Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Here is what we have this merge window:

   1) Support SW steering for mlx5 Connect-X6Dx, from Yevgeny Kliteynik.

   2) Add RSS multi group support to octeontx2-pf driver, from Geetha
      Sowjanya.

   3) Add support for KS8851 PHY. From Marek Vasut.

   4) Add support for GarfieldPeak bluetooth controller from Kiran K.

   5) Add support for half-duplex tcan4x5x can controllers.

   6) Add batch skb rx processing to bcrm63xx_enet, from Sieng Piaw
      Liew.

   7) Rework RX port offload infrastructure, particularly wrt, UDP
      tunneling, from Jakub Kicinski.

   8) Add BCM72116 PHY support, from Florian Fainelli.

   9) Remove Dsa specific notifiers, they are unnecessary. From Vladimir
      Oltean.

  10) Add support for picosecond rx delay in dwmac-meson8b chips. From
      Martin Blumenstingl.

  11) Support TSO on xfrm interfaces from Eyal Birger.

  12) Add support for MP_PRIO to mptcp stack, from Geliang Tang.

  13) Support BCM4908 integrated switch, from Rafał Miłecki.

  14) Support for directly accessing kernel module variables via module
      BTF info, from Andrii Naryiko.

  15) Add DASH (esktop and mobile Architecture for System Hardware)
      support to r8169 driver, from Heiner Kallweit.

  16) Add rx vlan filtering to dpaa2-eth, from Ionut-robert Aron.

  17) Add support for 100 base0x SFP devices, from Bjarni Jonasson.

  18) Support link aggregation in DSA, from Tobias Waldekranz.

  19) Support for bitwidse atomics in bpf, from Brendan Jackman.

  20) SmartEEE support in at803x driver, from Russell King.

  21) Add support for flow based tunneling to GTP, from Pravin B Shelar.

  22) Allow arbitrary number of interconnrcts in ipa, from Alex Elder.

  23) TLS RX offload for bonding, from Tariq Toukan.

  24) RX decap offklload support in mac80211, from Felix Fietkou.

  25) devlink health saupport in octeontx2-af, from George Cherian.

  26) Add TTL attr to SCM_TIMESTAMP_OPT_STATS, from Yousuk Seung

  27) Delegated actionss support in mptcp, from Paolo Abeni.

  28) Support receive timestamping when doin zerocopy tcp receive. From
      Arjun Ray.

  29) HTB offload support for mlx5, from Maxim Mikityanskiy.

  30) UDP GRO forwarding, from Maxim Mikityanskiy.

  31) TAPRIO offloading in dsa hellcreek driver, from Kurt Kanzenbach.

  32) Weighted random twos choice algorithm for ipvs, from Darby Payne.

  33) Fix netdev registration deadlock, from Johannes Berg.

  34) Various conversions to new tasklet api, from EmilRenner Berthing.

  35) Bulk skb allocations in veth, from Lorenzo Bianconi.

  36) New ethtool interface for lane setting, from Danielle Ratson.

  37) Offload failiure notifications for routes, from Amit Cohen.

  38) BCM4908 support, from Rafał Miłecki.

  39) Support several new iwlwifi chips, from Ihab Zhaika.

  40) Flow drector support for ipv6 in i40e, from Przemyslaw Patynowski.

  41) Support for mhi prrotocols, from Loic Poulain.

  42) Optimize bpf program stats.

  43) Implement RFC6056, for better port randomization, from Eric
      Dumazet.

  44) hsr tag offloading support from George McCollister.

  45) Netpoll support in qede, from Bhaskar Upadhaya.

  46) 2005/400g speed support in bonding 3ad mode, from Nikolay
      Aleksandrov.

  47) Netlink event support in mptcp, from Florian Westphal.

  48) Better skbuff caching, from Alexander Lobakin.

  49) MRP (Media Redundancy Protocol) offloading in DSA and a few
      drivers, from Horatiu Vultur.

  50) mqprio saupport in mvneta, from Maxime Chevallier.

