Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

6 files changed, 513 insertions, 35 deletions

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index b3073ae84018..d73232be1e99 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -136,7 +136,7 @@ endif
 
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
 
-BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o)
+BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
@@ -180,6 +180,9 @@ endif
 
 CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)
 
+$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
+	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
 
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 31ade77f5ef8..1d71ff8c52fa 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -18,6 +18,7 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <bpf/btf.h>
+#include <bpf/bpf_gen_internal.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -106,8 +107,10 @@ static int codegen_datasec_def(struct bpf_object *obj,
 
 	if (strcmp(sec_name, ".data") == 0) {
 		sec_ident = "data";
+		strip_mods = true;
 	} else if (strcmp(sec_name, ".bss") == 0) {
 		sec_ident = "bss";
+		strip_mods = true;
 	} else if (strcmp(sec_name, ".rodata") == 0) {
 		sec_ident = "rodata";
 		strip_mods = true;
@@ -129,6 +132,10 @@ static int codegen_datasec_def(struct bpf_object *obj,
 		int need_off = sec_var->offset, align_off, align;
 		__u32 var_type_id = var->type;
 
+		/* static variables are not exposed through BPF skeleton */
+		if (btf_var(var)->linkage == BTF_VAR_STATIC)
+			continue;
+
 		if (off > need_off) {
 			p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n",
 			      sec_name, i, need_off, off);
@@ -268,6 +275,327 @@ static void codegen(const char *template, ...)
 	free(s);
 }
 
