Merge branch 'linus/master' into rdma.git for-next

rdma.git merge resolution for the 4.19 merge window

Conflicts:
 drivers/infiniband/core/rdma_core.c
   - Use the rdma code and revise with the new spelling for
     atomic_fetch_add_unless
 drivers/nvme/host/rdma.c
   - Replace max_sge with max_send_sge in new blk code
 drivers/nvme/target/rdma.c
   - Use the blk code and revise to use NULL for ib_post_recv when
     appropriate
   - Replace max_sge with max_recv_sge in new blk code
 net/rds/ib_send.c
   - Use the net code and revise to use NULL for ib_post_recv when
     appropriate

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

229 files changed, 15362 insertions, 718 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5072cbd15c82
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define ELOOP           249     /* Too many symbolic links encountered */
 #define ENOSYS          251     /* Function not implemented */
 
-#define ENOTSUP         252     /* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED      253     /* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED       ECANCELLED      /* SuSv3 and Solaris wants one 'L' */
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..64aaa3f5f36c 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB                ( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP               ( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN                 ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV         ( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW          ( 8*32+ 0) /* Intel TPR Shadow */
@@ -341,6 +342,7 @@
 #define X86_FEATURE_PCONFIG             (18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL           (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP         (18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D           (18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES   (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD      (18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -373,5 +375,6 @@
 #define X86_BUG_SPECTRE_V1              X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2              X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS       X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF                    X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore
new file mode 100644
index 000000000000..dfe2bd5a4b95
--- /dev/null
+++ b/tools/bpf/.gitignore
@@ -0,0 +1,5 @@
+FEATURE-DUMP.bpf
+bpf_asm
+bpf_dbg
+bpf_exp.yacc.*
+bpf_jit_disasm
diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers
new file mode 100644
index 000000000000..c34fea77f39f
--- /dev/null
+++ b/tools/bpf/Makefile.helpers
@@ -0,0 +1,59 @@
+ifndef allow-override
+  include ../scripts/Makefile.include
+  include ../scripts/utilities.mak
+else
+  # Assume Makefile.helpers is being run from bpftool/Documentation
+  # subdirectory. Go up two more directories to fetch bpf.h header and
+  # associated script.
+  UP2DIR := ../../
+endif
+
+INSTALL ?= install
+RM ?= rm -f
+RMDIR ?= rmdir --ignore-fail-on-non-empty
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+prefix ?= /usr/local
+mandir ?= $(prefix)/man
+man7dir = $(mandir)/man7
+
+HELPERS_RST = bpf-helpers.rst
+MAN7_RST = $(HELPERS_RST)
+
+_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
+DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+helpers: man7
+man7: $(DOC_MAN7)
+
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
+$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h
+        $(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@
+
+$(OUTPUT)%.7: $(OUTPUT)%.rst
+ifndef RST2MAN_DEP
+        $(error "rst2man not found, but required to generate man pages")
+endif
+        $(QUIET_GEN)rst2man $< > $@
+
+helpers-clean:
+        $(call QUIET_CLEAN, eBPF_helpers-manpage)
+        $(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+
+helpers-install: helpers
+        $(call QUIET_INSTALL, eBPF_helpers-manpage)
+        $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+        $(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+helpers-uninstall:
+        $(call QUIET_UNINST, eBPF_helpers-manpage)
+        $(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
+        $(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+
+.PHONY: helpers helpers-clean helpers-install helpers-uninstall
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index d7e678c2d396..67167e44b726 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,3 +1,5 @@
 *.d
 bpftool
+bpftool*.8
+bpf-helpers.*
 FEATURE-DUMP.bpftool
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index a9d47c1558bb..f7663a3e60c9 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -15,12 +15,15 @@ prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
 
-MAN8_RST = $(wildcard *.rst)
+# Load targets for building eBPF helpers man page.
+include ../../Makefile.helpers
+
+MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst))
 
 _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
 DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
 
-man: man8
+man: man8 helpers
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
@@ -31,16 +34,16 @@ ifndef RST2MAN_DEP
 endif
         $(QUIET_GEN)rst2man $< > $@
 
-clean:
+clean: helpers-clean
         $(call QUIET_CLEAN, Documentation)
         $(Q)$(RM) $(DOC_MAN8)
 
-install: man
+install: man helpers-install
         $(call QUIET_INSTALL, Documentation-man)
         $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir)
         $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir)
 
-uninstall:
+uninstall: helpers-uninstall
         $(call QUIET_UNINST, Documentation-man)
         $(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8))
         $(Q)$(RMDIR) $(DESTDIR)$(man8dir)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index 7b0e6d453e92..edbe81534c6d 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -15,12 +15,13 @@ SYNOPSIS
         *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
         *COMMANDS* :=
-        { **show** | **list** | **attach** | **detach** | **help** }
+        { **show** | **list** | **tree** | **attach** | **detach** | **help** }
 
 MAP COMMANDS
 =============
 
 |       **bpftool** **cgroup { show | list }** *CGROUP*
+|       **bpftool** **cgroup tree** [*CGROUP_ROOT*]
 |       **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 |       **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 |       **bpftool** **cgroup help**
@@ -39,6 +40,15 @@ DESCRIPTION
                   Output will start with program ID followed by attach type,
                   attach flags and program name.
 
+        **bpftool cgroup tree** [*CGROUP_ROOT*]
+                  Iterate over all cgroups in *CGROUP_ROOT* and list all
+                  attached programs. If *CGROUP_ROOT* is not specified,
+                  bpftool uses cgroup v2 mountpoint.
+
+                  The output is similar to the output of cgroup show/list
+                  commands: it starts with absolute cgroup path, followed by
+                  program ID, attach type, attach flags and program name.
+
         **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
                   Attach program *PROG* to the cgroup *CGROUP* with attach type
                   *ATTACH_TYPE* and optional *ATTACH_FLAGS*.
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 43d34a5c3ec5..64156a16d530 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,10 +24,20 @@ MAP COMMANDS
 |       **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |       **bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |       **bpftool** **prog pin** *PROG* *FILE*
-|       **bpftool** **prog load** *OBJ* *FILE*
+|       **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 |       **bpftool** **prog help**
 |
+|       *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
 |       *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+|       *TYPE* := {
+|               **socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
+|               **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** |
+|               **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
+|               **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
+|               **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
+|               **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+|       }
+
 
 DESCRIPTION
 ===========
@@ -64,8 +74,19 @@ DESCRIPTION
 
                   Note: *FILE* must be located in *bpffs* mount.
 
-        **bpftool prog load** *OBJ* *FILE*
+        **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
                   Load bpf program from binary *OBJ* and pin as *FILE*.
+                  **type** is optional, if not specified program type will be
+                  inferred from section names.
+                  By default bpftool will create new maps as declared in the ELF
+                  object being loaded.  **map** parameter allows for the reuse
+                  of existing maps.  It can be specified multiple times, each
+                  time for a different map.  *IDX* refers to index of the map
+                  to be replaced in the ELF file counting from 0, while *NAME*
+                  allows to replace a map by name.  *MAP* specifies the map to
+                  use, referring to it by **id** or through a **pinned** file.
+                  If **dev** *NAME* is specified program will be loaded onto
+                  given networking device (offload).
 
                   Note: *FILE* must be located in *bpffs* mount.
 
@@ -159,6 +180,14 @@ EXAMPLES
     mov    %rbx,0x0(%rbp)
     48 89 5d 00
 
+|
+| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
+| **# bpftool prog show pinned /sys/fs/bpf/xdp1**
+|   9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
+|       loaded_at 2018-06-25T16:17:31-0700  uid 0
+|       xlated 488B  jited 336B  memlock 4096B  map_ids 7
+| **# rm /sys/fs/bpf/xdp1**
+|
 
 SEE ALSO
 ========
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 892dbf095bff..74288a2197ab 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -23,10 +23,10 @@ endif
 
 LIBBPF = $(BPF_PATH)libbpf.a
 
-BPFTOOL_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion)
+BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion)
 
 $(LIBBPF): FORCE
-        $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
+        $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a
 
 $(LIBBPF)-clean:
         $(call QUIET_CLEAN, libbpf)
@@ -52,7 +52,7 @@ INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
@@ -75,6 +75,10 @@ ifeq ($(feature-disassembler-four-args), 1)
 CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
 endif
 
+ifeq ($(feature-reallocarray), 0)
+CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
 include $(wildcard $(OUTPUT)*.d)
 
 all: $(OUTPUT)bpftool
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 1e1083321643..598066c40191 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,35 @@ _bpftool_get_prog_tags()
         command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
 }
 
+_bpftool_get_obj_map_names()
+{
+    local obj
+
+    obj=$1
+
+    maps=$(objdump -j maps -t $obj 2>/dev/null | \
+        command awk '/g     . maps/ {print $NF}')
+
+    COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) )
+}
+
+_bpftool_get_obj_map_idxs()
+{
+    local obj
+
+    obj=$1
+
+    nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g     . maps')
+
+    COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) )
+}
+
+_sysfs_get_netdevs()
+{
+    COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
+        "$cur" ) )
+}
+
 # For bpftool map update: retrieve type of the map to update.
 _bpftool_map_update_map_type()
 {
@@ -153,6 +182,13 @@ _bpftool()
     local cur prev words objword
     _init_completion || return
 
+    # Deal with options
+    if [[ ${words[cword]} == -* ]]; then
+        local c='--version --json --pretty --bpffs'
+        COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+        return 0
+    fi
+
     # Deal with simplest keywords
     case $prev in
         help|hex|opcodes|visual)
@@ -172,20 +208,23 @@ _bpftool()
             ;;
     esac
 
-    # Search for object and command
-    local object command cmdword
-    for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
-        [[ -n $object ]] && command=${words[cmdword]} && break
-        [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+    # Remove all options so completions don't have to deal with them.
+    local i
+    for (( i=1; i < ${#words[@]}; )); do
+        if [[ ${words[i]::1} == - ]]; then
+            words=( "${words[@]:0:i}" "${words[@]:i+1}" )
+            [[ $i -le $cword ]] && cword=$(( cword - 1 ))
+        else
+            i=$(( ++i ))
+        fi
     done
+    cur=${words[cword]}
+    prev=${words[cword - 1]}
+
+    local object=${words[1]} command=${words[2]}
 
-    if [[ -z $object ]]; then
+    if [[ -z $object || $cword -eq 1 ]]; then
         case $cur in
-            -*)
-                local c='--version --json --pretty'
-                COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
-                return 0
-                ;;
             *)
                 COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
                     command sed \
@@ -204,12 +243,14 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            case $prev in
-                id)
-                    _bpftool_get_prog_ids
-                    return 0
-                    ;;
-            esac
+            if [[ $command != "load" ]]; then
+                case $prev in
+                    id)
+                        _bpftool_get_prog_ids
+                        return 0
+                        ;;
+                esac
+            fi
 
             local PROG_TYPE='id pinned tag'
             case $command in
@@ -252,8 +293,57 @@ _bpftool()
                     return 0
                     ;;
                 load)
-                    _filedir
-                    return 0
+                    local obj
+
+                    if [[ ${#words[@]} -lt 6 ]]; then
+                        _filedir
+                        return 0
+                    fi
+
+                    obj=${words[3]}
+
+                    if [[ ${words[-4]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+                        return 0
+                    fi
+                    if [[ ${words[-3]} == "map" ]]; then
+                        if [[ ${words[-2]} == "idx" ]]; then
+                            _bpftool_get_obj_map_idxs $obj
+                        elif [[ ${words[-2]} == "name" ]]; then
+                            _bpftool_get_obj_map_names $obj
+                        fi
+                        return 0
+                    fi
+                    if [[ ${words[-2]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) )
+                        return 0
+                    fi
+
+                    case $prev in
+                        type)
+                            COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+                                                   "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        pinned)
+                            _filedir
+                            return 0
+                            ;;
+                        dev)
+                            _sysfs_get_netdevs
+                            return 0
+                            ;;
+                        *)
+                            COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
+                            _bpftool_once_attr 'type'
+                            _bpftool_once_attr 'dev'
+                            return 0
+                            ;;
+                    esac
                     ;;
                 *)
                     [[ $prev == $object ]] && \
@@ -404,6 +494,10 @@ _bpftool()
                     _filedir
                     return 0
                     ;;
+                tree)
+                    _filedir
+                    return 0
+                    ;;
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -445,7 +539,7 @@ _bpftool()
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'help attach detach \
-                            show list' -- "$cur" ) )
+                            show list tree' -- "$cur" ) )
                     ;;
             esac
             ;;
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
new file mode 100644
index 000000000000..55bc512a1831
--- /dev/null
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <ctype.h>
+#include <stdio.h> /* for (FILE *) used by json_writer */
+#include <string.h>
+#include <asm/byteorder.h>
+#include <linux/bitops.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+
+#include "btf.h"
+#include "json_writer.h"
+#include "main.h"
+
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+        (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+                              __u8 bit_offset, const void *data);
+
+static void btf_dumper_ptr(const void *data, json_writer_t *jw,
+                           bool is_plain_text)
+{
+        if (is_plain_text)
+                jsonw_printf(jw, "%p", *(unsigned long *)data);
+        else
+                jsonw_printf(jw, "%u", *(unsigned long *)data);
+}
+
+static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
+                               const void *data)
+{
+        int actual_type_id;
+
+        actual_type_id = btf__resolve_type(d->btf, type_id);
+        if (actual_type_id < 0)
+                return actual_type_id;
+
+        return btf_dumper_do_type(d, actual_type_id, 0, data);
+}
+
+static void btf_dumper_enum(const void *data, json_writer_t *jw)
+{
+        jsonw_printf(jw, "%d", *(int *)data);
+}
+
+static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
+                            const void *data)
+{
+        const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+        struct btf_array *arr = (struct btf_array *)(t + 1);
+        long long elem_size;
+        int ret = 0;
+        __u32 i;
+
+        elem_size = btf__resolve_size(d->btf, arr->type);
+        if (elem_size < 0)
+                return elem_size;
+
+        jsonw_start_array(d->jw);
+        for (i = 0; i < arr->nelems; i++) {
+                ret = btf_dumper_do_type(d, arr->type, 0,
+                                         data + i * elem_size);
+                if (ret)
+                        break;
+        }
+
+        jsonw_end_array(d->jw);
+        return ret;
+}
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+                                const void *data, json_writer_t *jw,
+                                bool is_plain_text)
+{
+        int left_shift_bits, right_shift_bits;
+        int nr_bits = BTF_INT_BITS(int_type);
+        int total_bits_offset;
+        int bytes_to_copy;
+        int bits_to_copy;
+        __u64 print_num;
+
+        total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+        data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+        bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+        bits_to_copy = bit_offset + nr_bits;
+        bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
+
+        print_num = 0;
+        memcpy(&print_num, data, bytes_to_copy);
+#if defined(__BIG_ENDIAN_BITFIELD)
+        left_shift_bits = bit_offset;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+        left_shift_bits = 64 - bits_to_copy;
+#else
+#error neither big nor little endian
+#endif
+        right_shift_bits = 64 - nr_bits;
+
+        print_num <<= left_shift_bits;
+        print_num >>= right_shift_bits;
+        if (is_plain_text)
+                jsonw_printf(jw, "0x%llx", print_num);
+        else
+                jsonw_printf(jw, "%llu", print_num);
+}
+
+static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
+                          const void *data, json_writer_t *jw,
+                          bool is_plain_text)
+{
+        __u32 *int_type;
+        __u32 nr_bits;
+
+        int_type = (__u32 *)(t + 1);
+        nr_bits = BTF_INT_BITS(*int_type);
+        /* if this is bit field */
+        if (bit_offset || BTF_INT_OFFSET(*int_type) ||
+            BITS_PER_BYTE_MASKED(nr_bits)) {
+                btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+                                    is_plain_text);
+                return 0;
+        }
+
+        switch (BTF_INT_ENCODING(*int_type)) {
+        case 0:
+                if (BTF_INT_BITS(*int_type) == 64)
+                        jsonw_printf(jw, "%lu", *(__u64 *)data);
+                else if (BTF_INT_BITS(*int_type) == 32)
+                        jsonw_printf(jw, "%u", *(__u32 *)data);
+                else if (BTF_INT_BITS(*int_type) == 16)
+                        jsonw_printf(jw, "%hu", *(__u16 *)data);
+                else if (BTF_INT_BITS(*int_type) == 8)
+                        jsonw_printf(jw, "%hhu", *(__u8 *)data);
+                else
+                        btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+                                            is_plain_text);
+                break;
+        case BTF_INT_SIGNED:
+                if (BTF_INT_BITS(*int_type) == 64)
+                        jsonw_printf(jw, "%ld", *(long long *)data);
+                else if (BTF_INT_BITS(*int_type) == 32)
+                        jsonw_printf(jw, "%d", *(int *)data);
+                else if (BTF_INT_BITS(*int_type) == 16)
+                        jsonw_printf(jw, "%hd", *(short *)data);
+                else if (BTF_INT_BITS(*int_type) == 8)
+                        jsonw_printf(jw, "%hhd", *(char *)data);
+                else
+                        btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+                                            is_plain_text);
+                break;
+        case BTF_INT_CHAR:
+                if (isprint(*(char *)data))
+                        jsonw_printf(jw, "\"%c\"", *(char *)data);
+                else
+                        if (is_plain_text)
+                                jsonw_printf(jw, "0x%hhx", *(char *)data);
+                        else
+                                jsonw_printf(jw, "\"\\u00%02hhx\"",
+                                             *(char *)data);
+                break;
+        case BTF_INT_BOOL:
+                jsonw_bool(jw, *(int *)data);
+                break;
+        default:
+                /* shouldn't happen */
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
+static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
+                             const void *data)
+{
+        const struct btf_type *t;
+        struct btf_member *m;
+        const void *data_off;
+        int ret = 0;
+        int i, vlen;
+
+        t = btf__type_by_id(d->btf, type_id);
+        if (!t)
+                return -EINVAL;
+
+        vlen = BTF_INFO_VLEN(t->info);
+        jsonw_start_object(d->jw);
+        m = (struct btf_member *)(t + 1);
+
+        for (i = 0; i < vlen; i++) {
+                data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+                jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
+                ret = btf_dumper_do_type(d, m[i].type,
+                                         BITS_PER_BYTE_MASKED(m[i].offset),
+                                         data_off);
+                if (ret)
+                        break;
+        }
+
+        jsonw_end_object(d->jw);
+
+        return ret;
+}
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+                              __u8 bit_offset, const void *data)
+{
+        const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+
+        switch (BTF_INFO_KIND(t->info)) {
+        case BTF_KIND_INT:
+                return btf_dumper_int(t, bit_offset, data, d->jw,
+                                     d->is_plain_text);
+        case BTF_KIND_STRUCT:
+        case BTF_KIND_UNION:
+                return btf_dumper_struct(d, type_id, data);
+        case BTF_KIND_ARRAY:
+                return btf_dumper_array(d, type_id, data);
+        case BTF_KIND_ENUM:
+                btf_dumper_enum(data, d->jw);
+                return 0;
+        case BTF_KIND_PTR:
+                btf_dumper_ptr(data, d->jw, d->is_plain_text);
+                return 0;
+        case BTF_KIND_UNKN:
+                jsonw_printf(d->jw, "(unknown)");
+                return 0;
+        case BTF_KIND_FWD:
+                /* map key or value can't be forward */
+                jsonw_printf(d->jw, "(fwd-kind-invalid)");
+                return -EINVAL;
+        case BTF_KIND_TYPEDEF:
+        case BTF_KIND_VOLATILE:
+        case BTF_KIND_CONST:
+        case BTF_KIND_RESTRICT:
+                return btf_dumper_modifier(d, type_id, data);
+        default:
+                jsonw_printf(d->jw, "(unsupported-kind");
+                return -EINVAL;
+        }
+}
+
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+                    const void *data)
+{
+        return btf_dumper_do_type(d, type_id, 0, data);
+}
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 16bee011e16c..ee7a9765c6b3 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -2,7 +2,12 @@
 // Copyright (C) 2017 Facebook
 // Author: Roman Gushchin <guro@fb.com>
 
+#define _XOPEN_SOURCE 500
+#include <errno.h>
 #include <fcntl.h>
+#include <ftw.h>
+#include <mntent.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/stat.h>
@@ -53,7 +58,8 @@ static enum bpf_attach_type parse_attach_type(const char *str)
 }
 
 static int show_bpf_prog(int id, const char *attach_type_str,
-                         const char *attach_flags_str)
+                         const char *attach_flags_str,
+                         int level)
 {
         struct bpf_prog_info info = {};
         __u32 info_len = sizeof(info);
@@ -78,7 +84,8 @@ static int show_bpf_prog(int id, const char *attach_type_str,
                 jsonw_string_field(json_wtr, "name", info.name);
                 jsonw_end_object(json_wtr);
         } else {
-                printf("%-8u %-15s %-15s %-15s\n", info.id,
+                printf("%s%-8u %-15s %-15s %-15s\n", level ? "    " : "",
+                       info.id,
                        attach_type_str,
                        attach_flags_str,
                        info.name);
@@ -88,7 +95,20 @@ static int show_bpf_prog(int id, const char *attach_type_str,
         return 0;
 }
 
-static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+{
+        __u32 prog_cnt = 0;
+        int ret;
+
+        ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt);
+        if (ret)
+                return -1;
+
+        return prog_cnt;
+}
+
+static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+                                   int level)
 {
         __u32 prog_ids[1024] = {0};
         char *attach_flags_str;
@@ -123,7 +143,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
 
         for (iter = 0; iter < prog_cnt; iter++)
                 show_bpf_prog(prog_ids[iter], attach_type_strings[type],
-                              attach_flags_str);
+                              attach_flags_str, level);
 
         return 0;
 }
@@ -161,7 +181,7 @@ static int do_show(int argc, char **argv)
                  * If we were able to get the show for at least one
                  * attach type, let's return 0.
                  */
-                if (show_attached_bpf_progs(cgroup_fd, type) == 0)
+                if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0)
                         ret = 0;
         }
 
@@ -173,6 +193,143 @@ exit:
         return ret;
 }
 
+/*
+ * To distinguish nftw() errors and do_show_tree_fn() errors
+ * and avoid duplicating error messages, let's return -2
+ * from do_show_tree_fn() in case of error.
+ */
+#define NFTW_ERR                -1
+#define SHOW_TREE_FN_ERR        -2
+static int do_show_tree_fn(const char *fpath, const struct stat *sb,
+                           int typeflag, struct FTW *ftw)
+{
+        enum bpf_attach_type type;
+        bool skip = true;
+        int cgroup_fd;
+
+        if (typeflag != FTW_D)
+                return 0;
+
+        cgroup_fd = open(fpath, O_RDONLY);
+        if (cgroup_fd < 0) {
+                p_err("can't open cgroup %s: %s", fpath, strerror(errno));
+                return SHOW_TREE_FN_ERR;
+        }
+
+        for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+                int count = count_attached_bpf_progs(cgroup_fd, type);
+
+                if (count < 0 && errno != EINVAL) {
+                        p_err("can't query bpf programs attached to %s: %s",
+                              fpath, strerror(errno));
+                        close(cgroup_fd);
+                        return SHOW_TREE_FN_ERR;
+                }
+                if (count > 0) {
+                        skip = false;
+                        break;
+                }
+        }
+
+        if (skip) {
+                close(cgroup_fd);
+                return 0;
+        }
+
+        if (json_output) {
+                jsonw_start_object(json_wtr);
+                jsonw_string_field(json_wtr, "cgroup", fpath);
+                jsonw_name(json_wtr, "programs");
+                jsonw_start_array(json_wtr);
+        } else {
+                printf("%s\n", fpath);
+        }
+
+        for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
+                show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+
+        if (json_output) {
+                jsonw_end_array(json_wtr);
+                jsonw_end_object(json_wtr);
+        }
+
+        close(cgroup_fd);
+
+        return 0;
+}
+
+static char *find_cgroup_root(void)
+{
+        struct mntent *mnt;
+        FILE *f;
+
+        f = fopen("/proc/mounts", "r");
+        if (f == NULL)
+                return NULL;
+
+        while ((mnt = getmntent(f))) {
+                if (strcmp(mnt->mnt_type, "cgroup2") == 0) {
+                        fclose(f);
+                        return strdup(mnt->mnt_dir);
+                }
+        }
+
+        fclose(f);
+        return NULL;
+}
+
+static int do_show_tree(int argc, char **argv)
+{
+        char *cgroup_root;
+        int ret;
+
+        switch (argc) {
+        case 0:
+                cgroup_root = find_cgroup_root();
+                if (!cgroup_root) {
+                        p_err("cgroup v2 isn't mounted");
+                        return -1;
+                }
+                break;
+        case 1:
+                cgroup_root = argv[0];
+                break;
+        default:
+                p_err("too many parameters for cgroup tree");
+                return -1;
+        }
+
+
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        else
+                printf("%s\n"
+                       "%-8s %-15s %-15s %-15s\n",
+                       "CgroupPath",
+                       "ID", "AttachType", "AttachFlags", "Name");
+
+        switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) {
+        case NFTW_ERR:
+                p_err("can't iterate over %s: %s", cgroup_root,
+                      strerror(errno));
+                ret = -1;
+                break;
+        case SHOW_TREE_FN_ERR:
+                ret = -1;
+                break;
+        default:
+                ret = 0;
+        }
+
+        if (json_output)
+                jsonw_end_array(json_wtr);
+
+        if (argc == 0)
+                free(cgroup_root);
+
+        return ret;
+}
+
 static int do_attach(int argc, char **argv)
 {
         enum bpf_attach_type attach_type;
@@ -289,6 +446,7 @@ static int do_help(int argc, char **argv)
 
         fprintf(stderr,
                 "Usage: %s %s { show | list } CGROUP\n"
+                "       %s %s tree [CGROUP_ROOT]\n"
                 "       %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n"
                 "       %s %s detach CGROUP ATTACH_TYPE PROG\n"
                 "       %s %s help\n"
@@ -298,6 +456,7 @@ static int do_help(int argc, char **argv)
                 "       " HELP_SPEC_PROGRAM "\n"
                 "       " HELP_SPEC_OPTIONS "\n"
                 "",
+                bin_name, argv[-2],
                 bin_name, argv[-2], bin_name, argv[-2],
                 bin_name, argv[-2], bin_name, argv[-2]);
 
@@ -307,6 +466,7 @@ static int do_help(int argc, char **argv)
 static const struct cmd cmds[] = {
         { "show",       do_show },
         { "list",       do_show },
+        { "tree",       do_show_tree },
         { "attach",     do_attach },
         { "detach",     do_detach },
         { "help",       do_help },
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 3f140eff039f..b3a0709ea7ed 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index eea7f14355f3..d15a62be6cf0 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <bfd.h>
 #include <ctype.h>
 #include <errno.h>
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 63fdb310b9a4..238e734d75b3 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #ifndef __BPF_TOOL_H
 #define __BPF_TOOL_H
 
@@ -44,6 +42,7 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/hashtable.h>
+#include <tools/libc_compat.h>
 
 #include "json_writer.h"
 
@@ -52,6 +51,21 @@
 #define NEXT_ARG()      ({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()     ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()       ({ p_err("what is '%s'?", *argv); -1; })
+#define GET_ARG()       ({ argc--; *argv++; })
+#define REQ_ARGS(cnt)                                                   \
+        ({                                                              \
+                int _cnt = (cnt);                                       \
+                bool _res;                                              \
+                                                                        \
+                if (argc < _cnt) {                                      \
+                        p_err("'%s' needs at least %d arguments, %d found", \
+                              argv[-1], _cnt, argc);                    \
+                        _res = false;                                   \
+                } else {                                                \
+                        _res = true;                                    \
+                }                                                       \
+                _res;                                                   \
+        })
 
 #define ERR_MAX_LEN     1024
 
@@ -61,6 +75,8 @@
         "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS                                               \
         "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+#define HELP_SPEC_MAP                                                   \
+        "MAP := { id MAP_ID | pinned FILE }"
 
 enum bpf_obj_type {
         BPF_OBJ_UNKNOWN,
@@ -122,6 +138,7 @@ int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
 
 int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
@@ -133,4 +150,19 @@ unsigned int get_page_size(void);
 unsigned int get_possible_cpus(void);
 const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
 
+struct btf_dumper {
+        const struct btf *btf;
+        json_writer_t *jw;
+        bool is_plain_text;
+};
+
+/* btf_dumper_type - print data along with type information
+ * @d: an instance containing context for dumping types
+ * @type_id: index in btf->types array. this points to the type to be dumped
+ * @data: pointer the actual data, i.e. the values to be printed
+ *
+ * Returns zero on success and negative error code otherwise
+ */
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+                    const void *data);
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index f74a8bcbda87..b2ec20e562bd 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -31,11 +31,10 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdio.h>
@@ -47,6 +46,8 @@
 
 #include <bpf.h>
 
+#include "btf.h"
+#include "json_writer.h"
 #include "main.h"
 
 static const char * const map_type_name[] = {
@@ -68,6 +69,7 @@ static const char * const map_type_name[] = {
         [BPF_MAP_TYPE_SOCKMAP]          = "sockmap",
         [BPF_MAP_TYPE_CPUMAP]           = "cpumap",
         [BPF_MAP_TYPE_SOCKHASH]         = "sockhash",
+        [BPF_MAP_TYPE_CGROUP_STORAGE]   = "cgroup_storage",
 };
 
 static bool map_is_per_cpu(__u32 type)
@@ -97,7 +99,7 @@ static void *alloc_value(struct bpf_map_info *info)
                 return malloc(info->value_size);
 }
 
-static int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv)
 {
         int fd;
 
@@ -152,8 +154,109 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
         return fd;
 }
 
+static int do_dump_btf(const struct btf_dumper *d,
+                       struct bpf_map_info *map_info, void *key,
+                       void *value)
+{
+        int ret;
+
+        /* start of key-value pair */
+        jsonw_start_object(d->jw);
+
+        jsonw_name(d->jw, "key");
+
+        ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+        if (ret)
+                goto err_end_obj;
+
+        jsonw_name(d->jw, "value");
+
+        ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+
+err_end_obj:
+        /* end of key-value pair */
+        jsonw_end_object(d->jw);
+
+        return ret;
+}
+
+static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
+{
+        struct bpf_btf_info btf_info = { 0 };
+        __u32 len = sizeof(btf_info);
+        __u32 last_size;
+        int btf_fd;
+        void *ptr;
+        int err;
+
+        err = 0;
+        *btf = NULL;
+        btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
+        if (btf_fd < 0)
+                return 0;
+
+        /* we won't know btf_size until we call bpf_obj_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.
+         */
+        btf_info.btf_size = 4096;
+        last_size = btf_info.btf_size;
+        ptr = malloc(last_size);
+        if (!ptr) {
+                err = -ENOMEM;
+                goto exit_free;
+        }
+
+        bzero(ptr, last_size);
+        btf_info.btf = ptr_to_u64(ptr);
+        err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+        if (!err && btf_info.btf_size > last_size) {
+                void *temp_ptr;
+
+                last_size = btf_info.btf_size;
+                temp_ptr = realloc(ptr, last_size);
+                if (!temp_ptr) {
+                        err = -ENOMEM;
+                        goto exit_free;
+                }
+                ptr = temp_ptr;
+                bzero(ptr, last_size);
+                btf_info.btf = ptr_to_u64(ptr);
+                err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+        }
+
+        if (err || btf_info.btf_size > last_size) {
+                err = errno;
+                goto exit_free;
+        }
+
+        *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+        if (IS_ERR(*btf)) {
+                err = PTR_ERR(*btf);
+                *btf = NULL;
+        }
+
+exit_free:
+        close(btf_fd);
+        free(ptr);
+
+        return err;
+}
+
+static json_writer_t *get_btf_writer(void)
+{
+        json_writer_t *jw = jsonw_new(stdout);
+
+        if (!jw)
+                return NULL;
+        jsonw_pretty(jw, true);
+
+        return jw;
+}
+
 static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
-                             unsigned char *value)
+                             unsigned char *value, struct btf *btf)
 {
         jsonw_start_object(json_wtr);
 
@@ -162,6 +265,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
                 print_hex_data_json(key, info->key_size);
                 jsonw_name(json_wtr, "value");
                 print_hex_data_json(value, info->value_size);
+                if (btf) {
+                        struct btf_dumper d = {
+                                .btf = btf,
+                                .jw = json_wtr,
+                                .is_plain_text = false,
+                        };
+
+                        jsonw_name(json_wtr, "formatted");
+                        do_dump_btf(&d, info, key, value);
+                }
         } else {
                 unsigned int i, n, step;
 
@@ -514,10 +627,12 @@ static int do_show(int argc, char **argv)
 
 static int do_dump(int argc, char **argv)
 {
+        struct bpf_map_info info = {};
         void *key, *value, *prev_key;
         unsigned int num_elems = 0;
-        struct bpf_map_info info = {};
         __u32 len = sizeof(info);
+        json_writer_t *btf_wtr;
+        struct btf *btf = NULL;
         int err;
         int fd;
 
@@ -543,8 +658,27 @@ static int do_dump(int argc, char **argv)
         }
 
         prev_key = NULL;
+
+        err = get_btf(&info, &btf);
+        if (err) {
+                p_err("failed to get btf");
+                goto exit_free;
+        }
+
         if (json_output)
                 jsonw_start_array(json_wtr);
+        else
+                if (btf) {
+                        btf_wtr = get_btf_writer();
+                        if (!btf_wtr) {
+                                p_info("failed to create json writer for btf. falling back to plain output");
+                                btf__free(btf);
+                                btf = NULL;
+                        } else {
+                                jsonw_start_array(btf_wtr);
+                        }
+                }
+
         while (true) {
                 err = bpf_map_get_next_key(fd, prev_key, key);
                 if (err) {
@@ -555,9 +689,19 @@ static int do_dump(int argc, char **argv)
 
                 if (!bpf_map_lookup_elem(fd, key, value)) {
                         if (json_output)
-                                print_entry_json(&info, key, value);
+                                print_entry_json(&info, key, value, btf);
                         else
-                                print_entry_plain(&info, key, value);
+                                if (btf) {
+                                        struct btf_dumper d = {
+                                                .btf = btf,
+                                                .jw = btf_wtr,
+                                                .is_plain_text = true,
+                                        };
+
+                                        do_dump_btf(&d, &info, key, value);
+                                } else {
+                                        print_entry_plain(&info, key, value);
+                                }
                 } else {
                         if (json_output) {
                                 jsonw_name(json_wtr, "key");
@@ -580,14 +724,19 @@ static int do_dump(int argc, char **argv)
 
         if (json_output)
                 jsonw_end_array(json_wtr);
-        else
+        else if (btf) {
+                jsonw_end_array(btf_wtr);
+                jsonw_destroy(&btf_wtr);
+        } else {
                 printf("Found %u element%s\n", num_elems,
                        num_elems != 1 ? "s" : "");
+        }
 
 exit_free:
         free(key);
         free(value);
         close(fd);
+        btf__free(btf);
 
         return err;
 }
@@ -643,6 +792,8 @@ static int do_lookup(int argc, char **argv)
 {
         struct bpf_map_info info = {};
         __u32 len = sizeof(info);
+        json_writer_t *btf_wtr;
+        struct btf *btf = NULL;
         void *key, *value;
         int err;
         int fd;
@@ -667,27 +818,60 @@ static int do_lookup(int argc, char **argv)
                 goto exit_free;
 
         err = bpf_map_lookup_elem(fd, key, value);
-        if (!err) {
-                if (json_output)
-                        print_entry_json(&info, key, value);
-                else
+        if (err) {
+                if (errno == ENOENT) {
+                        if (json_output) {
+                                jsonw_null(json_wtr);
+                        } else {
+                                printf("key:\n");
+                                fprint_hex(stdout, key, info.key_size, " ");
+                                printf("\n\nNot found\n");
+                        }
+                } else {
+                        p_err("lookup failed: %s", strerror(errno));
+                }
+
+                goto exit_free;
+        }
+
+        /* here means bpf_map_lookup_elem() succeeded */
+        err = get_btf(&info, &btf);
+        if (err) {
+                p_err("failed to get btf");
+                goto exit_free;
+        }
+
+        if (json_output) {
+                print_entry_json(&info, key, value, btf);
+        } else if (btf) {
+                /* if here json_wtr wouldn't have been initialised,
+                 * so let's create separate writer for btf
+                 */
+                btf_wtr = get_btf_writer();
+                if (!btf_wtr) {
+                        p_info("failed to create json writer for btf. falling back to plain output");
+                        btf__free(btf);
+                        btf = NULL;
                         print_entry_plain(&info, key, value);
-        } else if (errno == ENOENT) {
-                if (json_output) {
-                        jsonw_null(json_wtr);
                 } else {
-                        printf("key:\n");
-                        fprint_hex(stdout, key, info.key_size, " ");
-                        printf("\n\nNot found\n");
+                        struct btf_dumper d = {
+                                .btf = btf,
+                                .jw = btf_wtr,
+                                .is_plain_text = true,
+                        };
+
+                        do_dump_btf(&d, &info, key, value);
+                        jsonw_destroy(&btf_wtr);
                 }
         } else {
-                p_err("lookup failed: %s", strerror(errno));
+                print_entry_plain(&info, key, value);
         }
 
 exit_free:
         free(key);
         free(value);
         close(fd);
+        btf__free(btf);
 
         return err;
 }
@@ -830,7 +1014,7 @@ static int do_help(int argc, char **argv)
                 "       %s %s event_pipe MAP [cpu N index M]\n"
                 "       %s %s help\n"
                 "\n"
-                "       MAP := { id MAP_ID | pinned FILE }\n"
+                "       " HELP_SPEC_MAP "\n"
                 "       DATA := { [hex] BYTES }\n"
                 "       " HELP_SPEC_PROGRAM "\n"
                 "       VALUE := { DATA | MAP | PROG }\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 959aa53ab678..dce960d22106 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -31,8 +31,7 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
+#define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
 #include <stdarg.h>
@@ -41,9 +40,12 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <net/if.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include <linux/err.h>
+
 #include <bpf.h>
 #include <libbpf.h>
 
@@ -681,31 +683,247 @@ static int do_pin(int argc, char **argv)
         return err;
 }
 
+struct map_replace {
+        int idx;
+        int fd;
+        char *name;
+};
+
+int map_replace_compar(const void *p1, const void *p2)
+{
+        const struct map_replace *a = p1, *b = p2;
+
+        return a->idx - b->idx;
+}
+
 static int do_load(int argc, char **argv)
 {
+        enum bpf_attach_type expected_attach_type;
+        struct bpf_object_open_attr attr = {
+                .prog_type      = BPF_PROG_TYPE_UNSPEC,
+        };
+        struct map_replace *map_replace = NULL;
+        unsigned int old_map_fds = 0;
+        struct bpf_program *prog;
         struct bpf_object *obj;
-        int prog_fd;
-
-        if (argc != 2)
-                usage();
+        struct bpf_map *map;
+        const char *pinfile;
+        unsigned int i, j;
+        __u32 ifindex = 0;
+        int idx, err;
 
-        if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
-                p_err("failed to load program");
+        if (!REQ_ARGS(2))
                 return -1;
+        attr.file = GET_ARG();
+        pinfile = GET_ARG();
+
+        while (argc) {
+                if (is_prefix(*argv, "type")) {
+                        char *type;
+
+                        NEXT_ARG();
+
+                        if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+                                p_err("program type already specified");
+                                goto err_free_reuse_maps;
+                        }
+                        if (!REQ_ARGS(1))
+                                goto err_free_reuse_maps;
+
+                        /* Put a '/' at the end of type to appease libbpf */
+                        type = malloc(strlen(*argv) + 2);
+                        if (!type) {
+                                p_err("mem alloc failed");
+                                goto err_free_reuse_maps;
+                        }
+                        *type = 0;
+                        strcat(type, *argv);
+                        strcat(type, "/");
+
+                        err = libbpf_prog_type_by_name(type, &attr.prog_type,
+                                                       &expected_attach_type);
+                        free(type);
+                        if (err < 0) {
+                                p_err("unknown program type '%s'", *argv);
+                                goto err_free_reuse_maps;
+                        }
+                        NEXT_ARG();
+                } else if (is_prefix(*argv, "map")) {
+                        char *endptr, *name;
+                        int fd;
+
+                        NEXT_ARG();
+
+                        if (!REQ_ARGS(4))
+                                goto err_free_reuse_maps;
+
+                        if (is_prefix(*argv, "idx")) {
+                                NEXT_ARG();
+
+                                idx = strtoul(*argv, &endptr, 0);
+                                if (*endptr) {
+                                        p_err("can't parse %s as IDX", *argv);
+                                        goto err_free_reuse_maps;
+                                }
+                                name = NULL;
+                        } else if (is_prefix(*argv, "name")) {
+                                NEXT_ARG();
+
+                                name = *argv;
+                                idx = -1;
+                        } else {
+                                p_err("expected 'idx' or 'name', got: '%s'?",
+                                      *argv);
+                                goto err_free_reuse_maps;
+                        }
+                        NEXT_ARG();
+
+                        fd = map_parse_fd(&argc, &argv);
+                        if (fd < 0)
+                                goto err_free_reuse_maps;
+
+                        map_replace = reallocarray(map_replace, old_map_fds + 1,
+                                                   sizeof(*map_replace));
+                        if (!map_replace) {
+                                p_err("mem alloc failed");
+                                goto err_free_reuse_maps;
+                        }
+                        map_replace[old_map_fds].idx = idx;
+                        map_replace[old_map_fds].name = name;
+                        map_replace[old_map_fds].fd = fd;
+                        old_map_fds++;
+                } else if (is_prefix(*argv, "dev")) {
+                        NEXT_ARG();
+
+                        if (ifindex) {
+                                p_err("offload device already specified");
+                                goto err_free_reuse_maps;
+                        }
+                        if (!REQ_ARGS(1))
+                                goto err_free_reuse_maps;
+
+                        ifindex = if_nametoindex(*argv);
+                        if (!ifindex) {
+                                p_err("unrecognized netdevice '%s': %s",
+                                      *argv, strerror(errno));
+                                goto err_free_reuse_maps;
+                        }
+                        NEXT_ARG();
+                } else {
+                        p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
+                              *argv);
+                        goto err_free_reuse_maps;
+                }
+        }
+
+        obj = bpf_object__open_xattr(&attr);
+        if (IS_ERR_OR_NULL(obj)) {
+                p_err("failed to open object file");
+                goto err_free_reuse_maps;
+        }
+
+        prog = bpf_program__next(NULL, obj);
+        if (!prog) {
+                p_err("object file doesn't contain any bpf program");
+                goto err_close_obj;
+        }
+
+        bpf_program__set_ifindex(prog, ifindex);
+        if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+                const char *sec_name = bpf_program__title(prog, false);
+
+                err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
+                                               &expected_attach_type);
+                if (err < 0) {
+                        p_err("failed to guess program type based on section name %s\n",
+                              sec_name);
+                        goto err_close_obj;
+                }
+        }
+        bpf_program__set_type(prog, attr.prog_type);
+        bpf_program__set_expected_attach_type(prog, expected_attach_type);
+
+        qsort(map_replace, old_map_fds, sizeof(*map_replace),
+              map_replace_compar);
+
+        /* After the sort maps by name will be first on the list, because they
+         * have idx == -1.  Resolve them.
+         */
+        j = 0;
+        while (j < old_map_fds && map_replace[j].name) {
+                i = 0;
+                bpf_map__for_each(map, obj) {
+                        if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
+                                map_replace[j].idx = i;
+                                break;
+                        }
+                        i++;
+                }
+                if (map_replace[j].idx == -1) {
+                        p_err("unable to find map '%s'", map_replace[j].name);
+                        goto err_close_obj;
+                }
+                j++;
+        }
+        /* Resort if any names were resolved */
+        if (j)
+                qsort(map_replace, old_map_fds, sizeof(*map_replace),
+                      map_replace_compar);
+
+        /* Set ifindex and name reuse */
+        j = 0;
+        idx = 0;
+        bpf_map__for_each(map, obj) {
+                if (!bpf_map__is_offload_neutral(map))
+                        bpf_map__set_ifindex(map, ifindex);
+
+                if (j < old_map_fds && idx == map_replace[j].idx) {
+                        err = bpf_map__reuse_fd(map, map_replace[j++].fd);
+                        if (err) {
+                                p_err("unable to set up map reuse: %d", err);
+                                goto err_close_obj;
+                        }
+
+                        /* Next reuse wants to apply to the same map */
+                        if (j < old_map_fds && map_replace[j].idx == idx) {
+                                p_err("replacement for map idx %d specified more than once",
+                                      idx);
+                                goto err_close_obj;
+                        }
+                }
+
+                idx++;
+        }
+        if (j < old_map_fds) {
+                p_err("map idx '%d' not used", map_replace[j].idx);
+                goto err_close_obj;
+        }
+
+        err = bpf_object__load(obj);
+        if (err) {
+                p_err("failed to load object file");
+                goto err_close_obj;
         }
 
-        if (do_pin_fd(prog_fd, argv[1]))
+        if (do_pin_fd(bpf_program__fd(prog), pinfile))
                 goto err_close_obj;
 
         if (json_output)
                 jsonw_null(json_wtr);
 
         bpf_object__close(obj);
+        for (i = 0; i < old_map_fds; i++)
+                close(map_replace[i].fd);
+        free(map_replace);
 
         return 0;
 
 err_close_obj:
         bpf_object__close(obj);
+err_free_reuse_maps:
+        for (i = 0; i < old_map_fds; i++)
+                close(map_replace[i].fd);
+        free(map_replace);
         return -1;
 }
 
@@ -721,10 +939,19 @@ static int do_help(int argc, char **argv)
                 "       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
                 "       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
                 "       %s %s pin   PROG FILE\n"
-                "       %s %s load  OBJ  FILE\n"
+                "       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
+                "                         [map { idx IDX | name NAME } MAP]\n"
                 "       %s %s help\n"
                 "\n"
+                "       " HELP_SPEC_MAP "\n"
                 "       " HELP_SPEC_PROGRAM "\n"
+                "       TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
+                "                 tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
+                "                 cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
+                "                 lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+                "                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
+                "                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
+                "                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
                 "       " HELP_SPEC_OPTIONS "\n"
                 "",
                 bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index b97f1da60dd1..3284759df98a 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -35,6 +35,7 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#define _GNU_SOURCE
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -66,9 +67,8 @@ void kernel_syms_load(struct dump_data *dd)
         while (!feof(fp)) {
                 if (!fgets(buff, sizeof(buff), fp))
                         break;
-                tmp = realloc(dd->sym_mapping,
-                              (dd->sym_count + 1) *
-                              sizeof(*dd->sym_mapping));
+                tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
+                                   sizeof(*dd->sym_mapping));
                 if (!tmp) {
 out:
                         free(dd->sym_mapping);
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 950c1504ca37..9ec01f4454f9 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 5edf65e684ab..727050c40f09 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE
         $(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-        $(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
+        $(QUIET_LINK)$(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ $<
 
 FORCE:
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 5b6dda3b1ca8..f216b2f5c3d7 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -57,6 +57,7 @@ FEATURE_TESTS_BASIC :=                  \
         libunwind-aarch64               \
         pthread-attr-setaffinity-np     \
         pthread-barrier                 \
+        reallocarray                    \
         stackprotector-all              \
         timerfd                         \
         libdw-dwarf-unwind              \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dac9563b5470..0516259be70f 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -14,6 +14,7 @@ FILES=                                          \
          test-libaudit.bin                      \
          test-libbfd.bin                        \
          test-disassembler-four-args.bin        \
+         test-reallocarray.bin                  \
          test-liberty.bin                       \
          test-liberty-z.bin                     \
          test-cplus-demangle.bin                \
@@ -204,6 +205,9 @@ $(OUTPUT)test-libbfd.bin:
 $(OUTPUT)test-disassembler-four-args.bin:
         $(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
 
