPE_NETFILTER:
+ if (expected_attach_type == BPF_NETFILTER)
+ return 0;
+ return -EINVAL;
case BPF_PROG_TYPE_SYSCALL:
case BPF_PROG_TYPE_EXT:
if (expected_attach_type)
@@ -4590,7 +4594,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
switch (prog->type) {
case BPF_PROG_TYPE_EXT:
+ break;
case BPF_PROG_TYPE_NETFILTER:
+ if (attr->link_create.attach_type != BPF_NETFILTER) {
+ ret = -EINVAL;
+ goto out;
+ }
break;
case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_TRACEPOINT:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fbcf5a4e2fcd..5871aa78d01a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17033,7 +17033,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
insn->dst_reg,
shift);
- insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
+ insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
(1ULL << size * 8) - 1);
}
}
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index aeef06c465ef..5407241dbb45 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -108,7 +108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
cgroup_lock();
- percpu_down_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_lock(true);
/* all tasks in @from are being moved, all csets are source */
spin_lock_irq(&css_set_lock);
@@ -144,7 +144,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
} while (task && !ret);
out_err:
cgroup_migrate_finish(&mgctx);
- percpu_up_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_unlock(true);
cgroup_unlock();
return ret;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..4d42f0cbc11e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1798,7 +1798,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
{
struct cgroup *dcgrp = &dst_root->cgrp;
struct cgroup_subsys *ss;
- int ssid, i, ret;
+ int ssid, ret;
u16 dfl_disable_ss_mask = 0;
lockdep_assert_held(&cgroup_mutex);
@@ -1842,7 +1842,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
struct cgroup_root *src_root = ss->root;
struct cgroup *scgrp = &src_root->cgrp;
struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
- struct css_set *cset;
+ struct css_set *cset, *cset_pos;
+ struct css_task_iter *it;
WARN_ON(!css || cgroup_css(dcgrp, ss));
@@ -1860,9 +1861,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
css->cgroup = dcgrp;
spin_lock_irq(&css_set_lock);
- hash_for_each(css_set_table, i, cset, hlist)
+ WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+ list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+ e_cset_node[ss->id]) {
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
+ /*
+ * all css_sets of scgrp together in same order to dcgrp,
+ * patch in-flight iterators to preserve correct iteration.
+ * since the iterator is always advanced right away and
+ * finished when it->cset_pos meets it->cset_head, so only
+ * update it->cset_head is enough here.
+ */
+ list_for_each_entry(it, &cset->task_iters, iters_node)
+ if (it->cset_head == &scgrp->e_csets[ss->id])
+ it->cset_head = &dcgrp->e_csets[ss->id];
+ }
spin_unlock_irq(&css_set_lock);
if (ss->css_rstat_flush) {
@@ -6486,19 +6500,18 @@ err:
static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
{
+ struct cgroup *cgrp = kargs->cgrp;
+ struct css_set *cset = kargs->cset;
+
cgroup_threadgroup_change_end(current);
- if (kargs->flags & CLONE_INTO_CGROUP) {
- struct cgroup *cgrp = kargs->cgrp;
- struct css_set *cset = kargs->cset;
+ if (cset) {
+ put_css_set(cset);
+ kargs->cset = NULL;
+ }
+ if (kargs->flags & CLONE_INTO_CGROUP) {
cgroup_unlock();
-
- if (cset) {
- put_css_set(cset);
- kargs->cset = NULL;
- }
-
if (cgrp) {
cgroup_put(cgrp);
kargs->cgrp = NULL;
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 936473203a6b..122dacb3a443 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -108,16 +108,18 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
struct freezer *freezer = css_freezer(css);
struct freezer *parent = parent_freezer(freezer);
+ cpus_read_lock();
mutex_lock(&freezer_mutex);
freezer->state |= CGROUP_FREEZER_ONLINE;
if (parent && (parent->state & CGROUP_FREEZING)) {
freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
- static_branch_inc(&freezer_active);
+ static_branch_inc_cpuslocked(&freezer_active);
}
mutex_unlock(&freezer_mutex);
+ cpus_read_unlock();
return 0;
}
@@ -132,14 +134,16 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
{
struct freezer *freezer = css_freezer(css);
+ cpus_read_lock();
mutex_lock(&freezer_mutex);
if (freezer->state & CGROUP_FREEZING)
- static_branch_dec(&freezer_active);
+ static_branch_dec_cpuslocked(&freezer_active);
