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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-01-22

The following pull-request contains BPF updates for your *net-next* tree.

We've added 92 non-merge commits during the last 16 day(s) which contain
a total of 320 files changed, 7532 insertions(+), 1448 deletions(-).

The main changes are:

1) function by function verification and program extensions from Alexei.

2) massive cleanup of selftests/bpf from Toke and Andrii.

3) batched bpf map operations from Brian and Yonghong.

4) tcp congestion control in bpf from Martin.

5) bulking for non-map xdp_redirect form Toke.

6) bpf_send_signal_thread helper from Yonghong.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

23 files changed, 525 insertions, 78 deletions

diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 5535650800ab..f897eeeb0b4f 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
   check_feat := 0
@@ -73,7 +73,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c
 
 PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm
 
-all: $(PROGS) bpftool
+all: $(PROGS) bpftool runqslower
 
 $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm'
 $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o
@@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
-clean: bpftool_clean
+clean: bpftool_clean runqslower_clean
 	$(call QUIET_CLEAN, bpf-progs)
 	$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
 	       $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
@@ -97,7 +97,7 @@ clean: bpftool_clean
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
 	$(Q)$(RM) -r -- $(OUTPUT)feature
 
-install: $(PROGS) bpftool_install
+install: $(PROGS) bpftool_install runqslower_install
 	$(call QUIET_INSTALL, bpf_jit_disasm)
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
 	$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
@@ -115,4 +115,14 @@ bpftool_install:
 bpftool_clean:
 	$(call descend,bpftool,clean)
 
-.PHONY: all install clean bpftool bpftool_install bpftool_clean
+runqslower:
+	$(call descend,runqslower)
+
+runqslower_install:
+	$(call descend,runqslower,install)
+
+runqslower_clean:
+	$(call descend,runqslower,clean)
+
+.PHONY: all install clean bpftool bpftool_install bpftool_clean \
+	runqslower runqslower_install runqslower_clean
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 86a87da97d0b..94d91322895a 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -196,7 +196,7 @@ and global variables.
   #define __EXAMPLE_SKEL_H__
 
   #include <stdlib.h>
-  #include <libbpf.h>
+  #include <bpf/libbpf.h>
 
   struct example {
   	struct bpf_object_skeleton *skeleton;
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 39bc6f0f4f0b..c4e810335810 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -45,7 +45,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi \
-	-I$(srctree)/tools/lib/bpf \
+	-I$(srctree)/tools/lib \
 	-I$(srctree)/tools/perf
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index e5bc97b71ceb..4ba90d81b6a1 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -8,15 +8,15 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/hashtable.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -370,6 +370,10 @@ static int dump_btf_c(const struct btf *btf,
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 
+	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+	printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
+	printf("#endif\n\n");
+
 	if (root_type_cnt) {
 		for (i = 0; i < root_type_cnt; i++) {
 			err = btf_dump__dump_type(d, root_type_ids[i]);
@@ -386,6 +390,10 @@ static int dump_btf_c(const struct btf *btf,
 		}
 	}
 
+	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+	printf("#pragma clang attribute pop\n");
+	printf("#endif\n");
+
 done:
 	btf_dump__free(d);
 	return err;
@@ -524,7 +532,7 @@ static int do_dump(int argc, char **argv)
 		if (IS_ERR(btf)) {
 			err = PTR_ERR(btf);
 			btf = NULL;
-			p_err("failed to load BTF from %s: %s", 
+			p_err("failed to load BTF from %s: %s",
 			      *argv, strerror(err));
 			goto done;
 		}
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 397e5716ab6d..01cc52b834fa 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -8,8 +8,8 @@
 #include <linux/bitops.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 2f017caa678d..62c6a1d7cd18 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -14,7 +14,7 @@
 #include <sys/types.h>
 #include <unistd.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 88264abaa738..b75b8ec5469c 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -20,8 +20,8 @@
 #include <sys/stat.h>
 #include <sys/vfs.h>
 