+$(OUTPUT)test-reallocarray.bin:
+        $(BUILD)
+
 $(OUTPUT)test-liberty.bin:
         $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
diff --git a/tools/build/feature/test-reallocarray.c b/tools/build/feature/test-reallocarray.c
new file mode 100644
index 000000000000..8170de35150d
--- /dev/null
+++ b/tools/build/feature/test-reallocarray.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <stdlib.h>
+
+int main(void)
+{
+        return !!reallocarray(NULL, 1, 1);
+}
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 70fe61295733..0d35f18006a1 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -36,3 +36,7 @@
 #endif
 #define __printf(a, b)  __attribute__((format(printf, a, b)))
 #define __scanf(a, b)   __attribute__((format(scanf, a, b)))
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
new file mode 100644
index 000000000000..8712ff70995f
--- /dev/null
+++ b/tools/include/linux/overflow.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type)       (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({          \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        __builtin_add_overflow(__a, __b, __d);  \
+})
+
+#define check_sub_overflow(a, b, d) ({          \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        __builtin_sub_overflow(__a, __b, __d);  \
+})
+
+#define check_mul_overflow(a, b, d) ({          \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        __builtin_mul_overflow(__a, __b, __d);  \
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({     \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        *__d = __a + __b;                       \
+        *__d < __a;                             \
+})
+#define __unsigned_sub_overflow(a, b, d) ({     \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        *__d = __a - __b;                       \
+        __a < __b;                              \
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({             \
+        typeof(a) __a = (a);                            \
+        typeof(b) __b = (b);                            \
+        typeof(d) __d = (d);                            \
+        (void) (&__a == &__b);                          \
+        (void) (&__a == __d);                           \
+        *__d = __a * __b;                               \
+        __builtin_constant_p(__b) ?                     \
+          __b > 0 && __a > type_max(typeof(__a)) / __b : \
+          __a > 0 && __b > type_max(typeof(__b)) / __a;  \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({       \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        *__d = (u64)__a + (u64)__b;             \
+        (((~(__a ^ __b)) & (*__d ^ __a))        \
+                & type_min(typeof(__a))) != 0;  \
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({       \
+        typeof(a) __a = (a);                    \
+        typeof(b) __b = (b);                    \
+        typeof(d) __d = (d);                    \
+        (void) (&__a == &__b);                  \
+        (void) (&__a == __d);                   \
+        *__d = (u64)__a - (u64)__b;             \
+        ((((__a ^ __b)) & (*__d ^ __a))         \
+                & type_min(typeof(__a))) != 0;  \
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({                               \
+        typeof(a) __a = (a);                                            \
+        typeof(b) __b = (b);                                            \
+        typeof(d) __d = (d);                                            \
+        typeof(a) __tmax = type_max(typeof(a));                         \
+        typeof(a) __tmin = type_min(typeof(a));                         \
+        (void) (&__a == &__b);                                          \
+        (void) (&__a == __d);                                           \
+        *__d = (u64)__a * (u64)__b;                                     \
+        (__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||        \
+        (__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
+        (__b == (typeof(__b))-1 && __a == __tmin);                      \
+})
+
+
+#define check_add_overflow(a, b, d)                                     \
+        __builtin_choose_expr(is_signed_type(typeof(a)),                \
+                        __signed_add_overflow(a, b, d),                 \
+                        __unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d)                                     \
+        __builtin_choose_expr(is_signed_type(typeof(a)),                \
+                        __signed_sub_overflow(a, b, d),                 \
+                        __unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d)                                     \
+        __builtin_choose_expr(is_signed_type(typeof(a)),                \
+                        __signed_mul_overflow(a, b, d),                 \
+                        __unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+        size_t bytes;
+
+        if (check_mul_overflow(a, b, &bytes))
+                return SIZE_MAX;
+
+        return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+        size_t bytes;
+
+        if (check_mul_overflow(a, b, &bytes))
+                return SIZE_MAX;
+        if (check_mul_overflow(bytes, c, &bytes))
+                return SIZE_MAX;
+
+        return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+        size_t bytes;
+
+        if (check_mul_overflow(n, size, &bytes))
+                return SIZE_MAX;
+        if (check_add_overflow(bytes, c, &bytes))
+                return SIZE_MAX;
+
+        return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n)                                       \
+        __ab_c_size(n,                                                  \
+                    sizeof(*(p)->member) + __must_be_array((p)->member),\
+                    sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h
new file mode 100644
index 000000000000..664ced8cb1b0
--- /dev/null
+++ b/tools/include/tools/libc_compat.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+        size_t bytes;
+
+        if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+                return NULL;
+        return realloc(ptr, bytes);
+}
+#endif
+#endif
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 000000000000..42990676a55e
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+               compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+               compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+               compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+               compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+          compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+          compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+          compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+          compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+          compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+          compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+          compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+          compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+          compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+          compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+          compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+          compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+          compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+          compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at         264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+          compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+          compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+          compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b7db3261c62d..66917a4eba27 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
         __u8    data[0];        /* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+        __u64   cgroup_inode_id;        /* cgroup inode id */
+        __u32   attach_type;            /* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
         BPF_MAP_CREATE,
@@ -120,6 +125,8 @@ enum bpf_map_type {
         BPF_MAP_TYPE_CPUMAP,
         BPF_MAP_TYPE_XSKMAP,
         BPF_MAP_TYPE_SOCKHASH,
+        BPF_MAP_TYPE_CGROUP_STORAGE,
+        BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 };
 
 enum bpf_prog_type {
@@ -144,6 +151,7 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
         BPF_PROG_TYPE_LWT_SEG6LOCAL,
         BPF_PROG_TYPE_LIRC_MODE2,
+        BPF_PROG_TYPE_SK_REUSEPORT,
 };
 
 enum bpf_attach_type {
@@ -1371,6 +1379,20 @@ union bpf_attr {
  *              A 8-byte long non-decreasing number on success, or 0 if the
  *              socket field is missing inside *skb*.
  *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ *      Description
+ *              Equivalent to bpf_get_socket_cookie() helper that accepts
+ *              *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ *      Return
+ *              A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ *      Description
+ *              Equivalent to bpf_get_socket_cookie() helper that accepts
+ *              *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ *      Return
+ *              A 8-byte long non-decreasing number.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  *      Return
  *              The owner UID of the socket associated to *skb*. If the socket
@@ -1826,7 +1848,7 @@ union bpf_attr {
  *              A non-negative value equal to or less than *size* on success,
  *              or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  *      Description
  *              This helper is similar to **bpf_skb_load_bytes**\ () in that
  *              it provides an easy way to load *len* bytes from *offset*
@@ -1877,7 +1899,7 @@ union bpf_attr {
  *              * < 0 if any input argument is invalid
  *              *   0 on success (packet is forwarded, nexthop neighbor exists)
  *              * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
- *              *     packet is not forwarded or needs assist from full stack
+ *                packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *      Description
@@ -2033,7 +2055,6 @@ union bpf_attr {
  *              This helper is only available is the kernel was compiled with
  *              the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *              "**y**".
- *
  *      Return
  *              0
  *
@@ -2053,7 +2074,6 @@ union bpf_attr {
  *              This helper is only available is the kernel was compiled with
  *              the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *              "**y**".
- *
  *      Return
  *              0
  *
@@ -2073,10 +2093,54 @@ union bpf_attr {
  *      Return
  *              The id is returned or 0 in case the id could not be retrieved.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *      Description
+ *              Return id of cgroup v2 that is ancestor of cgroup associated
+ *              with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *              *ancestor_level* zero and each step down the hierarchy
+ *              increments the level. If *ancestor_level* == level of cgroup
+ *              associated with *skb*, then return value will be same as that
+ *              of **bpf_skb_cgroup_id**\ ().
+ *
+ *              The helper is useful to implement policies based on cgroups
+ *              that are upper in hierarchy than immediate cgroup associated
+ *              with *skb*.
+ *
+ *              The format of returned id and helper limitations are same as in
+ *              **bpf_skb_cgroup_id**\ ().
+ *      Return
+ *              The id is returned or 0 in case the id could not be retrieved.
+ *
  * u64 bpf_get_current_cgroup_id(void)
  *      Return
  *              A 64-bit integer containing the current cgroup id based
  *              on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ *      Description
+ *              Get the pointer to the local storage area.
+ *              The type and the size of the local storage is defined
+ *              by the *map* argument.
+ *              The *flags* meaning is specific for each map type,
+ *              and has to be 0 for cgroup local storage.
+ *
+ *              Depending on the bpf program type, a local storage area
+ *              can be shared between multiple instances of the bpf program,
+ *              running simultaneously.
+ *
+ *              A user should care about the synchronization by himself.
+ *              For example, by using the BPF_STX_XADD instruction to alter
+ *              the shared data.
+ *      Return
+ *              Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ *      Description
+ *              Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ *              It checks the selected sk is matching the incoming
+ *              request in the skb.
+ *      Return
+ *              0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -2159,7 +2223,10 @@ union bpf_attr {
         FN(rc_repeat),                  \
         FN(rc_keydown),                 \
         FN(skb_cgroup_id),              \
-        FN(get_current_cgroup_id),
+        FN(get_current_cgroup_id),      \
+        FN(get_local_storage),          \
+        FN(sk_select_reuseport),        \
+        FN(skb_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2376,6 +2443,30 @@ struct sk_msg_md {
         __u32 local_port;       /* stored in host byte order */
 };
 
+struct sk_reuseport_md {
+        /*
+         * Start of directly accessible data. It begins from
+         * the tcp/udp header.
+         */
+        void *data;
+        void *data_end;         /* End of directly accessible data */
+        /*
+         * Total length of packet (starting from the tcp/udp header).
+         * Note that the directly accessible bytes (data_end - data)
+         * could be less than this "len".  Those bytes could be
+         * indirectly read by a helper "bpf_skb_load_bytes()".
+         */
+        __u32 len;
+        /*
+         * Eth protocol in the mac header (network byte order). e.g.
+         * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+         */
+        __u32 eth_protocol;
+        __u32 ip_protocol;      /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+        __u32 bind_inany;       /* Is sock bound to an INANY address? */
+        __u32 hash;             /* A hash of the packet 4 tuples */
+};
+
 #define BPF_TAG_SIZE    8
 
 struct bpf_prog_info {
@@ -2557,6 +2648,9 @@ enum {
                                          * Arg1: old_state
                                          * Arg2: new_state
                                          */
+        BPF_SOCK_OPS_TCP_LISTEN_CB,     /* Called on listen(2), right after
+                                         * socket transition to LISTEN state.
+                                         */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the  BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ *              Definitions of the Internet Protocol.
+ *
+ * Version:     @(#)in.h        1.0.1   04/21/93
+ *
+ * Authors:     Original taken from the GNU Project <netinet/in.h> file.
+ *              Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,               /* Dummy protocol for TCP               */
+#define IPPROTO_IP              IPPROTO_IP
+  IPPROTO_ICMP = 1,             /* Internet Control Message Protocol    */
+#define IPPROTO_ICMP            IPPROTO_ICMP
+  IPPROTO_IGMP = 2,             /* Internet Group Management Protocol   */
+#define IPPROTO_IGMP            IPPROTO_IGMP
+  IPPROTO_IPIP = 4,             /* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP            IPPROTO_IPIP
+  IPPROTO_TCP = 6,              /* Transmission Control Protocol        */
+#define IPPROTO_TCP             IPPROTO_TCP
+  IPPROTO_EGP = 8,              /* Exterior Gateway Protocol            */
+#define IPPROTO_EGP             IPPROTO_EGP
+  IPPROTO_PUP = 12,             /* PUP protocol                         */
+#define IPPROTO_PUP             IPPROTO_PUP
+  IPPROTO_UDP = 17,             /* User Datagram Protocol               */
+#define IPPROTO_UDP             IPPROTO_UDP
+  IPPROTO_IDP = 22,             /* XNS IDP protocol                     */
+#define IPPROTO_IDP             IPPROTO_IDP
+  IPPROTO_TP = 29,              /* SO Transport Protocol Class 4        */
+#define IPPROTO_TP              IPPROTO_TP
+  IPPROTO_DCCP = 33,            /* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP            IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,            /* IPv6-in-IPv4 tunnelling              */
+#define IPPROTO_IPV6            IPPROTO_IPV6
+  IPPROTO_RSVP = 46,            /* RSVP Protocol                        */
+#define IPPROTO_RSVP            IPPROTO_RSVP
+  IPPROTO_GRE = 47,             /* Cisco GRE tunnels (rfc 1701,1702)    */
+#define IPPROTO_GRE             IPPROTO_GRE
+  IPPROTO_ESP = 50,             /* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP             IPPROTO_ESP
+  IPPROTO_AH = 51,              /* Authentication Header protocol       */
+#define IPPROTO_AH              IPPROTO_AH
+  IPPROTO_MTP = 92,             /* Multicast Transport Protocol         */
+#define IPPROTO_MTP             IPPROTO_MTP
+  IPPROTO_BEETPH = 94,          /* IP option pseudo header for BEET     */
+#define IPPROTO_BEETPH          IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,           /* Encapsulation Header                 */
+#define IPPROTO_ENCAP           IPPROTO_ENCAP
+  IPPROTO_PIM = 103,            /* Protocol Independent Multicast       */
+#define IPPROTO_PIM             IPPROTO_PIM
+  IPPROTO_COMP = 108,           /* Compression Header Protocol          */
+#define IPPROTO_COMP            IPPROTO_COMP
+  IPPROTO_SCTP = 132,           /* Stream Control Transport Protocol    */
+#define IPPROTO_SCTP            IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,        /* UDP-Lite (RFC 3828)                  */
+#define IPPROTO_UDPLITE         IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,           /* MPLS in IP (RFC 4023)                */
+#define IPPROTO_MPLS            IPPROTO_MPLS
+  IPPROTO_RAW = 255,            /* Raw IP packets                       */
+#define IPPROTO_RAW             IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+        __be32  s_addr;
+};
+#endif
+
+#define IP_TOS          1
+#define IP_TTL          2
+#define IP_HDRINCL      3
+#define IP_OPTIONS      4
+#define IP_ROUTER_ALERT 5
+#define IP_RECVOPTS     6
+#define IP_RETOPTS      7
+#define IP_PKTINFO      8
+#define IP_PKTOPTIONS   9
+#define IP_MTU_DISCOVER 10
+#define IP_RECVERR      11
+#define IP_RECVTTL      12
+#define IP_RECVTOS      13
+#define IP_MTU          14
+#define IP_FREEBIND     15
+#define IP_IPSEC_POLICY 16
+#define IP_XFRM_POLICY  17
+#define IP_PASSSEC      18
+#define IP_TRANSPARENT  19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS  IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM     23
+#define IP_BIND_ADDRESS_NO_PORT 24
+#define IP_RECVFRAGSIZE 25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT                0       /* Never send DF frames */
+#define IP_PMTUDISC_WANT                1       /* Use per route hints  */
+#define IP_PMTUDISC_DO                  2       /* Always DF            */
+#define IP_PMTUDISC_PROBE               3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE           4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT                5
+
+#define IP_MULTICAST_IF                 32
+#define IP_MULTICAST_TTL                33
+#define IP_MULTICAST_LOOP               34
+#define IP_ADD_MEMBERSHIP               35
+#define IP_DROP_MEMBERSHIP              36
+#define IP_UNBLOCK_SOURCE               37
+#define IP_BLOCK_SOURCE                 38
+#define IP_ADD_SOURCE_MEMBERSHIP        39
+#define IP_DROP_SOURCE_MEMBERSHIP       40
+#define IP_MSFILTER                     41
+#define MCAST_JOIN_GROUP                42
+#define MCAST_BLOCK_SOURCE              43
+#define MCAST_UNBLOCK_SOURCE            44
+#define MCAST_LEAVE_GROUP               45
+#define MCAST_JOIN_SOURCE_GROUP         46
+#define MCAST_LEAVE_SOURCE_GROUP        47
+#define MCAST_MSFILTER                  48
+#define IP_MULTICAST_ALL                49
+#define IP_UNICAST_IF                   50
+
+#define MCAST_EXCLUDE   0
+#define MCAST_INCLUDE   1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+        struct in_addr imr_multiaddr;   /* IP multicast address of group */
+        struct in_addr imr_interface;   /* local IP address of interface */
+};
+
+struct ip_mreqn {
+        struct in_addr  imr_multiaddr;          /* IP multicast address of group */
+        struct in_addr  imr_address;            /* local IP address of interface */
+        int             imr_ifindex;            /* Interface index */
+};
+
+struct ip_mreq_source {
+        __be32          imr_multiaddr;
+        __be32          imr_interface;
+        __be32          imr_sourceaddr;
+};
+
+struct ip_msfilter {
+        __be32          imsf_multiaddr;
+        __be32          imsf_interface;
+        __u32           imsf_fmode;
+        __u32           imsf_numsrc;
+        __be32          imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+        (sizeof(struct ip_msfilter) - sizeof(__u32) \
+        + (numsrc) * sizeof(__u32))
+
+struct group_req {
+        __u32                            gr_interface;  /* interface index */
+        struct __kernel_sockaddr_storage gr_group;      /* group address */
+};
+
+struct group_source_req {
+        __u32                            gsr_interface; /* interface index */
+        struct __kernel_sockaddr_storage gsr_group;     /* group address */
+        struct __kernel_sockaddr_storage gsr_source;    /* source address */
+};
+
+struct group_filter {
+        __u32                            gf_interface;  /* interface index */
+        struct __kernel_sockaddr_storage gf_group;      /* multicast address */
+        __u32                            gf_fmode;      /* filter mode */
+        __u32                            gf_numsrc;     /* number of sources */
+        struct __kernel_sockaddr_storage gf_slist[1];   /* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+        (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+        + (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+        int             ipi_ifindex;
+        struct in_addr  ipi_spec_dst;
+        struct in_addr  ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__   16              /* sizeof(struct sockaddr)      */
+struct sockaddr_in {
+  __kernel_sa_family_t  sin_family;     /* Address family               */
+  __be16                sin_port;       /* Port number                  */
+  struct in_addr        sin_addr;       /* Internet address             */
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char         __pad[__SOCK_SIZE__ - sizeof(short int) -
+                        sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero        __pad           /* for BSD UNIX comp. -FvK      */
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define IN_CLASSA(a)            ((((long int) (a)) & 0x80000000) == 0)
+#define IN_CLASSA_NET           0xff000000
+#define IN_CLASSA_NSHIFT        24
+#define IN_CLASSA_HOST          (0xffffffff & ~IN_CLASSA_NET)
+#define IN_CLASSA_MAX           128
+
+#define IN_CLASSB(a)            ((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define IN_CLASSB_NET           0xffff0000
+#define IN_CLASSB_NSHIFT        16
+#define IN_CLASSB_HOST          (0xffffffff & ~IN_CLASSB_NET)
+#define IN_CLASSB_MAX           65536
+
+#define IN_CLASSC(a)            ((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define IN_CLASSC_NET           0xffffff00
+#define IN_CLASSC_NSHIFT        8
+#define IN_CLASSC_HOST          (0xffffffff & ~IN_CLASSC_NET)
+
+#define IN_CLASSD(a)            ((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define IN_MULTICAST(a)         IN_CLASSD(a)
+#define IN_MULTICAST_NET        0xF0000000
+
+#define IN_EXPERIMENTAL(a)      ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_BADCLASS(a)          IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define INADDR_ANY              ((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define INADDR_BROADCAST        ((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define INADDR_NONE             ((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define IN_LOOPBACKNET          127
+
+/* Address to loopback in software to local host.  */
+#define INADDR_LOOPBACK         0x7f000001      /* 127.0.0.1   */
+#define IN_LOOPBACK(a)          ((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP     0xe0000000U     /* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP   0xe0000001U     /* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U     /* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU     /* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6070e655042d..13a861135127 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5390e7725e43..d49902e818b5 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
@@ -116,8 +116,8 @@ ifeq ($(feature-libelf-mmap), 1)
   override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
 endif
 
-ifeq ($(feature-libelf-getphdrnum), 1)
-  override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
+ifeq ($(feature-reallocarray), 0)
+  override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
 endif
 
 # Append required CFLAGS
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9ddc89dae962..60aa4ca8b2c5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -92,6 +92,7 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
         attr.btf_key_type_id = create_attr->btf_key_type_id;
         attr.btf_value_type_id = create_attr->btf_value_type_id;
         attr.map_ifindex = create_attr->map_ifindex;
+        attr.inner_map_fd = create_attr->inner_map_fd;
 
         return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 0639a30a457d..6f38164b2618 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -39,6 +39,7 @@ struct bpf_create_map_attr {
         __u32 btf_key_type_id;
         __u32 btf_value_type_id;
         __u32 map_ifindex;
+        __u32 inner_map_fd;
 };
 
 int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index c36a3a76986a..cf94b0770522 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -16,6 +16,11 @@
 
 #define BTF_MAX_NR_TYPES 65535
 
+#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
+                ((k) == BTF_KIND_VOLATILE) || \
+                ((k) == BTF_KIND_CONST) || \
+                ((k) == BTF_KIND_RESTRICT))
+
 static struct btf_type btf_void;
 
 struct btf {
@@ -32,14 +37,6 @@ struct btf {
         int fd;
 };
 
-static const char *btf_name_by_offset(const struct btf *btf, __u32 offset)
-{
-        if (offset < btf->hdr->str_len)
-                return &btf->strings[offset];
-        else
-                return NULL;
-}
-
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
         if (btf->types_size - btf->nr_types < 2) {
@@ -269,6 +266,26 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
         return nelems * size;
 }
 
+int btf__resolve_type(const struct btf *btf, __u32 type_id)
+{
+        const struct btf_type *t;
+        int depth = 0;
+
+        t = btf__type_by_id(btf, type_id);
+        while (depth < MAX_RESOLVE_DEPTH &&
+               !btf_type_is_void_or_null(t) &&
+               IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+                type_id = t->type;
+                t = btf__type_by_id(btf, type_id);
+                depth++;
+        }
+
+        if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
+                return -EINVAL;
+
+        return type_id;
+}
+
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
         __u32 i;
@@ -278,7 +295,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 
         for (i = 1; i <= btf->nr_types; i++) {
                 const struct btf_type *t = btf->types[i];
-                const char *name = btf_name_by_offset(btf, t->name_off);
+                const char *name = btf__name_by_offset(btf, t->name_off);
 
                 if (name && !strcmp(type_name, name))
                         return i;
@@ -368,3 +385,11 @@ int btf__fd(const struct btf *btf)
 {
         return btf->fd;
 }
+
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+        if (offset < btf->hdr->str_len)
+                return &btf->strings[offset];
+        else
+                return NULL;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index caac3a404dc5..4897e0724d4e 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -19,6 +19,8 @@ struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name);
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
 __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
+int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1aafdbe827fe..2abd0f112627 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -22,6 +22,7 @@
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
+#define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
@@ -42,6 +43,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
+#include <tools/libc_compat.h>
 #include <libelf.h>
 #include <gelf.h>
 
@@ -96,54 +98,6 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 
 #define STRERR_BUFSIZE  128
 
-#define ERRNO_OFFSET(e)         ((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c)       ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO        (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
-        [ERRCODE_OFFSET(LIBELF)]        = "Something wrong in libelf",
-        [ERRCODE_OFFSET(FORMAT)]        = "BPF object format invalid",
-        [ERRCODE_OFFSET(KVERSION)]      = "'version' section incorrect or lost",
-        [ERRCODE_OFFSET(ENDIAN)]        = "Endian mismatch",
-        [ERRCODE_OFFSET(INTERNAL)]      = "Internal error in libbpf",
-        [ERRCODE_OFFSET(RELOC)]         = "Relocation failed",
-        [ERRCODE_OFFSET(VERIFY)]        = "Kernel verifier blocks program loading",
-        [ERRCODE_OFFSET(PROG2BIG)]      = "Program too big",
-        [ERRCODE_OFFSET(KVER)]          = "Incorrect kernel version",
-        [ERRCODE_OFFSET(PROGTYPE)]      = "Kernel doesn't support this program type",
-        [ERRCODE_OFFSET(WRNGPID)]       = "Wrong pid in netlink message",
-        [ERRCODE_OFFSET(INVSEQ)]        = "Invalid netlink sequence",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
-        if (!buf || !size)
-                return -1;
-
-        err = err > 0 ? err : -err;
-
-        if (err < __LIBBPF_ERRNO__START) {
-                int ret;
-
-                ret = strerror_r(err, buf, size);
-                buf[size - 1] = '\0';
-                return ret;
-        }
-
-        if (err < __LIBBPF_ERRNO__END) {
-                const char *msg;
-
-                msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
-                snprintf(buf, size, "%s", msg);
-                buf[size - 1] = '\0';
-                return 0;
-        }
-
-        snprintf(buf, size, "Unknown libbpf error %d", err);
-        buf[size - 1] = '\0';
-        return -1;
-}
-
 #define CHECK_ERR(action, err, out) do {        \
         err = action;                   \
         if (err)                        \
@@ -235,6 +189,7 @@ struct bpf_object {
         size_t nr_maps;
 
         bool loaded;
+        bool has_pseudo_calls;
 
         /*
          * Information when doing elf related work. Only valid if fd
@@ -369,7 +324,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
         progs = obj->programs;
         nr_progs = obj->nr_programs;
 
-        progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
+        progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
         if (!progs) {
                 /*
                  * In this case the original obj->programs
@@ -401,10 +356,6 @@ bpf_object__init_prog_names(struct bpf_object *obj)
                 const char *name = NULL;
 
                 prog = &obj->programs[pi];
-                if (prog->idx == obj->efile.text_shndx) {
-                        name = ".text";
-                        goto skip_search;
-                }
 
                 for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
                      si++) {
@@ -427,12 +378,15 @@ bpf_object__init_prog_names(struct bpf_object *obj)
                         }
                 }
 
+                if (!name && prog->idx == obj->efile.text_shndx)
+                        name = ".text";
+
                 if (!name) {
                         pr_warning("failed to find sym for prog %s\n",
                                    prog->section_name);
                         return -EINVAL;
                 }
-skip_search:
+
                 prog->name = strdup(name);
                 if (!prog->name) {
                         pr_warning("failed to allocate memory for prog sym %s\n",
@@ -514,8 +468,10 @@ static int bpf_object__elf_init(struct bpf_object *obj)
         } else {
                 obj->efile.fd = open(obj->path, O_RDONLY);
                 if (obj->efile.fd < 0) {
-                        pr_warning("failed to open %s: %s\n", obj->path,
-                                        strerror(errno));
+                        char errmsg[STRERR_BUFSIZE];
+                        char *cp = strerror_r(errno, errmsg, sizeof(errmsg));
+
+                        pr_warning("failed to open %s: %s\n", obj->path, cp);
                         return -errno;
                 }
 
@@ -854,10 +810,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                                                       data->d_size, name, idx);
                         if (err) {
                                 char errmsg[STRERR_BUFSIZE];
+                                char *cp = strerror_r(-err, errmsg,
+                                                      sizeof(errmsg));
 
-                                strerror_r(-err, errmsg, sizeof(errmsg));
                                 pr_warning("failed to alloc program %s (%s): %s",
-                                           name, obj->path, errmsg);
+                                           name, obj->path, cp);
                         }
                 } else if (sh.sh_type == SHT_REL) {
                         void *reloc = obj->efile.reloc;
@@ -871,8 +828,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                                 continue;
                         }
 
-                        reloc = realloc(reloc,
-                                        sizeof(*obj->efile.reloc) * nr_reloc);
+                        reloc = reallocarray(reloc, nr_reloc,
+                                             sizeof(*obj->efile.reloc));
                         if (!reloc) {
                                 pr_warning("realloc failed\n");
                                 err = -ENOMEM;
@@ -920,6 +877,18 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
         return NULL;
 }
 
+struct bpf_program *
+bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
+{
+        struct bpf_program *pos;
+
+        bpf_object__for_each_program(pos, obj) {
+                if (pos->section_name && !strcmp(pos->section_name, title))
+                        return pos;
+        }
+        return NULL;
+}
+
 static int
 bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
                            Elf_Data *data, struct bpf_object *obj)
@@ -982,6 +951,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
                         prog->reloc_desc[i].type = RELO_CALL;
                         prog->reloc_desc[i].insn_idx = insn_idx;
                         prog->reloc_desc[i].text_off = sym.st_value;
+                        obj->has_pseudo_calls = true;
                         continue;
                 }
 
@@ -1085,6 +1055,53 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
         return 0;
 }
 
+int bpf_map__reuse_fd(struct bpf_map *map, int fd)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        int new_fd, err;
+        char *new_name;
+
+        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        if (err)
+                return err;
+
+        new_name = strdup(info.name);
+        if (!new_name)
+                return -errno;
+
+        new_fd = open("/", O_RDONLY | O_CLOEXEC);
+        if (new_fd < 0)
+                goto err_free_new_name;
+
+        new_fd = dup3(fd, new_fd, O_CLOEXEC);
+        if (new_fd < 0)
+                goto err_close_new_fd;
+
+        err = zclose(map->fd);
+        if (err)
+                goto err_close_new_fd;
+        free(map->name);
+
+        map->fd = new_fd;
+        map->name = new_name;
+        map->def.type = info.type;
+        map->def.key_size = info.key_size;
+        map->def.value_size = info.value_size;
+        map->def.max_entries = info.max_entries;
+        map->def.map_flags = info.map_flags;
+        map->btf_key_type_id = info.btf_key_type_id;
+        map->btf_value_type_id = info.btf_value_type_id;
+
+        return 0;
+
+err_close_new_fd:
+        close(new_fd);
+err_free_new_name:
+        free(new_name);
+        return -errno;
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1095,8 +1112,15 @@ bpf_object__create_maps(struct bpf_object *obj)
         for (i = 0; i < obj->nr_maps; i++) {
                 struct bpf_map *map = &obj->maps[i];
                 struct bpf_map_def *def = &map->def;
+                char *cp, errmsg[STRERR_BUFSIZE];
                 int *pfd = &map->fd;
 
+                if (map->fd >= 0) {
+                        pr_debug("skip map create (preset) %s: fd=%d\n",
+                                 map->name, map->fd);
+                        continue;
+                }
+
                 create_attr.name = map->name;
                 create_attr.map_ifindex = map->map_ifindex;
                 create_attr.map_type = def->type;
@@ -1116,8 +1140,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 
                 *pfd = bpf_create_map_xattr(&create_attr);
                 if (*pfd < 0 && create_attr.btf_key_type_id) {
+                        cp = strerror_r(errno, errmsg, sizeof(errmsg));
                         pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
-                                   map->name, strerror(errno), errno);
+                                   map->name, cp, errno);
                         create_attr.btf_fd = 0;
                         create_attr.btf_key_type_id = 0;
                         create_attr.btf_value_type_id = 0;
@@ -1130,9 +1155,9 @@ bpf_object__create_maps(struct bpf_object *obj)
                         size_t j;
 
                         err = *pfd;
+                        cp = strerror_r(errno, errmsg, sizeof(errmsg));
                         pr_warning("failed to create map (name: '%s'): %s\n",
-                                   map->name,
-                                   strerror(errno));
+                                   map->name, cp);
                         for (j = 0; j < i; j++)
                                 zclose(obj->maps[j].fd);
                         return err;
@@ -1167,7 +1192,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
                         return -LIBBPF_ERRNO__RELOC;
                 }
                 new_cnt = prog->insns_cnt + text->insns_cnt;
-                new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
+                new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
                 if (!new_insn) {
                         pr_warning("oom in prog realloc\n");
                         return -ENOMEM;
@@ -1284,6 +1309,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
              char *license, u32 kern_version, int *pfd, int prog_ifindex)
 {
         struct bpf_load_program_attr load_attr;
+        char *cp, errmsg[STRERR_BUFSIZE];
         char *log_buf;
         int ret;
 
@@ -1313,7 +1339,8 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
         }
 
         ret = -LIBBPF_ERRNO__LOAD;
-        pr_warning("load bpf program failed: %s\n", strerror(errno));
+        cp = strerror_r(errno, errmsg, sizeof(errmsg));
+        pr_warning("load bpf program failed: %s\n", cp);
 
         if (log_buf && log_buf[0] != '\0') {
                 ret = -LIBBPF_ERRNO__VERIFY;
@@ -1431,6 +1458,12 @@ out:
         return err;
 }
 
+static bool bpf_program__is_function_storage(struct bpf_program *prog,
+                                             struct bpf_object *obj)
+{
+        return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
+}
+
 static int
 bpf_object__load_progs(struct bpf_object *obj)
 {
@@ -1438,7 +1471,7 @@ bpf_object__load_progs(struct bpf_object *obj)
         int err;
 
         for (i = 0; i < obj->nr_programs; i++) {
-                if (obj->programs[i].idx == obj->efile.text_shndx)
+                if (bpf_program__is_function_storage(&obj->programs[i], obj))
                         continue;
                 err = bpf_program__load(&obj->programs[i],
                                         obj->license,
@@ -1468,6 +1501,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
         case BPF_PROG_TYPE_SK_MSG:
         case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
         case BPF_PROG_TYPE_LIRC_MODE2:
+        case BPF_PROG_TYPE_SK_REUSEPORT:
                 return false;
         case BPF_PROG_TYPE_UNSPEC:
         case BPF_PROG_TYPE_KPROBE:
@@ -1518,15 +1552,26 @@ out:
         return ERR_PTR(err);
 }
 
-struct bpf_object *bpf_object__open(const char *path)
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 {
         /* param validation */
-        if (!path)
+        if (!attr->file)
                 return NULL;
 
-        pr_debug("loading %s\n", path);
+        pr_debug("loading %s\n", attr->file);
 
-        return __bpf_object__open(path, NULL, 0, true);
+        return __bpf_object__open(attr->file, NULL, 0,
+                                  bpf_prog_type__needs_kver(attr->prog_type));
+}
+
+struct bpf_object *bpf_object__open(const char *path)
+{
+        struct bpf_object_open_attr attr = {
+                .file           = path,
+                .prog_type      = BPF_PROG_TYPE_UNSPEC,
+        };
+
+        return bpf_object__open_xattr(&attr);
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
@@ -1595,6 +1640,7 @@ out:
 
 static int check_path(const char *path)
 {
+        char *cp, errmsg[STRERR_BUFSIZE];
         struct statfs st_fs;
         char *dname, *dir;
         int err = 0;
@@ -1608,7 +1654,8 @@ static int check_path(const char *path)
 
         dir = dirname(dname);
         if (statfs(dir, &st_fs)) {
-                pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+                cp = strerror_r(errno, errmsg, sizeof(errmsg));
+                pr_warning("failed to statfs %s: %s\n", dir, cp);
                 err = -errno;
         }
         free(dname);
@@ -1624,6 +1671,7 @@ static int check_path(const char *path)
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
                               int instance)
 {
+        char *cp, errmsg[STRERR_BUFSIZE];
         int err;
 
         err = check_path(path);
@@ -1642,7 +1690,8 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
         }
 
         if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-                pr_warning("failed to pin program: %s\n", strerror(errno));
+                cp = strerror_r(errno, errmsg, sizeof(errmsg));
+                pr_warning("failed to pin program: %s\n", cp);
                 return -errno;
         }
         pr_debug("pinned program '%s'\n", path);
@@ -1652,13 +1701,16 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 
 static int make_dir(const char *path)
 {
+        char *cp, errmsg[STRERR_BUFSIZE];
         int err = 0;
 
         if (mkdir(path, 0700) && errno != EEXIST)
                 err = -errno;
 
-        if (err)
-                pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+        if (err) {
+                cp = strerror_r(-err, errmsg, sizeof(errmsg));
+                pr_warning("failed to mkdir %s: %s\n", path, cp);
+        }
         return err;
 }
 
@@ -1705,6 +1757,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 int bpf_map__pin(struct bpf_map *map, const char *path)
 {
+        char *cp, errmsg[STRERR_BUFSIZE];
         int err;
 
         err = check_path(path);
@@ -1717,7 +1770,8 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
         }
 
         if (bpf_obj_pin(map->fd, path)) {
-                pr_warning("failed to pin map: %s\n", strerror(errno));
+                cp = strerror_r(errno, errmsg, sizeof(errmsg));
+                pr_warning("failed to pin map: %s\n", cp);
                 return -errno;
         }
 
@@ -1863,8 +1917,8 @@ void *bpf_object__priv(struct bpf_object *obj)
         return obj ? obj->priv : ERR_PTR(-EINVAL);
 }
 
-struct bpf_program *
-bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+static struct bpf_program *
+__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
         size_t idx;
 
@@ -1885,6 +1939,18 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
         return &obj->programs[idx];
 }
 
+struct bpf_program *
+bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+{
+        struct bpf_program *prog = prev;
+
+        do {
+                prog = __bpf_program__next(prog, obj);
+        } while (prog && bpf_program__is_function_storage(prog, obj));
+
+        return prog;
+}
+
 int bpf_program__set_priv(struct bpf_program *prog, void *priv,
                           bpf_program_clear_priv_t clear_priv)
 {
@@ -1901,6 +1967,11 @@ void *bpf_program__priv(struct bpf_program *prog)
         return prog ? prog->priv : ERR_PTR(-EINVAL);
 }
 
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
+{
+        prog->prog_ifindex = ifindex;
+}
+
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 {
         const char *title;
@@ -1954,6 +2025,9 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
 {
         int fd;
 
+        if (!prog)
+                return -EINVAL;
+
         if (n >= prog->instances.nr || n < 0) {
                 pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
                            n, prog->section_name, prog->instances.nr);
@@ -2042,9 +2116,11 @@ static const struct {
         BPF_PROG_SEC("lwt_in",          BPF_PROG_TYPE_LWT_IN),
         BPF_PROG_SEC("lwt_out",         BPF_PROG_TYPE_LWT_OUT),
         BPF_PROG_SEC("lwt_xmit",        BPF_PROG_TYPE_LWT_XMIT),
+        BPF_PROG_SEC("lwt_seg6local",   BPF_PROG_TYPE_LWT_SEG6LOCAL),
         BPF_PROG_SEC("sockops",         BPF_PROG_TYPE_SOCK_OPS),
         BPF_PROG_SEC("sk_skb",          BPF_PROG_TYPE_SK_SKB),
         BPF_PROG_SEC("sk_msg",          BPF_PROG_TYPE_SK_MSG),
+        BPF_PROG_SEC("lirc_mode2",      BPF_PROG_TYPE_LIRC_MODE2),
         BPF_SA_PROG_SEC("cgroup/bind4", BPF_CGROUP_INET4_BIND),
         BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
         BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
@@ -2060,23 +2136,31 @@ static const struct {
 #undef BPF_S_PROG_SEC
 #undef BPF_SA_PROG_SEC
 
-static int bpf_program__identify_section(struct bpf_program *prog)
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+                             enum bpf_attach_type *expected_attach_type)
 {
         int i;
 
-        if (!prog->section_name)
-                goto err;
-
-        for (i = 0; i < ARRAY_SIZE(section_names); i++)
-                if (strncmp(prog->section_name, section_names[i].sec,
-                            section_names[i].len) == 0)
-                        return i;
+        if (!name)
+                return -EINVAL;
 
-err:
-        pr_warning("failed to guess program type based on section name %s\n",
-                   prog->section_name);
+        for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+                if (strncmp(name, section_names[i].sec, section_names[i].len))
+                        continue;
+                *prog_type = section_names[i].prog_type;
+                *expected_attach_type = section_names[i].expected_attach_type;
+                return 0;
+        }
+        return -EINVAL;
+}
 
-        return -1;
+static int
+bpf_program__identify_section(struct bpf_program *prog,
+                              enum bpf_prog_type *prog_type,
+                              enum bpf_attach_type *expected_attach_type)
+{
+        return libbpf_prog_type_by_name(prog->section_name, prog_type,
+                                        expected_attach_type);
 }
 
 int bpf_map__fd(struct bpf_map *map)
@@ -2125,6 +2209,16 @@ void *bpf_map__priv(struct bpf_map *map)
         return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
+bool bpf_map__is_offload_neutral(struct bpf_map *map)
+{
+        return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
+{
+        map->map_ifindex = ifindex;
+}
+
 struct bpf_map *
 bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 {
@@ -2199,12 +2293,15 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
                         struct bpf_object **pobj, int *prog_fd)
 {
+        struct bpf_object_open_attr open_attr = {
+                .file           = attr->file,
+                .prog_type      = attr->prog_type,
+        };
         struct bpf_program *prog, *first_prog = NULL;
         enum bpf_attach_type expected_attach_type;
         enum bpf_prog_type prog_type;
         struct bpf_object *obj;
         struct bpf_map *map;
-        int section_idx;
         int err;
 
         if (!attr)
@@ -2212,8 +2309,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
         if (!attr->file)
                 return -EINVAL;
 
-        obj = __bpf_object__open(attr->file, NULL, 0,
-                                 bpf_prog_type__needs_kver(attr->prog_type));
+        obj = bpf_object__open_xattr(&open_attr);
         if (IS_ERR_OR_NULL(obj))
                 return -ENOENT;
 
@@ -2226,26 +2322,27 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
                 prog->prog_ifindex = attr->ifindex;
                 expected_attach_type = attr->expected_attach_type;
                 if (prog_type == BPF_PROG_TYPE_UNSPEC) {
-                        section_idx = bpf_program__identify_section(prog);
-                        if (section_idx < 0) {
+                        err = bpf_program__identify_section(prog, &prog_type,
+                                                            &expected_attach_type);
+                        if (err < 0) {
+                                pr_warning("failed to guess program type based on section name %s\n",
+                                           prog->section_name);
                                 bpf_object__close(obj);
                                 return -EINVAL;
                         }
-                        prog_type = section_names[section_idx].prog_type;
-                        expected_attach_type =
-                                section_names[section_idx].expected_attach_type;
                 }
 
                 bpf_program__set_type(prog, prog_type);
                 bpf_program__set_expected_attach_type(prog,
                                                       expected_attach_type);
 
-                if (prog->idx != obj->efile.text_shndx && !first_prog)
+                if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
                         first_prog = prog;
         }
 
         bpf_map__for_each(map, obj) {
-                map->map_ifindex = attr->ifindex;
+                if (!bpf_map__is_offload_neutral(map))
+                        map->map_ifindex = attr->ifindex;
         }
 
         if (!first_prog) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b33ae02f7d0e..96c55fac54c3 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -66,7 +66,13 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 /* Hide internal to user */
 struct bpf_object;
 
+struct bpf_object_open_attr {
+        const char *file;
+        enum bpf_prog_type prog_type;
+};
+
 struct bpf_object *bpf_object__open(const char *path);
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
                                            size_t obj_buf_sz,
                                            const char *name);
@@ -80,6 +86,9 @@ const char *bpf_object__name(struct bpf_object *obj);
 unsigned int bpf_object__kversion(struct bpf_object *obj);
 int bpf_object__btf_fd(const struct bpf_object *obj);
 
+struct bpf_program *
+bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
+
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)                     \
         for ((pos) = bpf_object__next(NULL),            \
@@ -92,6 +101,9 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
                          bpf_object_clear_priv_t clear_priv);
 void *bpf_object__priv(struct bpf_object *prog);
 
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+                             enum bpf_attach_type *expected_attach_type);
+
 /* Accessors of bpf_program */
 struct bpf_program;
 struct bpf_program *bpf_program__next(struct bpf_program *prog,
@@ -109,6 +121,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv,
                           bpf_program_clear_priv_t clear_priv);
 
 void *bpf_program__priv(struct bpf_program *prog);
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
@@ -251,6 +264,9 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
                       bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+bool bpf_map__is_offload_neutral(struct bpf_map *map);
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 int bpf_map__pin(struct bpf_map *map, const char *path);
 
 long libbpf_get_error(const void *ptr);
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
new file mode 100644
index 000000000000..d9ba851bd7f9
--- /dev/null
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "libbpf.h"
+
+#define ERRNO_OFFSET(e)         ((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)       ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO        (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+        [ERRCODE_OFFSET(LIBELF)]        = "Something wrong in libelf",
+        [ERRCODE_OFFSET(FORMAT)]        = "BPF object format invalid",
+        [ERRCODE_OFFSET(KVERSION)]      = "'version' section incorrect or lost",
+        [ERRCODE_OFFSET(ENDIAN)]        = "Endian mismatch",
+        [ERRCODE_OFFSET(INTERNAL)]      = "Internal error in libbpf",
+        [ERRCODE_OFFSET(RELOC)]         = "Relocation failed",
+        [ERRCODE_OFFSET(VERIFY)]        = "Kernel verifier blocks program loading",
+        [ERRCODE_OFFSET(PROG2BIG)]      = "Program too big",
+        [ERRCODE_OFFSET(KVER)]          = "Incorrect kernel version",
+        [ERRCODE_OFFSET(PROGTYPE)]      = "Kernel doesn't support this program type",
+        [ERRCODE_OFFSET(WRNGPID)]       = "Wrong pid in netlink message",
+        [ERRCODE_OFFSET(INVSEQ)]        = "Invalid netlink sequence",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+        if (!buf || !size)
+                return -1;
+
+        err = err > 0 ? err : -err;
+
+        if (err < __LIBBPF_ERRNO__START) {
+                int ret;
+
+                ret = strerror_r(err, buf, size);
+                buf[size - 1] = '\0';
+                return ret;
+        }
+
+        if (err < __LIBBPF_ERRNO__END) {
+                const char *msg;
+
+                msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+                snprintf(buf, size, "%s", msg);
+                buf[size - 1] = '\0';
+                return 0;
+        }
+
+        snprintf(buf, size, "Unknown libbpf error %d", err);
+        buf[size - 1] = '\0';
+        return -1;
+}
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 1b09f3175a1f..0cbd1ef8f86d 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -804,7 +804,7 @@ type of fence:
 Second, some types of fence affect the way the memory subsystem
 propagates stores.  When a fence instruction is executed on CPU C:
 
-        For each other CPU C', smb_wmb() forces all po-earlier stores
+        For each other CPU C', smp_wmb() forces all po-earlier stores
         on C to propagate to C' before any po-later stores do.
 
         For each other CPU C', any store which propagates to C before
diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index ee4309a87fc4..af72700cc20a 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by
 locking will be seen as ordered by CPUs not holding that lock.
 Consider this example:
 
-        /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+        /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
         void CPU0(void)
         {
                 spin_lock(&mylock);
@@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb().  However, the older
 smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
 to understand their use cases.  The general approach is shown below:
 
-        /* See MP+wmbonceonce+rmbonceonce.litmus. */
+        /* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
         void CPU0(void)
         {
                 WRITE_ONCE(x, 1);
@@ -322,9 +322,9 @@ the following write-side code fragment:
 And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
 the corresponding read-side code fragment:
 
-        cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+        cur_cycle = READ_ONCE(log->l_curr_cycle);
         smp_rmb();
-        cur_block = ACCESS_ONCE(log->l_curr_block);
+        cur_block = READ_ONCE(log->l_curr_block);
 
 Alternatively, consider the following comment in function
 perf_output_put_handle() in kernel/events/ring_buffer.c:
@@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test.
 One way of avoiding the counter-intuitive outcome is through the use of a
 control dependency paired with a full memory barrier:
 
-        /* See LB+ctrlonceonce+mbonceonce.litmus. */
+        /* See LB+fencembonceonce+ctrlonceonce.litmus. */
         void CPU0(void)
         {
                 r0 = READ_ONCE(x);
@@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second,
 while another CPU stores to the second variable and then loads from the
 first.  Preserving order requires nothing less than full barriers:
 
-        /* See SB+mbonceonces.litmus. */
+        /* See SB+fencembonceonces.litmus. */
         void CPU0(void)
         {
                 WRITE_ONCE(x, 1);
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 734f7feaa5dc..ee987ce20aae 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -35,13 +35,13 @@ BASIC USAGE: HERD7
 The memory model is used, in conjunction with "herd7", to exhaustively
 explore the state space of small litmus tests.
 