freezer->state = 0;
mutex_unlock(&freezer_mutex);
+ cpus_read_unlock();
}
static void freezer_css_free(struct cgroup_subsys_state *css)
diff --git a/kernel/exit.c b/kernel/exit.c
index 34b90e2e7cf7..edb50b4c9972 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk)
tsk->flags |= PF_POSTCOREDUMP;
core_state = tsk->signal->core_state;
spin_unlock_irq(&tsk->sighand->siglock);
- if (core_state) {
+
+ /* The vhost_worker does not particpate in coredumps */
+ if (core_state &&
+ ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) {
struct core_thread self;
self.task = current;
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..41c964104b58 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -627,6 +627,7 @@ void free_task(struct task_struct *tsk)
arch_release_task_struct(tsk);
if (tsk->flags & PF_KTHREAD)
free_kthread_struct(tsk);
+ bpf_task_storage_free(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -979,7 +980,6 @@ void __put_task_struct(struct task_struct *tsk)
cgroup_free(tsk);
task_numa_free(tsk, true);
security_task_free(tsk);
- bpf_task_storage_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
@@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process(
p->flags &= ~PF_KTHREAD;
if (args->kthread)
p->flags |= PF_KTHREAD;
- if (args->user_worker)
- p->flags |= PF_USER_WORKER;
- if (args->io_thread) {
+ if (args->user_worker) {
/*
- * Mark us an IO worker, and block any signal that isn't
+ * Mark us a user worker, and block any signal that isn't
* fatal or STOP
*/
- p->flags |= PF_IO_WORKER;
+ p->flags |= PF_USER_WORKER;
siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
}
+ if (args->io_thread)
+ p->flags |= PF_IO_WORKER;
if (args->name)
strscpy_pad(p->comm, args->name, sizeof(p->comm));
@@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process(
if (retval)
goto bad_fork_cleanup_io;
- if (args->ignore_signals)
- ignore_signals(p);
-
stackleak_task_init(p);
if (pid != &init_struct_pid) {
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7a97bcb086bf..b4c31a5c1147 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -542,7 +542,7 @@ fail:
return ret;
}
-#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN)
/**
* msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device
* @dev: The device (PCI, platform etc) which will get sysfs entries
@@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev)
msi_for_each_desc(desc, dev, MSI_DESC_ALL)
msi_sysfs_remove_desc(dev, desc);
}
-#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */
#else /* CONFIG_SYSFS */
static inline int msi_sysfs_create_group(struct device *dev) { return 0; }
static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; }
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f989f5f1933b..69ee4a29136f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
}
offset = ALIGN(offset, align);
+
+ /*
+ * Check if the segment contains the entry point, if so,
+ * calculate the value of image->start based on it.
+ * If the compiler has produced more than one .text section
+ * (Eg: .text.hot), they are generally after the main .text
+ * section, and they shall not be used to calculate
+ * image->start. So do not re-calculate image->start if it
+ * is not set to the initial value, and warn the user so they
+ * have a chance to fix their purgatory's linker script.
+ */
if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
pi->ehdr->e_entry < (sechdrs[i].sh_addr
- + sechdrs[i].sh_size)) {
+ + sechdrs[i].sh_size) &&
+ !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
kbuf->image->start -= sechdrs[i].sh_addr;
kbuf->image->start += kbuf->mem + offset;
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dcd1d5bfc1e0..4dfd2f3e09b2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2263,6 +2263,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask)
static inline bool usage_skip(struct lock_list *entry, void *mask)
{
+ if (entry->class->lock_type == LD_LOCK_NORMAL)
+ return false;
+
/*
* Skip local_lock() for irq inversion detection.
*
@@ -2289,14 +2292,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask)
* As a result, we will skip local_lock(), when we search for irq
* inversion bugs.
*/
- if (entry->class->lock_type == LD_LOCK_PERCPU) {
- if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
- return false;
+ if (entry->class->lock_type == LD_LOCK_PERCPU &&
+ DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+ return false;
- return true;
- }
+ /*
+ * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually
+ * a lock and only used to override the wait_type.