-#include <bpf.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 03bdc5b3ac49..446ba891f1e2 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -12,8 +12,8 @@
 #include <linux/filter.h>
 #include <linux/limits.h>
 
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <zlib.h>
 
 #include "main.h"
@@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 		printf("\n");
 }
 
+static void
+probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+{
+	bool res;
+
+	res = bpf_probe_large_insn_limit(ifindex);
+	print_bool_feature("have_large_insn_limit",
+			   "Large program size limit",
+			   "HAVE_LARGE_INSN_LIMIT",
+			   res, define_prefix);
+}
+
 static int do_probe(int argc, char **argv)
 {
 	enum probe_component target = COMPONENT_UNSPEC;
@@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv)
 		probe_helpers_for_progtype(i, supported_types[i],
 					   define_prefix, ifindex);
 
+	print_end_then_start_section("misc",
+				     "Scanning miscellaneous eBPF features...",
+				     "/*** eBPF misc features ***/",
+				     define_prefix);
+	probe_large_insn_limit(define_prefix, ifindex);
+
 exit_close_json:
 	if (json_output) {
 		/* End current "section" of probes */
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 7ce09a9a6999..f8113b3646f5 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -12,15 +12,15 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -333,7 +333,7 @@ static int do_skeleton(int argc, char **argv)
 		#define %2$s						    \n\
 									    \n\
 		#include <stdlib.h>					    \n\
-		#include <libbpf.h>					    \n\
+		#include <bpf/libbpf.h>					    \n\
 									    \n\
 		struct %1$s {						    \n\
 			struct bpf_object_skeleton *skeleton;		    \n\
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index bfed711258ce..f7f5885aa3ba 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -24,7 +24,7 @@
 #include <dis-asm.h>
 #include <sys/stat.h>
 #include <limits.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 
 #include "json_writer.h"
 #include "main.h"
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 1fe91c558508..6d41bbfc6459 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -9,8 +9,8 @@
 #include <stdlib.h>
 #include <string.h>
 
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index c01f76fa6876..e6c85680b34d 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -15,9 +15,9 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -48,6 +48,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_QUEUE]			= "queue",
 	[BPF_MAP_TYPE_STACK]			= "stack",
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
+	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -251,6 +252,7 @@ static int do_dump_btf(const struct btf_dumper *d,
 		       struct bpf_map_info *map_info, void *key,
 		       void *value)
 {
+	__u32 value_id;
 	int ret;
 
 	/* start of key-value pair */
@@ -264,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d,
 			goto err_end_obj;
 	}
 
+	value_id = map_info->btf_vmlinux_value_type_id ?
+		: map_info->btf_value_type_id;
+
 	if (!map_is_per_cpu(map_info->type)) {
 		jsonw_name(d->jw, "value");
-		ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+		ret = btf_dumper_type(d, value_id, value);
 	} else {
 		unsigned int i, n, step;
 
@@ -278,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d,
 			jsonw_start_object(d->jw);
 			jsonw_int_field(d->jw, "cpu", i);
 			jsonw_name(d->jw, "value");
-			ret = btf_dumper_type(d, map_info->btf_value_type_id,
-					      value + i * step);
+			ret = btf_dumper_type(d, value_id, value + i * step);
 			jsonw_end_object(d->jw);
 			if (ret)
 				break;
@@ -915,37 +919,63 @@ static int maps_have_btf(int *fds, int nb_fds)
 {
 	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
-	struct btf *btf = NULL;
 	int err, i;
 
 	for (i = 0; i < nb_fds; i++) {
 		err = bpf_obj_get_info_by_fd(fds[i], &info, &len);
 		if (err) {
 			p_err("can't get map info: %s", strerror(errno));
-			goto err_close;
-		}
-
-		err = btf__get_from_id(info.btf_id, &btf);
-		if (err) {
-			p_err("failed to get btf");
-			goto err_close;
+			return -1;
 		}
 
