1 files changed, 146 insertions, 44 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1ed08967fb97..e8da032bb6fc 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
 #include <linux/bpf_perf_event.h>
 #include <linux/btf.h>
 #include <linux/filter.h>
@@ -368,8 +369,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
 	return &bpf_probe_write_user_proto;
 }
 
-static DEFINE_RAW_SPINLOCK(trace_printk_lock);
-
 #define MAX_TRACE_PRINTK_VARARGS	3
 #define BPF_TRACE_PRINTK_SIZE		1024
 
@@ -377,23 +376,22 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
 {
 	u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 };
-	u32 *bin_args;
-	static char buf[BPF_TRACE_PRINTK_SIZE];
-	unsigned long flags;
+	struct bpf_bprintf_data data = {
+		.get_bin_args	= true,
+		.get_buf	= true,
+	};
 	int ret;
 
-	ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args,
-				  MAX_TRACE_PRINTK_VARARGS);
+	ret = bpf_bprintf_prepare(fmt, fmt_size, args,
+				  MAX_TRACE_PRINTK_VARARGS, &data);
 	if (ret < 0)
 		return ret;
 
-	raw_spin_lock_irqsave(&trace_printk_lock, flags);
-	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+	ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args);
 
-	trace_bpf_trace_printk(buf);
-	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+	trace_bpf_trace_printk(data.buf);
 
-	bpf_bprintf_cleanup();
+	bpf_bprintf_cleanup(&data);
 
 	return ret;
 }
@@ -426,30 +424,29 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
-BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data,
+BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args,
 	   u32, data_len)
 {
-	static char buf[BPF_TRACE_PRINTK_SIZE];
-	unsigned long flags;
+	struct bpf_bprintf_data data = {
+		.get_bin_args	= true,
+		.get_buf	= true,
+	};
 	int ret, num_args;
-	u32 *bin_args;
 
 	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
-	    (data_len && !data))
+	    (data_len && !args))
 		return -EINVAL;
 	num_args = data_len / 8;
 
-	ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+	ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data);
 	if (ret < 0)
 		return ret;
 
-	raw_spin_lock_irqsave(&trace_printk_lock, flags);
-	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+	ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args);
 
-	trace_bpf_trace_printk(buf);
-	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+	trace_bpf_trace_printk(data.buf);
 
-	bpf_bprintf_cleanup();
+	bpf_bprintf_cleanup(&data);
 
 	return ret;
 }
@@ -471,23 +468,25 @@ const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void)
 }
 
 BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
-	   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 & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
-	    (data_len && !data))
+	    (data_len && !args))
 		return -EINVAL;
 	num_args = data_len / 8;
 
-	err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+	err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data);
 	if (err < 0)
 		return err;
 
-	seq_bprintf(m, fmt, bin_args);
+	seq_bprintf(m, fmt, data.bin_args);
 
-	bpf_bprintf_cleanup();
+	bpf_bprintf_cleanup(&data);
 
 	return seq_has_overflowed(m) ? -EOVERFLOW : 0;
 }
@@ -686,8 +685,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	}
 
 	perf_sample_data_init(sd, 0, 0);
-	sd->raw = &raw;
-	sd->sample_flags |= PERF_SAMPLE_RAW;
+	perf_sample_save_raw_data(sd, &raw);
 
 	err = __bpf_perf_event_output(regs, map, flags, sd);
 
@@ -745,8 +743,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
-	sd->raw = &raw;
-	sd->sample_flags |= PERF_SAMPLE_RAW;
+	perf_sample_save_raw_data(sd, &raw);
 
 	ret = __bpf_perf_event_output(regs, map, flags, sd);
 out:
@@ -773,7 +770,7 @@ BPF_CALL_0(bpf_get_current_task_btf)
 const struct bpf_func_proto bpf_get_current_task_btf_proto = {
 	.func		= bpf_get_current_task_btf,
 	.gpl_only	= true,
-	.ret_type	= RET_PTR_TO_BTF_ID,
+	.ret_type	= RET_PTR_TO_BTF_ID_TRUSTED,
 	.ret_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 };
 