  51) Remove of_phy_attach, no longer needed, from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1766 commits)
  octeontx2-pf: Fix otx2_get_fecparam()
  cteontx2-pf: cn10k: Prevent harmless double shift bugs
  net: stmmac: Add PCI bus info to ethtool driver query output
  ptp: ptp_clockmatrix: clean-up - parenthesis around a == b are unnecessary
  ptp: ptp_clockmatrix: Simplify code - remove unnecessary `err` variable.
  ptp: ptp_clockmatrix: Coding style - tighten vertical spacing.
  ptp: ptp_clockmatrix: Clean-up dev_*() messages.
  ptp: ptp_clockmatrix: Remove unused header declarations.
  ptp: ptp_clockmatrix: Add alignment of 1 PPS to idtcm_perout_enable.
  ptp: ptp_clockmatrix: Add wait_for_sys_apll_dpll_lock.
  net: stmmac: dwmac-sun8i: Add a shutdown callback
  net: stmmac: dwmac-sun8i: Minor probe function cleanup
  net: stmmac: dwmac-sun8i: Use reset_control_reset
  net: stmmac: dwmac-sun8i: Remove unnecessary PHY power check
  net: stmmac: dwmac-sun8i: Return void from PHY unpower
  r8169: use macro pm_ptr
  net: mdio: Remove of_phy_attach()
  net: mscc: ocelot: select PACKING in the Kconfig
  net: re-solve some conflicts after net -> net-next merge
  net: dsa: tag_rtl4_a: Support also egress tags
  ...

7 files changed, 267 insertions, 119 deletions

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 8a81b3679d2b..5d4cfac671d5 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 libbpf_version.h
 libbpf.pc
-FEATURE-DUMP.libbpf
 libbpf.so.*
 TAGS
 tags
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 55bd78b3496f..887a494ad5fc 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -58,28 +58,7 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf zlib bpf
-FEATURE_DISPLAY = libelf zlib bpf
-
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
-FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
-
-check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help
-ifdef MAKECMDGOALS
-ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
-  check_feat := 0
-endif
-endif
-
-ifeq ($(check_feat),1)
-ifeq ($(FEATURES_DUMP),)
-include $(srctree)/tools/build/Makefile.feature
-else
-include $(FEATURES_DUMP)
-endif
-endif
 
 export prefix libdir src obj
 
@@ -157,7 +136,7 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
+$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -175,7 +154,7 @@ $(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
+$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
@@ -264,34 +243,16 @@ install_pkgconfig: $(PC_FILE)
 
 install: install_lib install_pkgconfig install_headers
 
-### Cleaning rules
-
-config-clean:
-	$(call QUIET_CLEAN, feature-detect)
-	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
-
-clean: config-clean
+clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
 		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
-	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
-
-
 
-PHONY += force elfdep zdep bpfdep cscope tags
+PHONY += force cscope tags
 force:
 
-elfdep:
-	@if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi
-
-zdep:
-	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
-
-bpfdep:
-	@if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi
-
 cscope:
 	ls *.c *.h > cscope.files
 	cscope -b -q -I $(srctree)/include -f cscope.out
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index bbcefb3ff5a5..53b3e199fb25 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -195,17 +195,22 @@ enum bpf_enum_value_kind {
  * (local) BTF, used to record relocation.
  */
 #define bpf_core_read(dst, sz, src)					    \
-	bpf_probe_read_kernel(dst, sz,					    \
-			      (const void *)__builtin_preserve_access_index(src))
+	bpf_probe_read_kernel(dst, sz, (const void *)__builtin_preserve_access_index(src))
 
+/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */
+#define bpf_core_read_user(dst, sz, src)				    \
+	bpf_probe_read_user(dst, sz, (const void *)__builtin_preserve_access_index(src))
 /*
  * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str()
  * additionally emitting BPF CO-RE field relocation for specified source
  * argument.
  */
 #define bpf_core_read_str(dst, sz, src)					    \
-	bpf_probe_read_kernel_str(dst, sz,				    \
-				  (const void *)__builtin_preserve_access_index(src))
+	bpf_probe_read_kernel_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
+
+/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */
+#define bpf_core_read_user_str(dst, sz, src)				    \
+	bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src))
 
 #define ___concat(a, b) a ## b
 #define ___apply(fn, n) ___concat(fn, n)
@@ -264,30 +269,29 @@ enum bpf_enum_value_kind {
 	read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor)
 
