summaryrefslogtreecommitdiff
path: root/tools/lib/bpf
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-22 05:24:12 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-22 05:24:12 +0300
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /tools/lib/bpf
parent36289a03bcd3aabdf66de75cb6d1b4ee15726438 (diff)
parentd1fabc68f8e0541d41657096dc713cb01775652d (diff)
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.xz
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r--tools/lib/bpf/bpf.c20
-rw-r--r--tools/lib/bpf/bpf.h9
-rw-r--r--tools/lib/bpf/bpf_core_read.h4
-rw-r--r--tools/lib/bpf/bpf_helpers.h2
-rw-r--r--tools/lib/bpf/bpf_tracing.h320
-rw-r--r--tools/lib/bpf/btf.c24
-rw-r--r--tools/lib/bpf/btf_dump.c199
-rw-r--r--tools/lib/bpf/libbpf.c72
-rw-r--r--tools/lib/bpf/libbpf.h126
-rw-r--r--tools/lib/bpf/libbpf.map8
-rw-r--r--tools/lib/bpf/libbpf_errno.c16
-rw-r--r--tools/lib/bpf/libbpf_internal.h5
-rw-r--r--tools/lib/bpf/libbpf_probes.c83
-rw-r--r--tools/lib/bpf/libbpf_version.h2
-rw-r--r--tools/lib/bpf/netlink.c120
-rw-r--r--tools/lib/bpf/nlattr.c2
-rw-r--r--tools/lib/bpf/nlattr.h12
-rw-r--r--tools/lib/bpf/ringbuf.c4
-rw-r--r--tools/lib/bpf/usdt.bpf.h5
19 files changed, 856 insertions, 177 deletions
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9aff98f42a3d..e750b6f5fcc3 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1044,6 +1044,26 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
return libbpf_err_errno(err);
}
+int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len)
+{
+ return bpf_obj_get_info_by_fd(prog_fd, info, info_len);
+}
+
+int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len)
+{
+ return bpf_obj_get_info_by_fd(map_fd, info, info_len);
+}
+
+int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len)
+{
+ return bpf_obj_get_info_by_fd(btf_fd, info, info_len);
+}
+
+int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len)
+{
+ return bpf_obj_get_info_by_fd(link_fd, info, info_len);
+}
+
int bpf_raw_tracepoint_open(const char *name, int prog_fd)
{
const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 7468978d3c27..9ed9bceb4111 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -386,6 +386,15 @@ LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id,
const struct bpf_get_fd_by_id_opts *opts);
LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
+/* Type-safe variants of bpf_obj_get_info_by_fd(). The callers still needs to
+ * pass info_len, which should normally be
+ * sizeof(struct bpf_{prog,map,btf,link}_info), in order to be compatible with
+ * different libbpf and kernel versions.
+ */
+LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len);
+LIBBPF_API int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len);
+LIBBPF_API int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len);
+LIBBPF_API int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len);
struct bpf_prog_query_opts {
size_t sz; /* size of this struct for forward/backward compatibility */
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 496e6a8ee0dc..1ac57bb7ac55 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -364,7 +364,7 @@ enum bpf_enum_value_kind {
/* Non-CO-RE variant of BPF_CORE_READ_INTO() */
#define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \
- ___core_read(bpf_probe_read, bpf_probe_read, \
+ ___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel, \
dst, (src), a, ##__VA_ARGS__) \
})
@@ -400,7 +400,7 @@ enum bpf_enum_value_kind {
/* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */
#define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \
- ___core_read(bpf_probe_read_str, bpf_probe_read, \
+ ___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel, \
dst, (src), a, ##__VA_ARGS__) \
})
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index d37c4fe2849d..5ec1871acb2f 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -109,7 +109,7 @@
* This is a variable-specific variant of more global barrier().
*/
#ifndef barrier_var
-#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var))
+#define barrier_var(var) asm volatile("" : "+r"(var))
#endif
/*
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 2972dc25ff72..6db88f41fa0d 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -32,6 +32,9 @@
#elif defined(__TARGET_ARCH_arc)
#define bpf_target_arc
#define bpf_target_defined
+#elif defined(__TARGET_ARCH_loongarch)
+ #define bpf_target_loongarch
+ #define bpf_target_defined
#else
/* Fall back to what the compiler says */
@@ -62,6 +65,9 @@
#elif defined(__arc__)
#define bpf_target_arc
#define bpf_target_defined
+#elif defined(__loongarch__)
+ #define bpf_target_loongarch
+ #define bpf_target_defined
#endif /* no compiler target */
#endif
@@ -72,6 +78,10 @@
#if defined(bpf_target_x86)
+/*
+ * https://en.wikipedia.org/wiki/X86_calling_conventions#System_V_AMD64_ABI
+ */
+
#if defined(__KERNEL__) || defined(__VMLINUX_H__)
#define __PT_PARM1_REG di
@@ -79,25 +89,40 @@
#define __PT_PARM3_REG dx
#define __PT_PARM4_REG cx
#define __PT_PARM5_REG r8
+#define __PT_PARM6_REG r9
+/*
+ * Syscall uses r10 for PARM4. See arch/x86/entry/entry_64.S:entry_SYSCALL_64
+ * comments in Linux sources. And refer to syscall(2) manpage.
