summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/bpf_struct_ops.c14
-rw-r--r--kernel/bpf/btf.c5
-rw-r--r--kernel/bpf/cgroup.c7
-rw-r--r--kernel/bpf/syscall.c39
-rw-r--r--kernel/fork.c4
-rw-r--r--kernel/futex.c93
-rw-r--r--kernel/irq/manage.c11
-rw-r--r--kernel/notifier.c2
-rw-r--r--kernel/sys.c2
-rw-r--r--kernel/trace/bpf_trace.c2
10 files changed, 114 insertions, 65 deletions
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index ca5cc8cdb6eb..26cb51f2db72 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -490,13 +490,21 @@ static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
prev_state = cmpxchg(&st_map->kvalue.state,
BPF_STRUCT_OPS_STATE_INUSE,
BPF_STRUCT_OPS_STATE_TOBEFREE);
- if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) {
+ switch (prev_state) {
+ case BPF_STRUCT_OPS_STATE_INUSE:
st_map->st_ops->unreg(&st_map->kvalue.data);
if (refcount_dec_and_test(&st_map->kvalue.refcnt))
bpf_map_put(map);
+ return 0;
+ case BPF_STRUCT_OPS_STATE_TOBEFREE:
+ return -EINPROGRESS;
+ case BPF_STRUCT_OPS_STATE_INIT:
+ return -ENOENT;
+ default:
+ WARN_ON_ONCE(1);
+ /* Should never happen. Treat it as not found. */
+ return -ENOENT;
}
-
- return 0;
}
static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3b6dcfb6ea49..d65c6912bdaf 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2418,7 +2418,7 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
struct_size = struct_type->size;
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
- if (struct_size - bytes_offset < sizeof(int)) {
+ if (struct_size - bytes_offset < member_type->size) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
@@ -4600,7 +4600,7 @@ int btf_get_info_by_fd(const struct btf *btf,
union bpf_attr __user *uattr)
{
struct bpf_btf_info __user *uinfo;
- struct bpf_btf_info info = {};
+ struct bpf_btf_info info;
u32 info_copy, btf_copy;
void __user *ubtf;
u32 uinfo_len;
@@ -4609,6 +4609,7 @@ int btf_get_info_by_fd(const struct btf *btf,
uinfo_len = attr->info.info_len;
info_copy = min_t(u32, uinfo_len, sizeof(info));
+ memset(&info, 0, sizeof(info));
if (copy_from_user(&info, uinfo, info_copy))
return -EFAULT;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 80676fc00d81..cb305e71e7de 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -302,6 +302,9 @@ cleanup:
for (i = 0; i < NR; i++)
bpf_prog_array_free(arrays[i]);
+ for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+ cgroup_bpf_put(p);
+
percpu_ref_exit(&cgrp->bpf.refcnt);
return -ENOMEM;
@@ -418,8 +421,8 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
struct list_head *progs = &cgrp->bpf.progs[type];
struct bpf_prog *old_prog = NULL;
- struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
- *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
+ struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+ struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
struct bpf_prog_list *pl;
int err;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e0a3b34d7039..64783da34202 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -690,14 +690,15 @@ int bpf_get_file_flag(int flags)
offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
sizeof(attr->CMD##_LAST_FIELD)) != NULL
-/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes.
- * Return 0 on success and < 0 on error.
+/* dst and src must have at least "size" number of bytes.
+ * Return strlen on success and < 0 on error.