+static void print_hex(const char *data, int data_sz)
+{
+	int i, len;
+
+	for (i = 0, len = 0; i < data_sz; i++) {
+		int w = data[i] ? 4 : 2;
+
+		len += w;
+		if (len > 78) {
+			printf("\\\n");
+			len = w;
+		}
+		if (!data[i])
+			printf("\\0");
+		else
+			printf("\\x%02x", (unsigned char)data[i]);
+	}
+}
+
+static size_t bpf_map_mmap_sz(const struct bpf_map *map)
+{
+	long page_sz = sysconf(_SC_PAGE_SIZE);
+	size_t map_sz;
+
+	map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map);
+	map_sz = roundup(map_sz, page_sz);
+	return map_sz;
+}
+
+static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name)
+{
+	struct bpf_program *prog;
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *tp_name;
+
+		codegen("\
+			\n\
+			\n\
+			static inline int					    \n\
+			%1$s__%2$s__attach(struct %1$s *skel)			    \n\
+			{							    \n\
+				int prog_fd = skel->progs.%2$s.prog_fd;		    \n\
+			", obj_name, bpf_program__name(prog));
+
+		switch (bpf_program__get_type(prog)) {
+		case BPF_PROG_TYPE_RAW_TRACEPOINT:
+			tp_name = strchr(bpf_program__section_name(prog), '/') + 1;
+			printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name);
+			break;
+		case BPF_PROG_TYPE_TRACING:
+			printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n");
+			break;
+		default:
+			printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n");
+			break;
+		}
+		codegen("\
+			\n\
+										    \n\
+				if (fd > 0)					    \n\
+					skel->links.%1$s_fd = fd;		    \n\
+				return fd;					    \n\
+			}							    \n\
+			", bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+									    \n\
+		static inline int					    \n\
+		%1$s__attach(struct %1$s *skel)				    \n\
+		{							    \n\
+			int ret = 0;					    \n\
+									    \n\
+		", obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				ret = ret < 0 ? ret : %1$s__%2$s__attach(skel);   \n\
+			", obj_name, bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+			return ret < 0 ? ret : 0;			    \n\
+		}							    \n\
+									    \n\
+		static inline void					    \n\
+		%1$s__detach(struct %1$s *skel)				    \n\
+		{							    \n\
+		", obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				skel_closenz(skel->links.%1$s_fd);	    \n\
+			", bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+		}							    \n\
+		");
+}
+
+static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+
+	codegen("\
+		\n\
+		static void						    \n\
+		%1$s__destroy(struct %1$s *skel)			    \n\
+		{							    \n\
+			if (!skel)					    \n\
+				return;					    \n\
+			%1$s__detach(skel);				    \n\
+		",
+		obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				skel_closenz(skel->progs.%1$s.prog_fd);	    \n\
+			", bpf_program__name(prog));
+	}
+
+	bpf_object__for_each_map(map, obj) {
+		const char * ident;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+		if (bpf_map__is_internal(map) &&
+		    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			printf("\tmunmap(skel->%1$s, %2$zd);\n",
+			       ident, bpf_map_mmap_sz(map));
+		codegen("\
+			\n\
+				skel_closenz(skel->maps.%1$s.map_fd);	    \n\
+			", ident);
+	}
+	codegen("\
+		\n\
+			free(skel);					    \n\
+		}							    \n\
+		",
+		obj_name);
+}
+
+static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard)
+{
+	struct bpf_object_load_attr load_attr = {};
+	DECLARE_LIBBPF_OPTS(gen_loader_opts, opts);
+	struct bpf_map *map;
+	int err = 0;
+
+	err = bpf_object__gen_loader(obj, &opts);
+	if (err)
+		return err;
+
+	load_attr.obj = obj;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		load_attr.log_level = 1 + 2 + 4;
+
+	err = bpf_object__load_xattr(&load_attr);
+	if (err) {
+		p_err("failed to load object file");
+		goto out;
+	}
+	/* If there was no error during load then gen_loader_opts
+	 * are populated with the loader program.
+	 */
+
+	/* finish generating 'struct skel' */
+	codegen("\
+		\n\
+		};							    \n\
+		", obj_name);
+
+
+	codegen_attach_detach(obj, obj_name);
+
+	codegen_destroy(obj, obj_name);
+
+	codegen("\
+		\n\
+		static inline struct %1$s *				    \n\
+		%1$s__open(void)					    \n\
+		{							    \n\
+			struct %1$s *skel;				    \n\
+									    \n\
+			skel = calloc(sizeof(*skel), 1);		    \n\
+			if (!skel)					    \n\
+				goto cleanup;				    \n\
+			skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\
+		",
+		obj_name, opts.data_sz);
+	bpf_object__for_each_map(map, obj) {
+		const char *ident;
+		const void *mmap_data = NULL;
+		size_t mmap_size = 0;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+
+		if (!bpf_map__is_internal(map) ||
+		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			continue;
+
+		codegen("\
+			\n\
+				skel->%1$s =					 \n\
+					mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\
+					     MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\
+				if (skel->%1$s == (void *) -1)			 \n\
+					goto cleanup;				 \n\
+				memcpy(skel->%1$s, (void *)\"\\			 \n\
+			", ident, bpf_map_mmap_sz(map));
+		mmap_data = bpf_map__initial_value(map, &mmap_size);
+		print_hex(mmap_data, mmap_size);
+		printf("\", %2$zd);\n"
+		       "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n",
+		       ident, mmap_size);
+	}
+	codegen("\
+		\n\
+			return skel;					    \n\
+		cleanup:						    \n\
+			%1$s__destroy(skel);				    \n\
+			return NULL;					    \n\
+		}							    \n\
+									    \n\
+		static inline int					    \n\
+		%1$s__load(struct %1$s *skel)				    \n\
+		{							    \n\
+			struct bpf_load_and_run_opts opts = {};		    \n\
+			int err;					    \n\
+									    \n\
+			opts.ctx = (struct bpf_loader_ctx *)skel;	    \n\
+			opts.data_sz = %2$d;				    \n\
+			opts.data = (void *)\"\\			    \n\
+		",
+		obj_name, opts.data_sz);
+	print_hex(opts.data, opts.data_sz);
+	codegen("\
+		\n\
+		\";							    \n\
+		");
+
+	codegen("\
+		\n\
+			opts.insns_sz = %d;				    \n\
+			opts.insns = (void *)\"\\			    \n\
+		",
+		opts.insns_sz);
+	print_hex(opts.insns, opts.insns_sz);
+	codegen("\
+		\n\
+		\";							    \n\
+			err = bpf_load_and_run(&opts);			    \n\
+			if (err < 0)					    \n\
+				return err;				    \n\
+		", obj_name);
+	bpf_object__for_each_map(map, obj) {
+		const char *ident, *mmap_flags;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+
+		if (!bpf_map__is_internal(map) ||
+		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			continue;
+		if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
+			mmap_flags = "PROT_READ";
+		else
+			mmap_flags = "PROT_READ | PROT_WRITE";
+
+		printf("\tskel->%1$s =\n"
+		       "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n"
+		       "\t\t\tskel->maps.%1$s.map_fd, 0);\n",
+		       ident, bpf_map_mmap_sz(map), mmap_flags);
+	}
+	codegen("\
+		\n\
+			return 0;					    \n\
+		}							    \n\
+									    \n\
+		static inline struct %1$s *				    \n\
+		%1$s__open_and_load(void)				    \n\
+		{							    \n\
+			struct %1$s *skel;				    \n\
+									    \n\
+			skel = %1$s__open();				    \n\
+			if (!skel)					    \n\
+				return NULL;				    \n\
+			if (%1$s__load(skel)) {				    \n\
+				%1$s__destroy(skel);			    \n\
+				return NULL;				    \n\
+			}						    \n\
+			return skel;					    \n\
+		}							    \n\
+		", obj_name);
+
+	codegen("\
+		\n\
+									    \n\
+		#endif /* %s */						    \n\
+		",
+		header_guard);
+	err = 0;
+out:
+	return err;
+}
+
 static int do_skeleton(int argc, char **argv)
 {
 	char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")];
@@ -277,7 +605,7 @@ static int do_skeleton(int argc, char **argv)
 	struct bpf_object *obj = NULL;
 	const char *file, *ident;
 	struct bpf_program *prog;
-	int fd, len, err = -1;
+	int fd, err = -1;
 	struct bpf_map *map;
 	struct btf *btf;
 	struct stat st;
@@ -359,7 +687,25 @@ static int do_skeleton(int argc, char **argv)
 	}
 
