summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c46
-rw-r--r--kernel/bpf/devmap.c7
-rw-r--r--kernel/bpf/hashtab.c16
-rw-r--r--kernel/bpf/sockmap.c43
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/bpf/verifier.c11
-rw-r--r--kernel/fork.c33
-rw-r--r--kernel/freezer.c4
-rw-r--r--kernel/kthread.c8
-rw-r--r--kernel/memremap.c22
-rw-r--r--kernel/power/hibernate.c16
-rw-r--r--kernel/power/main.c12
-rw-r--r--kernel/power/suspend.c4
-rw-r--r--kernel/power/swap.c4
-rw-r--r--kernel/power/user.c4
-rw-r--r--kernel/reboot.c6
-rw-r--r--kernel/rseq.c41
-rw-r--r--kernel/sched/deadline.c11
-rw-r--r--kernel/softirq.c12
-rw-r--r--kernel/stop_machine.c6
-rw-r--r--kernel/time/tick-common.c3
-rw-r--r--kernel/trace/ring_buffer.c16
-rw-r--r--kernel/trace/trace.c14
-rw-r--r--kernel/trace/trace_events_trigger.c18
-rw-r--r--kernel/trace/trace_kprobe.c21
-rw-r--r--kernel/trace/trace_output.c5
26 files changed, 269 insertions, 118 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..9704934252b3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
-
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u64_num >>= bits_offset;
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642c97f6d1b8..d361fc1e3bf3 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
+ int err;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
{
int err;
- err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+ err = xdp_ok_fwd_dev(dst->dev, skb->len);
if (unlikely(err))
return err;
skb->dev = dst->dev;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
* old element will be freed immediately.
* Otherwise return an error
*/
- atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
}
l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
htab->map.numa_node);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
}
memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
- return ERR_PTR(-ENOMEM);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
}
}
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new->hash = hash;
return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
}
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index cf7b6a6dbd1f..98fb7938beea 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -312,10 +312,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
struct smap_psock *psock;
struct sock *osk;
+ lock_sock(sk);
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
+ release_sock(sk);
return sk->sk_prot->close(sk, timeout);
}
@@ -371,6 +373,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
e = psock_map_pop(sk, psock);
}
rcu_read_unlock();
+ release_sock(sk);
close_fun(sk, timeout);
}
@@ -568,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
while (sg[i].length) {
free += sg[i].length;
sk_mem_uncharge(sk, sg[i].length);
- put_page(sg_page(&sg[i]));
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
sg[i].length = 0;
sg[i].page_link = 0;
sg[i].offset = 0;
@@ -577,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ if (md->skb)
+ consume_skb(md->skb);
return free;
}
@@ -1230,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
@@ -1485,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -1896,7 +1902,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
if (!e) {
err = -ENOMEM;
- goto out_progs;
+ goto out_free;
}
}
@@ -2069,7 +2075,13 @@ static int sock_map_update_elem(struct bpf_map *map,
return -EOPNOTSUPP;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2342,7 +2354,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (err)
goto err;
- /* bpf_map_update_elem() can be called in_irq() */
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
raw_spin_lock_bh(&b->lock);
l_old = lookup_elem_raw(head, hash, key, key_size);
if (l_old && map_flags == BPF_NOEXIST) {
@@ -2360,12 +2375,6 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto bucket_err;
}
- psock = smap_psock_sk(sock);
- if (unlikely(!psock)) {
- err = -EINVAL;
- goto bucket_err;
- }
-
rcu_assign_pointer(e->hash_link, l_new);
rcu_assign_pointer(e->htab,
container_of(map, struct bpf_htab, map));
@@ -2388,12 +2397,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
raw_spin_unlock_bh(&b->lock);
return 0;
bucket_err:
+ smap_release_sock(psock, sock);
raw_spin_unlock_bh(&b->lock);
err:
kfree(e);
- psock = smap_psock_sk(sock);
- if (psock)
- smap_release_sock(psock, sock);
return err;
}
@@ -2415,7 +2422,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
return -EINVAL;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2472,10 +2485,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- raw_spin_lock_bh(&b->lock);
l = lookup_elem_raw(head, hash, key, key_size);
sk = l ? l->sk : NULL;
- raw_spin_unlock_bh(&b->lock);
return sk;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d10ecd78105f..a31a1ba0f8ea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
- return -ENOMEM;
+ goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
- err = -EFAULT;
+ err = -ENOTSUPP;
goto out_free;
}
cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
+out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
err = jit_subprogs(env);
if (err == 0)
return 0;
+ if (err == -EFAULT)
+ return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..1b27babc4c78 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -303,11 +303,36 @@ struct kmem_cache *files_cachep;