-		if (!btf)
+		if (!info.btf_id)
 			return 0;
 	}
 
 	return 1;
+}
 
-err_close:
-	for (; i < nb_fds; i++)
-		close(fds[i]);
-	return -1;
+static struct btf *btf_vmlinux;
+
+static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
+{
+	struct btf *btf = NULL;
+
+	if (info->btf_vmlinux_value_type_id) {
+		if (!btf_vmlinux) {
+			btf_vmlinux = libbpf_find_kernel_btf();
+			if (IS_ERR(btf_vmlinux))
+				p_err("failed to get kernel btf");
+		}
+		return btf_vmlinux;
+	} else if (info->btf_value_type_id) {
+		int err;
+
+		err = btf__get_from_id(info->btf_id, &btf);
+		if (err || !btf) {
+			p_err("failed to get btf");
+			btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH);
+		}
+	}
+
+	return btf;
+}
+
+static void free_map_kv_btf(struct btf *btf)
+{
+	if (!IS_ERR(btf) && btf != btf_vmlinux)
+		btf__free(btf);
+}
+
+static void free_btf_vmlinux(void)
+{
+	if (!IS_ERR(btf_vmlinux))
+		btf__free(btf_vmlinux);
 }
 
 static int
 map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
-	 bool enable_btf, bool show_header)
+	 bool show_header)
 {
 	void *key, *value, *prev_key;
 	unsigned int num_elems = 0;
@@ -962,18 +992,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
 
 	prev_key = NULL;
 
-	if (enable_btf) {
-		err = btf__get_from_id(info->btf_id, &btf);
-		if (err || !btf) {
-			/* enable_btf is true only if we've already checked
-			 * that all maps have BTF information.
-			 */
-			p_err("failed to get btf");
+	if (wtr) {
+		btf = get_map_kv_btf(info);
+		if (IS_ERR(btf)) {
+			err = PTR_ERR(btf);
 			goto exit_free;
 		}
-	}
 
-	if (wtr) {
 		if (show_header) {
 			jsonw_start_object(wtr);	/* map object */
 			show_map_header_json(info, wtr);
@@ -1012,7 +1037,7 @@ exit_free:
 	free(key);
 	free(value);
 	close(fd);
-	btf__free(btf);
+	free_map_kv_btf(btf);
 
 	return err;
 }
@@ -1021,7 +1046,7 @@ static int do_dump(int argc, char **argv)
 {
 	json_writer_t *wtr = NULL, *btf_wtr = NULL;
 	struct bpf_map_info info = {};
-	int nb_fds, i = 0, btf = 0;
+	int nb_fds, i = 0;
 	__u32 len = sizeof(info);
 	int *fds = NULL;
 	int err = -1;
@@ -1041,17 +1066,17 @@ static int do_dump(int argc, char **argv)
 	if (json_output) {
 		wtr = json_wtr;
 	} else {
-		btf = maps_have_btf(fds, nb_fds);
-		if (btf < 0)
+		int do_plain_btf;
+
+		do_plain_btf = maps_have_btf(fds, nb_fds);
+		if (do_plain_btf < 0)
 			goto exit_close;
-		if (btf) {
+
+		if (do_plain_btf) {
 			btf_wtr = get_btf_writer();
-			if (btf_wtr) {
-				wtr = btf_wtr;
-			} else {
+			wtr = btf_wtr;
+			if (!btf_wtr)
 				p_info("failed to create json writer for btf. falling back to plain output");
-				btf = 0;
-			}
 		}
 	}
 
@@ -1062,7 +1087,7 @@ static int do_dump(int argc, char **argv)
 			p_err("can't get map info: %s", strerror(errno));
 			break;
 		}
-		err = map_dump(fds[i], &info, wtr, btf, nb_fds > 1);
+		err = map_dump(fds[i], &info, wtr, nb_fds > 1);
 		if (!wtr && i != nb_fds - 1)
 			printf("\n");
 
