ebpf_functions: Modify function debian_kernel_version to be compatible with Debian 10.

.gitattributes

@@ -1 +1 @@
-assets/** export-ignore
+assets/ export-ignore

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +0,0 @@
-Thank you for considering a contribution!
-
-Please note that the `libbpf` authoritative source code is developed as part of bpf-next Linux source tree under tools/lib/bpf subdirectory and is periodically synced to Github. As such, all the libbpf changes should be sent to BPF mailing list, please don't open PRs here unless you are changing Github-specific parts of libbpf (e.g., Github-specific Makefile).

.github/actions/build-selftests/build_selftests.sh

@@ -40,7 +40,6 @@ else
 fi
 
 cd ${REPO_ROOT}/${REPO_PATH}
-make headers
 make \
 	CLANG=clang-${LLVM_VERSION} \
 	LLC=llc-${LLVM_VERSION} \

.github/actions/vmtest/action.yml

@@ -16,22 +16,6 @@ inputs:
 runs:
   using: "composite"
   steps:
-    # Allow CI user to access /dev/kvm (via qemu) w/o group change/relogin
-    # by changing permissions set by udev.
-    - name: Set /dev/kvm permissions
-      shell: bash
-      run: |
-        if [ -e /dev/kvm ]; then
-          echo "/dev/kvm exists"
-          if [ $(id -u) != 0 ]; then
-            echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' \
-              | sudo tee /etc/udev/rules.d/99-kvm4all.rules > /dev/null
-            sudo udevadm control --reload-rules
-            sudo udevadm trigger --name-match=kvm
-          fi
-        else
-          echo "/dev/kvm does not exist"
-        fi
     # setup environment
     - name: Setup environment
       uses: libbpf/ci/setup-build-env@main
@@ -62,8 +46,6 @@ runs:
         cd .kernel
         cat tools/testing/selftests/bpf/config \
             tools/testing/selftests/bpf/config.${{ inputs.arch }} > .config
-        # this file might or mihgt not exist depending on kernel version
-        cat tools/testing/selftests/bpf/config.vm >> .config || :
         make olddefconfig && make prepare
         cd -
         foldable end

.readthedocs.yaml

@@ -5,11 +5,6 @@
 # Required
 version: 2
 
-build:
-  os: "ubuntu-22.04"
-  tools:
-    python: "3.11"
-
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   builder: html
@@ -22,5 +17,6 @@ formats:
 
 # Optionally set the version of Python and requirements required to build your docs
 python:
+   version: 3.7
    install:
-   - requirements: docs/sphinx/requirements.txt
+   - requirements: docs/sphinx/requirements.txt

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-7c5e046bdcb2513f9decb3765d8bf92d604279cf
+71b547f561247897a0a14f3082730156c0533fed

CHECKPOINT-COMMIT

@@ -1 +1 @@
-98e20e5e13d2811898921f999288be7151a11954
+2ddade322925641ee2a75f13665c51f2e74d7791

ci/diffs/0001-bpf-patch-out-BPF_F_TEST_REG_INVARIANTS-for-old-kern.patch

@@ -1,29 +0,0 @@
-From 61e8893a1e32ab57d15974427f41b75de608dbda Mon Sep 17 00:00:00 2001
-From: Andrii Nakryiko <andrii@kernel.org>
-Date: Mon, 4 Dec 2023 21:21:23 -0800
-Subject: [PATCH] bpf: patch out BPF_F_TEST_REG_INVARIANTS for old kernels
-
-CI-only patch to avoid setting BPF_F_TEST_REG_INVARIANTS flag for old
-kernels that don't support it.
-
-Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
----
- tools/include/uapi/linux/bpf.h | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
-index e88746ba7d21..8344c9ce60e0 100644
---- a/tools/include/uapi/linux/bpf.h
-+++ b/tools/include/uapi/linux/bpf.h
-@@ -1201,7 +1201,7 @@ enum bpf_perf_event_type {
- #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
- 
- /* The verifier internal test flag. Behavior is undefined */
--#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
-+#define BPF_F_TEST_REG_INVARIANTS	(0)
- 
- /* link_create.kprobe_multi.flags used in LINK_CREATE command for
-  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
--- 
-2.34.1
-

ci/diffs/0001-s390-define-RUNTIME_DISCARD_EXIT-to-fix-link-error-w.patch

@@ -0,0 +1,70 @@
+From 6fba14e2ed9d159f76b23fa5c16f3ea99acbc003 Mon Sep 17 00:00:00 2001
+From: Masahiro Yamada <masahiroy@kernel.org>
+Date: Thu, 5 Jan 2023 12:13:06 +0900
+Subject: [PATCH] s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU
+ ld < 2.36
+
+Nathan Chancellor reports that the s390 vmlinux fails to link with
+GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID
+for arm64 and riscv").
+
+It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y.
+
+  $ s390x-linux-gnu-ld --version | head -n1
+  GNU ld (GNU Binutils for Debian) 2.35.2
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig
+  $ ./scripts/config -e CONFIG_EXPOLINE
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig
+  $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu-
+  `.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o
+  make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1
+  make: *** [Makefile:1252: vmlinux] Error 2
+
+arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT:
+
+        .exit.text : {
+                EXIT_TEXT
+        }
+
+But, at the same time, EXIT_TEXT is thrown away by DISCARD because
+s390 does not define RUNTIME_DISCARD_EXIT.
+
+I still do not understand why the latter wins after 99cb0d917ffa,
+but defining RUNTIME_DISCARD_EXIT seems correct because the comment
+line in arch/s390/kernel/vmlinux.lds.S says:
+
+        /*
+         * .exit.text is discarded at runtime, not link time,
+         * to deal with references from __bug_table
+         */
+
+Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output
+sections in scripts") cured this issue, so we cannot reproduce it with
+binutils 2.36+, but it is better to not rely on it.
+
+Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv")
+Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/
+Reported-by: Nathan Chancellor <nathan@kernel.org>
+Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
+Link: https://lore.kernel.org/r/20230105031306.1455409-1-masahiroy@kernel.org
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+---
+ arch/s390/kernel/vmlinux.lds.S | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
+index 5ea3830af0cc..6e101e6f499d 100644
+--- a/arch/s390/kernel/vmlinux.lds.S
++++ b/arch/s390/kernel/vmlinux.lds.S
+@@ -17,6 +17,8 @@
+ /* Handle ro_after_init data on our own. */
+ #define RO_AFTER_INIT_DATA
+ 
++#define RUNTIME_DISCARD_EXIT
++
+ #define EMITS_PT_NOTE
+ 
+ #include <asm-generic/vmlinux.lds.h>
+-- 
+2.30.2
+

ci/diffs/0001-selftests-bpf-Select-CONFIG_FUNCTION_ERROR_INJECTION.patch

@@ -0,0 +1,46 @@
+From a8dfde09c90109e3a98af54847e91bde7dc2d5c2 Mon Sep 17 00:00:00 2001
+From: Song Liu <song@kernel.org>
+Date: Tue, 13 Dec 2022 14:05:00 -0800
+Subject: [PATCH] selftests/bpf: Select CONFIG_FUNCTION_ERROR_INJECTION
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+BPF selftests require CONFIG_FUNCTION_ERROR_INJECTION to work. However,
+CONFIG_FUNCTION_ERROR_INJECTION is no longer 'y' by default after recent
+changes. As a result, we are seeing errors like the following from BPF CI:
+
+   bpf_testmod_test_read() is not modifiable
+   __x64_sys_setdomainname is not sleepable
+   __x64_sys_getpgid is not sleepable
+
+Fix this by explicitly selecting CONFIG_FUNCTION_ERROR_INJECTION in the
+selftest config.
+
+Fixes: a4412fdd49dc ("error-injection: Add prompt for function error injection")
+Reported-by: Daniel Müller <deso@posteo.net>
+Signed-off-by: Song Liu <song@kernel.org>
+Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Daniel Müller <deso@posteo.net>
+Link: https://lore.kernel.org/bpf/20221213220500.3427947-1-song@kernel.org
+Signed-off-by: Daniel Müller <deso@posteo.net>
+---
+ tools/testing/selftests/bpf/config | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
+index 612f69..63cd4a 100644
+--- a/tools/testing/selftests/bpf/config
++++ b/tools/testing/selftests/bpf/config
+@@ -16,6 +16,7 @@ CONFIG_CRYPTO_USER_API_HASH=y
+ CONFIG_DYNAMIC_FTRACE=y
+ CONFIG_FPROBE=y
+ CONFIG_FTRACE_SYSCALLS=y
++CONFIG_FUNCTION_ERROR_INJECTION=y
+ CONFIG_FUNCTION_TRACER=y
+ CONFIG_GENEVE=y
+ CONFIG_IKCONFIG=y
+-- 
+2.30.2
+