 /* "recursively" read a sequence of inner pointers using local __t var */
-#define ___rd_first(src, a) ___read(bpf_core_read, &__t, ___type(src), src, a);
-#define ___rd_last(...)							    \
-	___read(bpf_core_read, &__t,					    \
-		___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__));
-#define ___rd_p1(...) const void *__t; ___rd_first(__VA_ARGS__)
-#define ___rd_p2(...) ___rd_p1(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p3(...) ___rd_p2(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p4(...) ___rd_p3(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p5(...) ___rd_p4(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p6(...) ___rd_p5(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p7(...) ___rd_p6(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p8(...) ___rd_p7(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___rd_p9(...) ___rd_p8(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
-#define ___read_ptrs(src, ...)						    \
-	___apply(___rd_p, ___narg(__VA_ARGS__))(src, __VA_ARGS__)
-
-#define ___core_read0(fn, dst, src, a)					    \
+#define ___rd_first(fn, src, a) ___read(fn, &__t, ___type(src), src, a);
+#define ___rd_last(fn, ...)						    \
+	___read(fn, &__t, ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__));
+#define ___rd_p1(fn, ...) const void *__t; ___rd_first(fn, __VA_ARGS__)
+#define ___rd_p2(fn, ...) ___rd_p1(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p3(fn, ...) ___rd_p2(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p4(fn, ...) ___rd_p3(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p5(fn, ...) ___rd_p4(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p6(fn, ...) ___rd_p5(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p7(fn, ...) ___rd_p6(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p8(fn, ...) ___rd_p7(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___rd_p9(fn, ...) ___rd_p8(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__)
+#define ___read_ptrs(fn, src, ...)					    \
+	___apply(___rd_p, ___narg(__VA_ARGS__))(fn, src, __VA_ARGS__)
+
+#define ___core_read0(fn, fn_ptr, dst, src, a)				    \
 	___read(fn, dst, ___type(src), src, a);
-#define ___core_readN(fn, dst, src, ...)				    \
-	___read_ptrs(src, ___nolast(__VA_ARGS__))			    \
+#define ___core_readN(fn, fn_ptr, dst, src, ...)			    \
+	___read_ptrs(fn_ptr, src, ___nolast(__VA_ARGS__))		    \
 	___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t,	    \
 		___last(__VA_ARGS__));
-#define ___core_read(fn, dst, src, a, ...)				    \
-	___apply(___core_read, ___empty(__VA_ARGS__))(fn, dst,		    \
+#define ___core_read(fn, fn_ptr, dst, src, a, ...)			    \
+	___apply(___core_read, ___empty(__VA_ARGS__))(fn, fn_ptr, dst,	    \
 						      src, a, ##__VA_ARGS__)
 
 /*
@@ -295,20 +299,73 @@ enum bpf_enum_value_kind {
  * BPF_CORE_READ(), in which final field is read into user-provided storage.
  * See BPF_CORE_READ() below for more details on general usage.
  */
-#define BPF_CORE_READ_INTO(dst, src, a, ...)				    \
-	({								    \
-		___core_read(bpf_core_read, dst, (src), a, ##__VA_ARGS__)   \
-	})
+#define BPF_CORE_READ_INTO(dst, src, a, ...) ({				    \
+	___core_read(bpf_core_read, bpf_core_read,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Variant of BPF_CORE_READ_INTO() for reading from user-space memory.
+ *
+ * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use.
+ */
+#define BPF_CORE_READ_USER_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_core_read_user, bpf_core_read_user,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* 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,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ_USER_INTO().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_probe_read_user, bpf_probe_read_user,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
 
 /*
  * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as
  * BPF_CORE_READ() for intermediate pointers, but then executes (and returns
  * corresponding error code) bpf_core_read_str() for final string read.
  */
-#define BPF_CORE_READ_STR_INTO(dst, src, a, ...)			    \
-	({								    \
-		___core_read(bpf_core_read_str, dst, (src), a, ##__VA_ARGS__)\
-	})
+#define BPF_CORE_READ_STR_INTO(dst, src, a, ...) ({			    \
+	___core_read(bpf_core_read_str, bpf_core_read,			    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Variant of BPF_CORE_READ_STR_INTO() for reading from user-space memory.
+ *
+ * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use.
+ */
+#define BPF_CORE_READ_USER_STR_INTO(dst, src, a, ...) ({		    \
+	___core_read(bpf_core_read_user_str, bpf_core_read_user,	    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/* 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,		    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
+
+/*
+ * Non-CO-RE variant of BPF_CORE_READ_USER_STR_INTO().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER_STR_INTO(dst, src, a, ...) ({		    \
+	___core_read(bpf_probe_read_user_str, bpf_probe_read_user,	    \
+		     dst, (src), a, ##__VA_ARGS__)			    \
+})
 