+ */
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG r10
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
#define __PT_RET_REG sp
#define __PT_FP_REG bp
#define __PT_RC_REG ax
#define __PT_SP_REG sp
#define __PT_IP_REG ip
-/* syscall uses r10 for PARM4 */
-#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
-#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
#else
#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
#define __PT_PARM1_REG eax
#define __PT_PARM2_REG edx
#define __PT_PARM3_REG ecx
-/* i386 kernel is built with -mregparm=3 */
-#define __PT_PARM4_REG __unsupported__
-#define __PT_PARM5_REG __unsupported__
+/* i386 syscall ABI is very different, refer to syscall(2) manpage */
+#define __PT_PARM1_SYSCALL_REG ebx
+#define __PT_PARM2_SYSCALL_REG ecx
+#define __PT_PARM3_SYSCALL_REG edx
+#define __PT_PARM4_SYSCALL_REG esi
+#define __PT_PARM5_SYSCALL_REG edi
+#define __PT_PARM6_SYSCALL_REG ebp
+
#define __PT_RET_REG esp
#define __PT_FP_REG ebp
#define __PT_RC_REG eax
@@ -111,14 +136,20 @@
#define __PT_PARM3_REG rdx
#define __PT_PARM4_REG rcx
#define __PT_PARM5_REG r8
+#define __PT_PARM6_REG r9
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG r10
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
#define __PT_RET_REG rsp
#define __PT_FP_REG rbp
#define __PT_RC_REG rax
#define __PT_SP_REG rsp
#define __PT_IP_REG rip
-/* syscall uses r10 for PARM4 */
-#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10)
-#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10)
#endif /* __i386__ */
@@ -126,6 +157,10 @@
#elif defined(bpf_target_s390)
+/*
+ * https://github.com/IBM/s390x-abi/releases/download/v1.6/lzsabi_s390x.pdf
+ */
+
struct pt_regs___s390 {
unsigned long orig_gpr2;
};
@@ -137,21 +172,41 @@ struct pt_regs___s390 {
#define __PT_PARM3_REG gprs[4]
#define __PT_PARM4_REG gprs[5]
#define __PT_PARM5_REG gprs[6]
-#define __PT_RET_REG grps[14]
+
+#define __PT_PARM1_SYSCALL_REG orig_gpr2
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG gprs[7]
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+ BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG)
+
+#define __PT_RET_REG gprs[14]
#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */
#define __PT_RC_REG gprs[2]
#define __PT_SP_REG gprs[15]
#define __PT_IP_REG psw.addr
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
-#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
#elif defined(bpf_target_arm)
+/*
+ * https://github.com/ARM-software/abi-aa/blob/main/aapcs32/aapcs32.rst#machine-registers
+ */
+
#define __PT_PARM1_REG uregs[0]
#define __PT_PARM2_REG uregs[1]
#define __PT_PARM3_REG uregs[2]
#define __PT_PARM4_REG uregs[3]
-#define __PT_PARM5_REG uregs[4]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM6_SYSCALL_REG uregs[5]
+#define __PT_PARM7_SYSCALL_REG uregs[6]
+
#define __PT_RET_REG uregs[14]
#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */
#define __PT_RC_REG uregs[0]
@@ -160,6 +215,10 @@ struct pt_regs___s390 {
#elif defined(bpf_target_arm64)
+/*
+ * https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#machine-registers
+ */
+
struct pt_regs___arm64 {
unsigned long orig_x0;
};
@@ -171,21 +230,49 @@ struct pt_regs___arm64 {
#define __PT_PARM3_REG regs[2]
#define __PT_PARM4_REG regs[3]
#define __PT_PARM5_REG regs[4]
+#define __PT_PARM6_REG regs[5]
+#define __PT_PARM7_REG regs[6]
+#define __PT_PARM8_REG regs[7]
+
+#define __PT_PARM1_SYSCALL_REG orig_x0
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+ BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG)
+
#define __PT_RET_REG regs[30]
#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */
#define __PT_RC_REG regs[0]
#define __PT_SP_REG sp
#define __PT_IP_REG pc
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
-#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
#elif defined(bpf_target_mips)
+/*
+ * N64 ABI is assumed right now.
+ * https://en.wikipedia.org/wiki/MIPS_architecture#Calling_conventions
+ */
+
#define __PT_PARM1_REG regs[4]
#define __PT_PARM2_REG regs[5]
#define __PT_PARM3_REG regs[6]
#define __PT_PARM4_REG regs[7]
#define __PT_PARM5_REG regs[8]
+#define __PT_PARM6_REG regs[9]
+#define __PT_PARM7_REG regs[10]
+#define __PT_PARM8_REG regs[11]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG /* only N32/N64 */
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG /* only N32/N64 */
+
#define __PT_RET_REG regs[31]
#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */
#define __PT_RC_REG regs[2]
@@ -194,26 +281,58 @@ struct pt_regs___arm64 {
#elif defined(bpf_target_powerpc)
+/*
+ * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf (page 3-14,
+ * section "Function Calling Sequence")
+ */
+
#define __PT_PARM1_REG gpr[3]
#define __PT_PARM2_REG gpr[4]
#define __PT_PARM3_REG gpr[5]
#define __PT_PARM4_REG gpr[6]
#define __PT_PARM5_REG gpr[7]
+#define __PT_PARM6_REG gpr[8]
+#define __PT_PARM7_REG gpr[9]
+#define __PT_PARM8_REG gpr[10]
+
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
+#define __PT_PARM1_SYSCALL_REG orig_gpr3
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#if !defined(__arch64__)
+#define __PT_PARM7_SYSCALL_REG __PT_PARM7_REG /* only powerpc (not powerpc64) */
+#endif
+
#define __PT_RET_REG regs[31]
#define __PT_FP_REG __unsupported__
#define __PT_RC_REG gpr[3]
#define __PT_SP_REG sp
#define __PT_IP_REG nip
-/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
#elif defined(bpf_target_sparc)
+/*
+ * https://en.wikipedia.org/wiki/Calling_convention#SPARC
+ */
+
#define __PT_PARM1_REG u_regs[UREG_I0]
#define __PT_PARM2_REG u_regs[UREG_I1]
#define __PT_PARM3_REG u_regs[UREG_I2]
#define __PT_PARM4_REG u_regs[UREG_I3]
#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_PARM6_REG u_regs[UREG_I5]
+
+#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
+#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
#define __PT_RET_REG u_regs[UREG_I7]
#define __PT_FP_REG __unsupported__
#define __PT_RC_REG u_regs[UREG_I0]
@@ -227,22 +346,42 @@ struct pt_regs___arm64 {
#elif defined(bpf_target_riscv)
+/*
+ * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
+ */
+
#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
#define __PT_PARM1_REG a0
#define __PT_PARM2_REG a1
#define __PT_PARM3_REG a2
#define __PT_PARM4_REG a3
#define __PT_PARM5_REG a4
+#define __PT_PARM6_REG a5
+#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
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
#define __PT_RET_REG ra
#define __PT_FP_REG s0
#define __PT_RC_REG a0
#define __PT_SP_REG sp
#define __PT_IP_REG pc
-/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
#elif defined(bpf_target_arc)
+/*
+ * Section "Function Calling Sequence" (page 24):
+ * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf
+ */
+
/* 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
@@ -250,13 +389,55 @@ struct pt_regs___arm64 {
#define __PT_PARM3_REG scratch.r2
#define __PT_PARM4_REG scratch.r3
#define __PT_PARM5_REG scratch.r4
+#define __PT_PARM6_REG scratch.r5
+#define __PT_PARM7_REG scratch.r6
+#define __PT_PARM8_REG scratch.r7
+
+/* arc 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
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
#define __PT_RET_REG scratch.blink
-#define __PT_FP_REG __unsupported__
+#define __PT_FP_REG scratch.fp
#define __PT_RC_REG scratch.r0
#define __PT_SP_REG scratch.sp
#define __PT_IP_REG scratch.ret
-/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+
+#elif defined(bpf_target_loongarch)
+
+/*
+ * https://docs.kernel.org/loongarch/introduction.html
+ * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html
+ */
+
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_PARM6_REG regs[9]
+#define __PT_PARM7_REG regs[10]
+#define __PT_PARM8_REG regs[11]
+
+/* loongarch 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
+#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
+#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
+#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+
+#define __PT_RET_REG regs[1]
+#define __PT_FP_REG regs[22]
+#define __PT_RC_REG regs[4]
+#define __PT_SP_REG regs[3]
+#define __PT_IP_REG csr_era
#endif
@@ -264,16 +445,49 @@ struct pt_regs___arm64 {
struct pt_regs;
-/* allow some architecutres to override `struct pt_regs` */
+/* allow some architectures to override `struct pt_regs` */
#ifndef __PT_REGS_CAST
#define __PT_REGS_CAST(x) (x)
#endif
+/*
+ * Different architectures support different number of arguments passed
+ * through registers. i386 supports just 3, some arches support up to 8.
