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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

19 files changed, 3709 insertions, 571 deletions

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index ee9d5362f35b..e3962cfbc9a6 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1,3 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
+	    netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
+	    btf_dump.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f91639bf5650..9312066a1ae3 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
 
 BPF_VERSION = 0
 BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 3
+BPF_EXTRAVERSION = 4
 
 MAKEFLAGS += --no-print-directory
 
@@ -204,6 +204,16 @@ check_abi: $(OUTPUT)libbpf.so
 		     "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
 		     "Please make sure all LIBBPF_API symbols are"	 \
 		     "versioned in $(VERSION_SCRIPT)." >&2;		 \
+		readelf -s --wide $(OUTPUT)libbpf-in.o |		 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'|   \
+		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
+		readelf -s --wide $(OUTPUT)libbpf.so |			 \
+		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
+		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
+		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
+		     $(OUTPUT)libbpf_versioned_syms.tmp;		 \
+		rm $(OUTPUT)libbpf_global_syms.tmp			 \
+		   $(OUTPUT)libbpf_versioned_syms.tmp;			 \
 		exit 1;							 \
 	fi
 
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index cef7b77eab69..8928f7787f2d 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -9,7 +9,8 @@ described here. It's recommended to follow these conventions whenever a
 new function or type is added to keep libbpf API clean and consistent.
 
 All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
+``perf_buffer_``.
 
 System call wrappers
 --------------------
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c4a48086dc9a..c7d7993c44bb 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,10 +26,11 @@
 #include <memory.h>
 #include <unistd.h>
 #include <asm/unistd.h>
+#include <errno.h>
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
-#include <errno.h>
+#include "libbpf_internal.h"
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -53,10 +54,6 @@
 # endif
 #endif
 
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -256,6 +253,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	if (load_attr->name)
 		memcpy(attr.prog_name, load_attr->name,
 		       min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.prog_flags = load_attr->prog_flags;
 
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 	if (fd >= 0)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9593fec75652..ff42ca043dc8 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -87,6 +87,7 @@ struct bpf_load_program_attr {
 	const void *line_info;
 	__u32 line_info_cnt;
 	__u32 log_level;
+	__u32 prog_flags;
 };
 
 /* Flags to direct loading requirements */
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 6978314ea7f6..8c67561c93b0 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -6,10 +6,7 @@
 #include <linux/err.h>
 #include <linux/bpf.h>
 #include "libbpf.h"
-
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
+#include "libbpf_internal.h"
 
 struct bpf_prog_linfo {
 	void *raw_linfo;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 03348c4d6bd4..467224feb43b 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -4,17 +4,17 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
 #include <linux/err.h>
 #include <linux/btf.h>
+#include <gelf.h>
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
-
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min(a, b) ((a) < (b) ? (a) : (b))
+#include "hashmap.h"
 
 #define BTF_MAX_NR_TYPES 0x7fffffff
 #define BTF_MAX_STR_OFFSET 0x7fffffff
@@ -417,6 +417,132 @@ done:
 	return btf;
 }
 