 	get_header_guard(header_guard, obj_name);
-	codegen("\
+	if (use_loader) {
+		codegen("\
+		\n\
+		/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */   \n\
+		/* THIS FILE IS AUTOGENERATED! */			    \n\
+		#ifndef %2$s						    \n\
+		#define %2$s						    \n\
+									    \n\
+		#include <stdlib.h>					    \n\
+		#include <bpf/bpf.h>					    \n\
+		#include <bpf/skel_internal.h>				    \n\
+									    \n\
+		struct %1$s {						    \n\
+			struct bpf_loader_ctx ctx;			    \n\
+		",
+		obj_name, header_guard
+		);
+	} else {
+		codegen("\
 		\n\
 		/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */   \n\
 									    \n\
@@ -367,6 +713,7 @@ static int do_skeleton(int argc, char **argv)
 		#ifndef %2$s						    \n\
 		#define %2$s						    \n\
 									    \n\
+		#include <errno.h>					    \n\
 		#include <stdlib.h>					    \n\
 		#include <bpf/libbpf.h>					    \n\
 									    \n\
@@ -375,7 +722,8 @@ static int do_skeleton(int argc, char **argv)
 			struct bpf_object *obj;				    \n\
 		",
 		obj_name, header_guard
-	);
+		);
+	}
 
 	if (map_cnt) {
 		printf("\tstruct {\n");
@@ -383,7 +731,10 @@ static int do_skeleton(int argc, char **argv)
 			ident = get_map_ident(map);
 			if (!ident)
 				continue;
-			printf("\t\tstruct bpf_map *%s;\n", ident);
+			if (use_loader)
+				printf("\t\tstruct bpf_map_desc %s;\n", ident);
+			else
+				printf("\t\tstruct bpf_map *%s;\n", ident);
 		}
 		printf("\t} maps;\n");
 	}
@@ -391,14 +742,22 @@ static int do_skeleton(int argc, char **argv)
 	if (prog_cnt) {
 		printf("\tstruct {\n");
 		bpf_object__for_each_program(prog, obj) {
-			printf("\t\tstruct bpf_program *%s;\n",
-			       bpf_program__name(prog));
+			if (use_loader)
+				printf("\t\tstruct bpf_prog_desc %s;\n",
+				       bpf_program__name(prog));
+			else
+				printf("\t\tstruct bpf_program *%s;\n",
+				       bpf_program__name(prog));
 		}
 		printf("\t} progs;\n");
 		printf("\tstruct {\n");
 		bpf_object__for_each_program(prog, obj) {
-			printf("\t\tstruct bpf_link *%s;\n",
-			       bpf_program__name(prog));
+			if (use_loader)
+				printf("\t\tint %s_fd;\n",
+				       bpf_program__name(prog));
+			else
+				printf("\t\tstruct bpf_link *%s;\n",
+				       bpf_program__name(prog));
 		}
 		printf("\t} links;\n");
 	}
@@ -409,6 +768,10 @@ static int do_skeleton(int argc, char **argv)
 		if (err)
 			goto out;
 	}
+	if (use_loader) {
+		err = gen_trace(obj, obj_name, header_guard);
+		goto out;
+	}
 