 /*
  * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially
@@ -334,12 +391,46 @@ enum bpf_enum_value_kind {
  * N.B. Only up to 9 "field accessors" are supported, which should be more
  * than enough for any practical purpose.
  */
-#define BPF_CORE_READ(src, a, ...)					    \
-	({								    \
-		___type((src), a, ##__VA_ARGS__) __r;			    \
-		BPF_CORE_READ_INTO(&__r, (src), a, ##__VA_ARGS__);	    \
-		__r;							    \
-	})
+#define BPF_CORE_READ(src, a, ...) ({					    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_CORE_READ_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/*
+ * Variant of BPF_CORE_READ() for reading from user-space memory.
+ *
+ * NOTE: all the source types involved are still *kernel types* and need to
+ * exist in kernel (or kernel module) BTF, otherwise CO-RE relocation will
+ * fail. Custom user types are not relocatable with CO-RE.
+ * The typical situation in which BPF_CORE_READ_USER() might be used is to
+ * read kernel UAPI types from the user-space memory passed in as a syscall
+ * input argument.
+ */
+#define BPF_CORE_READ_USER(src, a, ...) ({				    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_CORE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/* Non-CO-RE variant of BPF_CORE_READ() */
+#define BPF_PROBE_READ(src, a, ...) ({					    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_PROBE_READ_INTO(&__r, (src), a, ##__VA_ARGS__);		    \
+	__r;								    \
+})
+
+/*
+ * Non-CO-RE variant of BPF_CORE_READ_USER().
+ *
+ * As no CO-RE relocations are emitted, source types can be arbitrary and are
+ * not restricted to kernel types only.
+ */
+#define BPF_PROBE_READ_USER(src, a, ...) ({				    \
+	___type((src), a, ##__VA_ARGS__) __r;				    \
+	BPF_PROBE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__);	    \
+	__r;								    \
+})
 
 #endif
 
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 72b251110c4d..ae6c975e0b87 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -30,7 +30,7 @@
 #define SEC(NAME) __attribute__((section(NAME), used))
 
 #ifndef __always_inline
-#define __always_inline __attribute__((always_inline))
+#define __always_inline inline __attribute__((always_inline))
 #endif
 #ifndef __noinline
 #define __noinline __attribute__((noinline))
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 9970a288dda5..d9c10830d749 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -858,6 +858,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	Elf_Scn *scn = NULL;
 	Elf *elf = NULL;
 	GElf_Ehdr ehdr;
+	size_t shstrndx;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("failed to init libelf for %s\n", path);
@@ -882,7 +883,14 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		pr_warn("failed to get EHDR from %s\n", path);
 		goto done;
 	}
-	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+
+	if (elf_getshdrstrndx(elf, &shstrndx)) {
+		pr_warn("failed to get section names section index for %s\n",
+			path);
+		goto done;
+	}
+
+	if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) {
 		pr_warn("failed to get e_shstrndx from %s\n", path);
 		goto done;
 	}
@@ -897,7 +905,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 				idx, path);
 			goto done;
 		}
-		name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+		name = elf_strptr(elf, shstrndx, sh.sh_name);
 		if (!name) {
 			pr_warn("failed to get section(%d) name from %s\n",
 				idx, path);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6ae748f6ea11..d43cc3f29dae 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -395,7 +395,8 @@ struct extern_desc {
 			unsigned long long addr;
 
 			/* target btf_id of the corresponding kernel var. */
-			int vmlinux_btf_id;
+			int kernel_btf_obj_fd;
+			int kernel_btf_id;
 
 			/* local btf_id of the ksym extern's type. */
 			__u32 type_id;
@@ -883,24 +884,24 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
 		if (btf_is_ptr(mtype)) {
 			struct bpf_program *prog;
 