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
 
-  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
 
 Here is the corresponding output:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   States 3
   0:r0=0; 1:r0=1;
   0:r0=1; 1:r0=0;
@@ -50,8 +50,8 @@ Here is the corresponding output:
   Witnesses
   Positive: 0 Negative: 3
   Condition exists (0:r0=0 /\ 1:r0=0)
-  Observation SB+mbonceonces Never 0 3
-  Time SB+mbonceonces 0.01
+  Observation SB+fencembonceonces Never 0 3
+  Time SB+fencembonceonces 0.01
   Hash=d66d99523e2cac6b06e66f4c995ebb48
 
 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
@@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7
 The "klitmus7" tool converts a litmus test into a Linux kernel module,
 which may then be loaded and run.
 
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
 
   $ mkdir mymodules
-  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
   $ cd mymodules ; make
   $ sudo sh run.sh
 
 The corresponding output includes:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   Histogram (3 states)
   644580  :>0:r0=1; 1:r0=0;
   644328  :>0:r0=0; 1:r0=1;
@@ -86,8 +86,8 @@ The corresponding output includes:
   Positive: 0, Negative: 2000000
   Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
   Hash=d66d99523e2cac6b06e66f4c995ebb48
-  Observation SB+mbonceonces Never 0 2000000
-  Time SB+mbonceonces 0.16
+  Observation SB+fencembonceonces Never 0 2000000
+  Time SB+fencembonceonces 0.16
 
 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
 that during two million trials, the state specified in this litmus
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 64f5740e0e75..b84fb2f67109 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -13,7 +13,7 @@
 
 "Linux-kernel memory consistency model"
 
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
                 'release (*smp_store_release*) ||
                 'acquire (*smp_load_acquire*) ||
                 'noreturn (* R of non-return RMW *)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
index 98a3716efa37..e729d2776e89 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -1,4 +1,4 @@
-C IRIW+mbonceonces+OnceOnce
+C IRIW+fencembonceonces+OnceOnce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 7a39a0aaa976..0f749e419b34 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,4 +1,4 @@
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
index de6708229dd1..4727f5aaf03b 100644
--- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -1,4 +1,4 @@
-C LB+ctrlonceonce+mbonceonce
+C LB+fencembonceonce+ctrlonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
index c078f38ff27a..a273da9faa6d 100644
--- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -1,4 +1,4 @@
-C MP+wmbonceonce+rmbonceonce
+C MP+fencewmbonceonce+fencermbonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
index a0e884ad2132..222a0b850b4a 100644
--- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C R+mbonceonces
+C R+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 17eb9a8c222d..4581ec2d3c57 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -18,7 +18,7 @@ CoWW+poonceonce.litmus
         Test of write-write coherence, that is, whether or not two
         successive writes to the same variable are ordered.
 
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
         Test of independent reads from independent writes with smp_mb()
         between each pairs of reads.  In other words, is smp_mb()
         sufficient to cause two different reading processes to agree on
@@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
         Can a release-acquire chain order a prior store against
         a later load?
 
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
         Does a control dependency and an smp_mb() suffice for the
         load-buffering litmus test, where each process reads from one
         of two variables then writes to the other?
@@ -88,14 +88,14 @@ MP+porevlocks.litmus
         As below, but with the first access of the writer process
         and the second access of reader process protected by a lock.
 
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
         Does a smp_wmb() (between the stores) and an smp_rmb() (between
         the loads) suffice for the message-passing litmus test, where one
         process writes data and then a flag, and the other process reads
         the flag and then the data.  (This is similar to the ISA2 tests,
         but with two processes instead of three.)
 
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
         This is the fully ordered (via smp_mb()) version of one of
         the classic counterintuitive litmus tests that illustrates the
         effects of store propagation delays.
@@ -103,7 +103,7 @@ R+mbonceonces.litmus
 R+poonceonces.litmus
         As above, but without the smp_mb() invocations.
 
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
         This is the fully ordered (again, via smp_mb() version of store
         buffering, which forms the core of Dekker's mutual-exclusion
         algorithm.
@@ -111,15 +111,24 @@ SB+mbonceonces.litmus
 SB+poonceonces.litmus
         As above, but without the smp_mb() invocations.
 
+SB+rfionceonce-poonceonces.litmus
+        This litmus test demonstrates that LKMM is not fully multicopy
+        atomic.  (Neither is it other multicopy atomic.)  This litmus test
+        also demonstrates the "locations" debugging aid, which designates
+        additional registers and locations to be printed out in the dump
+        of final states in the herd7 output.  Without the "locations"
+        statement, only those registers and locations mentioned in the
+        "exists" clause will be printed.
+
 S+poonceonces.litmus
         As below, but without the smp_wmb() and acquire load.
 
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
         Can a smp_wmb(), instead of a release, and an acquire order
         a prior store against a subsequent store?
 
 WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
         These two are members of an extension of the MP litmus-test
         class in which the first write is moved to a separate process.
         The second is forbidden because smp_store_release() is
@@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus
         As above, but with smp_mb__after_spinlock() immediately
         following the spin_lock().
 
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
         Is the ordering provided by a release-acquire chain sufficient
         to make ordering apparent to accesses by a process that does
         not participate in that release-acquire chain?
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
index c53350205d28..18479823cd6c 100644
--- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -1,4 +1,4 @@
-C S+wmbonceonce+poacquireonce
+C S+fencewmbonceonce+poacquireonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
index 74b874ffa8da..ed5fff18d223 100644
--- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C SB+mbonceonces
+C SB+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
new file mode 100644
index 000000000000..04a16603660b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r1;
+        int r2;
+
+        WRITE_ONCE(*x, 1);
+        r1 = READ_ONCE(*x);
+        r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+        int r3;
+        int r4;
+
+        WRITE_ONCE(*y, 1);
+        r3 = READ_ONCE(*y);
+        r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
index ad3448b941e6..e9947250d7de 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -1,4 +1,4 @@
-C WRC+pooncerelease+rmbonceonce+Once
+C WRC+pooncerelease+fencermbonceonce+Once
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
index a20fc3fafb53..88e70b87a683 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -1,4 +1,4 @@
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index af0aa15ab84e..ca528f9a24d4 100644..100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -9,7 +9,7 @@
 # appended.
 #
 # Usage:
-#       sh checkalllitmus.sh [ directory ]
+#       checkalllitmus.sh [ directory ]
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, whose default is defined by the checklitmus.sh script.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index e2e477472844..bf12a75c0719 100644..100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -8,7 +8,7 @@
 # with ".out" appended.
 #
 # Usage:
-#       sh checklitmus.sh file.litmus
+#       checklitmus.sh file.litmus
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f76d9914686a..c9d038f91af6 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -31,8 +31,8 @@ INCLUDES := -I$(srctree)/tools/include \
             -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
             -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Werror $(WARNINGS) $(HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
+CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
+LDFLAGS  += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/tools/objtool/arch/x86/include/asm/orc_types.h
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
         unsigned        sp_reg:4;
         unsigned        bp_reg:4;
         unsigned        type:2;
+        unsigned        end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
         s16             sp_offset;
         u8              sp_reg;
         u8              type;
+        u8              end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f4a25bd1871f..2928939b98ec 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1157,6 +1157,7 @@ static int read_unwind_hints(struct objtool_file *file)
 
                 cfa->offset = hint->sp_offset;
                 insn->state.type = hint->type;
+                insn->state.end = hint->end;
         }
 
         return 0;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index c6b68fcb926f..95700a2bcb7c 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,7 @@ struct insn_state {
         int stack_size;
         unsigned char type;
         bool bp_scratch;
-        bool drap;
+        bool drap, end;
         int drap_reg, drap_offset;
         struct cfi_reg vals[CFI_NUM_REGS];
 };
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index c3343820916a..faa444270ee3 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -203,7 +203,8 @@ int orc_dump(const char *_objname)
 
                 print_reg(orc[i].bp_reg, orc[i].bp_offset);
 
-                printf(" type:%s\n", orc_type_name(orc[i].type));
+                printf(" type:%s end:%d\n",
+                       orc_type_name(orc[i].type), orc[i].end);
         }
 
         elf_end(elf);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 18384d9be4e1..3f98dcfbc177 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file)
                 struct cfi_reg *cfa = &insn->state.cfa;
                 struct cfi_reg *bp = &insn->state.regs[CFI_BP];
 
+                orc->end = insn->state.end;
+
                 if (cfa->base == CFI_UNDEFINED) {
                         orc->sp_reg = ORC_REG_UNDEFINED;
                         continue;
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index 9074b477bff0..af146bb03b4d 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -31,12 +31,17 @@
 #define BILLION 1E9
 
 static char *result[] = { "NOT OKAY", "OKAY" };
+static char *irq[] = { "LEGACY", "MSI", "MSI-X" };
 
 struct pci_test {
         char            *device;
         char            barnum;
         bool            legacyirq;
         unsigned int    msinum;
+        unsigned int    msixnum;
+        int             irqtype;
+        bool            set_irqtype;
+        bool            get_irqtype;
         bool            read;
         bool            write;
         bool            copy;
@@ -65,6 +70,24 @@ static int run_test(struct pci_test *test)
                         fprintf(stdout, "%s\n", result[ret]);
         }
 
+        if (test->set_irqtype) {
+                ret = ioctl(fd, PCITEST_SET_IRQTYPE, test->irqtype);
+                fprintf(stdout, "SET IRQ TYPE TO %s:\t\t", irq[test->irqtype]);
+                if (ret < 0)
+                        fprintf(stdout, "FAILED\n");
+                else
+                        fprintf(stdout, "%s\n", result[ret]);
+        }
+
+        if (test->get_irqtype) {
+                ret = ioctl(fd, PCITEST_GET_IRQTYPE);
+                fprintf(stdout, "GET IRQ TYPE:\t\t");
+                if (ret < 0)
+                        fprintf(stdout, "FAILED\n");
+                else
+                        fprintf(stdout, "%s\n", irq[ret]);
+        }
+
         if (test->legacyirq) {
                 ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0);
                 fprintf(stdout, "LEGACY IRQ:\t");
@@ -83,6 +106,15 @@ static int run_test(struct pci_test *test)
                         fprintf(stdout, "%s\n", result[ret]);
         }
 
+        if (test->msixnum > 0 && test->msixnum <= 2048) {
+                ret = ioctl(fd, PCITEST_MSIX, test->msixnum);
+                fprintf(stdout, "MSI-X%d:\t\t", test->msixnum);
+                if (ret < 0)
+                        fprintf(stdout, "TEST FAILED\n");
+                else
+                        fprintf(stdout, "%s\n", result[ret]);
+        }
+
         if (test->write) {
                 ret = ioctl(fd, PCITEST_WRITE, test->size);
                 fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size);
@@ -133,7 +165,7 @@ int main(int argc, char **argv)
         /* set default endpoint device */
         test->device = "/dev/pci-endpoint-test.0";
 
-        while ((c = getopt(argc, argv, "D:b:m:lrwcs:")) != EOF)
+        while ((c = getopt(argc, argv, "D:b:m:x:i:Ilrwcs:")) != EOF)
         switch (c) {
         case 'D':
                 test->device = optarg;
@@ -151,6 +183,20 @@ int main(int argc, char **argv)
                 if (test->msinum < 1 || test->msinum > 32)
                         goto usage;
                 continue;
+        case 'x':
+                test->msixnum = atoi(optarg);
+                if (test->msixnum < 1 || test->msixnum > 2048)
+                        goto usage;
+                continue;
+        case 'i':
+                test->irqtype = atoi(optarg);
+                if (test->irqtype < 0 || test->irqtype > 2)
+                        goto usage;
+                test->set_irqtype = true;
+                continue;
+        case 'I':
+                test->get_irqtype = true;
+                continue;
         case 'r':
                 test->read = true;
                 continue;
@@ -173,6 +219,9 @@ usage:
                         "\t-D <dev>             PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n"
                         "\t-b <bar num>         BAR test (bar number between 0..5)\n"
                         "\t-m <msi num>         MSI test (msi number between 1..32)\n"
+                        "\t-x <msix num>        \tMSI-X test (msix number between 1..2048)\n"
+                        "\t-i <irq type>        \tSet IRQ type (0 - Legacy, 1 - MSI, 2 - MSI-X)\n"
+                        "\t-I                   Get current IRQ type configured\n"
                         "\t-l                   Legacy IRQ test\n"
                         "\t-r                   Read buffer test\n"
                         "\t-w                   Write buffer test\n"
diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh
index 77e8c85ef744..75ed48ff2990 100644
--- a/tools/pci/pcitest.sh
+++ b/tools/pci/pcitest.sh
@@ -16,7 +16,10 @@ echo
 echo "Interrupt tests"
 echo
 
+pcitest -i 0
 pcitest -l
+
+pcitest -i 1
 msi=1
 
 while [ $msi -lt 33 ]
@@ -26,9 +29,21 @@ do
 done
 echo
 
+pcitest -i 2
+msix=1
+
+while [ $msix -lt 2049 ]
+do
+        pcitest -x $msix
+        msix=`expr $msix + 1`
+done
+echo
+
 echo "Read Tests"
 echo
 
+pcitest -i 1
+
 pcitest -r -s 1
 pcitest -r -s 1024
 pcitest -r -s 1025
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
           "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
         selects either tracepoint event(s) or a hardware trace PMU
         (e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
         Don't record events issued by perf itself. This option should follow
-        a event selector (-e) which selects tracepoint event(s). It adds a
+        an event selector (-e) which selects tracepoint event(s). It adds a
         filter expression 'common_pid != $PERFPID' to filters. If other
         '--filter' exists, the new filter expression will be combined with
         them by '&&'.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f5a3b402589e..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
@@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
         $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+        $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
         $(sndrv_ctl_ioctl_array) \
         $(kcmp_type_array) \
         $(kvm_ioctl_array) \
+        $(socket_ipproto_array) \
         $(vhost_virtio_ioctl_array) \
         $(madvise_behavior_array) \
         $(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
                 $(OUTPUT)$(sndrv_pcm_ioctl_array) \
                 $(OUTPUT)$(kvm_ioctl_array) \
                 $(OUTPUT)$(kcmp_type_array) \
+                $(OUTPUT)$(socket_ipproto_array) \
                 $(OUTPUT)$(vhost_virtio_ioctl_array) \
                 $(OUTPUT)$(perf_ioctl_array) \
                 $(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..f013b115dc86 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+        $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+        $(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..52e197317d3e
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+        echo "Could not read input file" >&2
+        exit 1
+fi
+
+create_table_from_c()
+{
+        local sc nr last_sc
+
+        create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+        {
+
+        cat <<-_EoHEADER
+                #include <stdio.h>
+                #define __ARCH_WANT_RENAMEAT
+                #include "$input"
+                int main(int argc, char *argv[])
+                {
+        _EoHEADER
+
+        while read sc nr; do
+                printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+                last_sc=$sc
+        done
+
+        printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+        printf "}\n"
+
+        } | $hostcc -o $create_table_exe -x c -
+
+        $create_table_exe
+
+        rm -f $create_table_exe
+}
+
+create_table()
+{
+        echo "static const char *syscalltbl_arm64[] = {"
+        create_table_from_c
+        echo "};"
+}
+
+$gcc -E -dM -x c  $input               \
+        |sed -ne 's/^#define __NR_//p' \
+        |sort -t' ' -k2 -nu            \
+        |create_table
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index ef5d59a5742e..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
         }
 
         /*
-         * Check if return address is on the stack.
+         * Check if return address is on the stack. If return address
+         * is in a register (typically R0), it is yet to be saved on
+         * the stack.
          */
-        if (nops != 0 || ops != NULL)
+        if ((nops != 0 || ops != NULL) &&
+                !(nops == 1 && ops[0].atom == DW_OP_regx &&
+                        ops[0].number2 == 0 && ops[0].offset == 0))
                 return 0;
 
         /*
@@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
         if (!chain || chain->nr < 3)
                 return skip_slot;
 
-        ip = chain->ips[2];
+        ip = chain->ips[1];
 
         thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-        if (strstr(cpuid, "IBM/S390")) {
+        if (strstr(cpuid, "IBM")) {
                 kvm->exit_reasons = sie_exit_reasons;
                 kvm->exit_reasons_isa = "SIE";
         } else
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
         fprintf(out, "%s\n", bf);
         fprintf(out, "  -------------------------------------------------------------\n");
 
-        hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+        hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
         fprintf(out, "=================================================\n");
         fprintf(out, "#\n");
 
-        hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+        hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
         fprintf(out, "\n");
         fprintf(out, "=================================================\n");
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
         " s             Toggle full length of symbol and source line columns \n"
         " q             Return back to cacheline list \n";
 
+        if (!he)
+                return 0;
+
         /* Display compact version first. */
         c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
         hists__output_resort(hists, NULL);
 
         hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-                       symbol_conf.use_callchain);
+                       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c04dc7b53797..02f7a3c27761 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
                 hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
                 hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-                               symbol_conf.use_callchain ||
-                               symbol_conf.show_branchflag_count);
+                               !(symbol_conf.use_callchain ||
+                                 symbol_conf.show_branchflag_count));
                 fprintf(stdout, "\n\n");
         }
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 05be023c3f0e..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
         return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-        if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-            perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-                return 1;
-
-        return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
                                      union perf_event *event,
                                      struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
                 fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-        FILE *output = stat_config.output;
-        double msecs = avg / NSEC_PER_MSEC;
-        const char *fmt_v, *fmt_n;
-        char name[25];
-
-        fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-        fmt_n = csv_output ? "%s" : "%-25s";
-
-        aggr_printout(evsel, id, nr);
-
-        scnprintf(name, sizeof(name), "%s%s",
-                  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-        fprintf(output, fmt_v, msecs, csv_sep);
-
-        if (csv_output)
-                fprintf(output, "%s%s", evsel->unit, csv_sep);
-        else
-                fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-        fprintf(output, fmt_n, name);
-
-        if (evsel->cgrp)
-                fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
         int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
                 return;
         }
 
-        if (metric_only)
-                /* nothing */;
-        else if (nsec_counter(counter))
-                nsec_printout(id, nr, counter, uval);
-        else
+        if (!metric_only)
                 abs_printout(id, nr, counter, uval);
 
         out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
                     alias->scale != counter->scale ||
                     alias->cgrp != counter->cgrp ||
                     strcmp(alias->unit, counter->unit) ||
-                    nsec_counter(alias) != nsec_counter(counter))
+                    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
                         break;
                 alias->merged_stat = true;
                 cb(alias, data, false);
@@ -2449,6 +2405,18 @@ static int add_default_attributes(void)
                 return 0;
 
         if (transaction_run) {
+                /* Handle -T as -M transaction. Once platform specific metrics
+                 * support has been added to the json files, all archictures
+                 * will use this approach. To determine transaction support
+                 * on an architecture test for such a metric name.
+                 */
+                if (metricgroup__has_metric("transaction")) {
+                        struct option opt = { .value = &evsel_list };
+
+                        return metricgroup__parse_groups(&opt, "transaction",
+                                                         &metric_events);
+                }
+
                 if (pmu_have_event("cpu", "cycles-ct") &&
                     pmu_have_event("cpu", "el-start"))
                         err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
         hists__fprintf(hists, false, top->print_entries - printed, win_width,
-                       top->min_percent, stdout, symbol_conf.use_callchain);
+                       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
         int idx = val - sa->offset;
 
-        if (idx < 0 || idx >= sa->nr_entries)
+        if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
                 return scnprintf(bf, size, intfmt, val);
 
         return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +761,12 @@ static struct syscall_fmt {
           .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
         { .name     = "socket",
           .arg = { [0] = STRARRAY(family, socket_families),
-                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+                   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
         { .name     = "socketpair",
           .arg = { [0] = STRARRAY(family, socket_families),
-                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+                   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
         { .name     = "stat", .alias = "newstat", },
         { .name     = "statx",
           .arg = { [0] = { .scnprintf = SCA_FDAT,        /* fdat */ },
@@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
                 if (trace__validate_ev_qualifier(trace))
                         goto out;
+                trace->trace_syscalls = true;
         }
 
         err = 0;
@@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
                 },
                 .output = stderr,
                 .show_comm = true,
-                .trace_syscalls = true,
+                .trace_syscalls = false,
                 .kernel_syscallchains = false,
                 .max_stack = UINT_MAX,
         };
@@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
         if (!trace.trace_syscalls && !trace.trace_pgfaults &&
             trace.evlist->nr_entries == 0 /* Was --events used? */) {
-                pr_err("Please specify something to trace.\n");
-                return -1;
-        }
-
-        if (!trace.trace_syscalls && trace.ev_qualifier) {
-                pr_err("The -e option can't be used with --no-syscalls.\n");
-                goto out;
+                trace.trace_syscalls = true;
         }
 
         if (output_name != NULL) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
         return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS                     1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "0",
                 "EventName": "CPU_CYCLES",
                 "BriefDescription": "CPU Cycles",
                 "PublicDescription": "Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "1",
                 "EventName": "INSTRUCTIONS",
                 "BriefDescription": "Instructions",
                 "PublicDescription": "Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "2",
                 "EventName": "L1I_DIR_WRITES",
                 "BriefDescription": "L1I Directory Writes",
                 "PublicDescription": "Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "3",
                 "EventName": "L1I_PENALTY_CYCLES",
                 "BriefDescription": "L1I Penalty Cycles",
                 "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "4",
                 "EventName": "L1D_DIR_WRITES",
                 "BriefDescription": "L1D Directory Writes",
                 "PublicDescription": "Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "5",
                 "EventName": "L1D_PENALTY_CYCLES",
                 "BriefDescription": "L1D Penalty Cycles",
                 "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "32",
                 "EventName": "PROBLEM_STATE_CPU_CYCLES",
                 "BriefDescription": "Problem-State CPU Cycles",
                 "PublicDescription": "Problem-State Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "33",
                 "EventName": "PROBLEM_STATE_INSTRUCTIONS",
                 "BriefDescription": "Problem-State Instructions",
                 "PublicDescription": "Problem-State Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "34",
                 "EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
                 "BriefDescription": "Problem-State L1I Directory Writes",
                 "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "35",
                 "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1I Penalty Cycles",
                 "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "36",
                 "EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
                 "BriefDescription": "Problem-State L1D Directory Writes",
                 "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "37",
                 "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "64",
                 "EventName": "PRNG_FUNCTIONS",
                 "BriefDescription": "PRNG Functions",
                 "PublicDescription": "Total number of the PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "65",
                 "EventName": "PRNG_CYCLES",
                 "BriefDescription": "PRNG Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "66",
                 "EventName": "PRNG_BLOCKED_FUNCTIONS",
                 "BriefDescription": "PRNG Blocked Functions",
                 "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "67",
                 "EventName": "PRNG_BLOCKED_CYCLES",
                 "BriefDescription": "PRNG Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "68",
                 "EventName": "SHA_FUNCTIONS",
                 "BriefDescription": "SHA Functions",
                 "PublicDescription": "Total number of SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "69",
                 "EventName": "SHA_CYCLES",
                 "BriefDescription": "SHA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "70",
                 "EventName": "SHA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "SHA Blocked Functions",
                 "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "71",
                 "EventName": "SHA_BLOCKED_CYCLES",
                 "BriefDescription": "SHA Bloced Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "72",
                 "EventName": "DEA_FUNCTIONS",
                 "BriefDescription": "DEA Functions",
                 "PublicDescription": "Total number of the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "73",
                 "EventName": "DEA_CYCLES",
                 "BriefDescription": "DEA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "74",
                 "EventName": "DEA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "DEA Blocked Functions",
                 "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "75",
                 "EventName": "DEA_BLOCKED_CYCLES",
                 "BriefDescription": "DEA Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "76",
                 "EventName": "AES_FUNCTIONS",
                 "BriefDescription": "AES Functions",
                 "PublicDescription": "Total number of AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "77",
                 "EventName": "AES_CYCLES",
                 "BriefDescription": "AES Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "78",
                 "EventName": "AES_BLOCKED_FUNCTIONS",
                 "BriefDescription": "AES Blocked Functions",
                 "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "79",
                 "EventName": "AES_BLOCKED_CYCLES",
                 "BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "128",
                 "EventName": "L1I_L2_SOURCED_WRITES",
                 "BriefDescription": "L1I L2 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "129",
                 "EventName": "L1D_L2_SOURCED_WRITES",
                 "BriefDescription": "L1D L2 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "130",
                 "EventName": "L1I_L3_LOCAL_WRITES",
                 "BriefDescription": "L1I L3 Local Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "131",
                 "EventName": "L1D_L3_LOCAL_WRITES",
                 "BriefDescription": "L1D L3 Local Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "132",
                 "EventName": "L1I_L3_REMOTE_WRITES",
                 "BriefDescription": "L1I L3 Remote Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "133",
                 "EventName": "L1D_L3_REMOTE_WRITES",
                 "BriefDescription": "L1D L3 Remote Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "134",
                 "EventName": "L1D_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1D Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "135",
                 "EventName": "L1I_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1I Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "136",
                 "EventName": "L1D_RO_EXCL_WRITES",
                 "BriefDescription": "L1D Read-only Exclusive Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "137",
                 "EventName": "L1I_CACHELINE_INVALIDATES",
                 "BriefDescription": "L1I Cacheline Invalidates",
                 "PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "138",
                 "EventName": "ITLB1_WRITES",
                 "BriefDescription": "ITLB1 Writes",
                 "PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "139",
                 "EventName": "DTLB1_WRITES",
                 "BriefDescription": "DTLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "140",
                 "EventName": "TLB2_PTE_WRITES",
                 "BriefDescription": "TLB2 PTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "141",
                 "EventName": "TLB2_CRSTE_WRITES",
                 "BriefDescription": "TLB2 CRSTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "142",
                 "EventName": "TLB2_CRSTE_HPAGE_WRITES",
                 "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "145",
                 "EventName": "ITLB1_MISSES",
                 "BriefDescription": "ITLB1 Misses",
                 "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "146",
                 "EventName": "DTLB1_MISSES",
                 "BriefDescription": "DTLB1 Misses",
                 "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "147",
                 "EventName": "L2C_STORES_SENT",
                 "BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "0",
                 "EventName": "CPU_CYCLES",
                 "BriefDescription": "CPU Cycles",
                 "PublicDescription": "Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "1",
                 "EventName": "INSTRUCTIONS",
                 "BriefDescription": "Instructions",
                 "PublicDescription": "Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "2",
                 "EventName": "L1I_DIR_WRITES",
                 "BriefDescription": "L1I Directory Writes",
                 "PublicDescription": "Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "3",
                 "EventName": "L1I_PENALTY_CYCLES",
                 "BriefDescription": "L1I Penalty Cycles",
                 "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "4",
                 "EventName": "L1D_DIR_WRITES",
                 "BriefDescription": "L1D Directory Writes",
                 "PublicDescription": "Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "5",
                 "EventName": "L1D_PENALTY_CYCLES",
                 "BriefDescription": "L1D Penalty Cycles",
                 "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "32",
                 "EventName": "PROBLEM_STATE_CPU_CYCLES",
                 "BriefDescription": "Problem-State CPU Cycles",
                 "PublicDescription": "Problem-State Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "33",
                 "EventName": "PROBLEM_STATE_INSTRUCTIONS",
                 "BriefDescription": "Problem-State Instructions",
                 "PublicDescription": "Problem-State Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "34",
                 "EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
                 "BriefDescription": "Problem-State L1I Directory Writes",
                 "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "35",
                 "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1I Penalty Cycles",
                 "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "36",
                 "EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
                 "BriefDescription": "Problem-State L1D Directory Writes",
                 "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "37",
                 "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "64",
                 "EventName": "PRNG_FUNCTIONS",
                 "BriefDescription": "PRNG Functions",
                 "PublicDescription": "Total number of the PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "65",
                 "EventName": "PRNG_CYCLES",
                 "BriefDescription": "PRNG Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "66",
                 "EventName": "PRNG_BLOCKED_FUNCTIONS",
                 "BriefDescription": "PRNG Blocked Functions",
                 "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "67",
                 "EventName": "PRNG_BLOCKED_CYCLES",
                 "BriefDescription": "PRNG Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "68",
                 "EventName": "SHA_FUNCTIONS",
                 "BriefDescription": "SHA Functions",
                 "PublicDescription": "Total number of SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "69",
                 "EventName": "SHA_CYCLES",
                 "BriefDescription": "SHA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "70",
                 "EventName": "SHA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "SHA Blocked Functions",
                 "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "71",
                 "EventName": "SHA_BLOCKED_CYCLES",
                 "BriefDescription": "SHA Bloced Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "72",
                 "EventName": "DEA_FUNCTIONS",
                 "BriefDescription": "DEA Functions",
                 "PublicDescription": "Total number of the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "73",
                 "EventName": "DEA_CYCLES",
                 "BriefDescription": "DEA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "74",
                 "EventName": "DEA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "DEA Blocked Functions",
                 "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "75",
                 "EventName": "DEA_BLOCKED_CYCLES",
                 "BriefDescription": "DEA Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "76",
                 "EventName": "AES_FUNCTIONS",
                 "BriefDescription": "AES Functions",
                 "PublicDescription": "Total number of AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "77",
                 "EventName": "AES_CYCLES",
                 "BriefDescription": "AES Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "78",
                 "EventName": "AES_BLOCKED_FUNCTIONS",
                 "BriefDescription": "AES Blocked Functions",
                 "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "79",
                 "EventName": "AES_BLOCKED_CYCLES",
                 "BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "128",
                 "EventName": "L1D_RO_EXCL_WRITES",
                 "BriefDescription": "L1D Read-only Exclusive Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "129",
                 "EventName": "DTLB1_WRITES",
                 "BriefDescription": "DTLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "130",
                 "EventName": "DTLB1_MISSES",
                 "BriefDescription": "DTLB1 Misses",
                 "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "131",
                 "EventName": "DTLB1_HPAGE_WRITES",
                 "BriefDescription": "DTLB1 One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "132",
                 "EventName": "DTLB1_GPAGE_WRITES",
                 "BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
                 "PublicDescription": "Counter:132       Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "133",
                 "EventName": "L1D_L2D_SOURCED_WRITES",
                 "BriefDescription": "L1D L2D Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "134",
                 "EventName": "ITLB1_WRITES",
                 "BriefDescription": "ITLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "135",
                 "EventName": "ITLB1_MISSES",
                 "BriefDescription": "ITLB1 Misses",
                 "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "136",
                 "EventName": "L1I_L2I_SOURCED_WRITES",
                 "BriefDescription": "L1I L2I Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "137",
                 "EventName": "TLB2_PTE_WRITES",
                 "BriefDescription": "TLB2 PTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "138",
                 "EventName": "TLB2_CRSTE_HPAGE_WRITES",
                 "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "139",
                 "EventName": "TLB2_CRSTE_WRITES",
                 "BriefDescription": "TLB2 CRSTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "140",
                 "EventName": "TX_C_TEND",
                 "BriefDescription": "Completed TEND instructions in constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "141",
                 "EventName": "TX_NC_TEND",
                 "BriefDescription": "Completed TEND instructions in non-constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "143",
                 "EventName": "L1C_TLB1_MISSES",
                 "BriefDescription": "L1C TLB1 Misses",
                 "PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "144",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "145",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "146",
                 "EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Node L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "147",
                 "EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "148",
                 "EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Node L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "149",
                 "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "150",
                 "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "151",
                 "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Drawer L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "152",
                 "EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "153",
                 "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "154",
                 "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "155",
                 "EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "156",
                 "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "157",
                 "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "158",
                 "EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Node Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "159",
                 "EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "160",
                 "EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "161",
                 "EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "162",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "163",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "164",
                 "EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "165",
                 "EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "166",
                 "EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Node L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "167",
                 "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "168",
                 "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "169",
                 "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Drawer L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "170",
                 "EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "171",
                 "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "172",
                 "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "173",
                 "EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "174",
                 "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "175",
                 "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "176",
                 "EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Node Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "177",
                 "EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "178",
                 "EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "179",
                 "EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "218",
                 "EventName": "TX_NC_TABORT",
                 "BriefDescription": "Aborted transactions in non-constrained TX mode",
                 "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "219",
                 "EventName": "TX_C_TABORT_NO_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
                 "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "220",
                 "EventName": "TX_C_TABORT_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
                 "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "448",
                 "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
                 "BriefDescription": "Cycle count with one thread active",
                 "PublicDescription": "Cycle count with one thread active"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "449",
                 "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
                 "BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "0",
                 "EventName": "CPU_CYCLES",
                 "BriefDescription": "CPU Cycles",
                 "PublicDescription": "Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "1",
                 "EventName": "INSTRUCTIONS",
                 "BriefDescription": "Instructions",
                 "PublicDescription": "Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "2",
                 "EventName": "L1I_DIR_WRITES",
                 "BriefDescription": "L1I Directory Writes",
                 "PublicDescription": "Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "3",
                 "EventName": "L1I_PENALTY_CYCLES",
                 "BriefDescription": "L1I Penalty Cycles",
                 "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "4",
                 "EventName": "L1D_DIR_WRITES",
                 "BriefDescription": "L1D Directory Writes",
                 "PublicDescription": "Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "5",
                 "EventName": "L1D_PENALTY_CYCLES",
                 "BriefDescription": "L1D Penalty Cycles",
                 "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "32",
                 "EventName": "PROBLEM_STATE_CPU_CYCLES",
                 "BriefDescription": "Problem-State CPU Cycles",
                 "PublicDescription": "Problem-State Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "33",
                 "EventName": "PROBLEM_STATE_INSTRUCTIONS",
                 "BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "64",
                 "EventName": "PRNG_FUNCTIONS",
                 "BriefDescription": "PRNG Functions",
                 "PublicDescription": "Total number of the PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "65",
                 "EventName": "PRNG_CYCLES",
                 "BriefDescription": "PRNG Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "66",
                 "EventName": "PRNG_BLOCKED_FUNCTIONS",
                 "BriefDescription": "PRNG Blocked Functions",
                 "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "67",
                 "EventName": "PRNG_BLOCKED_CYCLES",
                 "BriefDescription": "PRNG Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "68",
                 "EventName": "SHA_FUNCTIONS",
                 "BriefDescription": "SHA Functions",
                 "PublicDescription": "Total number of SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "69",
                 "EventName": "SHA_CYCLES",
                 "BriefDescription": "SHA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "70",
                 "EventName": "SHA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "SHA Blocked Functions",
                 "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "71",
                 "EventName": "SHA_BLOCKED_CYCLES",
                 "BriefDescription": "SHA Bloced Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "72",
                 "EventName": "DEA_FUNCTIONS",
                 "BriefDescription": "DEA Functions",
                 "PublicDescription": "Total number of the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "73",
                 "EventName": "DEA_CYCLES",
                 "BriefDescription": "DEA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "74",
                 "EventName": "DEA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "DEA Blocked Functions",
                 "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "75",
                 "EventName": "DEA_BLOCKED_CYCLES",
                 "BriefDescription": "DEA Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "76",
                 "EventName": "AES_FUNCTIONS",
                 "BriefDescription": "AES Functions",
                 "PublicDescription": "Total number of AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "77",
                 "EventName": "AES_CYCLES",
                 "BriefDescription": "AES Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "78",
                 "EventName": "AES_BLOCKED_FUNCTIONS",
                 "BriefDescription": "AES Blocked Functions",
                 "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "79",
                 "EventName": "AES_BLOCKED_CYCLES",
                 "BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "128",
                 "EventName": "L1D_RO_EXCL_WRITES",
                 "BriefDescription": "L1D Read-only Exclusive Writes",
                 "PublicDescription": "Counter:128       Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "129",
                 "EventName": "DTLB2_WRITES",
                 "BriefDescription": "DTLB2 Writes",
                 "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "130",
                 "EventName": "DTLB2_MISSES",
                 "BriefDescription": "DTLB2 Misses",
                 "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "131",
                 "EventName": "DTLB2_HPAGE_WRITES",
                 "BriefDescription": "DTLB2 One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "132",
                 "EventName": "DTLB2_GPAGE_WRITES",
                 "BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
                 "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "133",
                 "EventName": "L1D_L2D_SOURCED_WRITES",
                 "BriefDescription": "L1D L2D Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "134",
                 "EventName": "ITLB2_WRITES",
                 "BriefDescription": "ITLB2 Writes",
                 "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "135",
                 "EventName": "ITLB2_MISSES",
                 "BriefDescription": "ITLB2 Misses",
                 "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "136",
                 "EventName": "L1I_L2I_SOURCED_WRITES",
                 "BriefDescription": "L1I L2I Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "137",
                 "EventName": "TLB2_PTE_WRITES",
                 "BriefDescription": "TLB2 PTE Writes",
                 "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "138",
                 "EventName": "TLB2_CRSTE_WRITES",
                 "BriefDescription": "TLB2 CRSTE Writes",
                 "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "139",
                 "EventName": "TLB2_ENGINES_BUSY",
                 "BriefDescription": "TLB2 Engines Busy",
                 "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "140",
                 "EventName": "TX_C_TEND",
                 "BriefDescription": "Completed TEND instructions in constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "141",
                 "EventName": "TX_NC_TEND",
                 "BriefDescription": "Completed TEND instructions in non-constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "143",
                 "EventName": "L1C_TLB2_MISSES",
                 "BriefDescription": "L1C TLB2 Misses",
                 "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "144",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "145",
                 "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "146",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "147",
                 "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Cluster L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "148",
                 "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Cluster Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "149",
                 "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "150",
                 "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "151",
                 "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "152",
                 "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "153",
                 "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "154",
                 "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "155",
                 "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "156",
                 "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "157",
                 "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "158",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "162",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "163",
                 "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "164",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "165",
                 "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Cluster L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "166",
                 "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Cluster Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "167",
                 "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "168",
                 "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "169",
                 "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "170",
                 "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "171",
                 "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "172",
                 "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "173",
                 "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "174",
                 "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "175",
                 "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "224",
                 "EventName": "BCD_DFP_EXECUTION_SLOTS",
                 "BriefDescription": "BCD DFP Execution Slots",
                 "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "225",
                 "EventName": "VX_BCD_EXECUTION_SLOTS",
                 "BriefDescription": "VX BCD Execution Slots",
                 "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "226",
                 "EventName": "DECIMAL_INSTRUCTIONS",
                 "BriefDescription": "Decimal Instructions",
                 "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "232",
                 "EventName": "LAST_HOST_TRANSLATIONS",
                 "BriefDescription": "Last host translation done",
                 "PublicDescription": "Last Host Translation done"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "243",
                 "EventName": "TX_NC_TABORT",
                 "BriefDescription": "Aborted transactions in non-constrained TX mode",
                 "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "244",
                 "EventName": "TX_C_TABORT_NO_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
                 "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "245",
                 "EventName": "TX_C_TABORT_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
                 "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "448",
                 "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
                 "BriefDescription": "Cycle count with one thread active",
                 "PublicDescription": "Cycle count with one thread active"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "449",
                 "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
                 "BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "0",
                 "EventName": "CPU_CYCLES",
                 "BriefDescription": "CPU Cycles",
                 "PublicDescription": "Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "1",
                 "EventName": "INSTRUCTIONS",
                 "BriefDescription": "Instructions",
                 "PublicDescription": "Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "2",
                 "EventName": "L1I_DIR_WRITES",
                 "BriefDescription": "L1I Directory Writes",
                 "PublicDescription": "Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "3",
                 "EventName": "L1I_PENALTY_CYCLES",
                 "BriefDescription": "L1I Penalty Cycles",
                 "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "4",
                 "EventName": "L1D_DIR_WRITES",
                 "BriefDescription": "L1D Directory Writes",
                 "PublicDescription": "Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "5",
                 "EventName": "L1D_PENALTY_CYCLES",
                 "BriefDescription": "L1D Penalty Cycles",
                 "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "32",
                 "EventName": "PROBLEM_STATE_CPU_CYCLES",
                 "BriefDescription": "Problem-State CPU Cycles",
                 "PublicDescription": "Problem-State Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "33",
                 "EventName": "PROBLEM_STATE_INSTRUCTIONS",
                 "BriefDescription": "Problem-State Instructions",
                 "PublicDescription": "Problem-State Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "34",
                 "EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
                 "BriefDescription": "Problem-State L1I Directory Writes",
                 "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "35",
                 "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1I Penalty Cycles",
                 "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "36",
                 "EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
                 "BriefDescription": "Problem-State L1D Directory Writes",
                 "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "37",
                 "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "64",
                 "EventName": "PRNG_FUNCTIONS",
                 "BriefDescription": "PRNG Functions",
                 "PublicDescription": "Total number of the PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "65",
                 "EventName": "PRNG_CYCLES",
                 "BriefDescription": "PRNG Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "66",
                 "EventName": "PRNG_BLOCKED_FUNCTIONS",
                 "BriefDescription": "PRNG Blocked Functions",
                 "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "67",
                 "EventName": "PRNG_BLOCKED_CYCLES",
                 "BriefDescription": "PRNG Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "68",
                 "EventName": "SHA_FUNCTIONS",
                 "BriefDescription": "SHA Functions",
                 "PublicDescription": "Total number of SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "69",
                 "EventName": "SHA_CYCLES",
                 "BriefDescription": "SHA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "70",
                 "EventName": "SHA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "SHA Blocked Functions",
                 "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "71",
                 "EventName": "SHA_BLOCKED_CYCLES",
                 "BriefDescription": "SHA Bloced Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "72",
                 "EventName": "DEA_FUNCTIONS",
                 "BriefDescription": "DEA Functions",
                 "PublicDescription": "Total number of the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "73",
                 "EventName": "DEA_CYCLES",
                 "BriefDescription": "DEA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "74",
                 "EventName": "DEA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "DEA Blocked Functions",
                 "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "75",
                 "EventName": "DEA_BLOCKED_CYCLES",
                 "BriefDescription": "DEA Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "76",
                 "EventName": "AES_FUNCTIONS",
                 "BriefDescription": "AES Functions",
                 "PublicDescription": "Total number of AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "77",
                 "EventName": "AES_CYCLES",
                 "BriefDescription": "AES Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "78",
                 "EventName": "AES_BLOCKED_FUNCTIONS",
                 "BriefDescription": "AES Blocked Functions",
                 "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "79",
                 "EventName": "AES_BLOCKED_CYCLES",
                 "BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "128",
                 "EventName": "L1D_L2_SOURCED_WRITES",
                 "BriefDescription": "L1D L2 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "129",
                 "EventName": "L1I_L2_SOURCED_WRITES",
                 "BriefDescription": "L1I L2 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "130",
                 "EventName": "DTLB1_MISSES",
                 "BriefDescription": "DTLB1 Misses",
                 "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "131",
                 "EventName": "ITLB1_MISSES",
                 "BriefDescription": "ITLB1 Misses",
                 "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "133",
                 "EventName": "L2C_STORES_SENT",
                 "BriefDescription": "L2C Stores Sent",
                 "PublicDescription": "Incremented by one for every store sent to Level-2 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "134",
                 "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Book L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "135",
                 "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "136",
                 "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "137",
                 "EventName": "L1D_RO_EXCL_WRITES",
                 "BriefDescription": "L1D Read-only Exclusive Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "138",
                 "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "139",
                 "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "140",
                 "EventName": "DTLB1_HPAGE_WRITES",
                 "BriefDescription": "DTLB1 One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "141",
                 "EventName": "L1D_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1D Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "142",
                 "EventName": "L1I_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1I Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "143",
                 "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Book L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "144",
                 "EventName": "DTLB1_WRITES",
                 "BriefDescription": "DTLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "145",
                 "EventName": "ITLB1_WRITES",
                 "BriefDescription": "ITLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "146",
                 "EventName": "TLB2_PTE_WRITES",
                 "BriefDescription": "TLB2 PTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "147",
                 "EventName": "TLB2_CRSTE_HPAGE_WRITES",
                 "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "148",
                 "EventName": "TLB2_CRSTE_WRITES",
                 "BriefDescription": "TLB2 CRSTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "150",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "152",
                 "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "153",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "155",
                 "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "0",
                 "EventName": "CPU_CYCLES",
                 "BriefDescription": "CPU Cycles",
                 "PublicDescription": "Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "1",
                 "EventName": "INSTRUCTIONS",
                 "BriefDescription": "Instructions",
                 "PublicDescription": "Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "2",
                 "EventName": "L1I_DIR_WRITES",
                 "BriefDescription": "L1I Directory Writes",
                 "PublicDescription": "Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "3",
                 "EventName": "L1I_PENALTY_CYCLES",
                 "BriefDescription": "L1I Penalty Cycles",
                 "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "4",
                 "EventName": "L1D_DIR_WRITES",
                 "BriefDescription": "L1D Directory Writes",
                 "PublicDescription": "Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "5",
                 "EventName": "L1D_PENALTY_CYCLES",
                 "BriefDescription": "L1D Penalty Cycles",
                 "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "32",
                 "EventName": "PROBLEM_STATE_CPU_CYCLES",
                 "BriefDescription": "Problem-State CPU Cycles",
                 "PublicDescription": "Problem-State Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "33",
                 "EventName": "PROBLEM_STATE_INSTRUCTIONS",
                 "BriefDescription": "Problem-State Instructions",
                 "PublicDescription": "Problem-State Instruction Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "34",
                 "EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
                 "BriefDescription": "Problem-State L1I Directory Writes",
                 "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "35",
                 "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1I Penalty Cycles",
                 "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "36",
                 "EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
                 "BriefDescription": "Problem-State L1D Directory Writes",
                 "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "37",
                 "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
                 "BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "64",
                 "EventName": "PRNG_FUNCTIONS",
                 "BriefDescription": "PRNG Functions",
                 "PublicDescription": "Total number of the PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "65",
                 "EventName": "PRNG_CYCLES",
                 "BriefDescription": "PRNG Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "66",
                 "EventName": "PRNG_BLOCKED_FUNCTIONS",
                 "BriefDescription": "PRNG Blocked Functions",
                 "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "67",
                 "EventName": "PRNG_BLOCKED_CYCLES",
                 "BriefDescription": "PRNG Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "68",
                 "EventName": "SHA_FUNCTIONS",
                 "BriefDescription": "SHA Functions",
                 "PublicDescription": "Total number of SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "69",
                 "EventName": "SHA_CYCLES",
                 "BriefDescription": "SHA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "70",
                 "EventName": "SHA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "SHA Blocked Functions",
                 "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "71",
                 "EventName": "SHA_BLOCKED_CYCLES",
                 "BriefDescription": "SHA Bloced Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "72",
                 "EventName": "DEA_FUNCTIONS",
                 "BriefDescription": "DEA Functions",
                 "PublicDescription": "Total number of the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "73",
                 "EventName": "DEA_CYCLES",
                 "BriefDescription": "DEA Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "74",
                 "EventName": "DEA_BLOCKED_FUNCTIONS",
                 "BriefDescription": "DEA Blocked Functions",
                 "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "75",
                 "EventName": "DEA_BLOCKED_CYCLES",
                 "BriefDescription": "DEA Blocked Cycles",
                 "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "76",
                 "EventName": "AES_FUNCTIONS",
                 "BriefDescription": "AES Functions",
                 "PublicDescription": "Total number of AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "77",
                 "EventName": "AES_CYCLES",
                 "BriefDescription": "AES Cycles",
                 "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "78",
                 "EventName": "AES_BLOCKED_FUNCTIONS",
                 "BriefDescription": "AES Blocked Functions",
                 "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "79",
                 "EventName": "AES_BLOCKED_CYCLES",
                 "BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "128",
                 "EventName": "DTLB1_MISSES",
                 "BriefDescription": "DTLB1 Misses",
                 "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "129",
                 "EventName": "ITLB1_MISSES",
                 "BriefDescription": "ITLB1 Misses",
                 "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "130",
                 "EventName": "L1D_L2I_SOURCED_WRITES",
                 "BriefDescription": "L1D L2I Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "131",
                 "EventName": "L1I_L2I_SOURCED_WRITES",
                 "BriefDescription": "L1I L2I Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "132",
                 "EventName": "L1D_L2D_SOURCED_WRITES",
                 "BriefDescription": "L1D L2D Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "133",
                 "EventName": "DTLB1_WRITES",
                 "BriefDescription": "DTLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "135",
                 "EventName": "L1D_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1D Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "137",
                 "EventName": "L1I_LMEM_SOURCED_WRITES",
                 "BriefDescription": "L1I Local Memory Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "138",
                 "EventName": "L1D_RO_EXCL_WRITES",
                 "BriefDescription": "L1D Read-only Exclusive Writes",
                 "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "139",
                 "EventName": "DTLB1_HPAGE_WRITES",
                 "BriefDescription": "DTLB1 One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "140",
                 "EventName": "ITLB1_WRITES",
                 "BriefDescription": "ITLB1 Writes",
                 "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "141",
                 "EventName": "TLB2_PTE_WRITES",
                 "BriefDescription": "TLB2 PTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "142",
                 "EventName": "TLB2_CRSTE_HPAGE_WRITES",
                 "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "143",
                 "EventName": "TLB2_CRSTE_WRITES",
                 "BriefDescription": "TLB2 CRSTE Writes",
                 "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "144",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "145",
                 "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "146",
                 "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Book L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "147",
                 "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D On-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "148",
                 "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1D Off-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "149",
                 "EventName": "TX_NC_TEND",
                 "BriefDescription": "Completed TEND instructions in non-constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "150",
                 "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "151",
                 "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "152",
                 "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "153",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "154",
                 "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Chip L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "155",
                 "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Book L3 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "156",
                 "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I On-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "157",
                 "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
                 "BriefDescription": "L1I Off-Book L4 Sourced Writes",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "158",
                 "EventName": "TX_C_TEND",
                 "BriefDescription": "Completed TEND instructions in constrained TX mode",
                 "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "159",
                 "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "160",
                 "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "161",
                 "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
                 "BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
                 "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "177",
                 "EventName": "TX_NC_TABORT",
                 "BriefDescription": "Aborted transactions in non-constrained TX mode",
                 "PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "178",
                 "EventName": "TX_C_TABORT_NO_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
                 "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
         },
         {
+                "Unit": "CPU-M-CF",
                 "EventCode": "179",
                 "EventName": "TX_C_TABORT_SPECIAL",
                 "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
         { "QPI LL", "uncore_qpi" },
         { "SBO", "uncore_sbox" },
         { "iMPH-U", "uncore_arb" },
+        { "CPU-M-CF", "cpum_cf" },
+        { "CPU-M-SF", "cpum_sf" },
         {}
 };
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index dd850a26d579..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
         if (!t->subtest.get_nr)
                 pr_debug("%s:", t->desc);
         else
-                pr_debug("%s subtest %d:", t->desc, subtest);
+                pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
         switch (err) {
         case TEST_OK:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 61211918bfba..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
         return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+        return 0;
+}
+
 static int count_tracepoints(void)
 {
         struct dirent *events_ent;
@@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = {
                 .check = test__intel_pt,
                 .id    = 52,
         },
+        {
+                .name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+                .check = test__checkevent_complex_name,
+                .id    = 53
+        }
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
                 .check = test__checkevent_pmu_partial_time_callgraph,
                 .id    = 2,
         },
+        {
+                .name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+                .check = test__checkevent_complex_name,
+                .id    = 3,
+        }
 };
 
 struct terms_test {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 94e513e62b34..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,11 +13,24 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+        event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+                        grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+        if [ $? -ne 0 -o -z "$event_name" ] ; then
+                printf "FAIL: could not add event\n"
+                return 1
+        fi
+}
+
 trace_libc_inet_pton_backtrace() {
 
         expected=`mktemp -u /tmp/expected.XXX`
 
-        echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+        echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
         echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
         case "$(uname -m)" in
         s390x)
@@ -26,6 +39,12 @@ trace_libc_inet_pton_backtrace() {
                 echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
                 echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
                 ;;
+        ppc64|ppc64le)
+                eventattr='max-stack=4'
+                echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+                echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+                echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+                ;;
         *)
                 eventattr='max-stack=3'
                 echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
@@ -35,7 +54,7 @@ trace_libc_inet_pton_backtrace() {
 
         perf_data=`mktemp -u /tmp/perf.data.XXX`
         perf_script=`mktemp -u /tmp/perf.script.XXX`
-        perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+        perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
         perf script -i $perf_data > $perf_script
 
         exec 3<$perf_script
@@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() {
                 echo "$line" | egrep -q "$pattern"
                 if [ $? -ne 0 ] ; then
                         printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
-                        exit 1
+                        return 1
                 fi
         done
 