@@ -1073,13 +1098,14 @@ static int do_dump(int argc, char **argv)
 	if (wtr && nb_fds > 1)
 		jsonw_end_array(wtr);	/* root array */
 
-	if (btf)
+	if (btf_wtr)
 		jsonw_destroy(&btf_wtr);
 exit_close:
 	for (; i < nb_fds; i++)
 		close(fds[i]);
 exit_free:
 	free(fds);
+	free_btf_vmlinux();
 	return err;
 }
 
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 4c5531d1a450..d9b29c17fbb8 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -6,7 +6,7 @@
  */
 #include <errno.h>
 #include <fcntl.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include <poll.h>
 #include <signal.h>
 #include <stdbool.h>
@@ -21,7 +21,7 @@
 #include <sys/mman.h>
 #include <sys/syscall.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 #include <perf-sys.h>
 
 #include "main.h"
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index d93bee298e54..c5e3895b7c8b 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -7,7 +7,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <net/if.h>
 #include <linux/if.h>
 #include <linux/rtnetlink.h>
@@ -16,9 +17,8 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 
-#include <bpf.h>
-#include <nlattr.h>
-#include "libbpf_internal.h"
+#include "bpf/nlattr.h"
+#include "bpf/libbpf_internal.h"
 #include "main.h"
 #include "netlink_dumper.h"
 
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 550a0f537eed..5f65140b003b 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -3,11 +3,11 @@
 
 #include <stdlib.h>
 #include <string.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include <linux/rtnetlink.h>
 #include <linux/tc_act/tc_bpf.h>
 
-#include <nlattr.h>
+#include "bpf/nlattr.h"
 #include "main.h"
 #include "netlink_dumper.h"
 
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index b2046f33e23f..3341aa14acda 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -13,7 +13,7 @@
 #include <unistd.h>
 #include <ftw.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 47a61ac42dc0..a3521deca869 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -17,9 +17,9 @@
 #include <linux/err.h>
 #include <linux/sizes.h>
 