+static bool btf_check_endianness(const GElf_Ehdr *ehdr)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
+	int err = 0, fd = -1, idx = 0;
+	struct btf *btf = NULL;
+	Elf_Scn *scn = NULL;
+	Elf *elf = NULL;
+	GElf_Ehdr ehdr;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warning("failed to init libelf for %s\n", path);
+		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
+	}
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		err = -errno;
+		pr_warning("failed to open %s: %s\n", path, strerror(errno));
+		return ERR_PTR(err);
+	}
+
+	err = -LIBBPF_ERRNO__FORMAT;
+
+	elf = elf_begin(fd, ELF_C_READ, NULL);
+	if (!elf) {
+		pr_warning("failed to open %s as ELF file\n", path);
+		goto done;
+	}
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warning("failed to get EHDR from %s\n", path);
+		goto done;
+	}
+	if (!btf_check_endianness(&ehdr)) {
+		pr_warning("non-native ELF endianness is not supported\n");
+		goto done;
+	}
+	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+		pr_warning("failed to get e_shstrndx from %s\n", path);
+		goto done;
+	}
+
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		GElf_Shdr sh;
+		char *name;
+
+		idx++;
+		if (gelf_getshdr(scn, &sh) != &sh) {
+			pr_warning("failed to get section(%d) header from %s\n",
+				   idx, path);
+			goto done;
+		}
+		name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+		if (!name) {
+			pr_warning("failed to get section(%d) name from %s\n",
+				   idx, path);
+			goto done;
+		}
+		if (strcmp(name, BTF_ELF_SEC) == 0) {
+			btf_data = elf_getdata(scn, 0);
+			if (!btf_data) {
+				pr_warning("failed to get section(%d, %s) data from %s\n",
+					   idx, name, path);
+				goto done;
+			}
+			continue;
+		} else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+			btf_ext_data = elf_getdata(scn, 0);
+			if (!btf_ext_data) {
+				pr_warning("failed to get section(%d, %s) data from %s\n",
+					   idx, name, path);
+				goto done;
+			}
+			continue;
+		}
+	}
+
+	err = 0;
+
+	if (!btf_data) {
+		err = -ENOENT;
+		goto done;
+	}
+	btf = btf__new(btf_data->d_buf, btf_data->d_size);
+	if (IS_ERR(btf))
+		goto done;
+
+	if (btf_ext && btf_ext_data) {
+		*btf_ext = btf_ext__new(btf_ext_data->d_buf,
+					btf_ext_data->d_size);
+		if (IS_ERR(*btf_ext))
+			goto done;
+	} else if (btf_ext) {
+		*btf_ext = NULL;
+	}
+done:
+	if (elf)
+		elf_end(elf);
+	close(fd);
+
+	if (err)
+		return ERR_PTR(err);
+	/*
+	 * btf is always parsed before btf_ext, so no need to clean up
+	 * btf_ext, if btf loading failed
+	 */
+	if (IS_ERR(btf))
+		return btf;
+	if (btf_ext && IS_ERR(*btf_ext)) {
+		btf__free(btf);
+		err = PTR_ERR(*btf_ext);
+		return ERR_PTR(err);
+	}
+	return btf;
+}
+
 static int compare_vsi_off(const void *_a, const void *_b)
 {
 	const struct btf_var_secinfo *a = _a;
@@ -1165,16 +1291,9 @@ done:
 	return err;
 }
 
-#define BTF_DEDUP_TABLE_DEFAULT_SIZE (1 << 14)
-#define BTF_DEDUP_TABLE_MAX_SIZE_LOG 31
 #define BTF_UNPROCESSED_ID ((__u32)-1)
 #define BTF_IN_PROGRESS_ID ((__u32)-2)
 
-struct btf_dedup_node {
-	struct btf_dedup_node *next;
-	__u32 type_id;
-};
-
 struct btf_dedup {
 	/* .BTF section to be deduped in-place */
 	struct btf *btf;
@@ -1190,7 +1309,7 @@ struct btf_dedup {
 	 * candidates, which is fine because we rely on subsequent
 	 * btf_xxx_equal() checks to authoritatively verify type equality.
 	 */
-	struct btf_dedup_node **dedup_table;
+	struct hashmap *dedup_table;
 	/* Canonical types map */
 	__u32 *map;
 	/* Hypothetical mapping, used during type graph equivalence checks */
@@ -1215,30 +1334,18 @@ struct btf_str_ptrs {
 	__u32 cap;
 };
 
-static inline __u32 hash_combine(__u32 h, __u32 value)
+static long hash_combine(long h, long value)
 {
-/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
-#define GOLDEN_RATIO_PRIME 0x9e370001UL
-	return h * 37 + value * GOLDEN_RATIO_PRIME;
-#undef GOLDEN_RATIO_PRIME
+	return h * 31 + value;
 }
 
-#define for_each_dedup_cand(d, hash, node) \
-	for (node = d->dedup_table[hash & (d->opts.dedup_table_size - 1)]; \
-	     node;							   \
-	     node = node->next)
+#define for_each_dedup_cand(d, node, hash) \
+	hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
 
-static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id)
+static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
 {
-	struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node));
-	int bucket = hash & (d->opts.dedup_table_size - 1);
-
-	if (!node)
-		return -ENOMEM;
-	node->type_id = type_id;
-	node->next = d->dedup_table[bucket];
-	d->dedup_table[bucket] = node;
-	return 0;
+	return hashmap__append(d->dedup_table,
+			       (void *)hash, (void *)(long)type_id);
 }
 
 static int btf_dedup_hypot_map_add(struct btf_dedup *d,
@@ -1267,36 +1374,10 @@ static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
 	d->hypot_cnt = 0;
 }
 