+ */
+#ifndef __PT_PARM4_REG
+#define __PT_PARM4_REG __unsupported__
+#endif
+#ifndef __PT_PARM5_REG
+#define __PT_PARM5_REG __unsupported__
+#endif
+#ifndef __PT_PARM6_REG
+#define __PT_PARM6_REG __unsupported__
+#endif
+#ifndef __PT_PARM7_REG
+#define __PT_PARM7_REG __unsupported__
+#endif
+#ifndef __PT_PARM8_REG
+#define __PT_PARM8_REG __unsupported__
+#endif
+/*
+ * Similarly, syscall-specific conventions might differ between function call
+ * conventions within each architecutre. All supported architectures pass
+ * either 6 or 7 syscall arguments in registers.
+ *
+ * See syscall(2) manpage for succinct table with information on each arch.
+ */
+#ifndef __PT_PARM7_SYSCALL_REG
+#define __PT_PARM7_SYSCALL_REG __unsupported__
+#endif
+
#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_PARM6(x) (__PT_REGS_CAST(x)->__PT_PARM6_REG)
+#define PT_REGS_PARM7(x) (__PT_REGS_CAST(x)->__PT_PARM7_REG)
+#define PT_REGS_PARM8(x) (__PT_REGS_CAST(x)->__PT_PARM8_REG)
#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
@@ -285,6 +499,9 @@ struct pt_regs;
#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_PARM6_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_REG)
+#define PT_REGS_PARM7_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_REG)
+#define PT_REGS_PARM8_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM8_REG)
#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
@@ -311,24 +528,33 @@ struct pt_regs;
#endif
#ifndef PT_REGS_PARM1_SYSCALL
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x)
+#define PT_REGS_PARM1_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM1_SYSCALL_REG)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM2_SYSCALL
+#define PT_REGS_PARM2_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM2_SYSCALL_REG)
+#define PT_REGS_PARM2_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM3_SYSCALL
+#define PT_REGS_PARM3_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM3_SYSCALL_REG)
+#define PT_REGS_PARM3_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_SYSCALL_REG)
#endif
-#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x)
-#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x)
#ifndef PT_REGS_PARM4_SYSCALL
-#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x)
+#define PT_REGS_PARM4_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM4_SYSCALL_REG)
+#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_SYSCALL_REG)
#endif
-#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x)
-
-#ifndef PT_REGS_PARM1_CORE_SYSCALL
-#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x)
+#ifndef PT_REGS_PARM5_SYSCALL
+#define PT_REGS_PARM5_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM5_SYSCALL_REG)
+#define PT_REGS_PARM5_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_SYSCALL_REG)
#endif
-#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x)
-#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x)
-#ifndef PT_REGS_PARM4_CORE_SYSCALL
-#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x)
+#ifndef PT_REGS_PARM6_SYSCALL
+#define PT_REGS_PARM6_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM6_SYSCALL_REG)
+#define PT_REGS_PARM6_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_SYSCALL_REG)
+#endif
+#ifndef PT_REGS_PARM7_SYSCALL
+#define PT_REGS_PARM7_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM7_SYSCALL_REG)
+#define PT_REGS_PARM7_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_SYSCALL_REG)
#endif
-#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x)
#else /* defined(bpf_target_defined) */
@@ -337,6 +563,9 @@ struct pt_regs;
#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM8(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -348,6 +577,9 @@ struct pt_regs;
#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM8_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -362,12 +594,16 @@ struct pt_regs;
#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM6_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM7_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#endif /* defined(bpf_target_defined) */
@@ -553,6 +789,9 @@ struct pt_regs;
#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx)
+#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx)
+#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx)
#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
/*
@@ -609,6 +848,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs)
+#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs)
#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */
@@ -618,6 +859,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs)
#define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
/*
@@ -667,4 +910,11 @@ ____##name(struct pt_regs *ctx, ##args)
#define BPF_KPROBE_SYSCALL BPF_KSYSCALL
+/* BPF_UPROBE and BPF_URETPROBE are identical to BPF_KPROBE and BPF_KRETPROBE,
+ * but are named way less confusingly for SEC("uprobe") and SEC("uretprobe")
+ * use cases.
+ */
+#define BPF_UPROBE(name, args...) BPF_KPROBE(name, ##args)
+#define BPF_URETPROBE(name, args...) BPF_KRETPROBE(name, ##args)
+
#endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 71e165b09ed5..9181d36118d2 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -688,8 +688,21 @@ int btf__align_of(const struct btf *btf, __u32 id)
if (align <= 0)
return libbpf_err(align);
max_align = max(max_align, align);
+
+ /* if field offset isn't aligned according to field
+ * type's alignment, then struct must be packed
+ */
+ if (btf_member_bitfield_size(t, i) == 0 &&
+ (m->offset % (8 * align)) != 0)
+ return 1;
}
+ /* if struct/union size isn't a multiple of its alignment,
+ * then struct must be packed
+ */
+ if ((t->size % max_align) != 0)
+ return 1;
+
return max_align;
}
default:
@@ -990,7 +1003,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
err = 0;
if (!btf_data) {
- err = -ENOENT;
+ pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path);
+ err = -ENODATA;
goto done;
}
btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
@@ -1336,9 +1350,9 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf)
void *ptr;
int err;
- /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+ /* we won't know btf_size until we call bpf_btf_get_info_by_fd(). so
* let's start with a sane default - 4KiB here - and resize it only if
- * bpf_obj_get_info_by_fd() needs a bigger buffer.
+ * bpf_btf_get_info_by_fd() needs a bigger buffer.
