Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-04-28

The main changes are:

1) Add link detach and following re-attach for trampolines, from Jiri Olsa.

2) Use kernel's "binary printf" lib for formatted output BPF helpers (which
   avoids the needs for variadic argument handling), from Florent Revest.

3) Fix verifier 64 to 32 bit min/max bound propagation, from Daniel Borkmann.

4) Convert cpumap to use netif_receive_skb_list(), from Lorenzo Bianconi.

5) Add generic batched-ops support to percpu array map, from Pedro Tammela.

6) Various CO-RE relocation BPF selftests fixes, from Andrii Nakryiko.

7) Misc doc rst fixes, from Hengqi Chen.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  bpf, docs: Fix literal block for example code
  bpf, cpumap: Bulk skb using netif_receive_skb_list
  bpf: Fix propagation of 32 bit unsigned bounds from 64 bit bounds
  bpf: Lock bpf_trace_printk's tmp buf before it is written to
  selftests/bpf: Fix core_reloc test runner
  selftests/bpf: Fix field existence CO-RE reloc tests
  selftests/bpf: Fix BPF_CORE_READ_BITFIELD() macro
  libbpf: Support BTF_KIND_FLOAT during type compatibility checks in CO-RE
  selftests/bpf: Add remaining ASSERT_xxx() variants
  selftests/bpf: Use ASSERT macros in lsm test
  selftests/bpf: Test that module can't be unloaded with attached trampoline
  selftests/bpf: Add re-attach test to lsm test
  selftests/bpf: Add re-attach test to fexit_test
  selftests/bpf: Add re-attach test to fentry_test
  bpf: Allow trampoline re-attach for tracing and lsm programs
====================

Link: https://lore.kernel.org/r/20210427233740.22238-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 145 insertions, 136 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 463d25e1e67e..3c4105603f9d 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -698,6 +698,8 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_delete_elem = array_map_delete_elem,
 	.map_seq_show_elem = percpu_array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
+	.map_lookup_batch = generic_map_lookup_batch,
+	.map_update_batch = generic_map_update_batch,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_array_elem,
 	.map_btf_name = "bpf_array",
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 0cf2791d5099..5dd3e866599a 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -27,7 +27,7 @@
 #include <linux/capability.h>
 #include <trace/events/xdp.h>
 
-#include <linux/netdevice.h>   /* netif_receive_skb_core */
+#include <linux/netdevice.h>   /* netif_receive_skb_list */
 #include <linux/etherdevice.h> /* eth_type_trans */
 
 /* General idea: XDP packets getting XDP redirected to another CPU,
@@ -252,11 +252,12 @@ static int cpu_map_kthread_run(void *data)
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		unsigned int kmem_alloc_drops = 0, sched = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		unsigned int drops = 0, sched = 0;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
 		int i, n, m, nframes;
+		LIST_HEAD(list);
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -297,7 +298,7 @@ static int cpu_map_kthread_run(void *data)
 			if (unlikely(m == 0)) {
 				for (i = 0; i < nframes; i++)
 					skbs[i] = NULL; /* effect: xdp_return_frame */
-				drops += nframes;
+				kmem_alloc_drops += nframes;
 			}
 		}
 
@@ -305,7 +306,6 @@ static int cpu_map_kthread_run(void *data)
 		for (i = 0; i < nframes; i++) {
 			struct xdp_frame *xdpf = frames[i];
 			struct sk_buff *skb = skbs[i];
-			int ret;
 
 			skb = __xdp_build_skb_from_frame(xdpf, skb,
 							 xdpf->dev_rx);
@@ -314,13 +314,13 @@ static int cpu_map_kthread_run(void *data)
 				continue;
 			}
 
-			/* Inject into network stack */
-			ret = netif_receive_skb_core(skb);
-			if (ret == NET_RX_DROP)
-				drops++;
+			list_add_tail(&skb->list, &list);
 		}
+		netif_receive_skb_list(&list);
+
 		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
+					 sched, &stats);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 85b26ca5aacd..544773970dbc 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -707,9 +707,6 @@ static int try_get_fmt_tmp_buf(char **tmp_buf)
 	struct bpf_printf_buf *bufs;
 	int used;
 