-static void btf_dedup_table_free(struct btf_dedup *d)
-{
-	struct btf_dedup_node *head, *tmp;
-	int i;
-
-	if (!d->dedup_table)
-		return;
-
-	for (i = 0; i < d->opts.dedup_table_size; i++) {
-		while (d->dedup_table[i]) {
-			tmp = d->dedup_table[i];
-			d->dedup_table[i] = tmp->next;
-			free(tmp);
-		}
-
-		head = d->dedup_table[i];
-		while (head) {
-			tmp = head;
-			head = head->next;
-			free(tmp);
-		}
-	}
-
-	free(d->dedup_table);
-	d->dedup_table = NULL;
-}
-
 static void btf_dedup_free(struct btf_dedup *d)
 {
-	btf_dedup_table_free(d);
+	hashmap__free(d->dedup_table);
+	d->dedup_table = NULL;
 
 	free(d->map);
 	d->map = NULL;
@@ -1310,40 +1391,43 @@ static void btf_dedup_free(struct btf_dedup *d)
 	free(d);
 }
 
-/* Find closest power of two >= to size, capped at 2^max_size_log */
-static __u32 roundup_pow2_max(__u32 size, int max_size_log)
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
 {
-	int i;
+	return (size_t)key;
+}
 
-	for (i = 0; i < max_size_log  && (1U << i) < size;  i++)
-		;
-	return 1U << i;
+static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+{
+	return 0;
 }
 
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+	return k1 == k2;
+}
 
 static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 				       const struct btf_dedup_opts *opts)
 {
 	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
+	hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
 	int i, err = 0;
-	__u32 sz;
 
 	if (!d)
 		return ERR_PTR(-ENOMEM);
 
 	d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
-	sz = opts && opts->dedup_table_size ? opts->dedup_table_size
-					    : BTF_DEDUP_TABLE_DEFAULT_SIZE;
-	sz = roundup_pow2_max(sz, BTF_DEDUP_TABLE_MAX_SIZE_LOG);
-	d->opts.dedup_table_size = sz;
+	/* dedup_table_size is now used only to force collisions in tests */
+	if (opts && opts->dedup_table_size == 1)
+		hash_fn = btf_dedup_collision_hash_fn;
 
 	d->btf = btf;
 	d->btf_ext = btf_ext;
 
-	d->dedup_table = calloc(d->opts.dedup_table_size,
-				sizeof(struct btf_dedup_node *));
-	if (!d->dedup_table) {
-		err = -ENOMEM;
+	d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(d->dedup_table)) {
+		err = PTR_ERR(d->dedup_table);
+		d->dedup_table = NULL;
 		goto done;
 	}
 
@@ -1662,9 +1746,9 @@ done:
 	return err;
 }
 
-static __u32 btf_hash_common(struct btf_type *t)
+static long btf_hash_common(struct btf_type *t)
 {
-	__u32 h;
+	long h;
 
 	h = hash_combine(0, t->name_off);
 	h = hash_combine(h, t->info);
@@ -1680,10 +1764,10 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 }
 
 /* Calculate type signature hash of INT. */
-static __u32 btf_hash_int(struct btf_type *t)
+static long btf_hash_int(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
-	__u32 h;
+	long h;
 
 	h = btf_hash_common(t);
 	h = hash_combine(h, info);
@@ -1703,9 +1787,9 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
 }
 
 /* Calculate type signature hash of ENUM. */
-static __u32 btf_hash_enum(struct btf_type *t)
+static long btf_hash_enum(struct btf_type *t)
 {
-	__u32 h;
+	long h;
 
 	/* don't hash vlen and enum members to support enum fwd resolving */
 	h = hash_combine(0, t->name_off);
@@ -1757,11 +1841,11 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
  * as referenced type IDs equivalence is established separately during type
  * graph equivalence check algorithm.
  */
-static __u32 btf_hash_struct(struct btf_type *t)
+static long btf_hash_struct(struct btf_type *t)
 {
 	struct btf_member *member = (struct btf_member *)(t + 1);
 	__u32 vlen = BTF_INFO_VLEN(t->info);
-	__u32 h = btf_hash_common(t);
+	long h = btf_hash_common(t);
 	int i;
 
 	for (i = 0; i < vlen; i++) {
@@ -1804,10 +1888,10 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
  * under assumption that they were already resolved to canonical type IDs and
  * are not going to change.
  */
-static __u32 btf_hash_array(struct btf_type *t)
+static long btf_hash_array(struct btf_type *t)
 {
 	struct btf_array *info = (struct btf_array *)(t + 1);
-	__u32 h = btf_hash_common(t);
+	long h = btf_hash_common(t);
 