ci/diffs/0001-selftests-bpf-xskxceiver-ksft_print_msg-fix-format-t.patch

@@ -1,89 +0,0 @@
-From fe69a1b1b6ed9ffc2c578c63f526026a8ab74f0c Mon Sep 17 00:00:00 2001
-From: Anders Roxell <anders.roxell@linaro.org>
-Date: Thu, 9 Nov 2023 18:43:28 +0100
-Subject: [PATCH] selftests: bpf: xskxceiver: ksft_print_msg: fix format type
- error
-
-Crossbuilding selftests/bpf for architecture arm64, format specifies
-type error show up like.
-
-xskxceiver.c:912:34: error: format specifies type 'int' but the argument
-has type '__u64' (aka 'unsigned long long') [-Werror,-Wformat]
- ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
-                                                                ~~
-                                                                %llu
-                __func__, pkt->pkt_nb, meta->count);
-                                       ^~~~~~~~~~~
-xskxceiver.c:929:55: error: format specifies type 'unsigned long long' but
- the argument has type 'u64' (aka 'unsigned long') [-Werror,-Wformat]
- ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
-                                    ~~~~             ^~~~
-
-Fixing the issues by casting to (unsigned long long) and changing the
-specifiers to be %llu from %d and %u, since with u64s it might be %llx
-or %lx, depending on architecture.
-
-Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
-Link: https://lore.kernel.org/r/20231109174328.1774571-1-anders.roxell@linaro.org
-Signed-off-by: Alexei Starovoitov <ast@kernel.org>
----
- tools/testing/selftests/bpf/xskxceiver.c | 19 ++++++++++++-------
- 1 file changed, 12 insertions(+), 7 deletions(-)
-
-diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
-index 591ca9637b23..b604c570309a 100644
---- a/tools/testing/selftests/bpf/xskxceiver.c
-+++ b/tools/testing/selftests/bpf/xskxceiver.c
-@@ -908,8 +908,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
- 	struct xdp_info *meta = data - sizeof(struct xdp_info);
- 
- 	if (meta->count != pkt->pkt_nb) {
--		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
--			       __func__, pkt->pkt_nb, meta->count);
-+		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
-+			       __func__, pkt->pkt_nb,
-+			       (unsigned long long)meta->count);
- 		return false;
- 	}
- 
-@@ -926,11 +927,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp
- 
- 	if (addr >= umem->num_frames * umem->frame_size ||
- 	    addr + len > umem->num_frames * umem->frame_size) {
--		ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
-+		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
-+			       (unsigned long long)addr, len);
- 		return false;
- 	}
- 	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
--		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
-+		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
-+			       (unsigned long long)addr, len);
- 		return false;
- 	}
- 
-@@ -1029,7 +1032,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
- 			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
- 
- 			ksft_print_msg("[%s] Too many packets completed\n", __func__);
--			ksft_print_msg("Last completion address: %llx\n", addr);
-+			ksft_print_msg("Last completion address: %llx\n",
-+				       (unsigned long long)addr);
- 			return TEST_FAILURE;
- 		}
- 
-@@ -1513,8 +1517,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
- 	}
- 
- 	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
--		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
--			       __func__, stats.tx_invalid_descs,
-+		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
-+			       __func__,
-+			       (unsigned long long)stats.tx_invalid_descs,
- 			       ifobject->xsk->pkt_stream->nb_pkts);
- 		return TEST_FAILURE;
- 	}
--- 
-2.34.1
-

ci/diffs/0001-veth-take-into-account-peer-device-for-NETDEV_XDP_AC.patch

@@ -0,0 +1,83 @@
+From 8267fc71abb2dc47338570e56dd3473a58313fce Mon Sep 17 00:00:00 2001
+From: Lorenzo Bianconi <lorenzo@kernel.org>
+Date: Mon, 17 Apr 2023 23:53:22 +0200
+Subject: [PATCH] veth: take into account peer device for
+ NETDEV_XDP_ACT_NDO_XMIT xdp_features flag
+
+For veth pairs, NETDEV_XDP_ACT_NDO_XMIT is supported by the current
+device if the peer one is running a XDP program or if it has GRO enabled.
+Fix the xdp_features flags reporting considering peer device and not
+current one for NETDEV_XDP_ACT_NDO_XMIT.
+
+Fixes: fccca038f300 ("veth: take into account device reconfiguration for xdp_features flag")
+Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
+Link: https://lore.kernel.org/r/4f1ca6f6f6b42ae125bfdb5c7782217c83968b2e.1681767806.git.lorenzo@kernel.org
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+---
+ drivers/net/veth.c | 17 +++++++++++------
+ 1 file changed, 11 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/net/veth.c b/drivers/net/veth.c
+index e1b38fbf1dd9..4b3c6647edc6 100644
+--- a/drivers/net/veth.c
++++ b/drivers/net/veth.c
+@@ -1262,11 +1262,12 @@ static void veth_set_xdp_features(struct net_device *dev)
+ 
+ 	peer = rtnl_dereference(priv->peer);
+ 	if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) {
++		struct veth_priv *priv_peer = netdev_priv(peer);
+ 		xdp_features_t val = NETDEV_XDP_ACT_BASIC |
+ 				     NETDEV_XDP_ACT_REDIRECT |
+ 				     NETDEV_XDP_ACT_RX_SG;
+ 
+-		if (priv->_xdp_prog || veth_gro_requested(dev))
++		if (priv_peer->_xdp_prog || veth_gro_requested(peer))
+ 			val |= NETDEV_XDP_ACT_NDO_XMIT |
+ 			       NETDEV_XDP_ACT_NDO_XMIT_SG;
+ 		xdp_set_features_flag(dev, val);
+@@ -1504,19 +1505,23 @@ static int veth_set_features(struct net_device *dev,
+ {
+ 	netdev_features_t changed = features ^ dev->features;
+ 	struct veth_priv *priv = netdev_priv(dev);
++	struct net_device *peer;
+ 	int err;
+ 
+ 	if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog)
+ 		return 0;
+ 
++	peer = rtnl_dereference(priv->peer);
+ 	if (features & NETIF_F_GRO) {
+ 		err = veth_napi_enable(dev);
+ 		if (err)
+ 			return err;
+ 
+-		xdp_features_set_redirect_target(dev, true);
++		if (peer)
++			xdp_features_set_redirect_target(peer, true);
+ 	} else {
+-		xdp_features_clear_redirect_target(dev);
++		if (peer)
++			xdp_features_clear_redirect_target(peer);
+ 		veth_napi_del(dev);
+ 	}
+ 	return 0;
+@@ -1598,13 +1603,13 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ 			peer->max_mtu = max_mtu;
+ 		}
+ 
+-		xdp_features_set_redirect_target(dev, true);
++		xdp_features_set_redirect_target(peer, true);
+ 	}
+ 
+ 	if (old_prog) {
+ 		if (!prog) {
+-			if (!veth_gro_requested(dev))
+-				xdp_features_clear_redirect_target(dev);
++			if (peer && !veth_gro_requested(dev))
++				xdp_features_clear_redirect_target(peer);
+ 
+ 			if (dev->flags & IFF_UP)
+ 				veth_disable_xdp(dev);
+-- 
+2.34.1
+

ci/vmtest/configs/ALLOWLIST-5.5.0

@@ -32,7 +32,11 @@ raw_tp_writable_test_run
 rdonly_maps
 section_names
 signal_pending
+skeleton
 sockmap_ktls
+sockopt
+sockopt_inherit
+sockopt_multi
 spinlock
 stacktrace_map
 stacktrace_map_raw_tp

ci/vmtest/configs/DENYLIST-5.5.0

@@ -1,5 +1,118 @@
-# This complements ALLOWLIST-5.5.0 but excludes subtest that can't work on 5.5
+# This file is not used and is there for historic purposes only.
+# See ALLOWLIST-5.5.0 instead.
 
+# PERMANENTLY DISABLED
+align			# verifier output format changed
+atomics			# new atomic operations (v5.12+)
+atomic_bounds		# new atomic operations (v5.12+)
+bind_perm		# changed semantics of return values (v5.12+)
+bpf_cookie		# 5.15+
+bpf_iter		# bpf_iter support is missing
+bpf_obj_id		# bpf_link support missing for GET_OBJ_INFO, GET_FD_BY_ID, etc
+bpf_tcp_ca		# STRUCT_OPS is missing
+btf_map_in_map		# inner map leak fixed in 5.8
+btf_skc_cls_ingress	# v5.10+ functionality
+cg_storage_multi	# v5.9+ functionality
+cgroup_attach_multi	# BPF_F_REPLACE_PROG missing
+cgroup_link		# LINK_CREATE is missing
+cgroup_skb_sk_lookup	# bpf_sk_lookup_tcp() helper is missing
+check_mtu		# missing BPF helper (v5.12+)
+cls_redirect		# bpf_csum_level() helper is missing
+connect_force_port	# cgroup/get{peer,sock}name{4,6} support is missing
+d_path			# v5.10+ feature
+enable_stats		# BPF_ENABLE_STATS support is missing
+fentry_fexit		# bpf_prog_test_tracing missing
+fentry_test		# bpf_prog_test_tracing missing
+fexit_bpf2bpf		# freplace is missing
+fexit_sleep		# relies on bpf_trampoline fix in 5.12+
+fexit_test		# bpf_prog_test_tracing missing
+flow_dissector		# bpf_link-based flow dissector is in 5.8+
+flow_dissector_reattach
+for_each		# v5.12+
+get_func_ip_test	# v5.15+
+get_stack_raw_tp	# exercising BPF verifier bug causing infinite loop
+hash_large_key		# v5.11+
+ima			# v5.11+
+kfree_skb		# 32-bit pointer arith in test_pkt_access
+ksyms			# __start_BTF has different name
+kfunc_call		# v5.13+
+link_pinning		# bpf_link is missing
+linked_vars		# v5.13+
+load_bytes_relative	# new functionality in 5.8
+lookup_and_delete	# v5.14+
+map_init		# per-CPU LRU missing
+map_ptr			# test uses BPF_MAP_TYPE_RINGBUF, added in 5.8
+metadata		# v5.10+
+migrate_reuseport	# v5.14+
+mmap			# 5.5 kernel is too permissive with re-mmaping
+modify_return		# fmod_ret support is missing
+module_attach		# module BTF support missing (v5.11+)
+netcnt
+netns_cookie		# v5.15+
+ns_current_pid_tgid	# bpf_get_ns_current_pid_tgid() helper is missing
+pe_preserve_elems	# v5.10+
+perf_branches		# bpf_read_branch_records() helper is missing
+perf_link		# v5.15+
+pkt_access		# 32-bit pointer arith in test_pkt_access
+probe_read_user_str	# kernel bug with garbage bytes at the end
+prog_run_xattr		# 32-bit pointer arith in test_pkt_access
+raw_tp_test_run		# v5.10+
+recursion		# v5.12+
+ringbuf			# BPF_MAP_TYPE_RINGBUF is supported in 5.8+
+
+# bug in verifier w/ tracking references
+#reference_tracking/classifier/sk_lookup_success
+reference_tracking
+
+select_reuseport	# UDP support is missing
+send_signal		# bpf_send_signal_thread() helper is missing
+sk_assign		# bpf_sk_assign helper missing
+sk_lookup		# v5.9+
+sk_storage_tracing	# missing bpf_sk_storage_get() helper
+skb_ctx			# ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN is missing
+skb_helpers		# helpers added in 5.8+
+skeleton		# creates too big ARRAY map
+snprintf		# v5.13+
+snprintf_btf		# v5.10+
+sock_fields		# v5.10+
+socket_cookie		# v5.12+
+sockmap_basic		# uses new socket fields, 5.8+
+sockmap_listen		# no listen socket supportin SOCKMAP
+sockopt_sk
+sockopt_qos_to_cc	# v5.15+
+stacktrace_build_id	# v5.9+
+stack_var_off		# v5.12+
+syscall			# v5.14+
+task_local_storage	# v5.12+
+task_pt_regs		# v5.15+
+tcp_hdr_options		# v5.10+, new TCP header options feature in BPF
+tcpbpf_user		# LINK_CREATE is missing
+tc_redirect		# v5.14+
+test_bpffs		# v5.10+, new CONFIG_BPF_PRELOAD=y and CONFIG_BPF_PRELOAD_UMG=y|m
+test_bprm_opts		# v5.11+
+test_global_funcs	# kernel doesn't support BTF linkage=global on FUNCs
+test_local_storage	# v5.10+ feature
+test_lsm		# no BPF_LSM support
+test_overhead		# no fmod_ret support
+test_profiler		# needs verifier logic improvements from v5.10+
+test_skb_pkt_end	# v5.11+
+timer			# v5.15+
+timer_mim		# v5.15+
+trace_ext		# v5.10+
+trace_printk		# v5.14+
+trampoline_count	# v5.12+ have lower allowed limits
+udp_limit		# no cgroup/sock_release BPF program type (5.9+)
+varlen			# verifier bug fixed in later kernels
+vmlinux			# hrtimer_nanosleep() signature changed incompatibly
+xdp_adjust_tail		# new XDP functionality added in 5.8
+xdp_attach		# IFLA_XDP_EXPECTED_FD support is missing
+xdp_bonding		# v5.15+
+xdp_bpf2bpf		# freplace is missing
+xdp_context_test_run	# v5.15+
+xdp_cpumap_attach	# v5.9+
+xdp_devmap_attach	# new feature in 5.8
+xdp_link		# v5.9+
+
+# SUBTESTS FAILING (block entire test until blocking subtests works properly)
 btf			# "size check test", "func (Non zero vlen)"
 tailcalls		# tailcall_bpf2bpf_1, tailcall_bpf2bpf_2, tailcall_bpf2bpf_3
-tc_bpf/tc_bpf_non_root

ci/vmtest/configs/DENYLIST-latest

@@ -1,12 +1 @@
 decap_sanity  # weird failure with decap_sanity_ns netns already existing, TBD
-empty_skb # waiting the fix in bpf tree to make it to bpf-next
-bpf_nf/tc-bpf-ct # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
-bpf_nf/xdp-ct   # test consistently failing on x86: https://github.com/libbpf/libbpf/pull/698#issuecomment-1590341200
-kprobe_multi_bench_attach # suspected to cause crashes in CI
-find_vma # test consistently fails on latest kernel, see https://github.com/libbpf/libbpf/issues/754 for details
-bpf_cookie/perf_event
-send_signal/send_signal_nmi
-send_signal/send_signal_nmi_thread
-
-lwt_reroute # crashes kernel, fix pending upstream
-tc_links_ingress # fails, same fix is pending upstream

ci/vmtest/configs/DENYLIST-latest.s390x

@@ -1,4 +1,3 @@
 # TEMPORARY
-sockmap_listen/sockhash VSOCK test_vsock_redir
 usdt/basic                               # failing verifier due to bounds check after LLVM update
 usdt/multispec                           # same as above

ci/vmtest/run_selftests.sh

@@ -13,7 +13,7 @@ read_lists() {
 		if [[ -s "$path" ]]; then
 			cat "$path"
 		fi;
-	done) | cut -d'#' -f1 | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//' | tr -s '\n' ','
+	done) | cut -d'#' -f1 | tr -s ' \t\n' ','
 }
 
 test_progs() {
@@ -22,7 +22,7 @@ test_progs() {
 		# "&& true" does not change the return code (it is not executed
 		# if the Python script fails), but it prevents exiting on a
 		# failure due to the "set -e".
-		./test_progs ${DENYLIST:+-d"$DENYLIST"} ${ALLOWLIST:+-a"$ALLOWLIST"} && true
+		./test_progs ${DENYLIST:+-d$DENYLIST} ${ALLOWLIST:+-a$ALLOWLIST} && true
 		echo "test_progs:$?" >> "${STATUS_FILE}"
 		foldable end test_progs
 	fi
@@ -30,7 +30,7 @@ test_progs() {
 
 test_progs_no_alu32() {
 	foldable start test_progs-no_alu32 "Testing test_progs-no_alu32"
-	./test_progs-no_alu32 ${DENYLIST:+-d"$DENYLIST"} ${ALLOWLIST:+-a"$ALLOWLIST"} && true
+	./test_progs-no_alu32 ${DENYLIST:+-d$DENYLIST} ${ALLOWLIST:+-a$ALLOWLIST} && true
 	echo "test_progs-no_alu32:$?" >> "${STATUS_FILE}"
 	foldable end test_progs-no_alu32
 }
@@ -55,13 +55,6 @@ test_verifier() {
 
 foldable end vm_init
 
-foldable start kernel_config "Kconfig"
-
-zcat /proc/config.gz
-
-foldable end kernel_config
-
-
 configs_path=/${PROJECT_NAME}/selftests/bpf
 local_configs_path=${PROJECT_NAME}/vmtest/configs
 DENYLIST=$(read_lists \

docs/conf.py

@@ -18,7 +18,6 @@ extensions = [
     'sphinx.ext.viewcode',
     'sphinx.ext.imgmath',
     'sphinx.ext.todo',
-    'sphinx_rtd_theme',
     'breathe',
 ]
 

docs/program_types.rst

@@ -56,16 +56,6 @@ described in more detail in the footnotes.
 |                                           | ``BPF_CGROUP_UDP6_RECVMSG``            | ``cgroup/recvmsg6``              |           |
 +                                           +----------------------------------------+----------------------------------+-----------+
 |                                           | ``BPF_CGROUP_UDP6_SENDMSG``            | ``cgroup/sendmsg6``              |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_CONNECT``            | ``cgroup/connect_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_SENDMSG``            | ``cgroup/sendmsg_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_RECVMSG``            | ``cgroup/recvmsg_unix``          |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_GETPEERNAME``        | ``cgroup/getpeername_unix``      |           |
-|                                           +----------------------------------------+----------------------------------+-----------+
-|                                           | ``BPF_CGROUP_UNIX_GETSOCKNAME``        | ``cgroup/getsockname_unix``      |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_CGROUP_SOCK``             | ``BPF_CGROUP_INET4_POST_BIND``         | ``cgroup/post_bind4``            |           |
 +                                           +----------------------------------------+----------------------------------+-----------+

docs/sphinx/requirements.txt

@@ -1,2 +1 @@
-breathe
-sphinx_rtd_theme
+breathe

include/uapi/linux/bpf.h

@@ -19,7 +19,6 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
-#define BPF_MEMSX	0x80	/* load with sign extension */
 #define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
 #define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