*/
last_size = 4096;
ptr = malloc(last_size);
@@ -1348,7 +1362,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf)
memset(&btf_info, 0, sizeof(btf_info));
btf_info.btf = ptr_to_u64(ptr);
btf_info.btf_size = last_size;
- err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+ err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len);
if (!err && btf_info.btf_size > last_size) {
void *temp_ptr;
@@ -1366,7 +1380,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf)
btf_info.btf = ptr_to_u64(ptr);
btf_info.btf_size = last_size;
- err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+ err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len);
}
if (err || btf_info.btf_size > last_size) {
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index deb2bc9a0a7b..580985ee5545 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -13,6 +13,7 @@
#include <ctype.h>
#include <endian.h>
#include <errno.h>
+#include <limits.h>
#include <linux/err.h>
#include <linux/btf.h>
#include <linux/kernel.h>
@@ -833,14 +834,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
const struct btf_type *t)
{
const struct btf_member *m;
- int align, i, bit_sz;
+ int max_align = 1, align, i, bit_sz;
__u16 vlen;
- align = btf__align_of(btf, id);
- /* size of a non-packed struct has to be a multiple of its alignment*/
- if (align && t->size % align)
- return true;
-
m = btf_members(t);
vlen = btf_vlen(t);
/* all non-bitfield fields have to be naturally aligned */
@@ -849,8 +845,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
bit_sz = btf_member_bitfield_size(t, i);
if (align && bit_sz == 0 && m->offset % (8 * align) != 0)
return true;
+ max_align = max(align, max_align);
}
-
+ /* size of a non-packed struct has to be a multiple of its alignment */
+ if (t->size % max_align != 0)
+ return true;
/*
* if original struct was marked as packed, but its layout is
* naturally aligned, we'll detect that it's not packed
@@ -858,44 +857,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
return false;
}
-static int chip_away_bits(int total, int at_most)
-{
- return total % at_most ? : at_most;
-}
-
static void btf_dump_emit_bit_padding(const struct btf_dump *d,
- int cur_off, int m_off, int m_bit_sz,
- int align, int lvl)
+ int cur_off, int next_off, int next_align,
+ bool in_bitfield, int lvl)
{
- int off_diff = m_off - cur_off;
- int ptr_bits = d->ptr_sz * 8;
+ const struct {
+ const char *name;
+ int bits;
+ } pads[] = {
+ {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8}
+ };
+ int new_off, pad_bits, bits, i;
+ const char *pad_type;
+
+ if (cur_off >= next_off)
+ return; /* no gap */
+
+ /* For filling out padding we want to take advantage of
+ * natural alignment rules to minimize unnecessary explicit
+ * padding. First, we find the largest type (among long, int,
+ * short, or char) that can be used to force naturally aligned
+ * boundary. Once determined, we'll use such type to fill in
+ * the remaining padding gap. In some cases we can rely on
+ * compiler filling some gaps, but sometimes we need to force
+ * alignment to close natural alignment with markers like
+ * `long: 0` (this is always the case for bitfields). Note
+ * that even if struct itself has, let's say 4-byte alignment
+ * (i.e., it only uses up to int-aligned types), using `long:
+ * X;` explicit padding doesn't actually change struct's
+ * overall alignment requirements, but compiler does take into
+ * account that type's (long, in this example) natural
+ * alignment requirements when adding implicit padding. We use
+ * this fact heavily and don't worry about ruining correct
+ * struct alignment requirement.
+ */
+ for (i = 0; i < ARRAY_SIZE(pads); i++) {
+ pad_bits = pads[i].bits;
+ pad_type = pads[i].name;
- if (off_diff <= 0)
- /* no gap */
- return;
- if (m_bit_sz == 0 && off_diff < align * 8)
- /* natural padding will take care of a gap */
- return;
+ new_off = roundup(cur_off, pad_bits);
+ if (new_off <= next_off)
+ break;
+ }
- while (off_diff > 0) {
- const char *pad_type;
- int pad_bits;
-
- if (ptr_bits > 32 && off_diff > 32) {
- pad_type = "long";
- pad_bits = chip_away_bits(off_diff, ptr_bits);
- } else if (off_diff > 16) {
- pad_type = "int";
- pad_bits = chip_away_bits(off_diff, 32);
- } else if (off_diff > 8) {
- pad_type = "short";
- pad_bits = chip_away_bits(off_diff, 16);
- } else {
- pad_type = "char";
- pad_bits = chip_away_bits(off_diff, 8);
+ if (new_off > cur_off && new_off <= next_off) {
+ /* We need explicit `<type>: 0` aligning mark if next
+ * field is right on alignment offset and its
+ * alignment requirement is less strict than <type>'s
+ * alignment (so compiler won't naturally align to the
+ * offset we expect), or if subsequent `<type>: X`,
+ * will actually completely fit in the remaining hole,
+ * making compiler basically ignore `<type>: X`
+ * completely.
+ */
+ if (in_bitfield ||
+ (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) ||
+ (new_off != next_off && next_off - new_off <= new_off - cur_off))
+ /* but for bitfields we'll emit explicit bit count */
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type,
+ in_bitfield ? new_off - cur_off : 0);
+ cur_off = new_off;
+ }
+
+ /* Now we know we start at naturally aligned offset for a chosen
+ * padding type (long, int, short, or char), and so the rest is just
+ * a straightforward filling of remaining padding gap with full
+ * `<type>: sizeof(<type>);` markers, except for the last one, which
+ * might need smaller than sizeof(<type>) padding.
+ */
+ while (cur_off != next_off) {
+ bits = min(next_off - cur_off, pad_bits);
+ if (bits == pad_bits) {
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+ cur_off += bits;
+ continue;
+ }
+ /* For the remainder padding that doesn't cover entire
+ * pad_type bit length, we pick the smallest necessary type.
+ * This is pure aesthetics, we could have just used `long`,
+ * but having smallest necessary one communicates better the
+ * scale of the padding gap.
