Merging upstream version 6.1.82.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 60 insertions, 36 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 08a8e8102..050893704 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -222,7 +222,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)
 {
-	struct xdp_rxq_info rxq;
+	struct xdp_rxq_info rxq = {};
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6212e4ae0..83f8f67e9 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -28,12 +28,13 @@
  *
  * Different map implementations will rely on rcu in map methods
  * lookup/update/delete, therefore eBPF programs must run under rcu lock
- * if program is allowed to access maps, so check rcu_read_lock_held in
- * all three functions.
+ * if program is allowed to access maps, so check rcu_read_lock_held() or
+ * rcu_read_lock_trace_held() in all three functions.
  */
 BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return (unsigned long) map->ops->map_lookup_elem(map, key);
 }
 
@@ -49,7 +50,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
 BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
 	   void *, value, u64, flags)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_update_elem(map, key, value, flags);
 }
 
@@ -66,7 +68,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
 
 BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_delete_elem(map, key);
 }
 
@@ -750,19 +753,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
  * arguments representation.
  */
-#define MAX_BPRINTF_BUF_LEN	512
+#define MAX_BPRINTF_BIN_ARGS	512
 
 /* Support executing three nested bprintf helper calls on a given CPU */
 #define MAX_BPRINTF_NEST_LEVEL	3
 struct bpf_bprintf_buffers {
-	char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN];
+	char bin_args[MAX_BPRINTF_BIN_ARGS];
+	char buf[MAX_BPRINTF_BUF];
 };
-static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs);
+
+static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
 static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
 
-static int try_get_fmt_tmp_buf(char **tmp_buf)
+static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
 {
-	struct bpf_bprintf_buffers *bufs;
 	int nest_level;
 
 	preempt_disable();
@@ -772,18 +776,19 @@ static int try_get_fmt_tmp_buf(char **tmp_buf)
 		preempt_enable();
 		return -EBUSY;
 	}
-	bufs = this_cpu_ptr(&bpf_bprintf_bufs);
-	*tmp_buf = bufs->tmp_bufs[nest_level - 1];
+	*bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]);
 
 	return 0;
 }
 
-void bpf_bprintf_cleanup(void)
+void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
 {
-	if (this_cpu_read(bpf_bprintf_nest_level)) {
-		this_cpu_dec(bpf_bprintf_nest_level);
-		preempt_enable();
-	}
+	if (!data->bin_args && !data->buf)
+		return;
+	if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
+		return;
+	this_cpu_dec(bpf_bprintf_nest_level);
+	preempt_enable();
 }
 
 /*
@@ -792,18 +797,20 @@ void bpf_bprintf_cleanup(void)
  * Returns a negative value if fmt is an invalid format string or 0 otherwise.
  *
  * This can be used in two ways:
- * - Format string verification only: when bin_args is NULL
+ * - Format string verification only: when data->get_bin_args is false
  * - Arguments preparation: in addition to the above verification, it writes in
- *   bin_args a binary representation of arguments usable by bstr_printf where
- *   pointers from BPF have been sanitized.
+ *   data->bin_args a binary representation of arguments usable by bstr_printf
+ *   where pointers from BPF have been sanitized.
  *
  * In argument preparation mode, if 0 is returned, safe temporary buffers are
  * allocated and bpf_bprintf_cleanup should be called to free them after use.
  */
 int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
-			u32 **bin_args, u32 num_args)
+			u32 num_args, struct bpf_bprintf_data *data)
 {
+	bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
 	char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end;
+	struct bpf_bprintf_buffers *buffers = NULL;
 	size_t sizeof_cur_arg, sizeof_cur_ip;
 	int err, i, num_spec = 0;
 	u64 cur_arg;
@@ -814,14 +821,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 		return -EINVAL;
 	fmt_size = fmt_end - fmt;
 
-	if (bin_args) {
-		if (num_args && try_get_fmt_tmp_buf(&tmp_buf))
-			return -EBUSY;
+	if (get_buffers && try_get_buffers(&buffers))
+		return -EBUSY;
 
-		tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN;
-		*bin_args = (u32 *)tmp_buf;
+	if (data->get_bin_args) {
+		if (num_args)
+			tmp_buf = buffers->bin_args;
+		tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS;
+		data->bin_args = (u32 *)tmp_buf;
 	}
 
+	if (data->get_buf)
+		data->buf = buffers->buf;
+
 	for (i = 0; i < fmt_size; i++) {
 		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
 			err = -EINVAL;
@@ -1015,31 +1027,33 @@ nocopy_fmt:
 	err = 0;
 out:
 	if (err)
-		bpf_bprintf_cleanup();
+		bpf_bprintf_cleanup(data);
 	return err;
 }
 
 BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
-	   const void *, data, u32, data_len)
+	   const void *, args, u32, data_len)
 {
+	struct bpf_bprintf_data data = {
+		.get_bin_args	= true,
+	};
 	int err, num_args;
-	u32 *bin_args;
 
 	if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 ||
-	    (data_len && !data))
+	    (data_len && !args))
 		return -EINVAL;
 	num_args = data_len / 8;
 
 	/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
 	 * can safely give an unbounded size.
 	 */
-	err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args);
+	err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data);
 	if (err < 0)
 		return err;
 
-	err = bstr_printf(str, str_size, fmt, bin_args);
+	err = bstr_printf(str, str_size, fmt, data.bin_args);
 
-	bpf_bprintf_cleanup();
+	bpf_bprintf_cleanup(&data);
 
 	return err + 1;
 }
@@ -1077,6 +1091,7 @@ struct bpf_hrtimer {
 	struct bpf_prog *prog;
 	void __rcu *callback_fn;
 	void *value;
+	struct rcu_head rcu;
 };
 
 /* the actual struct hidden inside uapi struct bpf_timer */
@@ -1298,6 +1313,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer)
 
 	if (in_nmi())
 		return -EOPNOTSUPP;
+	rcu_read_lock();
 	__bpf_spin_lock_irqsave(&timer->lock);
 	t = timer->timer;
 	if (!t) {
@@ -1319,6 +1335,7 @@ out:
 	 * if it was running.
 	 */
 	ret = ret ?: hrtimer_cancel(&t->timer);
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -1373,7 +1390,7 @@ out:
 	 */
 	if (this_cpu_read(hrtimer_running) != t)
 		hrtimer_cancel(&t->timer);
-	kfree(t);
+	kfree_rcu(t, rcu);
 }
 
 BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8d0c38a8d..1e46a8469 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1598,6 +1598,9 @@ int generic_map_delete_batch(struct bpf_map *map,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
@@ -1657,6 +1660,9 @@ int generic_map_update_batch(struct bpf_map *map,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 23b6d57b5..1a29ac4db 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7448,6 +7448,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
 	struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
 	struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
 	struct bpf_map *fmt_map = fmt_reg->map_ptr;
+	struct bpf_bprintf_data data = {};
 	int err, fmt_map_off, num_args;
 	u64 fmt_addr;
 	char *fmt;
@@ -7472,7 +7473,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
 	/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
 	 * can focus on validating the format specifiers.
 	 */
-	err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args);
+	err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data);
 	if (err < 0)
 		verbose(env, "Invalid format string\n");