@@ -932,14 +931,7 @@ enum bpf_map_type {
 	 */
 	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
-	/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
-	 * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
-	 * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
-	 * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
-	 * deprecated.
-	 */
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
@@ -994,7 +986,6 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
-	BPF_PROG_TYPE_NETFILTER,
 };
 
 enum bpf_attach_type {
@@ -1043,17 +1034,6 @@ enum bpf_attach_type {
 	BPF_TRACE_KPROBE_MULTI,
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
-	BPF_NETFILTER,
-	BPF_TCX_INGRESS,
-	BPF_TCX_EGRESS,
-	BPF_TRACE_UPROBE_MULTI,
-	BPF_CGROUP_UNIX_CONNECT,
-	BPF_CGROUP_UNIX_SENDMSG,
-	BPF_CGROUP_UNIX_RECVMSG,
-	BPF_CGROUP_UNIX_GETPEERNAME,
-	BPF_CGROUP_UNIX_GETSOCKNAME,
-	BPF_NETKIT_PRIMARY,
-	BPF_NETKIT_PEER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1070,23 +1050,8 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_PERF_EVENT = 7,
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
-	BPF_LINK_TYPE_NETFILTER = 10,
-	BPF_LINK_TYPE_TCX = 11,
-	BPF_LINK_TYPE_UPROBE_MULTI = 12,
-	BPF_LINK_TYPE_NETKIT = 13,
-	__MAX_BPF_LINK_TYPE,
-};
 
-#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
-
-enum bpf_perf_event_type {
-	BPF_PERF_EVENT_UNSPEC = 0,
-	BPF_PERF_EVENT_UPROBE = 1,
-	BPF_PERF_EVENT_URETPROBE = 2,
-	BPF_PERF_EVENT_KPROBE = 3,
-	BPF_PERF_EVENT_KRETPROBE = 4,
-	BPF_PERF_EVENT_TRACEPOINT = 5,
-	BPF_PERF_EVENT_EVENT = 6,
+	MAX_BPF_LINK_TYPE,
 };
 
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
@@ -1135,12 +1100,7 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
-/* Generic attachment flags. */
 #define BPF_F_REPLACE		(1U << 2)
-#define BPF_F_BEFORE		(1U << 3)
-#define BPF_F_AFTER		(1U << 4)
-#define BPF_F_ID		(1U << 5)
-#define BPF_F_LINK		BPF_F_LINK /* 1 << 13 */
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -1202,27 +1162,10 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
-/* The verifier internal test flag. Behavior is undefined */
-#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
-
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-enum {
-	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
-};
-
-/* link_create.uprobe_multi.flags used in LINK_CREATE command for
- * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
- */
-enum {
-	BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
-};
-
-/* link_create.netfilter.flags used in LINK_CREATE command for
- * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
- */
-#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
@@ -1327,9 +1270,6 @@ enum {
 
 /* Create a map that will be registered/unregesitered by the backed bpf_link */
 	BPF_F_LINK		= (1U << 13),
-
-/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
-	BPF_F_PATH_FD		= (1U << 14),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1478,29 +1418,17 @@ union bpf_attr {
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
 		__u32		file_flags;
-		/* Same as dirfd in openat() syscall; see openat(2)
-		 * manpage for details of path FD and pathname semantics;
-		 * path_fd should accompanied by BPF_F_PATH_FD flag set in
-		 * file_flags field, otherwise it should be set to zero;
-		 * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed.
-		 */
-		__s32		path_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
-		union {
-			__u32	target_fd;	/* target object to attach to or ... */
-			__u32	target_ifindex;	/* target ifindex */
-		};
-		__u32		attach_bpf_fd;
+		__u32		target_fd;	/* container object to attach to */
+		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
 		__u32		attach_flags;
-		__u32		replace_bpf_fd;
-		union {
-			__u32	relative_fd;
-			__u32	relative_id;
-		};
-		__u64		expected_revision;
+		__u32		replace_bpf_fd;	/* previously attached eBPF
+						 * program to replace if
+						 * BPF_F_REPLACE is used
+						 */
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -1546,26 +1474,16 @@ union bpf_attr {
 	} info;
 
 	struct { /* anonymous struct used by BPF_PROG_QUERY command */
-		union {
-			__u32	target_fd;	/* target object to query or ... */
-			__u32	target_ifindex;	/* target ifindex */
-		};
+		__u32		target_fd;	/* container object to query */
 		__u32		attach_type;
 		__u32		query_flags;
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
-		union {
-			__u32	prog_cnt;
-			__u32	count;
-		};
-		__u32		:32;
+		__u32		prog_cnt;
 		/* output: per-program attach_flags.
 		 * not allowed to be set during effective query.
 		 */
 		__aligned_u64	prog_attach_flags;
-		__aligned_u64	link_ids;
-		__aligned_u64	link_attach_flags;
-		__u64		revision;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -1608,13 +1526,13 @@ union bpf_attr {
 			__u32		map_fd;		/* struct_ops to attach */
 		};
 		union {
-			__u32	target_fd;	/* target object to attach to or ... */
-			__u32	target_ifindex; /* target ifindex */
+			__u32		target_fd;	/* object to attach to */
+			__u32		target_ifindex; /* target ifindex */
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 		union {
-			__u32	target_btf_id;	/* btf_id of target to attach to */
+			__u32		target_btf_id;	/* btf_id of target to attach to */
 			struct {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
@@ -1642,35 +1560,6 @@ union bpf_attr {
 				 */
 				__u64		cookie;
 			} tracing;
-			struct {
-				__u32		pf;
-				__u32		hooknum;
-				__s32		priority;
-				__u32		flags;
-			} netfilter;
-			struct {
-				union {
-					__u32	relative_fd;
-					__u32	relative_id;
-				};
-				__u64		expected_revision;
-			} tcx;
-			struct {
-				__aligned_u64	path;
-				__aligned_u64	offsets;
-				__aligned_u64	ref_ctr_offsets;
-				__aligned_u64	cookies;
-				__u32		cnt;
-				__u32		flags;
-				__u32		pid;
-			} uprobe_multi;
-			struct {
-				union {
-					__u32	relative_fd;
-					__u32	relative_id;
-				};
-				__u64		expected_revision;
-			} netkit;
 		};
 	} link_create;
 
@@ -1989,9 +1878,7 @@ union bpf_attr {
  * 		performed again, if the helper is used in combination with
  * 		direct packet access.
  * 	Return
- * 		0 on success, or a negative error in case of failure. Positive
- * 		error indicates a potential drop or congestion in the target
- * 		device. The particular positive error codes are not defined.
+ * 		0 on success, or a negative error in case of failure.
  *
  * u64 bpf_get_current_pid_tgid(void)
  * 	Description
@@ -2724,8 +2611,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
- *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
@@ -2963,8 +2850,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
- *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the same set of *optname*\ s that is supported by
@@ -3272,10 +3159,6 @@ union bpf_attr {
  *		**BPF_FIB_LOOKUP_DIRECT**
  *			Do a direct table lookup vs full lookup using FIB
  *			rules.
- *		**BPF_FIB_LOOKUP_TBID**
- *			Used with BPF_FIB_LOOKUP_DIRECT.
- *			Use the routing table ID present in *params*->tbid
- *			for the fib lookup.
  *		**BPF_FIB_LOOKUP_OUTPUT**
  *			Perform lookup from an egress perspective (default is
  *			ingress).
@@ -3284,11 +3167,6 @@ union bpf_attr {
  *			and *params*->smac will not be set as output. A common
  *			use case is to call **bpf_redirect_neigh**\ () after
  *			doing **bpf_fib_lookup**\ ().
- *		**BPF_FIB_LOOKUP_SRC**
- *			Derive and set source IP addr in *params*->ipv{4,6}_src
- *			for the nexthop. If the src addr cannot be derived,
- *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
- *			case, *params*->dmac and *params*->smac are not set either.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -4258,6 +4136,9 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the operation is not supported, for example
  *		a call from outside of TC ingress.
  *
+ *		**-ESOCKTNOSUPPORT** if the socket type is not supported
+ *		(reuseport).
+ *
  * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
@@ -4522,8 +4403,6 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
- *		Note: the user stack will only be populated if the *task* is
- *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4535,7 +4414,6 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
- *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
@@ -5124,8 +5002,6 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
- *		**BPF_F_TIMER_CPU_PIN**
- *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -5145,14 +5021,9 @@ union bpf_attr {
  * u64 bpf_get_func_ip(void *ctx)
  * 	Description
  * 		Get address of the traced function (for tracing and kprobe programs).
- *
- * 		When called for kprobe program attached as uprobe it returns
- * 		probe address for both entry and return uprobe.
- *
  * 	Return
- * 		Address of the traced function for kprobe.
+ * 		Address of the traced function.
  * 		0 for kprobes placed within the function (not at the entry).
- * 		Address of the probe for uprobe and return uprobe.
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
@@ -6293,19 +6164,6 @@ struct bpf_sock_tuple {
 	};
 };
 
-/* (Simplified) user return codes for tcx prog type.
- * A valid tcx program must return one of these defined values. All other
- * return codes are reserved for future use. Must remain compatible with
- * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
- * return codes are mapped to TCX_NEXT.
- */
-enum tcx_action_base {
-	TCX_NEXT	= -1,
-	TCX_PASS	= 0,
-	TCX_DROP	= 2,
-	TCX_REDIRECT	= 7,
-};
-
 struct bpf_xdp_sock {
 	__u32 queue_id;
 };
@@ -6552,62 +6410,6 @@ struct bpf_link_info {
 		struct {
 			__u32 map_id;
 		} struct_ops;
-		struct {
-			__u32 pf;
-			__u32 hooknum;
-			__s32 priority;
-			__u32 flags;
-		} netfilter;
-		struct {
-			__aligned_u64 addrs;
-			__u32 count; /* in/out: kprobe_multi function count */
-			__u32 flags;
-			__u64 missed;
-		} kprobe_multi;
-		struct {
-			__aligned_u64 path;
-			__aligned_u64 offsets;
-			__aligned_u64 ref_ctr_offsets;
-			__aligned_u64 cookies;
-			__u32 path_size; /* in/out: real path size on success, including zero byte */
-			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
-			__u32 flags;
-			__u32 pid;
-		} uprobe_multi;
-		struct {
-			__u32 type; /* enum bpf_perf_event_type */
-			__u32 :32;
-			union {
-				struct {
-					__aligned_u64 file_name; /* in/out */
-					__u32 name_len;
-					__u32 offset; /* offset from file_name */
-				} uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
-				struct {
-					__aligned_u64 func_name; /* in/out */
-					__u32 name_len;
-					__u32 offset; /* offset from func_name */
-					__u64 addr;
-					__u64 missed;
-				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
-				struct {
-					__aligned_u64 tp_name;   /* in/out */
-					__u32 name_len;
-				} tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
-				struct {
-					__u64 config;
-					__u32 type;
-				} event; /* BPF_PERF_EVENT_EVENT */
-			};
-		} perf_event;
-		struct {
-			__u32 ifindex;
-			__u32 attach_type;
-		} tcx;
-		struct {
-			__u32 ifindex;
-			__u32 attach_type;
-		} netkit;
 	};
 } __attribute__((aligned(8)));
 
@@ -7005,8 +6807,6 @@ enum {
 	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
-	BPF_FIB_LOOKUP_TBID    = (1U << 3),
-	BPF_FIB_LOOKUP_SRC     = (1U << 4),
 };
 
 enum {
@@ -7019,7 +6819,6 @@ enum {
 	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
 	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
 	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
-	BPF_FIB_LKUP_RET_NO_SRC_ADDR,  /* failed to derive IP src addr */
 };
 
 struct bpf_fib_lookup {
@@ -7054,9 +6853,6 @@ struct bpf_fib_lookup {
 		__u32	rt_metric;
 	};
 
-	/* input: source address to consider for lookup
-	 * output: source address result from lookup
-	 */
 	union {
 		__be32		ipv4_src;
 		__u32		ipv6_src[4];  /* in6_addr; network order */
@@ -7071,19 +6867,9 @@ struct bpf_fib_lookup {
 		__u32		ipv6_dst[4];  /* in6_addr; network order */
 	};
 
-	union {
-		struct {
-			/* output */
-			__be16	h_vlan_proto;
-			__be16	h_vlan_TCI;
-		};
-		/* input: when accompanied with the
-		 * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
-		 * specific routing table to use for the fib lookup.
-		 */
-		__u32	tbid;
-	};
-
+	/* output */
+	__be16	h_vlan_proto;
+	__be16	h_vlan_TCI;
 	__u8	smac[6];     /* ETH_ALEN */
 	__u8	dmac[6];     /* ETH_ALEN */
 };
@@ -7169,31 +6955,38 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 __opaque[3];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 __opaque[2];
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 __opaque[4];
+	__u64 :64;
+	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 __opaque[1];
+	__u32 :32;
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
@@ -7349,11 +7142,9 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
- *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
-	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */

include/uapi/linux/fcntl.h

@@ -112,9 +112,4 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
-/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
-#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
-					compare object identity and may not
-					be usable to open_by_handle_at(2) */
-
 #endif /* _UAPI_LINUX_FCNTL_H */

include/uapi/linux/if_link.h

@@ -211,9 +211,6 @@ struct rtnl_link_stats {
  * @rx_nohandler: Number of packets received on the interface
  *   but dropped by the networking stack because the device is
  *   not designated to receive packets (e.g. backup link in a bond).
- *
- * @rx_otherhost_dropped: Number of packets dropped due to mismatch
- *   in destination MAC address.
  */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;
@@ -246,23 +243,6 @@ struct rtnl_link_stats64 {
 	__u64	rx_compressed;
 	__u64	tx_compressed;
 	__u64	rx_nohandler;
-
-	__u64	rx_otherhost_dropped;
-};
-
-/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
- * for struct rtnl_link_stats64.
- */
-struct rtnl_hw_stats64 {
-	__u64	rx_packets;
-	__u64	tx_packets;
-	__u64	rx_bytes;
-	__u64	tx_bytes;
-	__u64	rx_errors;
-	__u64	tx_errors;
-	__u64	rx_dropped;
-	__u64	tx_dropped;
-	__u64	multicast;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -370,13 +350,7 @@ enum {
 	IFLA_GRO_MAX_SIZE,
 	IFLA_TSO_MAX_SIZE,
 	IFLA_TSO_MAX_SEGS,
-	IFLA_ALLMULTI,		/* Allmulti count: > 0 means acts ALLMULTI */
 
-	IFLA_DEVLINK_PORT,
-
-	IFLA_GSO_IPV4_MAX_SIZE,
-	IFLA_GRO_IPV4_MAX_SIZE,
-	IFLA_DPLL_PIN,
 	__IFLA_MAX
 };
 
@@ -565,12 +539,6 @@ enum {
 	IFLA_BRPORT_MRP_IN_OPEN,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
-	IFLA_BRPORT_LOCKED,
-	IFLA_BRPORT_MAB,
-	IFLA_BRPORT_MCAST_N_GROUPS,
-	IFLA_BRPORT_MCAST_MAX_GROUPS,
-	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
-	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -748,79 +716,7 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
-/* Tunnel RTM header */
-struct tunnel_msg {
-	__u8 family;
-	__u8 flags;
-	__u16 reserved2;
-	__u32 ifindex;
-};
-
-/* netkit section */
-enum netkit_action {
-	NETKIT_NEXT	= -1,
-	NETKIT_PASS	= 0,
-	NETKIT_DROP	= 2,
-	NETKIT_REDIRECT	= 7,
-};
-
-enum netkit_mode {
-	NETKIT_L2,
-	NETKIT_L3,
-};
-
-enum {
-	IFLA_NETKIT_UNSPEC,
-	IFLA_NETKIT_PEER_INFO,
-	IFLA_NETKIT_PRIMARY,
-	IFLA_NETKIT_POLICY,
-	IFLA_NETKIT_PEER_POLICY,
-	IFLA_NETKIT_MODE,
-	__IFLA_NETKIT_MAX,
-};
-#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
-
 /* VXLAN section */
-
-/* include statistics in the dump */
-#define TUNNEL_MSG_FLAG_STATS	0x01
-
-#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
-
-/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
-enum {
-	VNIFILTER_ENTRY_STATS_UNSPEC,
-	VNIFILTER_ENTRY_STATS_RX_BYTES,
-	VNIFILTER_ENTRY_STATS_RX_PKTS,
-	VNIFILTER_ENTRY_STATS_RX_DROPS,
-	VNIFILTER_ENTRY_STATS_RX_ERRORS,
-	VNIFILTER_ENTRY_STATS_TX_BYTES,
-	VNIFILTER_ENTRY_STATS_TX_PKTS,
-	VNIFILTER_ENTRY_STATS_TX_DROPS,
-	VNIFILTER_ENTRY_STATS_TX_ERRORS,
-	VNIFILTER_ENTRY_STATS_PAD,
-	__VNIFILTER_ENTRY_STATS_MAX
-};
-#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
-
-enum {
-	VXLAN_VNIFILTER_ENTRY_UNSPEC,
-	VXLAN_VNIFILTER_ENTRY_START,
-	VXLAN_VNIFILTER_ENTRY_END,
-	VXLAN_VNIFILTER_ENTRY_GROUP,