-			mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+			prog = st_ops->progs[i];
+			if (!prog)
+				continue;
+
 			kern_mtype = skip_mods_and_typedefs(kern_btf,
 							    kern_mtype->type,
 							    &kern_mtype_id);
-			if (!btf_is_func_proto(mtype) ||
-			    !btf_is_func_proto(kern_mtype)) {
-				pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+
+			/* mtype->type must be a func_proto which was
+			 * guaranteed in bpf_object__collect_st_ops_relos(),
+			 * so only check kern_mtype for func_proto here.
+			 */
+			if (!btf_is_func_proto(kern_mtype)) {
+				pr_warn("struct_ops init_kern %s: kernel member %s is not a func ptr\n",
 					map->name, mname);
 				return -ENOTSUP;
 			}
 
-			prog = st_ops->progs[i];
-			if (!prog) {
-				pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
-					 map->name, mname);
-				continue;
-			}
-
 			prog->attach_btf_id = kern_type_id;
 			prog->expected_attach_type = kern_member_idx;
 
@@ -6162,7 +6163,8 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			} else /* EXT_KSYM */ {
 				if (ext->ksym.type_id) { /* typed ksyms */
 					insn[0].src_reg = BPF_PSEUDO_BTF_ID;
-					insn[0].imm = ext->ksym.vmlinux_btf_id;
+					insn[0].imm = ext->ksym.kernel_btf_id;
+					insn[1].imm = ext->ksym.kernel_btf_obj_fd;
 				} else { /* typeless ksyms */
 					insn[0].imm = (__u32)ext->ksym.addr;
 					insn[1].imm = ext->ksym.addr >> 32;
@@ -7319,7 +7321,8 @@ out:
 static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 {
 	struct extern_desc *ext;
-	int i, id;
+	struct btf *btf;
+	int i, j, id, btf_fd, err;
 
 	for (i = 0; i < obj->nr_extern; i++) {
 		const struct btf_type *targ_var, *targ_type;
@@ -7331,10 +7334,25 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		if (ext->type != EXT_KSYM || !ext->ksym.type_id)
 			continue;
 
-		id = btf__find_by_name_kind(obj->btf_vmlinux, ext->name,
-					    BTF_KIND_VAR);
+		btf = obj->btf_vmlinux;
+		btf_fd = 0;
+		id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
+		if (id == -ENOENT) {
+			err = load_module_btfs(obj);
+			if (err)
+				return err;
+
+			for (j = 0; j < obj->btf_module_cnt; j++) {
+				btf = obj->btf_modules[j].btf;
+				/* we assume module BTF FD is always >0 */
+				btf_fd = obj->btf_modules[j].fd;
+				id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
+				if (id != -ENOENT)
+					break;
+			}
+		}
 		if (id <= 0) {
-			pr_warn("extern (ksym) '%s': failed to find BTF ID in vmlinux BTF.\n",
+			pr_warn("extern (ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
 				ext->name);
 			return -ESRCH;
 		}
@@ -7343,24 +7361,19 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		local_type_id = ext->ksym.type_id;
 
 		/* find target type_id */
-		targ_var = btf__type_by_id(obj->btf_vmlinux, id);
-		targ_var_name = btf__name_by_offset(obj->btf_vmlinux,
-						    targ_var->name_off);
-		targ_type = skip_mods_and_typedefs(obj->btf_vmlinux,
-						   targ_var->type,
-						   &targ_type_id);
+		targ_var = btf__type_by_id(btf, id);
+		targ_var_name = btf__name_by_offset(btf, targ_var->name_off);
+		targ_type = skip_mods_and_typedefs(btf, targ_var->type, &targ_type_id);
 
 		ret = bpf_core_types_are_compat(obj->btf, local_type_id,
-						obj->btf_vmlinux, targ_type_id);
+						btf, targ_type_id);
 		if (ret <= 0) {
 			const struct btf_type *local_type;
 			const char *targ_name, *local_name;
 
 			local_type = btf__type_by_id(obj->btf, local_type_id);
-			local_name = btf__name_by_offset(obj->btf,
-							 local_type->name_off);
-			targ_name = btf__name_by_offset(obj->btf_vmlinux,
-							targ_type->name_off);
+			local_name = btf__name_by_offset(obj->btf, local_type->name_off);
+			targ_name = btf__name_by_offset(btf, targ_type->name_off);
 