@@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
         # even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+        if [ -n "$event_name" ] ; then
+                perf probe -q -d $event_name
+        fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${perf_data} ${perf_script} ${expected}
-perf probe -q -d probe_libc:inet_pton
+delete_libc_inet_pton_event
 exit $err
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
         sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[      ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/     [\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[     ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[     ]\+0x" $header_dir/i915_drm.h | \
         sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[       ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h    | \
+egrep $regex ${header_dir}/kvm.h        | \
         sed -r "s/$regex/\2 \1/g"       | \
         egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
         sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
         sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
         sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+        static DEFINE_STRARRAY(socket_ipproto);
+
+        return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int domain = syscall_arg__val(arg, 0);
+
+        if (domain == AF_INET || domain == AF_INET6)
+                return socket__scnprintf_ipproto(arg->val, bf, size);
+
+        return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
         sed -r "s/$regex/\2 \1/g"       | \
         sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
         sed -r "s/$regex/\2 \1/g"       | \
         sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                                char *bf, size_t bfsz, FILE *fp,
-                               bool use_callchain)
+                               bool ignore_callchains)
 {
         int ret;
         int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
         ret = fprintf(fp, "%s\n", bf);
 
-        if (hist_entry__has_callchains(he) && use_callchain)
+        if (hist_entry__has_callchains(he) && !ignore_callchains)
                 callchain_ret = hist_entry_callchain__fprintf(he, total_period,
                                                               0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                       int max_cols, float min_pcnt, FILE *fp,
-                      bool use_callchain)
+                      bool ignore_callchains)
 {
         struct rb_node *nd;
         size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 if (percent < min_pcnt)
                         continue;
 
-                ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+                ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
                 if (max_rows && ++nr_rows >= max_rows)
                         break;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
         err = bpf_object__load(obj);
         if (err) {
-                pr_debug("bpf: load objects failed\n");
+                char bf[128];
+                libbpf_strerror(err, bf, sizeof(bf));
+                pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
                 return err;
         }
         return 0;
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-        if (cs)
-                refcount_inc(&cs->refcnt);
-        return cs;
+        if (cs && refcount_inc_not_zero(&cs->refcnt))
+                return cs;
+
+        return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
                 parent = *p;
                 iter = rb_entry(parent, struct comm_str, rb_node);
 
+                /*
+                 * If we race with comm_str__put, iter->refcnt is 0
+                 * and it will be removed within comm_str__put call
+                 * shortly, ignore it in this search.
+                 */
                 cmp = strcmp(str, iter->str);
-                if (!cmp)
-                        return comm_str__get(iter);
+                if (!cmp && comm_str__get(iter))
+                        return iter;
 
                 if (cmp < 0)
                         p = &(*p)->rb_left;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR       0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
         void *data;
         void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
         decoder->tail = 0;
         decoder->packet_count = 0;
         for (i = 0; i < MAX_BUFFER; i++) {
-                decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-                decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+                decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+                decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
                 decoder->packet_buffer[i].last_instr_taken_branch = false;
                 decoder->packet_buffer[i].exc = false;
                 decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
         decoder->packet_buffer[et].exc = false;
         decoder->packet_buffer[et].exc_ret = false;
         decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-        decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-        decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+        decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+        decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
         if (decoder->packet_count == MAX_BUFFER - 1)
                 return OCSD_RESP_WAIT;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+        CS_ETM_EMPTY = 0,
         CS_ETM_RANGE = 1 << 0,
         CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+        /* Returns 0 for the CS_ETM_TRACE_ON packet */
+        if (packet->sample_type == CS_ETM_TRACE_ON)
+                return 0;
+
         /*
          * The packet records the execution range with an exclusive end address
          *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
         return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+        /* Returns 0 for the CS_ETM_TRACE_ON packet */
+        if (packet->sample_type == CS_ETM_TRACE_ON)
+                return 0;
+
+        return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
         /*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
         be       = &bs->entries[etmq->last_branch_pos];
         be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-        be->to   = etmq->packet->start_addr;
+        be->to   = cs_etm__first_executed_instr(etmq->packet);
         /* No support for mispredict */
         be->flags.mispred = 0;
         be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
         sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
         sample.pid = etmq->pid;
         sample.tid = etmq->tid;
-        sample.addr = etmq->packet->start_addr;
+        sample.addr = cs_etm__first_executed_instr(etmq->packet);
         sample.id = etmq->etm->branches_id;
         sample.stream_id = etmq->etm->branches_id;
         sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
                 etmq->period_instructions = instrs_over;
         }
 
-        if (etm->sample_branches &&
-            etmq->prev_packet &&
-            etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-            etmq->prev_packet->last_instr_taken_branch) {
-                ret = cs_etm__synth_branch_sample(etmq);
-                if (ret)
-                        return ret;
+        if (etm->sample_branches && etmq->prev_packet) {
+                bool generate_sample = false;
+
+                /* Generate sample for tracing on packet */
+                if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+                        generate_sample = true;
+
+                /* Generate sample for branch taken packet */
+                if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+                    etmq->prev_packet->last_instr_taken_branch)
+                        generate_sample = true;
+
+                if (generate_sample) {
+                        ret = cs_etm__synth_branch_sample(etmq);
+                        if (ret)
+                                return ret;
+                }
         }
 
         if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
         int err = 0;
+        struct cs_etm_auxtrace *etm = etmq->etm;
         struct cs_etm_packet *tmp;
 
+        if (!etmq->prev_packet)
+                return 0;
+
+        /* Handle start tracing packet */
+        if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+                goto swap_packet;
+
         if (etmq->etm->synth_opts.last_branch &&
-            etmq->prev_packet &&
             etmq->prev_packet->sample_type == CS_ETM_RANGE) {
                 /*
                  * Generate a last branch event for the branches left in the
@@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
                 err = cs_etm__synth_instruction_sample(
                         etmq, addr,
                         etmq->period_instructions);
+                if (err)
+                        return err;
+
                 etmq->period_instructions = 0;
 
+        }
+
+        if (etm->sample_branches &&
+            etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+                err = cs_etm__synth_branch_sample(etmq);
+                if (err)
+                        return err;
+        }
+
+swap_packet:
+        if (etmq->etm->synth_opts.last_branch) {
                 /*
                  * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
                  * the next incoming packet.
@@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
                                          */
                                         cs_etm__flush(etmq);
                                         break;
+                                case CS_ETM_EMPTY:
+                                        /*
+                                         * Should not receive empty packet,
+                                         * report error.
+                                         */
+                                        pr_err("CS ETM Trace: empty packet\n");
+                                        return -EINVAL;
                                 default:
                                         break;
                                 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
                 evsel->attr.sample_period = 1;
         }
 
+        if (perf_evsel__is_clock(evsel)) {
+                /*
+                 * The evsel->unit points to static alias->unit
+                 * so it's ok to use static string in here.
+                 */
+                static const char *unit = "msec";
+
+                evsel->unit = unit;
+                evsel->scale = 1e-6;
+        }
+
         return evsel;
 }
 
@@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
         }
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+        return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+               (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
                 else
                         perf_evsel__reset_sample_bit(evsel, PERIOD);
         }
+
+        /*
+         * For initial_delay, a dummy event is added implicitly.
+         * The software event will trigger -EOPNOTSUPP error out,
+         * if BRANCH_STACK bit is set.
+         */
+        if (opts->initial_delay && is_dummy_event(evsel))
+                perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..973c03167947 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-        struct perf_event_attr *attr = &evsel->attr;
+        return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
 
-        return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-                (attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+        return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+               perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
 struct perf_attr_details {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 653ff65aa2c3..5af58aac91ad 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPR(NUMA_TOPOLOGY, numa_topology,  true),
         FEAT_OPN(BRANCH_STACK,  branch_stack,   false),
         FEAT_OPR(PMU_MAPPINGS,  pmu_mappings,   false),
-        FEAT_OPN(GROUP_DESC,    group_desc,     false),
+        FEAT_OPR(GROUP_DESC,    group_desc,     false),
         FEAT_OPN(AUXTRACE,      auxtrace,       false),
         FEAT_OPN(STAT,          stat,           false),
         FEAT_OPN(CACHE,         cache,          true),
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                       int max_cols, float min_pcnt, FILE *fp,
-                      bool use_callchain);
+                      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..b300a3973448 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-                                                  struct threads *threads,
-                                                  pid_t pid, pid_t tid,
-                                                  bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+                          int pid, int tid)
 {
-        struct rb_node **p = &threads->entries.rb_node;
-        struct rb_node *parent = NULL;
         struct thread *th;
 
-        /*
-         * Front-end cache - TID lookups come in blocks,
-         * so most of the time we dont have to look up
-         * the full rbtree:
-         */
         th = threads->last_match;
         if (th != NULL) {
                 if (th->tid == tid) {
@@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                 threads->last_match = NULL;
         }
 
+        return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+                        int pid, int tid)
+{
+        struct thread *th = NULL;
+
+        if (perf_singlethreaded)
+                th = __threads__get_last_match(threads, machine, pid, tid);
+
+        return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+        threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+        if (perf_singlethreaded)
+                __threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+                                                  struct threads *threads,
+                                                  pid_t pid, pid_t tid,
+                                                  bool create)
+{
+        struct rb_node **p = &threads->entries.rb_node;
+        struct rb_node *parent = NULL;
+        struct thread *th;
+
+        th = threads__get_last_match(threads, machine, pid, tid);
+        if (th)
+                return th;
+
         while (*p != NULL) {
                 parent = *p;
                 th = rb_entry(parent, struct thread, rb_node);
 
                 if (th->tid == tid) {
-                        threads->last_match = th;
+                        threads__set_last_match(threads, th);
                         machine__update_thread_pid(machine, th, pid);
                         return thread__get(th);
                 }
@@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                  * It is now in the rbtree, get a ref
                  */
                 thread__get(th);
-                threads->last_match = th;
+                threads__set_last_match(threads, th);
                 ++threads->nr;
         }
 
@@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
         struct threads *threads = machine__threads(machine, th->tid);
 
         if (threads->last_match == th)
-                threads->last_match = NULL;
+                threads__set_last_match(threads, NULL);
 
         BUG_ON(refcount_read(&th->refcnt) == 0);
         if (lock)
@@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
         struct callchain_cursor *cursor = arg;
         const char *srcline = NULL;
+        u64 addr;
 
         if (symbol_conf.hide_unresolved && entry->sym == NULL)
                 return 0;
@@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
         if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
                 return 0;
 
-        srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+        /*
+         * Convert entry->ip from a virtual address to an offset in
+         * its corresponding binary.
+         */
+        addr = map__map_ip(entry->map, entry->ip);
+
+        srcline = callchain_srcline(entry->map, entry->sym, addr);
         return callchain_cursor_append(cursor, entry->ip,
                                        entry->map, entry->sym,
                                        false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
                                 if (raw)
                                         s = (char *)pe->metric_name;
                                 else {
-                                        if (asprintf(&s, "%s\n\t[%s]",
-                                                     pe->metric_name, pe->desc) < 0)
+                                        if (asprintf(&s, "%s\n%*s%s]",
+                                                     pe->metric_name, 8, "[", pe->desc) < 0)
                                                 return;
                                 }
 
@@ -490,3 +490,25 @@ out:
         metricgroup__free_egroups(&group_list);
         return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+        struct pmu_events_map *map = perf_pmu__find_map(NULL);
+        struct pmu_event *pe;
+        int i;
+
+        if (!map)
+                return false;
+
+        for (i = 0; ; i++) {
+                pe = &map->table[i];
+
+                if (!pe->name && !pe->metric_group && !pe->metric_name)
+                        break;
+                if (!pe->metric_expr)
+                        continue;
+                if (match_metric(pe->metric_name, metric))
+                        return true;
+        }
+        return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
                         struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 3ba6a1742f91..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
         if (stat(path, &st) == 0)
                 return 1;
 
-        /* Look for cpu sysfs (specific to s390) */
-        scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-                  sysfs, name);
-        if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-                return 1;
-
         return 0;
 }
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                         ratio = total / avg;
 
                 print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-        } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-                   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+        } else if (perf_evsel__is_clock(evsel)) {
                 if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
                         print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-                                     avg / ratio);
+                                     avg / (ratio * evsel->scale));
                 else
                         print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
         } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
         if (__report_module(&al, ip, ui))
                 return -1;
 
-        e->ip  = al.addr;
+        e->ip  = ip;
         e->map = al.map;
         e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
         struct addr_location al;
 
         e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-        e.ip = al.addr;
+        e.ip  = ip;
         e.map = al.map;
 
         pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a362e3d7abc6..fff7fb1285fc 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -22,7 +22,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
         test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
-        test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user
+        test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
+        test_socket_cookie test_cgroup_storage test_select_reuseport
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
         test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -33,7 +34,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
         test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
         test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
         test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
-        get_cgroup_id_kern.o
+        get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
+        test_skb_cgroup_id_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -44,10 +46,11 @@ TEST_PROGS := test_kmod.sh \
         test_sock_addr.sh \
         test_tunnel.sh \
         test_lwt_seg6local.sh \
-        test_lirc_mode2.sh
+        test_lirc_mode2.sh \
+        test_skb_cgroup_id.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
 
 include ../lib.mk
 
@@ -58,11 +61,15 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
 $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
+$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
+$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 
 .PHONY: force
 
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 810de20e8e26..e4be7730222d 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,6 +65,8 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
         (void *) BPF_FUNC_xdp_adjust_head;
 static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
         (void *) BPF_FUNC_xdp_adjust_meta;
+static int (*bpf_get_socket_cookie)(void *ctx) =
+        (void *) BPF_FUNC_get_socket_cookie;
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
                              int optlen) =
         (void *) BPF_FUNC_setsockopt;
@@ -109,6 +111,8 @@ static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
 static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
                                      int size, int flags) =
         (void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_sk_select_reuseport)(void *ctx, void *map, void *key, __u32 flags) =
+        (void *) BPF_FUNC_sk_select_reuseport;
 static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
         (void *) BPF_FUNC_get_stack;
 static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
@@ -133,6 +137,12 @@ static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
         (void *) BPF_FUNC_rc_keydown;
 static unsigned long long (*bpf_get_current_cgroup_id)(void) =
         (void *) BPF_FUNC_get_current_cgroup_id;
+static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
+        (void *) BPF_FUNC_get_local_storage;
+static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
+        (void *) BPF_FUNC_skb_cgroup_id;
+static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
+        (void *) BPF_FUNC_skb_ancestor_cgroup_id;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -169,6 +179,8 @@ struct bpf_map_def {
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
         (void *) BPF_FUNC_skb_load_bytes;
+static int (*bpf_skb_load_bytes_relative)(void *ctx, int off, void *to, int len, __u32 start_header) =
+        (void *) BPF_FUNC_skb_load_bytes_relative;
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
         (void *) BPF_FUNC_skb_store_bytes;
 static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index d0811b3d6a6f..315a44fa32af 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -44,4 +44,8 @@ static inline unsigned int bpf_num_possible_cpus(void)
                 name[bpf_num_possible_cpus()]
 #define bpf_percpu(name, cpu) name[(cpu)].v
 
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
 #endif /* __BPF_UTIL__ */
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index c87b4e052ce9..cf16948aad4a 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -118,7 +118,7 @@ static int join_cgroup_from_top(char *cgroup_path)
  *
  * On success, it returns 0, otherwise on failure it returns 1.
  */
-int join_cgroup(char *path)
+int join_cgroup(const char *path)
 {
         char cgroup_path[PATH_MAX + 1];
 
@@ -158,7 +158,7 @@ void cleanup_cgroup_environment(void)
  * On success, it returns the file descriptor. On failure it returns 0.
  * If there is a failure, it prints the error to stderr.
  */
-int create_and_get_cgroup(char *path)
+int create_and_get_cgroup(const char *path)
 {
         char cgroup_path[PATH_MAX + 1];
         int fd;
@@ -186,7 +186,7 @@ int create_and_get_cgroup(char *path)
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(char *path)
+unsigned long long get_cgroup_id(const char *path)
 {
         int dirfd, err, flags, mount_id, fhsize;
         union {
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 20a4a5dcd469..d64bb8957090 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -9,10 +9,10 @@
         __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
 
-int create_and_get_cgroup(char *path);
-int join_cgroup(char *path);
+int create_and_get_cgroup(const char *path);
+int join_cgroup(const char *path);
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
-unsigned long long get_cgroup_id(char *path);
+unsigned long long get_cgroup_id(const char *path);
 
 #endif
diff --git a/tools/testing/selftests/bpf/socket_cookie_prog.c b/tools/testing/selftests/bpf/socket_cookie_prog.c
new file mode 100644
index 000000000000..9ff8ac4b0bf6
--- /dev/null
+++ b/tools/testing/selftests/bpf/socket_cookie_prog.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include <sys/socket.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct bpf_map_def SEC("maps") socket_cookies = {
+        .type = BPF_MAP_TYPE_HASH,
+        .key_size = sizeof(__u64),
+        .value_size = sizeof(__u32),
+        .max_entries = 1 << 8,
+};
+
+SEC("cgroup/connect6")
+int set_cookie(struct bpf_sock_addr *ctx)
+{
+        __u32 cookie_value = 0xFF;
+        __u64 cookie_key;
+
+        if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
+                return 1;
+
+        cookie_key = bpf_get_socket_cookie(ctx);
+        if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0))
+                return 0;
+
+        return 1;
+}
+
+SEC("sockops")
+int update_cookie(struct bpf_sock_ops *ctx)
+{
+        __u32 new_cookie_value;
+        __u32 *cookie_value;
+        __u64 cookie_key;
+
+        if (ctx->family != AF_INET6)
+                return 1;
+
+        if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+                return 1;
+
+        cookie_key = bpf_get_socket_cookie(ctx);
+
+        cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key);
+        if (!cookie_value)
+                return 1;
+
+        new_cookie_value = (ctx->local_port << 8) | *cookie_value;
+        bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0);
+
+        return 1;
+}
+
+int _version SEC("version") = 1;
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
index 481dccdf140c..7f8200a8702b 100755
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python3
 #
 # SPDX-License-Identifier: GPL-2.0
 #
@@ -9,11 +9,11 @@ import subprocess
 import select
 
 def read(sock, n):
-    buf = ''
+    buf = b''
     while len(buf) < n:
         rem = n - len(buf)
         try: s = sock.recv(rem)
-        except (socket.error), e: return ''
+        except (socket.error) as e: return b''
         buf += s
     return buf
 
@@ -22,7 +22,7 @@ def send(sock, s):
     count = 0
     while count < total:
         try: n = sock.send(s)
-        except (socket.error), e: n = 0
+        except (socket.error) as e: n = 0
         if n == 0:
             return count;
         count += n
@@ -39,10 +39,10 @@ try:
 except socket.error as e:
     sys.exit(1)
 
-buf = ''
+buf = b''
 n = 0
 while n < 1000:
-    buf += '+'
+    buf += b'+'
     n += 1
 
 sock.settimeout(1);
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
index bc454d7d0be2..b39903fca4c8 100755
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python3
 #
 # SPDX-License-Identifier: GPL-2.0
 #
@@ -9,11 +9,11 @@ import subprocess
 import select
 
 def read(sock, n):
-    buf = ''
+    buf = b''
     while len(buf) < n:
         rem = n - len(buf)
         try: s = sock.recv(rem)
-        except (socket.error), e: return ''
+        except (socket.error) as e: return b''
         buf += s
     return buf
 
@@ -22,7 +22,7 @@ def send(sock, s):
     count = 0
     while count < total:
         try: n = sock.send(s)
-        except (socket.error), e: n = 0
+        except (socket.error) as e: n = 0
         if n == 0:
             return count;
         count += n
@@ -43,7 +43,7 @@ host = socket.gethostname()
 
 try: serverSocket.bind((host, 0))
 except socket.error as msg:
-    print 'bind fails: ', msg
+    print('bind fails: ' + str(msg))
 
 sn = serverSocket.getsockname()
 serverPort = sn[1]
@@ -51,10 +51,10 @@ serverPort = sn[1]
 cmdStr = ("./tcp_client.py %d &") % (serverPort)
 os.system(cmdStr)
 
-buf = ''
+buf = b''
 n = 0
 while n < 500:
-    buf += '.'
+    buf += b'.'
     n += 1
 
 serverSocket.listen(MAX_PORTS)
@@ -79,5 +79,5 @@ while True:
                 serverSocket.close()
                 sys.exit(0)
     else:
-        print 'Select timeout!'
+        print('Select timeout!')
         sys.exit(1)
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 6b1b302310fe..5f377ec53f2f 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -18,10 +18,7 @@
 
 #include "../../../include/linux/filter.h"
 #include "bpf_rlimit.h"
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_util.h"
 
 #define MAX_INSNS       512
 #define MAX_MATCHES     16
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index ffdd27737c9e..6b5cfeb7a9cc 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -19,6 +19,7 @@
 #include <bpf/btf.h>
 
 #include "bpf_rlimit.h"
+#include "bpf_util.h"
 
 static uint32_t pass_cnt;
 static uint32_t error_cnt;
@@ -93,10 +94,6 @@ static int __base_pr(const char *format, ...)
 #define MAX_NR_RAW_TYPES 1024
 #define BTF_LOG_BUF_SIZE 65535
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 static struct args {
         unsigned int raw_test_num;
         unsigned int file_test_num;
@@ -131,6 +128,8 @@ struct btf_raw_test {
         __u32 max_entries;
         bool btf_load_err;
         bool map_create_err;
+        bool ordered_map;
+        bool lossless_map;
         int hdr_len_delta;
         int type_off_delta;
         int str_off_delta;
@@ -2093,8 +2092,7 @@ struct pprint_mapv {
         } aenum;
 };
 
-static struct btf_raw_test pprint_test = {
-        .descr = "BTF pretty print test #1",
+static struct btf_raw_test pprint_test_template = {
         .raw_types = {
                 /* unsighed char */                     /* [1] */
                 BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
@@ -2146,8 +2144,6 @@ static struct btf_raw_test pprint_test = {
         },
         .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
         .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
-        .map_type = BPF_MAP_TYPE_ARRAY,
-        .map_name = "pprint_test",
         .key_size = sizeof(unsigned int),
         .value_size = sizeof(struct pprint_mapv),
         .key_type_id = 3,       /* unsigned int */
@@ -2155,6 +2151,40 @@ static struct btf_raw_test pprint_test = {
         .max_entries = 128 * 1024,
 };
 
+static struct btf_pprint_test_meta {
+        const char *descr;
+        enum bpf_map_type map_type;
+        const char *map_name;
+        bool ordered_map;
+        bool lossless_map;
+} pprint_tests_meta[] = {
+{
+        .descr = "BTF pretty print array",
+        .map_type = BPF_MAP_TYPE_ARRAY,
+        .map_name = "pprint_test_array",
+        .ordered_map = true,
+        .lossless_map = true,
+},
+
+{
+        .descr = "BTF pretty print hash",
+        .map_type = BPF_MAP_TYPE_HASH,
+        .map_name = "pprint_test_hash",
+        .ordered_map = false,
+        .lossless_map = true,
+},
+
+{
+        .descr = "BTF pretty print lru hash",
+        .map_type = BPF_MAP_TYPE_LRU_HASH,
+        .map_name = "pprint_test_lru_hash",
+        .ordered_map = false,
+        .lossless_map = false,
+},
+
+};
+
+
 static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
 {
         v->ui32 = i;
@@ -2166,10 +2196,12 @@ static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
         v->aenum = i & 0x03;
 }
 
-static int test_pprint(void)
+static int do_test_pprint(void)
 {
-        const struct btf_raw_test *test = &pprint_test;
+        const struct btf_raw_test *test = &pprint_test_template;
         struct bpf_create_map_attr create_attr = {};
+        unsigned int key, nr_read_elems;
+        bool ordered_map, lossless_map;
         int map_fd = -1, btf_fd = -1;
         struct pprint_mapv mapv = {};
         unsigned int raw_btf_size;
@@ -2178,7 +2210,6 @@ static int test_pprint(void)
         char pin_path[255];
         size_t line_len = 0;
         char *line = NULL;
-        unsigned int key;
         uint8_t *raw_btf;
         ssize_t nread;
         int err, ret;
@@ -2251,14 +2282,18 @@ static int test_pprint(void)
                 goto done;
         }
 
-        key = 0;
+        nr_read_elems = 0;
+        ordered_map = test->ordered_map;
+        lossless_map = test->lossless_map;
         do {
                 ssize_t nexpected_line;
+                unsigned int next_key;
 
-                set_pprint_mapv(&mapv, key);
+                next_key = ordered_map ? nr_read_elems : atoi(line);
+                set_pprint_mapv(&mapv, next_key);
                 nexpected_line = snprintf(expected_line, sizeof(expected_line),
                                           "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
-                                          key,
+                                          next_key,
                                           mapv.ui32, mapv.si32,
                                           mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
                                           mapv.ui64,
@@ -2281,11 +2316,12 @@ static int test_pprint(void)
                 }
 
                 nread = getline(&line, &line_len, pin_file);
-        } while (++key < test->max_entries && nread > 0);
+        } while (++nr_read_elems < test->max_entries && nread > 0);
 
-        if (CHECK(key < test->max_entries,
-                  "Unexpected EOF. key:%u test->max_entries:%u",
-                  key, test->max_entries)) {
+        if (lossless_map &&
+            CHECK(nr_read_elems < test->max_entries,
+                  "Unexpected EOF. nr_read_elems:%u test->max_entries:%u",
+                  nr_read_elems, test->max_entries)) {
                 err = -1;
                 goto done;
         }
@@ -2314,6 +2350,24 @@ done:
         return err;
 }
 
+static int test_pprint(void)
+{
+        unsigned int i;
+        int err = 0;
+
+        for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
+                pprint_test_template.descr = pprint_tests_meta[i].descr;
+                pprint_test_template.map_type = pprint_tests_meta[i].map_type;
+                pprint_test_template.map_name = pprint_tests_meta[i].map_name;
+                pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
+                pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+
+                err |= count_result(do_test_pprint());
+        }
+
+        return err;
+}
+
 static void usage(const char *cmd)
 {
         fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
@@ -2409,7 +2463,7 @@ int main(int argc, char **argv)
                 err |= test_file();
 
         if (args.pprint_test)
-                err |= count_result(test_pprint());
+                err |= test_pprint();
 
         if (args.raw_test || args.get_info_test || args.file_test ||
             args.pprint_test)
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
new file mode 100644
index 000000000000..dc83fb2d3f27
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <bpf/bpf.h>
+#include <linux/filter.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "cgroup_helpers.h"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
+
+int main(int argc, char **argv)
+{
+        struct bpf_insn prog[] = {
+                BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
+                BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+                BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                             BPF_FUNC_get_local_storage),
+                BPF_MOV64_IMM(BPF_REG_1, 1),
+                BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+                BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
+                BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                BPF_EXIT_INSN(),
+        };
+        size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+        int error = EXIT_FAILURE;
+        int map_fd, prog_fd, cgroup_fd;
+        struct bpf_cgroup_storage_key key;
+        unsigned long long value;
+
+        map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
+                                sizeof(value), 0, 0);
+        if (map_fd < 0) {
+                printf("Failed to create map: %s\n", strerror(errno));
+                goto out;
+        }
+
+        prog[0].imm = map_fd;
+        prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+                                   prog, insns_cnt, "GPL", 0,
+                                   bpf_log_buf, BPF_LOG_BUF_SIZE);
+        if (prog_fd < 0) {
+                printf("Failed to load bpf program: %s\n", bpf_log_buf);
+                goto out;
+        }
+
+        if (setup_cgroup_environment()) {
+                printf("Failed to setup cgroup environment\n");
+                goto err;
+        }
+
+        /* Create a cgroup, get fd, and join it */
+        cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+        if (!cgroup_fd) {
+                printf("Failed to create test cgroup\n");
+                goto err;
+        }
+
+        if (join_cgroup(TEST_CGROUP)) {
+                printf("Failed to join cgroup\n");
+                goto err;
+        }
+
+        /* Attach the bpf program */
+        if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+                printf("Failed to attach bpf program\n");
+                goto err;
+        }
+
+        if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+                printf("Failed to get the first key in cgroup storage\n");
+                goto err;
+        }
+
+        if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+                printf("Failed to lookup cgroup storage\n");
+                goto err;
+        }
+
+        /* Every second packet should be dropped */
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+        /* Check the counter in the cgroup local storage */
+        if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+                printf("Failed to lookup cgroup storage\n");
+                goto err;
+        }
+
+        if (value != 3) {
+                printf("Unexpected data in the cgroup storage: %llu\n", value);
+                goto err;
+        }
+
+        /* Bump the counter in the cgroup local storage */
+        value++;
+        if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
+                printf("Failed to update the data in the cgroup storage\n");
+                goto err;
+        }
+
+        /* Every second packet should be dropped */
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+        assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+        /* Check the final value of the counter in the cgroup local storage */
+        if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+                printf("Failed to lookup the cgroup storage\n");
+                goto err;
+        }
+
+        if (value != 7) {
+                printf("Unexpected data in the cgroup storage: %llu\n", value);
+                goto err;
+        }
+
+        error = 0;
+        printf("test_cgroup_storage:PASS\n");
+
+err:
+        cleanup_cgroup_environment();
+
+out:
+        return error;
+}
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 6c253343a6f9..6f54f84144a0 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -17,7 +17,8 @@
 #include <stdlib.h>
 
 #include <sys/wait.h>
-
+#include <sys/socket.h>
+#include <netinet/in.h>
 #include <linux/bpf.h>
 
 #include <bpf/bpf.h>
@@ -26,8 +27,21 @@
 #include "bpf_util.h"
 #include "bpf_rlimit.h"
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 static int map_flags;
 
+#define CHECK(condition, tag, format...) ({                             \
+        int __ret = !!(condition);                                      \
+        if (__ret) {                                                    \
+                printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);     \
+                printf(format);                                         \
+                exit(-1);                                               \
+        }                                                               \
+})
+
 static void test_hashmap(int task, void *data)
 {
         long long key, next_key, first_key, value;
@@ -1150,6 +1164,250 @@ static void test_map_wronly(void)
         assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
 }
 
+static void prepare_reuseport_grp(int type, int map_fd,
+                                  __s64 *fds64, __u64 *sk_cookies,
+                                  unsigned int n)
+{
+        socklen_t optlen, addrlen;
+        struct sockaddr_in6 s6;
+        const __u32 index0 = 0;
+        const int optval = 1;
+        unsigned int i;
+        u64 sk_cookie;
+        __s64 fd64;
+        int err;
+
+        s6.sin6_family = AF_INET6;
+        s6.sin6_addr = in6addr_any;
+        s6.sin6_port = 0;
+        addrlen = sizeof(s6);
+        optlen = sizeof(sk_cookie);
+
+        for (i = 0; i < n; i++) {
+                fd64 = socket(AF_INET6, type, 0);
+                CHECK(fd64 == -1, "socket()",
+                      "sock_type:%d fd64:%lld errno:%d\n",
+                      type, fd64, errno);
+
+                err = setsockopt(fd64, SOL_SOCKET, SO_REUSEPORT,
+                                 &optval, sizeof(optval));
+                CHECK(err == -1, "setsockopt(SO_REUSEPORT)",
+                      "err:%d errno:%d\n", err, errno);
+
+                /* reuseport_array does not allow unbound sk */
+                err = bpf_map_update_elem(map_fd, &index0, &fd64,
+                                          BPF_ANY);
+                CHECK(err != -1 || errno != EINVAL,
+                      "reuseport array update unbound sk",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+
+                err = bind(fd64, (struct sockaddr *)&s6, sizeof(s6));
+                CHECK(err == -1, "bind()",
+                      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+                if (i == 0) {
+                        err = getsockname(fd64, (struct sockaddr *)&s6,
+                                          &addrlen);
+                        CHECK(err == -1, "getsockname()",
+                              "sock_type:%d err:%d errno:%d\n",
+                              type, err, errno);
+                }
+
+                err = getsockopt(fd64, SOL_SOCKET, SO_COOKIE, &sk_cookie,
+                                 &optlen);
+                CHECK(err == -1, "getsockopt(SO_COOKIE)",
+                      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+                if (type == SOCK_STREAM) {
+                        /*
+                         * reuseport_array does not allow
+                         * non-listening tcp sk.
+                         */
+                        err = bpf_map_update_elem(map_fd, &index0, &fd64,
+                                                  BPF_ANY);
+                        CHECK(err != -1 || errno != EINVAL,
+                              "reuseport array update non-listening sk",
+                              "sock_type:%d err:%d errno:%d\n",
+                              type, err, errno);
+                        err = listen(fd64, 0);
+                        CHECK(err == -1, "listen()",
+                              "sock_type:%d, err:%d errno:%d\n",
+                              type, err, errno);
+                }
+
+                fds64[i] = fd64;
+                sk_cookies[i] = sk_cookie;
+        }
+}
+
+static void test_reuseport_array(void)
+{
+#define REUSEPORT_FD_IDX(err, last) ({ (err) ? last : !last; })
+
+        const __u32 array_size = 4, index0 = 0, index3 = 3;
+        int types[2] = { SOCK_STREAM, SOCK_DGRAM }, type;
+        __u64 grpa_cookies[2], sk_cookie, map_cookie;
+        __s64 grpa_fds64[2] = { -1, -1 }, fd64 = -1;
+        const __u32 bad_index = array_size;
+        int map_fd, err, t, f;
+        __u32 fds_idx = 0;
+        int fd;
+
+        map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+                                sizeof(__u32), sizeof(__u64), array_size, 0);
+        CHECK(map_fd == -1, "reuseport array create",
+              "map_fd:%d, errno:%d\n", map_fd, errno);
+
+        /* Test lookup/update/delete with invalid index */
+        err = bpf_map_delete_elem(map_fd, &bad_index);
+        CHECK(err != -1 || errno != E2BIG, "reuseport array del >=max_entries",
+              "err:%d errno:%d\n", err, errno);
+
+        err = bpf_map_update_elem(map_fd, &bad_index, &fd64, BPF_ANY);
+        CHECK(err != -1 || errno != E2BIG,
+              "reuseport array update >=max_entries",
+              "err:%d errno:%d\n", err, errno);
+
+        err = bpf_map_lookup_elem(map_fd, &bad_index, &map_cookie);
+        CHECK(err != -1 || errno != ENOENT,
+              "reuseport array update >=max_entries",
+              "err:%d errno:%d\n", err, errno);
+
+        /* Test lookup/delete non existence elem */
+        err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+        CHECK(err != -1 || errno != ENOENT,
+              "reuseport array lookup not-exist elem",
+              "err:%d errno:%d\n", err, errno);
+        err = bpf_map_delete_elem(map_fd, &index3);
+        CHECK(err != -1 || errno != ENOENT,
+              "reuseport array del not-exist elem",
+              "err:%d errno:%d\n", err, errno);
+
+        for (t = 0; t < ARRAY_SIZE(types); t++) {
+                type = types[t];
+
+                prepare_reuseport_grp(type, map_fd, grpa_fds64,
+                                      grpa_cookies, ARRAY_SIZE(grpa_fds64));
+
+                /* Test BPF_* update flags */
+                /* BPF_EXIST failure case */
+                err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+                                          BPF_EXIST);
+                CHECK(err != -1 || errno != ENOENT,
+                      "reuseport array update empty elem BPF_EXIST",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+                fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+                /* BPF_NOEXIST success case */
+                err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+                                          BPF_NOEXIST);
+                CHECK(err == -1,
+                      "reuseport array update empty elem BPF_NOEXIST",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+                fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+                /* BPF_EXIST success case. */
+                err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+                                          BPF_EXIST);
+                CHECK(err == -1,
+                      "reuseport array update same elem BPF_EXIST",
+                      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+                fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+                /* BPF_NOEXIST failure case */
+                err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+                                          BPF_NOEXIST);
+                CHECK(err != -1 || errno != EEXIST,
+                      "reuseport array update non-empty elem BPF_NOEXIST",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+                fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+                /* BPF_ANY case (always succeed) */
+                err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+                                          BPF_ANY);
+                CHECK(err == -1,
+                      "reuseport array update same sk with BPF_ANY",
+                      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+                fd64 = grpa_fds64[fds_idx];
+                sk_cookie = grpa_cookies[fds_idx];
+
+                /* The same sk cannot be added to reuseport_array twice */
+                err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_ANY);
+                CHECK(err != -1 || errno != EBUSY,
+                      "reuseport array update same sk with same index",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+
+                err = bpf_map_update_elem(map_fd, &index0, &fd64, BPF_ANY);
+                CHECK(err != -1 || errno != EBUSY,
+                      "reuseport array update same sk with different index",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+
+                /* Test delete elem */
+                err = bpf_map_delete_elem(map_fd, &index3);
+                CHECK(err == -1, "reuseport array delete sk",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+
+                /* Add it back with BPF_NOEXIST */
+                err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
+                CHECK(err == -1,
+                      "reuseport array re-add with BPF_NOEXIST after del",
+                      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+                /* Test cookie */
+                err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+                CHECK(err == -1 || sk_cookie != map_cookie,
+                      "reuseport array lookup re-added sk",
+                      "sock_type:%d err:%d errno:%d sk_cookie:0x%llx map_cookie:0x%llxn",
+                      type, err, errno, sk_cookie, map_cookie);
+
+                /* Test elem removed by close() */
+                for (f = 0; f < ARRAY_SIZE(grpa_fds64); f++)
+                        close(grpa_fds64[f]);
+                err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+                CHECK(err != -1 || errno != ENOENT,
+                      "reuseport array lookup after close()",
+                      "sock_type:%d err:%d errno:%d\n",
+                      type, err, errno);
+        }
+
+        /* Test SOCK_RAW */
+        fd64 = socket(AF_INET6, SOCK_RAW, IPPROTO_UDP);
+        CHECK(fd64 == -1, "socket(SOCK_RAW)", "err:%d errno:%d\n",
+              err, errno);
+        err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
+        CHECK(err != -1 || errno != ENOTSUPP, "reuseport array update SOCK_RAW",
+              "err:%d errno:%d\n", err, errno);
+        close(fd64);
+
+        /* Close the 64 bit value map */
+        close(map_fd);
+
+        /* Test 32 bit fd */
+        map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+                                sizeof(__u32), sizeof(__u32), array_size, 0);
+        CHECK(map_fd == -1, "reuseport array create",
+              "map_fd:%d, errno:%d\n", map_fd, errno);
+        prepare_reuseport_grp(SOCK_STREAM, map_fd, &fd64, &sk_cookie, 1);
+        fd = fd64;
+        err = bpf_map_update_elem(map_fd, &index3, &fd, BPF_NOEXIST);
+        CHECK(err == -1, "reuseport array update 32 bit fd",
+              "err:%d errno:%d\n", err, errno);
+        err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+        CHECK(err != -1 || errno != ENOSPC,
+              "reuseport array lookup 32 bit fd",
+              "err:%d errno:%d\n", err, errno);
+        close(fd);
+        close(map_fd);
+}
+
 static void run_all_tests(void)
 {
         test_hashmap(0, NULL);
@@ -1170,6 +1428,8 @@ static void run_all_tests(void)
 
         test_map_rdonly();
         test_map_wronly();
+
+        test_reuseport_array();
 }
 
 int main(void)
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index be800d0e7a84..d59642e70f56 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -158,8 +158,9 @@ def tool(name, args, flags, JSON=True, ns="", fail=True, include_stderr=False):
     else:
         return ret, out
 
-def bpftool(args, JSON=True, ns="", fail=True):
-    return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns, fail=fail)
+def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False):
+    return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns,
+                fail=fail, include_stderr=include_stderr)
 
 def bpftool_prog_list(expected=None, ns=""):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
@@ -201,6 +202,21 @@ def bpftool_map_list_wait(expected=0, n_retry=20):
         time.sleep(0.05)
     raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
 
+def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None,
+                      fail=True, include_stderr=False):
+    args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name)
+    if prog_type is not None:
+        args += " type " + prog_type
+    if dev is not None:
+        args += " dev " + dev
+    if len(maps):
+        args += " map " + " map ".join(maps)
+
+    res = bpftool(args, fail=fail, include_stderr=include_stderr)
+    if res[0] == 0:
+        files.append(file_name)
+    return res
+
 def ip(args, force=False, JSON=True, ns="", fail=True, include_stderr=False):
     if force:
         args = "-force " + args
@@ -307,21 +323,25 @@ class NetdevSim:
     Class for netdevsim netdevice and its attributes.
     """
 
-    def __init__(self):
+    def __init__(self, link=None):
+        self.link = link
+
         self.dev = self._netdevsim_create()
         devs.append(self)
 
         self.ns = ""
 
         self.dfs_dir = '/sys/kernel/debug/netdevsim/%s' % (self.dev['ifname'])
+        self.sdev_dir = self.dfs_dir + '/sdev/'
         self.dfs_refresh()
 
     def __getitem__(self, key):
         return self.dev[key]
 
     def _netdevsim_create(self):
+        link = "" if self.link is None else "link " + self.link.dev['ifname']
         _, old  = ip("link show")
-        ip("link add sim%d type netdevsim")
+        ip("link add sim%d {link} type netdevsim".format(link=link))
         _, new  = ip("link show")
 
         for dev in new:
@@ -339,13 +359,18 @@ class NetdevSim:
         self.dfs = DebugfsDir(self.dfs_dir)
         return self.dfs
 