-#include <bpf.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 
 #include "cfg.h"
 #include "main.h"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 5b91ee65a080..8608cd68cdd0 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -7,7 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 
 #include "disasm.h"
 #include "json_writer.h"
diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore
new file mode 100644
index 000000000000..90a456a2a72f
--- /dev/null
+++ b/tools/bpf/runqslower/.gitignore
@@ -0,0 +1 @@
+/.output
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
new file mode 100644
index 000000000000..faf5418609ea
--- /dev/null
+++ b/tools/bpf/runqslower/Makefile
@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG := clang
+LLC := llc
+LLVM_STRIP := llvm-strip
+DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+LIBBPF_SRC := $(abspath ../../lib/bpf)
+BPFOBJ := $(OUTPUT)/libbpf.a
+BPF_INCLUDE := $(OUTPUT)
+INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+CFLAGS := -g -Wall
+
+# Try to detect best kernel BTF source
+KERNEL_REL := $(shell uname -r)
+VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL)
+VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword			       \
+					  $(wildcard $(VMLINUX_BTF_PATHS))))
+
+abs_out := $(abspath $(OUTPUT))
+ifeq ($(V),1)
+Q =
+msg =
+else
+Q = @
+msg = @printf '  %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
+endif
+
+.DELETE_ON_ERROR:
+
+.PHONY: all clean runqslower
+all: runqslower
+
+runqslower: $(OUTPUT)/runqslower
+
+clean:
+	$(call msg,CLEAN)
+	$(Q)rm -rf $(OUTPUT) runqslower
+
+$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+	$(call msg,BINARY,$@)
+	$(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@
+
+$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h	      \
+			$(OUTPUT)/runqslower.bpf.o
+
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
+	$(call msg,GEN-SKEL,$@)
+	$(Q)$(BPFTOOL) gen skeleton $< > $@
+
+$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
+	$(call msg,BPF,$@)
+	$(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES)			      \
+		 -c $(filter %.c,$^) -o $@ &&				      \
+	$(LLVM_STRIP) -g $@
+
+$(OUTPUT)/%.o: %.c | $(OUTPUT)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $(OUTPUT)
+
+$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
+	$(call msg,GEN,$@)
+	$(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
+		echo "Couldn't find kernel BTF; set VMLINUX_BTF to"	       \
+			"specify its location." >&2;			       \
+		exit 1;\
+	fi
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+
+$(BPFOBJ): | $(OUTPUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)			       \
+		    OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+
+$(DEFAULT_BPFTOOL):
+	$(Q)$(MAKE) $(submake_extras) -C ../bpftool			      \
+		    prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
new file mode 100644
index 000000000000..48a39f72fadf
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "runqslower.h"
+
+#define TASK_RUNNING 0
+
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+const volatile __u64 min_us = 0;
+const volatile pid_t targ_pid = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 10240);
+	__type(key, u32);
+	__type(value, u64);
+} start SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+} events SEC(".maps");
+
+/* record enqueue timestamp */
+__always_inline
+static int trace_enqueue(u32 tgid, u32 pid)
+{
+	u64 ts;
+
+	if (!pid || (targ_pid && targ_pid != pid))
+		return 0;
+
+	ts = bpf_ktime_get_ns();
+	bpf_map_update_elem(&start, &pid, &ts, 0);
+	return 0;
+}
+
+SEC("tp_btf/sched_wakeup")
+int handle__sched_wakeup(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_wakeup_new")
+int handle__sched_wakeup_new(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_switch")
+int handle__sched_switch(u64 *ctx)
+{
+	/* TP_PROTO(bool preempt, struct task_struct *prev,
+	 *	    struct task_struct *next)
+	 */
+	struct task_struct *prev = (struct task_struct *)ctx[1];
+	struct task_struct *next = (struct task_struct *)ctx[2];
+	struct event event = {};
+	u64 *tsp, delta_us;
+	long state;
+	u32 pid;
+
+	/* ivcsw: treat like an enqueue event and store timestamp */
+	if (prev->state == TASK_RUNNING)
+		trace_enqueue(prev->tgid, prev->pid);
+
+	pid = next->pid;
+
+	/* fetch timestamp and calculate delta */
+	tsp = bpf_map_lookup_elem(&start, &pid);
+	if (!tsp)
+		return 0;   /* missed enqueue */
+
+	delta_us = (bpf_ktime_get_ns() - *tsp) / 1000;
+	if (min_us && delta_us <= min_us)
+		return 0;
+
+	event.pid = pid;
+	event.delta_us = delta_us;
+	bpf_get_current_comm(&event.task, sizeof(event.task));
+
+	/* output */