-	VXLAN_VNIFILTER_ENTRY_GROUP6,
-	VXLAN_VNIFILTER_ENTRY_STATS,
-	__VXLAN_VNIFILTER_ENTRY_MAX
-};
-#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
-
-enum {
-	VXLAN_VNIFILTER_UNSPEC,
-	VXLAN_VNIFILTER_ENTRY,
-	__VXLAN_VNIFILTER_MAX
-};
-#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
-
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -852,8 +748,6 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
-	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
-	IFLA_VXLAN_LOCALBYPASS,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -887,7 +781,6 @@ enum {
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
-	IFLA_GENEVE_INNER_PROTO_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -933,8 +826,6 @@ enum {
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
 	IFLA_GTP_ROLE,
-	IFLA_GTP_CREATE_SOCKETS,
-	IFLA_GTP_RESTART_COUNT,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1271,17 +1162,6 @@ enum {
 
 #define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
 
-enum {
-	IFLA_STATS_GETSET_UNSPEC,
-	IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
-				 * a filter mask for the corresponding group.
-				 */
-	IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
-	__IFLA_STATS_GETSET_MAX,
-};
-
-#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
-
 /* These are embedded into IFLA_STATS_LINK_XSTATS:
  * [IFLA_STATS_LINK_XSTATS]
  * -> [LINK_XSTATS_TYPE_xxx]
@@ -1299,21 +1179,10 @@ enum {
 enum {
 	IFLA_OFFLOAD_XSTATS_UNSPEC,
 	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO,	/* HW stats info. A nest */
-	IFLA_OFFLOAD_XSTATS_L3_STATS,	/* struct rtnl_hw_stats64 */
 	__IFLA_OFFLOAD_XSTATS_MAX
 };
 #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
 
-enum {
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST,		/* u8 */
-	IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED,		/* u8 */
-	__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
-};
-#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
-	(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
-
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
@@ -1412,14 +1281,4 @@ enum {
 
 #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
 
-/* DSA section */
-
-enum {
-	IFLA_DSA_UNSPEC,
-	IFLA_DSA_MASTER,
-	__IFLA_DSA_MAX,
-};
-
-#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
-
 #endif /* _UAPI_LINUX_IF_LINK_H */

include/uapi/linux/if_xdp.h

@@ -25,21 +25,9 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
-/* By setting this option, userspace application indicates that it can
- * handle multiple descriptors per packet thus enabling AF_XDP to split
- * multi-buffer XDP frames into multiple Rx descriptors. Without this set
- * such frames will be dropped.
- */
-#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
-
-/* Force checksum calculation in software. Can be used for testing or
- * working around potential HW issues. This option causes performance
- * degradation and only works in XDP_COPY mode.
- */
-#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -82,7 +70,6 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
-	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
@@ -112,41 +99,6 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
-/* Request transmit timestamp. Upon completion, put it into tx_timestamp
- * field of union xsk_tx_metadata.
- */
-#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
-
-/* Request transmit checksum offload. Checksum start position and offset
- * are communicated via csum_start and csum_offset fields of union
- * xsk_tx_metadata.
- */
-#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
-
-/* AF_XDP offloads request. 'request' union member is consumed by the driver
- * when the packet is being transmitted. 'completion' union member is
- * filled by the driver when the transmit completion arrives.
- */
-struct xsk_tx_metadata {
-	__u64 flags;
-
-	union {
-		struct {
-			/* XDP_TXMD_FLAGS_CHECKSUM */
-
-			/* Offset from desc->addr where checksumming should start. */
-			__u16 csum_start;
-			/* Offset from csum_start where checksum should be stored. */
-			__u16 csum_offset;
-		} request;
-
-		struct {
-			/* XDP_TXMD_FLAGS_TIMESTAMP */
-			__u64 tx_timestamp;
-		} completion;
-	};
-};
-
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -156,14 +108,4 @@ struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
-/* Flag indicating that the packet continues with the buffer pointed out by the
- * next frame in the ring. The end of the packet is signalled by setting this
- * bit to zero. For single buffer packets, every descriptor has 'options' set
- * to 0 and this maintains backward compatibility.
- */
-#define XDP_PKT_CONTD (1 << 0)
-
-/* TX packet carries valid metadata. */
-#define XDP_TX_METADATA (1 << 1)
-
 #endif /* _LINUX_IF_XDP_H */

include/uapi/linux/netdev.h

@@ -11,7 +11,7 @@
 
 /**
  * enum netdev_xdp_act
- * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
  *   (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
  * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
  * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
@@ -34,125 +34,28 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_RX_SG = 32,
 	NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
 
-	/* private: */
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
-/**
- * enum netdev_xdp_rx_metadata
- * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
- *   timestamp via bpf_xdp_metadata_rx_timestamp().
- * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
- *   hash via bpf_xdp_metadata_rx_hash().
- * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
- *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
- */
-enum netdev_xdp_rx_metadata {
-	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
-	NETDEV_XDP_RX_METADATA_HASH = 2,
-	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
-};
-
-/**
- * enum netdev_xsk_flags
- * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
- *   by the driver.
- * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
- *   driver.
- */
-enum netdev_xsk_flags {
-	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
-	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
-
-	/* private: */
-	NETDEV_XSK_FLAGS_MASK = 3,
-};
-
-enum netdev_queue_type {
-	NETDEV_QUEUE_TYPE_RX,
-	NETDEV_QUEUE_TYPE_TX,
-};
-
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
-	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
-	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
-	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
-enum {
-	NETDEV_A_PAGE_POOL_ID = 1,
-	NETDEV_A_PAGE_POOL_IFINDEX,
-	NETDEV_A_PAGE_POOL_NAPI_ID,
-	NETDEV_A_PAGE_POOL_INFLIGHT,
-	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
-	NETDEV_A_PAGE_POOL_DETACH_TIME,
-
-	__NETDEV_A_PAGE_POOL_MAX,
-	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
-};
-
-enum {
-	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
-	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
-	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
-
-	__NETDEV_A_PAGE_POOL_STATS_MAX,
-	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
-};
-
-enum {
-	NETDEV_A_NAPI_IFINDEX = 1,
-	NETDEV_A_NAPI_ID,
-	NETDEV_A_NAPI_IRQ,
-	NETDEV_A_NAPI_PID,
-
-	__NETDEV_A_NAPI_MAX,
-	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
-};
-
-enum {
-	NETDEV_A_QUEUE_ID = 1,
-	NETDEV_A_QUEUE_IFINDEX,
-	NETDEV_A_QUEUE_TYPE,
-	NETDEV_A_QUEUE_NAPI_ID,
-
-	__NETDEV_A_QUEUE_MAX,
-	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
-};
-
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
-	NETDEV_CMD_PAGE_POOL_GET,
-	NETDEV_CMD_PAGE_POOL_ADD_NTF,
-	NETDEV_CMD_PAGE_POOL_DEL_NTF,
-	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
-	NETDEV_CMD_PAGE_POOL_STATS_GET,
-	NETDEV_CMD_QUEUE_GET,
-	NETDEV_CMD_NAPI_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
-#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */

include/uapi/linux/perf_event.h

@@ -1339,8 +1339,7 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
-#define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
+/* 5-0x8 available */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */

include/uapi/linux/pkt_cls.h

@@ -204,6 +204,37 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
 /* ROUTE filter */
 
 enum {
@@ -234,6 +265,22 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
 /* Flow filter */
 
 enum {

include/uapi/linux/pkt_sched.h

@@ -457,6 +457,115 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO		8
+#define TC_CBQ_MAXLEVEL		8
+#define TC_CBQ_DEF_EWMA		5
+
+struct tc_cbq_lssopt {
+	unsigned char	change;
+	unsigned char	flags;
+#define TCF_CBQ_LSS_BOUNDED	1
+#define TCF_CBQ_LSS_ISOLATED	2
+	unsigned char  	ewma_log;
+	unsigned char  	level;
+#define TCF_CBQ_LSS_FLAGS	1
+#define TCF_CBQ_LSS_EWMA	2
+#define TCF_CBQ_LSS_MAXIDLE	4
+#define TCF_CBQ_LSS_MINIDLE	8
+#define TCF_CBQ_LSS_OFFTIME	0x10
+#define TCF_CBQ_LSS_AVPKT	0x20
+	__u32		maxidle;
+	__u32		minidle;
+	__u32		offtime;
+	__u32		avpkt;
+};
+
+struct tc_cbq_wrropt {
+	unsigned char	flags;
+	unsigned char	priority;
+	unsigned char	cpriority;
+	unsigned char	__reserved;
+	__u32		allot;
+	__u32		weight;
+};
+
+struct tc_cbq_ovl {
+	unsigned char	strategy;
+#define	TC_CBQ_OVL_CLASSIC	0
+#define	TC_CBQ_OVL_DELAY	1
+#define	TC_CBQ_OVL_LOWPRIO	2
+#define	TC_CBQ_OVL_DROP		3
+#define	TC_CBQ_OVL_RCLASSIC	4
+	unsigned char	priority2;
+	__u16		pad;
+	__u32		penalty;
+};
+
+struct tc_cbq_police {
+	unsigned char	police;
+	unsigned char	__res1;
+	unsigned short	__res2;
+};
+
+struct tc_cbq_fopt {
+	__u32		split;
+	__u32		defmap;
+	__u32		defchange;
+};
+
+struct tc_cbq_xstats {
+	__u32		borrows;
+	__u32		overactions;
+	__s32		avgidle;
+	__s32		undertime;
+};
+
+enum {
+	TCA_CBQ_UNSPEC,
+	TCA_CBQ_LSSOPT,
+	TCA_CBQ_WRROPT,
+	TCA_CBQ_FOPT,
+	TCA_CBQ_OVL_STRATEGY,
+	TCA_CBQ_RATE,
+	TCA_CBQ_RTAB,
+	TCA_CBQ_POLICE,
+	__TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+	TCA_DSMARK_UNSPEC,
+	TCA_DSMARK_INDICES,
+	TCA_DSMARK_DEFAULT_INDEX,
+	TCA_DSMARK_SET_TC_INDEX,
+	TCA_DSMARK_MASK,
+	TCA_DSMARK_VALUE,
+	__TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM  section */
+
+enum {
+	TCA_ATM_UNSPEC,
+	TCA_ATM_FD,		/* file/socket descriptor */
+	TCA_ATM_PTR,		/* pointer to descriptor - later */
+	TCA_ATM_HDR,		/* LL header */
+	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
+	TCA_ATM_ADDR,		/* PVC address (for output only) */
+	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
+	__TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
+
 /* Network emulator */
 
 enum {

scripts/build-fuzzers.sh

@@ -41,14 +41,14 @@ fi
 # due to https://bugs.gentoo.org/794601) so let's just point the script to
 # commits referring to versions of libelf that actually can be built
 rm -rf elfutils
-git clone https://sourceware.org/git/elfutils.git
+git clone git://sourceware.org/git/elfutils.git
 (
 cd elfutils
-git checkout 67a187d4c1790058fc7fd218317851cb68bb087c
+git checkout e9f3045caa5c4498f371383e5519151942d48b6d
 git log --oneline -1
 
 # ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
-sed -i 's/^\(NO_UNDEFINED=\).*/\1/' configure.ac
+find -name Makefile.am | xargs sed -i 's/,--no-undefined//'
 
 # ASan isn't compatible with -Wl,-z,defs either:
 # https://clang.llvm.org/docs/AddressSanitizer.html#usage
@@ -62,7 +62,6 @@ fi
 
 autoreconf -i -f
 if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
-            --disable-demangler --without-bzlib --without-lzma --without-zstd \
 	    CC="$CC" CFLAGS="-Wno-error $CFLAGS" CXX="$CXX" CXXFLAGS="-Wno-error $CXXFLAGS" LDFLAGS="$CFLAGS"; then
     cat config.log
     exit 1

src/Makefile

@@ -9,7 +9,7 @@ else
 endif
 
 LIBBPF_MAJOR_VERSION := 1
-LIBBPF_MINOR_VERSION := 4
+LIBBPF_MINOR_VERSION := 2
 LIBBPF_PATCH_VERSION := 0
 LIBBPF_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).$(LIBBPF_PATCH_VERSION)
 LIBBPF_MAJMIN_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).0
@@ -35,10 +35,7 @@ ALL_CFLAGS := $(INCLUDES)
 SHARED_CFLAGS += -fPIC -fvisibility=hidden -DSHARED
 
 CFLAGS ?= -g -O2 -Werror -Wall -std=gnu89
-ALL_CFLAGS += $(CFLAGS) 						\
-	      -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64		\
-	      -Wno-unknown-warning-option -Wno-format-overflow		\
-	      $(EXTRA_CFLAGS)
+ALL_CFLAGS += $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 $(EXTRA_CFLAGS)
 ALL_LDFLAGS += $(LDFLAGS) $(EXTRA_LDFLAGS)
 
 ifdef NO_PKG_CONFIG
@@ -55,7 +52,7 @@ STATIC_OBJDIR := $(OBJDIR)/staticobjs
 OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
 	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o \
 	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
-	relo_core.o usdt.o zip.o elf.o
+	relo_core.o usdt.o zip.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 

src/bpf.c

@@ -572,30 +572,20 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co
 				    (void *)keys, (void *)values, count, opts);
 }
 
-int bpf_obj_pin_opts(int fd, const char *pathname, const struct bpf_obj_pin_opts *opts)
+int bpf_obj_pin(int fd, const char *pathname)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, path_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int ret;
 
-	if (!OPTS_VALID(opts, bpf_obj_pin_opts))
-		return libbpf_err(-EINVAL);
-
 	memset(&attr, 0, attr_sz);
-	attr.path_fd = OPTS_GET(opts, path_fd, 0);
 	attr.pathname = ptr_to_u64((void *)pathname);
-	attr.file_flags = OPTS_GET(opts, file_flags, 0);
 	attr.bpf_fd = fd;
 
 	ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_obj_pin(int fd, const char *pathname)
-{
-	return bpf_obj_pin_opts(fd, pathname, NULL);
-}
-
 int bpf_obj_get(const char *pathname)
 {
 	return bpf_obj_get_opts(pathname, NULL);
@@ -603,7 +593,7 @@ int bpf_obj_get(const char *pathname)
 
 int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, path_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int fd;
 
@@ -611,7 +601,6 @@ int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts)
 		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-	attr.path_fd = OPTS_GET(opts, path_fd, 0);
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.file_flags = OPTS_GET(opts, file_flags, 0);
 
@@ -629,89 +618,55 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 	return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
 }
 
-int bpf_prog_attach_opts(int prog_fd, int target, enum bpf_attach_type type,
-			 const struct bpf_prog_attach_opts *opts)
+int bpf_prog_attach_opts(int prog_fd, int target_fd,
+			  enum bpf_attach_type type,
+			  const struct bpf_prog_attach_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
-	__u32 relative_id, flags;
-	int ret, relative_fd;
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
 		return libbpf_err(-EINVAL);
 
-	relative_id = OPTS_GET(opts, relative_id, 0);
-	relative_fd = OPTS_GET(opts, relative_fd, 0);
-	flags = OPTS_GET(opts, flags, 0);
-
-	/* validate we don't have unexpected combinations of non-zero fields */
-	if (relative_fd && relative_id)
-		return libbpf_err(-EINVAL);
-
 	memset(&attr, 0, attr_sz);
-	attr.target_fd		= target;
-	attr.attach_bpf_fd	= prog_fd;
-	attr.attach_type	= type;
-	attr.replace_bpf_fd	= OPTS_GET(opts, replace_fd, 0);
-	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
-
-	if (relative_id) {
-		attr.attach_flags = flags | BPF_F_ID;
-		attr.relative_id  = relative_id;
-	} else {
-		attr.attach_flags = flags;
-		attr.relative_fd  = relative_fd;
-	}
+	attr.target_fd	   = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type   = type;
+	attr.attach_flags  = OPTS_GET(opts, flags, 0);
+	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
 	ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach_opts(int prog_fd, int target, enum bpf_attach_type type,
-			 const struct bpf_prog_detach_opts *opts)
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, expected_revision);
-	__u32 relative_id, flags;
-	int ret, relative_fd;
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
-
-	if (!OPTS_VALID(opts, bpf_prog_detach_opts))
-		return libbpf_err(-EINVAL);
-
-	relative_id = OPTS_GET(opts, relative_id, 0);
-	relative_fd = OPTS_GET(opts, relative_fd, 0);
-	flags = OPTS_GET(opts, flags, 0);
-
-	/* validate we don't have unexpected combinations of non-zero fields */