+    def dfs_read(self, f):
+        path = os.path.join(self.dfs_dir, f)
+        _, data = cmd('cat %s' % (path))
+        return data.strip()
+
     def dfs_num_bound_progs(self):
-        path = os.path.join(self.dfs_dir, "bpf_bound_progs")
+        path = os.path.join(self.sdev_dir, "bpf_bound_progs")
         _, progs = cmd('ls %s' % (path))
         return len(progs.split())
 
     def dfs_get_bound_progs(self, expected):
-        progs = DebugfsDir(os.path.join(self.dfs_dir, "bpf_bound_progs"))
+        progs = DebugfsDir(os.path.join(self.sdev_dir, "bpf_bound_progs"))
         if expected is not None:
             if len(progs) != expected:
                 fail(True, "%d BPF programs bound, expected %d" %
@@ -547,11 +572,11 @@ def check_extack(output, reference, args):
     if skip_extack:
         return
     lines = output.split("\n")
-    comp = len(lines) >= 2 and lines[1] == reference
+    comp = len(lines) >= 2 and lines[1] == 'Error: ' + reference
     fail(not comp, "Missing or incorrect netlink extack message")
 
 def check_extack_nsim(output, reference, args):
-    check_extack(output, "Error: netdevsim: " + reference, args)
+    check_extack(output, "netdevsim: " + reference, args)
 
 def check_no_extack(res, needle):
     fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
@@ -654,7 +679,7 @@ try:
     ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "TC filter loaded without enabling TC offloads")
-    check_extack(err, "Error: TC offload is disabled on net device.", args)
+    check_extack(err, "TC offload is disabled on net device.", args)
     sim.wait_for_flush()
 
     sim.set_ethtool_tc_offloads(True)
@@ -694,7 +719,7 @@ try:
                                          skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "Offloaded a filter to chain other than 0")
-    check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+    check_extack(err, "Driver supports only offload of chain 0.", args)
     sim.tc_flush_filters()
 
     start_test("Test TC replace...")
@@ -814,24 +839,20 @@ try:
          "Device parameters reported for non-offloaded program")
 
     start_test("Test XDP prog replace with bad flags...")
-    ret, _, err = sim.set_xdp(obj, "offload", force=True,
+    ret, _, err = sim.set_xdp(obj, "generic", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    fail(err.count("File exists") != 1, "Replaced driver XDP with generic")
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test XDP prog remove with bad flags...")
-    ret, _, err = sim.unset_xdp("offload", force=True,
-                                fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
     ret, _, err = sim.unset_xdp("", force=True,
                                 fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    fail(ret == 0, "Removed program with a bad mode")
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test MTU restrictions...")
     ret, _ = sim.set_mtu(9000, fail=False)
@@ -846,6 +867,25 @@ try:
     sim.set_mtu(1500)
 
     sim.wait_for_flush()
+    start_test("Test non-offload XDP attaching to HW...")
+    bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/nooffload")
+    nooffload = bpf_pinned("/sys/fs/bpf/nooffload")
+    ret, _, err = sim.set_xdp(nooffload, "offload",
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "attached non-offloaded XDP program to HW")
+    check_extack_nsim(err, "xdpoffload of non-bound program.", args)
+    rm("/sys/fs/bpf/nooffload")
+
+    start_test("Test offload XDP attaching to drv...")
+    bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload",
+                      dev=sim['ifname'])
+    offload = bpf_pinned("/sys/fs/bpf/offload")
+    ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True)
+    fail(ret == 0, "attached offloaded XDP program to drv")
+    check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args)
+    rm("/sys/fs/bpf/offload")
+    sim.wait_for_flush()
+
     start_test("Test XDP offload...")
     _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True)
     ipl = sim.ip_link_show(xdp=True)
@@ -891,6 +931,60 @@ try:
     rm(pin_file)
     bpftool_prog_list_wait(expected=0)
 
+    start_test("Test multi-attachment XDP - attach...")
+    sim.set_xdp(obj, "offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+    fail("prog" not in xdp, "Base program not reported in single program mode")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with one program")
+
+    sim.set_xdp(obj, "")
+    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded2 = sim.dfs_read("bpf_offloaded_id")
+
+    fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
+    fail("prog" in two_xdps, "Base program reported in multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(two_xdps["attached"]) != 2,
+         "Wrong attached program count with two programs")
+    fail(two_xdps["attached"][0]["prog"]["id"] ==
+         two_xdps["attached"][1]["prog"]["id"],
+         "offloaded and drv programs have the same id")
+    fail(offloaded != offloaded2,
+         "offload ID changed after loading driver program")
+
+    start_test("Test multi-attachment XDP - replace...")
+    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+    fail(err.count("busy") != 1, "Replaced one of programs without -force")
+
+    start_test("Test multi-attachment XDP - detach...")
+    ret, _, err = sim.unset_xdp("drv", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program with a bad mode")
+    check_extack(err, "program loaded with different flags.", args)
+
+    sim.unset_xdp("offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+
+    fail(xdp["mode"] != 1, "Bad mode reported after multiple programs")
+    fail("prog" not in xdp,
+         "Base program not reported after multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with remaining programs")
+    fail(offloaded != "0", "offload ID reported with only driver program left")
+
+    start_test("Test multi-attachment XDP - device remove...")
+    sim.set_xdp(obj, "offload")
+    sim.remove()
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+
     start_test("Test mixing of TC and XDP...")
     sim.tc_add_ingress()
     sim.set_xdp(obj, "offload")
@@ -1085,6 +1179,106 @@ try:
     fail(ret == 0,
          "netdevsim didn't refuse to create a map with offload disabled")
 
+    sim.remove()
+
+    start_test("Test multi-dev ASIC program reuse...")
+    simA = NetdevSim()
+    simB1 = NetdevSim()
+    simB2 = NetdevSim(link=simB1)
+    simB3 = NetdevSim(link=simB1)
+    sims = (simA, simB1, simB2, simB3)
+    simB = (simB1, simB2, simB3)
+
+    bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA",
+                      dev=simA['ifname'])
+    progA = bpf_pinned("/sys/fs/bpf/nsimA")
+    bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB",
+                      dev=simB1['ifname'])
+    progB = bpf_pinned("/sys/fs/bpf/nsimB")
+
+    simA.set_xdp(progA, "offload", JSON=False)
+    for d in simB:
+        d.set_xdp(progB, "offload", JSON=False)
+
+    start_test("Test multi-dev ASIC cross-dev replace...")
+    ret, _ = simA.set_xdp(progB, "offload", force=True, JSON=False, fail=False)
+    fail(ret == 0, "cross-ASIC program allowed")
+    for d in simB:
+        ret, _ = d.set_xdp(progA, "offload", force=True, JSON=False, fail=False)
+        fail(ret == 0, "cross-ASIC program allowed")
+
+    start_test("Test multi-dev ASIC cross-dev install...")
+    for d in sims:
+        d.unset_xdp("offload")
+
+    ret, _, err = simA.set_xdp(progB, "offload", force=True, JSON=False,
+                               fail=False, include_stderr=True)
+    fail(ret == 0, "cross-ASIC program allowed")
+    check_extack_nsim(err, "program bound to different dev.", args)
+    for d in simB:
+        ret, _, err = d.set_xdp(progA, "offload", force=True, JSON=False,
+                                fail=False, include_stderr=True)
+        fail(ret == 0, "cross-ASIC program allowed")
+        check_extack_nsim(err, "program bound to different dev.", args)
+
+    start_test("Test multi-dev ASIC cross-dev map reuse...")
+
+    mapA = bpftool("prog show %s" % (progA))[1]["map_ids"][0]
+    mapB = bpftool("prog show %s" % (progB))[1]["map_ids"][0]
+
+    ret, _ = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_",
+                               dev=simB3['ifname'],
+                               maps=["idx 0 id %d" % (mapB)],
+                               fail=False)
+    fail(ret != 0, "couldn't reuse a map on the same ASIC")
+    rm("/sys/fs/bpf/nsimB_")
+
+    ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA_",
+                                    dev=simA['ifname'],
+                                    maps=["idx 0 id %d" % (mapB)],
+                                    fail=False, include_stderr=True)
+    fail(ret == 0, "could reuse a map on a different ASIC")
+    fail(err.count("offload device mismatch between prog and map") == 0,
+         "error message missing for cross-ASIC map")
+
+    ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_",
+                                    dev=simB1['ifname'],
+                                    maps=["idx 0 id %d" % (mapA)],
+                                    fail=False, include_stderr=True)
+    fail(ret == 0, "could reuse a map on a different ASIC")
+    fail(err.count("offload device mismatch between prog and map") == 0,
+         "error message missing for cross-ASIC map")
+
+    start_test("Test multi-dev ASIC cross-dev destruction...")
+    bpftool_prog_list_wait(expected=2)
+
+    simA.remove()
+    bpftool_prog_list_wait(expected=1)
+
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB != simB1['ifname'], "program not bound to originial device")
+    simB1.remove()
+    bpftool_prog_list_wait(expected=1)
+
+    start_test("Test multi-dev ASIC cross-dev destruction - move...")
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB not in (simB2['ifname'], simB3['ifname']),
+         "program not bound to remaining devices")
+
+    simB2.remove()
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB != simB3['ifname'], "program not bound to remaining device")
+
+    simB3.remove()
+    bpftool_prog_list_wait(expected=0)
+
+    start_test("Test multi-dev ASIC cross-dev destruction - orphaned...")
+    ret, out = bpftool("prog show %s" % (progB), fail=False)
+    fail(ret == 0, "got information about orphaned program")
+    fail("error" not in out, "no error reported for get info on orphaned")
+    fail(out["error"] != "can't get prog info: No such device",
+         "wrong error for get info on orphaned")
+
     print("%s: OK" % (os.path.basename(__file__)))
 
 finally:
diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/test_select_reuseport.c
new file mode 100644
index 000000000000..75646d9b34aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport.c
@@ -0,0 +1,688 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <sys/types.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "test_select_reuseport_common.h"
+
+#define MIN_TCPHDR_LEN 20
+#define UDPHDR_LEN 8
+
+#define TCP_SYNCOOKIE_SYSCTL "/proc/sys/net/ipv4/tcp_syncookies"
+#define TCP_FO_SYSCTL "/proc/sys/net/ipv4/tcp_fastopen"
+#define REUSEPORT_ARRAY_SIZE 32
+
+static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
+static enum result expected_results[NR_RESULTS];
+static int sk_fds[REUSEPORT_ARRAY_SIZE];
+static int reuseport_array, outer_map;
+static int select_by_skb_data_prog;
+static int saved_tcp_syncookie;
+static struct bpf_object *obj;
+static int saved_tcp_fo;
+static __u32 index_zero;
+static int epfd;
+
+static union sa46 {
+        struct sockaddr_in6 v6;
+        struct sockaddr_in v4;
+        sa_family_t family;
+} srv_sa;
+
+#define CHECK(condition, tag, format...) ({                             \
+        int __ret = !!(condition);                                      \
+        if (__ret) {                                                    \
+                printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);     \
+                printf(format);                                         \
+                exit(-1);                                               \
+        }                                                               \
+})
+
+static void create_maps(void)
+{
+        struct bpf_create_map_attr attr = {};
+
+        /* Creating reuseport_array */
+        attr.name = "reuseport_array";
+        attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
+        attr.key_size = sizeof(__u32);
+        attr.value_size = sizeof(__u32);
+        attr.max_entries = REUSEPORT_ARRAY_SIZE;
+
+        reuseport_array = bpf_create_map_xattr(&attr);
+        CHECK(reuseport_array == -1, "creating reuseport_array",
+              "reuseport_array:%d errno:%d\n", reuseport_array, errno);
+
+        /* Creating outer_map */
+        attr.name = "outer_map";
+        attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS;
+        attr.key_size = sizeof(__u32);
+        attr.value_size = sizeof(__u32);
+        attr.max_entries = 1;
+        attr.inner_map_fd = reuseport_array;
+        outer_map = bpf_create_map_xattr(&attr);
+        CHECK(outer_map == -1, "creating outer_map",
+              "outer_map:%d errno:%d\n", outer_map, errno);
+}
+
+static void prepare_bpf_obj(void)
+{
+        struct bpf_program *prog;
+        struct bpf_map *map;
+        int err;
+        struct bpf_object_open_attr attr = {
+                .file = "test_select_reuseport_kern.o",
+                .prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+        };
+
+        obj = bpf_object__open_xattr(&attr);
+        CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o",
+              "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj));
+
+        prog = bpf_program__next(NULL, obj);
+        CHECK(!prog, "get first bpf_program", "!prog\n");
+        bpf_program__set_type(prog, attr.prog_type);
+
+        map = bpf_object__find_map_by_name(obj, "outer_map");
+        CHECK(!map, "find outer_map", "!map\n");
+        err = bpf_map__reuse_fd(map, outer_map);
+        CHECK(err, "reuse outer_map", "err:%d\n", err);
+
+        err = bpf_object__load(obj);
+        CHECK(err, "load bpf_object", "err:%d\n", err);
+
+        select_by_skb_data_prog = bpf_program__fd(prog);
+        CHECK(select_by_skb_data_prog == -1, "get prog fd",
+              "select_by_skb_data_prog:%d\n", select_by_skb_data_prog);
+
+        map = bpf_object__find_map_by_name(obj, "result_map");
+        CHECK(!map, "find result_map", "!map\n");
+        result_map = bpf_map__fd(map);
+        CHECK(result_map == -1, "get result_map fd",
+              "result_map:%d\n", result_map);
+
+        map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map");
+        CHECK(!map, "find tmp_index_ovr_map", "!map\n");
+        tmp_index_ovr_map = bpf_map__fd(map);
+        CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd",
+              "tmp_index_ovr_map:%d\n", tmp_index_ovr_map);
+
+        map = bpf_object__find_map_by_name(obj, "linum_map");
+        CHECK(!map, "find linum_map", "!map\n");
+        linum_map = bpf_map__fd(map);
+        CHECK(linum_map == -1, "get linum_map fd",
+              "linum_map:%d\n", linum_map);
+
+        map = bpf_object__find_map_by_name(obj, "data_check_map");
+        CHECK(!map, "find data_check_map", "!map\n");
+        data_check_map = bpf_map__fd(map);
+        CHECK(data_check_map == -1, "get data_check_map fd",
+              "data_check_map:%d\n", data_check_map);
+}
+
+static void sa46_init_loopback(union sa46 *sa, sa_family_t family)
+{
+        memset(sa, 0, sizeof(*sa));
+        sa->family = family;
+        if (sa->family == AF_INET6)
+                sa->v6.sin6_addr = in6addr_loopback;
+        else
+                sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+}
+
+static void sa46_init_inany(union sa46 *sa, sa_family_t family)
+{
+        memset(sa, 0, sizeof(*sa));
+        sa->family = family;
+        if (sa->family == AF_INET6)
+                sa->v6.sin6_addr = in6addr_any;
+        else
+                sa->v4.sin_addr.s_addr = INADDR_ANY;
+}
+
+static int read_int_sysctl(const char *sysctl)
+{
+        char buf[16];
+        int fd, ret;
+
+        fd = open(sysctl, 0);
+        CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
+              sysctl, fd, errno);
+
+        ret = read(fd, buf, sizeof(buf));
+        CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n",
+              sysctl, ret, errno);
+        close(fd);
+
+        return atoi(buf);
+}
+
+static void write_int_sysctl(const char *sysctl, int v)
+{
+        int fd, ret, size;
+        char buf[16];
+
+        fd = open(sysctl, O_RDWR);
+        CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
+              sysctl, fd, errno);
+
+        size = snprintf(buf, sizeof(buf), "%d", v);
+        ret = write(fd, buf, size);
+        CHECK(ret != size, "write(sysctl)",
+              "sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno);
+        close(fd);
+}
+
+static void restore_sysctls(void)
+{
+        write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
+        write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
+}
+
+static void enable_fastopen(void)
+{
+        int fo;
+
+        fo = read_int_sysctl(TCP_FO_SYSCTL);
+        write_int_sysctl(TCP_FO_SYSCTL, fo | 7);
+}
+
+static void enable_syncookie(void)
+{
+        write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2);
+}
+
+static void disable_syncookie(void)
+{
+        write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0);
+}
+
+static __u32 get_linum(void)
+{
+        __u32 linum;
+        int err;
+
+        err = bpf_map_lookup_elem(linum_map, &index_zero, &linum);
+        CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n",
+              err, errno);
+
+        return linum;
+}
+
+static void check_data(int type, sa_family_t family, const struct cmd *cmd,
+                       int cli_fd)
+{
+        struct data_check expected = {}, result;
+        union sa46 cli_sa;
+        socklen_t addrlen;
+        int err;
+
+        addrlen = sizeof(cli_sa);
+        err = getsockname(cli_fd, (struct sockaddr *)&cli_sa,
+                          &addrlen);
+        CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n",
+              err, errno);
+
+        err = bpf_map_lookup_elem(data_check_map, &index_zero, &result);
+        CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
+              err, errno);
+
+        if (type == SOCK_STREAM) {
+                expected.len = MIN_TCPHDR_LEN;
+                expected.ip_protocol = IPPROTO_TCP;
+        } else {
+                expected.len = UDPHDR_LEN;
+                expected.ip_protocol = IPPROTO_UDP;
+        }
+
+        if (family == AF_INET6) {
+                expected.eth_protocol = htons(ETH_P_IPV6);
+                expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] &&
+                        !srv_sa.v6.sin6_addr.s6_addr32[2] &&
+                        !srv_sa.v6.sin6_addr.s6_addr32[1] &&
+                        !srv_sa.v6.sin6_addr.s6_addr32[0];
+
+                memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32,
+                       sizeof(cli_sa.v6.sin6_addr));
+                memcpy(&expected.skb_addrs[4], &in6addr_loopback,
+                       sizeof(in6addr_loopback));
+                expected.skb_ports[0] = cli_sa.v6.sin6_port;
+                expected.skb_ports[1] = srv_sa.v6.sin6_port;
+        } else {
+                expected.eth_protocol = htons(ETH_P_IP);
+                expected.bind_inany = !srv_sa.v4.sin_addr.s_addr;
+
+                expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr;
+                expected.skb_addrs[1] = htonl(INADDR_LOOPBACK);
+                expected.skb_ports[0] = cli_sa.v4.sin_port;
+                expected.skb_ports[1] = srv_sa.v4.sin_port;
+        }
+
+        if (memcmp(&result, &expected, offsetof(struct data_check,
+                                                equal_check_end))) {
+                printf("unexpected data_check\n");
+                printf("  result: (0x%x, %u, %u)\n",
+                       result.eth_protocol, result.ip_protocol,
+                       result.bind_inany);
+                printf("expected: (0x%x, %u, %u)\n",
+                       expected.eth_protocol, expected.ip_protocol,
+                       expected.bind_inany);
+                CHECK(1, "data_check result != expected",
+                      "bpf_prog_linum:%u\n", get_linum());
+        }
+
+        CHECK(!result.hash, "data_check result.hash empty",
+              "result.hash:%u", result.hash);
+
+        expected.len += cmd ? sizeof(*cmd) : 0;
+        if (type == SOCK_STREAM)
+                CHECK(expected.len > result.len, "expected.len > result.len",
+                      "expected.len:%u result.len:%u bpf_prog_linum:%u\n",
+                      expected.len, result.len, get_linum());
+        else
+                CHECK(expected.len != result.len, "expected.len != result.len",
+                      "expected.len:%u result.len:%u bpf_prog_linum:%u\n",
+                      expected.len, result.len, get_linum());
+}
+
+static void check_results(void)
+{
+        __u32 results[NR_RESULTS];
+        __u32 i, broken = 0;
+        int err;
+
+        for (i = 0; i < NR_RESULTS; i++) {
+                err = bpf_map_lookup_elem(result_map, &i, &results[i]);
+                CHECK(err == -1, "lookup_elem(result_map)",
+                      "i:%u err:%d errno:%d\n", i, err, errno);
+        }
+
+        for (i = 0; i < NR_RESULTS; i++) {
+                if (results[i] != expected_results[i]) {
+                        broken = i;
+                        break;
+                }
+        }
+
+        if (i == NR_RESULTS)
+                return;
+
+        printf("unexpected result\n");
+        printf(" result: [");
+        printf("%u", results[0]);
+        for (i = 1; i < NR_RESULTS; i++)
+                printf(", %u", results[i]);
+        printf("]\n");
+
+        printf("expected: [");
+        printf("%u", expected_results[0]);
+        for (i = 1; i < NR_RESULTS; i++)
+                printf(", %u", expected_results[i]);
+        printf("]\n");
+
+        CHECK(expected_results[broken] != results[broken],
+              "unexpected result",
+              "expected_results[%u] != results[%u] bpf_prog_linum:%u\n",
+              broken, broken, get_linum());
+}
+
+static int send_data(int type, sa_family_t family, void *data, size_t len,
+                     enum result expected)
+{
+        union sa46 cli_sa;
+        int fd, err;
+
+        fd = socket(family, type, 0);
+        CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno);
+
+        sa46_init_loopback(&cli_sa, family);
+        err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa));
+        CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno);
+
+        err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa,
+                     sizeof(srv_sa));
+        CHECK(err != len && expected >= PASS,
+              "sendto()", "family:%u err:%d errno:%d expected:%d\n",
+              family, err, errno, expected);
+
+        return fd;
+}
+
+static void do_test(int type, sa_family_t family, struct cmd *cmd,
+                    enum result expected)
+{
+        int nev, srv_fd, cli_fd;
+        struct epoll_event ev;
+        struct cmd rcv_cmd;
+        ssize_t nread;
+
+        cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0,
+                           expected);
+        nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0);
+        CHECK((nev <= 0 && expected >= PASS) ||
+              (nev > 0 && expected < PASS),
+              "nev <> expected",
+              "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n",
+              nev, expected, type, family,
+              cmd ? cmd->reuseport_index : -1,
+              cmd ? cmd->pass_on_failure : -1);
+        check_results();
+        check_data(type, family, cmd, cli_fd);
+
+        if (expected < PASS)
+                return;
+
+        CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT &&
+              cmd->reuseport_index != ev.data.u32,
+              "check cmd->reuseport_index",
+              "cmd:(%u, %u) ev.data.u32:%u\n",
+              cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32);
+
+        srv_fd = sk_fds[ev.data.u32];
+        if (type == SOCK_STREAM) {
+                int new_fd = accept(srv_fd, NULL, 0);
+
+                CHECK(new_fd == -1, "accept(srv_fd)",
+                      "ev.data.u32:%u new_fd:%d errno:%d\n",
+                      ev.data.u32, new_fd, errno);
+
+                nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+                CHECK(nread != sizeof(rcv_cmd),
+                      "recv(new_fd)",
+                      "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+                      ev.data.u32, nread, sizeof(rcv_cmd), errno);
+
+                close(new_fd);
+        } else {
+                nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+                CHECK(nread != sizeof(rcv_cmd),
+                      "recv(sk_fds)",
+                      "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+                      ev.data.u32, nread, sizeof(rcv_cmd), errno);
+        }
+
+        close(cli_fd);
+}
+
+static void test_err_inner_map(int type, sa_family_t family)
+{
+        struct cmd cmd = {
+                .reuseport_index = 0,
+                .pass_on_failure = 0,
+        };
+
+        printf("%s: ", __func__);
+        expected_results[DROP_ERR_INNER_MAP]++;
+        do_test(type, family, &cmd, DROP_ERR_INNER_MAP);
+        printf("OK\n");
+}
+
+static void test_err_skb_data(int type, sa_family_t family)
+{
+        printf("%s: ", __func__);
+        expected_results[DROP_ERR_SKB_DATA]++;
+        do_test(type, family, NULL, DROP_ERR_SKB_DATA);
+        printf("OK\n");
+}
+
+static void test_err_sk_select_port(int type, sa_family_t family)
+{
+        struct cmd cmd = {
+                .reuseport_index = REUSEPORT_ARRAY_SIZE,
+                .pass_on_failure = 0,
+        };
+
+        printf("%s: ", __func__);
+        expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++;
+        do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT);
+        printf("OK\n");
+}
+
+static void test_pass(int type, sa_family_t family)
+{
+        struct cmd cmd;
+        int i;
+
+        printf("%s: ", __func__);
+        cmd.pass_on_failure = 0;
+        for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+                expected_results[PASS]++;
+                cmd.reuseport_index = i;
+                do_test(type, family, &cmd, PASS);
+        }
+        printf("OK\n");
+}
+
+static void test_syncookie(int type, sa_family_t family)
+{
+        int err, tmp_index = 1;
+        struct cmd cmd = {
+                .reuseport_index = 0,
+                .pass_on_failure = 0,
+        };
+
+        if (type != SOCK_STREAM)
+                return;
+
+        printf("%s: ", __func__);
+        /*
+         * +1 for TCP-SYN and
+         * +1 for the TCP-ACK (ack the syncookie)
+         */
+        expected_results[PASS] += 2;
+        enable_syncookie();
+        /*
+         * Simulate TCP-SYN and TCP-ACK are handled by two different sk:
+         * TCP-SYN: select sk_fds[tmp_index = 1] tmp_index is from the
+         *          tmp_index_ovr_map
+         * TCP-ACK: select sk_fds[reuseport_index = 0] reuseport_index
+         *          is from the cmd.reuseport_index
+         */
+        err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero,
+                                  &tmp_index, BPF_ANY);
+        CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)",
+              "err:%d errno:%d\n", err, errno);
+        do_test(type, family, &cmd, PASS);
+        err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero,
+                                  &tmp_index);
+        CHECK(err == -1 || tmp_index != -1,
+              "lookup_elem(tmp_index_ovr_map)",
+              "err:%d errno:%d tmp_index:%d\n",
+              err, errno, tmp_index);
+        disable_syncookie();
+        printf("OK\n");
+}
+
+static void test_pass_on_err(int type, sa_family_t family)
+{
+        struct cmd cmd = {
+                .reuseport_index = REUSEPORT_ARRAY_SIZE,
+                .pass_on_failure = 1,
+        };
+
+        printf("%s: ", __func__);
+        expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1;
+        do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT);
+        printf("OK\n");
+}
+
+static void prepare_sk_fds(int type, sa_family_t family, bool inany)
+{
+        const int first = REUSEPORT_ARRAY_SIZE - 1;
+        int i, err, optval = 1;
+        struct epoll_event ev;
+        socklen_t addrlen;
+
+        if (inany)
+                sa46_init_inany(&srv_sa, family);
+        else
+                sa46_init_loopback(&srv_sa, family);
+        addrlen = sizeof(srv_sa);
+
+        /*
+         * The sk_fds[] is filled from the back such that the order
+         * is exactly opposite to the (struct sock_reuseport *)reuse->socks[].
+         */
+        for (i = first; i >= 0; i--) {
+                sk_fds[i] = socket(family, type, 0);
+                CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n",
+                      i, sk_fds[i], errno);
+                err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT,
+                                 &optval, sizeof(optval));
+                CHECK(err == -1, "setsockopt(SO_REUSEPORT)",
+                      "sk_fds[%d] err:%d errno:%d\n",
+                      i, err, errno);
+
+                if (i == first) {
+                        err = setsockopt(sk_fds[i], SOL_SOCKET,
+                                         SO_ATTACH_REUSEPORT_EBPF,
+                                         &select_by_skb_data_prog,
+                                         sizeof(select_by_skb_data_prog));
+                        CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
+                              "err:%d errno:%d\n", err, errno);
+                }
+
+                err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen);
+                CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n",
+                      i, err, errno);
+
+                if (type == SOCK_STREAM) {
+                        err = listen(sk_fds[i], 10);
+                        CHECK(err == -1, "listen()",
+                              "sk_fds[%d] err:%d errno:%d\n",
+                              i, err, errno);
+                }
+
+                err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i],
+                                          BPF_NOEXIST);
+                CHECK(err == -1, "update_elem(reuseport_array)",
+                      "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+
+                if (i == first) {
+                        socklen_t addrlen = sizeof(srv_sa);
+
+                        err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa,
+                                          &addrlen);
+                        CHECK(err == -1, "getsockname()",
+                              "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+                }
+        }
+
+        epfd = epoll_create(1);
+        CHECK(epfd == -1, "epoll_create(1)",
+              "epfd:%d errno:%d\n", epfd, errno);
+
+        ev.events = EPOLLIN;
+        for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+                ev.data.u32 = i;
+                err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev);
+                CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i);
+        }
+}
+
+static void setup_per_test(int type, unsigned short family, bool inany)
+{
+        int ovr = -1, err;
+
+        prepare_sk_fds(type, family, inany);
+        err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr,
+                                  BPF_ANY);
+        CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)",
+              "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup_per_test(void)
+{
+        int i, err;
+
+        for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++)
+                close(sk_fds[i]);
+        close(epfd);
+
+        err = bpf_map_delete_elem(outer_map, &index_zero);
+        CHECK(err == -1, "delete_elem(outer_map)",
+              "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup(void)
+{
+        close(outer_map);
+        close(reuseport_array);
+        bpf_object__close(obj);
+}
+
+static void test_all(void)
+{
+        /* Extra SOCK_STREAM to test bind_inany==true */
+        const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM };
+        const char * const type_strings[] = { "TCP", "UDP", "TCP" };
+        const char * const family_strings[] = { "IPv6", "IPv4" };
+        const unsigned short families[] = { AF_INET6, AF_INET };
+        const bool bind_inany[] = { false, false, true };
+        int t, f, err;
+
+        for (f = 0; f < ARRAY_SIZE(families); f++) {
+                unsigned short family = families[f];
+
+                for (t = 0; t < ARRAY_SIZE(types); t++) {
+                        bool inany = bind_inany[t];
+                        int type = types[t];
+
+                        printf("######## %s/%s %s ########\n",
+                               family_strings[f], type_strings[t],
+                                inany ? " INANY  " : "LOOPBACK");
+
+                        setup_per_test(type, family, inany);
+
+                        test_err_inner_map(type, family);
+
+                        /* Install reuseport_array to the outer_map */
+                        err = bpf_map_update_elem(outer_map, &index_zero,
+                                                  &reuseport_array, BPF_ANY);
+                        CHECK(err == -1, "update_elem(outer_map)",
+                              "err:%d errno:%d\n", err, errno);
+
+                        test_err_skb_data(type, family);
+                        test_err_sk_select_port(type, family);
+                        test_pass(type, family);
+                        test_syncookie(type, family);
+                        test_pass_on_err(type, family);
+
+                        cleanup_per_test();
+                        printf("\n");
+                }
+        }
+}
+
+int main(int argc, const char **argv)
+{
+        create_maps();
+        prepare_bpf_obj();
+        saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+        saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
+        enable_fastopen();
+        disable_syncookie();
+        atexit(restore_sysctls);
+
+        test_all();
+
+        cleanup();
+        return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_select_reuseport_common.h b/tools/testing/selftests/bpf/test_select_reuseport_common.h
new file mode 100644
index 000000000000..08eb2a9f145f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport_common.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef __TEST_SELECT_REUSEPORT_COMMON_H
+#define __TEST_SELECT_REUSEPORT_COMMON_H
+
+#include <linux/types.h>
+
+enum result {
+        DROP_ERR_INNER_MAP,
+        DROP_ERR_SKB_DATA,
+        DROP_ERR_SK_SELECT_REUSEPORT,
+        DROP_MISC,
+        PASS,
+        PASS_ERR_SK_SELECT_REUSEPORT,
+        NR_RESULTS,
+};
+
+struct cmd {
+        __u32 reuseport_index;
+        __u32 pass_on_failure;
+};
+
+struct data_check {
+        __u32 ip_protocol;
+        __u32 skb_addrs[8];
+        __u16 skb_ports[2];
+        __u16 eth_protocol;
+        __u8  bind_inany;
+        __u8  equal_check_end[0];
+
+        __u32 len;
+        __u32 hash;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/test_select_reuseport_kern.c
new file mode 100644
index 000000000000..5b54ec637ada
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport_kern.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#include "bpf_endian.h"
+#include "bpf_helpers.h"
+#include "test_select_reuseport_common.h"
+
+int _version SEC("version") = 1;
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+struct bpf_map_def SEC("maps") outer_map = {
+        .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(__u32),
+        .max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") result_map = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(__u32),
+        .max_entries = NR_RESULTS,
+};
+
+struct bpf_map_def SEC("maps") tmp_index_ovr_map = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(int),
+        .max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") linum_map = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(__u32),
+        .max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") data_check_map = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(struct data_check),
+        .max_entries = 1,
+};
+
+#define GOTO_DONE(_result) ({                   \
+        result = (_result);                     \
+        linum = __LINE__;                       \
+        goto done;                              \
+})
+
+SEC("select_by_skb_data")
+int _select_by_skb_data(struct sk_reuseport_md *reuse_md)
+{
+        __u32 linum, index = 0, flags = 0, index_zero = 0;
+        __u32 *result_cnt, *linum_value;
+        struct data_check data_check = {};
+        struct cmd *cmd, cmd_copy;
+        void *data, *data_end;
+        void *reuseport_array;
+        enum result result;
+        int *index_ovr;
+        int err;
+
+        data = reuse_md->data;
+        data_end = reuse_md->data_end;
+        data_check.len = reuse_md->len;
+        data_check.eth_protocol = reuse_md->eth_protocol;
+        data_check.ip_protocol = reuse_md->ip_protocol;
+        data_check.hash = reuse_md->hash;
+        data_check.bind_inany = reuse_md->bind_inany;
+        if (data_check.eth_protocol == bpf_htons(ETH_P_IP)) {
+                if (bpf_skb_load_bytes_relative(reuse_md,
+                                                offsetof(struct iphdr, saddr),
+                                                data_check.skb_addrs, 8,
+                                                BPF_HDR_START_NET))
+                        GOTO_DONE(DROP_MISC);
+        } else {
+                if (bpf_skb_load_bytes_relative(reuse_md,
+                                                offsetof(struct ipv6hdr, saddr),
+                                                data_check.skb_addrs, 32,
+                                                BPF_HDR_START_NET))
+                        GOTO_DONE(DROP_MISC);
+        }
+
+        /*
+         * The ip_protocol could be a compile time decision
+         * if the bpf_prog.o is dedicated to either TCP or
+         * UDP.
+         *
+         * Otherwise, reuse_md->ip_protocol or
+         * the protocol field in the iphdr can be used.
+         */
+        if (data_check.ip_protocol == IPPROTO_TCP) {
+                struct tcphdr *th = data;
+
+                if (th + 1 > data_end)
+                        GOTO_DONE(DROP_MISC);
+
+                data_check.skb_ports[0] = th->source;
+                data_check.skb_ports[1] = th->dest;
+
+                if ((th->doff << 2) + sizeof(*cmd) > data_check.len)
+                        GOTO_DONE(DROP_ERR_SKB_DATA);
+                if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy,
+                                       sizeof(cmd_copy)))
+                        GOTO_DONE(DROP_MISC);
+                cmd = &cmd_copy;
+        } else if (data_check.ip_protocol == IPPROTO_UDP) {
+                struct udphdr *uh = data;
+
+                if (uh + 1 > data_end)
+                        GOTO_DONE(DROP_MISC);
+
+                data_check.skb_ports[0] = uh->source;
+                data_check.skb_ports[1] = uh->dest;
+
+                if (sizeof(struct udphdr) + sizeof(*cmd) > data_check.len)
+                        GOTO_DONE(DROP_ERR_SKB_DATA);
+                if (data + sizeof(struct udphdr) + sizeof(*cmd) > data_end) {
+                        if (bpf_skb_load_bytes(reuse_md, sizeof(struct udphdr),
+                                               &cmd_copy, sizeof(cmd_copy)))
+                                GOTO_DONE(DROP_MISC);
+                        cmd = &cmd_copy;
+                } else {
+                        cmd = data + sizeof(struct udphdr);
+                }
+        } else {
+                GOTO_DONE(DROP_MISC);
+        }
+
+        reuseport_array = bpf_map_lookup_elem(&outer_map, &index_zero);
+        if (!reuseport_array)
+                GOTO_DONE(DROP_ERR_INNER_MAP);
+
+        index = cmd->reuseport_index;
+        index_ovr = bpf_map_lookup_elem(&tmp_index_ovr_map, &index_zero);
+        if (!index_ovr)
+                GOTO_DONE(DROP_MISC);
+
+        if (*index_ovr != -1) {
+                index = *index_ovr;
+                *index_ovr = -1;
+        }
+        err = bpf_sk_select_reuseport(reuse_md, reuseport_array, &index,
+                                      flags);
+        if (!err)
+                GOTO_DONE(PASS);
+
+        if (cmd->pass_on_failure)
+                GOTO_DONE(PASS_ERR_SK_SELECT_REUSEPORT);
+        else
+                GOTO_DONE(DROP_ERR_SK_SELECT_REUSEPORT);
+
+done:
+        result_cnt = bpf_map_lookup_elem(&result_map, &result);
+        if (!result_cnt)
+                return SK_DROP;
+
+        bpf_map_update_elem(&linum_map, &index_zero, &linum, BPF_ANY);
+        bpf_map_update_elem(&data_check_map, &index_zero, &data_check, BPF_ANY);
+
+        (*result_cnt)++;
+        return result < PASS ? SK_DROP : SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
new file mode 100755
index 000000000000..42544a969abc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Facebook
+
+set -eu
+
+wait_for_ip()
+{
+        local _i
+        echo -n "Wait for testing link-local IP to become available "
+        for _i in $(seq ${MAX_PING_TRIES}); do
+                echo -n "."
+                if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+                        echo " OK"
+                        return
+                fi
+                sleep 1
+        done
+        echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
+        exit 1
+}
+
+setup()
+{
+        # Create testing interfaces not to interfere with current environment.
+        ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
+        ip link set ${TEST_IF} up
+        ip link set ${TEST_IF_PEER} up
+
+        wait_for_ip
+
+        tc qdisc add dev ${TEST_IF} clsact
+        tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
+                sec ${BPF_PROG_SECTION} da
+
+        BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
+                        awk '/ id / {sub(/.* id /, "", $0); print($1)}')
+}
+
+cleanup()
+{
+        ip link del ${TEST_IF} 2>/dev/null || :
+        ip link del ${TEST_IF_PEER} 2>/dev/null || :
+}
+
+main()
+{
+        trap cleanup EXIT 2 3 6 15
+        setup
+        ${PROG} ${TEST_IF} ${BPF_PROG_ID}
+}
+
+DIR=$(dirname $0)
+TEST_IF="test_cgid_1"
+TEST_IF_PEER="test_cgid_2"
+MAX_PING_TRIES=5
+BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
+BPF_PROG_SECTION="cgroup_id_logger"
+BPF_PROG_ID=0
+PROG="${DIR}/test_skb_cgroup_id_user"
+
+main
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
new file mode 100644
index 000000000000..68cf9829f5a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+#include <string.h>
+
+#include "bpf_helpers.h"
+
+#define NUM_CGROUP_LEVELS       4
+
+struct bpf_map_def SEC("maps") cgroup_ids = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(__u32),
+        .value_size = sizeof(__u64),
+        .max_entries = NUM_CGROUP_LEVELS,
+};
+
+static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
+{
+        __u64 id;
+
+        /* [1] &level passed to external function that may change it, it's
+         *     incompatible with loop unroll.
+         */
+        id = bpf_skb_ancestor_cgroup_id(skb, level);
+        bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
+}
+
+SEC("cgroup_id_logger")
+int log_cgroup_id(struct __sk_buff *skb)
+{
+        /* Loop unroll can't be used here due to [1]. Unrolling manually.
+         * Number of calls should be in sync with NUM_CGROUP_LEVELS.
+         */
+        log_nth_level(skb, 0);
+        log_nth_level(skb, 1);
+        log_nth_level(skb, 2);
+        log_nth_level(skb, 3);
+
+        return TC_ACT_OK;
+}
+
+int _version SEC("version") = 1;
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
new file mode 100644
index 000000000000..c121cc59f314
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define CGROUP_PATH             "/skb_cgroup_test"
+#define NUM_CGROUP_LEVELS       4
+
+/* RFC 4291, Section 2.7.1 */
+#define LINKLOCAL_MULTICAST     "ff02::1"
+
+static int mk_dst_addr(const char *ip, const char *iface,
+                       struct sockaddr_in6 *dst)
+{
+        memset(dst, 0, sizeof(*dst));
+
+        dst->sin6_family = AF_INET6;
+        dst->sin6_port = htons(1025);
+
+        if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
+                log_err("Invalid IPv6: %s", ip);
+                return -1;
+        }
+
+        dst->sin6_scope_id = if_nametoindex(iface);
+        if (!dst->sin6_scope_id) {
+                log_err("Failed to get index of iface: %s", iface);
+                return -1;
+        }
+
+        return 0;
+}
+
+static int send_packet(const char *iface)
+{
+        struct sockaddr_in6 dst;
+        char msg[] = "msg";
+        int err = 0;
+        int fd = -1;
+
+        if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
+                goto err;
+
+        fd = socket(AF_INET6, SOCK_DGRAM, 0);
+        if (fd == -1) {
+                log_err("Failed to create UDP socket");
+                goto err;
+        }
+
+        if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
+                   sizeof(dst)) == -1) {
+                log_err("Failed to send datagram");
+                goto err;
+        }
+
+        goto out;
+err:
+        err = -1;
+out:
+        if (fd >= 0)
+                close(fd);
+        return err;
+}
+
+int get_map_fd_by_prog_id(int prog_id)
+{
+        struct bpf_prog_info info = {};
+        __u32 info_len = sizeof(info);
+        __u32 map_ids[1];
+        int prog_fd = -1;
+        int map_fd = -1;
+
+        prog_fd = bpf_prog_get_fd_by_id(prog_id);
+        if (prog_fd < 0) {
+                log_err("Failed to get fd by prog id %d", prog_id);
+                goto err;
+        }
+
+        info.nr_map_ids = 1;
+        info.map_ids = (__u64) (unsigned long) map_ids;
+
+        if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
+                log_err("Failed to get info by prog fd %d", prog_fd);
+                goto err;
+        }
+
+        if (!info.nr_map_ids) {
+                log_err("No maps found for prog fd %d", prog_fd);
+                goto err;
+        }
+
+        map_fd = bpf_map_get_fd_by_id(map_ids[0]);
+        if (map_fd < 0)
+                log_err("Failed to get fd by map id %d", map_ids[0]);
+err:
+        if (prog_fd >= 0)
+                close(prog_fd);
+        return map_fd;
+}
+
+int check_ancestor_cgroup_ids(int prog_id)
+{
+        __u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
+        __u32 level;
+        int err = 0;
+        int map_fd;
+
+        expected_ids[0] = 0x100000001;  /* root cgroup */
+        expected_ids[1] = get_cgroup_id("");
+        expected_ids[2] = get_cgroup_id(CGROUP_PATH);
+        expected_ids[3] = 0; /* non-existent cgroup */
+
+        map_fd = get_map_fd_by_prog_id(prog_id);
+        if (map_fd < 0)
+                goto err;
+
+        for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
+                if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
+                        log_err("Failed to lookup key %d", level);
+                        goto err;
+                }
+                if (actual_ids[level] != expected_ids[level]) {
+                        log_err("%llx (actual) != %llx (expected), level: %u\n",
+                                actual_ids[level], expected_ids[level], level);
+                        goto err;
+                }
+        }
+
+        goto out;
+err:
+        err = -1;
+out:
+        if (map_fd >= 0)
+                close(map_fd);
+        return err;
+}
+
+int main(int argc, char **argv)
+{
+        int cgfd = -1;
+        int err = 0;
+
+        if (argc < 3) {
+                fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
+                exit(EXIT_FAILURE);
+        }
+
+        if (setup_cgroup_environment())
+                goto err;
+
+        cgfd = create_and_get_cgroup(CGROUP_PATH);
+        if (!cgfd)
+                goto err;
+
+        if (join_cgroup(CGROUP_PATH))
+                goto err;
+
+        if (send_packet(argv[1]))
+                goto err;
+
+        if (check_ancestor_cgroup_ids(atoi(argv[2])))
+                goto err;
+
+        goto out;
+err:
+        err = -1;
+out:
+        close(cgfd);
+        cleanup_cgroup_environment();
+        printf("[%s]\n", err ? "FAIL" : "PASS");
+        return err;
+}
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index f4d99fabc56d..b8ebe2f58074 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -14,10 +14,7 @@
 
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_util.h"
 
 #define CG_PATH         "/foo"
 #define MAX_INSNS       512
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index a5e76b9219b9..aeeb76a54d63 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -20,15 +20,12 @@
 
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
+#include "bpf_util.h"
 
 #ifndef ENOTSUPP
 # define ENOTSUPP 524
 #endif
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 #define CG_PATH "/foo"
 #define CONNECT4_PROG_PATH      "./connect4_prog.o"
 #define CONNECT6_PROG_PATH      "./connect6_prog.o"
@@ -998,8 +995,9 @@ int init_pktinfo(int domain, struct cmsghdr *cmsg)
         return 0;
 }
 
-static int sendmsg_to_server(const struct sockaddr_storage *addr,
-                             socklen_t addr_len, int set_cmsg, int *syscall_err)
+static int sendmsg_to_server(int type, const struct sockaddr_storage *addr,
+                             socklen_t addr_len, int set_cmsg, int flags,
+                             int *syscall_err)
 {
         union {
                 char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))];
@@ -1022,7 +1020,7 @@ static int sendmsg_to_server(const struct sockaddr_storage *addr,
                 goto err;
         }
 
-        fd = socket(domain, SOCK_DGRAM, 0);
+        fd = socket(domain, type, 0);
         if (fd == -1) {
                 log_err("Failed to create client socket");
                 goto err;
@@ -1052,7 +1050,7 @@ static int sendmsg_to_server(const struct sockaddr_storage *addr,
                 }
         }
 
-        if (sendmsg(fd, &hdr, 0) != sizeof(data)) {
+        if (sendmsg(fd, &hdr, flags) != sizeof(data)) {
                 log_err("Fail to send message to server");
                 *syscall_err = errno;
                 goto err;
@@ -1066,6 +1064,15 @@ out:
         return fd;
 }
 
+static int fastconnect_to_server(const struct sockaddr_storage *addr,
+                                 socklen_t addr_len)
+{
+        int sendmsg_err;
+
+        return sendmsg_to_server(SOCK_STREAM, addr, addr_len, /*set_cmsg*/0,
+                                 MSG_FASTOPEN, &sendmsg_err);
+}
+
 static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr)
 {
         struct timeval tv;
@@ -1185,6 +1192,20 @@ static int run_connect_test_case(const struct sock_addr_test *test)
         if (cmp_local_ip(clientfd, &expected_src_addr))
                 goto err;
 
+        if (test->type == SOCK_STREAM) {
+                /* Test TCP Fast Open scenario */
+                clientfd = fastconnect_to_server(&requested_addr, addr_len);
+                if (clientfd == -1)
+                        goto err;
+
+                /* Make sure src and dst addrs were overridden properly */
+                if (cmp_peer_addr(clientfd, &expected_addr))
+                        goto err;
+
+                if (cmp_local_ip(clientfd, &expected_src_addr))
+                        goto err;
+        }
+
         goto out;
 err:
         err = -1;
@@ -1222,8 +1243,9 @@ static int run_sendmsg_test_case(const struct sock_addr_test *test)
                 if (clientfd >= 0)
                         close(clientfd);
 