 	h = hash_combine(h, info->type);
 	h = hash_combine(h, info->index_type);
@@ -1858,11 +1942,11 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
  * under assumption that they were already resolved to canonical type IDs and
  * are not going to change.
  */
-static inline __u32 btf_hash_fnproto(struct btf_type *t)
+static long btf_hash_fnproto(struct btf_type *t)
 {
 	struct btf_param *member = (struct btf_param *)(t + 1);
 	__u16 vlen = BTF_INFO_VLEN(t->info);
-	__u32 h = btf_hash_common(t);
+	long h = btf_hash_common(t);
 	int i;
 
 	for (i = 0; i < vlen; i++) {
@@ -1880,7 +1964,7 @@ static inline __u32 btf_hash_fnproto(struct btf_type *t)
  * This function is called during reference types deduplication to compare
  * FUNC_PROTO to potential canonical representative.
  */
-static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
 	struct btf_param *m1, *m2;
 	__u16 vlen;
@@ -1906,7 +1990,7 @@ static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
  * IDs. This check is performed during type graph equivalence check and
  * referenced types equivalence is checked separately.
  */
-static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
+static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 {
 	struct btf_param *m1, *m2;
 	__u16 vlen;
@@ -1937,11 +2021,12 @@ static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
 static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 {
 	struct btf_type *t = d->btf->types[type_id];
+	struct hashmap_entry *hash_entry;
 	struct btf_type *cand;
-	struct btf_dedup_node *cand_node;
 	/* if we don't find equivalent type, then we are canonical */
 	__u32 new_id = type_id;
-	__u32 h;
+	__u32 cand_id;
+	long h;
 
 	switch (BTF_INFO_KIND(t->info)) {
 	case BTF_KIND_CONST:
@@ -1960,10 +2045,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 
 	case BTF_KIND_INT:
 		h = btf_hash_int(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_int(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 		}
@@ -1971,10 +2057,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 
 	case BTF_KIND_ENUM:
 		h = btf_hash_enum(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_enum(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 			if (d->opts.dont_resolve_fwds)
@@ -1982,21 +2069,22 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 			if (btf_compat_enum(t, cand)) {
 				if (btf_is_enum_fwd(t)) {
 					/* resolve fwd to full enum */
-					new_id = cand_node->type_id;
+					new_id = cand_id;
 					break;
 				}
 				/* resolve canonical enum fwd to full enum */
-				d->map[cand_node->type_id] = type_id;
+				d->map[cand_id] = type_id;
 			}
 		}
 		break;
 
 	case BTF_KIND_FWD:
 		h = btf_hash_common(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_common(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 		}
@@ -2397,12 +2485,12 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
  */
 static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_dedup_node *cand_node;
 	struct btf_type *cand_type, *t;
+	struct hashmap_entry *hash_entry;
 	/* if we don't find equivalent type, then we are canonical */
 	__u32 new_id = type_id;
 	__u16 kind;
-	__u32 h;
+	long h;
 
 	/* already deduped or is in process of deduping (loop detected) */
 	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
@@ -2415,7 +2503,8 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		return 0;
 
 	h = btf_hash_struct(t);
-	for_each_dedup_cand(d, h, cand_node) {
+	for_each_dedup_cand(d, hash_entry, h) {
+		__u32 cand_id = (__u32)(long)hash_entry->value;
 		int eq;
 
 		/*
@@ -2428,17 +2517,17 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		 * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because
 		 * FWD and compatible STRUCT/UNION are considered equivalent.
 		 */
-		cand_type = d->btf->types[cand_node->type_id];
+		cand_type = d->btf->types[cand_id];
 		if (!btf_shallow_equal_struct(t, cand_type))
 			continue;
 
 		btf_dedup_clear_hypot_map(d);
-		eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id);
+		eq = btf_dedup_is_equiv(d, type_id, cand_id);
 		if (eq < 0)
 			return eq;
 		if (!eq)
 			continue;
-		new_id = cand_node->type_id;
+		new_id = cand_id;
 		btf_dedup_merge_hypot_map(d);
 		break;
 	}
@@ -2488,12 +2577,12 @@ static int btf_dedup_struct_types(struct btf_dedup *d)
  */
 static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_dedup_node *cand_node;
+	struct hashmap_entry *hash_entry;
+	__u32 new_id = type_id, cand_id;
 	struct btf_type *t, *cand;
 	/* if we don't find equivalent type, then we are representative type */
-	__u32 new_id = type_id;
 	int ref_type_id;
-	__u32 h;
+	long h;
 
 	if (d->map[type_id] == BTF_IN_PROGRESS_ID)
 		return -ELOOP;
@@ -2516,10 +2605,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		t->type = ref_type_id;
 