-	if (relative_fd && relative_id)
-		return libbpf_err(-EINVAL);
+	int ret;
 
 	memset(&attr, 0, attr_sz);
-	attr.target_fd		= target;
-	attr.attach_bpf_fd	= prog_fd;
-	attr.attach_type	= type;
-	attr.expected_revision	= OPTS_GET(opts, expected_revision, 0);
-
-	if (relative_id) {
-		attr.attach_flags = flags | BPF_F_ID;
-		attr.relative_id  = relative_id;
-	} else {
-		attr.attach_flags = flags;
-		attr.relative_fd  = relative_fd;
-	}
+	attr.target_fd	 = target_fd;
+	attr.attach_type = type;
 
 	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
-{
-	return bpf_prog_detach_opts(0, target_fd, type, NULL);
-}
-
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
-	return bpf_prog_detach_opts(prog_fd, target_fd, type, NULL);
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.target_fd	 = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type = type;
+
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_create(int prog_fd, int target_fd,
@@ -719,9 +674,9 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    const struct bpf_link_create_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
-	__u32 target_btf_id, iter_info_len, relative_id;
-	int fd, err, relative_fd;
+	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
+	int fd, err;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return libbpf_err(-EINVAL);
@@ -767,17 +722,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, kprobe_multi))
 			return libbpf_err(-EINVAL);
 		break;
-	case BPF_TRACE_UPROBE_MULTI:
-		attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0);
-		attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0);
-		attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0));
-		attr.link_create.uprobe_multi.offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.offsets, 0));
-		attr.link_create.uprobe_multi.ref_ctr_offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.ref_ctr_offsets, 0));
-		attr.link_create.uprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, uprobe_multi.cookies, 0));
-		attr.link_create.uprobe_multi.pid = OPTS_GET(opts, uprobe_multi.pid, 0);
-		if (!OPTS_ZEROED(opts, uprobe_multi))
-			return libbpf_err(-EINVAL);
-		break;
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
@@ -786,46 +730,6 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tracing))
 			return libbpf_err(-EINVAL);
 		break;
-	case BPF_NETFILTER:
-		attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0);
-		attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0);
-		attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0);
-		attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0);
-		if (!OPTS_ZEROED(opts, netfilter))
-			return libbpf_err(-EINVAL);
-		break;
-	case BPF_TCX_INGRESS:
-	case BPF_TCX_EGRESS:
-		relative_fd = OPTS_GET(opts, tcx.relative_fd, 0);
-		relative_id = OPTS_GET(opts, tcx.relative_id, 0);
-		if (relative_fd && relative_id)
-			return libbpf_err(-EINVAL);
-		if (relative_id) {
-			attr.link_create.tcx.relative_id = relative_id;
-			attr.link_create.flags |= BPF_F_ID;
-		} else {
-			attr.link_create.tcx.relative_fd = relative_fd;
-		}
-		attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0);
-		if (!OPTS_ZEROED(opts, tcx))
-			return libbpf_err(-EINVAL);
-		break;
-	case BPF_NETKIT_PRIMARY:
-	case BPF_NETKIT_PEER:
-		relative_fd = OPTS_GET(opts, netkit.relative_fd, 0);
-		relative_id = OPTS_GET(opts, netkit.relative_id, 0);
-		if (relative_fd && relative_id)
-			return libbpf_err(-EINVAL);
-		if (relative_id) {
-			attr.link_create.netkit.relative_id = relative_id;
-			attr.link_create.flags |= BPF_F_ID;
-		} else {
-			attr.link_create.netkit.relative_fd = relative_fd;
-		}
-		attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0);
-		if (!OPTS_ZEROED(opts, netkit))
-			return libbpf_err(-EINVAL);
-		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
@@ -918,7 +822,8 @@ int bpf_iter_create(int link_fd)
 	return libbpf_err_errno(fd);
 }
 
-int bpf_prog_query_opts(int target, enum bpf_attach_type type,
+int bpf_prog_query_opts(int target_fd,
+			enum bpf_attach_type type,
 			struct bpf_prog_query_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, query);
@@ -929,20 +834,18 @@ int bpf_prog_query_opts(int target, enum bpf_attach_type type,
 		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, attr_sz);
-	attr.query.target_fd		= target;
-	attr.query.attach_type		= type;
-	attr.query.query_flags		= OPTS_GET(opts, query_flags, 0);
-	attr.query.count		= OPTS_GET(opts, count, 0);
-	attr.query.prog_ids		= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
-	attr.query.link_ids		= ptr_to_u64(OPTS_GET(opts, link_ids, NULL));
-	attr.query.prog_attach_flags	= ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
-	attr.query.link_attach_flags	= ptr_to_u64(OPTS_GET(opts, link_attach_flags, NULL));
+
+	attr.query.target_fd	= target_fd;
+	attr.query.attach_type	= type;
+	attr.query.query_flags	= OPTS_GET(opts, query_flags, 0);
+	attr.query.prog_cnt	= OPTS_GET(opts, prog_cnt, 0);
+	attr.query.prog_ids	= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
+	attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
 
 	ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz);
 
 	OPTS_SET(opts, attach_flags, attr.query.attach_flags);
-	OPTS_SET(opts, revision, attr.query.revision);
-	OPTS_SET(opts, count, attr.query.count);
+	OPTS_SET(opts, prog_cnt, attr.query.prog_cnt);
 
 	return libbpf_err_errno(ret);
 }

src/bpf.h

@@ -284,96 +284,36 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
 
-struct bpf_obj_pin_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-
-	__u32 file_flags;
-	int path_fd;
-
-	size_t :0;
-};
-#define bpf_obj_pin_opts__last_field path_fd
-
-LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
-LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname,
-				const struct bpf_obj_pin_opts *opts);
-
 struct bpf_obj_get_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 
 	__u32 file_flags;
-	int path_fd;
 
 	size_t :0;
 };
-#define bpf_obj_get_opts__last_field path_fd
+#define bpf_obj_get_opts__last_field file_flags
 
+LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
 LIBBPF_API int bpf_obj_get_opts(const char *pathname,
 				const struct bpf_obj_get_opts *opts);
 
+struct bpf_prog_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	unsigned int flags;
+	int replace_prog_fd;
+};
+#define bpf_prog_attach_opts__last_field replace_prog_fd
+
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
-struct bpf_prog_attach_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	union {
-		int replace_prog_fd;
-		int replace_fd;
-	};
-	int relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_prog_attach_opts__last_field expected_revision
-
-struct bpf_prog_detach_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	int relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_prog_detach_opts__last_field expected_revision
-
-/**
- * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to
- * *prog_fd* to a *target* which can represent a file descriptor or netdevice
- * ifindex.
- *
- * @param prog_fd BPF program file descriptor
- * @param target attach location file descriptor or ifindex
- * @param type attach type for the BPF program
- * @param opts options for configuring the attachment
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target,
-				    enum bpf_attach_type type,
-				    const struct bpf_prog_attach_opts *opts);
-
-/**
- * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to
- * *prog_fd* from a *target* which can represent a file descriptor or netdevice
- * ifindex.
- *
- * @param prog_fd BPF program file descriptor
- * @param target detach location file descriptor or ifindex
- * @param type detach type for the BPF program
- * @param opts options for configuring the detachment
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target,
-				    enum bpf_attach_type type,
-				    const struct bpf_prog_detach_opts *opts);
-
 union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */
 struct bpf_link_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -392,38 +332,13 @@ struct bpf_link_create_opts {
 			const unsigned long *addrs;
 			const __u64 *cookies;
 		} kprobe_multi;
-		struct {
-			__u32 flags;
-			__u32 cnt;
-			const char *path;
-			const unsigned long *offsets;
-			const unsigned long *ref_ctr_offsets;
-			const __u64 *cookies;
-			__u32 pid;
-		} uprobe_multi;
 		struct {
 			__u64 cookie;
 		} tracing;
-		struct {
-			__u32 pf;
-			__u32 hooknum;
-			__s32 priority;
-			__u32 flags;
-		} netfilter;
-		struct {
-			__u32 relative_fd;
-			__u32 relative_id;
-			__u64 expected_revision;
-		} tcx;
-		struct {
-			__u32 relative_fd;
-			__u32 relative_id;
-			__u64 expected_revision;
-		} netkit;
 	};
 	size_t :0;
 };
-#define bpf_link_create_opts__last_field uprobe_multi.pid
+#define bpf_link_create_opts__last_field kprobe_multi.cookies
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -560,31 +475,13 @@ struct bpf_prog_query_opts {
 	__u32 query_flags;
 	__u32 attach_flags; /* output argument */
 	__u32 *prog_ids;
-	union {
-		/* input+output argument */
-		__u32 prog_cnt;
-		__u32 count;
-	};
+	__u32 prog_cnt; /* input+output argument */
 	__u32 *prog_attach_flags;
-	__u32 *link_ids;
-	__u32 *link_attach_flags;
-	__u64 revision;
-	size_t :0;
 };
-#define bpf_prog_query_opts__last_field revision
+#define bpf_prog_query_opts__last_field prog_attach_flags
 
-/**
- * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links
- * which are attached to *target* which can represent a file descriptor or
- * netdevice ifindex.
- *
- * @param target query location file descriptor or ifindex
- * @param type attach type for the BPF program
- * @param opts options for configuring the query
- * @return 0, on success; negative error code, otherwise (errno is also set to
- * the error code)
- */
-LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type,
+LIBBPF_API int bpf_prog_query_opts(int target_fd,
+				   enum bpf_attach_type type,
 				   struct bpf_prog_query_opts *opts);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,

src/bpf_core_read.h

@@ -111,38 +111,6 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
-/*
- * Write to a bitfield, identified by s->field.
- * This is the inverse of BPF_CORE_WRITE_BITFIELD().
- */
-#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
-	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
-	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
-	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
-	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
-	unsigned long long mask, val, nval = new_val;			\
-	unsigned int rpad = rshift - lshift;				\
-									\
-	asm volatile("" : "+r"(p));					\
-									\
-	switch (byte_size) {						\
-	case 1: val = *(unsigned char *)p; break;			\
-	case 2: val = *(unsigned short *)p; break;			\
-	case 4: val = *(unsigned int *)p; break;			\
-	case 8: val = *(unsigned long long *)p; break;			\
-	}								\
-									\
-	mask = (~0ULL << rshift) >> lshift;				\
-	val = (val & ~mask) | ((nval << rpad) & mask);			\
-									\
-	switch (byte_size) {						\
-	case 1: *(unsigned char *)p      = val; break;			\
-	case 2: *(unsigned short *)p     = val; break;			\
-	case 4: *(unsigned int *)p       = val; break;			\
-	case 8: *(unsigned long long *)p = val; break;			\
-	}								\
-})
-
 #define ___bpf_field_ref1(field)	(field)
 #define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
 #define ___bpf_field_ref(args...)					    \

src/bpf_helper_defs.h

@@ -350,9 +350,7 @@ static long (*bpf_tail_call)(void *ctx, void *prog_array_map, __u32 index) = (vo
  * 	direct packet access.
  *
  * Returns
- * 	0 on success, or a negative error in case of failure. Positive
- * 	error indicates a potential drop or congestion in the target
- * 	device. The particular positive error codes are not defined.
+ * 	0 on success, or a negative error in case of failure.
  */
 static long (*bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 flags) = (void *) 13;
 
@@ -1206,8 +1204,8 @@ static long (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48;
  * 	*bpf_socket* should be one of the following:
  *
  * 	* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
- * 	  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 	  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 	This helper actually implements a subset of **setsockopt()**.
  * 	It supports the following *level*\ s:
@@ -1477,8 +1475,8 @@ static long (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct
  * 	*bpf_socket* should be one of the following:
  *
  * 	* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
- * 	  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 	  and **BPF_CGROUP_INET6_CONNECT**.
  *
  * 	This helper actually implements a subset of **getsockopt()**.
  * 	It supports the same set of *optname*\ s that is supported by
@@ -1834,10 +1832,6 @@ static long (*bpf_skb_load_bytes_relative)(const void *skb, __u32 offset, void *
  * 	**BPF_FIB_LOOKUP_DIRECT**
  * 		Do a direct table lookup vs full lookup using FIB
  * 		rules.
- * 	**BPF_FIB_LOOKUP_TBID**
- * 		Used with BPF_FIB_LOOKUP_DIRECT.
- * 		Use the routing table ID present in *params*->tbid
- * 		for the fib lookup.
  * 	**BPF_FIB_LOOKUP_OUTPUT**
  * 		Perform lookup from an egress perspective (default is
  * 		ingress).
@@ -1846,11 +1840,6 @@ static long (*bpf_skb_load_bytes_relative)(const void *skb, __u32 offset, void *
  * 		and *params*->smac will not be set as output. A common
  * 		use case is to call **bpf_redirect_neigh**\ () after
  * 		doing **bpf_fib_lookup**\ ().
- * 	**BPF_FIB_LOOKUP_SRC**
- * 		Derive and set source IP addr in *params*->ipv{4,6}_src
- * 		for the nexthop. If the src addr cannot be derived,
- * 		**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
- * 		case, *params*->dmac and *params*->smac are not set either.
  *
  * 	*ctx* is either **struct xdp_md** for XDP programs or
  * 	**struct sk_buff** tc cls_act programs.
@@ -3040,6 +3029,9 @@ static __u64 (*bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = (void *
  *
  * 	**-EOPNOTSUPP** if the operation is not supported, for example
  * 	a call from outside of TC ingress.
+ *
+ * 	**-ESOCKTNOSUPPORT** if the socket type is not supported
+ * 	(reuseport).
  */
 static long (*bpf_sk_assign)(void *ctx, void *sk, __u64 flags) = (void *) 124;
 
@@ -3322,8 +3314,6 @@ static struct udp6_sock *(*bpf_skc_to_udp6_sock)(void *sk) = (void *) 140;
  * bpf_get_task_stack
  *
  * 	Return a user or a kernel stack in bpf program provided buffer.
- * 	Note: the user stack will only be populated if the *task* is
- * 	the current task; all other tasks will return -EOPNOTSUPP.
  * 	To achieve this, the helper needs *task*, which is a valid
  * 	pointer to **struct task_struct**. To store the stacktrace, the
  * 	bpf program provides *buf* with a nonnegative *size*.
@@ -3335,7 +3325,6 @@ static struct udp6_sock *(*bpf_skc_to_udp6_sock)(void *sk) = (void *) 140;
  *
  * 	**BPF_F_USER_STACK**
  * 		Collect a user space stack instead of a kernel stack.
- * 		The *task* must be the current task.
  * 	**BPF_F_USER_BUILD_ID**
  * 		Collect buildid+offset instead of ips for user stack,
  * 		only valid if **BPF_F_USER_STACK** is also specified.
@@ -4044,8 +4033,6 @@ static long (*bpf_timer_set_callback)(struct bpf_timer *timer, void *callback_fn
  * 	**BPF_F_TIMER_ABS**
  * 		Start the timer in absolute expire value instead of the
  * 		default relative one.
- * 	**BPF_F_TIMER_CPU_PIN**
- * 		Timer will be pinned to the CPU of the caller.
  *
  *
  * Returns
@@ -4074,14 +4061,9 @@ static long (*bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172;
  *
  * 	Get address of the traced function (for tracing and kprobe programs).
  *
- * 	When called for kprobe program attached as uprobe it returns
- * 	probe address for both entry and return uprobe.
- *
- *
  * Returns
- * 	Address of the traced function for kprobe.
+ * 	Address of the traced function.
  * 	0 for kprobes placed within the function (not at the entry).
- * 	Address of the probe for uprobe and return uprobe.
  */
 static __u64 (*bpf_get_func_ip)(void *ctx) = (void *) 173;
 