*/
-static int bpf_obj_name_cpy(char *dst, const char *src)
+int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
{
- const char *end = src + BPF_OBJ_NAME_LEN;
+ const char *end = src + size;
+ const char *orig_src = src;
- memset(dst, 0, BPF_OBJ_NAME_LEN);
+ memset(dst, 0, size);
/* Copy all isalnum(), '_' and '.' chars. */
while (src < end && *src) {
if (!isalnum(*src) &&
@@ -706,11 +707,11 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
*dst++ = *src++;
}
- /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */
+ /* No '\0' found in "size" number of bytes */
if (src == end)
return -EINVAL;
- return 0;
+ return src - orig_src;
}
int map_check_no_btf(const struct bpf_map *map,
@@ -804,8 +805,9 @@ static int map_create(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
- err = bpf_obj_name_cpy(map->name, attr->map_name);
- if (err)
+ err = bpf_obj_name_cpy(map->name, attr->map_name,
+ sizeof(attr->map_name));
+ if (err < 0)
goto free_map;
atomic64_set(&map->refcnt, 1);
@@ -1515,6 +1517,11 @@ static int map_freeze(const union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
+ if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ fdput(f);
+ return -ENOTSUPP;
+ }
+
mutex_lock(&map->freeze_mutex);
if (map->writecnt) {
@@ -2099,8 +2106,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
goto free_prog;
prog->aux->load_time = ktime_get_boottime_ns();
- err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
- if (err)
+ err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
+ sizeof(attr->prog_name));
+ if (err < 0)
goto free_prog;
/* run eBPF verifier */
@@ -2978,7 +2986,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
union bpf_attr __user *uattr)
{
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
- struct bpf_prog_info info = {};
+ struct bpf_prog_info info;
u32 info_len = attr->info.info_len;
struct bpf_prog_stats stats;
char __user *uinsns;
@@ -2990,6 +2998,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
return err;
info_len = min_t(u32, sizeof(info), info_len);
+ memset(&info, 0, sizeof(info));
if (copy_from_user(&info, uinfo, info_len))
return -EFAULT;
@@ -3253,7 +3262,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
union bpf_attr __user *uattr)
{
struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
- struct bpf_map_info info = {};
+ struct bpf_map_info info;
u32 info_len = attr->info.info_len;
int err;
@@ -3262,6 +3271,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
return err;
info_len = min_t(u32, sizeof(info), info_len);
+ memset(&info, 0, sizeof(info));
info.type = map->map_type;
info.id = map->id;
info.key_size = map->key_size;
@@ -3650,7 +3660,7 @@ out_put_progs:
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
- union bpf_attr attr = {};
+ union bpf_attr attr;
int err;
if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
@@ -3662,6 +3672,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
size = min_t(u32, size, sizeof(attr));
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
+ memset(&attr, 0, sizeof(attr));
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
diff --git a/kernel/fork.c b/kernel/fork.c
index 86425305cd4a..d90af13431c7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -397,8 +397,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
THREAD_SIZE / 1024 * account);
- mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
+ mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
}
}
diff --git a/kernel/futex.c b/kernel/futex.c
index 0cf84c8664f2..82dfacb3250e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
*/
static struct futex_hash_bucket *hash_futex(union futex_key *key)
{
- u32 hash = jhash2((u32*)&key->both.word,
- (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
+ u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
key->both.offset);
+
return &futex_queues[hash & (futex_hashsize - 1)];
}
@@ -429,7 +429,7 @@ static void get_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- ihold(key->shared.inode); /* implies smp_mb(); (B) */
+ smp_mb(); /* explicit smp_mb(); (B) */
break;
case FUT_OFF_MMSHARED:
futex_get_mm(key); /* implies smp_mb(); (B) */
@@ -463,7 +463,6 @@ static void drop_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- iput(key->shared.inode);
break;
case FUT_OFF_MMSHARED:
mmdrop(key->private.mm);
@@ -505,6 +504,46 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
return timeout;
}
+/*
+ * Generate a machine wide unique identifier for this inode.
+ *
+ * This relies on u64 not wrapping in the life-time of the machine; which with
+ * 1ns resolution means almost 585 years.
+ *
+ * This further relies on the fact that a well formed program will not unmap
+ * the file while it has a (shared) futex waiting on it. This mapping will have
+ * a file reference which pins the mount and inode.
+ *
+ * If for some reason an inode gets evicted and read back in again, it will get
+ * a new sequence number and will _NOT_ match, even though it is the exact same
+ * file.
+ *
+ * It is important that match_futex() will never have a false-positive, esp.
+ * for PI futexes that can mess up the state. The above argues that false-negatives
+ * are only possible for malformed programs.
+ */
+static u64 get_inode_sequence_number(struct inode *inode)
+{
+ static atomic64_t i_seq;
+ u64 old;
+
+ /* Does the inode already have a sequence number? */
+ old = atomic64_read(&inode->i_sequence);
+ if (likely(old))
+ return old;
+
+ for (;;) {
+ u64 new = atomic64_add_return(1, &i_seq);
+ if (WARN_ON_ONCE(!new))
+ continue;
+
+ old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new);
+ if (old)
+ return old;
+ return new;
+ }
+}
+
/**
* get_futex_key() - Get parameters which are the keys for a futex
* @uaddr: virtual address of the futex
@@ -517,9 +556,15 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
*
* The key words are stored in @key on success.