struct kmem_cache *fs_cachep;
/* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+ if (vma)
+ vma_init(vma, mm);
+ return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+ struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+ if (new) {
+ *new = *orig;
+ INIT_LIST_HEAD(&new->anon_vma_chain);
+ }
+ return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
static void account_kernel_stack(struct task_struct *tsk, int account)
{
void *stack = task_stack_page(tsk);
@@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
goto fail_nomem;
charge = len;
}
- tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
- *tmp = *mpnt;
- INIT_LIST_HEAD(&tmp->anon_vma_chain);
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
@@ -539,7 +562,7 @@ fail_uprobe_end:
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
- kmem_cache_free(vm_area_cachep, tmp);
+ vm_area_free(tmp);
fail_nomem:
retval = -ENOMEM;
vm_unacct_memory(charge);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 6f56a9e219fa..b162b74611e4 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -15,7 +15,9 @@
atomic_t system_freezing_cnt = ATOMIC_INIT(0);
EXPORT_SYMBOL(system_freezing_cnt);
-/* indicate whether PM freezing is in effect, protected by pm_mutex */
+/* indicate whether PM freezing is in effect, protected by
+ * system_transition_mutex
+ */
bool pm_freezing;
bool pm_nosig_freezing;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 750cb8082694..486dedbd9af5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..38283363da06 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
unsigned long pfn, pgoff, order;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
+ struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
+ align_end = align_start + align_size - 1;
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
mutex_lock(&pgmap_lock);
error = 0;
- align_end = align_start + align_size - 1;
foreach_order_pgoff(res, order, pgoff) {
error = __radix_tree_insert(&pgmap_radix,
@@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_enable;
/*
@@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
} else if (!count)
__put_page(page);
}
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9c85c7822383..abef759de7c8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,7 @@ static int create_image(int platform_mode)
* hibernation_snapshot - Quiesce devices and create a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held.
+ * This routine must be called with system_transition_mutex held.
*/
int hibernation_snapshot(int platform_mode)
{
@@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode)
* hibernation_restore - Quiesce devices and restore from a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
- * This routine must be called with pm_mutex held. If it is successful, control
- * reappears in the restored target kernel in hibernation_snapshot().
+ * This routine must be called with system_transition_mutex held. If it is
+ * successful, control reappears in the restored target kernel in
+ * hibernation_snapshot().
*/
int hibernation_restore(int platform_mode)
{
@@ -638,6 +639,7 @@ static void power_down(void)
break;
case HIBERNATION_PLATFORM:
hibernation_platform_enter();
+ /* Fall through */
case HIBERNATION_SHUTDOWN:
if (pm_power_off)
kernel_power_off();
@@ -805,13 +807,13 @@ static int software_resume(void)
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
- * calling hibernate functions (which take pm_mutex) this can
- * cause lockdep to complain about a possible ABBA deadlock
+ * calling hibernate functions (which take system_transition_mutex)
+ * this can cause lockdep to complain about a possible ABBA deadlock
* which cannot happen since we're in the boot code here and
* sysfs can't be invoked yet. Therefore, we use a subclass
* here to avoid lockdep complaining.
*/
- mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+ mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
if (swsusp_resume_device)
goto Check_image;
@@ -899,7 +901,7 @@ static int software_resume(void)
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d9706da10930..35b50823d83b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,17 +15,16 @@
#include <linux/workqueue.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/suspend.h>
#include "power.h"
-DEFINE_MUTEX(pm_mutex);
-
#ifdef CONFIG_PM_SLEEP
void lock_system_sleep(void)
{
current->flags |= PF_FREEZER_SKIP;
- mutex_lock(&pm_mutex);
+ mutex_lock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(lock_system_sleep);
@@ -37,8 +36,9 @@ void unlock_system_sleep(void)
*
* Reason:
* Fundamentally, we just don't need it, because freezing condition
- * doesn't come into effect until we release the pm_mutex lock,
- * since the freezer always works with pm_mutex held.
+ * doesn't come into effect until we release the
+ * system_transition_mutex lock, since the freezer always works with
+ * system_transition_mutex held.
*
* More importantly, in the case of hibernation,
* unlock_system_sleep() gets called in snapshot_read() and
@@ -47,7 +47,7 @@ void unlock_system_sleep(void)
* enter the refrigerator, thus causing hibernation to lockup.