-	if (*tmp_buf)
-		return 0;
-
 	preempt_disable();
 	used = this_cpu_inc_return(bpf_printf_buf_used);
 	if (WARN_ON_ONCE(used > 1)) {
@@ -723,7 +720,7 @@ static int try_get_fmt_tmp_buf(char **tmp_buf)
 	return 0;
 }
 
-void bpf_printf_cleanup(void)
+void bpf_bprintf_cleanup(void)
 {
 	if (this_cpu_read(bpf_printf_buf_used)) {
 		this_cpu_dec(bpf_printf_buf_used);
@@ -732,43 +729,45 @@ void bpf_printf_cleanup(void)
 }
 
 /*
- * bpf_parse_fmt_str - Generic pass on format strings for printf-like helpers
+ * bpf_bprintf_prepare - Generic pass on format strings for bprintf-like helpers
  *
  * 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 final_args and mod are NULL
+ * - Format string verification only: when bin_args is NULL
  * - Arguments preparation: in addition to the above verification, it writes in
- *   final_args a copy of raw_args where pointers from BPF have been sanitized
- *   into pointers safe to use by snprintf. This also writes in the mod array
- *   the size requirement of each argument, usable by BPF_CAST_FMT_ARG for ex.
+ *   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_printf_cleanup should be called to free them after use.
+ * allocated and bpf_bprintf_cleanup should be called to free them after use.
  */
-int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
-			u64 *final_args, enum bpf_printf_mod_type *mod,
-			u32 num_args)
+int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+			u32 **bin_args, u32 num_args)
 {
-	char *unsafe_ptr = NULL, *tmp_buf = NULL, *fmt_end;
-	size_t tmp_buf_len = MAX_PRINTF_BUF_LEN;
-	int err, i, num_spec = 0, copy_size;
-	enum bpf_printf_mod_type cur_mod;
+	char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end;
+	size_t sizeof_cur_arg, sizeof_cur_ip;
+	int err, i, num_spec = 0;
 	u64 cur_arg;
-	char fmt_ptype;
-
-	if (!!final_args != !!mod)
-		return -EINVAL;
+	char fmt_ptype, cur_ip[16], ip_spec[] = "%pXX";
 
 	fmt_end = strnchr(fmt, fmt_size, 0);
 	if (!fmt_end)
 		return -EINVAL;
 	fmt_size = fmt_end - fmt;
 
+	if (bin_args) {
+		if (num_args && try_get_fmt_tmp_buf(&tmp_buf))
+			return -EBUSY;
+
+		tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN;
+		*bin_args = (u32 *)tmp_buf;
+	}
+
 	for (i = 0; i < fmt_size; i++) {
 		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
 			err = -EINVAL;
-			goto cleanup;
+			goto out;
 		}
 
 		if (fmt[i] != '%')
@@ -781,7 +780,7 @@ int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 
 		if (num_spec >= num_args) {
 			err = -EINVAL;
-			goto cleanup;
+			goto out;
 		}
 
 		/* The string is zero-terminated so if fmt[i] != 0, we can
@@ -800,7 +799,7 @@ int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 		}
 
 		if (fmt[i] == 'p') {
-			cur_mod = BPF_PRINTF_LONG;
+			sizeof_cur_arg = sizeof(long);
 
 			if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
 			    fmt[i + 2] == 's') {
@@ -811,117 +810,140 @@ int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 
 			if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
 			    ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
-			    fmt[i + 1] == 'x' || fmt[i + 1] == 'B' ||
-			    fmt[i + 1] == 's' || fmt[i + 1] == 'S') {
+			    fmt[i + 1] == 'x' || fmt[i + 1] == 's' ||
+			    fmt[i + 1] == 'S') {
 				/* just kernel pointers */
-				if (final_args)
+				if (tmp_buf)
 					cur_arg = raw_args[num_spec];
-				goto fmt_next;
+				i++;
+				goto nocopy_fmt;
+			}
+
+			if (fmt[i + 1] == 'B') {
+				if (tmp_buf)  {
+					err = snprintf(tmp_buf,
+						       (tmp_buf_end - tmp_buf),
+						       "%pB",
+						       (void *)(long)raw_args[num_spec]);
+					tmp_buf += (err + 1);
+				}
+
+				i++;
+				num_spec++;
+				continue;
 			}
 