+ */
+ for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) {
+ pad_type = pads[i].name;
+ pad_bits = pads[i].bits;
+ if (pad_bits < bits)
+ continue;
+
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits);
+ cur_off += bits;
+ break;
}
- btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
- off_diff -= pad_bits;
}
}
@@ -915,9 +967,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
{
const struct btf_member *m = btf_members(t);
bool is_struct = btf_is_struct(t);
- int align, i, packed, off = 0;
+ bool packed, prev_bitfield = false;
+ int align, i, off = 0;
__u16 vlen = btf_vlen(t);
+ align = btf__align_of(d->btf, id);
packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
btf_dump_printf(d, "%s%s%s {",
@@ -927,41 +981,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
for (i = 0; i < vlen; i++, m++) {
const char *fname;
- int m_off, m_sz;
+ int m_off, m_sz, m_align;
+ bool in_bitfield;
fname = btf_name_of(d, m->name_off);
m_sz = btf_member_bitfield_size(t, i);
m_off = btf_member_bit_offset(t, i);
- align = packed ? 1 : btf__align_of(d->btf, m->type);
+ m_align = packed ? 1 : btf__align_of(d->btf, m->type);
+
+ in_bitfield = prev_bitfield && m_sz != 0;
- btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+ btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1);
btf_dump_printf(d, "\n%s", pfx(lvl + 1));
btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
if (m_sz) {
btf_dump_printf(d, ": %d", m_sz);
off = m_off + m_sz;
+ prev_bitfield = true;
} else {
m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
off = m_off + m_sz * 8;
+ prev_bitfield = false;
}
+
btf_dump_printf(d, ";");
}
/* pad at the end, if necessary */
- if (is_struct) {
- align = packed ? 1 : btf__align_of(d->btf, id);
- btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align,
- lvl + 1);
- }
+ if (is_struct)
+ btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1);
/*
* Keep `struct empty {}` on a single line,
* only print newline when there are regular or padding fields.
*/
- if (vlen || t->size)
+ if (vlen || t->size) {
btf_dump_printf(d, "\n");
- btf_dump_printf(d, "%s}", pfx(lvl));
+ btf_dump_printf(d, "%s}", pfx(lvl));
+ } else {
+ btf_dump_printf(d, "}");
+ }
if (packed)
btf_dump_printf(d, " __attribute__((packed))");
}
@@ -1073,6 +1133,43 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
else
btf_dump_emit_enum64_val(d, t, lvl, vlen);
btf_dump_printf(d, "\n%s}", pfx(lvl));
+
+ /* special case enums with special sizes */
+ if (t->size == 1) {
+ /* one-byte enums can be forced with mode(byte) attribute */
+ btf_dump_printf(d, " __attribute__((mode(byte)))");
+ } else if (t->size == 8 && d->ptr_sz == 8) {
+ /* enum can be 8-byte sized if one of the enumerator values
+ * doesn't fit in 32-bit integer, or by adding mode(word)
+ * attribute (but probably only on 64-bit architectures); do
+ * our best here to try to satisfy the contract without adding
+ * unnecessary attributes
+ */
+ bool needs_word_mode;
+
+ if (btf_is_enum(t)) {
+ /* enum can't represent 64-bit values, so we need word mode */
+ needs_word_mode = true;
+ } else {
+ /* enum64 needs mode(word) if none of its values has
+ * non-zero upper 32-bits (which means that all values
+ * fit in 32-bit integers and won't cause compiler to
+ * bump enum to be 64-bit naturally
+ */
+ int i;
+
+ needs_word_mode = true;
+ for (i = 0; i < vlen; i++) {
+ if (btf_enum64(t)[i].val_hi32 != 0) {
+ needs_word_mode = false;
+ break;
+ }
+ }
+ }
+ if (needs_word_mode)
+ btf_dump_printf(d, " __attribute__((mode(word)))");
+ }
+
}
static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2a82f49ce16f..05c4db355f28 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -34,7 +34,6 @@
#include <linux/limits.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
-#include <linux/version.h>
#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
@@ -870,42 +869,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
return 0;
}
-__u32 get_kernel_version(void)
-{
- /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release,
- * but Ubuntu provides /proc/version_signature file, as described at
- * https://ubuntu.com/kernel, with an example contents below, which we
- * can use to get a proper LINUX_VERSION_CODE.
- *
- * Ubuntu 5.4.0-12.15-generic 5.4.8
- *
- * In the above, 5.4.8 is what kernel is actually expecting, while
- * uname() call will return 5.4.0 in info.release.
- */
- const char *ubuntu_kver_file = "/proc/version_signature";
- __u32 major, minor, patch;
- struct utsname info;
-
- if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) {
- FILE *f;
-
- f = fopen(ubuntu_kver_file, "r");
- if (f) {
- if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) {
- fclose(f);
- return KERNEL_VERSION(major, minor, patch);
- }
- fclose(f);
- }
- /* something went wrong, fall back to uname() approach */
- }
-
- uname(&info);
- if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
- return 0;
- return KERNEL_VERSION(major, minor, patch);
-}
-
static const struct btf_member *
find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
{
@@ -4382,7 +4345,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
char *new_name;
memset(&info, 0, len);
- err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ err = bpf_map_get_info_by_fd(fd, &info, &len);
if (err && errno == EINVAL)
err = bpf_get_map_info_from_fdinfo(fd, &info);
if (err)
@@ -4766,7 +4729,7 @@ static int probe_module_btf(void)
* kernel's module BTF support coincides with support for
* name/name_len fields in struct bpf_btf_info.
*/
- err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ err = bpf_btf_get_info_by_fd(fd, &info, &len);
close(fd);
return !err;
}
@@ -4929,7 +4892,7 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
int err;
memset(&map_info, 0, map_info_len);
- err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+ err = bpf_map_get_info_by_fd(map_fd, &map_info, &map_info_len);
if (err && errno == EINVAL)
err = bpf_get_map_info_from_fdinfo(map_fd, &map_info);
if (err) {
@@ -5474,7 +5437,7 @@ static int load_module_btfs(struct bpf_object *obj)
info.name = ptr_to_u64(name);
info.name_len = sizeof(name);
- err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ err = bpf_btf_get_info_by_fd(fd, &info, &len);
if (err) {
err = -errno;
pr_warn("failed to get BTF object #%d info: %d\n", id, err);
@@ -7355,7 +7318,7 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
if (!bpf_map__is_internal(m))
continue;
if (!kernel_supports(obj, FEAT_ARRAY_MMAP))
- m->def.map_flags ^= BPF_F_MMAPABLE;
+ m->def.map_flags &= ~BPF_F_MMAPABLE;
}
return 0;
@@ -8605,6 +8568,7 @@ static const struct bpf_sec_def section_defs[] = {
SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT),
SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE),
+ SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE),
SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
};
@@ -9066,9 +9030,9 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
int err;
memset(&info, 0, info_len);
- err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
+ err = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len);
if (err) {
- pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n",
+ pr_warn("failed bpf_prog_get_info_by_fd for FD %d: %d\n",
attach_prog_fd, err);
return err;
}
@@ -9903,7 +9867,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
char errmsg[STRERR_BUFSIZE];
int type, pfd;
- if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
+ if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
return -EINVAL;
memset(&attr, 0, attr_sz);
@@ -9994,9 +9958,16 @@ static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
const char *kfunc_name, size_t offset)
{
static int index = 0;
+ int i;
snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset,
__sync_fetch_and_add(&index, 1));
+
+ /* sanitize binary_path in the probe name */
+ for (i = 0; buf[i]; i++) {
+ if (!isalnum(buf[i]))
+ buf[i] = '_';
+ }
}
static int add_kprobe_event_legacy(const char *probe_name, bool retprobe,
@@ -11702,17 +11673,22 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
const size_t attr_sz = sizeof(struct perf_event_attr);
struct perf_buffer_params p = {};
struct perf_event_attr attr;
+ __u32 sample_period;
if (!OPTS_VALID(opts, perf_buffer_opts))
return libbpf_err_ptr(-EINVAL);
+ sample_period = OPTS_GET(opts, sample_period, 1);
+ if (!sample_period)
+ sample_period = 1;
+
memset(&attr, 0, attr_sz);
attr.size = attr_sz;
attr.config = PERF_COUNT_SW_BPF_OUTPUT;
attr.type = PERF_TYPE_SOFTWARE;
attr.sample_type = PERF_SAMPLE_RAW;
- attr.sample_period = 1;
- attr.wakeup_events = 1;
+ attr.sample_period = sample_period;
+ attr.wakeup_events = sample_period;
p.attr = &attr;
p.sample_cb = sample_cb;
@@ -11765,7 +11741,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
/* best-effort sanity checks */
memset(&map, 0, sizeof(map));
map_info_len = sizeof(map);
- err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len);
+ err = bpf_map_get_info_by_fd(map_fd, &map, &map_info_len);
if (err) {
err = -errno;
/* if BPF_OBJ_GET_INFO_BY_FD is supported, will return
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index eee883f007f9..2efd80f6f7b9 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -96,6 +96,12 @@ enum libbpf_print_level {
typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
const char *, va_list ap);
+/**
+ * @brief **libbpf_set_print()** sets user-provided log callback function to
+ * be used for libbpf warnings and informational messages.