 	codegen("\
 		\n\
@@ -431,18 +794,23 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__open_opts(const struct bpf_object_open_opts *opts)    \n\
 		{							    \n\
 			struct %1$s *obj;				    \n\
+			int err;					    \n\
 									    \n\
 			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
-			if (!obj)					    \n\
+			if (!obj) {					    \n\
+				errno = ENOMEM;				    \n\
 				return NULL;				    \n\
-			if (%1$s__create_skeleton(obj))			    \n\
-				goto err;				    \n\
-			if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\
-				goto err;				    \n\
+			}						    \n\
+									    \n\
+			err = %1$s__create_skeleton(obj);		    \n\
+			err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\
+			if (err)					    \n\
+				goto err_out;				    \n\
 									    \n\
 			return obj;					    \n\
-		err:							    \n\
+		err_out:						    \n\
 			%1$s__destroy(obj);				    \n\
+			errno = -err;					    \n\
 			return NULL;					    \n\
 		}							    \n\
 									    \n\
@@ -462,12 +830,15 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__open_and_load(void)				    \n\
 		{							    \n\
 			struct %1$s *obj;				    \n\
+			int err;					    \n\
 									    \n\
 			obj = %1$s__open();				    \n\
 			if (!obj)					    \n\
 				return NULL;				    \n\
-			if (%1$s__load(obj)) {				    \n\
+			err = %1$s__load(obj);				    \n\
+			if (err) {					    \n\
 				%1$s__destroy(obj);			    \n\
+				errno = -err;				    \n\
 				return NULL;				    \n\
 			}						    \n\
 			return obj;					    \n\
@@ -498,7 +869,7 @@ static int do_skeleton(int argc, char **argv)
 									    \n\
 			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
 			if (!s)						    \n\
-				return -1;				    \n\
+				goto err;				    \n\
 			obj->skeleton = s;				    \n\
 									    \n\
 			s->sz = sizeof(*s);				    \n\
@@ -578,19 +949,7 @@ static int do_skeleton(int argc, char **argv)
 		file_sz);
 
 	/* embed contents of BPF object file */
-	for (i = 0, len = 0; i < file_sz; i++) {
-		int w = obj_data[i] ? 4 : 2;
-
-		len += w;
-		if (len > 78) {
-			printf("\\\n");
-			len = w;
-		}
-		if (!obj_data[i])
-			printf("\\0");
-		else
-			printf("\\x%02x", (unsigned char)obj_data[i]);
-	}
+	print_hex(obj_data, file_sz);
 
 	codegen("\
 		\n\
@@ -599,7 +958,7 @@ static int do_skeleton(int argc, char **argv)
 			return 0;					    \n\
 		err:							    \n\
 			bpf_object__destroy_skeleton(s);		    \n\
-			return -1;					    \n\
+			return -ENOMEM;					    \n\
 		}							    \n\
 									    \n\
 		#endif /* %s */						    \n\
@@ -636,7 +995,7 @@ static int do_object(int argc, char **argv)
 	while (argc) {
 		file = GET_ARG();
 
-		err = bpf_linker__add_file(linker, file);
+		err = bpf_linker__add_file(linker, file, NULL);
 		if (err) {
 			p_err("failed to link '%s': %s (%d)", file, strerror(err), err);
 			goto out;
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d9afb730136a..3ddfd4843738 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -29,6 +29,7 @@ bool show_pinned;
 bool block_mount;
 bool verifier_logs;
 bool relaxed_maps;
+bool use_loader;
 struct btf *base_btf;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
@@ -340,8 +341,10 @@ static int do_batch(int argc, char **argv)
 		n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines);
 		if (!n_argc)
 			continue;
-		if (n_argc < 0)
+		if (n_argc < 0) {
+			err = n_argc;
 			goto err_close;
+		}
 
 		if (json_output) {
 			jsonw_start_object(json_wtr);
@@ -392,6 +395,7 @@ int main(int argc, char **argv)
 		{ "mapcompat",	no_argument,	NULL,	'm' },
 		{ "nomount",	no_argument,	NULL,	'n' },
 		{ "debug",	no_argument,	NULL,	'd' },
+		{ "use-loader",	no_argument,	NULL,	'L' },
 		{ "base-btf",	required_argument, NULL, 'B' },
 		{ 0 }
 	};
@@ -409,7 +413,7 @@ int main(int argc, char **argv)
 	hash_init(link_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "VhpjfmndB:",
+	while ((opt = getopt_long(argc, argv, "VhpjfLmndB:",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -452,6 +456,9 @@ int main(int argc, char **argv)
 				return -1;
 			}
 			break;
+		case 'L':
+			use_loader = true;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 76e91641262b..c1cf29798b99 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -90,6 +90,7 @@ extern bool show_pids;
 extern bool block_mount;
 extern bool verifier_logs;
 extern bool relaxed_maps;
+extern bool use_loader;
 extern struct btf *base_btf;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index da4846c9856a..cc48726740ad 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -16,6 +16,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
+#include <dirent.h>
 