 			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
 			if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') ||
 			    (fmt[i + 2] != '4' && fmt[i + 2] != '6')) {
 				err = -EINVAL;
-				goto cleanup;
+				goto out;
 			}
 
 			i += 2;
-			if (!final_args)
-				goto fmt_next;
+			if (!tmp_buf)
+				goto nocopy_fmt;
 
-			if (try_get_fmt_tmp_buf(&tmp_buf)) {
-				err = -EBUSY;
-				goto out;
-			}
-
-			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
-			if (tmp_buf_len < copy_size) {
+			sizeof_cur_ip = (fmt[i] == '4') ? 4 : 16;
+			if (tmp_buf_end - tmp_buf < sizeof_cur_ip) {
 				err = -ENOSPC;
-				goto cleanup;
+				goto out;
 			}
 
 			unsafe_ptr = (char *)(long)raw_args[num_spec];
-			err = copy_from_kernel_nofault(tmp_buf, unsafe_ptr,
-						       copy_size);
+			err = copy_from_kernel_nofault(cur_ip, unsafe_ptr,
+						       sizeof_cur_ip);
 			if (err < 0)
-				memset(tmp_buf, 0, copy_size);
-			cur_arg = (u64)(long)tmp_buf;
-			tmp_buf += copy_size;
-			tmp_buf_len -= copy_size;
+				memset(cur_ip, 0, sizeof_cur_ip);
+
+			/* hack: bstr_printf expects IP addresses to be
+			 * pre-formatted as strings, ironically, the easiest way
+			 * to do that is to call snprintf.
+			 */
+			ip_spec[2] = fmt[i - 1];
+			ip_spec[3] = fmt[i];
+			err = snprintf(tmp_buf, tmp_buf_end - tmp_buf,
+				       ip_spec, &cur_ip);
 
-			goto fmt_next;
+			tmp_buf += err + 1;
+			num_spec++;
+
+			continue;
 		} else if (fmt[i] == 's') {
-			cur_mod = BPF_PRINTF_LONG;
 			fmt_ptype = fmt[i];
 fmt_str:
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
 			    !ispunct(fmt[i + 1])) {
 				err = -EINVAL;
-				goto cleanup;
-			}
-
-			if (!final_args)
-				goto fmt_next;
-
-			if (try_get_fmt_tmp_buf(&tmp_buf)) {
-				err = -EBUSY;
 				goto out;
 			}
 
-			if (!tmp_buf_len) {
+			if (!tmp_buf)
+				goto nocopy_fmt;
+
+			if (tmp_buf_end == tmp_buf) {
 				err = -ENOSPC;
-				goto cleanup;
+				goto out;
 			}
 
 			unsafe_ptr = (char *)(long)raw_args[num_spec];
 			err = bpf_trace_copy_string(tmp_buf, unsafe_ptr,
-						    fmt_ptype, tmp_buf_len);
+						    fmt_ptype,
+						    tmp_buf_end - tmp_buf);
 			if (err < 0) {
 				tmp_buf[0] = '\0';
 				err = 1;
 			}
 
-			cur_arg = (u64)(long)tmp_buf;
 			tmp_buf += err;
-			tmp_buf_len -= err;
+			num_spec++;
 
-			goto fmt_next;
+			continue;
 		}
 
-		cur_mod = BPF_PRINTF_INT;
+		sizeof_cur_arg = sizeof(int);
 
 		if (fmt[i] == 'l') {
-			cur_mod = BPF_PRINTF_LONG;
+			sizeof_cur_arg = sizeof(long);
 			i++;
 		}
 		if (fmt[i] == 'l') {
-			cur_mod = BPF_PRINTF_LONG_LONG;
+			sizeof_cur_arg = sizeof(long long);
 			i++;
 		}
 
 		if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' &&
 		    fmt[i] != 'x' && fmt[i] != 'X') {
 			err = -EINVAL;
-			goto cleanup;
+			goto out;
 		}
 