+ * @param fn The log print function. If NULL, libbpf won't print anything.
+ * @return Pointer to old print function.
+ */
LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn);
/* Hide internal to user */
@@ -174,6 +180,14 @@ struct bpf_object_open_opts {
};
#define bpf_object_open_opts__last_field kernel_log_level
+/**
+ * @brief **bpf_object__open()** creates a bpf_object by opening
+ * the BPF ELF object file pointed to by the passed path and loading it
+ * into memory.
+ * @param path BPF object file path.
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
/**
@@ -203,16 +217,46 @@ LIBBPF_API struct bpf_object *
bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
const struct bpf_object_open_opts *opts);
-/* Load/unload object into/from kernel */
+/**
+ * @brief **bpf_object__load()** loads BPF object into kernel.
+ * @param obj Pointer to a valid BPF object instance returned by
+ * **bpf_object__open*()** APIs
+ * @return 0, on success; negative error code, otherwise, error code is
+ * stored in errno
+ */
LIBBPF_API int bpf_object__load(struct bpf_object *obj);
-LIBBPF_API void bpf_object__close(struct bpf_object *object);
+/**
+ * @brief **bpf_object__close()** closes a BPF object and releases all
+ * resources.
+ * @param obj Pointer to a valid BPF object
+ */
+LIBBPF_API void bpf_object__close(struct bpf_object *obj);
-/* pin_maps and unpin_maps can both be called with a NULL path, in which case
- * they will use the pin_path attribute of each map (and ignore all maps that
- * don't have a pin_path set).
+/**
+ * @brief **bpf_object__pin_maps()** pins each map contained within
+ * the BPF object at the passed directory.
+ * @param obj Pointer to a valid BPF object
+ * @param path A directory where maps should be pinned.
+ * @return 0, on success; negative error code, otherwise
+ *
+ * If `path` is NULL `bpf_map__pin` (which is being used on each map)
+ * will use the pin_path attribute of each map. In this case, maps that
+ * don't have a pin_path set will be ignored.
*/
LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+
+/**
+ * @brief **bpf_object__unpin_maps()** unpins each map contained within
+ * the BPF object found in the passed directory.
+ * @param obj Pointer to a valid BPF object
+ * @param path A directory where pinned maps should be searched for.
+ * @return 0, on success; negative error code, otherwise
+ *
+ * If `path` is NULL `bpf_map__unpin` (which is being used on each map)
+ * will use the pin_path attribute of each map. In this case, maps that
+ * don't have a pin_path set will be ignored.
+ */
LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
const char *path);
LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
@@ -823,10 +867,57 @@ LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize
* @return true, if the map is an internal map; false, otherwise
*/
LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__set_pin_path()** sets the path attribute that tells where the
+ * BPF map should be pinned. This does not actually create the 'pin'.
+ * @param map The bpf_map
+ * @param path The path
+ * @return 0, on success; negative error, otherwise
+ */
LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
+
+/**
+ * @brief **bpf_map__pin_path()** gets the path attribute that tells where the
+ * BPF map should be pinned.
+ * @param map The bpf_map
+ * @return The path string; which can be NULL
+ */
LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__is_pinned()** tells the caller whether or not the
+ * passed map has been pinned via a 'pin' file.
+ * @param map The bpf_map
+ * @return true, if the map is pinned; false, otherwise
+ */
LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__pin()** creates a file that serves as a 'pin'
+ * for the BPF map. This increments the reference count on the
+ * BPF map which will keep the BPF map loaded even after the
+ * userspace process which loaded it has exited.
+ * @param map The bpf_map to pin
+ * @param path A file path for the 'pin'
+ * @return 0, on success; negative error, otherwise
+ *
+ * If `path` is NULL the maps `pin_path` attribute will be used. If this is
+ * also NULL, an error will be returned and the map will not be pinned.
+ */
LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+
+/**
+ * @brief **bpf_map__unpin()** removes the file that serves as a
+ * 'pin' for the BPF map.
+ * @param map The bpf_map to unpin
+ * @param path A file path for the 'pin'
+ * @return 0, on success; negative error, otherwise
+ *
+ * The `path` parameter can be NULL, in which case the `pin_path`
+ * map attribute is unpinned. If both the `path` parameter and
+ * `pin_path` map attribute are set, they must be equal.
+ */
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
@@ -957,9 +1048,10 @@ struct bpf_xdp_query_opts {
__u32 hw_prog_id; /* output */
__u32 skb_prog_id; /* output */
__u8 attach_mode; /* output */
+ __u64 feature_flags; /* output */
size_t :0;
};
-#define bpf_xdp_query_opts__last_field attach_mode
+#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);
@@ -1039,7 +1131,8 @@ struct user_ring_buffer_opts {
#define user_ring_buffer_opts__last_field sz
-/* @brief **user_ring_buffer__new()** creates a new instance of a user ring
+/**
+ * @brief **user_ring_buffer__new()** creates a new instance of a user ring
* buffer.