*
- * For shared mappings, it's (page->index, file_inode(vma->vm_file),
- * offset_within_page). For private mappings, it's (uaddr, current->mm).
- * We can usually work out the index without swapping in the page.
+ * For shared mappings (when @fshared), the key is:
+ * ( inode->i_sequence, page->index, offset_within_page )
+ * [ also see get_inode_sequence_number() ]
+ *
+ * For private mappings (or when !@fshared), the key is:
+ * ( current->mm, address, 0 )
+ *
+ * This allows (cross process, where applicable) identification of the futex
+ * without keeping the page pinned for the duration of the FUTEX_WAIT.
*
* lock_page() might sleep, the caller should not hold a spinlock.
*/
@@ -659,8 +704,6 @@ again:
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
} else {
struct inode *inode;
@@ -692,40 +735,14 @@ again:
goto again;
}
- /*
- * Take a reference unless it is about to be freed. Previously
- * this reference was taken by ihold under the page lock
- * pinning the inode in place so i_lock was unnecessary. The
- * only way for this check to fail is if the inode was
- * truncated in parallel which is almost certainly an
- * application bug. In such a case, just retry.
- *
- * We are not calling into get_futex_key_refs() in file-backed
- * cases, therefore a successful atomic_inc return below will
- * guarantee that get_futex_key() will still imply smp_mb(); (B).
- */
- if (!atomic_inc_not_zero(&inode->i_count)) {
- rcu_read_unlock();
- put_page(page);
-
- goto again;
- }
-
- /* Should be impossible but lets be paranoid for now */
- if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
- err = -EFAULT;
- rcu_read_unlock();
- iput(inode);
-
- goto out;
- }
-
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
- key->shared.inode = inode;
+ key->shared.i_seq = get_inode_sequence_number(inode);
key->shared.pgoff = basepage_index(tail);
rcu_read_unlock();
}
+ get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
out:
put_page(page);
return err;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7eee98c38f25..fe40c658f86f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -323,7 +323,11 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
if (desc->affinity_notify) {
kref_get(&desc->affinity_notify->kref);
- schedule_work(&desc->affinity_notify->work);
+ if (!schedule_work(&desc->affinity_notify->work)) {
+ /* Work was already scheduled, drop our extra ref */
+ kref_put(&desc->affinity_notify->kref,
+ desc->affinity_notify->release);
+ }
}
irqd_set(data, IRQD_AFFINITY_SET);
@@ -423,7 +427,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (old_notify) {
- cancel_work_sync(&old_notify->work);
+ if (cancel_work_sync(&old_notify->work)) {
+ /* Pending work had a ref, put that one too */
+ kref_put(&old_notify->kref, old_notify->release);
+ }
kref_put(&old_notify->kref, old_notify->release);
}
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 63d7501ac638..5989bbb93039 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -519,7 +519,7 @@ NOKPROBE_SYMBOL(notify_die);
int register_die_notifier(struct notifier_block *nb)
{
- vmalloc_sync_all();
+ vmalloc_sync_mappings();
return atomic_notifier_chain_register(&die_chain, nb);
}
EXPORT_SYMBOL_GPL(register_die_notifier);
diff --git a/kernel/sys.c b/kernel/sys.c
index f9bc5c303e3f..d325f3ab624a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -47,6 +47,7 @@
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>
+#include <linux/time_namespace.h>
#include <linux/binfmts.h>
#include <linux/sched.h>
@@ -2546,6 +2547,7 @@ static int do_sysinfo(struct sysinfo *info)
memset(info, 0, sizeof(struct sysinfo));
ktime_get_boottime_ts64(&tp);
+ timens_add_boottime(&tp);
info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 37ffceab608f..ca1796747a77 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -730,7 +730,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
- if (in_nmi()) {
+ if (irqs_disabled()) {
/* Do an early check on signal validity. Otherwise,
* the error is lost in deferred irq_work.
*/
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2024-12-28 18:36:15 +0000