*/
current->flags &= ~PF_FREEZER_SKIP;
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
}
EXPORT_SYMBOL_GPL(unlock_system_sleep);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..9e13afe65a14 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state)
} else if (!valid_state(state)) {
return -EINVAL;
}
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
if (state == PM_SUSPEND_TO_IDLE)
@@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state)
pm_pr_dbg("Finishing wakeup.\n");
suspend_finish();
Unlock:
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c2bcf97d24c8..d7f6c1a288d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags)
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_read_next(&snapshot);
- if (error < PAGE_SIZE) {
+ if (error < (int)PAGE_SIZE) {
if (error >= 0)
error = -EFAULT;
@@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p)
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_write_next(&snapshot);
- if (error < PAGE_SIZE)
+ if (error < (int)PAGE_SIZE)
return error < 0 ? error : -EFAULT;
header = (struct swsusp_info *)data_of(snapshot);
error = get_swap_reader(&handle, flags_p);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index abd225550271..2d8b60a3c86b 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!mutex_trylock(&pm_mutex))
+ if (!mutex_trylock(&system_transition_mutex))
return -EBUSY;
lock_device_hotplug();
@@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
}
unlock_device_hotplug();
- mutex_unlock(&pm_mutex);
+ mutex_unlock(&system_transition_mutex);
return error;
}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e4ced883d8de..8fb44dec9ad7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -294,7 +294,7 @@ void kernel_power_off(void)
}
EXPORT_SYMBOL_GPL(kernel_power_off);
-static DEFINE_MUTEX(reboot_mutex);
+DEFINE_MUTEX(system_transition_mutex);
/*
* Reboot system call: for obvious reasons only root may call it,
@@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
- mutex_lock(&reboot_mutex);
+ mutex_lock(&system_transition_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
@@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
ret = -EINVAL;
break;
}
- mutex_unlock(&reboot_mutex);
+ mutex_unlock(&system_transition_mutex);
return ret;
}
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 22b6acf1ad63..c6242d8594dc 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
{
u32 cpu_id = raw_smp_processor_id();
- if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id, &t->rseq->cpu_id_start))
return -EFAULT;
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
trace_rseq_update(t);
return 0;
@@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
/*
* Reset cpu_id_start to its initial state (0).
*/
- if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
return -EFAULT;
/*
* Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
* in after unregistration can figure out that rseq needs to be
* registered again.
*/
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
return 0;
}
@@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
{
struct rseq_cs __user *urseq_cs;
- unsigned long ptr;
+ u64 ptr;
u32 __user *usig;
u32 sig;
int ret;
- ret = __get_user(ptr, &t->rseq->rseq_cs);
- if (ret)
- return ret;
+ if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+ return -EFAULT;
if (!ptr) {
memset(rseq_cs, 0, sizeof(*rseq_cs));
return 0;
}
- urseq_cs = (struct rseq_cs __user *)ptr;
+ if (ptr >= TASK_SIZE)
+ return -EINVAL;
+ urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
return -EFAULT;
- if (rseq_cs->version > 0)
- return -EINVAL;
+ if (rseq_cs->start_ip >= TASK_SIZE ||
+ rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+ rseq_cs->abort_ip >= TASK_SIZE ||
+ rseq_cs->version > 0)
+ return -EINVAL;
+ /* Check for overflow. */
+ if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+ return -EINVAL;
/* Ensure that abort_ip is not in the critical section. */
if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
return -EINVAL;
- usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+ usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
ret = get_user(sig, usig);
if (ret)
return ret;
@@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
printk_ratelimited(KERN_WARNING
"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
sig, current->rseq_sig, current->pid, usig);
- return -EPERM;
+ return -EINVAL;
}
return 0;
}
@@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
int ret;
/* Get thread flags. */
- ret = __get_user(flags, &t->rseq->flags);
+ ret = get_user(flags, &t->rseq->flags);
if (ret)
return ret;
@@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t)
* of code outside of the rseq assembly block. This performs
* a lazy clear of the rseq_cs field.
*
- * Set rseq_cs to NULL with single-copy atomicity.
+ * Set rseq_cs to NULL.
*/
- return __put_user(0UL, &t->rseq->rseq_cs);
+ if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+ return -EFAULT;
+ return 0;
}
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fbfc3f1d368a..10c7b51c0d1f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2290,8 +2290,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
if (task_on_rq_queued(p) && p->dl.dl_runtime)
task_non_contending(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ /*
+ * Inactive timer is armed. However, p is leaving DEADLINE and
+ * might migrate away from this rq while continuing to run on
+ * some other class. We need to remove its contribution from
+ * this rq running_bw now, or sub_rq_bw (below) will complain.