src/bpf_helpers.h

@@ -77,21 +77,16 @@
 /*
  * Helper macros to manipulate data structures
  */
-
-/* offsetof() definition that uses __builtin_offset() might not preserve field
- * offset CO-RE relocation properly, so force-redefine offsetof() using
- * old-school approach which works with CO-RE correctly
- */
-#undef offsetof
-#define offsetof(type, member)	((unsigned long)&((type *)0)->member)
-
-/* redefined container_of() to ensure we use the above offsetof() macro */
-#undef container_of
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER)	((unsigned long)&((TYPE *)0)->MEMBER)
+#endif
+#ifndef container_of
 #define container_of(ptr, type, member)				\
 	({							\
 		void *__mptr = (void *)(ptr);			\
 		((type *)(__mptr - offsetof(type, member)));	\
 	})
+#endif
 
 /*
  * Compiler (optimization) barrier.
@@ -181,16 +176,12 @@ enum libbpf_tristate {
 #define __ksym __attribute__((section(".ksyms")))
 #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
 #define __kptr __attribute__((btf_type_tag("kptr")))
-#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
 
 #define bpf_ksym_exists(sym) ({									\
 	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
 	!!sym;											\
 })
 
-#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
-#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
-
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
 #endif

src/bpf_tracing.h

@@ -2,7 +2,7 @@
 #ifndef __BPF_TRACING_H__
 #define __BPF_TRACING_H__
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
@@ -351,7 +351,6 @@ struct pt_regs___arm64 {
  * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
  */
 
-/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG a0
 #define __PT_PARM2_REG a1
@@ -362,6 +361,8 @@ struct pt_regs___arm64 {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
+/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 #define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
 #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
@@ -382,7 +383,7 @@ struct pt_regs___arm64 {
  * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf
  */
 
-/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */
+/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG scratch.r0
 #define __PT_PARM2_REG scratch.r1

src/btf.c

@@ -448,165 +448,6 @@ static int btf_parse_type_sec(struct btf *btf)
 	return 0;
 }
 
-static int btf_validate_str(const struct btf *btf, __u32 str_off, const char *what, __u32 type_id)
-{
-	const char *s;
-
-	s = btf__str_by_offset(btf, str_off);
-	if (!s) {
-		pr_warn("btf: type [%u]: invalid %s (string offset %u)\n", type_id, what, str_off);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int btf_validate_id(const struct btf *btf, __u32 id, __u32 ctx_id)
-{
-	const struct btf_type *t;
-
-	t = btf__type_by_id(btf, id);
-	if (!t) {
-		pr_warn("btf: type [%u]: invalid referenced type ID %u\n", ctx_id, id);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int btf_validate_type(const struct btf *btf, const struct btf_type *t, __u32 id)
-{
-	__u32 kind = btf_kind(t);
-	int err, i, n;
-
-	err = btf_validate_str(btf, t->name_off, "type name", id);
-	if (err)
-		return err;
-
-	switch (kind) {
-	case BTF_KIND_UNKN:
-	case BTF_KIND_INT:
-	case BTF_KIND_FWD:
-	case BTF_KIND_FLOAT:
-		break;
-	case BTF_KIND_PTR:
-	case BTF_KIND_TYPEDEF:
-	case BTF_KIND_VOLATILE:
-	case BTF_KIND_CONST:
-	case BTF_KIND_RESTRICT:
-	case BTF_KIND_VAR:
-	case BTF_KIND_DECL_TAG:
-	case BTF_KIND_TYPE_TAG:
-		err = btf_validate_id(btf, t->type, id);
-		if (err)
-			return err;
-		break;
-	case BTF_KIND_ARRAY: {
-		const struct btf_array *a = btf_array(t);
-
-		err = btf_validate_id(btf, a->type, id);
-		err = err ?: btf_validate_id(btf, a->index_type, id);
-		if (err)
-			return err;
-		break;
-	}
-	case BTF_KIND_STRUCT:
-	case BTF_KIND_UNION: {
-		const struct btf_member *m = btf_members(t);
-
-		n = btf_vlen(t);
-		for (i = 0; i < n; i++, m++) {
-			err = btf_validate_str(btf, m->name_off, "field name", id);
-			err = err ?: btf_validate_id(btf, m->type, id);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_ENUM: {
-		const struct btf_enum *m = btf_enum(t);
-
-		n = btf_vlen(t);
-		for (i = 0; i < n; i++, m++) {
-			err = btf_validate_str(btf, m->name_off, "enum name", id);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_ENUM64: {
-		const struct btf_enum64 *m = btf_enum64(t);
-
-		n = btf_vlen(t);
-		for (i = 0; i < n; i++, m++) {
-			err = btf_validate_str(btf, m->name_off, "enum name", id);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_FUNC: {
-		const struct btf_type *ft;
-
-		err = btf_validate_id(btf, t->type, id);
-		if (err)
-			return err;
-		ft = btf__type_by_id(btf, t->type);
-		if (btf_kind(ft) != BTF_KIND_FUNC_PROTO) {
-			pr_warn("btf: type [%u]: referenced type [%u] is not FUNC_PROTO\n", id, t->type);
-			return -EINVAL;
-		}
-		break;
-	}
-	case BTF_KIND_FUNC_PROTO: {
-		const struct btf_param *m = btf_params(t);
-
-		n = btf_vlen(t);
-		for (i = 0; i < n; i++, m++) {
-			err = btf_validate_str(btf, m->name_off, "param name", id);
-			err = err ?: btf_validate_id(btf, m->type, id);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	case BTF_KIND_DATASEC: {
-		const struct btf_var_secinfo *m = btf_var_secinfos(t);
-
-		n = btf_vlen(t);
-		for (i = 0; i < n; i++, m++) {
-			err = btf_validate_id(btf, m->type, id);
-			if (err)
-				return err;
-		}
-		break;
-	}
-	default:
-		pr_warn("btf: type [%u]: unrecognized kind %u\n", id, kind);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-/* Validate basic sanity of BTF. It's intentionally less thorough than
- * kernel's validation and validates only properties of BTF that libbpf relies
- * on to be correct (e.g., valid type IDs, valid string offsets, etc)
- */
-static int btf_sanity_check(const struct btf *btf)
-{
-	const struct btf_type *t;
-	__u32 i, n = btf__type_cnt(btf);
-	int err;
-
-	for (i = 1; i < n; i++) {
-		t = btf_type_by_id(btf, i);
-		err = btf_validate_type(btf, t, i);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 __u32 btf__type_cnt(const struct btf *btf)
 {
 	return btf->start_id + btf->nr_types;
@@ -1061,7 +902,6 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	err = btf_parse_str_sec(btf);
 	err = err ?: btf_parse_type_sec(btf);
-	err = err ?: btf_sanity_check(btf);
 	if (err)
 		goto done;
 
@@ -1224,7 +1064,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
 	int err = 0;
 	long sz;
 
-	f = fopen(path, "rbe");
+	f = fopen(path, "rb");
 	if (!f) {
 		err = -errno;
 		goto err_out;

src/btf_dump.c

@@ -2250,25 +2250,9 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d,
 					     const struct btf_type *t,
 					     __u32 id,
 					     const void *data,
-					     __u8 bits_offset,
-					     __u8 bit_sz)
+					     __u8 bits_offset)
 {
-	__s64 size;
-
-	if (bit_sz) {
-		/* bits_offset is at most 7. bit_sz is at most 128. */
-		__u8 nr_bytes = (bits_offset + bit_sz + 7) / 8;
-
-		/* When bit_sz is non zero, it is called from
-		 * btf_dump_struct_data() where it only cares about
-		 * negative error value.
-		 * Return nr_bytes in success case to make it
-		 * consistent as the regular integer case below.
-		 */
-		return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes;
-	}
-
-	size = btf__resolve_size(d->btf, id);
+	__s64 size = btf__resolve_size(d->btf, id);
 
 	if (size < 0 || size >= INT_MAX) {
 		pr_warn("unexpected size [%zu] for id [%u]\n",
@@ -2423,7 +2407,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 {
 	int size, err = 0;
 
-	size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz);
+	size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset);
 	if (size < 0)
 		return size;
 	err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz);

src/elf.c

@@ -1,560 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
-#include <libelf.h>
-#include <gelf.h>
-#include <fcntl.h>
-#include <linux/kernel.h>
-
-#include "libbpf_internal.h"
-#include "str_error.h"
-
-#define STRERR_BUFSIZE  128
-
-/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
- * the symbol is hidden and can only be seen when referenced using an
- * explicit version number. This is a GNU extension.
- */
-#define VERSYM_HIDDEN	0x8000
-
-/* This is the mask for the rest of the data in a word read from a
- * SHT_GNU_versym section.
- */
-#define VERSYM_VERSION	0x7fff
-
-int elf_open(const char *binary_path, struct elf_fd *elf_fd)
-{
-	char errmsg[STRERR_BUFSIZE];
-	int fd, ret;
-	Elf *elf;
-
-	if (elf_version(EV_CURRENT) == EV_NONE) {
-		pr_warn("elf: failed to init libelf for %s\n", binary_path);
-		return -LIBBPF_ERRNO__LIBELF;
-	}
-	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("elf: failed to open %s: %s\n", binary_path,
-			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
-		return ret;
-	}
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
-		close(fd);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-	elf_fd->fd = fd;
-	elf_fd->elf = elf;
-	return 0;
-}
-
-void elf_close(struct elf_fd *elf_fd)
-{
-	if (!elf_fd)
-		return;
-	elf_end(elf_fd->elf);
-	close(elf_fd->fd);
-}
-
-/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
-static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
-{
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		GElf_Shdr sh;
-
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		if (sh.sh_type == sh_type)
-			return scn;
-	}
-	return NULL;
-}
-
-struct elf_sym {
-	const char *name;
-	GElf_Sym sym;
-	GElf_Shdr sh;
-	int ver;
-	bool hidden;
-};
-
-struct elf_sym_iter {
-	Elf *elf;
-	Elf_Data *syms;
-	Elf_Data *versyms;
-	Elf_Data *verdefs;
-	size_t nr_syms;
-	size_t strtabidx;
-	size_t verdef_strtabidx;
-	size_t next_sym_idx;
-	struct elf_sym sym;
-	int st_type;
-};
-
-static int elf_sym_iter_new(struct elf_sym_iter *iter,
-			    Elf *elf, const char *binary_path,
-			    int sh_type, int st_type)
-{
-	Elf_Scn *scn = NULL;
-	GElf_Ehdr ehdr;
-	GElf_Shdr sh;
-
-	memset(iter, 0, sizeof(*iter));
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		return -EINVAL;
-	}
-
-	scn = elf_find_next_scn_by_type(elf, sh_type, NULL);
-	if (!scn) {
-		pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
-			 binary_path);
-		return -ENOENT;
-	}
-
-	if (!gelf_getshdr(scn, &sh))
-		return -EINVAL;
-
-	iter->strtabidx = sh.sh_link;
-	iter->syms = elf_getdata(scn, 0);
-	if (!iter->syms) {
-		pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
-			binary_path, elf_errmsg(-1));
-		return -EINVAL;
-	}
-	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
-	iter->elf = elf;
-	iter->st_type = st_type;
-
-	/* Version symbol table is meaningful to dynsym only */
-	if (sh_type != SHT_DYNSYM)
-		return 0;
-
-	scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL);
-	if (!scn)
-		return 0;
-	iter->versyms = elf_getdata(scn, 0);
-
-	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
-	if (!scn)
-		return 0;
-
-	iter->verdefs = elf_getdata(scn, 0);
-	if (!iter->verdefs || !gelf_getshdr(scn, &sh)) {
-		pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path);
-		return -EINVAL;
-	}
-	iter->verdef_strtabidx = sh.sh_link;
-
-	return 0;
-}
-
-static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
-{
-	struct elf_sym *ret = &iter->sym;
-	GElf_Sym *sym = &ret->sym;
-	const char *name = NULL;
-	GElf_Versym versym;
-	Elf_Scn *sym_scn;
-	size_t idx;
-
-	for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) {
-		if (!gelf_getsym(iter->syms, idx, sym))
-			continue;
-		if (GELF_ST_TYPE(sym->st_info) != iter->st_type)
-			continue;
-		name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name);
-		if (!name)
-			continue;
-		sym_scn = elf_getscn(iter->elf, sym->st_shndx);
-		if (!sym_scn)
-			continue;
-		if (!gelf_getshdr(sym_scn, &ret->sh))
-			continue;
-
-		iter->next_sym_idx = idx + 1;
-		ret->name = name;
-		ret->ver = 0;
-		ret->hidden = false;
-
-		if (iter->versyms) {
-			if (!gelf_getversym(iter->versyms, idx, &versym))
-				continue;
-			ret->ver = versym & VERSYM_VERSION;
-			ret->hidden = versym & VERSYM_HIDDEN;
-		}
-		return ret;
-	}
-
-	return NULL;
-}
-
-static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
-{
-	GElf_Verdaux verdaux;
-	GElf_Verdef verdef;
-	int offset;
-
-	if (!iter->verdefs)
-		return NULL;
-
-	offset = 0;
-	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
-		if (verdef.vd_ndx != ver) {
-			if (!verdef.vd_next)
-				break;
-
-			offset += verdef.vd_next;
-			continue;
-		}
-
-		if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux))
-			break;
-
-		return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name);
-
-	}
-	return NULL;
-}
-
-static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym,
-			 const char *name, size_t name_len, const char *lib_ver)
-{
-	const char *ver_name;
-
-	/* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER
-	 * make sure the func part matches the user specified name
-	 */
-	if (strncmp(sym->name, name, name_len) != 0)
-		return false;
-
-	/* ...but we don't want a search for "foo" to match 'foo2" also, so any
-	 * additional characters in sname should be of the form "@@LIB".
-	 */
-	if (sym->name[name_len] != '\0' && sym->name[name_len] != '@')
-		return false;
-
-	/* If user does not specify symbol version, then we got a match */
-	if (!lib_ver)
-		return true;
-
-	/* If user specifies symbol version, for dynamic symbols,
-	 * get version name from ELF verdef section for comparison.
-	 */
-	if (sh_type == SHT_DYNSYM) {
-		ver_name = elf_get_vername(iter, sym->ver);
-		if (!ver_name)
-			return false;
-		return strcmp(ver_name, lib_ver) == 0;
-	}
-
-	/* For normal symbols, it is already in form of func@LIB_VER */
-	return strcmp(sym->name, name) == 0;
-}
-
-/* Transform symbol's virtual address (absolute for binaries and relative
- * for shared libs) into file offset, which is what kernel is expecting
- * for uprobe/uretprobe attachment.
- * See Documentation/trace/uprobetracer.rst for more details. This is done
- * by looking up symbol's containing section's header and using iter's virtual
- * address (sh_addr) and corresponding file offset (sh_offset) to transform
- * sym.st_value (virtual address) into desired final file offset.
- */
-static unsigned long elf_sym_offset(struct elf_sym *sym)
-{
-	return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset;
-}
-
-/* Find offset of function name in the provided ELF object. "binary_path" is
- * the path to the ELF binary represented by "elf", and only used for error
- * reporting matters. "name" matches symbol name or name@@LIB for library
- * functions.
- */
-long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
-{
-	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	const char *at_symbol, *lib_ver;
-	bool is_shared_lib;
-	long ret = -ENOENT;
-	size_t name_len;
-	GElf_Ehdr ehdr;
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		ret = -LIBBPF_ERRNO__FORMAT;
-		goto out;
-	}
-	/* for shared lib case, we do not need to calculate relative offset */
-	is_shared_lib = ehdr.e_type == ET_DYN;
-
-	/* Does name specify "@@LIB_VER" or "@LIB_VER" ? */
-	at_symbol = strchr(name, '@');
-	if (at_symbol) {
-		name_len = at_symbol - name;
-		/* skip second @ if it's @@LIB_VER case */
-		if (at_symbol[1] == '@')
-			at_symbol++;
-		lib_ver = at_symbol + 1;
-	} else {
-		name_len = strlen(name);
-		lib_ver = NULL;
-	}
-
-	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
-	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
-	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
-	 * reported as a warning/error.
-	 */
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-		int last_bind = -1;
-		int cur_bind;
-
-		ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC);
-		if (ret == -ENOENT)
-			continue;
-		if (ret)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver))
-				continue;
-
-			cur_bind = GELF_ST_BIND(sym->sym.st_info);
-
-			if (ret > 0) {
-				/* handle multiple matches */
-				if (elf_sym_offset(sym) == ret) {
-					/* same offset, no problem */
-					continue;
-				} else if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
-						sym->name, name, binary_path);
-					ret = -LIBBPF_ERRNO__FORMAT;
-					goto out;
-				} else if (cur_bind == STB_WEAK) {