@@ -832,6 +829,7 @@ static void do_bpf_send_signal(struct irq_work *entry)
 
 	work = container_of(entry, struct send_signal_irq_work, irq_work);
 	group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
+	put_task_struct(work->task);
 }
 
 static int bpf_send_signal_common(u32 sig, enum pid_type type)
@@ -847,6 +845,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
+	/* Task should not be pid=1 to avoid kernel panic. */
+	if (unlikely(is_global_init(current)))
+		return -EPERM;
 
 	if (irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,
@@ -863,7 +864,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		 * to the irq_work. The current task may change when queued
 		 * irq works get executed.
 		 */
-		work->task = current;
+		work->task = get_task_struct(current);
 		work->sig = sig;
 		work->type = type;
 		irq_work_queue(&work->irq_work);
@@ -1234,7 +1235,7 @@ __diag_ignore_all("-Wmissing-prototypes",
  * Return: a bpf_key pointer with a valid key pointer if the key is found, a
  *         NULL pointer otherwise.
  */
-struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+__bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
 {
 	key_ref_t key_ref;
 	struct bpf_key *bkey;
@@ -1283,7 +1284,7 @@ struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
  * Return: a bpf_key pointer with an invalid key pointer set from the
  *         pre-determined ID on success, a NULL pointer otherwise
  */
-struct bpf_key *bpf_lookup_system_key(u64 id)
+__bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id)
 {
 	struct bpf_key *bkey;
 
@@ -1307,7 +1308,7 @@ struct bpf_key *bpf_lookup_system_key(u64 id)
  * Decrement the reference count of the key inside *bkey*, if the pointer
  * is valid, and free *bkey*.
  */
-void bpf_key_put(struct bpf_key *bkey)
+__bpf_kfunc void bpf_key_put(struct bpf_key *bkey)
 {
 	if (bkey->has_ref)
 		key_put(bkey->key);
@@ -1327,7 +1328,7 @@ void bpf_key_put(struct bpf_key *bkey)
  *
  * Return: 0 on success, a negative value on error.
  */
-int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
+__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 			       struct bpf_dynptr_kern *sig_ptr,
 			       struct bpf_key *trusted_keyring)
 {
@@ -1456,6 +1457,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_get_current_ancestor_cgroup_id:
 		return &bpf_get_current_ancestor_cgroup_id_proto;
+	case BPF_FUNC_cgrp_storage_get:
+		return &bpf_cgrp_storage_get_proto;
+	case BPF_FUNC_cgrp_storage_delete:
+		return &bpf_cgrp_storage_delete_proto;
 #endif
 	case BPF_FUNC_send_signal:
 		return &bpf_send_signal_proto;
@@ -1480,9 +1485,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_task_stack:
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
-		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+		return &bpf_copy_from_user_proto;
 	case BPF_FUNC_copy_from_user_task:
-		return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL;
+		return &bpf_copy_from_user_task_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_per_cpu_ptr:
@@ -1490,8 +1495,12 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_this_cpu_ptr:
 		return &bpf_this_cpu_ptr_proto;
 	case BPF_FUNC_task_storage_get:
+		if (bpf_prog_check_recur(prog))
+			return &bpf_task_storage_get_recur_proto;
 		return &bpf_task_storage_get_proto;
 	case BPF_FUNC_task_storage_delete:
+		if (bpf_prog_check_recur(prog))
+			return &bpf_task_storage_delete_recur_proto;
 		return &bpf_task_storage_delete_proto;
 	case BPF_FUNC_for_each_map_elem:
 		return &bpf_for_each_map_elem_proto;
@@ -2452,6 +2461,8 @@ struct bpf_kprobe_multi_link {
 	unsigned long *addrs;
 	u64 *cookies;
 	u32 cnt;
+	u32 mods_cnt;
+	struct module **mods;
 };
 
 struct bpf_kprobe_multi_run_ctx {
@@ -2507,6 +2518,14 @@ error:
 	return err;
 }
 
+static void kprobe_multi_put_modules(struct module **mods, u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++)
+		module_put(mods[i]);
+}
+
 static void free_user_syms(struct user_syms *us)
 {
 	kvfree(us->syms);
@@ -2519,6 +2538,7 @@ static void bpf_kprobe_multi_link_release(struct bpf_link *link)
 