+ */
+ if (p->dl.dl_non_contending)
+ sub_running_bw(&p->dl, &rq->dl);
sub_rq_bw(&p->dl, &rq->dl);
+ }
/*
* We cannot use inactive_task_timer() to invoke sub_running_bw()
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 900dcfee542c..75ffc1d1a2e0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -79,12 +79,16 @@ static void wakeup_softirqd(void)
/*
* If ksoftirqd is scheduled, we do not want to process pending softirqs
- * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness,
+ * unless we're doing some of the synchronous softirqs.
*/
-static bool ksoftirqd_running(void)
+#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
+static bool ksoftirqd_running(unsigned long pending)
{
struct task_struct *tsk = __this_cpu_read(ksoftirqd);
+ if (pending & SOFTIRQ_NOW_MASK)
+ return false;
return tsk && (tsk->state == TASK_RUNNING);
}
@@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void)
pending = local_softirq_pending();
- if (pending && !ksoftirqd_running())
+ if (pending && !ksoftirqd_running(pending))
do_softirq_own_stack();
local_irq_restore(flags);
@@ -355,7 +359,7 @@ void irq_enter(void)
static inline void invoke_softirq(void)
{
- if (ksoftirqd_running())
+ if (ksoftirqd_running(local_softirq_pending()))
return;
if (!force_irqthreads) {
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index f89014a2c238..1ff523dae6e2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -270,7 +270,11 @@ unlock:
goto retry;
}
- wake_up_q(&wakeq);
+ if (!err) {
+ preempt_disable();
+ wake_up_q(&wakeq);
+ preempt_enable();
+ }
return err;
}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b7005dd21ec1..14de3727b18e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
*/
return !curdev ||
newdev->rating > curdev->rating ||
- (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
- !tick_check_percpu(curdev, newdev, smp_processor_id()));
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
}
/*
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
}
/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
* @cpu: The CPU buffer to stop
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f054bd6a1c66..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
@@ -3365,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
print_event_info(buf, m);
- seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
- seq_printf(m, "# | | | %s | |\n", tgid ? " | " : "");
+ seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
+ seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
}
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
@@ -3386,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
tgid ? tgid_space : space);
seq_printf(m, "# %s||| / delay\n",
tgid ? tgid_space : space);
- seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n",
+ seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n",
tgid ? " TGID " : space);
- seq_printf(m, "# | | | %s|||| | |\n",
+ seq_printf(m, "# | | %s | |||| | |\n",
tgid ? " | " : space);
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d18249683682..5dea177cef53 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops,
goto out_free;
out_reg:
+ /* Up the trigger_data count to make sure reg doesn't free it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
/*
* The above returns on success the # of functions enabled,
@@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops,
* Consider no functions a failure too.
*/
if (!ret) {
+ cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
ret = -ENOENT;
- goto out_free;
- } else if (ret < 0)
- goto out_free;
- ret = 0;
+ } else if (ret > 0)
+ ret = 0;
+
+ /* Down the counter of trigger_data or free it if not used anymore */
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out;
}
+ /* Up the trigger_data count to make sure nothing frees it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
+
if (trigger) {
number = strsep(&trigger, ":");
@@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out_disable;
/* Just return zero, not the number of enabled functions */
ret = 0;
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
- kfree(trigger_data);
+ event_trigger_free(trigger_ops, trigger_data);
kfree(enable_data);
goto out;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..6b71860f3998 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
+ struct event_file_link *link = NULL;
int ret = 0;
if (file) {
- struct event_file_link *link;
-
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
ret = -ENOMEM;
@@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
else
ret = enable_kprobe(&tk->rp.kp);
}
+
+ if (ret) {
+ if (file) {
+ /* Notice the if is true on not WARN() */
+ if (!WARN_ON_ONCE(!link))
+ list_del_rcu(&link->list);
+ kfree(link);
+ tk->tp.flags &= ~TP_FLAG_TRACE;
+ } else {
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
+ }
+ }
out:
return ret;
}
@@ -1480,8 +1491,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
}
ret = __register_trace_kprobe(tk);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(tk->tp.call.print_fmt);
goto error;
+ }
return &tk->tp.call;
error:
@@ -1501,6 +1514,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
}
__unregister_trace_kprobe(tk);
+
+ kfree(tk->tp.call.print_fmt);
free_trace_kprobe(tk);
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 90db994ac900..1c8e30fda46a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
trace_seq_printf(s, "(%5d) ", tgid);
}
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
+
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
generated by cgit (git 2.34.1) at 2025-04-02 23:53:21 +0000