-					/* already have a non-weak bind, and
-					 * this is a weak bind, so ignore.
-					 */
-					continue;
-				}
-			}
-
-			ret = elf_sym_offset(sym);
-			last_bind = cur_bind;
-		}
-		if (ret > 0)
-			break;
-	}
-
-	if (ret > 0) {
-		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
-			 ret);
-	} else {
-		if (ret == 0) {
-			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
-				is_shared_lib ? "should not be 0 in a shared library" :
-						"try using shared library path instead");
-			ret = -ENOENT;
-		} else {
-			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
-		}
-	}
-out:
-	return ret;
-}
-
-/* Find offset of function name in ELF object specified by path. "name" matches
- * symbol name or name@@LIB for library functions.
- */
-long elf_find_func_offset_from_file(const char *binary_path, const char *name)
-{
-	struct elf_fd elf_fd;
-	long ret = -ENOENT;
-
-	ret = elf_open(binary_path, &elf_fd);
-	if (ret)
-		return ret;
-	ret = elf_find_func_offset(elf_fd.elf, binary_path, name);
-	elf_close(&elf_fd);
-	return ret;
-}
-
-struct symbol {
-	const char *name;
-	int bind;
-	int idx;
-};
-
-static int symbol_cmp(const void *a, const void *b)
-{
-	const struct symbol *sym_a = a;
-	const struct symbol *sym_b = b;
-
-	return strcmp(sym_a->name, sym_b->name);
-}
-
-/*
- * Return offsets in @poffsets for symbols specified in @syms array argument.
- * On success returns 0 and offsets are returned in allocated array with @cnt
- * size, that needs to be released by the caller.
- */
-int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets,
-			     int st_type)
-{
-	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	int err = 0, i, cnt_done = 0;
-	unsigned long *offsets;
-	struct symbol *symbols;
-	struct elf_fd elf_fd;
-
-	err = elf_open(binary_path, &elf_fd);
-	if (err)
-		return err;
-
-	offsets = calloc(cnt, sizeof(*offsets));
-	symbols = calloc(cnt, sizeof(*symbols));
-
-	if (!offsets || !symbols) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0; i < cnt; i++) {
-		symbols[i].name = syms[i];
-		symbols[i].idx = i;
-	}
-
-	qsort(symbols, cnt, sizeof(*symbols), symbol_cmp);
-
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type);
-		if (err == -ENOENT)
-			continue;
-		if (err)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			unsigned long sym_offset = elf_sym_offset(sym);
-			int bind = GELF_ST_BIND(sym->sym.st_info);
-			struct symbol *found, tmp = {
-				.name = sym->name,
-			};
-			unsigned long *offset;
-
-			found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp);
-			if (!found)
-				continue;
-
-			offset = &offsets[found->idx];
-			if (*offset > 0) {
-				/* same offset, no problem */
-				if (*offset == sym_offset)
-					continue;
-				/* handle multiple matches */
-				if (found->bind != STB_WEAK && bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n",
-						sym->name, sym_offset, binary_path, *offset);
-					err = -ESRCH;
-					goto out;
-				} else if (bind == STB_WEAK) {
-					/* already have a non-weak bind, and
-					 * this is a weak bind, so ignore.
-					 */
-					continue;
-				}
-			} else {
-				cnt_done++;
-			}
-			*offset = sym_offset;
-			found->bind = bind;
-		}
-	}
-
-	if (cnt != cnt_done) {
-		err = -ENOENT;
-		goto out;
-	}
-
-	*poffsets = offsets;
-
-out:
-	free(symbols);
-	if (err)
-		free(offsets);
-	elf_close(&elf_fd);
-	return err;
-}
-
-/*
- * Return offsets in @poffsets for symbols specified by @pattern argument.
- * On success returns 0 and offsets are returned in allocated @poffsets
- * array with the @pctn size, that needs to be released by the caller.
- */
-int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
-				unsigned long **poffsets, size_t *pcnt)
-{
-	int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM };
-	unsigned long *offsets = NULL;
-	size_t cap = 0, cnt = 0;
-	struct elf_fd elf_fd;
-	int err = 0, i;
-
-	err = elf_open(binary_path, &elf_fd);
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
-		struct elf_sym_iter iter;
-		struct elf_sym *sym;
-
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
-		if (err == -ENOENT)
-			continue;
-		if (err)
-			goto out;
-
-		while ((sym = elf_sym_iter_next(&iter))) {
-			if (!glob_match(sym->name, pattern))
-				continue;
-
-			err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets),
-						cnt + 1);
-			if (err)
-				goto out;
-
-			offsets[cnt++] = elf_sym_offset(sym);
-		}
-
-		/* If we found anything in the first symbol section,
-		 * do not search others to avoid duplicates.
-		 */
-		if (cnt)
-			break;
-	}
-
-	if (cnt) {
-		*poffsets = offsets;
-		*pcnt = cnt;
-	} else {
-		err = -ENOENT;
-	}
-
-out:
-	if (err)
-		free(offsets);
-	elf_close(&elf_fd);
-	return err;
-}

src/gen_loader.c

@@ -703,17 +703,17 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo
 	/* obtain fd in BPF_REG_9 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
 	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
-	/* load fd_array slot pointer */
-	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
-	/* store BTF fd in slot, 0 for vmlinux */
-	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
-	/* jump to insn[insn_idx].off store if fd denotes module BTF */
+	/* jump to fd_array store if fd denotes module BTF */
 	emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2));
 	/* set the default value for off */
 	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
 	/* skip BTF fd store for vmlinux BTF */
-	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1));
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
+	/* load fd_array slot pointer */
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
+	/* store BTF fd in slot */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
 	/* store index into insn[insn_idx].off */
 	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
 log:

src/hashmap.h

@@ -80,6 +80,16 @@ struct hashmap {
 	size_t sz;
 };
 
+#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
+	.hash_fn = (hash_fn),			\
+	.equal_fn = (equal_fn),			\
+	.ctx = (ctx),				\
+	.buckets = NULL,			\
+	.cap = 0,				\
+	.cap_bits = 0,				\
+	.sz = 0,				\
+}
+
 void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
 		   hashmap_equal_fn equal_fn, void *ctx);
 struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,

src/libbpf.h

@@ -266,7 +266,6 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
 LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
 					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
-LIBBPF_API int bpf_object__unpin(struct bpf_object *object, const char *path);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
@@ -530,57 +529,6 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
 				      const struct bpf_kprobe_multi_opts *opts);
 
-struct bpf_uprobe_multi_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	/* array of function symbols to attach to */
-	const char **syms;
-	/* array of function addresses to attach to */
-	const unsigned long *offsets;
-	/* optional, array of associated ref counter offsets */
-	const unsigned long *ref_ctr_offsets;
-	/* optional, array of associated BPF cookies */
-	const __u64 *cookies;
-	/* number of elements in syms/addrs/cookies arrays */
-	size_t cnt;
-	/* create return uprobes */
-	bool retprobe;
-	size_t :0;
-};
-
-#define bpf_uprobe_multi_opts__last_field retprobe
-
-/**
- * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program
- * to multiple uprobes with uprobe_multi link.
- *
- * User can specify 2 mutually exclusive set of inputs:
- *
- *   1) use only path/func_pattern/pid arguments
- *
- *   2) use path/pid with allowed combinations of
- *      syms/offsets/ref_ctr_offsets/cookies/cnt
- *
- *      - syms and offsets are mutually exclusive
- *      - ref_ctr_offsets and cookies are optional
- *
- *
- * @param prog BPF program to attach
- * @param pid Process ID to attach the uprobe to, 0 for self (own process),
- * -1 for all processes
- * @param binary_path Path to binary
- * @param func_pattern Regular expression to specify functions to attach
- * BPF program to
- * @param opts Additional options (see **struct bpf_uprobe_multi_opts**)
- * @return 0, on success; negative error code, otherwise
- */
-LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
-				 pid_t pid,
-				 const char *binary_path,
-				 const char *func_pattern,
-				 const struct bpf_uprobe_multi_opts *opts);
-
 struct bpf_ksyscall_opts {
 	/* size of this struct, for forward/backward compatibility */
 	size_t sz;
@@ -770,51 +718,6 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
-struct bpf_netfilter_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-
-	__u32 pf;
-	__u32 hooknum;
-	__s32 priority;
-	__u32 flags;
-};
-#define bpf_netfilter_opts__last_field flags
-
-LIBBPF_API struct bpf_link *
-bpf_program__attach_netfilter(const struct bpf_program *prog,
-			      const struct bpf_netfilter_opts *opts);
-
-struct bpf_tcx_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	__u32 flags;
-	__u32 relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_tcx_opts__last_field expected_revision
-
-LIBBPF_API struct bpf_link *
-bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
-			const struct bpf_tcx_opts *opts);
-
-struct bpf_netkit_opts {
-	/* size of this struct, for forward/backward compatibility */
-	size_t sz;
-	__u32 flags;
-	__u32 relative_fd;
-	__u32 relative_id;
-	__u64 expected_revision;
-	size_t :0;
-};
-#define bpf_netkit_opts__last_field expected_revision
-
-LIBBPF_API struct bpf_link *
-bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
-			   const struct bpf_netkit_opts *opts);
-
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
@@ -966,22 +869,8 @@ LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node);
 /* get/set map key size */
 LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size);
-/* get map value size */
+/* get/set map value size */
 LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map);
-/**
- * @brief **bpf_map__set_value_size()** sets map value size.
- * @param map the BPF map instance
- * @return 0, on success; negative error, otherwise
- *
- * There is a special case for maps with associated memory-mapped regions, like
- * the global data section maps (bss, data, rodata). When this function is used
- * on such a map, the mapped region is resized. Afterward, an attempt is made to
- * adjust the corresponding BTF info. This attempt is best-effort and can only
- * succeed if the last variable of the data section map is an array. The array
- * BTF type is replaced by a new BTF array type with a different length.
- * Any previously existing pointers returned from bpf_map__initial_value() or
- * corresponding data section skeleton pointer must be reinitialized.
- */
 LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size);
 /* get map key/value BTF type IDs */
 LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
@@ -995,7 +884,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
-LIBBPF_API void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
+LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 
 /**
  * @brief **bpf_map__is_internal()** tells the caller whether or not the
@@ -1187,10 +1076,9 @@ struct bpf_xdp_query_opts {
 	__u32 skb_prog_id;	/* output */
 	__u8 attach_mode;	/* output */
 	__u64 feature_flags;	/* output */
-	__u32 xdp_zc_max_segs;	/* output */
 	size_t :0;
 };
-#define bpf_xdp_query_opts__last_field xdp_zc_max_segs
+#define bpf_xdp_query_opts__last_field feature_flags
 
 LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
 			      const struct bpf_xdp_attach_opts *opts);
@@ -1244,7 +1132,6 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
 
 /* Ring buffer APIs */
 struct ring_buffer;
-struct ring;
 struct user_ring_buffer;
 
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
@@ -1265,78 +1152,6 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
-/**
- * @brief **ring_buffer__ring()** returns the ringbuffer object inside a given
- * ringbuffer manager representing a single BPF_MAP_TYPE_RINGBUF map instance.
- *
- * @param rb A ringbuffer manager object.
- * @param idx An index into the ringbuffers contained within the ringbuffer
- * manager object. The index is 0-based and corresponds to the order in which
- * ring_buffer__add was called.
- * @return A ringbuffer object on success; NULL and errno set if the index is
- * invalid.
- */
-LIBBPF_API struct ring *ring_buffer__ring(struct ring_buffer *rb,
-					  unsigned int idx);
-
-/**
- * @brief **ring__consumer_pos()** returns the current consumer position in the
- * given ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The current consumer position.
- */
-LIBBPF_API unsigned long ring__consumer_pos(const struct ring *r);
-
-/**
- * @brief **ring__producer_pos()** returns the current producer position in the
- * given ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The current producer position.
- */
-LIBBPF_API unsigned long ring__producer_pos(const struct ring *r);
-
-/**
- * @brief **ring__avail_data_size()** returns the number of bytes in the
- * ringbuffer not yet consumed. This has no locking associated with it, so it
- * can be inaccurate if operations are ongoing while this is called. However, it
- * should still show the correct trend over the long-term.
- *
- * @param r A ringbuffer object.
- * @return The number of bytes not yet consumed.
- */
-LIBBPF_API size_t ring__avail_data_size(const struct ring *r);
-
-/**
- * @brief **ring__size()** returns the total size of the ringbuffer's map data
- * area (excluding special producer/consumer pages). Effectively this gives the
- * amount of usable bytes of data inside the ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The total size of the ringbuffer map data area.
- */
-LIBBPF_API size_t ring__size(const struct ring *r);
-
-/**
- * @brief **ring__map_fd()** returns the file descriptor underlying the given
- * ringbuffer.
- *
- * @param r A ringbuffer object.
- * @return The underlying ringbuffer file descriptor
- */
-LIBBPF_API int ring__map_fd(const struct ring *r);
-
-/**
- * @brief **ring__consume()** consumes available ringbuffer data without event
- * polling.
- *
- * @param r A ringbuffer object.
- * @return The number of records consumed (or INT_MAX, whichever is less), or
- * a negative number if any of the callbacks return an error.
- */
-LIBBPF_API int ring__consume(struct ring *r);
-
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };

src/libbpf.map

@@ -391,24 +391,3 @@ LIBBPF_1.2.0 {
 		bpf_map_get_info_by_fd;
 		bpf_prog_get_info_by_fd;
 } LIBBPF_1.1.0;
-
-LIBBPF_1.3.0 {
-	global:
-		bpf_obj_pin_opts;
-		bpf_object__unpin;
-		bpf_prog_detach_opts;
-		bpf_program__attach_netfilter;
-		bpf_program__attach_netkit;
-		bpf_program__attach_tcx;
-		bpf_program__attach_uprobe_multi;
-		ring__avail_data_size;
-		ring__consume;
-		ring__consumer_pos;
-		ring__map_fd;
-		ring__producer_pos;
-		ring__size;
-		ring_buffer__ring;
-} LIBBPF_1.2.0;
-
-LIBBPF_1.4.0 {
-} LIBBPF_1.3.0;

src/libbpf_common.h

@@ -70,23 +70,4 @@
 		};							    \
 	})
 
-/* Helper macro to clear and optionally reinitialize libbpf options struct
- *
- * Small helper macro to reset all fields and to reinitialize the common
- * structure size member. Values provided by users in struct initializer-
- * syntax as varargs can be provided as well to reinitialize options struct
- * specific members.
- */
-#define LIBBPF_OPTS_RESET(NAME, ...)					    \
-	do {								    \
-		typeof(NAME) ___##NAME = ({ 				    \
-			memset(&___##NAME, 0, sizeof(NAME));		    \
-			(typeof(NAME)) {				    \
-				.sz = sizeof(NAME),			    \
-				__VA_ARGS__				    \
-			};						    \
-		});							    \
-		memcpy(&NAME, &___##NAME, sizeof(NAME));		    \
-	} while (0)
-
 #endif /* __LIBBPF_LIBBPF_COMMON_H */

src/libbpf_internal.h

@@ -15,7 +15,6 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <libelf.h>
 #include "relo_core.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -355,8 +354,6 @@ enum kern_feature_id {
 	FEAT_BTF_ENUM64,
 	/* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */
 	FEAT_SYSCALL_WRAPPER,
-	/* BPF multi-uprobe link support */
-	FEAT_UPROBE_MULTI_LINK,
 	__FEAT_CNT,
 };
 