*
* @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map.
@@ -1050,7 +1143,8 @@ struct user_ring_buffer_opts {
LIBBPF_API struct user_ring_buffer *
user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
-/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
+/**
+ * @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
* user ring buffer.
* @param rb A pointer to a user ring buffer.
* @param size The size of the sample, in bytes.
@@ -1070,7 +1164,8 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
*/
LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size);
-/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
+/**
+ * @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
* ring buffer, possibly blocking for up to @timeout_ms until a sample becomes
* available.
* @param rb The user ring buffer.
@@ -1114,7 +1209,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
__u32 size,
int timeout_ms);
-/* @brief **user_ring_buffer__submit()** submits a previously reserved sample
+/**
+ * @brief **user_ring_buffer__submit()** submits a previously reserved sample
* into the ring buffer.
* @param rb The user ring buffer.
* @param sample A reserved sample.
@@ -1124,7 +1220,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
*/
LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample);
-/* @brief **user_ring_buffer__discard()** discards a previously reserved sample.
+/**
+ * @brief **user_ring_buffer__discard()** discards a previously reserved sample.
* @param rb The user ring buffer.
* @param sample A reserved sample.
*
@@ -1133,7 +1230,8 @@ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *samp
*/
LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample);
-/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously
+/**
+ * @brief **user_ring_buffer__free()** frees a ring buffer that was previously
* created with **user_ring_buffer__new()**.
* @param rb The user ring buffer being freed.
*/
@@ -1149,8 +1247,10 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt);
/* common use perf buffer options */
struct perf_buffer_opts {
size_t sz;
+ __u32 sample_period;
+ size_t :0;
};
-#define perf_buffer_opts__last_field sz
+#define perf_buffer_opts__last_field sample_period
/**
* @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 71bf5691a689..50dde1f6521e 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -382,3 +382,11 @@ LIBBPF_1.1.0 {
user_ring_buffer__reserve_blocking;
user_ring_buffer__submit;
} LIBBPF_1.0.0;
+
+LIBBPF_1.2.0 {
+ global:
+ bpf_btf_get_info_by_fd;
+ bpf_link_get_info_by_fd;
+ bpf_map_get_info_by_fd;
+ bpf_prog_get_info_by_fd;
+} LIBBPF_1.1.0;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 96f67a772a1b..6b180172ec6b 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -39,14 +39,14 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
int libbpf_strerror(int err, char *buf, size_t size)
{
+ int ret;
+
if (!buf || !size)
return libbpf_err(-EINVAL);
err = err > 0 ? err : -err;
if (err < __LIBBPF_ERRNO__START) {
- int ret;
-
ret = strerror_r(err, buf, size);
buf[size - 1] = '\0';
return libbpf_err_errno(ret);
@@ -56,12 +56,20 @@ int libbpf_strerror(int err, char *buf, size_t size)
const char *msg;
msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
- snprintf(buf, size, "%s", msg);
+ ret = snprintf(buf, size, "%s", msg);
buf[size - 1] = '\0';
+ /* The length of the buf and msg is positive.
+ * A negative number may be returned only when the
+ * size exceeds INT_MAX. Not likely to appear.
+ */
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
return 0;
}
- snprintf(buf, size, "Unknown libbpf error %d", err);
+ ret = snprintf(buf, size, "Unknown libbpf error %d", err);
buf[size - 1] = '\0';
+ if (ret >= size)
+ return libbpf_err(-ERANGE);
return libbpf_err(-ENOENT);
}
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 377642ff51fc..fbaf68335394 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -20,8 +20,8 @@
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-/* prevent accidental re-addition of reallocarray() */
-#pragma GCC poison reallocarray
+/* prevent accidental re-addition of reallocarray()/strlcpy() */
+#pragma GCC poison reallocarray strlcpy
#include "libbpf.h"
#include "btf.h"
@@ -543,6 +543,7 @@ static inline int ensure_good_fd(int fd)
fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
saved_errno = errno;
close(old_fd);
+ errno = saved_errno;
if (fd < 0) {
pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
errno = saved_errno;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index b44fcbb4b42e..4f3bc968ff8e 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -12,11 +12,94 @@
#include <linux/btf.h>
#include <linux/filter.h>
#include <linux/kernel.h>
+#include <linux/version.h>
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_internal.h"
+/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release,
+ * but Ubuntu provides /proc/version_signature file, as described at
+ * https://ubuntu.com/kernel, with an example contents below, which we
+ * can use to get a proper LINUX_VERSION_CODE.
+ *
+ * Ubuntu 5.4.0-12.15-generic 5.4.8
+ *
+ * In the above, 5.4.8 is what kernel is actually expecting, while
+ * uname() call will return 5.4.0 in info.release.
+ */
+static __u32 get_ubuntu_kernel_version(void)
+{
+ const char *ubuntu_kver_file = "/proc/version_signature";
+ __u32 major, minor, patch;
+ int ret;
+ FILE *f;
+
+ if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0)
+ return 0;
+
+ f = fopen(ubuntu_kver_file, "r");
+ if (!f)
+ return 0;
+
+ ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch);
+ fclose(f);
+ if (ret != 3)
+ return 0;
+
+ return KERNEL_VERSION(major, minor, patch);
+}
+
+/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release.
+ * Instead, it is provided in info.version. An example content of
+ * Debian 10 looks like the below.
+ *
+ * utsname::release 4.19.0-22-amd64
+ * utsname::version #1 SMP Debian 4.19.260-1 (2022-09-29)
+ *
+ * In the above, 4.19.260 is what kernel is actually expecting, while
+ * uname() call will return 4.19.0 in info.release.