 #include <linux/err.h>
 #include <linux/perf_event.h>
@@ -24,6 +25,8 @@
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf_gen_internal.h>
+#include <bpf/skel_internal.h>
 
 #include "cfg.h"
 #include "main.h"
@@ -1499,7 +1502,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	set_max_rlimit();
 
 	obj = bpf_object__open_file(file, &open_opts);
-	if (IS_ERR_OR_NULL(obj)) {
+	if (libbpf_get_error(obj)) {
 		p_err("failed to open object file");
 		goto err_free_reuse_maps;
 	}
@@ -1645,8 +1648,110 @@ err_free_reuse_maps:
 	return -1;
 }
 
+static int count_open_fds(void)
+{
+	DIR *dp = opendir("/proc/self/fd");
+	struct dirent *de;
+	int cnt = -3;
+
+	if (!dp)
+		return -1;
+
+	while ((de = readdir(dp)))
+		cnt++;
+
+	closedir(dp);
+	return cnt;
+}
+
+static int try_loader(struct gen_loader_opts *gen)
+{
+	struct bpf_load_and_run_opts opts = {};
+	struct bpf_loader_ctx *ctx;
+	int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc),
+					     sizeof(struct bpf_prog_desc));
+	int log_buf_sz = (1u << 24) - 1;
+	int err, fds_before, fd_delta;
+	char *log_buf;
+
+	ctx = alloca(ctx_sz);
+	memset(ctx, 0, ctx_sz);
+	ctx->sz = ctx_sz;
+	ctx->log_level = 1;
+	ctx->log_size = log_buf_sz;
+	log_buf = malloc(log_buf_sz);
+	if (!log_buf)
+		return -ENOMEM;
+	ctx->log_buf = (long) log_buf;
+	opts.ctx = ctx;
+	opts.data = gen->data;
+	opts.data_sz = gen->data_sz;
+	opts.insns = gen->insns;
+	opts.insns_sz = gen->insns_sz;
+	fds_before = count_open_fds();
+	err = bpf_load_and_run(&opts);
+	fd_delta = count_open_fds() - fds_before;
+	if (err < 0) {
+		fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf);
+		if (fd_delta)
+			fprintf(stderr, "loader prog leaked %d FDs\n",
+				fd_delta);
+	}
+	free(log_buf);
+	return err;
+}
+
+static int do_loader(int argc, char **argv)
+{
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts);
+	DECLARE_LIBBPF_OPTS(gen_loader_opts, gen);
+	struct bpf_object_load_attr load_attr = {};
+	struct bpf_object *obj;
+	const char *file;
+	int err = 0;
+
+	if (!REQ_ARGS(1))
+		return -1;
+	file = GET_ARG();
+
+	obj = bpf_object__open_file(file, &open_opts);
+	if (libbpf_get_error(obj)) {
+		p_err("failed to open object file");
+		goto err_close_obj;
+	}
+
+	err = bpf_object__gen_loader(obj, &gen);
+	if (err)
+		goto err_close_obj;
+
+	load_attr.obj = obj;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		load_attr.log_level = 1 + 2 + 4;
+
+	err = bpf_object__load_xattr(&load_attr);
+	if (err) {
+		p_err("failed to load object file");
+		goto err_close_obj;
+	}
+
+	if (verifier_logs) {
+		struct dump_data dd = {};
+
+		kernel_syms_load(&dd);
+		dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false);
+		kernel_syms_destroy(&dd);
+	}
+	err = try_loader(&gen);
+err_close_obj:
+	bpf_object__close(obj);
+	return err;
+}
+
 static int do_load(int argc, char **argv)
 {
+	if (use_loader)
+		return do_loader(argc, argv);
 	return load_with_options(argc, argv, true);
 }
 
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 6fc3e6f7f40c..f1f32e21d5cd 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -196,6 +196,9 @@ static const char *print_imm(void *private_data,
 	else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
+	else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE)
+		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+			 "map[idx:%u]+%u", insn->imm, (insn + 1)->imm);
 	else if (insn->src_reg == BPF_PSEUDO_FUNC)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "subprog[%+d]", insn->imm);