-                clientfd = sendmsg_to_server(&requested_addr, addr_len,
-                                             set_cmsg, &err);
+                clientfd = sendmsg_to_server(test->type, &requested_addr,
+                                             addr_len, set_cmsg, /*flags*/0,
+                                             &err);
                 if (err)
                         goto out;
                 else if (clientfd == -1)
diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
new file mode 100644
index 000000000000..68e108e4687a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH                 "/foo"
+#define SOCKET_COOKIE_PROG      "./socket_cookie_prog.o"
+
+static int start_server(void)
+{
+        struct sockaddr_in6 addr;
+        int fd;
+
+        fd = socket(AF_INET6, SOCK_STREAM, 0);
+        if (fd == -1) {
+                log_err("Failed to create server socket");
+                goto out;
+        }
+
+        memset(&addr, 0, sizeof(addr));
+        addr.sin6_family = AF_INET6;
+        addr.sin6_addr = in6addr_loopback;
+        addr.sin6_port = 0;
+
+        if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) == -1) {
+                log_err("Failed to bind server socket");
+                goto close_out;
+        }
+
+        if (listen(fd, 128) == -1) {
+                log_err("Failed to listen on server socket");
+                goto close_out;
+        }
+
+        goto out;
+
+close_out:
+        close(fd);
+        fd = -1;
+out:
+        return fd;
+}
+
+static int connect_to_server(int server_fd)
+{
+        struct sockaddr_storage addr;
+        socklen_t len = sizeof(addr);
+        int fd;
+
+        fd = socket(AF_INET6, SOCK_STREAM, 0);
+        if (fd == -1) {
+                log_err("Failed to create client socket");
+                goto out;
+        }
+
+        if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+                log_err("Failed to get server addr");
+                goto close_out;
+        }
+
+        if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+                log_err("Fail to connect to server");
+                goto close_out;
+        }
+
+        goto out;
+
+close_out:
+        close(fd);
+        fd = -1;
+out:
+        return fd;
+}
+
+static int validate_map(struct bpf_map *map, int client_fd)
+{
+        __u32 cookie_expected_value;
+        struct sockaddr_in6 addr;
+        socklen_t len = sizeof(addr);
+        __u32 cookie_value;
+        __u64 cookie_key;
+        int err = 0;
+        int map_fd;
+
+        if (!map) {
+                log_err("Map not found in BPF object");
+                goto err;
+        }
+
+        map_fd = bpf_map__fd(map);
+
+        err = bpf_map_get_next_key(map_fd, NULL, &cookie_key);
+        if (err) {
+                log_err("Can't get cookie key from map");
+                goto out;
+        }
+
+        err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value);
+        if (err) {
+                log_err("Can't get cookie value from map");
+                goto out;
+        }
+
+        err = getsockname(client_fd, (struct sockaddr *)&addr, &len);
+        if (err) {
+                log_err("Can't get client local addr");
+                goto out;
+        }
+
+        cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF;
+        if (cookie_value != cookie_expected_value) {
+                log_err("Unexpected value in map: %x != %x", cookie_value,
+                        cookie_expected_value);
+                goto err;
+        }
+
+        goto out;
+err:
+        err = -1;
+out:
+        return err;
+}
+
+static int run_test(int cgfd)
+{
+        enum bpf_attach_type attach_type;
+        struct bpf_prog_load_attr attr;
+        struct bpf_program *prog;
+        struct bpf_object *pobj;
+        const char *prog_name;
+        int server_fd = -1;
+        int client_fd = -1;
+        int prog_fd = -1;
+        int err = 0;
+
+        memset(&attr, 0, sizeof(attr));
+        attr.file = SOCKET_COOKIE_PROG;
+        attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+
+        err = bpf_prog_load_xattr(&attr, &pobj, &prog_fd);
+        if (err) {
+                log_err("Failed to load %s", attr.file);
+                goto out;
+        }
+
+        bpf_object__for_each_program(prog, pobj) {
+                prog_name = bpf_program__title(prog, /*needs_copy*/ false);
+
+                if (strcmp(prog_name, "cgroup/connect6") == 0) {
+                        attach_type = BPF_CGROUP_INET6_CONNECT;
+                } else if (strcmp(prog_name, "sockops") == 0) {
+                        attach_type = BPF_CGROUP_SOCK_OPS;
+                } else {
+                        log_err("Unexpected prog: %s", prog_name);
+                        goto err;
+                }
+
+                err = bpf_prog_attach(bpf_program__fd(prog), cgfd, attach_type,
+                                      BPF_F_ALLOW_OVERRIDE);
+                if (err) {
+                        log_err("Failed to attach prog %s", prog_name);
+                        goto out;
+                }
+        }
+
+        server_fd = start_server();
+        if (server_fd == -1)
+                goto err;
+
+        client_fd = connect_to_server(server_fd);
+        if (client_fd == -1)
+                goto err;
+
+        if (validate_map(bpf_map__next(NULL, pobj), client_fd))
+                goto err;
+
+        goto out;
+err:
+        err = -1;
+out:
+        close(client_fd);
+        close(server_fd);
+        bpf_object__close(pobj);
+        printf("%s\n", err ? "FAILED" : "PASSED");
+        return err;
+}
+
+int main(int argc, char **argv)
+{
+        int cgfd = -1;
+        int err = 0;
+
+        if (setup_cgroup_environment())
+                goto err;
+
+        cgfd = create_and_get_cgroup(CG_PATH);
+        if (!cgfd)
+                goto err;
+
+        if (join_cgroup(CG_PATH))
+                goto err;
+
+        if (run_test(cgfd))
+                goto err;
+
+        goto out;
+err:
+        err = -1;
+out:
+        close(cgfd);
+        cleanup_cgroup_environment();
+        return err;
+}
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
index 2fe43289943c..7bcfa6207005 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf.h
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -12,5 +12,6 @@ struct tcpbpf_globals {
         __u32 good_cb_test_rv;
         __u64 bytes_received;
         __u64 bytes_acked;
+        __u32 num_listen;
 };
 #endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 3e645ee41ed5..4b7fd540cea9 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -96,15 +96,22 @@ int bpf_testcb(struct bpf_sock_ops *skops)
                         if (!gp)
                                 break;
                         g = *gp;
-                        g.total_retrans = skops->total_retrans;
-                        g.data_segs_in = skops->data_segs_in;
-                        g.data_segs_out = skops->data_segs_out;
-                        g.bytes_received = skops->bytes_received;
-                        g.bytes_acked = skops->bytes_acked;
+                        if (skops->args[0] == BPF_TCP_LISTEN) {
+                                g.num_listen++;
+                        } else {
+                                g.total_retrans = skops->total_retrans;
+                                g.data_segs_in = skops->data_segs_in;
+                                g.data_segs_out = skops->data_segs_out;
+                                g.bytes_received = skops->bytes_received;
+                                g.bytes_acked = skops->bytes_acked;
+                        }
                         bpf_map_update_elem(&global_map, &key, &g,
                                             BPF_ANY);
                 }
                 break;
+        case BPF_SOCK_OPS_TCP_LISTEN_CB:
+                bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+                break;
         default:
                 rv = -1;
         }
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 84ab5163c828..a275c2971376 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -1,27 +1,59 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <stdio.h>
 #include <unistd.h>
 #include <errno.h>
-#include <signal.h>
 #include <string.h>
-#include <assert.h>
-#include <linux/perf_event.h>
-#include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
 #include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
-#include "bpf_util.h"
+
 #include "bpf_rlimit.h"
-#include <linux/perf_event.h>
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
 #include "test_tcpbpf.h"
 
+#define EXPECT_EQ(expected, actual, fmt)                        \
+        do {                                                    \
+                if ((expected) != (actual)) {                   \
+                        printf("  Value of: " #actual "\n"      \
+                               "    Actual: %" fmt "\n"         \
+                               "  Expected: %" fmt "\n",        \
+                               (actual), (expected));           \
+                        goto err;                               \
+                }                                               \
+        } while (0)
+
+int verify_result(const struct tcpbpf_globals *result)
+{
+        __u32 expected_events;
+
+        expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+                           (1 << BPF_SOCK_OPS_RWND_INIT) |
+                           (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+                           (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+                           (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+                           (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+                           (1 << BPF_SOCK_OPS_STATE_CB) |
+                           (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+        EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
+        EXPECT_EQ(501ULL, result->bytes_received, "llu");
+        EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
+        EXPECT_EQ(1, result->data_segs_in, PRIu32);
+        EXPECT_EQ(1, result->data_segs_out, PRIu32);
+        EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
+        EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
+        EXPECT_EQ(1, result->num_listen, PRIu32);
+
+        return 0;
+err:
+        return -1;
+}
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
                         const char *name)
 {
@@ -35,42 +67,28 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
         return bpf_map__fd(map);
 }
 
-#define SYSTEM(CMD)                                             \
-        do {                                                    \
-                if (system(CMD)) {                              \
-                        printf("system(%s) FAILS!\n", CMD);     \
-                }                                               \
-        } while (0)
-
 int main(int argc, char **argv)
 {
         const char *file = "test_tcpbpf_kern.o";
         struct tcpbpf_globals g = {0};
-        int cg_fd, prog_fd, map_fd;
-        bool debug_flag = false;
+        const char *cg_path = "/foo";
         int error = EXIT_FAILURE;
         struct bpf_object *obj;
-        char cmd[100], *dir;
-        struct stat buffer;
+        int prog_fd, map_fd;
+        int cg_fd = -1;
         __u32 key = 0;
-        int pid;
         int rv;
 
-        if (argc > 1 && strcmp(argv[1], "-d") == 0)
-                debug_flag = true;
+        if (setup_cgroup_environment())
+                goto err;
 
-        dir = "/tmp/cgroupv2/foo";
+        cg_fd = create_and_get_cgroup(cg_path);
+        if (!cg_fd)
+                goto err;
 
-        if (stat(dir, &buffer) != 0) {
-                SYSTEM("mkdir -p /tmp/cgroupv2");
-                SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
-                SYSTEM("mkdir -p /tmp/cgroupv2/foo");
-        }
-        pid = (int) getpid();
-        sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
-        SYSTEM(cmd);
+        if (join_cgroup(cg_path))
+                goto err;
 
-        cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
         if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
                 printf("FAILED: load_bpf_file failed for: %s\n", file);
                 goto err;
@@ -83,7 +101,10 @@ int main(int argc, char **argv)
                 goto err;
         }
 
-        SYSTEM("./tcp_server.py");
+        if (system("./tcp_server.py")) {
+                printf("FAILED: TCP server\n");
+                goto err;
+        }
 
         map_fd = bpf_find_map(__func__, obj, "global_map");
         if (map_fd < 0)
@@ -95,34 +116,16 @@ int main(int argc, char **argv)
                 goto err;
         }
 
-        if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
-            g.data_segs_in != 1 || g.data_segs_out != 1 ||
-            (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
-                g.good_cb_test_rv != 0) {
+        if (verify_result(&g)) {
                 printf("FAILED: Wrong stats\n");
-                if (debug_flag) {
-                        printf("\n");
-                        printf("bytes_received: %d (expecting 501)\n",
-                               (int)g.bytes_received);
-                        printf("bytes_acked:    %d (expecting 1002)\n",
-                               (int)g.bytes_acked);
-                        printf("data_segs_in:   %d (expecting 1)\n",
-                               g.data_segs_in);
-                        printf("data_segs_out:  %d (expecting 1)\n",
-                               g.data_segs_out);
-                        printf("event_map:      0x%x (at least 0x47e)\n",
-                               g.event_map);
-                        printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
-                               g.bad_cb_test_rv);
-                        printf("good_cb_test_rv:0x%x (expecting 0)\n",
-                               g.good_cb_test_rv);
-                }
                 goto err;
         }
+
         printf("PASSED!\n");
         error = 0;
 err:
         bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+        close(cg_fd);
+        cleanup_cgroup_environment();
         return error;
-
 }
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 41106d9d5cc7..67c412d19c09 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -42,15 +42,12 @@
 #endif
 #include "bpf_rlimit.h"
 #include "bpf_rand.h"
+#include "bpf_util.h"
 #include "../../../include/linux/filter.h"
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 #define MAX_INSNS       BPF_MAXINSNS
 #define MAX_FIXUPS      8
-#define MAX_NR_MAPS     7
+#define MAX_NR_MAPS     8
 #define POINTER_VALUE   0xcafe4all
 #define TEST_DATA_LEN   64
 
@@ -70,6 +67,7 @@ struct bpf_test {
         int fixup_prog1[MAX_FIXUPS];
         int fixup_prog2[MAX_FIXUPS];
         int fixup_map_in_map[MAX_FIXUPS];
+        int fixup_cgroup_storage[MAX_FIXUPS];
         const char *errstr;
         const char *errstr_unpriv;
         uint32_t retval;
@@ -4631,6 +4629,121 @@ static struct bpf_test tests[] = {
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
+                "valid cgroup storage access",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_cgroup_storage = { 1 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid cgroup storage access 1",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 1 },
+                .result = REJECT,
+                .errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid cgroup storage access 2",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 1),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "fd 1 is not pointing to valid bpf_map",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid per-cgroup storage access 3",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_cgroup_storage = { 1 },
+                .result = REJECT,
+                .errstr = "invalid access to map value, value_size=64 off=256 size=4",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid cgroup storage access 4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_cgroup_storage = { 1 },
+                .result = REJECT,
+                .errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid cgroup storage access 5",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 7),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_cgroup_storage = { 1 },
+                .result = REJECT,
+                .errstr = "get_local_storage() doesn't support non-zero flags",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
+                "invalid cgroup storage access 6",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_get_local_storage),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_cgroup_storage = { 1 },
+                .result = REJECT,
+                .errstr = "get_local_storage() doesn't support non-zero flags",
+                .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+        },
+        {
                 "multiple registers share map_lookup_elem result",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_1, 10),
@@ -6997,7 +7110,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
-                        BPF_MOV64_REG(BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map_in_map = { 3 },
@@ -7020,7 +7133,7 @@ static struct bpf_test tests[] = {
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
-                        BPF_MOV64_REG(BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map_in_map = { 3 },
@@ -7042,7 +7155,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
-                        BPF_MOV64_REG(BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map_in_map = { 3 },
@@ -12372,6 +12485,32 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
                 .errstr = "variable ctx access var_off=(0x0; 0x4)",
         },
+        {
+                "mov64 src == dst",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_2),
+                        // Check bounds are OK
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .result = ACCEPT,
+        },
+        {
+                "mov64 src != dst",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_3),
+                        // Check bounds are OK
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .result = ACCEPT,
+        },
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -12476,6 +12615,19 @@ static int create_map_in_map(void)
         return outer_map_fd;
 }
 
+static int create_cgroup_storage(void)
+{
+        int fd;
+
+        fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+                            sizeof(struct bpf_cgroup_storage_key),
+                            TEST_DATA_LEN, 0, 0);
+        if (fd < 0)
+                printf("Failed to create array '%s'!\n", strerror(errno));
+
+        return fd;
+}
+
 static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
@@ -12488,6 +12640,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
         int *fixup_prog1 = test->fixup_prog1;
         int *fixup_prog2 = test->fixup_prog2;
         int *fixup_map_in_map = test->fixup_map_in_map;
+        int *fixup_cgroup_storage = test->fixup_cgroup_storage;
 
         if (test->fill_helper)
                 test->fill_helper(test);
@@ -12555,6 +12708,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
                         fixup_map_in_map++;
                 } while (*fixup_map_in_map);
         }
+
+        if (*fixup_cgroup_storage) {
+                map_fds[7] = create_cgroup_storage();
+                do {
+                        prog[*fixup_cgroup_storage].imm = map_fds[7];
+                        fixup_cgroup_storage++;
+                } while (*fixup_cgroup_storage);
+        }
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 3868dcb63420..cabe2a3a3b30 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -88,7 +88,7 @@ static int page_size;
 static int page_cnt = 8;
 static struct perf_event_mmap_page *header;
 
-int perf_event_mmap(int fd)
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header)
 {
         void *base;
         int mmap_size;
@@ -102,10 +102,15 @@ int perf_event_mmap(int fd)
                 return -1;
         }
 
-        header = base;
+        *header = base;
         return 0;
 }
 
+int perf_event_mmap(int fd)
+{
+        return perf_event_mmap_header(fd, &header);
+}
+
 static int perf_event_poll(int fd)
 {
         struct pollfd pfd = { .fd = fd, .events = POLLIN };
@@ -163,3 +168,42 @@ int perf_event_poller(int fd, perf_event_print_fn output_fn)
 
         return ret;
 }
+
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+                            int num_fds, perf_event_print_fn output_fn)
+{
+        enum bpf_perf_event_ret ret;
+        struct pollfd *pfds;
+        void *buf = NULL;
+        size_t len = 0;
+        int i;
+
+        pfds = calloc(num_fds, sizeof(*pfds));
+        if (!pfds)
+                return LIBBPF_PERF_EVENT_ERROR;
+
+        for (i = 0; i < num_fds; i++) {
+                pfds[i].fd = fds[i];
+                pfds[i].events = POLLIN;
+        }
+
+        for (;;) {
+                poll(pfds, num_fds, 1000);
+                for (i = 0; i < num_fds; i++) {
+                        if (!pfds[i].revents)
+                                continue;
+
+                        ret = bpf_perf_event_read_simple(headers[i],
+                                                         page_cnt * page_size,
+                                                         page_size, &buf, &len,
+                                                         bpf_perf_event_print,
+                                                         output_fn);
+                        if (ret != LIBBPF_PERF_EVENT_CONT)
+                                break;
+                }
+        }
+        free(buf);
+        free(pfds);
+
+        return ret;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 3b4bcf7f5084..18924f23db1b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -3,6 +3,7 @@
 #define __TRACE_HELPER_H
 
 #include <libbpf.h>
+#include <linux/perf_event.h>
 
 struct ksym {
         long addr;
@@ -16,6 +17,9 @@ long ksym_get_addr(const char *name);
 typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
 
 int perf_event_mmap(int fd);
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header);
 /* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */
 int perf_event_poller(int fd, perf_event_print_fn output_fn);
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+                            int num_fds, perf_event_print_fn output_fn);
 #endif
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
new file mode 100755
index 000000000000..76f1ab4898d9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
@@ -0,0 +1,217 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# ../../../net/forwarding/mirror_gre_topo_lib.sh for more details.
+#
+# Test offloading various features of offloading gretap mirrors specific to
+# mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+source $lib_dir/mirror_lib.sh
+source $lib_dir/mirror_gre_lib.sh
+source $lib_dir/mirror_gre_topo_lib.sh
+
+setup_keyful()
+{
+        tunnel_create gt6-key ip6gretap 2001:db8:3::1 2001:db8:3::2 \
+                      ttl 100 tos inherit allow-localremote \
+                      key 1234
+
+        tunnel_create h3-gt6-key ip6gretap 2001:db8:3::2 2001:db8:3::1 \
+                      key 1234
+        ip link set h3-gt6-key vrf v$h3
+        matchall_sink_create h3-gt6-key
+
+        ip address add dev $swp3 2001:db8:3::1/64
+        ip address add dev $h3 2001:db8:3::2/64
+}
+
+cleanup_keyful()
+{
+        ip address del dev $h3 2001:db8:3::2/64
+        ip address del dev $swp3 2001:db8:3::1/64
+
+        tunnel_destroy h3-gt6-key
+        tunnel_destroy gt6-key
+}
+
+setup_soft()
+{
+        # Set up a topology for testing underlay routes that point at an
+        # unsupported soft device.
+
+        tunnel_create gt6-soft ip6gretap 2001:db8:4::1 2001:db8:4::2 \
+                      ttl 100 tos inherit allow-localremote
+
+        tunnel_create h3-gt6-soft ip6gretap 2001:db8:4::2 2001:db8:4::1
+        ip link set h3-gt6-soft vrf v$h3
+        matchall_sink_create h3-gt6-soft
+
+        ip link add name v1 type veth peer name v2
+        ip link set dev v1 up
+        ip address add dev v1 2001:db8:4::1/64
+
+        ip link set dev v2 vrf v$h3
+        ip link set dev v2 up
+        ip address add dev v2 2001:db8:4::2/64
+}
+
+cleanup_soft()
+{
+        ip link del dev v1
+
+        tunnel_destroy h3-gt6-soft
+        tunnel_destroy gt6-soft
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        swp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        vrf_prepare
+        mirror_gre_topo_create
+
+        ip address add dev $swp3 2001:db8:2::1/64
+        ip address add dev $h3 2001:db8:2::2/64
+
+        ip address add dev $swp3 192.0.2.129/28
+        ip address add dev $h3 192.0.2.130/28
+
+        setup_keyful
+        setup_soft
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        cleanup_soft
+        cleanup_keyful
+
+        ip address del dev $h3 2001:db8:2::2/64
+        ip address del dev $swp3 2001:db8:2::1/64
+
+        ip address del dev $h3 192.0.2.130/28
+        ip address del dev $swp3 192.0.2.129/28
+
+        mirror_gre_topo_destroy
+        vrf_cleanup
+}
+
+test_span_gre_ttl_inherit()
+{
+        local tundev=$1; shift
+        local type=$1; shift
+        local what=$1; shift
+
+        RET=0
+
+        ip link set dev $tundev type $type ttl inherit
+        mirror_install $swp1 ingress $tundev "matchall $tcflags"
+        fail_test_span_gre_dir $tundev ingress
+
+        ip link set dev $tundev type $type ttl 100
+
+        quick_test_span_gre_dir $tundev ingress
+        mirror_uninstall $swp1 ingress
+
+        log_test "$what: no offload on TTL of inherit ($tcflags)"
+}
+
+test_span_gre_tos_fixed()
+{
+        local tundev=$1; shift
+        local type=$1; shift
+        local what=$1; shift
+
+        RET=0
+
+        ip link set dev $tundev type $type tos 0x10
+        mirror_install $swp1 ingress $tundev "matchall $tcflags"
+        fail_test_span_gre_dir $tundev ingress
+
+        ip link set dev $tundev type $type tos inherit
+        quick_test_span_gre_dir $tundev ingress
+        mirror_uninstall $swp1 ingress
+
+        log_test "$what: no offload on a fixed TOS ($tcflags)"
+}
+
+test_span_failable()
+{
+        local should_fail=$1; shift
+        local tundev=$1; shift
+        local what=$1; shift
+
+        RET=0
+
+        mirror_install $swp1 ingress $tundev "matchall $tcflags"
+        if ((should_fail)); then
+            fail_test_span_gre_dir  $tundev ingress
+        else
+            quick_test_span_gre_dir $tundev ingress
+        fi
+        mirror_uninstall $swp1 ingress
+
+        log_test "$what: should_fail=$should_fail ($tcflags)"
+}
+
+test_failable()
+{
+        local should_fail=$1; shift
+
+        test_span_failable $should_fail gt6-key "mirror to keyful gretap"
+        test_span_failable $should_fail gt6-soft "mirror to gretap w/ soft underlay"
+}
+
+test_sw()
+{
+        slow_path_trap_install $swp1 ingress
+        slow_path_trap_install $swp1 egress
+
+        test_failable 0
+
+        slow_path_trap_uninstall $swp1 egress
+        slow_path_trap_uninstall $swp1 ingress
+}
+
+test_hw()
+{
+        test_failable 1
+
+        test_span_gre_tos_fixed gt4 gretap "mirror to gretap"
+        test_span_gre_tos_fixed gt6 ip6gretap "mirror to ip6gretap"
+
+        test_span_gre_ttl_inherit gt4 gretap "mirror to gretap"
+        test_span_gre_ttl_inherit gt6 ip6gretap "mirror to ip6gretap"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+if ! tc_offload_check; then
+    check_err 1 "Could not test offloaded functionality"
+    log_test "mlxsw-specific tests for mirror to gretap"
+    exit
+fi
+
+tcflags="skip_hw"
+test_sw
+
+tcflags="skip_sw"
+test_hw
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
new file mode 100644
index 000000000000..6f3a70df63bc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
@@ -0,0 +1,197 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Test offloading a number of mirrors-to-gretap. The test creates a number of
+# tunnels. Then it adds one flower mirror for each of the tunnels, matching a
+# given host IP. Then it generates traffic at each of the host IPs and checks
+# that the traffic has been mirrored at the appropriate tunnel.
+#
+#   +--------------------------+                   +--------------------------+
+#   | H1                       |                   |                       H2 |
+#   |     + $h1                |                   |                $h2 +     |
+#   |     | 2001:db8:1:X::1/64 |                   | 2001:db8:1:X::2/64 |     |
+#   +-----|--------------------+                   +--------------------|-----+
+#         |                                                             |
+#   +-----|-------------------------------------------------------------|-----+
+#   | SW  o--> mirrors                                                  |     |
+#   | +---|-------------------------------------------------------------|---+ |
+#   | |   + $swp1                    BR                           $swp2 +   | |
+#   | +---------------------------------------------------------------------+ |
+#   |                                                                         |
+#   |     + $swp3                          + gt6-<X> (ip6gretap)              |
+#   |     | 2001:db8:2:X::1/64             : loc=2001:db8:2:X::1              |
+#   |     |                                : rem=2001:db8:2:X::2              |
+#   |     |                                : ttl=100                          |
+#   |     |                                : tos=inherit                      |
+#   |     |                                :                                  |
+#   +-----|--------------------------------:----------------------------------+
+#         |                                :
+#   +-----|--------------------------------:----------------------------------+
+#   | H3  + $h3                            + h3-gt6-<X> (ip6gretap)           |
+#   |       2001:db8:2:X::2/64               loc=2001:db8:2:X::2              |
+#   |                                        rem=2001:db8:2:X::1              |
+#   |                                        ttl=100                          |
+#   |                                        tos=inherit                      |
+#   |                                                                         |
+#   +-------------------------------------------------------------------------+
+
+source ../../../../net/forwarding/mirror_lib.sh
+
+MIRROR_NUM_NETIFS=6
+
+mirror_gre_ipv6_addr()
+{
+        local net=$1; shift
+        local num=$1; shift
+
+        printf "2001:db8:%x:%x" $net $num
+}
+
+mirror_gre_tunnels_create()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+
+        MIRROR_GRE_BATCH_FILE="$(mktemp)"
+        for ((i=0; i < count; ++i)); do
+                local match_dip=$(mirror_gre_ipv6_addr 1 $i)::2
+                local htun=h3-gt6-$i
+                local tun=gt6-$i
+
+                ((mirror_gre_tunnels++))
+
+                ip address add dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+                ip address add dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+
+                ip address add dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+                ip address add dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+
+                tunnel_create $tun ip6gretap \
+                              $(mirror_gre_ipv6_addr 2 $i)::1 \
+                              $(mirror_gre_ipv6_addr 2 $i)::2 \
+                              ttl 100 tos inherit allow-localremote
+
+                tunnel_create $htun ip6gretap \
+                              $(mirror_gre_ipv6_addr 2 $i)::2 \
+                              $(mirror_gre_ipv6_addr 2 $i)::1
+                ip link set $htun vrf v$h3
+                matchall_sink_create $htun
+
+                cat >> $MIRROR_GRE_BATCH_FILE <<-EOF
+                        filter add dev $swp1 ingress pref 1000 \
+                                protocol ipv6 \
+                                flower $tcflags dst_ip $match_dip \
+                                action mirred egress mirror dev $tun
+                EOF
+        done
+
+        tc -b $MIRROR_GRE_BATCH_FILE
+        check_err_fail $should_fail $? "Mirror rule insertion"
+}
+
+mirror_gre_tunnels_destroy()
+{
+        local count=$1; shift
+
+        for ((i=0; i < count; ++i)); do
+                local htun=h3-gt6-$i
+                local tun=gt6-$i
+
+                ip address del dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+                ip address del dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+
+                ip address del dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+                ip address del dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+
+                tunnel_destroy $htun
+                tunnel_destroy $tun
+        done
+}
+
+__mirror_gre_test()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+
+        mirror_gre_tunnels_create $count $should_fail
+        if ((should_fail)); then
+            return
+        fi
+
+        sleep 5
+
+        for ((i = 0; i < count; ++i)); do
+                local dip=$(mirror_gre_ipv6_addr 1 $i)::2
+                local htun=h3-gt6-$i
+                local message
+
+                icmp6_capture_install $htun
+                mirror_test v$h1 "" $dip $htun 100 10
+                icmp6_capture_uninstall $htun
+        done
+}
+
+mirror_gre_test()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+
+        if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+                check_err 1 "Could not test offloaded functionality"
+                return
+        fi
+
+        tcflags="skip_sw"
+        __mirror_gre_test $count $should_fail
+}
+
+mirror_gre_setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        swp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        mirror_gre_tunnels=0
+
+        vrf_prepare
+
+        simple_if_init $h1
+        simple_if_init $h2
+        simple_if_init $h3
+
+        ip link add name br1 type bridge vlan_filtering 1
+        ip link set dev br1 up
+
+        ip link set dev $swp1 master br1
+        ip link set dev $swp1 up
+        tc qdisc add dev $swp1 clsact
+
+        ip link set dev $swp2 master br1
+        ip link set dev $swp2 up
+
+        ip link set dev $swp3 up
+}
+
+mirror_gre_cleanup()
+{
+        mirror_gre_tunnels_destroy $mirror_gre_tunnels
+
+        ip link set dev $swp3 down
+
+        ip link set dev $swp2 down
+
+        tc qdisc del dev $swp1 clsact
+        ip link set dev $swp1 down
+
+        ip link del dev br1
+
+        simple_if_fini $h3
+        simple_if_fini $h2
+        simple_if_fini $h1
+
+        vrf_cleanup
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
new file mode 100755
index 000000000000..1ca631d5aaba
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -0,0 +1,189 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for DSCP prioritization and rewrite. Packets ingress $swp1 with a DSCP
+# tag and are prioritized according to the map at $swp1. They egress $swp2 and
+# the DSCP value is updated to match the map at that interface. The updated DSCP
+# tag is verified at $h2.
+#
+# ICMP responses are produced with the same DSCP tag that arrived at $h2. They
+# go through prioritization at $swp2 and DSCP retagging at $swp1. The tag is
+# verified at $h1--it should match the original tag.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1             |                             |            $h2 +     |
+# |    | 192.0.2.1/28    |                             |   192.0.2.2/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                                                |
+# +----|----------------------------------------------------------------|-----+
+# | SW |                                                                |     |
+# |  +-|----------------------------------------------------------------|-+   |
+# |  | + $swp1                       BR                           $swp2 + |   |
+# |  |   APP=0,5,10 .. 7,5,17                      APP=0,5,20 .. 7,5,27   |   |
+# |  +--------------------------------------------------------------------+   |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+        ping_ipv4
+        test_dscp
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+
+h1_create()
+{
+        local dscp;
+
+        simple_if_init $h1 192.0.2.1/28
+        tc qdisc add dev $h1 clsact
+        dscp_capture_install $h1 10
+}
+
+h1_destroy()
+{
+        dscp_capture_uninstall $h1 10
+        tc qdisc del dev $h1 clsact
+        simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.2/28
+        tc qdisc add dev $h2 clsact
+        dscp_capture_install $h2 20
+}
+
+h2_destroy()
+{
+        dscp_capture_uninstall $h2 20
+        tc qdisc del dev $h2 clsact
+        simple_if_fini $h2 192.0.2.2/28
+}
+
+dscp_map()
+{
+        local base=$1; shift
+
+        for prio in {0..7}; do
+                echo app=$prio,5,$((base + prio))
+        done
+}
+
+switch_create()
+{
+        ip link add name br1 type bridge vlan_filtering 1
+        ip link set dev br1 up
+        ip link set dev $swp1 master br1
+        ip link set dev $swp1 up
+        ip link set dev $swp2 master br1
+        ip link set dev $swp2 up
+
+        lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null
+        lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null
+        lldpad_app_wait_set $swp1
+        lldpad_app_wait_set $swp2
+}
+
+switch_destroy()
+{
+        lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null
+        lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null
+        lldpad_app_wait_del
+
+        ip link set dev $swp2 nomaster
+        ip link set dev $swp1 nomaster
+        ip link del dev br1
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+        switch_create
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        switch_destroy
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+ping_ipv4()
+{
+        ping_test $h1 192.0.2.2
+}
+
+dscp_ping_test()
+{
+        local vrf_name=$1; shift
+        local sip=$1; shift
+        local dip=$1; shift
+        local prio=$1; shift
+        local dev_10=$1; shift
+        local dev_20=$1; shift
+
+        local dscp_10=$(((prio + 10) << 2))
+        local dscp_20=$(((prio + 20) << 2))
+
+        RET=0
+
+        local -A t0s
+        eval "t0s=($(dscp_fetch_stats $dev_10 10)
+                   $(dscp_fetch_stats $dev_20 20))"
+
+        ip vrf exec $vrf_name \
+           ${PING} -Q $dscp_10 ${sip:+-I $sip} $dip \
+                   -c 10 -i 0.1 -w 2 &> /dev/null
+
+        local -A t1s
+        eval "t1s=($(dscp_fetch_stats $dev_10 10)
+                   $(dscp_fetch_stats $dev_20 20))"
+
+        for key in ${!t0s[@]}; do
+                local expect
+                if ((key == prio+10 || key == prio+20)); then
+                        expect=10
+                else
+                        expect=0
+                fi
+
+                local delta=$((t1s[$key] - t0s[$key]))
+                ((expect == delta))
+                check_err $? "DSCP $key: Expected to capture $expect packets, got $delta."
+        done
+
+        log_test "DSCP rewrite: $dscp_10-(prio $prio)-$dscp_20"
+}
+
+test_dscp()
+{
+        for prio in {0..7}; do
+                dscp_ping_test v$h1 192.0.2.1 192.0.2.2 $prio $h1 $h2
+        done
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
new file mode 100755
index 000000000000..281d90766e12
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
@@ -0,0 +1,233 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for DSCP prioritization in the router.
+#
+# With ip_forward_update_priority disabled, the packets are expected to keep
+# their DSCP (which in this test uses only values 0..7) intact as they are
+# forwarded by the switch. That is verified at $h2. ICMP responses are formed
+# with the same DSCP as the requests, and likewise pass through the switch
+# intact, which is verified at $h1.
+#
+# With ip_forward_update_priority enabled, router reprioritizes the packets
+# according to the table in reprioritize(). Thus, say, DSCP 7 maps to priority
+# 4, which on egress maps back to DSCP 4. The response packet then gets
+# reprioritized to 6, getting DSCP 6 on egress.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1             |                             |            $h2 +     |
+# |    | 192.0.2.1/28    |                             |  192.0.2.18/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                                                |
+# +----|----------------------------------------------------------------|-----+
+# | SW |                                                                |     |
+# |    + $swp1                                                    $swp2 +     |
+# |      192.0.2.2/28                                     192.0.2.17/28       |
+# |      APP=0,5,0 .. 7,5,7                          APP=0,5,0 .. 7,5,7       |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+        ping_ipv4
+        test_update
+        test_no_update
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+
+reprioritize()
+{
+        local in=$1; shift
+
+        # This is based on rt_tos2priority in include/net/route.h. Assuming 1:1
+        # mapping between priorities and TOS, it yields a new priority for a
+        # packet with ingress priority of $in.
+        local -a reprio=(0 0 2 2 6 6 4 4)
+
+        echo ${reprio[$in]}
+}
+
+h1_create()
+{
+        local dscp;
+
+        simple_if_init $h1 192.0.2.1/28
+        tc qdisc add dev $h1 clsact
+        dscp_capture_install $h1 0
+        ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+}
+
+h1_destroy()
+{
+        ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+        dscp_capture_uninstall $h1 0
+        tc qdisc del dev $h1 clsact
+        simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.18/28
+        tc qdisc add dev $h2 clsact
+        dscp_capture_install $h2 0
+        ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+}
+
+h2_destroy()
+{
+        ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+        dscp_capture_uninstall $h2 0
+        tc qdisc del dev $h2 clsact
+        simple_if_fini $h2 192.0.2.18/28
+}
+
+dscp_map()
+{
+        local base=$1; shift
+
+        for prio in {0..7}; do
+                echo app=$prio,5,$((base + prio))
+        done
+}
+
+switch_create()
+{
+        simple_if_init $swp1 192.0.2.2/28
+        __simple_if_init $swp2 v$swp1 192.0.2.17/28
+
+        lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null
+        lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null
+        lldpad_app_wait_set $swp1
+        lldpad_app_wait_set $swp2
+}
+
+switch_destroy()
+{
+        lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null
+        lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null
+        lldpad_app_wait_del
+
+        __simple_if_fini $swp2 192.0.2.17/28
+        simple_if_fini $swp1 192.0.2.2/28
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        vrf_prepare
+
+        sysctl_set net.ipv4.ip_forward_update_priority 1
+        h1_create
+        h2_create
+        switch_create
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        switch_destroy
+        h2_destroy
+        h1_destroy
+        sysctl_restore net.ipv4.ip_forward_update_priority
+
+        vrf_cleanup
+}
+
+ping_ipv4()
+{
+        ping_test $h1 192.0.2.18
+}
+
+dscp_ping_test()
+{
+        local vrf_name=$1; shift
+        local sip=$1; shift
+        local dip=$1; shift
+        local prio=$1; shift
+        local reprio=$1; shift
+        local dev1=$1; shift
+        local dev2=$1; shift
+
+        local prio2=$($reprio $prio)   # ICMP Request egress prio
+        local prio3=$($reprio $prio2)  # ICMP Response egress prio
+
+        local dscp=$((prio << 2))     # ICMP Request ingress DSCP
+        local dscp2=$((prio2 << 2))   # ICMP Request egress DSCP
+        local dscp3=$((prio3 << 2))   # ICMP Response egress DSCP
+
+        RET=0
+
+        eval "local -A dev1_t0s=($(dscp_fetch_stats $dev1 0))"
+        eval "local -A dev2_t0s=($(dscp_fetch_stats $dev2 0))"
+
+        ip vrf exec $vrf_name \
+           ${PING} -Q $dscp ${sip:+-I $sip} $dip \
+                   -c 10 -i 0.1 -w 2 &> /dev/null
+
+        eval "local -A dev1_t1s=($(dscp_fetch_stats $dev1 0))"
+        eval "local -A dev2_t1s=($(dscp_fetch_stats $dev2 0))"
+
+        for i in {0..7}; do
+                local dscpi=$((i << 2))
+                local expect2=0
+                local expect3=0
+
+                if ((i == prio2)); then
+                        expect2=10
+                fi
+                if ((i == prio3)); then
+                        expect3=10
+                fi
+
+                local delta=$((dev2_t1s[$i] - dev2_t0s[$i]))
+                ((expect2 == delta))
+                check_err $? "DSCP $dscpi@$dev2: Expected to capture $expect2 packets, got $delta."
+
+                delta=$((dev1_t1s[$i] - dev1_t0s[$i]))
+                ((expect3 == delta))
+                check_err $? "DSCP $dscpi@$dev1: Expected to capture $expect3 packets, got $delta."
+        done
+
+        log_test "DSCP rewrite: $dscp-(prio $prio2)-$dscp2-(prio $prio3)-$dscp3"
+}
+
+__test_update()
+{
+        local update=$1; shift
+        local reprio=$1; shift
+
+        sysctl_restore net.ipv4.ip_forward_update_priority
+        sysctl_set net.ipv4.ip_forward_update_priority $update
+
+        for prio in {0..7}; do
+                dscp_ping_test v$h1 192.0.2.1 192.0.2.18 $prio $reprio $h1 $h2
+        done
+}
+
+test_update()
+{
+        __test_update 1 reprioritize
+}
+
+test_no_update()
+{
+        __test_update 0 echo
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
new file mode 100644
index 000000000000..d231649b4f01
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
@@ -0,0 +1,167 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ROUTER_NUM_NETIFS=4
+
+router_h1_create()
+{
+        simple_if_init $h1 192.0.1.1/24
+        ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1
+}
+
+router_h1_destroy()
+{
+        ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1
+        simple_if_fini $h1 192.0.1.1/24
+}
+
+router_h2_create()
+{
+        simple_if_init $h2 192.0.2.1/24
+        tc qdisc add dev $h2 handle ffff: ingress
+}
+
+router_h2_destroy()
+{
+        tc qdisc del dev $h2 handle ffff: ingress
+        simple_if_fini $h2 192.0.2.1/24
+}
+
+router_create()
+{
+        ip link set dev $rp1 up
+        ip link set dev $rp2 up
+
+        ip address add 192.0.1.2/24 dev $rp1
+        ip address add 192.0.2.2/24 dev $rp2
+}
+
+router_destroy()
+{
+        ip address del 192.0.2.2/24 dev $rp2
+        ip address del 192.0.1.2/24 dev $rp1
+
+        ip link set dev $rp2 down
+        ip link set dev $rp1 down
+}
+
+router_setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        rp1=${NETIFS[p2]}
+
+        rp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        h1mac=$(mac_get $h1)
+        rp1mac=$(mac_get $rp1)
+
+        vrf_prepare
+
+        router_h1_create
+        router_h2_create
+
+        router_create
+}
+
+router_offload_validate()
+{
+        local route_count=$1
+        local offloaded_count
+
+        offloaded_count=$(ip route | grep -o 'offload' | wc -l)
+        [[ $offloaded_count -ge $route_count ]]
+}
+
+router_routes_create()
+{
+        local route_count=$1
+        local count=0
+
+        ROUTE_FILE="$(mktemp)"
+
+        for i in {0..255}
+        do
+                for j in {0..255}
+                do
+                        for k in {0..255}
+                        do
+                                if [[ $count -eq $route_count ]]; then
+                                        break 3
+                                fi
+
+                                echo route add 193.${i}.${j}.${k}/32 via \
+                                       192.0.2.1 dev $rp2  >> $ROUTE_FILE
+                                ((count++))
+                        done
+                done
+        done
+
+        ip -b $ROUTE_FILE &> /dev/null
+}
+
+router_routes_destroy()
+{
+        if [[ -v ROUTE_FILE ]]; then
+                rm -f $ROUTE_FILE
+        fi
+}
+
+router_test()
+{
+        local route_count=$1
+        local should_fail=$2
+        local count=0
+
+        RET=0
+
+        router_routes_create $route_count
+
+        router_offload_validate $route_count
+        check_err_fail $should_fail $? "Offload of $route_count routes"
+        if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then
+                return
+        fi
+
+        tc filter add dev $h2 ingress protocol ip pref 1 flower \
+                skip_sw dst_ip 193.0.0.0/8 action drop
+
+        for i in {0..255}
+        do
+                for j in {0..255}
+                do
+                        for k in {0..255}
+                        do
+                                if [[ $count -eq $route_count ]]; then
+                                        break 3
+                                fi
+
+                                $MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \
+                                        -A 192.0.1.1 -B 193.${i}.${j}.${k} \
+                                        -t ip -q
+                                ((count++))
+                        done
+                done
+        done
+
+        tc_check_packets "dev $h2 ingress" 1 $route_count
+        check_err $? "Offload mismatch"
+
+        tc filter del dev $h2 ingress protocol ip pref 1 flower \
+                skip_sw dst_ip 193.0.0.0/8 action drop
+
+        router_routes_destroy
+}
+
+router_cleanup()
+{
+        pre_cleanup
+
+        router_routes_destroy
+        router_destroy
+
+        router_h2_destroy
+        router_h1_destroy
+
+        vrf_cleanup
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
new file mode 100755
index 000000000000..3b75180f455d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -0,0 +1,366 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking the A-TCAM and C-TCAM operation in Spectrum-2.
+# It tries to exercise as many code paths in the eRP state machine as
+# possible.
+
+lib_dir=$(dirname $0)/../../../../net/forwarding
+
+ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
+        multiple_masks_test ctcam_edge_cases_test"
+NUM_NETIFS=2
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+tcflags="skip_hw"
+
+h1_create()
+{
+        simple_if_init $h1 192.0.2.1/24 198.51.100.1/24
+}
+
+h1_destroy()
+{
+        simple_if_fini $h1 192.0.2.1/24 198.51.100.1/24
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.2/24 198.51.100.2/24
+        tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+        tc qdisc del dev $h2 clsact
+        simple_if_fini $h2 192.0.2.2/24 198.51.100.2/24
+}
+
+single_mask_test()
+{
+        # When only a single mask is required, the device uses the master
+        # mask and not the eRP table. Verify that under this mode the right
+        # filter is matched
+
+        RET=0
+
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 1
+        check_err $? "Single filter - did not match"
+
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 198.51.100.2 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 2
+        check_err $? "Two filters - did not match highest priority"
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 1
+        check_err $? "Two filters - did not match lowest priority"
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 2
+        check_err $? "Single filter - did not match after delete"
+
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+        log_test "single mask test ($tcflags)"
+}
+
+identical_filters_test()
+{
+        # When two filters that only differ in their priority are used,
+        # one needs to be inserted into the C-TCAM. This test verifies
+        # that filters are correctly spilled to C-TCAM and that the right
+        # filter is matched
+
+        RET=0
+
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 1
+        check_err $? "Did not match A-TCAM filter"
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 1
+        check_err $? "Did not match C-TCAM filter after A-TCAM delete"
+
+        tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 2
+        check_err $? "Did not match C-TCAM filter after A-TCAM add"
+
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 103 1
+        check_err $? "Did not match A-TCAM filter after C-TCAM delete"
+
+        tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+
+        log_test "identical filters test ($tcflags)"
+}
+
+two_masks_test()
+{
+        # When more than one mask is required, the eRP table is used. This
+        # test verifies that the eRP table is correctly allocated and used
+
+        RET=0
+
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+                $tcflags dst_ip 192.0.0.0/16 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 1
+        check_err $? "Two filters - did not match highest priority"
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 103 1
+        check_err $? "Single filter - did not match"
+
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 192.0.2.0/24 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 1
+        check_err $? "Two filters - did not match highest priority after add"
+
+        tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+        log_test "two masks test ($tcflags)"
+}
+
+multiple_masks_test()
+{
+        # The number of masks in a region is limited. Once the maximum
+        # number of masks has been reached filters that require new
+        # masks are spilled to the C-TCAM. This test verifies that
+        # spillage is performed correctly and that the right filter is
+        # matched
+
+        local index
+
+        RET=0
+
+        NUM_MASKS=32
+        BASE_INDEX=100
+
+        for i in $(eval echo {1..$NUM_MASKS}); do
+                index=$((BASE_INDEX - i))
+
+                tc filter add dev $h2 ingress protocol ip pref $index \
+                        handle $index \
+                        flower $tcflags dst_ip 192.0.2.2/${i} src_ip 192.0.2.1 \
+                        action drop
+
+                $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 \
+                        -B 192.0.2.2 -t ip -q
+
+                tc_check_packets "dev $h2 ingress" $index 1
+                check_err $? "$i filters - did not match highest priority (add)"
+        done
+
+        for i in $(eval echo {$NUM_MASKS..1}); do
+                index=$((BASE_INDEX - i))
+
+                $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 \
+                        -B 192.0.2.2 -t ip -q
+
+                tc_check_packets "dev $h2 ingress" $index 2
+                check_err $? "$i filters - did not match highest priority (del)"
+
+                tc filter del dev $h2 ingress protocol ip pref $index \
+                        handle $index flower
+        done
+
+        log_test "multiple masks test ($tcflags)"
+}
+
+ctcam_two_atcam_masks_test()
+{
+        RET=0
+
+        # First case: C-TCAM is disabled when there are two A-TCAM masks.
+        # We push a filter into the C-TCAM by using two identical filters
+        # as in identical_filters_test()
+
+        # Filter goes into A-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        # Filter goes into C-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        # Filter goes into A-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+                $tcflags dst_ip 192.0.2.0/24 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 1
+        check_err $? "Did not match A-TCAM filter"
+
+        # Delete both A-TCAM and C-TCAM filters and make sure the remaining
+        # A-TCAM filter still works
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 103 1
+        check_err $? "Did not match A-TCAM filter"
+
+        tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+
+        log_test "ctcam with two atcam masks test ($tcflags)"
+}
+
+ctcam_one_atcam_mask_test()
+{
+        RET=0
+
+        # Second case: C-TCAM is disabled when there is one A-TCAM mask.
+        # The test is similar to identical_filters_test()
+
+        # Filter goes into A-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        # Filter goes into C-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 101 1
+        check_err $? "Did not match C-TCAM filter"
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+        $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+                -t ip -q
+
+        tc_check_packets "dev $h2 ingress" 102 1
+        check_err $? "Did not match A-TCAM filter"
+
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+        log_test "ctcam with one atcam mask test ($tcflags)"
+}
+
+ctcam_no_atcam_masks_test()
+{
+        RET=0
+
+        # Third case: C-TCAM is disabled when there are no A-TCAM masks
+        # This test exercises the code path that transitions the eRP table
+        # to its initial state after deleting the last C-TCAM mask
+
+        # Filter goes into A-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+        # Filter goes into C-TCAM
+        tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+                $tcflags dst_ip 192.0.2.2 action drop
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+        tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+        log_test "ctcam with no atcam masks test ($tcflags)"
+}
+
+ctcam_edge_cases_test()
+{
+        # When the C-TCAM is disabled after deleting the last C-TCAM
+        # mask, we want to make sure the eRP state machine is put in
+        # the correct state
+
+        ctcam_two_atcam_masks_test
+        ctcam_one_atcam_mask_test
+        ctcam_no_atcam_masks_test
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        h2=${NETIFS[p2]}
+        h1mac=$(mac_get $h1)
+        h2mac=$(mac_get $h2)
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+if ! tc_offload_check; then
+        check_err 1 "Could not test offloaded functionality"
+        log_test "mlxsw-specific tests for tc flower"
+        exit
+else
+        tcflags="skip_sw"
+        tests_run
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
new file mode 100644
index 000000000000..73035e25085d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
@@ -0,0 +1,119 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source "../../../../net/forwarding/devlink_lib.sh"
+
+if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then
+        echo "SKIP: test is tailored for Mellanox Spectrum"
+        exit 1
+fi
+
+# Needed for returning to default
+declare -A KVD_DEFAULTS
+
+KVD_CHILDREN="linear hash_single hash_double"
+KVDL_CHILDREN="singles chunks large_chunks"
+
+devlink_sp_resource_minimize()
+{
+        local size
+        local i
+
+        for i in $KVD_CHILDREN; do
+                size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+                devlink_resource_size_set "$size" kvd "$i"
+        done
+
+        for i in $KVDL_CHILDREN; do
+                size=$(devlink_resource_get kvd linear "$i" | \
+                       jq '.["size_min"]')
+                devlink_resource_size_set "$size" kvd linear "$i"
+        done
+}
+
+devlink_sp_size_kvd_to_default()
+{
+        local need_reload=0
+        local i
+
+        for i in $KVD_CHILDREN; do
+                local size=$(echo "${KVD_DEFAULTS[kvd_$i]}" | jq '.["size"]')
+                current_size=$(devlink_resource_size_get kvd "$i")
+
+                if [ "$size" -ne "$current_size" ]; then
+                        devlink_resource_size_set "$size" kvd "$i"
+                        need_reload=1
+                fi
+        done
+
+        for i in $KVDL_CHILDREN; do
+                local size=$(echo "${KVD_DEFAULTS[kvd_linear_$i]}" | \
+                             jq '.["size"]')
+                current_size=$(devlink_resource_size_get kvd linear "$i")
+
+                if [ "$size" -ne "$current_size" ]; then
+                        devlink_resource_size_set "$size" kvd linear "$i"
+                        need_reload=1
+                fi
+        done
+
+        if [ "$need_reload" -ne "0" ]; then
+                devlink_reload
+        fi
+}
+
+devlink_sp_read_kvd_defaults()
+{
+        local key
+        local i
+
+        KVD_DEFAULTS[kvd]=$(devlink_resource_get "kvd")
+        for i in $KVD_CHILDREN; do
+                key=kvd_$i
+                KVD_DEFAULTS[$key]=$(devlink_resource_get kvd "$i")
+        done
+
+        for i in $KVDL_CHILDREN; do
+                key=kvd_linear_$i
+                KVD_DEFAULTS[$key]=$(devlink_resource_get kvd linear "$i")
+        done
+}
+
+KVD_PROFILES="default scale ipv4_max"
+
+devlink_sp_resource_kvd_profile_set()
+{
+        local profile=$1
+
+        case "$profile" in
+        scale)
+                devlink_resource_size_set 64000 kvd linear
+                devlink_resource_size_set 15616 kvd linear singles
+                devlink_resource_size_set 32000 kvd linear chunks
+                devlink_resource_size_set 16384 kvd linear large_chunks
+                devlink_resource_size_set 128000 kvd hash_single
+                devlink_resource_size_set 48000 kvd hash_double
+                devlink_reload
+                ;;
+        ipv4_max)
+                devlink_resource_size_set 64000 kvd linear
+                devlink_resource_size_set 15616 kvd linear singles
+                devlink_resource_size_set 32000 kvd linear chunks
+                devlink_resource_size_set 16384 kvd linear large_chunks
+                devlink_resource_size_set 144000 kvd hash_single
+                devlink_resource_size_set 32768 kvd hash_double
+                devlink_reload
+                ;;
+        default)
+                devlink_resource_size_set 98304 kvd linear
+                devlink_resource_size_set 16384 kvd linear singles
+                devlink_resource_size_set 49152 kvd linear chunks
+                devlink_resource_size_set 32768 kvd linear large_chunks
+                devlink_resource_size_set 87040 kvd hash_single
+                devlink_resource_size_set 60416 kvd hash_double
+                devlink_reload
+                ;;
+        *)
+                check_err 1 "Unknown profile $profile"
+        esac
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh
new file mode 100755
index 000000000000..b1fe960e398a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=1
+source devlink_lib_spectrum.sh
+
+setup_prepare()
+{
+        devlink_sp_read_kvd_defaults
+}
+
+cleanup()
+{
+        pre_cleanup
+        devlink_sp_size_kvd_to_default
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+profiles_test()
+{
+        local i
+
+        log_info "Running profile tests"
+
+        for i in $KVD_PROFILES; do
+                RET=0
+                devlink_sp_resource_kvd_profile_set $i
+                log_test "'$i' profile"
+        done
+
+        # Default is explicitly tested at end to ensure it's actually applied
+        RET=0
+        devlink_sp_resource_kvd_profile_set "default"
+        log_test "'default' profile"
+}
+
+resources_min_test()
+{
+        local size
+        local i
+        local j
+
+        log_info "Running KVD-minimum tests"
+
+        for i in $KVD_CHILDREN; do
+                RET=0
+                size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+                devlink_resource_size_set "$size" kvd "$i"
+
+                # In case of linear, need to minimize sub-resources as well
+                if [[ "$i" == "linear" ]]; then
+                        for j in $KVDL_CHILDREN; do
+                                devlink_resource_size_set 0 kvd linear "$j"
+                        done
+                fi
+
+                devlink_reload
+                devlink_sp_size_kvd_to_default
+                log_test "'$i' minimize [$size]"
+        done
+}
+
+resources_max_test()
+{
+        local min_size
+        local size
+        local i
+        local j
+
+        log_info "Running KVD-maximum tests"
+        for i in $KVD_CHILDREN; do
+                RET=0
+                devlink_sp_resource_minimize
+
+                # Calculate the maximum possible size for the given partition
+                size=$(devlink_resource_size_get kvd)
+                for j in $KVD_CHILDREN; do
+                        if [ "$i" != "$j" ]; then
+                                min_size=$(devlink_resource_get kvd "$j" | \
+                                           jq '.["size_min"]')
+                                size=$((size - min_size))
+                        fi
+                done
+
+                # Test almost maximum size
+                devlink_resource_size_set "$((size - 128))" kvd "$i"
+                devlink_reload
+                log_test "'$i' almost maximize [$((size - 128))]"
+
+                # Test above maximum size
+                devlink resource set "$DEVLINK_DEV" \
+                        path "kvd/$i" size $((size + 128)) &> /dev/null
+                check_fail $? "Set kvd/$i to size $((size + 128)) should fail"
+                log_test "'$i' Overflow rejection [$((size + 128))]"
+
+                # Test maximum size
+                if [ "$i" == "hash_single" ] || [ "$i" == "hash_double" ]; then
+                        echo "SKIP: Observed problem with exact max $i"
+                        continue
+                fi
+
+                devlink_resource_size_set "$size" kvd "$i"
+                devlink_reload
+                log_test "'$i' maximize [$size]"
+
+                devlink_sp_size_kvd_to_default
+        done
+}
+
+profiles_test
+resources_min_test
+resources_max_test
+
+exit "$RET"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh
new file mode 100644
index 000000000000..8d2186c7c62b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../mirror_gre_scale.sh
+
+mirror_gre_get_target()
+{
+        local should_fail=$1; shift
+
+        if ((! should_fail)); then
+                echo 3
+        else
+                echo 4
+        fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
new file mode 100755
index 000000000000..a0a80e1a69e8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=6
+source ../../../../net/forwarding/lib.sh
+source ../../../../net/forwarding/tc_common.sh
+source devlink_lib_spectrum.sh
+
+current_test=""
+
+cleanup()
+{
+        pre_cleanup
+        if [ ! -z $current_test ]; then
+                ${current_test}_cleanup
+        fi
+        devlink_sp_size_kvd_to_default
+}
+
+devlink_sp_read_kvd_defaults
+trap cleanup EXIT
+
+ALL_TESTS="router tc_flower mirror_gre"
+for current_test in ${TESTS:-$ALL_TESTS}; do
+        source ${current_test}_scale.sh
+
+        num_netifs_var=${current_test^^}_NUM_NETIFS
+        num_netifs=${!num_netifs_var:-$NUM_NETIFS}
+
+        for profile in $KVD_PROFILES; do
+                RET=0
+                devlink_sp_resource_kvd_profile_set $profile
+                if [[ $RET -gt 0 ]]; then
+                        log_test "'$current_test' [$profile] setting"
+                        continue
+                fi
+
+                for should_fail in 0 1; do
+                        RET=0
+                        target=$(${current_test}_get_target "$should_fail")
+                        ${current_test}_setup_prepare
+                        setup_wait $num_netifs
+                        ${current_test}_test "$target" "$should_fail"
+                        ${current_test}_cleanup
+                        if [[ "$should_fail" -eq 0 ]]; then
+                                log_test "'$current_test' [$profile] $target"
+                        else
+                                log_test "'$current_test' [$profile] overflow $target"
+                        fi
+                done
+        done
+done
+current_test=""
+
+exit "$RET"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh
new file mode 100644
index 000000000000..21c4697d5bab
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../router_scale.sh
+
+router_get_target()
+{
+        local should_fail=$1
+        local target
+
+        target=$(devlink_resource_size_get kvd hash_single)
+
+        if [[ $should_fail -eq 0 ]]; then
+                target=$((target * 85 / 100))
+        else
+                target=$((target + 1))
+        fi
+
+        echo $target
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh
new file mode 100644
index 000000000000..f9bfd8937765
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../tc_flower_scale.sh
+
+tc_flower_get_target()
+{
+        local should_fail=$1; shift
+
+        # 6144 (6x1024) is the theoretical maximum.
+        # One bank of 512 rules is taken by the 18-byte MC router rule.
+        # One rule is the ACL catch-all.
+        # 6144 - 512 - 1 = 5631
+        local target=5631
+
+        if ((! should_fail)); then
+                echo $target
+        else
+                echo $((target + 1))
+        fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
new file mode 100644
index 000000000000..a6d733d2a4b4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
@@ -0,0 +1,134 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for resource limit of offloaded flower rules. The test adds a given
+# number of flower matches for different IPv6 addresses, then generates traffic,
+# and ensures each was hit exactly once. This file contains functions to set up
+# a testing topology and run the test, and is meant to be sourced from a test
+# script that calls the testing routine with a given number of rules.
+
+TC_FLOWER_NUM_NETIFS=2
+
+tc_flower_h1_create()
+{
+        simple_if_init $h1
+        tc qdisc add dev $h1 clsact
+}
+
+tc_flower_h1_destroy()
+{
+        tc qdisc del dev $h1 clsact
+        simple_if_fini $h1
+}
+
+tc_flower_h2_create()
+{
+        simple_if_init $h2
+        tc qdisc add dev $h2 clsact
+}
+
+tc_flower_h2_destroy()
+{
+        tc qdisc del dev $h2 clsact
+        simple_if_fini $h2
+}
+
+tc_flower_setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        h2=${NETIFS[p2]}
+
+        vrf_prepare
+
+        tc_flower_h1_create
+        tc_flower_h2_create
+}
+
+tc_flower_cleanup()
+{
+        pre_cleanup
+
+        tc_flower_h2_destroy
+        tc_flower_h1_destroy
+
+        vrf_cleanup
+
+        if [[ -v TC_FLOWER_BATCH_FILE ]]; then
+                rm -f $TC_FLOWER_BATCH_FILE
+        fi
+}
+
+tc_flower_addr()
+{
+        local num=$1; shift
+
+        printf "2001:db8:1::%x" $num
+}
+
+tc_flower_rules_create()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+
+        TC_FLOWER_BATCH_FILE="$(mktemp)"
+
+        for ((i = 0; i < count; ++i)); do
+                cat >> $TC_FLOWER_BATCH_FILE <<-EOF
+                        filter add dev $h2 ingress \
+                                prot ipv6 \
+                                pref 1000 \
+                                flower $tcflags dst_ip $(tc_flower_addr $i) \
+                                action drop
+                EOF
+        done
+
+        tc -b $TC_FLOWER_BATCH_FILE
+        check_err_fail $should_fail $? "Rule insertion"
+}
+
+__tc_flower_test()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+        local last=$((count - 1))
+
+        tc_flower_rules_create $count $should_fail
+
+        for ((i = 0; i < count; ++i)); do
+                $MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \
+                        -A 2001:db8:2::1 \
+                        -B $(tc_flower_addr $i)
+        done
+
+        MISMATCHES=$(
+                tc -j -s filter show dev $h2 ingress |
+                jq -r '[ .[] | select(.kind == "flower") | .options |
+                         values as $rule | .actions[].stats.packets |
+                         select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] |
+                       join(", ")'
+        )
+
+        test -z "$MISMATCHES"
+        check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES"
+}
+
+tc_flower_test()
+{
+        local count=$1; shift
+        local should_fail=$1; shift
+
+        # We use lower 16 bits of IPv6 address for match. Also there are only 16
+        # bits of rule priority space.
+        if ((count > 65536)); then
+                check_err 1 "Invalid count of $count. At most 65536 rules supported"
+                return
+        fi
+
+        if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+                check_err 1 "Could not test offloaded functionality"
+                return
+        fi
+
+        tcflags="skip_sw"
+        __tc_flower_test $count $should_fail
+}
diff --git a/tools/testing/selftests/gpio/gpio-mockup-chardev.c b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
index 667e916fa7cc..f8d468f54e98 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-chardev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
@@ -225,10 +225,10 @@ int gpio_pin_test(struct gpiochip_info *cinfo, int line, int flag, int value)
                 if (flag & GPIOHANDLE_REQUEST_ACTIVE_LOW)
                         debugfs_value = !debugfs_value;
 