-		if (final_args)
+		if (tmp_buf)
 			cur_arg = raw_args[num_spec];
-fmt_next:
-		if (final_args) {
-			mod[num_spec] = cur_mod;
-			final_args[num_spec] = cur_arg;
+nocopy_fmt:
+		if (tmp_buf) {
+			tmp_buf = PTR_ALIGN(tmp_buf, sizeof(u32));
+			if (tmp_buf_end - tmp_buf < sizeof_cur_arg) {
+				err = -ENOSPC;
+				goto out;
+			}
+
+			if (sizeof_cur_arg == 8) {
+				*(u32 *)tmp_buf = *(u32 *)&cur_arg;
+				*(u32 *)(tmp_buf + 4) = *((u32 *)&cur_arg + 1);
+			} else {
+				*(u32 *)tmp_buf = (u32)(long)cur_arg;
+			}
+			tmp_buf += sizeof_cur_arg;
 		}
 		num_spec++;
 	}
 
 	err = 0;
-cleanup:
-	if (err)
-		bpf_printf_cleanup();
 out:
+	if (err)
+		bpf_bprintf_cleanup();
 	return err;
 }
 
@@ -930,9 +952,8 @@ out:
 BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
 	   const void *, data, u32, data_len)
 {
-	enum bpf_printf_mod_type mod[MAX_SNPRINTF_VARARGS];
-	u64 args[MAX_SNPRINTF_VARARGS];
 	int err, num_args;
+	u32 *bin_args;
 
 	if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
 	    (data_len && !data))
@@ -942,22 +963,13 @@ BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
 	/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
 	 * can safely give an unbounded size.
 	 */
-	err = bpf_printf_prepare(fmt, UINT_MAX, data, args, mod, num_args);
+	err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args);
 	if (err < 0)
 		return err;
 
-	/* Maximumly we can have MAX_SNPRINTF_VARARGS parameters, just give
-	 * all of them to snprintf().
-	 */
-	err = snprintf(str, str_size, fmt, BPF_CAST_FMT_ARG(0, args, mod),
-		BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
-		BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
-		BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
-		BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
-		BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
-		BPF_CAST_FMT_ARG(11, args, mod));
-
-	bpf_printf_cleanup();
+	err = bstr_printf(str, str_size, fmt, bin_args);
+
+	bpf_bprintf_cleanup();
 
 	return err + 1;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fd495190115e..941ca06d9dfa 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2648,14 +2648,25 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	 *   target_btf_id using the link_create API.
 	 *
 	 * - if tgt_prog == NULL when this function was called using the old
-         *   raw_tracepoint_open API, and we need a target from prog->aux
-         *
-         * The combination of no saved target in prog->aux, and no target
-         * specified on load is illegal, and we reject that here.
+	 *   raw_tracepoint_open API, and we need a target from prog->aux
+	 *
+	 * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program
+	 *   was detached and is going for re-attachment.
 	 */
 	if (!prog->aux->dst_trampoline && !tgt_prog) {
-		err = -ENOENT;
-		goto out_unlock;
+		/*
+		 * Allow re-attach for TRACING and LSM programs. If it's
+		 * currently linked, bpf_trampoline_link_prog will fail.
+		 * EXT programs need to specify tgt_prog_fd, so they
+		 * re-attach in separate code path.
+		 */
+		if (prog->type != BPF_PROG_TYPE_TRACING &&
+		    prog->type != BPF_PROG_TYPE_LSM) {
+			err = -EINVAL;
+			goto out_unlock;
+		}
+		btf_id = prog->aux->attach_btf_id;
+		key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id);
 	}
 