+ */
- return false;
+ return true;
}
/*
@@ -4768,7 +4773,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
for (; depth < curr->lockdep_depth; depth++) {
struct held_lock *prev = curr->held_locks + depth;
- u8 prev_inner = hlock_class(prev)->wait_type_inner;
+ struct lock_class *class = hlock_class(prev);
+ u8 prev_inner = class->wait_type_inner;
if (prev_inner) {
/*
@@ -4778,6 +4784,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
* Also due to trylocks.
*/
curr_inner = min(curr_inner, prev_inner);
+
+ /*
+ * Allow override for annotations -- this is typically
+ * only valid/needed for code that only exists when
+ * CONFIG_PREEMPT_RT=n.
+ */
+ if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE))
+ curr_inner = prev_inner;
}
}
diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c
index e97232b125eb..8a5d6d63b06c 100644
--- a/kernel/module/decompress.c
+++ b/kernel/module/decompress.c
@@ -257,7 +257,7 @@ static ssize_t module_zstd_decompress(struct load_info *info,
do {
struct page *page = module_get_next_page(info);
- if (!IS_ERR(page)) {
+ if (IS_ERR(page)) {
retval = PTR_ERR(page);
goto out;
}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 044aa2c9e3cb..4e2cf784cf8c 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
MOD_RODATA,
MOD_RO_AFTER_INIT,
MOD_DATA,
- MOD_INVALID, /* This is needed to match the masks array */
+ MOD_DATA,
};
static const int init_m_to_mem_type[] = {
MOD_INIT_TEXT,
MOD_INIT_RODATA,
MOD_INVALID,
MOD_INIT_DATA,
- MOD_INVALID, /* This is needed to match the masks array */
+ MOD_INIT_DATA,
};
for (m = 0; m < ARRAY_SIZE(masks); ++m) {
diff --git a/kernel/module/stats.c b/kernel/module/stats.c
index ad7b6ada29f2..6ab2c94d6bc3 100644
--- a/kernel/module/stats.c
+++ b/kernel/module/stats.c
@@ -276,6 +276,7 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf,
struct mod_fail_load *mod_fail;
unsigned int len, size, count_failed = 0;
char *buf;
+ int ret;
u32 live_mod_count, fkreads, fdecompress, fbecoming, floads;
unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes,
idecompress_bytes, imod_bytes, total_virtual_lost;
@@ -390,8 +391,9 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf,
out_unlock:
mutex_unlock(&module_mutex);
out:
+ ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
kfree(buf);
- return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+ return ret;
}
#undef MAX_PREAMBLE
#undef MAX_FAILED_MOD_PRINT
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f6330f0e9ca..2547fa73bde5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p)
while_each_thread(p, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
- count++;
+ /* Don't require de_thread to wait for the vhost_worker */
+ if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
+ count++;
/* Don't bother with already dead threads */
if (t->exit_state)
@@ -2861,11 +2863,11 @@ relock:
}
/*
- * PF_IO_WORKER threads will catch and exit on fatal signals
+ * PF_USER_WORKER threads will catch and exit on fatal signals
* themselves. They have cleanup that must be performed, so
* we cannot call do_exit() on their behalf.
*/
- if (current->flags & PF_IO_WORKER)
+ if (current->flags & PF_USER_WORKER)
goto out;
/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 65b8658da829..e9138cd7a0f5 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -218,19 +218,8 @@ static void tick_setup_device(struct tick_device *td,
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- ktime_t next_p;
- u32 rem;
-
tick_do_timer_cpu = cpu;
-
- next_p = ktime_get();
- div_u64_rem(next_p, TICK_NSEC, &rem);
- if (rem) {
- next_p -= rem;
- next_p += TICK_NSEC;
- }
-
- tick_next_period = next_p;
+ tick_next_period = ktime_get();
#ifdef CONFIG_NO_HZ_FULL
/*
* The boot CPU may be nohz_full, in which case set
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 52254679ec48..42c0be3080bd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -161,8 +161,19 @@ static ktime_t tick_init_jiffy_update(void)
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
/* Did we start the jiffies update yet ? */
- if (last_jiffies_update == 0)
+ if (last_jiffies_update == 0) {
+ u32 rem;
+
+ /*
+ * Ensure that the tick is aligned to a multiple of
+ * TICK_NSEC.