-                if (!(debugfs_dir == OUT && value == debugfs_value))
+                if (!(debugfs_dir == OUT && value == debugfs_value)) {
                         errno = -EINVAL;
-                ret = -errno;
-
+                        ret = -errno;
+                }
         }
         gpiotools_release_linehandle(fd);
 
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 1a0ac3a29ec5..78b24cf76f40 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -13,3 +13,4 @@ udpgso
 udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
+tls
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 663e11e85727..9cca68e440a0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -13,7 +13,7 @@ TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index 4a0964c42860..b8a2af8fcfb7 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -46,6 +46,8 @@ Guidelines for Writing Tests
 
 o Where possible, reuse an existing topology for different tests instead
   of recreating the same topology.
+o Tests that use anything but the most trivial topologies should include
+  an ASCII art showing the topology.
 o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and
   RFC 5737, respectively.
 o Where possible, tests shall be written so that they can be reused by
diff --git a/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh
new file mode 100755
index 000000000000..a43b4645c4de
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6 flooding"
+NUM_NETIFS=6
+CHECK_TC="yes"
+source lib.sh
+
+h1_create()
+{
+        simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+        simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+        simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h3_create()
+{
+        simple_if_init $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+h3_destroy()
+{
+        simple_if_fini $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+switch_create()
+{
+        ip link add dev br0 type bridge
+
+        ip link set dev $swp1 master br0
+        ip link set dev $swp2 master br0
+        ip link set dev $swp3 master br0
+
+        ip link set dev $swp1 type bridge_slave isolated on
+        check_err $? "Can't set isolation on port $swp1"
+        ip link set dev $swp2 type bridge_slave isolated on
+        check_err $? "Can't set isolation on port $swp2"
+        ip link set dev $swp3 type bridge_slave isolated off
+        check_err $? "Can't disable isolation on port $swp3"
+
+        ip link set dev br0 up
+        ip link set dev $swp1 up
+        ip link set dev $swp2 up
+        ip link set dev $swp3 up
+}
+
+switch_destroy()
+{
+        ip link set dev $swp3 down
+        ip link set dev $swp2 down
+        ip link set dev $swp1 down
+
+        ip link del dev br0
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        swp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+        h3_create
+
+        switch_create
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        switch_destroy
+
+        h3_destroy
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+ping_ipv4()
+{
+        RET=0
+        ping_do $h1 192.0.2.2
+        check_fail $? "Ping worked when it should not have"
+
+        RET=0
+        ping_do $h3 192.0.2.2
+        check_err $? "Ping didn't work when it should have"
+
+        log_test "Isolated port ping"
+}
+
+ping_ipv6()
+{
+        RET=0
+        ping6_do $h1 2001:db8:1::2
+        check_fail $? "Ping6 worked when it should not have"
+
+        RET=0
+        ping6_do $h3 2001:db8:1::2
+        check_err $? "Ping6 didn't work when it should have"
+
+        log_test "Isolated port ping6"
+}
+
+flooding()
+{
+        local mac=de:ad:be:ef:13:37
+        local ip=192.0.2.100
+
+        RET=0
+        flood_test_do false $mac $ip $h1 $h2
+        check_err $? "Packet was flooded when it should not have been"
+
+        RET=0
+        flood_test_do true $mac $ip $h3 $h2
+        check_err $? "Packet was not flooded when it should have been"
+
+        log_test "Isolated port flooding"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
new file mode 100644
index 000000000000..5ab1e5f43022
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+##############################################################################
+# Source library
+
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+        relative_path="."
+fi
+
+source "$relative_path/lib.sh"
+
+##############################################################################
+# Defines
+
+DEVLINK_DEV=$(devlink port show | grep "${NETIFS[p1]}" | \
+              grep -v "${NETIFS[p1]}[0-9]" | cut -d" " -f1 | \
+              rev | cut -d"/" -f2- | rev)
+if [ -z "$DEVLINK_DEV" ]; then
+        echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it"
+        exit 1
+fi
+if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then
+        echo "SKIP: devlink device's bus is not PCI"
+        exit 1
+fi
+
+DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \
+                 -n | cut -d" " -f3)
+
+##############################################################################
+# Sanity checks
+
+devlink -j resource show "$DEVLINK_DEV" &> /dev/null
+if [ $? -ne 0 ]; then
+        echo "SKIP: iproute2 too old, missing devlink resource support"
+        exit 1
+fi
+
+##############################################################################
+# Devlink helpers
+
+devlink_resource_names_to_path()
+{
+        local resource
+        local path=""
+
+        for resource in "${@}"; do
+                if [ "$path" == "" ]; then
+                        path="$resource"
+                else
+                        path="${path}/$resource"
+                fi
+        done
+
+        echo "$path"
+}
+
+devlink_resource_get()
+{
+        local name=$1
+        local resource_name=.[][\"$DEVLINK_DEV\"]
+
+        resource_name="$resource_name | .[] | select (.name == \"$name\")"
+
+        shift
+        for resource in "${@}"; do
+                resource_name="${resource_name} | .[\"resources\"][] | \
+                               select (.name == \"$resource\")"
+        done
+
+        devlink -j resource show "$DEVLINK_DEV" | jq "$resource_name"
+}
+
+devlink_resource_size_get()
+{
+        local size=$(devlink_resource_get "$@" | jq '.["size_new"]')
+
+        if [ "$size" == "null" ]; then
+                devlink_resource_get "$@" | jq '.["size"]'
+        else
+                echo "$size"
+        fi
+}
+
+devlink_resource_size_set()
+{
+        local new_size=$1
+        local path
+
+        shift
+        path=$(devlink_resource_names_to_path "$@")
+        devlink resource set "$DEVLINK_DEV" path "$path" size "$new_size"
+        check_err $? "Failed setting path $path to size $size"
+}
+
+devlink_reload()
+{
+        local still_pending
+
+        devlink dev reload "$DEVLINK_DEV" &> /dev/null
+        check_err $? "Failed reload"
+
+        still_pending=$(devlink resource show "$DEVLINK_DEV" | \
+                        grep -c "size_new")
+        check_err $still_pending "Failed reload - There are still unset sizes"
+}
diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh
new file mode 100755
index 000000000000..cca2baa03fb8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh
@@ -0,0 +1,253 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |      192.0.2.1/28 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|------------------------+
+# | SW1               |                        |
+# |              $ol1 +                        |
+# |      192.0.2.2/28                          |
+# |                                            |
+# |  + g1a (gre)          + g1b (gre)          |
+# |    loc=192.0.2.65       loc=192.0.2.81     |
+# |    rem=192.0.2.66 --.   rem=192.0.2.82 --. |
+# |    tos=inherit      |   tos=inherit      | |
+# |  .------------------'                    | |
+# |  |                    .------------------' |
+# |  v                    v                    |
+# |  + $ul1.111 (vlan)    + $ul1.222 (vlan)    |
+# |  | 192.0.2.129/28     | 192.0.2.145/28     |
+# |   \                  /                     |
+# |    \________________/                      |
+# |            |                               |
+# |            + $ul1                          |
+# +------------|-------------------------------+
+#              |
+# +------------|-------------------------------+
+# | SW2        + $ul2                          |
+# |     _______|________                       |
+# |    /                \                      |
+# |   /                  \                     |
+# |  + $ul2.111 (vlan)    + $ul2.222 (vlan)    |
+# |  ^ 192.0.2.130/28     ^ 192.0.2.146/28     |
+# |  |                    |                    |
+# |  |                    '------------------. |
+# |  '------------------.                    | |
+# |  + g2a (gre)        | + g2b (gre)        | |
+# |    loc=192.0.2.66   |   loc=192.0.2.82   | |
+# |    rem=192.0.2.65 --'   rem=192.0.2.81 --' |
+# |    tos=inherit          tos=inherit        |
+# |                                            |
+# |              $ol2 +                        |
+# |     192.0.2.17/28 |                        |
+# +-------------------|------------------------+
+#                     |
+# +-------------------|-----+
+# | H2                |     |
+# |               $h2 +     |
+# |     192.0.2.18/28       |
+# +-------------------------+
+
+ALL_TESTS="
+        ping_ipv4
+        multipath_ipv4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+        simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+        ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+}
+
+h1_destroy()
+{
+        ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+        simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+        simple_if_init $ol1 192.0.2.2/28
+        __simple_if_init $ul1 v$ol1
+        vlan_create $ul1 111 v$ol1 192.0.2.129/28
+        vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+        tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+        __simple_if_init g1a v$ol1 192.0.2.65/32
+        ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+        tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+        __simple_if_init g1b v$ol1 192.0.2.81/32
+        ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+        ip route add vrf v$ol1 192.0.2.16/28 \
+           nexthop dev g1a \
+           nexthop dev g1b
+
+        tc qdisc add dev $ul1 clsact
+        tc filter add dev $ul1 egress pref 111 prot ipv4 \
+           flower dst_ip 192.0.2.66 action pass
+        tc filter add dev $ul1 egress pref 222 prot ipv4 \
+           flower dst_ip 192.0.2.82 action pass
+}
+
+sw1_destroy()
+{
+        tc qdisc del dev $ul1 clsact
+
+        ip route del vrf v$ol1 192.0.2.16/28
+
+        ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+        __simple_if_fini g1b 192.0.2.81/32
+        tunnel_destroy g1b
+
+        ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+        __simple_if_fini g1a 192.0.2.65/32
+        tunnel_destroy g1a
+
+        vlan_destroy $ul1 222
+        vlan_destroy $ul1 111
+        __simple_if_fini $ul1
+        simple_if_fini $ol1 192.0.2.2/28
+}
+
+sw2_create()
+{
+        simple_if_init $ol2 192.0.2.17/28
+        __simple_if_init $ul2 v$ol2
+        vlan_create $ul2 111 v$ol2 192.0.2.130/28
+        vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+        tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+        __simple_if_init g2a v$ol2 192.0.2.66/32
+        ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+        tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+        __simple_if_init g2b v$ol2 192.0.2.82/32
+        ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+        ip route add vrf v$ol2 192.0.2.0/28 \
+           nexthop dev g2a \
+           nexthop dev g2b
+}
+
+sw2_destroy()
+{
+        ip route del vrf v$ol2 192.0.2.0/28
+
+        ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+        __simple_if_fini g2b 192.0.2.82/32
+        tunnel_destroy g2b
+
+        ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+        __simple_if_fini g2a 192.0.2.66/32
+        tunnel_destroy g2a
+
+        vlan_destroy $ul2 222
+        vlan_destroy $ul2 111
+        __simple_if_fini $ul2
+        simple_if_fini $ol2 192.0.2.17/28
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.18/28
+        ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+}
+
+h2_destroy()
+{
+        ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+        simple_if_fini $h2 192.0.2.18/28
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        ol1=${NETIFS[p2]}
+
+        ul1=${NETIFS[p3]}
+        ul2=${NETIFS[p4]}
+
+        ol2=${NETIFS[p5]}
+        h2=${NETIFS[p6]}
+
+        vrf_prepare
+        h1_create
+        sw1_create
+        sw2_create
+        h2_create
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        h2_destroy
+        sw2_destroy
+        sw1_destroy
+        h1_destroy
+        vrf_cleanup
+}
+
+multipath4_test()
+{
+        local what=$1; shift
+        local weight1=$1; shift
+        local weight2=$1; shift
+
+        sysctl_set net.ipv4.fib_multipath_hash_policy 1
+        ip route replace vrf v$ol1 192.0.2.16/28 \
+           nexthop dev g1a weight $weight1 \
+           nexthop dev g1b weight $weight2
+
+        local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+        local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+        ip vrf exec v$h1 \
+           $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+               -d 1msec -t udp "sp=1024,dp=0-32768"
+
+        local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+        local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+        local d111=$((t1_111 - t0_111))
+        local d222=$((t1_222 - t0_222))
+        multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+        ip route replace vrf v$ol1 192.0.2.16/28 \
+           nexthop dev g1a \
+           nexthop dev g1b
+        sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+        ping_test $h1 192.0.2.18
+}
+
+multipath_ipv4()
+{
+        log_info "Running IPv4 multipath tests"
+        multipath4_test "ECMP" 1 1
+        multipath4_test "Weighted MP 2:1" 2 1
+        multipath4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 7b18a53aa556..ca53b539aa2d 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -8,14 +8,21 @@
 PING=${PING:=ping}
 PING6=${PING6:=ping6}
 MZ=${MZ:=mausezahn}
+ARPING=${ARPING:=arping}
+TEAMD=${TEAMD:=teamd}
 WAIT_TIME=${WAIT_TIME:=5}
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no}
 NETIF_TYPE=${NETIF_TYPE:=veth}
 NETIF_CREATE=${NETIF_CREATE:=yes}
 
-if [[ -f forwarding.config ]]; then
-        source forwarding.config
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+        relative_path="."
+fi
+
+if [[ -f $relative_path/forwarding.config ]]; then
+        source "$relative_path/forwarding.config"
 fi
 
 ##############################################################################
@@ -28,7 +35,10 @@ check_tc_version()
                 echo "SKIP: iproute2 too old; tc is missing JSON support"
                 exit 1
         fi
+}
 
+check_tc_shblock_support()
+{
         tc filter help 2>&1 | grep block &> /dev/null
         if [[ $? -ne 0 ]]; then
                 echo "SKIP: iproute2 too old; tc is missing shared block support"
@@ -36,6 +46,15 @@ check_tc_version()
         fi
 }
 
+check_tc_chain_support()
+{
+        tc help 2>&1|grep chain &> /dev/null
+        if [[ $? -ne 0 ]]; then
+                echo "SKIP: iproute2 too old; tc is missing chain support"
+                exit 1
+        fi
+}
+
 if [[ "$(id -u)" -ne 0 ]]; then
         echo "SKIP: need root privileges"
         exit 0
@@ -45,15 +64,18 @@ if [[ "$CHECK_TC" = "yes" ]]; then
         check_tc_version
 fi
 
-if [[ ! -x "$(command -v jq)" ]]; then
-        echo "SKIP: jq not installed"
-        exit 1
-fi
+require_command()
+{
+        local cmd=$1; shift
 
-if [[ ! -x "$(command -v $MZ)" ]]; then
-        echo "SKIP: $MZ not installed"
-        exit 1
-fi
+        if [[ ! -x "$(command -v "$cmd")" ]]; then
+                echo "SKIP: $cmd not installed"
+                exit 1
+        fi
+}
+
+require_command jq
+require_command $MZ
 
 if [[ ! -v NUM_NETIFS ]]; then
         echo "SKIP: importer does not define \"NUM_NETIFS\""
@@ -151,6 +173,19 @@ check_fail()
         fi
 }
 
+check_err_fail()
+{
+        local should_fail=$1; shift
+        local err=$1; shift
+        local what=$1; shift
+
+        if ((should_fail)); then
+                check_fail $err "$what succeeded, but should have failed"
+        else
+                check_err $err "$what failed"
+        fi
+}
+
 log_test()
 {
         local test_name=$1
@@ -185,24 +220,54 @@ log_info()
         echo "INFO: $msg"
 }
 
+setup_wait_dev()
+{
+        local dev=$1; shift
+
+        while true; do
+                ip link show dev $dev up \
+                        | grep 'state UP' &> /dev/null
+                if [[ $? -ne 0 ]]; then
+                        sleep 1
+                else
+                        break
+                fi
+        done
+}
+
 setup_wait()
 {
-        for i in $(eval echo {1..$NUM_NETIFS}); do
-                while true; do
-                        ip link show dev ${NETIFS[p$i]} up \
-                                | grep 'state UP' &> /dev/null
-                        if [[ $? -ne 0 ]]; then
-                                sleep 1
-                        else
-                                break
-                        fi
-                done
+        local num_netifs=${1:-$NUM_NETIFS}
+
+        for ((i = 1; i <= num_netifs; ++i)); do
+                setup_wait_dev ${NETIFS[p$i]}
         done
 
         # Make sure links are ready.
         sleep $WAIT_TIME
 }
 
+lldpad_app_wait_set()
+{
+        local dev=$1; shift
+
+        while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+                echo "$dev: waiting for lldpad to push pending APP updates"
+                sleep 5
+        done
+}
+
+lldpad_app_wait_del()
+{
+        # Give lldpad a chance to push down the changes. If the device is downed
+        # too soon, the updates will be left pending. However, they will have
+        # been struck off the lldpad's DB already, so we won't be able to tell
+        # they are pending. Then on next test iteration this would cause
+        # weirdness as newly-added APP rules conflict with the old ones,
+        # sometimes getting stuck in an "unknown" state.
+        sleep 5
+}
+
 pre_cleanup()
 {
         if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then
@@ -287,6 +352,29 @@ __addr_add_del()
         done
 }
 
+__simple_if_init()
+{
+        local if_name=$1; shift
+        local vrf_name=$1; shift
+        local addrs=("${@}")
+
+        ip link set dev $if_name master $vrf_name
+        ip link set dev $if_name up
+
+        __addr_add_del $if_name add "${addrs[@]}"
+}
+
+__simple_if_fini()
+{
+        local if_name=$1; shift
+        local addrs=("${@}")
+
+        __addr_add_del $if_name del "${addrs[@]}"
+
+        ip link set dev $if_name down
+        ip link set dev $if_name nomaster
+}
+
 simple_if_init()
 {
         local if_name=$1
@@ -298,11 +386,8 @@ simple_if_init()
         array=("${@}")
 
         vrf_create $vrf_name
-        ip link set dev $if_name master $vrf_name
         ip link set dev $vrf_name up
-        ip link set dev $if_name up
-
-        __addr_add_del $if_name add "${array[@]}"
+        __simple_if_init $if_name $vrf_name "${array[@]}"
 }
 
 simple_if_fini()
@@ -315,9 +400,7 @@ simple_if_fini()
         vrf_name=v$if_name
         array=("${@}")
 
-        __addr_add_del $if_name del "${array[@]}"
-
-        ip link set dev $if_name down
+        __simple_if_fini $if_name "${array[@]}"
         vrf_destroy $vrf_name
 }
 
@@ -365,6 +448,28 @@ vlan_destroy()
         ip link del dev $name
 }
 
+team_create()
+{
+        local if_name=$1; shift
+        local mode=$1; shift
+
+        require_command $TEAMD
+        $TEAMD -t $if_name -d -c '{"runner": {"name": "'$mode'"}}'
+        for slave in "$@"; do
+                ip link set dev $slave down
+                ip link set dev $slave master $if_name
+                ip link set dev $slave up
+        done
+        ip link set dev $if_name up
+}
+
+team_destroy()
+{
+        local if_name=$1; shift
+
+        $TEAMD -t $if_name -k
+}
+
 master_name_get()
 {
         local if_name=$1
@@ -383,9 +488,10 @@ tc_rule_stats_get()
 {
         local dev=$1; shift
         local pref=$1; shift
+        local dir=$1; shift
 
-        tc -j -s filter show dev $dev ingress pref $pref |
-        jq '.[1].options.actions[].stats.packets'
+        tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
+            | jq '.[1].options.actions[].stats.packets'
 }
 
 mac_get()
@@ -437,7 +543,9 @@ forwarding_restore()
 
 tc_offload_check()
 {
-        for i in $(eval echo {1..$NUM_NETIFS}); do
+        local num_netifs=${1:-$NUM_NETIFS}
+
+        for ((i = 1; i <= num_netifs; ++i)); do
                 ethtool -k ${NETIFS[p$i]} \
                         | grep "hw-tc-offload: on" &> /dev/null
                 if [[ $? -ne 0 ]]; then
@@ -453,9 +561,15 @@ trap_install()
         local dev=$1; shift
         local direction=$1; shift
 
-        # For slow-path testing, we need to install a trap to get to
-        # slow path the packets that would otherwise be switched in HW.
-        tc filter add dev $dev $direction pref 1 flower skip_sw action trap
+        # Some devices may not support or need in-hardware trapping of traffic
+        # (e.g. the veth pairs that this library creates for non-existent
+        # loopbacks). Use continue instead, so that there is a filter in there
+        # (some tests check counters), and so that other filters are still
+        # processed.
+        tc filter add dev $dev $direction pref 1 \
+                flower skip_sw action trap 2>/dev/null \
+            || tc filter add dev $dev $direction pref 1 \
+                       flower action continue
 }
 
 trap_uninstall()
@@ -463,11 +577,13 @@ trap_uninstall()
         local dev=$1; shift
         local direction=$1; shift
 
-        tc filter del dev $dev $direction pref 1 flower skip_sw
+        tc filter del dev $dev $direction pref 1 flower
 }
 
 slow_path_trap_install()
 {
+        # For slow-path testing, we need to install a trap to get to
+        # slow path the packets that would otherwise be switched in HW.
         if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
                 trap_install "$@"
         fi
@@ -537,6 +653,48 @@ vlan_capture_uninstall()
         __vlan_capture_add_del del 100 "$@"
 }
 
+__dscp_capture_add_del()
+{
+        local add_del=$1; shift
+        local dev=$1; shift
+        local base=$1; shift
+        local dscp;
+
+        for prio in {0..7}; do
+                dscp=$((base + prio))
+                __icmp_capture_add_del $add_del $((dscp + 100)) "" $dev \
+                                       "skip_hw ip_tos $((dscp << 2))"
+        done
+}
+
+dscp_capture_install()
+{
+        local dev=$1; shift
+        local base=$1; shift
+
+        __dscp_capture_add_del add $dev $base
+}
+
+dscp_capture_uninstall()
+{
+        local dev=$1; shift
+        local base=$1; shift
+
+        __dscp_capture_add_del del $dev $base
+}
+
+dscp_fetch_stats()
+{
+        local dev=$1; shift
+        local base=$1; shift
+
+        for prio in {0..7}; do
+                local dscp=$((base + prio))
+                local t=$(tc_rule_stats_get $dev $((dscp + 100)))
+                echo "[$dscp]=$t "
+        done
+}
+
 matchall_sink_create()
 {
         local dev=$1; shift
@@ -557,33 +715,86 @@ tests_run()
         done
 }
 
+multipath_eval()
+{
+        local desc="$1"
+        local weight_rp12=$2
+        local weight_rp13=$3
+        local packets_rp12=$4
+        local packets_rp13=$5
+        local weights_ratio packets_ratio diff
+
+        RET=0
+
+        if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+                weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
+                                | bc -l)
+        else
+                weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" \
+                                | bc -l)
+        fi
+
+        if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
+               check_err 1 "Packet difference is 0"
+               log_test "Multipath"
+               log_info "Expected ratio $weights_ratio"
+               return
+        fi
+
+        if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+                packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
+                                | bc -l)
+        else
+                packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" \
+                                | bc -l)
+        fi
+
+        diff=$(echo $weights_ratio - $packets_ratio | bc -l)
+        diff=${diff#-}
+
+        test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
+        check_err $? "Too large discrepancy between expected and measured ratios"
+        log_test "$desc"
+        log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
+}
+
 ##############################################################################
 # Tests
 
-ping_test()
+ping_do()
 {
         local if_name=$1
         local dip=$2
         local vrf_name
 
-        RET=0
-
         vrf_name=$(master_name_get $if_name)
         ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping_test()
+{
+        RET=0
+
+        ping_do $1 $2
         check_err $?
         log_test "ping"
 }
 
-ping6_test()
+ping6_do()
 {
         local if_name=$1
         local dip=$2
         local vrf_name
 
-        RET=0
-
         vrf_name=$(master_name_get $if_name)
         ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping6_test()
+{
+        RET=0
+
+        ping6_do $1 $2
         check_err $?
         log_test "ping6"
 }
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh
new file mode 100755
index 000000000000..c5095da7f6bf
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh
@@ -0,0 +1,132 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device without vlan filtering (802.1d).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+#  +---------------------+                             +---------------------+
+#  | H1                  |                             |                  H2 |
+#  |     + $h1           |                             |           $h2 +     |
+#  |     | 192.0.2.1/28  |                             |  192.0.2.2/28 |     |
+#  +-----|---------------+                             +---------------|-----+
+#        |                                                             |
+#  +-----|-------------------------------------------------------------|-----+
+#  | SW  o---> mirror                                                  |     |
+#  | +---|-------------------------------------------------------------|---+ |
+#  | |   + $swp1            + br1 (802.1q bridge)                $swp2 +   | |
+#  | +---------------------------------------------------------------------+ |
+#  |                                                                         |
+#  | +---------------------------------------------------------------------+ |
+#  | |                      + br2 (802.1d bridge)                          | |
+#  | |                        192.0.2.129/28                               | |
+#  | |   + $swp3              2001:db8:2::1/64                             | |
+#  | +---|-----------------------------------------------------------------+ |
+#  |     |                                          ^                    ^   |
+#  |     |                     + gt6 (ip6gretap)    | + gt4 (gretap)     |   |
+#  |     |                     : loc=2001:db8:2::1  | : loc=192.0.2.129  |   |
+#  |     |                     : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+   |
+#  |     |                     : ttl=100              : ttl=100              |
+#  |     |                     : tos=inherit          : tos=inherit          |
+#  +-----|---------------------:----------------------:----------------------+
+#        |                     :                      :
+#  +-----|---------------------:----------------------:----------------------+
+#  | H3  + $h3                 + h3-gt6(ip6gretap)    + h3-gt4 (gretap)      |
+#  |       192.0.2.130/28        loc=2001:db8:2::2      loc=192.0.2.130      |
+#  |       2001:db8:2::2/64      rem=2001:db8:2::1      rem=192.0.2.129      |
+#  |                             ttl=100                ttl=100              |
+#  |                             tos=inherit            tos=inherit          |
+#  +-------------------------------------------------------------------------+
+
+ALL_TESTS="
+        test_gretap
+        test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        swp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        vrf_prepare
+        mirror_gre_topo_create
+
+        ip link add name br2 type bridge vlan_filtering 0
+        ip link set dev br2 up
+
+        ip link set dev $swp3 master br2
+        ip route add 192.0.2.130/32 dev br2
+        ip -6 route add 2001:db8:2::2/128 dev br2
+
+        ip address add dev br2 192.0.2.129/28
+        ip address add dev br2 2001:db8:2::1/64
+
+        ip address add dev $h3 192.0.2.130/28
+        ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        ip address del dev $h3 2001:db8:2::2/64
+        ip address del dev $h3 192.0.2.130/28
+        ip link del dev br2
+
+        mirror_gre_topo_destroy
+        vrf_cleanup
+}
+
+test_gretap()
+{
+        full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+        full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+        full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+        full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_all()
+{
+        slow_path_trap_install $swp1 ingress
+        slow_path_trap_install $swp1 egress
+
+        tests_run
+
+        slow_path_trap_uninstall $swp1 egress
+        slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+        echo "WARN: Could not test offloaded functionality"
+else
+        tcflags="skip_sw"
+        test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
index 3bb4c2ba7b14..197e769c2ed1 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
@@ -74,12 +74,14 @@ test_vlan_match()
 
 test_gretap()
 {
-        test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+        test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+                        "mirror to gretap"
 }
 
 test_ip6gretap()
 {
-        test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+        test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+                        "mirror to ip6gretap"
 }
 
 test_gretap_stp()
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
new file mode 100755
index 000000000000..a3402cd8d5b6
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
@@ -0,0 +1,126 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device with vlan filtering (802.1q).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+#  +---------------------+                               +---------------------+
+#  | H1                  |                               |                  H2 |
+#  |     + $h1           |                               |           $h2 +     |
+#  |     | 192.0.2.1/28  |                               |  192.0.2.2/28 |     |
+#  +-----|---------------+                               +---------------|-----+
+#        |                                                               |
+#  +-----|---------------------------------------------------------------|-----+
+#  | SW  o---> mirror                                                    |     |
+#  | +---|---------------------------------------------------------------|---+ |
+#  | |   + $swp1                  + br1 (802.1q bridge)            $swp2 +   | |
+#  | |                              192.0.2.129/28                           | |
+#  | |   + $swp3                    2001:db8:2::1/64                         | |
+#  | |   | vid555                   vid555[pvid,untagged]                    | |
+#  | +---|-------------------------------------------------------------------+ |
+#  |     |                                          ^                      ^   |
+#  |     |                     + gt6 (ip6gretap)    |   + gt4 (gretap)     |   |
+#  |     |                     : loc=2001:db8:2::1  |   : loc=192.0.2.129  |   |
+#  |     |                     : rem=2001:db8:2::2 -+   : rem=192.0.2.130 -+   |
+#  |     |                     : ttl=100                : ttl=100              |
+#  |     |                     : tos=inherit            : tos=inherit          |
+#  +-----|---------------------:------------------------:----------------------+
+#        |                     :                        :
+#  +-----|---------------------:------------------------:----------------------+
+#  | H3  + $h3                 + h3-gt6(ip6gretap)      + h3-gt4 (gretap)      |
+#  |     |                       loc=2001:db8:2::2        loc=192.0.2.130      |
+#  |     + $h3.555               rem=2001:db8:2::1        rem=192.0.2.129      |
+#  |       192.0.2.130/28        ttl=100                  ttl=100              |
+#  |       2001:db8:2::2/64      tos=inherit              tos=inherit          |
+#  +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+        test_gretap
+        test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        swp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        vrf_prepare
+        mirror_gre_topo_create
+
+        ip link set dev $swp3 master br1
+        bridge vlan add dev br1 vid 555 pvid untagged self
+        ip address add dev br1 192.0.2.129/28
+        ip address add dev br1 2001:db8:2::1/64
+
+        ip -4 route add 192.0.2.130/32 dev br1
+        ip -6 route add 2001:db8:2::2/128 dev br1
+
+        vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+        bridge vlan add dev $swp3 vid 555
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        ip link set dev $swp3 nomaster
+        vlan_destroy $h3 555
+
+        mirror_gre_topo_destroy
+        vrf_cleanup
+}
+
+test_gretap()
+{
+        full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+        full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+        full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+        full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+tests()
+{
+        slow_path_trap_install $swp1 ingress
+        slow_path_trap_install $swp1 egress
+
+        tests_run
+
+        slow_path_trap_uninstall $swp1 egress
+        slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+tests
+
+if ! tc_offload_check; then
+        echo "WARN: Could not test offloaded functionality"
+else
+        tcflags="skip_sw"
+        tests
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
new file mode 100755
index 000000000000..61844caf671e
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
@@ -0,0 +1,283 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device with vlan filtering (802.1q), and the egress device is a team
+# device.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |     + $h1.333        |                             |        $h1.555 +     |
+# |     | 192.0.2.1/28   |                             |  192.0.2.18/28 |     |
+# +-----|----------------+                             +----------------|-----+
+#       |                               $h1                             |
+#       +--------------------------------+------------------------------+
+#                                        |
+# +--------------------------------------|------------------------------------+
+# | SW                                   o---> mirror                         |
+# |                                      |                                    |
+# |     +--------------------------------+------------------------------+     |
+# |     |                              $swp1                            |     |
+# |     + $swp1.333                                           $swp1.555 +     |
+# |       192.0.2.2/28                                    192.0.2.17/28       |
+# |                                                                           |
+# | +-----------------------------------------------------------------------+ |
+# | |                        BR1 (802.1q)                                   | |
+# | |     + lag (team)       192.0.2.129/28                                 | |
+# | |    / \                 2001:db8:2::1/64                               | |
+# | +---/---\---------------------------------------------------------------+ |
+# |    /     \                                                            ^   |
+# |   |       \                                        + gt4 (gretap)     |   |
+# |   |        \                                         loc=192.0.2.129  |   |
+# |   |         \                                        rem=192.0.2.130 -+   |
+# |   |          \                                       ttl=100              |
+# |   |           \                                      tos=inherit          |
+# |   |            \                                                          |
+# |   |             \_________________________________                        |
+# |   |                                               \                       |
+# |   + $swp3                                          + $swp4                |
+# +---|------------------------------------------------|----------------------+
+#     |                                                |
+# +---|----------------------+                     +---|----------------------+
+# |   + $h3               H3 |                     |   + $h4               H4 |
+# |     192.0.2.130/28       |                     |     192.0.2.130/28       |
+# |     2001:db8:2::2/64     |                     |     2001:db8:2::2/64     |
+# +--------------------------+                     +--------------------------+
+
+ALL_TESTS="
+        test_mirror_gretap_first
+        test_mirror_gretap_second
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+require_command $ARPING
+
+vlan_host_create()
+{
+        local if_name=$1; shift
+        local vid=$1; shift
+        local vrf_name=$1; shift
+        local ips=("${@}")
+
+        vrf_create $vrf_name
+        ip link set dev $vrf_name up
+        vlan_create $if_name $vid $vrf_name "${ips[@]}"
+}
+
+vlan_host_destroy()
+{
+        local if_name=$1; shift
+        local vid=$1; shift
+        local vrf_name=$1; shift
+
+        vlan_destroy $if_name $vid
+        ip link set dev $vrf_name down
+        vrf_destroy $vrf_name
+}
+
+h1_create()
+{
+        vlan_host_create $h1 333 vrf-h1 192.0.2.1/28
+        ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+        ip -4 route del 192.0.2.16/28 vrf vrf-h1
+        vlan_host_destroy $h1 333 vrf-h1
+}
+
+h2_create()
+{
+        vlan_host_create $h1 555 vrf-h2 192.0.2.18/28
+        ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17
+}
+
+h2_destroy()
+{
+        ip -4 route del 192.0.2.0/28 vrf vrf-h2
+        vlan_host_destroy $h1 555 vrf-h2
+}
+
+h3_create()
+{
+        simple_if_init $h3 192.0.2.130/28
+        tc qdisc add dev $h3 clsact
+}
+
+h3_destroy()
+{
+        tc qdisc del dev $h3 clsact
+        simple_if_fini $h3 192.0.2.130/28
+}
+
+h4_create()
+{
+        simple_if_init $h4 192.0.2.130/28
+        tc qdisc add dev $h4 clsact
+}
+
+h4_destroy()
+{
+        tc qdisc del dev $h4 clsact
+        simple_if_fini $h4 192.0.2.130/28
+}
+
+switch_create()
+{
+        ip link set dev $swp1 up
+        tc qdisc add dev $swp1 clsact
+        vlan_create $swp1 333 "" 192.0.2.2/28
+        vlan_create $swp1 555 "" 192.0.2.17/28
+
+        tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+                      ttl 100 tos inherit
+
+        ip link set dev $swp3 up
+        ip link set dev $swp4 up
+
+        ip link add name br1 type bridge vlan_filtering 1
+        ip link set dev br1 up
+        __addr_add_del br1 add 192.0.2.129/32
+        ip -4 route add 192.0.2.130/32 dev br1
+
+        team_create lag loadbalance $swp3 $swp4
+        ip link set dev lag master br1
+}
+
+switch_destroy()
+{
+        ip link set dev lag nomaster
+        team_destroy lag
+
+        ip -4 route del 192.0.2.130/32 dev br1
+        __addr_add_del br1 del 192.0.2.129/32
+        ip link set dev br1 down
+        ip link del dev br1
+
+        ip link set dev $swp4 down
+        ip link set dev $swp3 down
+
+        tunnel_destroy gt4
+
+        vlan_destroy $swp1 555
+        vlan_destroy $swp1 333
+        tc qdisc del dev $swp1 clsact
+        ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp3=${NETIFS[p3]}
+        h3=${NETIFS[p4]}
+
+        swp4=${NETIFS[p5]}
+        h4=${NETIFS[p6]}
+
+        vrf_prepare
+
+        ip link set dev $h1 up
+        h1_create
+        h2_create
+        h3_create
+        h4_create
+        switch_create
+
+        trap_install $h3 ingress
+        trap_install $h4 ingress
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        trap_uninstall $h4 ingress
+        trap_uninstall $h3 ingress
+
+        switch_destroy
+        h4_destroy
+        h3_destroy
+        h2_destroy
+        h1_destroy
+        ip link set dev $h1 down
+
+        vrf_cleanup
+}
+
+test_lag_slave()
+{
+        local host_dev=$1; shift
+        local up_dev=$1; shift
+        local down_dev=$1; shift
+        local what=$1; shift
+
+        RET=0
+
+        mirror_install $swp1 ingress gt4 \
+                       "proto 802.1q flower vlan_id 333 $tcflags"
+
+        # Test connectivity through $up_dev when $down_dev is set down.
+        ip link set dev $down_dev down
+        setup_wait_dev $up_dev
+        setup_wait_dev $host_dev
+        $ARPING -I br1 192.0.2.130 -qfc 1
+        sleep 2
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 10
+
+        # Test lack of connectivity when both slaves are down.
+        ip link set dev $up_dev down
+        sleep 2
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0
+
+        ip link set dev $up_dev up
+        ip link set dev $down_dev up
+        mirror_uninstall $swp1 ingress
+
+        log_test "$what ($tcflags)"
+}
+
+test_mirror_gretap_first()
+{
+        test_lag_slave $h3 $swp3 $swp4 "mirror to gretap: LAG first slave"
+}
+
+test_mirror_gretap_second()
+{
+        test_lag_slave $h4 $swp4 $swp3 "mirror to gretap: LAG second slave"
+}
+
+test_all()
+{
+        slow_path_trap_install $swp1 ingress
+        slow_path_trap_install $swp1 egress
+
+        tests_run
+
+        slow_path_trap_uninstall $swp1 egress
+        slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+        echo "WARN: Could not test offloaded functionality"
+else
+        tcflags="skip_sw"
+        test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
index aa29d46186a8..135902aa8b11 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
@@ -122,15 +122,8 @@ test_span_gre_egress_up()
         # After setting the device up, wait for neighbor to get resolved so that
         # we can expect mirroring to work.
         ip link set dev $swp3 up
-        while true; do
-                ip neigh sh dev $swp3 $remote_ip nud reachable |
-                    grep -q ^
-                if [[ $? -ne 0 ]]; then
-                        sleep 1
-                else
-                        break
-                fi
-        done
+        setup_wait_dev $swp3
+        ping -c 1 -I $swp3 $remote_ip &>/dev/null
 