@@ -555,20 +552,6 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
-/* Point *fixed_fd* to the same file that *tmp_fd* points to.
- * Regardless of success, *tmp_fd* is closed.
- * Whatever *fixed_fd* pointed to is closed silently.
- */
-static inline int reuse_fd(int fixed_fd, int tmp_fd)
-{
-	int err;
-
-	err = dup2(tmp_fd, fixed_fd);
-	err = err < 0 ? -errno : 0;
-	close(tmp_fd); /* clean up temporary FD */
-	return err;
-}
-
 /* The following two functions are exposed to bpftool */
 int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 		       size_t local_essent_len,
@@ -594,23 +577,4 @@ static inline bool is_pow_of_2(size_t x)
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
-bool glob_match(const char *str, const char *pat);
-
-long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
-long elf_find_func_offset_from_file(const char *binary_path, const char *name);
-
-struct elf_fd {
-	Elf *elf;
-	int fd;
-};
-
-int elf_open(const char *binary_path, struct elf_fd *elf_fd);
-void elf_close(struct elf_fd *elf_fd);
-
-int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets,
-			     int st_type);
-int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
-				 unsigned long **poffsets, size_t *pcnt);
-
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_probes.c

@@ -38,7 +38,7 @@ static __u32 get_ubuntu_kernel_version(void)
 	if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0)
 		return 0;
 
-	f = fopen(ubuntu_kver_file, "re");
+	f = fopen(ubuntu_kver_file, "r");
 	if (!f)
 		return 0;
 
@@ -74,7 +74,11 @@ static __u32 get_debian_kernel_version(struct utsname *info)
 	if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3)
 		return 0;
 
-	return KERNEL_VERSION(major, minor, patch);
+	// Patch to run on Debian 10
+	if (major == 4 && minor == 19)
+		return KERNEL_VERSION(major, minor, 255);
+        else
+		return KERNEL_VERSION(major, minor, patch);
 }
 
 __u32 get_kernel_version(void)
@@ -181,9 +185,6 @@ static int probe_prog_load(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 		break;
-	case BPF_PROG_TYPE_NETFILTER:
-		opts.expected_attach_type = BPF_NETFILTER;
-		break;
 	default:
 		return -EOPNOTSUPP;
 	}

src/libbpf_version.h

@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 4
+#define LIBBPF_MINOR_VERSION 2
 
 #endif /* __LIBBPF_VERSION_H */

src/linker.c

@@ -719,28 +719,13 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			return -EINVAL;
 		}
 
-		if (is_dwarf_sec_name(sec->sec_name))
-			continue;
+		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign))
+			return -EINVAL;
+		if (sec->shdr->sh_addralign != sec->data->d_align)
+			return -EINVAL;
 
-		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) {
-			pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
-				obj->filename);
+		if (sec->shdr->sh_size != sec->data->d_size)
 			return -EINVAL;
-		}
-		if (sec->shdr->sh_addralign != sec->data->d_align) {
-			pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
-				(long long unsigned)sec->data->d_align, obj->filename);
-			return -EINVAL;
-		}
-
-		if (sec->shdr->sh_size != sec->data->d_size) {
-			pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n",
-				sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
-				(long long unsigned)sec->data->d_size, obj->filename);
-			return -EINVAL;
-		}
 
 		switch (sec->shdr->sh_type) {
 		case SHT_SYMTAB:
@@ -752,12 +737,8 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			break;
 		case SHT_PROGBITS:
 			if (sec->shdr->sh_flags & SHF_EXECINSTR) {
-				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) {
-					pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n",
-						sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
-						obj->filename);
+				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0)
 					return -EINVAL;
-				}
 			}
 			break;
 		case SHT_NOBITS:

src/netlink.c

@@ -45,7 +45,6 @@ struct xdp_id_md {
 
 struct xdp_features_md {
 	int ifindex;
-	__u32 xdp_zc_max_segs;
 	__u64 flags;
 };
 
@@ -422,9 +421,6 @@ static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 		return NL_CONT;
 
 	md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
-	if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS])
-		md->xdp_zc_max_segs =
-			libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]);
 	return NL_DONE;
 }
 
@@ -497,7 +493,6 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
 		return libbpf_err(err);
 
 	opts->feature_flags = md.flags;
-	opts->xdp_zc_max_segs = md.xdp_zc_max_segs;
 
 skip_feature_flags:
 	return 0;

src/relo_core.c

@@ -776,7 +776,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		break;
 	case BPF_CORE_FIELD_SIGNED:
 		*val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) ||
-		       (btf_is_int(mt) && (btf_int_encoding(mt) & BTF_INT_SIGNED));
+		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
 		break;

src/ringbuf.c

@@ -34,7 +34,7 @@ struct ring {
 
 struct ring_buffer {
 	struct epoll_event *events;
-	struct ring **rings;
+	struct ring *rings;
 	size_t page_size;
 	int epoll_fd;
 	int ring_cnt;
@@ -57,7 +57,7 @@ struct ringbuf_hdr {
 	__u32 pad;
 };
 
-static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r)
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
 {
 	if (r->consumer_pos) {
 		munmap(r->consumer_pos, rb->page_size);
@@ -67,8 +67,6 @@ static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r)
 		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
 		r->producer_pos = NULL;
 	}
-
-	free(r);
 }
 
 /* Add extra RINGBUF maps to this ring buffer manager */
@@ -109,10 +107,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		return libbpf_err(-ENOMEM);
 	rb->events = tmp;
 
-	r = calloc(1, sizeof(*r));
-	if (!r)
-		return libbpf_err(-ENOMEM);
-	rb->rings[rb->ring_cnt] = r;
+	r = &rb->rings[rb->ring_cnt];
+	memset(r, 0, sizeof(*r));
 
 	r->map_fd = map_fd;
 	r->sample_cb = sample_cb;
@@ -125,7 +121,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
 			map_fd, err);
-		goto err_out;
+		return libbpf_err(err);
 	}
 	r->consumer_pos = tmp;
 
@@ -135,16 +131,16 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	 */
 	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
 	if (mmap_sz != (__u64)(size_t)mmap_sz) {
-		err = -E2BIG;
 		pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries);
-		goto err_out;
+		return libbpf_err(-E2BIG);
 	}
 	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
+		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
 			map_fd, err);
-		goto err_out;
+		return libbpf_err(err);
 	}
 	r->producer_pos = tmp;
 	r->data = tmp + rb->page_size;
@@ -156,17 +152,14 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	e->data.fd = rb->ring_cnt;
 	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
 		err = -errno;
+		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
 			map_fd, err);
-		goto err_out;
+		return libbpf_err(err);
 	}
 
 	rb->ring_cnt++;
 	return 0;
-
-err_out:
-	ringbuf_free_ring(rb, r);
-	return libbpf_err(err);
 }
 
 void ring_buffer__free(struct ring_buffer *rb)
@@ -177,7 +170,7 @@ void ring_buffer__free(struct ring_buffer *rb)
 		return;
 
 	for (i = 0; i < rb->ring_cnt; ++i)
-		ringbuf_free_ring(rb, rb->rings[i]);
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
 	if (rb->epoll_fd >= 0)
 		close(rb->epoll_fd);
 
@@ -285,7 +278,7 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	int i;
 
 	for (i = 0; i < rb->ring_cnt; i++) {
-		struct ring *ring = rb->rings[i];
+		struct ring *ring = &rb->rings[i];
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
@@ -312,7 +305,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 	for (i = 0; i < cnt; i++) {
 		__u32 ring_id = rb->events[i].data.fd;
-		struct ring *ring = rb->rings[ring_id];
+		struct ring *ring = &rb->rings[ring_id];
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
@@ -330,58 +323,6 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
 	return rb->epoll_fd;
 }
 
-struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx)
-{
-	if (idx >= rb->ring_cnt)
-		return errno = ERANGE, NULL;
-
-	return rb->rings[idx];
-}
-
-unsigned long ring__consumer_pos(const struct ring *r)
-{
-	/* Synchronizes with smp_store_release() in ringbuf_process_ring(). */
-	return smp_load_acquire(r->consumer_pos);
-}
-
-unsigned long ring__producer_pos(const struct ring *r)
-{
-	/* Synchronizes with smp_store_release() in __bpf_ringbuf_reserve() in
-	 * the kernel.
-	 */
-	return smp_load_acquire(r->producer_pos);
-}
-
-size_t ring__avail_data_size(const struct ring *r)
-{
-	unsigned long cons_pos, prod_pos;
-
-	cons_pos = ring__consumer_pos(r);
-	prod_pos = ring__producer_pos(r);
-	return prod_pos - cons_pos;
-}
-
-size_t ring__size(const struct ring *r)
-{
-	return r->mask + 1;
-}
-
-int ring__map_fd(const struct ring *r)
-{
-	return r->map_fd;
-}
-
-int ring__consume(struct ring *r)
-{
-	int64_t res;
-
-	res = ringbuf_process_ring(r);
-	if (res < 0)
-		return libbpf_err(res);
-
-	return res > INT_MAX ? INT_MAX : res;
-}
-
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {

src/usdt.bpf.h

@@ -4,8 +4,8 @@
 #define __USDT_BPF_H__
 
 #include <linux/errno.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 /* Below types and maps are internal implementation details of libbpf's USDT
  * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should

src/usdt.c

@@ -250,7 +250,6 @@ struct usdt_manager {
 
 	bool has_bpf_cookie;
 	bool has_sema_refcnt;
-	bool has_uprobe_multi;
 };
 
 struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
@@ -285,11 +284,6 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 	 */
 	man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0;
 
-	/*
-	 * Detect kernel support for uprobe multi link to be used for attaching
-	 * usdt probes.
-	 */
-	man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK);
 	return man;
 }
 
@@ -472,7 +466,7 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs,
 
 proceed:
 	sprintf(line, "/proc/%d/maps", pid);
-	f = fopen(line, "re");
+	f = fopen(line, "r");
 	if (!f) {
 		err = -errno;
 		pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n",
@@ -777,7 +771,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 		target->rel_ip = usdt_rel_ip;
 		target->sema_off = usdt_sema_off;
 
-		/* notes.args references strings from ELF itself, so they can
+		/* notes.args references strings from Elf itself, so they can
 		 * be referenced safely until elf_end() call
 		 */
 		target->spec_str = note.args;
@@ -814,8 +808,6 @@ struct bpf_link_usdt {
 		long abs_ip;
 		struct bpf_link *link;
 	} *uprobes;
-
-	struct bpf_link *multi_link;
 };
 
 static int bpf_link_usdt_detach(struct bpf_link *link)
@@ -824,9 +816,6 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 	struct usdt_manager *man = usdt_link->usdt_man;
 	int i;
 
-	bpf_link__destroy(usdt_link->multi_link);
-
-	/* When having multi_link, uprobe_cnt is 0 */
 	for (i = 0; i < usdt_link->uprobe_cnt; i++) {
 		/* detach underlying uprobe link */
 		bpf_link__destroy(usdt_link->uprobes[i].link);
@@ -863,11 +852,8 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 		 * system is so exhausted on memory, it's the least of user's
 		 * concerns, probably.
 		 * So just do our best here to return those IDs to usdt_manager.
-		 * Another edge case when we can legitimately get NULL is when
-		 * new_cnt is zero, which can happen in some edge cases, so we
-		 * need to be careful about that.
 		 */
-		if (new_free_ids || new_cnt == 0) {
+		if (new_free_ids) {
 			memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids,
 			       usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids));
 			man->free_spec_ids = new_free_ids;
@@ -957,24 +943,33 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 					  const char *usdt_provider, const char *usdt_name,
 					  __u64 usdt_cookie)
 {
-	unsigned long *offsets = NULL, *ref_ctr_offsets = NULL;
-	int i, err, spec_map_fd, ip_map_fd;
+	int i, fd, err, spec_map_fd, ip_map_fd;
 	LIBBPF_OPTS(bpf_uprobe_opts, opts);
 	struct hashmap *specs_hash = NULL;
 	struct bpf_link_usdt *link = NULL;
 	struct usdt_target *targets = NULL;
-	__u64 *cookies = NULL;
-	struct elf_fd elf_fd;
 	size_t target_cnt;
+	Elf *elf;
 
 	spec_map_fd = bpf_map__fd(man->specs_map);
 	ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map);
 
-	err = elf_open(path, &elf_fd);
-	if (err)
+	/* TODO: perform path resolution similar to uprobe's */
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		err = -errno;
+		pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err);
 		return libbpf_err_ptr(err);
+	}
 
-	err = sanity_check_usdt_elf(elf_fd.elf, path);
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		err = -EBADF;
+		pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1));
+		goto err_out;
+	}
+
+	err = sanity_check_usdt_elf(elf, path);
 	if (err)
 		goto err_out;
 
@@ -987,7 +982,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	/* discover USDT in given binary, optionally limiting
 	 * activations to a given PID, if pid > 0
 	 */
-	err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name,
+	err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name,
 				   usdt_cookie, &targets, &target_cnt);
 	if (err <= 0) {
 		err = (err == 0) ? -ENOENT : err;
@@ -1010,21 +1005,10 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 	link->link.detach = &bpf_link_usdt_detach;
 	link->link.dealloc = &bpf_link_usdt_dealloc;
 
-	if (man->has_uprobe_multi) {
-		offsets = calloc(target_cnt, sizeof(*offsets));
-		cookies = calloc(target_cnt, sizeof(*cookies));
-		ref_ctr_offsets = calloc(target_cnt, sizeof(*ref_ctr_offsets));
-
-		if (!offsets || !ref_ctr_offsets || !cookies) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-	} else {
-		link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
-		if (!link->uprobes) {
-			err = -ENOMEM;
-			goto err_out;
-		}
+	link->uprobes = calloc(target_cnt, sizeof(*link->uprobes));
+	if (!link->uprobes) {
+		err = -ENOMEM;
+		goto err_out;
 	}
 
 	for (i = 0; i < target_cnt; i++) {
@@ -1065,65 +1049,37 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
 			goto err_out;
 		}
 
-		if (man->has_uprobe_multi) {
-			offsets[i] = target->rel_ip;
-			ref_ctr_offsets[i] = target->sema_off;
-			cookies[i] = spec_id;
-		} else {
-			opts.ref_ctr_offset = target->sema_off;
-			opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
-			uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
-								      target->rel_ip, &opts);
-			err = libbpf_get_error(uprobe_link);
-			if (err) {
-				pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
-					i, usdt_provider, usdt_name, path, err);
-				goto err_out;
-			}
-
-			link->uprobes[i].link = uprobe_link;
-			link->uprobes[i].abs_ip = target->abs_ip;
-			link->uprobe_cnt++;
-		}
-	}
-
-	if (man->has_uprobe_multi) {
-		LIBBPF_OPTS(bpf_uprobe_multi_opts, opts_multi,
-			.ref_ctr_offsets = ref_ctr_offsets,
-			.offsets = offsets,
-			.cookies = cookies,
-			.cnt = target_cnt,
-		);
-
-		link->multi_link = bpf_program__attach_uprobe_multi(prog, pid, path,
-								    NULL, &opts_multi);
-		if (!link->multi_link) {
-			err = -errno;
-			pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %d\n",
-				usdt_provider, usdt_name, path, err);
+		opts.ref_ctr_offset = target->sema_off;
+		opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0;
+		uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path,
+							      target->rel_ip, &opts);
+		err = libbpf_get_error(uprobe_link);
+		if (err) {
+			pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n",
+				i, usdt_provider, usdt_name, path, err);
 			goto err_out;
 		}
 
-		free(offsets);
-		free(ref_ctr_offsets);
-		free(cookies);
+		link->uprobes[i].link = uprobe_link;
+		link->uprobes[i].abs_ip = target->abs_ip;
+		link->uprobe_cnt++;
 	}
 
 	free(targets);
 	hashmap__free(specs_hash);
-	elf_close(&elf_fd);
+	elf_end(elf);
+	close(fd);
+
 	return &link->link;
 
 err_out:
-	free(offsets);
-	free(ref_ctr_offsets);
-	free(cookies);
-
 	if (link)
 		bpf_link__destroy(&link->link);
 	free(targets);
 	hashmap__free(specs_hash);
-	elf_close(&elf_fd);
+	if (elf)
+		elf_end(elf);
+	close(fd);
 	return libbpf_err_ptr(err);
 }