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
 	unregister_fprobe(&kmulti_link->fp);
+	kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt);
 }
 
 static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
@@ -2528,6 +2548,7 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
 	kvfree(kmulti_link->addrs);
 	kvfree(kmulti_link->cookies);
+	kfree(kmulti_link->mods);
 	kfree(kmulti_link);
 }
 
@@ -2550,7 +2571,7 @@ static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void
 	swap(*cookie_a, *cookie_b);
 }
 
-static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b)
+static int bpf_kprobe_multi_addrs_cmp(const void *a, const void *b)
 {
 	const unsigned long *addr_a = a, *addr_b = b;
 
@@ -2561,7 +2582,7 @@ static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b)
 
 static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv)
 {
-	return __bpf_kprobe_multi_cookie_cmp(a, b);
+	return bpf_kprobe_multi_addrs_cmp(a, b);
 }
 
 static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
@@ -2579,7 +2600,7 @@ static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
 		return 0;
 	entry_ip = run_ctx->entry_ip;
 	addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip),
-		       __bpf_kprobe_multi_cookie_cmp);
+		       bpf_kprobe_multi_addrs_cmp);
 	if (!addr)
 		return 0;
 	cookie = link->cookies + (addr - link->addrs);
@@ -2663,6 +2684,79 @@ static void symbols_swap_r(void *a, void *b, int size, const void *priv)
 	}
 }
 
+struct modules_array {
+	struct module **mods;
+	int mods_cnt;
+	int mods_cap;
+};
+
+static int add_module(struct modules_array *arr, struct module *mod)
+{
+	struct module **mods;
+
+	if (arr->mods_cnt == arr->mods_cap) {
+		arr->mods_cap = max(16, arr->mods_cap * 3 / 2);
+		mods = krealloc_array(arr->mods, arr->mods_cap, sizeof(*mods), GFP_KERNEL);
+		if (!mods)
+			return -ENOMEM;
+		arr->mods = mods;
+	}
+
+	arr->mods[arr->mods_cnt] = mod;
+	arr->mods_cnt++;
+	return 0;
+}
+
+static bool has_module(struct modules_array *arr, struct module *mod)
+{
+	int i;
+
+	for (i = arr->mods_cnt - 1; i >= 0; i--) {
+		if (arr->mods[i] == mod)
+			return true;
+	}
+	return false;
+}
+
+static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u32 addrs_cnt)
+{
+	struct modules_array arr = {};
+	u32 i, err = 0;
+
+	for (i = 0; i < addrs_cnt; i++) {
+		struct module *mod;
+
+		preempt_disable();
+		mod = __module_address(addrs[i]);
+		/* Either no module or we it's already stored  */
+		if (!mod || has_module(&arr, mod)) {
+			preempt_enable();
+			continue;
+		}
+		if (!try_module_get(mod))
+			err = -EINVAL;
+		preempt_enable();
+		if (err)
+			break;
+		err = add_module(&arr, mod);
+		if (err) {
+			module_put(mod);
+			break;
+		}
+	}
+
+	/* We return either err < 0 in case of error, ... */
+	if (err) {
+		kprobe_multi_put_modules(arr.mods, arr.mods_cnt);
+		kfree(arr.mods);
+		return err;
+	}
+
+	/* or number of modules found if everything is ok. */
+	*mods = arr.mods;
+	return arr.mods_cnt;
+}
+
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_kprobe_multi_link *link = NULL;
@@ -2775,8 +2869,16 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		       link);
 	}
 
+	err = get_modules_for_addrs(&link->mods, addrs, cnt);
+	if (err < 0) {
+		bpf_link_cleanup(&link_primer);
+		return err;
+	}
+	link->mods_cnt = err;
+
 	err = register_fprobe_ips(&link->fp, addrs, cnt);
 	if (err) {
+		kprobe_multi_put_modules(link->mods, link->mods_cnt);
 		bpf_link_cleanup(&link_primer);
 		return err;
 	}