+ */
+static __u32 get_debian_kernel_version(struct utsname *info)
+{
+ __u32 major, minor, patch;
+ char *p;
+
+ p = strstr(info->version, "Debian ");
+ if (!p) {
+ /* This is not a Debian kernel. */
+ return 0;
+ }
+
+ if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3)
+ return 0;
+
+ return KERNEL_VERSION(major, minor, patch);
+}
+
+__u32 get_kernel_version(void)
+{
+ __u32 major, minor, patch, version;
+ struct utsname info;
+
+ /* Check if this is an Ubuntu kernel. */
+ version = get_ubuntu_kernel_version();
+ if (version != 0)
+ return version;
+
+ uname(&info);
+
+ /* Check if this is a Debian kernel. */
+ version = get_debian_kernel_version(&info);
+ if (version != 0)
+ return version;
+
+ if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
+ return 0;
+
+ return KERNEL_VERSION(major, minor, patch);
+}
+
static int probe_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, size_t insns_cnt,
char *log_buf, size_t log_buf_sz)
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index e944f5bce728..1fd2eeac5cfc 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
#define __LIBBPF_VERSION_H
#define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 1
+#define LIBBPF_MINOR_VERSION 2
#endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 35104580870c..1653e7a8b0a1 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -9,6 +9,7 @@
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
#include <linux/rtnetlink.h>
+#include <linux/netdev.h>
#include <sys/socket.h>
#include <errno.h>
#include <time.h>
@@ -39,9 +40,15 @@ struct xdp_id_md {
int ifindex;
__u32 flags;
struct xdp_link_info info;
+ __u64 feature_flags;
};
-static int libbpf_netlink_open(__u32 *nl_pid)
+struct xdp_features_md {
+ int ifindex;
+ __u64 flags;
+};
+
+static int libbpf_netlink_open(__u32 *nl_pid, int proto)
{
struct sockaddr_nl sa;
socklen_t addrlen;
@@ -51,7 +58,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
- sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
+ sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto);
if (sock < 0)
return -errno;
@@ -212,14 +219,14 @@ done:
}
static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
- __dump_nlmsg_t parse_msg,
+ int proto, __dump_nlmsg_t parse_msg,
libbpf_dump_nlmsg_t parse_attr,
void *cookie)
{
__u32 nl_pid = 0;
int sock, ret;
- sock = libbpf_netlink_open(&nl_pid);
+ sock = libbpf_netlink_open(&nl_pid, proto);
if (sock < 0)
return sock;
@@ -238,6 +245,43 @@ out:
return ret;
}
+static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1];
+ __u16 *id = cookie;
+
+ libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+ if (!tb[CTRL_ATTR_FAMILY_ID])
+ return NL_CONT;
+
+ *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+ return NL_DONE;
+}
+
+static int libbpf_netlink_resolve_genl_family_id(const char *name,
+ __u16 len, __u16 *id)
+{
+ struct libbpf_nla_req req = {
+ .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN),
+ .nh.nlmsg_type = GENL_ID_CTRL,
+ .nh.nlmsg_flags = NLM_F_REQUEST,
+ .gnl.cmd = CTRL_CMD_GETFAMILY,
+ .gnl.version = 2,
+ };
+ int err;
+
+ err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len);
+ if (err < 0)
+ return err;
+
+ return libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_genl_family_id, NULL, id);
+}
+
static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
__u32 flags)
{
@@ -271,7 +315,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
}
nlattr_end_nested(&req, nla);
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
@@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
return 0;
}
+static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[NETDEV_CMD_MAX + 1];
+ struct xdp_features_md *md = cookie;
+ __u32 ifindex;
+
+ libbpf_nla_parse(tb, NETDEV_CMD_MAX, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+
+ if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES])
+ return NL_CONT;
+
+ ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]);
+ if (ifindex != md->ifindex)
+ return NL_CONT;
+
+ md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
+ return NL_DONE;
+}
+
int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
{
struct libbpf_nla_req req = {
@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
.ifinfo.ifi_family = AF_PACKET,
};
struct xdp_id_md xdp_id = {};
+ struct xdp_features_md md = {
+ .ifindex = ifindex,
+ };
+ __u16 id;
int err;
if (!OPTS_VALID(opts, bpf_xdp_query_opts))
@@ -382,7 +453,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
xdp_id.ifindex = ifindex;
xdp_id.flags = xdp_flags;
- err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+ err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg,
get_xdp_info, &xdp_id);
if (err)
return libbpf_err(err);
@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
+ if (!OPTS_HAS(opts, feature_flags))
+ return 0;
+
+ err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+ if (err < 0)
+ return libbpf_err(err);
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = id;
+ req.gnl.cmd = NETDEV_CMD_DEV_GET;
+ req.gnl.version = 2;
+
+ err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+ if (err < 0)
+ return libbpf_err(err);
+
+ err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_xdp_features, NULL, &md);
+ if (err)
+ return libbpf_err(err);
+
+ opts->feature_flags = md.flags;
+
return 0;
}
@@ -493,7 +589,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
if (ret < 0)
return ret;
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
@@ -593,7 +689,7 @@ static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
int len, ret;
memset(&info, 0, info_len);
- ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+ ret = bpf_prog_get_info_by_fd(fd, &info, &info_len);
if (ret < 0)
return ret;
@@ -673,7 +769,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
@@ -739,7 +836,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
return ret;
}
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_tc_detach(const struct bpf_tc_hook *hook,
@@ -804,7 +901,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 3900d052ed19..975e265eab3b 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -178,7 +178,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
hlen += nlmsg_len(&err->msg);
attr = (struct nlattr *) ((void *) err + hlen);
- alen = nlh->nlmsg_len - hlen;
+ alen = (void *)nlh + nlh->nlmsg_len - (void *)attr;
if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
extack_policy) != 0) {
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 4d15ae2ff812..d92d1c1de700 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -14,6 +14,7 @@
#include <errno.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
+#include <linux/genetlink.h>
/* avoid multiple definition of netlink features */
#define __LINUX_NETLINK_H
@@ -58,6 +59,7 @@ struct libbpf_nla_req {
union {
struct ifinfomsg ifinfo;
struct tcmsg tc;
+ struct genlmsghdr gnl;
};
char buf[128];
};
@@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
return *(uint8_t *)libbpf_nla_data(nla);
}
+static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla)
+{
+ return *(uint16_t *)libbpf_nla_data(nla);
+}
+
static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
{
return *(uint32_t *)libbpf_nla_data(nla);
}
+static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla)
+{
+ return *(uint64_t *)libbpf_nla_data(nla);
+}
+
static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
{
return (const char *)libbpf_nla_data(nla);
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 47855af25f3b..02199364db13 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -83,7 +83,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
memset(&info, 0, sizeof(info));
- err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+ err = bpf_map_get_info_by_fd(map_fd, &info, &len);
if (err) {
err = -errno;
pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
@@ -359,7 +359,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
memset(&info, 0, sizeof(info));
- err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+ err = bpf_map_get_info_by_fd(map_fd, &info, &len);
if (err) {
err = -errno;
pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index fdfd235e52c4..0bd4c135acc2 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -130,7 +130,10 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
if (!spec)
return -ESRCH;
- if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt)
+ if (arg_num >= BPF_USDT_MAX_ARG_CNT)
+ return -ENOENT;
+ barrier_var(arg_num);
+ if (arg_num >= spec->arg_cnt)
return -ENOENT;
arg_spec = &spec->args[arg_num];