+ */
+ div_u64_rem(tick_next_period, TICK_NSEC, &rem);
+ if (rem)
+ tick_next_period += TICK_NSEC - rem;
+
last_jiffies_update = tick_next_period;
+ }
period = last_jiffies_update;
write_seqcount_end(&jiffies_seq);
raw_spin_unlock(&jiffies_lock);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9a050e36dc6c..1f4b07da327a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -900,13 +900,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
{
+ struct path copy;
long len;
char *p;
if (!sz)
return 0;
- p = d_path(path, buf, sz);
+ /*
+ * The path pointer is verified as trusted and safe to use,
+ * but let's double check it's valid anyway to workaround
+ * potentially broken verifier.
+ */
+ len = copy_from_kernel_nofault(&copy, path, sizeof(*path));
+ if (len < 0)
+ return len;
+
+ p = d_path(&copy, buf, sz);
if (IS_ERR(p)) {
len = PTR_ERR(p);
} else {
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 9abb3905bc8e..18d36842faf5 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -17,36 +17,30 @@
struct fprobe_rethook_node {
struct rethook_node node;
unsigned long entry_ip;
+ unsigned long entry_parent_ip;
char data[];
};
-static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ops, struct ftrace_regs *fregs)
+static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
struct fprobe_rethook_node *fpr;
struct rethook_node *rh = NULL;
struct fprobe *fp;
void *entry_data = NULL;
- int bit, ret;
+ int ret = 0;
fp = container_of(ops, struct fprobe, ops);
- if (fprobe_disabled(fp))
- return;
-
- bit = ftrace_test_recursion_trylock(ip, parent_ip);
- if (bit < 0) {
- fp->nmissed++;
- return;
- }
if (fp->exit_handler) {
rh = rethook_try_get(fp->rethook);
if (!rh) {
fp->nmissed++;
- goto out;
+ return;
}
fpr = container_of(rh, struct fprobe_rethook_node, node);
fpr->entry_ip = ip;
+ fpr->entry_parent_ip = parent_ip;
if (fp->entry_data_size)
entry_data = fpr->data;
}
@@ -61,23 +55,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
else
rethook_hook(rh, ftrace_get_regs(fregs), true);
}
-out:
+}
+
+static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+ struct fprobe *fp;
+ int bit;
+
+ fp = container_of(ops, struct fprobe, ops);
+ if (fprobe_disabled(fp))
+ return;
+
+ /* recursion detection has to go before any traceable function and
+ * all functions before this point should be marked as notrace
+ */
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
+ if (bit < 0) {
+ fp->nmissed++;
+ return;
+ }
+ __fprobe_handler(ip, parent_ip, ops, fregs);
ftrace_test_recursion_unlock(bit);
+
}
NOKPROBE_SYMBOL(fprobe_handler);
static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
- struct fprobe *fp = container_of(ops, struct fprobe, ops);
+ struct fprobe *fp;
+ int bit;
+
+ fp = container_of(ops, struct fprobe, ops);
+ if (fprobe_disabled(fp))
+ return;
+
+ /* recursion detection has to go before any traceable function and
+ * all functions called before this point should be marked as notrace
+ */
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
+ if (bit < 0) {
+ fp->nmissed++;
+ return;
+ }
if (unlikely(kprobe_running())) {
fp->nmissed++;
return;
}
+
kprobe_busy_begin();
- fprobe_handler(ip, parent_ip, ops, fregs);
+ __fprobe_handler(ip, parent_ip, ops, fregs);
kprobe_busy_end();
+ ftrace_test_recursion_unlock(bit);
}
static void fprobe_exit_handler(struct rethook_node *rh, void *data,
@@ -85,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
{
struct fprobe *fp = (struct fprobe *)data;
struct fprobe_rethook_node *fpr;
+ int bit;
if (!fp || fprobe_disabled(fp))
return;
fpr = container_of(rh, struct fprobe_rethook_node, node);
+ /*
+ * we need to assure no calls to traceable functions in-between the
+ * end of fprobe_handler and the beginning of fprobe_exit_handler.
+ */
+ bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip);
+ if (bit < 0) {
+ fp->nmissed++;
+ return;
+ }
+
fp->exit_handler(fp, fpr->entry_ip, regs,
fp->entry_data_size ? (void *)fpr->data : NULL);
+ ftrace_test_recursion_unlock(bit);
}
NOKPROBE_SYMBOL(fprobe_exit_handler);
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 32c3dfdb4d6a..60f6cb2b486b 100644
--- a/kernel/trace/rethook.c
+++ b/