+	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
+			      &event, sizeof(event));
+
+	bpf_map_delete_elem(&start, &pid);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c
new file mode 100644
index 000000000000..d89715844952
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+#include <argp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <time.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "runqslower.h"
+#include "runqslower.skel.h"
+
+struct env {
+	pid_t pid;
+	__u64 min_us;
+	bool verbose;
+} env = {
+	.min_us = 10000,
+};
+
+const char *argp_program_version = "runqslower 0.1";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"runqslower    Trace long process scheduling delays.\n"
+"              For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n"
+"\n"
+"This script traces high scheduling delays between tasks being\n"
+"ready to run and them running on CPU after that.\n"
+"\n"
+"USAGE: runqslower [-p PID] [min_us]\n"
+"\n"
+"EXAMPLES:\n"
+"    runqslower         # trace run queue latency higher than 10000 us (default)\n"
+"    runqslower 1000    # trace run queue latency higher than 1000 us\n"
+"    runqslower -p 123  # trace pid 123 only\n";
+
+static const struct argp_option opts[] = {
+	{ "pid", 'p', "PID", 0, "Process PID to trace"},
+	{ "verbose", 'v', NULL, 0, "Verbose debug output" },
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	static int pos_args;
+	int pid;
+	long long min_us;
+
+	switch (key) {
+	case 'v':
+		env.verbose = true;
+		break;
+	case 'p':
+		errno = 0;
+		pid = strtol(arg, NULL, 10);
+		if (errno || pid <= 0) {
+			fprintf(stderr, "Invalid PID: %s\n", arg);
+			argp_usage(state);
+		}
+		env.pid = pid;
+		break;
+	case ARGP_KEY_ARG:
+		if (pos_args++) {
+			fprintf(stderr,
+				"Unrecognized positional argument: %s\n", arg);
+			argp_usage(state);
+		}
+		errno = 0;
+		min_us = strtoll(arg, NULL, 10);
+		if (errno || min_us <= 0) {
+			fprintf(stderr, "Invalid delay (in us): %s\n", arg);
+			argp_usage(state);
+		}
+		env.min_us = min_us;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+int libbpf_print_fn(enum libbpf_print_level level,
+		    const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+	struct rlimit rlim_new = {
+		.rlim_cur	= RLIM_INFINITY,
+		.rlim_max	= RLIM_INFINITY,
+	};
+
+	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
+{
+	const struct event *e = data;
+	struct tm *tm;
+	char ts[32];
+	time_t t;
+
+	time(&t);
+	tm = localtime(&t);
+	strftime(ts, sizeof(ts), "%H:%M:%S", tm);
+	printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us);
+}
+
+void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
+{
+	printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu);
+}
+
+int main(int argc, char **argv)
+{
+	static const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+	};
+	struct perf_buffer_opts pb_opts;
+	struct perf_buffer *pb = NULL;
+	struct runqslower_bpf *obj;
+	int err;
+
+	err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+	if (err)
+		return err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	err = bump_memlock_rlimit();
+	if (err) {
+		fprintf(stderr, "failed to increase rlimit: %d", err);
+		return 1;
+	}
+
+	obj = runqslower_bpf__open();
+	if (!obj) {
+		fprintf(stderr, "failed to open and/or load BPF object\n");
+		return 1;
+	}
+
+	/* initialize global data (filtering options) */
+	obj->rodata->targ_pid = env.pid;
+	obj->rodata->min_us = env.min_us;
+
+	err = runqslower_bpf__load(obj);
+	if (err) {
+		fprintf(stderr, "failed to load BPF object: %d\n", err);
+		goto cleanup;
+	}
+
+	err = runqslower_bpf__attach(obj);
+	if (err) {
+		fprintf(stderr, "failed to attach BPF programs\n");
+		goto cleanup;
+	}
+
+	printf("Tracing run queue latency higher than %llu us\n", env.min_us);
+	printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
+
+	pb_opts.sample_cb = handle_event;
+	pb_opts.lost_cb = handle_lost_events;
+	pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+	err = libbpf_get_error(pb);
+	if (err) {
+		pb = NULL;
+		fprintf(stderr, "failed to open perf buffer: %d\n", err);
+		goto cleanup;
+	}
+
+	while ((err = perf_buffer__poll(pb, 100)) >= 0)
+		;
+	printf("Error polling perf buffer: %d\n", err);
+
+cleanup:
+	perf_buffer__free(pb);
+	runqslower_bpf__destroy(obj);
+
+	return err != 0;
+}
diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h
new file mode 100644
index 000000000000..9db225425e5f
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __RUNQSLOWER_H
+#define __RUNQSLOWER_H
+
+#define TASK_COMM_LEN 16
+
+struct event {
+	char task[TASK_COMM_LEN];
+	__u64 delta_us;
+	pid_t pid;
+};
+
+#endif /* __RUNQSLOWER_H */