 			pr_warn("extern (ksym) '%s': incompatible types, expected [%d] %s %s, but kernel has [%d] %s %s\n",
 				ext->name, local_type_id,
@@ -7370,7 +7383,8 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		}
 
 		ext->is_set = true;
-		ext->ksym.vmlinux_btf_id = id;
+		ext->ksym.kernel_btf_obj_fd = btf_fd;
+		ext->ksym.kernel_btf_id = id;
 		pr_debug("extern (ksym) '%s': resolved to [%d] %s %s\n",
 			 ext->name, id, btf_kind_str(targ_var), targ_var_name);
 	}
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e3e41ceeb1bc..ffbb588724d8 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -46,6 +46,11 @@
  #define PF_XDP AF_XDP
 #endif
 
+enum xsk_prog {
+	XSK_PROG_FALLBACK,
+	XSK_PROG_REDIRECT_FLAGS,
+};
+
 struct xsk_umem {
 	struct xsk_ring_prod *fill_save;
 	struct xsk_ring_cons *comp_save;
@@ -351,6 +356,54 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
 DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
+static enum xsk_prog get_xsk_prog(void)
+{
+	enum xsk_prog detected = XSK_PROG_FALLBACK;
+	struct bpf_load_program_attr prog_attr;
+	struct bpf_create_map_attr map_attr;
+	__u32 size_out, retval, duration;
+	char data_in = 0, data_out;
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_MOV64_IMM(BPF_REG_3, XDP_PASS),
+		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, map_fd, ret;
+
+	memset(&map_attr, 0, sizeof(map_attr));
+	map_attr.map_type = BPF_MAP_TYPE_XSKMAP;
+	map_attr.key_size = sizeof(int);
+	map_attr.value_size = sizeof(int);
+	map_attr.max_entries = 1;
+
+	map_fd = bpf_create_map_xattr(&map_attr);
+	if (map_fd < 0)
+		return detected;
+
+	insns[0].imm = map_fd;
+
+	memset(&prog_attr, 0, sizeof(prog_attr));
+	prog_attr.prog_type = BPF_PROG_TYPE_XDP;
+	prog_attr.insns = insns;
+	prog_attr.insns_cnt = ARRAY_SIZE(insns);
+	prog_attr.license = "GPL";
+
+	prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0);
+	if (prog_fd < 0) {
+		close(map_fd);
+		return detected;
+	}
+
+	ret = bpf_prog_test_run(prog_fd, 0, &data_in, 1, &data_out, &size_out, &retval, &duration);
+	if (!ret && retval == XDP_PASS)
+		detected = XSK_PROG_REDIRECT_FLAGS;
+	close(prog_fd);
+	close(map_fd);
+	return detected;
+}
+
 static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 {
 	static const int log_buf_size = 16 * 1024;
@@ -358,7 +411,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	char log_buf[log_buf_size];
 	int err, prog_fd;
 
-	/* This is the C-program:
+	/* This is the fallback C-program:
 	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
 	 * {
 	 *     int ret, index = ctx->rx_queue_index;
@@ -414,9 +467,31 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 		/* The jumps are to this instruction */
 		BPF_EXIT_INSN(),
 	};
-	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
+	/* This is the post-5.3 kernel C-program:
+	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
+	 * {
+	 *     return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS);
+	 * }
+	 */
+	struct bpf_insn prog_redirect_flags[] = {
+		/* r2 = *(u32 *)(r1 + 16) */
+		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
+		/* r1 = xskmap[] */
+		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
+		/* r3 = XDP_PASS */
+		BPF_MOV64_IMM(BPF_REG_3, 2),
+		/* call bpf_redirect_map */
+		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt[] = {sizeof(prog) / sizeof(struct bpf_insn),
+			      sizeof(prog_redirect_flags) / sizeof(struct bpf_insn),
+	};
+	struct bpf_insn *progs[] = {prog, prog_redirect_flags};
+	enum xsk_prog option = get_xsk_prog();
+
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, progs[option], insns_cnt[option],
 				   "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
 				   log_buf_size);
 	if (prog_fd < 0) {
@@ -442,7 +517,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 	struct ifreq ifr = {};
 	int fd, err, ret;
 
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	fd = socket(AF_LOCAL, SOCK_DGRAM, 0);
 	if (fd < 0)
 		return -errno;