 		h = btf_hash_common(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_common(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 		}
@@ -2539,10 +2629,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		info->index_type = ref_type_id;
 
 		h = btf_hash_array(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_array(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 		}
@@ -2570,10 +2661,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 
 		h = btf_hash_fnproto(t);
-		for_each_dedup_cand(d, h, cand_node) {
-			cand = d->btf->types[cand_node->type_id];
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = d->btf->types[cand_id];
 			if (btf_equal_fnproto(t, cand)) {
-				new_id = cand_node->type_id;
+				new_id = cand_id;
 				break;
 			}
 		}
@@ -2600,7 +2692,9 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 		if (err < 0)
 			return err;
 	}
-	btf_dedup_table_free(d);
+	/* we won't need d->dedup_table anymore */
+	hashmap__free(d->dedup_table);
+	d->dedup_table = NULL;
 	return 0;
 }
 
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index c7b399e81fce..88a52ae56fc6 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -4,6 +4,7 @@
 #ifndef __LIBBPF_BTF_H
 #define __LIBBPF_BTF_H
 
+#include <stdarg.h>
 #include <linux/types.h>
 
 #ifdef __cplusplus
@@ -16,6 +17,7 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
 
 struct btf;
 struct btf_ext;
@@ -59,6 +61,8 @@ struct btf_ext_header {
 
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API struct btf *btf__parse_elf(const char *path,
+				      struct btf_ext **btf_ext);
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
@@ -100,6 +104,22 @@ struct btf_dedup_opts {
 LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 			  const struct btf_dedup_opts *opts);
 
+struct btf_dump;
+
+struct btf_dump_opts {
+	void *ctx;
+};
+
+typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
+
+LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
+					  const struct btf_ext *btf_ext,
+					  const struct btf_dump_opts *opts,
+					  btf_dump_printf_fn_t printf_fn);
+LIBBPF_API void btf_dump__free(struct btf_dump *d);
+
+LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
new file mode 100644
index 000000000000..7065bb5b2752
--- /dev/null
+++ b/tools/lib/bpf/btf_dump.c
@@ -0,0 +1,1333 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C type converter.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include "btf.h"
+#include "hashmap.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
+static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
+
+static const char *pfx(int lvl)
+{
+	return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl];
+}
+
+enum btf_dump_type_order_state {
+	NOT_ORDERED,
+	ORDERING,
+	ORDERED,
+};
+
+enum btf_dump_type_emit_state {
+	NOT_EMITTED,
+	EMITTING,
+	EMITTED,
+};
+
+/* per-type auxiliary state */
+struct btf_dump_type_aux_state {
+	/* topological sorting state */
+	enum btf_dump_type_order_state order_state: 2;
+	/* emitting state used to determine the need for forward declaration */
+	enum btf_dump_type_emit_state emit_state: 2;
+	/* whether forward declaration was already emitted */
+	__u8 fwd_emitted: 1;
+	/* whether unique non-duplicate name was already assigned */
+	__u8 name_resolved: 1;
+};
+
+struct btf_dump {
+	const struct btf *btf;
+	const struct btf_ext *btf_ext;
+	btf_dump_printf_fn_t printf_fn;
+	struct btf_dump_opts opts;
+
+	/* per-type auxiliary state */
+	struct btf_dump_type_aux_state *type_states;
+	/* per-type optional cached unique name, must be freed, if present */
+	const char **cached_names;
+
+	/* topo-sorted list of dependent type definitions */
+	__u32 *emit_queue;
+	int emit_queue_cap;
+	int emit_queue_cnt;
+
+	/*
+	 * stack of type declarations (e.g., chain of modifiers, arrays,
+	 * funcs, etc)
+	 */
+	__u32 *decl_stack;
+	int decl_stack_cap;
+	int decl_stack_cnt;
+
+	/* maps struct/union/enum name to a number of name occurrences */
+	struct hashmap *type_names;
+	/*
+	 * maps typedef identifiers and enum value names to a number of such
+	 * name occurrences
+	 */
+	struct hashmap *ident_names;
+};
+
+static size_t str_hash_fn(const void *key, void *ctx)
+{
+	const char *s = key;
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
+static bool str_equal_fn(const void *a, const void *b, void *ctx)
+{
+	return strcmp(a, b) == 0;
+}
+
+static __u16 btf_kind_of(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info);
+}
+
+static __u16 btf_vlen_of(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static bool btf_kflag_of(const struct btf_type *t)
+{
+	return BT