 	if (!prog->aux->dst_trampoline ||
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 4aa8b52adf25..2d44b5aa0057 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -444,7 +444,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 	tr->progs_cnt[kind]++;
 	err = bpf_trampoline_update(tr);
 	if (err) {
-		hlist_del(&prog->aux->tramp_hlist);
+		hlist_del_init(&prog->aux->tramp_hlist);
 		tr->progs_cnt[kind]--;
 	}
 out:
@@ -467,7 +467,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 		tr->extension_prog = NULL;
 		goto out;
 	}
-	hlist_del(&prog->aux->tramp_hlist);
+	hlist_del_init(&prog->aux->tramp_hlist);
 	tr->progs_cnt[kind]--;
 	err = bpf_trampoline_update(tr);
 out:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 637462e9b6ee..8fd552c16763 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1398,9 +1398,7 @@ static bool __reg64_bound_s32(s64 a)
 
 static bool __reg64_bound_u32(u64 a)
 {
-	if (a > U32_MIN && a < U32_MAX)
-		return true;
-	return false;
+	return a > U32_MIN && a < U32_MAX;
 }
 
 static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
@@ -1411,10 +1409,10 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
 		reg->s32_min_value = (s32)reg->smin_value;
 		reg->s32_max_value = (s32)reg->smax_value;
 	}
-	if (__reg64_bound_u32(reg->umin_value))
+	if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
 		reg->u32_min_value = (u32)reg->umin_value;
-	if (__reg64_bound_u32(reg->umax_value))
 		reg->u32_max_value = (u32)reg->umax_value;
+	}
 
 	/* Intersecting with the old var_off might have improved our bounds
 	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
@@ -5948,7 +5946,7 @@ 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_printf_prepare(fmt, UINT_MAX, NULL, NULL, NULL, num_args);
+	err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args);
 	if (err < 0)
 		verbose(env, "Invalid format string\n");
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2a8bcdc927c7..d2d7cf6cfe83 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -381,27 +381,23 @@ 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 };
-	enum bpf_printf_mod_type mod[MAX_TRACE_PRINTK_VARARGS];
+	u32 *bin_args;
 	static char buf[BPF_TRACE_PRINTK_SIZE];
 	unsigned long flags;
 	int ret;
 
-	ret = bpf_printf_prepare(fmt, fmt_size, args, args, mod,
-				 MAX_TRACE_PRINTK_VARARGS);
+	ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args,
+				  MAX_TRACE_PRINTK_VARARGS);
 	if (ret < 0)
 		return ret;
 
-	ret = snprintf(buf, sizeof(buf), fmt, BPF_CAST_FMT_ARG(0, args, mod),
-		BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod));
-	/* snprintf() will not append null for zero-length strings */
-	if (ret == 0)
-		buf[0] = '\0';
-
 	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+
 	trace_bpf_trace_printk(buf);
 	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
 
-	bpf_printf_cleanup();
+	bpf_bprintf_cleanup();
 
 	return ret;
 }
@@ -435,31 +431,21 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 	   const void *, data, u32, data_len)
 {
-	enum bpf_printf_mod_type mod[MAX_SEQ_PRINTF_VARARGS];
-	u64 args[MAX_SEQ_PRINTF_VARARGS];
 	int err, num_args;
+	u32 *bin_args;
 
 	if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 ||
 	    (data_len && !data))
 		return -EINVAL;
 	num_args = data_len / 8;
 
-	err = bpf_printf_prepare(fmt, fmt_size, data, args, mod, num_args);
+	err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
 	if (err < 0)
 		return err;
 
-	/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
-	 * all of them to seq_printf().
-	 */
-	seq_printf(m, fmt, BPF_CAST_FMT_ARG(0, args, mod),
-		BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
-		BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
-		BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
-		BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
-		BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
-		BPF_CAST_FMT_ARG(11, args, mod));
-
-	bpf_printf_cleanup();
+	seq_bprintf(m, fmt, bin_args);
+
+	bpf_bprintf_cleanup();
 
 	return seq_has_overflowed(m) ? -EOVERFLOW : 0;
 }