         quick_test_span_gre_dir $tundev ingress
         mirror_uninstall $swp1 ingress
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh
new file mode 100755
index 000000000000..9edf4cb104a8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh
@@ -0,0 +1,285 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# team device.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1.333         |                             |        $h1.555 +     |
+# |    | 192.0.2.1/28    |                             |  192.0.2.18/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                $h1                             |
+#      +---------------------------------+------------------------------+
+#                                        |
+# +--------------------------------------|------------------------------------+
+# | SW                                   o---> mirror                         |
+# |                                      |                                    |
+# |   +----------------------------------+------------------------------+     |
+# |   |                                $swp1                            |     |
+# |   + $swp1.333                                             $swp1.555 +     |
+# |     192.0.2.2/28                                      192.0.2.17/28       |
+# |                                                                           |
+# |                                                                           |
+# |   + gt4 (gretap)      ,-> + lag1 (team)                                   |
+# |     loc=192.0.2.129   |   | 192.0.2.129/28                                |
+# |     rem=192.0.2.130 --'   |                                               |
+# |     ttl=100               |                                               |
+# |     tos=inherit           |                                               |
+# |      _____________________|______________________                         |
+# |     /                                            \                        |
+# |    /                                              \                       |
+# |   + $swp3                                          + $swp4                |
+# +---|------------------------------------------------|----------------------+
+#     |                                                |
+# +---|------------------------------------------------|----------------------+
+# |   + $h3                                            + $h4               H3 |
+# |    \                                              /                       |
+# |     \____________________________________________/                        |
+# |                           |                                               |
+# |                           + lag2 (team)                                   |
+# |                             192.0.2.130/28                                |
+# |                                                                           |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+        test_mirror_gretap_first
+        test_mirror_gretap_second
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+require_command $ARPING
+
+vlan_host_create()
+{
+        local if_name=$1; shift
+        local vid=$1; shift
+        local vrf_name=$1; shift
+        local ips=("${@}")
+
+        vrf_create $vrf_name
+        ip link set dev $vrf_name up
+        vlan_create $if_name $vid $vrf_name "${ips[@]}"
+}
+
+vlan_host_destroy()
+{
+        local if_name=$1; shift
+        local vid=$1; shift
+        local vrf_name=$1; shift
+
+        vlan_destroy $if_name $vid
+        ip link set dev $vrf_name down
+        vrf_destroy $vrf_name
+}
+
+h1_create()
+{
+        vlan_host_create $h1 333 vrf-h1 192.0.2.1/28
+        ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+        ip -4 route del 192.0.2.16/28 vrf vrf-h1
+        vlan_host_destroy $h1 333 vrf-h1
+}
+
+h2_create()
+{
+        vlan_host_create $h1 555 vrf-h2 192.0.2.18/28
+        ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17
+}
+
+h2_destroy()
+{
+        ip -4 route del 192.0.2.0/28 vrf vrf-h2
+        vlan_host_destroy $h1 555 vrf-h2
+}
+
+h3_create_team()
+{
+        team_create lag2 lacp $h3 $h4
+        __simple_if_init lag2 vrf-h3 192.0.2.130/32
+        ip -4 route add vrf vrf-h3 192.0.2.129/32 dev lag2
+}
+
+h3_destroy_team()
+{
+        ip -4 route del vrf vrf-h3 192.0.2.129/32 dev lag2
+        __simple_if_fini lag2 192.0.2.130/32
+        team_destroy lag2
+
+        ip link set dev $h3 down
+        ip link set dev $h4 down
+}
+
+h3_create()
+{
+        vrf_create vrf-h3
+        ip link set dev vrf-h3 up
+        tc qdisc add dev $h3 clsact
+        tc qdisc add dev $h4 clsact
+        h3_create_team
+}
+
+h3_destroy()
+{
+        h3_destroy_team
+        tc qdisc del dev $h4 clsact
+        tc qdisc del dev $h3 clsact
+        ip link set dev vrf-h3 down
+        vrf_destroy vrf-h3
+}
+
+switch_create()
+{
+        ip link set dev $swp1 up
+        tc qdisc add dev $swp1 clsact
+        vlan_create $swp1 333 "" 192.0.2.2/28
+        vlan_create $swp1 555 "" 192.0.2.17/28
+
+        tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+                      ttl 100 tos inherit
+
+        ip link set dev $swp3 up
+        ip link set dev $swp4 up
+        team_create lag1 lacp $swp3 $swp4
+        __addr_add_del lag1 add 192.0.2.129/32
+        ip -4 route add 192.0.2.130/32 dev lag1
+}
+
+switch_destroy()
+{
+        ip -4 route del 192.0.2.130/32 dev lag1
+        __addr_add_del lag1 del 192.0.2.129/32
+        team_destroy lag1
+
+        ip link set dev $swp4 down
+        ip link set dev $swp3 down
+
+        tunnel_destroy gt4
+
+        vlan_destroy $swp1 555
+        vlan_destroy $swp1 333
+        tc qdisc del dev $swp1 clsact
+        ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp3=${NETIFS[p3]}
+        h3=${NETIFS[p4]}
+
+        swp4=${NETIFS[p5]}
+        h4=${NETIFS[p6]}
+
+        vrf_prepare
+
+        ip link set dev $h1 up
+        h1_create
+        h2_create
+        h3_create
+        switch_create
+
+        trap_install $h3 ingress
+        trap_install $h4 ingress
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        trap_uninstall $h4 ingress
+        trap_uninstall $h3 ingress
+
+        switch_destroy
+        h3_destroy
+        h2_destroy
+        h1_destroy
+        ip link set dev $h1 down
+
+        vrf_cleanup
+}
+
+test_lag_slave()
+{
+        local up_dev=$1; shift
+        local down_dev=$1; shift
+        local what=$1; shift
+
+        RET=0
+
+        mirror_install $swp1 ingress gt4 \
+                       "proto 802.1q flower vlan_id 333 $tcflags"
+
+        # Move $down_dev away from the team. That will prompt change in
+        # txability of the connected device, without changing its upness. The
+        # driver should notice the txability change and move the traffic to the
+        # other slave.
+        ip link set dev $down_dev nomaster
+        sleep 2
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $up_dev 1 10
+
+        # Test lack of connectivity when neither slave is txable.
+        ip link set dev $up_dev nomaster
+        sleep 2
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0
+        mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0
+        mirror_uninstall $swp1 ingress
+
+        # Recreate H3's team device, because mlxsw, which this test is
+        # predominantly mean to test, requires a bottom-up construction and
+        # doesn't allow enslavement to a device that already has an upper.
+        h3_destroy_team
+        h3_create_team
+        # Wait for ${h,swp}{3,4}.
+        setup_wait
+
+        log_test "$what ($tcflags)"
+}
+
+test_mirror_gretap_first()
+{
+        test_lag_slave $h3 $h4 "mirror to gretap: LAG first slave"
+}
+
+test_mirror_gretap_second()
+{
+        test_lag_slave $h4 $h3 "mirror to gretap: LAG second slave"
+}
+
+test_all()
+{
+        slow_path_trap_install $swp1 ingress
+        slow_path_trap_install $swp1 egress
+
+        tests_run
+
+        slow_path_trap_uninstall $swp1 egress
+        slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+        echo "WARN: Could not test offloaded functionality"
+else
+        tcflags="skip_sw"
+        test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
index 619b469365be..fac486178ef7 100644
--- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-source mirror_lib.sh
+source "$relative_path/mirror_lib.sh"
 
 quick_test_span_gre_dir_ips()
 {
@@ -62,7 +62,7 @@ full_test_span_gre_dir_vlan_ips()
                           "$backward_type" "$ip1" "$ip2"
 
         tc filter add dev $h3 ingress pref 77 prot 802.1q \
-                flower $vlan_match ip_proto 0x2f \
+                flower $vlan_match \
                 action pass
         mirror_test v$h1 $ip1 $ip2 $h3 77 10
         tc filter del dev $h3 ingress pref 77
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
index 8fa681eb90e7..6f9ef1820e93 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
@@ -35,6 +35,8 @@ setup_prepare()
         vrf_prepare
         mirror_gre_topo_create
 
+        sysctl_set net.ipv4.conf.v$h3.rp_filter 0
+
         ip address add dev $swp3 192.0.2.161/28
         ip address add dev $h3 192.0.2.162/28
         ip address add dev gt4 192.0.2.129/32
@@ -61,6 +63,8 @@ cleanup()
         ip address del dev $h3 192.0.2.162/28
         ip address del dev $swp3 192.0.2.161/28
 
+        sysctl_restore net.ipv4.conf.v$h3.rp_filter 0
+
         mirror_gre_topo_destroy
         vrf_cleanup
 
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
index 253419564708..39c03e2867f4 100644
--- a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
@@ -33,7 +33,7 @@
 #   |                                                                         |
 #   +-------------------------------------------------------------------------+
 
-source mirror_topo_lib.sh
+source "$relative_path/mirror_topo_lib.sh"
 
 mirror_gre_topo_h3_create()
 {
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index 5dbc7a08f4bd..204b25f13934 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -28,6 +28,8 @@ source mirror_lib.sh
 source mirror_gre_lib.sh
 source mirror_gre_topo_lib.sh
 
+require_command $ARPING
+
 setup_prepare()
 {
         h1=${NETIFS[p1]}
@@ -39,6 +41,12 @@ setup_prepare()
         swp3=${NETIFS[p5]}
         h3=${NETIFS[p6]}
 
+        # gt4's remote address is at $h3.555, not $h3. Thus the packets arriving
+        # directly to $h3 for test_gretap_untagged_egress() are rejected by
+        # rp_filter and the test spuriously fails.
+        sysctl_set net.ipv4.conf.all.rp_filter 0
+        sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
         vrf_prepare
         mirror_gre_topo_create
 
@@ -65,6 +73,9 @@ cleanup()
 
         mirror_gre_topo_destroy
         vrf_cleanup
+
+        sysctl_restore net.ipv4.conf.$h3.rp_filter
+        sysctl_restore net.ipv4.conf.all.rp_filter
 }
 
 test_vlan_match()
@@ -79,12 +90,14 @@ test_vlan_match()
 
 test_gretap()
 {
-        test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+        test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+                        "mirror to gretap"
 }
 
 test_ip6gretap()
 {
-        test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+        test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+                        "mirror to ip6gretap"
 }
 
 test_span_gre_forbidden_cpu()
@@ -138,7 +151,7 @@ test_span_gre_forbidden_egress()
 
         bridge vlan add dev $swp3 vid 555
         # Re-prime FDB
-        arping -I br1.555 192.0.2.130 -fqc 1
+        $ARPING -I br1.555 192.0.2.130 -fqc 1
         sleep 1
         quick_test_span_gre_dir $tundev ingress
 
@@ -212,7 +225,7 @@ test_span_gre_fdb_roaming()
 
         bridge fdb del dev $swp2 $h3mac vlan 555 master
         # Re-prime FDB
-        arping -I br1.555 192.0.2.130 -fqc 1
+        $ARPING -I br1.555 192.0.2.130 -fqc 1
         sleep 1
         quick_test_span_gre_dir $tundev ingress
 
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
index d36dc26c6c51..07991e1025c7 100644
--- a/tools/testing/selftests/net/forwarding/mirror_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -105,7 +105,7 @@ do_test_span_vlan_dir_ips()
         # Install the capture as skip_hw to avoid double-counting of packets.
         # The traffic is meant for local box anyway, so will be trapped to
         # kernel.
-        vlan_capture_install $dev "skip_hw vlan_id $vid"
+        vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip"
         mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
         mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
         vlan_capture_uninstall $dev
diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh
new file mode 100755
index 000000000000..ebc596a272f7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge.sh
@@ -0,0 +1,113 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+        ping_ipv4
+        ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+        simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+        ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+        ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+        ip -6 route del 2001:db8:2::/64 vrf v$h1
+        ip -4 route del 192.0.2.128/28 vrf v$h1
+        simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+        ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+        ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+        ip -6 route del 2001:db8:1::/64 vrf v$h2
+        ip -4 route del 192.0.2.0/28 vrf v$h2
+        simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+}
+
+router_create()
+{
+        ip link add name br1 type bridge vlan_filtering 1
+        ip link set dev br1 up
+
+        ip link set dev $swp1 master br1
+        ip link set dev $swp1 up
+        __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+        ip link set dev $swp2 up
+        __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+        __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+        ip link set dev $swp2 down
+
+        __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+        ip link set dev $swp1 down
+        ip link set dev $swp1 nomaster
+
+        ip link del dev br1
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+
+        router_create
+
+        forwarding_enable
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        forwarding_restore
+
+        router_destroy
+
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+ping_ipv4()
+{
+        ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+        ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
new file mode 100755
index 000000000000..fef88eb4b873
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
@@ -0,0 +1,132 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+        ping_ipv4
+        ping_ipv6
+        vlan
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+        simple_if_init $h1
+        vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64
+        ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+        ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+        ip -6 route del 2001:db8:2::/64 vrf v$h1
+        ip -4 route del 192.0.2.128/28 vrf v$h1
+        vlan_destroy $h1 555
+        simple_if_fini $h1
+}
+
+h2_create()
+{
+        simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+        ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+        ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+        ip -6 route del 2001:db8:1::/64 vrf v$h2
+        ip -4 route del 192.0.2.0/28 vrf v$h2
+        simple_if_fini $h2 192.0.2.130/28
+}
+
+router_create()
+{
+        ip link add name br1 type bridge vlan_filtering 1
+        ip link set dev br1 up
+
+        ip link set dev $swp1 master br1
+        ip link set dev $swp1 up
+
+        bridge vlan add dev br1 vid 555 self pvid untagged
+        bridge vlan add dev $swp1 vid 555
+
+        __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+        ip link set dev $swp2 up
+        __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+        __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+        ip link set dev $swp2 down
+
+        __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+        ip link set dev $swp1 down
+        ip link set dev $swp1 nomaster
+
+        ip link del dev br1
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        swp1=${NETIFS[p2]}
+
+        swp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+
+        router_create
+
+        forwarding_enable
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        forwarding_restore
+
+        router_destroy
+
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+vlan()
+{
+        RET=0
+
+        bridge vlan add dev br1 vid 333 self
+        check_err $? "Can't add a non-PVID VLAN"
+        bridge vlan del dev br1 vid 333 self
+        check_err $? "Can't remove a non-PVID VLAN"
+
+        log_test "vlan"
+}
+
+ping_ipv4()
+{
+        ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+        ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh
new file mode 100755
index 000000000000..7bd2ebb6e9de
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh
@@ -0,0 +1,233 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4"
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+        vrf_create "vrf-h1"
+        ip link set dev $h1 master vrf-h1
+
+        ip link set dev vrf-h1 up
+        ip link set dev $h1 up
+
+        ip address add 192.0.2.2/24 dev $h1
+
+        ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+        ip route add 198.51.200.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+}
+
+h1_destroy()
+{
+        ip route del 198.51.200.0/24 vrf vrf-h1
+        ip route del 198.51.100.0/24 vrf vrf-h1
+
+        ip address del 192.0.2.2/24 dev $h1
+
+        ip link set dev $h1 down
+        vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+        vrf_create "vrf-h2"
+        ip link set dev $h2 master vrf-h2
+
+        ip link set dev vrf-h2 up
+        ip link set dev $h2 up
+
+        ip address add 198.51.100.2/24 dev $h2
+
+        ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+        ip route add 198.51.200.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+}
+
+h2_destroy()
+{
+        ip route del 198.51.200.0/24 vrf vrf-h2
+        ip route del 192.0.2.0/24 vrf vrf-h2
+
+        ip address del 198.51.100.2/24 dev $h2
+
+        ip link set dev $h2 down
+        vrf_destroy "vrf-h2"
+}
+
+h3_create()
+{
+        vrf_create "vrf-h3"
+        ip link set dev $h3 master vrf-h3
+
+        ip link set dev vrf-h3 up
+        ip link set dev $h3 up
+
+        ip address add 198.51.200.2/24 dev $h3
+
+        ip route add 192.0.2.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+        ip route add 198.51.100.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+}
+
+h3_destroy()
+{
+        ip route del 198.51.100.0/24 vrf vrf-h3
+        ip route del 192.0.2.0/24 vrf vrf-h3
+
+        ip address del 198.51.200.2/24 dev $h3
+
+        ip link set dev $h3 down
+        vrf_destroy "vrf-h3"
+}
+
+router_create()
+{
+        ip link set dev $rp1 up
+        ip link set dev $rp2 up
+        ip link set dev $rp3 up
+
+        ip address add 192.0.2.1/24 dev $rp1
+
+        ip address add 198.51.100.1/24 dev $rp2
+        ip address add 198.51.200.1/24 dev $rp3
+}
+
+router_destroy()
+{
+        ip address del 198.51.200.1/24 dev $rp3
+        ip address del 198.51.100.1/24 dev $rp2
+
+        ip address del 192.0.2.1/24 dev $rp1
+
+        ip link set dev $rp3 down
+        ip link set dev $rp2 down
+        ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+        h1=${NETIFS[p1]}
+        rp1=${NETIFS[p2]}
+
+        rp2=${NETIFS[p3]}
+        h2=${NETIFS[p4]}
+
+        rp3=${NETIFS[p5]}
+        h3=${NETIFS[p6]}
+
+        vrf_prepare
+
+        h1_create
+        h2_create
+        h3_create
+
+        router_create
+
+        forwarding_enable
+}
+
+cleanup()
+{
+        pre_cleanup
+
+        forwarding_restore
+
+        router_destroy
+
+        h3_destroy
+        h2_destroy
+        h1_destroy
+
+        vrf_cleanup
+}
+
+bc_forwarding_disable()
+{
+        sysctl_set net.ipv4.conf.all.bc_forwarding 0
+        sysctl_set net.ipv4.conf.$rp1.bc_forwarding 0
+}
+
+bc_forwarding_enable()
+{
+        sysctl_set net.ipv4.conf.all.bc_forwarding 1
+        sysctl_set net.ipv4.conf.$rp1.bc_forwarding 1
+}
+
+bc_forwarding_restore()
+{
+        sysctl_restore net.ipv4.conf.$rp1.bc_forwarding
+        sysctl_restore net.ipv4.conf.all.bc_forwarding
+}
+
+ping_test_from()
+{
+        local oif=$1
+        local dip=$2
+        local from=$3
+        local fail=${4:-0}
+
+        RET=0
+
+        log_info "ping $dip, expected reply from $from"
+        ip vrf exec $(master_name_get $oif) \
+        $PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null
+        check_err_fail $fail $?
+}
+
+ping_ipv4()
+{
+        sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+
+        bc_forwarding_disable
+        log_info "bc_forwarding disabled on r1 =>"
+        ping_test_from $h1 198.51.100.255 192.0.2.1
+        log_test "h1 -> net2: reply from r1 (not forwarding)"
+        ping_test_from $h1 198.51.200.255 192.0.2.1
+        log_test "h1 -> net3: reply from r1 (not forwarding)"
+        ping_test_from $h1 192.0.2.255 192.0.2.1
+        log_test "h1 -> net1: reply from r1 (not dropping)"
+        ping_test_from $h1 255.255.255.255 192.0.2.1
+        log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+        ping_test_from $h2 192.0.2.255 198.51.100.1
+        log_test "h2 -> net1: reply from r1 (not forwarding)"
+        ping_test_from $h2 198.51.200.255 198.51.100.1
+        log_test "h2 -> net3: reply from r1 (not forwarding)"
+        ping_test_from $h2 198.51.100.255 198.51.100.1
+        log_test "h2 -> net2: reply from r1 (not dropping)"
+        ping_test_from $h2 255.255.255.255 198.51.100.1
+        log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+        bc_forwarding_restore
+
+        bc_forwarding_enable
+        log_info "bc_forwarding enabled on r1 =>"
+        ping_test_from $h1 198.51.100.255 198.51.100.2
+        log_test "h1 -> net2: reply from h2 (forwarding)"
+        ping_test_from $h1 198.51.200.255 198.51.200.2
+        log_test "h1 -> net3: reply from h3 (forwarding)"
+        ping_test_from $h1 192.0.2.255 192.0.2.1 1
+        log_test "h1 -> net1: no reply (dropping)"
+        ping_test_from $h1 255.255.255.255 192.0.2.1
+        log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+        ping_test_from $h2 192.0.2.255 192.0.2.2
+        log_test "h2 -> net1: reply from h1 (forwarding)"
+        ping_test_from $h2 198.51.200.255 198.51.200.2
+        log_test "h2 -> net3: reply from h3 (forwarding)"
+        ping_test_from $h2 198.51.100.255 198.51.100.1 1
+        log_test "h2 -> net2: no reply (dropping)"
+        ping_test_from $h2 255.255.255.255 198.51.100.1
+        log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+        bc_forwarding_restore
+
+        sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index 8b6d0fb6d604..79a209927962 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -159,45 +159,6 @@ router2_destroy()
         vrf_destroy "vrf-r2"
 }
 
-multipath_eval()
-{
-       local desc="$1"
-       local weight_rp12=$2
-       local weight_rp13=$3
-       local packets_rp12=$4
-       local packets_rp13=$5
-       local weights_ratio packets_ratio diff
-
-       RET=0
-
-       if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
-              check_err 1 "Packet difference is 0"
-              log_test "Multipath"
-              log_info "Expected ratio $weights_ratio"
-              return
-       fi
-
-       if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
-               weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
-                       | bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
-                       | bc -l)
-       else
-               weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \
-                       bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \
-                       bc -l)
-       fi
-
-       diff=$(echo $weights_ratio - $packets_ratio | bc -l)
-       diff=${diff#-}
-
-       test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
-       check_err $? "Too large discrepancy between expected and measured ratios"
-       log_test "$desc"
-       log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
-}
-
 multipath4_test()
 {
        local desc="$1"
diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index d2c783e94df3..2934fb5ed2a2 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -1,7 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="unreachable_chain_test gact_goto_chain_test"
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test create_destroy_chain \
+           template_filter_fits"
 NUM_NETIFS=2
 source tc_common.sh
 source lib.sh
@@ -80,6 +81,87 @@ gact_goto_chain_test()
         log_test "gact goto chain ($tcflags)"
 }
 
+create_destroy_chain()
+{
+        RET=0
+
+        tc chain add dev $h2 ingress
+        check_err $? "Failed to create default chain"
+
+        output="$(tc -j chain get dev $h2 ingress)"
+        check_err $? "Failed to get default chain"
+
+        echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null
+        check_err $? "Unexpected output for default chain"
+
+        tc chain add dev $h2 ingress chain 1
+        check_err $? "Failed to create chain 1"
+
+        output="$(tc -j chain get dev $h2 ingress chain 1)"
+        check_err $? "Failed to get chain 1"
+
+        echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null
+        check_err $? "Unexpected output for chain 1"
+
+        output="$(tc -j chain show dev $h2 ingress)"
+        check_err $? "Failed to dump chains"
+
+        echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null
+        check_err $? "Can't find default chain in dump"
+
+        echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null
+        check_err $? "Can't find chain 1 in dump"
+
+        tc chain del dev $h2 ingress
+        check_err $? "Failed to destroy default chain"
+
+        tc chain del dev $h2 ingress chain 1
+        check_err $? "Failed to destroy chain 1"
+
+        log_test "create destroy chain"
+}
+
+template_filter_fits()
+{
+        RET=0
+
+        tc chain add dev $h2 ingress protocol ip \
+                flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+        tc chain add dev $h2 ingress chain 1 protocol ip \
+                flower src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \
+                flower dst_mac $h2mac action drop
+        check_err $? "Failed to insert filter which fits template"
+
+        tc filter add dev $h2 ingress protocol ip pref 1 handle 1102 \
+                flower src_mac $h2mac action drop &> /dev/null
+        check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+        tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+                flower src_mac $h2mac action drop
+        check_err $? "Failed to insert filter which fits template"
+
+        tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \
+                flower dst_mac $h2mac action drop &> /dev/null
+        check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+        tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \
+                flower &> /dev/null
+        tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+                flower &> /dev/null
+
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 1102 \
+                flower &> /dev/null
+        tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 \
+                flower &> /dev/null
+
+        tc chain del dev $h2 ingress chain 1
+        tc chain del dev $h2 ingress
+
+        log_test "template filter fits"
+}
+
 setup_prepare()
 {
         h1=${NETIFS[p1]}
@@ -103,6 +185,8 @@ cleanup()
         vrf_cleanup
 }
 
+check_tc_chain_support
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
index b5b917203815..9826a446e2c0 100755
--- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh
+++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
@@ -105,6 +105,8 @@ cleanup()
         ip link set $swp2 address $swp2origmac
 }
 
+check_tc_shblock_support
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/ip6_gre_headroom.sh b/tools/testing/selftests/net/ip6_gre_headroom.sh
new file mode 100755
index 000000000000..5b41e8bb6e2d
--- /dev/null
+++ b/tools/testing/selftests/net/ip6_gre_headroom.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that enough headroom is reserved for the first packet passing through an
+# IPv6 GRE-like netdevice.
+
+setup_prepare()
+{
+        ip link add h1 type veth peer name swp1
+        ip link add h3 type veth peer name swp3
+
+        ip link set dev h1 up
+        ip address add 192.0.2.1/28 dev h1
+
+        ip link add dev vh3 type vrf table 20
+        ip link set dev h3 master vh3
+        ip link set dev vh3 up
+        ip link set dev h3 up
+
+        ip link set dev swp3 up
+        ip address add dev swp3 2001:db8:2::1/64
+        ip address add dev swp3 2001:db8:2::3/64
+
+        ip link set dev swp1 up
+        tc qdisc add dev swp1 clsact
+
+        ip link add name er6 type ip6erspan \
+           local 2001:db8:2::1 remote 2001:db8:2::2 oseq okey 123
+        ip link set dev er6 up
+
+        ip link add name gt6 type ip6gretap \
+           local 2001:db8:2::3 remote 2001:db8:2::4
+        ip link set dev gt6 up
+
+        sleep 1
+}
+
+cleanup()
+{
+        ip link del dev gt6
+        ip link del dev er6
+        ip link del dev swp1
+        ip link del dev swp3
+        ip link del dev vh3
+}
+
+test_headroom()
+{
+        local type=$1; shift
+        local tundev=$1; shift
+
+        tc filter add dev swp1 ingress pref 1000 matchall skip_hw \
+                action mirred egress mirror dev $tundev
+        ping -I h1 192.0.2.2 -c 1 -w 2 &> /dev/null
+        tc filter del dev swp1 ingress pref 1000
+
+        # If it doesn't panic, it passes.
+        printf "TEST: %-60s  [PASS]\n" "$type headroom"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+test_headroom ip6gretap gt6
+test_headroom ip6erspan er6
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 0d7a44fa30af..08c341b49760 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -525,18 +525,21 @@ kci_test_macsec()
 #-------------------------------------------------------------------
 kci_test_ipsec()
 {
-        srcip="14.0.0.52"
-        dstip="14.0.0.70"
+        ret=0
         algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+        srcip=192.168.123.1
+        dstip=192.168.123.2
+        spi=7
+
+        ip addr add $srcip dev $devdummy
 
         # flush to be sure there's nothing configured
         ip x s flush ; ip x p flush
         check_err $?
 
         # start the monitor in the background
-        tmpfile=`mktemp ipsectestXXX`
-        ip x m > $tmpfile &
-        mpid=$!
+        tmpfile=`mktemp /var/run/ipsectestXXX`
+        mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null`
         sleep 0.2
 
         ipsecid="proto esp src $srcip dst $dstip spi 0x07"
@@ -599,6 +602,7 @@ kci_test_ipsec()
         check_err $?
         ip x p flush
         check_err $?
+        ip addr del $srcip/32 dev $devdummy
 
         if [ $ret -ne 0 ]; then
                 echo "FAIL: ipsec"
@@ -607,6 +611,119 @@ kci_test_ipsec()
         echo "PASS: ipsec"
 }
 
+#-------------------------------------------------------------------
+# Example commands
+#   ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07 replay-window 32 \
+#            aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+#            sel src 14.0.0.52/24 dst 14.0.0.70/24
+#            offload dev sim1 dir out
+#   ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+#            tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07
+#
+#-------------------------------------------------------------------
+kci_test_ipsec_offload()
+{
+        ret=0
+        algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+        srcip=192.168.123.3
+        dstip=192.168.123.4
+        dev=simx1
+        sysfsd=/sys/kernel/debug/netdevsim/$dev
+        sysfsf=$sysfsd/ipsec
+
+        # setup netdevsim since dummydev doesn't have offload support
+        modprobe netdevsim
+        check_err $?
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: ipsec_offload can't load netdevsim"
+                return 1
+        fi
+
+        ip link add $dev type netdevsim
+        ip addr add $srcip dev $dev
+        ip link set $dev up
+        if [ ! -d $sysfsd ] ; then
+                echo "FAIL: ipsec_offload can't create device $dev"
+                return 1
+        fi
+        if [ ! -f $sysfsf ] ; then
+                echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload"
+                return 1
+        fi
+
+        # flush to be sure there's nothing configured
+        ip x s flush ; ip x p flush
+
+        # create offloaded SAs, both in and out
+        ip x p add dir out src $srcip/24 dst $dstip/24 \
+            tmpl proto esp src $srcip dst $dstip spi 9 \
+            mode transport reqid 42
+        check_err $?
+        ip x p add dir out src $dstip/24 dst $srcip/24 \
+            tmpl proto esp src $dstip dst $srcip spi 9 \
+            mode transport reqid 42
+        check_err $?
+
+        ip x s add proto esp src $srcip dst $dstip spi 9 \
+            mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \
+            offload dev $dev dir out
+        check_err $?
+        ip x s add proto esp src $dstip dst $srcip spi 9 \
+            mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \
+            offload dev $dev dir in
+        check_err $?
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: ipsec_offload can't create SA"
+                return 1
+        fi
+
+        # does offload show up in ip output
+        lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"`
+        if [ $lines -ne 2 ] ; then
+                echo "FAIL: ipsec_offload SA offload missing from list output"
+                check_err 1
+        fi
+
+        # use ping to exercise the Tx path
+        ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null
+
+        # does driver have correct offload info
+        diff $sysfsf - << EOF
+SA count=2 tx=3
+sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000
+sa[0]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[0]    key=0x34333231 38373635 32313039 36353433
+sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0
+sa[1]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[1]    key=0x34333231 38373635 32313039 36353433
+EOF
+        if [ $? -ne 0 ] ; then
+                echo "FAIL: ipsec_offload incorrect driver data"
+                check_err 1
+        fi
+
+        # does offload get removed from driver
+        ip x s flush
+        ip x p flush
+        lines=`grep -c "SA count=0" $sysfsf`
+        if [ $lines -ne 1 ] ; then
+                echo "FAIL: ipsec_offload SA not removed from driver"
+                check_err 1
+        fi
+
+        # clean up any leftovers
+        ip link del $dev
+        rmmod netdevsim
+
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: ipsec_offload"
+                return 1
+        fi
+        echo "PASS: ipsec_offload"
+}
+
 kci_test_gretap()
 {
         testns="testns"
@@ -861,6 +978,7 @@ kci_test_rtnl()
         kci_test_encap
         kci_test_macsec
         kci_test_ipsec
+        kci_test_ipsec_offload
 
         kci_del_dummy
 }
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
new file mode 100644
index 000000000000..b3ebf2646e52
--- /dev/null
+++ b/tools/testing/selftests/net/tls.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/tls.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+
+#include <sys/types.h>
+#include <sys/sendfile.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+
+#include "../kselftest_harness.h"
+
+#define TLS_PAYLOAD_MAX_LEN 16384
+#define SOL_TLS 282
+
+FIXTURE(tls)
+{
+        int fd, cfd;
+        bool notls;
+};
+
+FIXTURE_SETUP(tls)
+{
+        struct tls12_crypto_info_aes_gcm_128 tls12;
+        struct sockaddr_in addr;
+        socklen_t len;
+        int sfd, ret;
+
+        self->notls = false;
+        len = sizeof(addr);
+
+        memset(&tls12, 0, sizeof(tls12));
+        tls12.info.version = TLS_1_2_VERSION;
+        tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+        addr.sin_family = AF_INET;
+        addr.sin_addr.s_addr = htonl(INADDR_ANY);
+        addr.sin_port = 0;
+
+        self->fd = socket(AF_INET, SOCK_STREAM, 0);
+        sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+        ret = bind(sfd, &addr, sizeof(addr));
+        ASSERT_EQ(ret, 0);
+        ret = listen(sfd, 10);
+        ASSERT_EQ(ret, 0);
+
+        ret = getsockname(sfd, &addr, &len);
+        ASSERT_EQ(ret, 0);
+
+        ret = connect(self->fd, &addr, sizeof(addr));
+        ASSERT_EQ(ret, 0);
+
+        ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+        if (ret != 0) {
+                self->notls = true;
+                printf("Failure setting TCP_ULP, testing without tls\n");
+        }
+
+        if (!self->notls) {
+                ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
+                                 sizeof(tls12));
+                ASSERT_EQ(ret, 0);
+        }
+
+        self->cfd = accept(sfd, &addr, &len);
+        ASSERT_GE(self->cfd, 0);
+
+        if (!self->notls) {
+                ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls",
+                                 sizeof("tls"));
+                ASSERT_EQ(ret, 0);
+
+                ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
+                                 sizeof(tls12));
+                ASSERT_EQ(ret, 0);
+        }
+
+        close(sfd);
+}
+
+FIXTURE_TEARDOWN(tls)
+{
+        close(self->fd);
+        close(self->cfd);
+}
+
+TEST_F(tls, sendfile)
+{
+        int filefd = open("/proc/self/exe", O_RDONLY);
+        struct stat st;
+
+        EXPECT_GE(filefd, 0);
+        fstat(filefd, &st);
+        EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+}
+
+TEST_F(tls, send_then_sendfile)
+{
+        int filefd = open("/proc/self/exe", O_RDONLY);
+        char const *test_str = "test_send";
+        int to_send = strlen(test_str) + 1;
+        char recv_buf[10];
+        struct stat st;
+        char *buf;
+
+        EXPECT_GE(filefd, 0);
+        fstat(filefd, &st);
+        buf = (char *)malloc(st.st_size);
+
+        EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
+        EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+        EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
+
+        EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+        EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+}
+
+TEST_F(tls, recv_max)
+{
+        unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+        char recv_mem[TLS_PAYLOAD_MAX_LEN];
+        char buf[TLS_PAYLOAD_MAX_LEN];
+
+        EXPECT_GE(send(self->fd, buf, send_len, 0), 0);
+        EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+        EXPECT_EQ(memcmp(buf, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recv_small)
+{
+        char const *test_str = "test_read";
+        int send_len = 10;
+        char buf[10];
+
+        send_len = strlen(test_str) + 1;
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+        EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, msg_more)
+{
+        char const *test_str = "test_read";
+        int send_len = 10;
+        char buf[10 * 2];
+
+        EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+        EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+                  send_len * 2);
+        EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_single)
+{
+        struct msghdr msg;
+
+        char const *test_str = "test_sendmsg";
+        size_t send_len = 13;
+        struct iovec vec;
+        char buf[13];
+
+        vec.iov_base = (char *)test_str;
+        vec.iov_len = send_len;
+        memset(&msg, 0, sizeof(struct msghdr));
+        msg.msg_iov = &vec;
+        msg.msg_iovlen = 1;
+        EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+        EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+        EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_large)
+{
+        void *mem = malloc(16384);
+        size_t send_len = 16384;
+        size_t sends = 128;
+        struct msghdr msg;
+        size_t recvs = 0;
+        size_t sent = 0;
+
+        memset(&msg, 0, sizeof(struct msghdr));
+        while (sent++ < sends) {
+                struct iovec vec = { (void *)mem, send_len };
+
+                msg.msg_iov = &vec;
+                msg.msg_iovlen = 1;
+                EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len);
+        }
+
+        while (recvs++ < sends)
+                EXPECT_NE(recv(self->fd, mem, send_len, 0), -1);
+
+        free(mem);
+}
+
+TEST_F(tls, sendmsg_multiple)
+{
+        char const *test_str = "test_sendmsg_multiple";
+        struct iovec vec[5];
+        char *test_strs[5];
+        struct msghdr msg;
+        int total_len = 0;
+        int len_cmp = 0;
+        int iov_len = 5;
+        char *buf;
+        int i;
+
+        memset(&msg, 0, sizeof(struct msghdr));
+        for (i = 0; i < iov_len; i++) {
+                test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+                snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+                vec[i].iov_base = (void *)test_strs[i];
+                vec[i].iov_len = strlen(test_strs[i]) + 1;
+                total_len += vec[i].iov_len;
+        }
+        msg.msg_iov = vec;
+        msg.msg_iovlen = iov_len;
+
+        EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len);
+        buf = malloc(total_len);
+        EXPECT_NE(recv(self->fd, buf, total_len, 0), -1);
+        for (i = 0; i < iov_len; i++) {
+                EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp,
+                                 strlen(test_strs[i])),
+                          0);
+                len_cmp += strlen(buf + len_cmp) + 1;
+        }
+        for (i = 0; i < iov_len; i++)
+                free(test_strs[i]);
+        free(buf);
+}
+
+TEST_F(tls, sendmsg_multiple_stress)
+{
+        char const *test_str = "abcdefghijklmno";
+        struct iovec vec[1024];
+        char *test_strs[1024];
+        int iov_len = 1024;
+        int total_len = 0;
+        char buf[1 << 14];
+        struct msghdr msg;
+        int len_cmp = 0;
+        int i;
+
+        memset(&msg, 0, sizeof(struct msghdr));
+        for (i = 0; i < iov_len; i++) {
+                test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+                snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+                vec[i].iov_base = (void *)test_strs[i];
+                vec[i].iov_len = strlen(test_strs[i]) + 1;
+                total_len += vec[i].iov_len;
+        }
+        msg.msg_iov = vec;
+        msg.msg_iovlen = iov_len;
+
+        EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len);
+        EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1);
+
+        for (i = 0; i < iov_len; i++)
+                len_cmp += strlen(buf + len_cmp) + 1;
+
+        for (i = 0; i < iov_len; i++)
+                free(test_strs[i]);
+}
+
+TEST_F(tls, splice_from_pipe)
+{
+        int send_len = TLS_PAYLOAD_MAX_LEN;
+        char mem_send[TLS_PAYLOAD_MAX_LEN];
+        char mem_recv[TLS_PAYLOAD_MAX_LEN];
+        int p[2];
+
+        ASSERT_GE(pipe(p), 0);
+        EXPECT_GE(write(p[1], mem_send, send_len), 0);
+        EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
+        EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+        EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_from_pipe2)
+{
+        int send_len = 16000;
+        char mem_send[16000];
+        char mem_recv[16000];
+        int p2[2];
+        int p[2];
+
+        ASSERT_GE(pipe(p), 0);
+        ASSERT_GE(pipe(p2), 0);
+        EXPECT_GE(write(p[1], mem_send, 8000), 0);
+        EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
+        EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
+        EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
+        EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+        EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, send_and_splice)
+{
+        int send_len = TLS_PAYLOAD_MAX_LEN;
+        char mem_send[TLS_PAYLOAD_MAX_LEN];
+        char mem_recv[TLS_PAYLOAD_MAX_LEN];
+        char const *test_str = "test_read";
+        int send_len2 = 10;
+        char buf[10];
+        int p[2];
+
+        ASSERT_GE(pipe(p), 0);
+        EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
+        EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+        EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
+
+        EXPECT_GE(write(p[1], mem_send, send_len), send_len);
+        EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
+
+        EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+        EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_to_pipe)
+{
+        int send_len = TLS_PAYLOAD_MAX_LEN;
+        char mem_send[TLS_PAYLOAD_MAX_LEN];
+        char mem_recv[TLS_PAYLOAD_MAX_LEN];
+        int p[2];
+
+        ASSERT_GE(pipe(p), 0);
+        EXPECT_GE(send(self->fd, mem_send, send_len, 0), 0);
+        EXPECT_GE(splice(self->cfd, NULL, p[1], NULL, send_len, 0), 0);
+        EXPECT_GE(read(p[0], mem_recv, send_len), 0);
+        EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single)
+{
+        char const *test_str = "test_recvmsg_single";
+        int send_len = strlen(test_str) + 1;
+        char buf[20];
+        struct msghdr hdr;
+        struct iovec vec;
+
+        memset(&hdr, 0, sizeof(hdr));
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        vec.iov_base = (char *)buf;
+        vec.iov_len = send_len;
+        hdr.msg_iovlen = 1;
+        hdr.msg_iov = &vec;
+        EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+        EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single_max)
+{
+        int send_len = TLS_PAYLOAD_MAX_LEN;
+        char send_mem[TLS_PAYLOAD_MAX_LEN];
+        char recv_mem[TLS_PAYLOAD_MAX_LEN];
+        struct iovec vec;
+        struct msghdr hdr;
+
+        EXPECT_EQ(send(self->fd, send_mem, send_len, 0), send_len);
+        vec.iov_base = (char *)recv_mem;
+        vec.iov_len = TLS_PAYLOAD_MAX_LEN;
+
+        hdr.msg_iovlen = 1;
+        hdr.msg_iov = &vec;
+        EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+        EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_multiple)
+{
+        unsigned int msg_iovlen = 1024;
+        unsigned int len_compared = 0;
+        struct iovec vec[1024];
+        char *iov_base[1024];
+        unsigned int iov_len = 16;
+        int send_len = 1 << 14;
+        char buf[1 << 14];
+        struct msghdr hdr;
+        int i;
+
+        EXPECT_EQ(send(self->fd, buf, send_len, 0), send_len);
+        for (i = 0; i < msg_iovlen; i++) {
+                iov_base[i] = (char *)malloc(iov_len);
+                vec[i].iov_base = iov_base[i];
+                vec[i].iov_len = iov_len;
+        }
+
+        hdr.msg_iovlen = msg_iovlen;
+        hdr.msg_iov = vec;
+        EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+        for (i = 0; i < msg_iovlen; i++)
+                len_compared += iov_len;
+
+        for (i = 0; i < msg_iovlen; i++)
+                free(iov_base[i]);
+}
+
+TEST_F(tls, single_send_multiple_recv)
+{
+        unsigned int total_len = TLS_PAYLOAD_MAX_LEN * 2;
+        unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+        char send_mem[TLS_PAYLOAD_MAX_LEN * 2];
+        char recv_mem[TLS_PAYLOAD_MAX_LEN * 2];
+
+        EXPECT_GE(send(self->fd, send_mem, total_len, 0), 0);
+        memset(recv_mem, 0, total_len);
+
+        EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+        EXPECT_NE(recv(self->cfd, recv_mem + send_len, send_len, 0), -1);
+        EXPECT_EQ(memcmp(send_mem, recv_mem, total_len), 0);
+}
+
+TEST_F(tls, multiple_send_single_recv)
+{
+        unsigned int total_len = 2 * 10;
+        unsigned int send_len = 10;
+        char recv_mem[2 * 10];
+        char send_mem[10];
+
+        EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+        EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+        memset(recv_mem, 0, total_len);
+        EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+
+        EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+        EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
+}
+
+TEST_F(tls, recv_partial)
+{
+        char const *test_str = "test_read_partial";
+        char const *test_str_first = "test_read";
+        char const *test_str_second = "_partial";
+        int send_len = strlen(test_str) + 1;
+        char recv_mem[18];
+
+        memset(recv_mem, 0, sizeof(recv_mem));
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), 0), -1);
+        EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
+        memset(recv_mem, 0, sizeof(recv_mem));
+        EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), 0), -1);
+        EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
+                  0);
+}
+
+TEST_F(tls, recv_nonblock)
+{
+        char buf[4096];
+        bool err;
+
+        EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+        err = (errno == EAGAIN || errno == EWOULDBLOCK);
+        EXPECT_EQ(err, true);
+}
+
+TEST_F(tls, recv_peek)
+{
+        char const *test_str = "test_read_peek";
+        int send_len = strlen(test_str) + 1;
+        char buf[15];
+
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+        EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+        memset(buf, 0, sizeof(buf));
+        EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+        EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recv_peek_multiple)
+{
+        char const *test_str = "test_read_peek";
+        int send_len = strlen(test_str) + 1;
+        unsigned int num_peeks = 100;
+        char buf[15];
+        int i;
+
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        for (i = 0; i < num_peeks; i++) {
+                EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+                EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+                memset(buf, 0, sizeof(buf));
+        }
+        EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+        EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, pollin)
+{
+        char const *test_str = "test_poll";
+        struct pollfd fd = { 0, 0, 0 };
+        char buf[10];
+        int send_len = 10;
+
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        fd.fd = self->cfd;
+        fd.events = POLLIN;
+
+        EXPECT_EQ(poll(&fd, 1, 20), 1);
+        EXPECT_EQ(fd.revents & POLLIN, 1);
+        EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+        /* Test timing out */
+        EXPECT_EQ(poll(&fd, 1, 20), 0);
+}
+
+TEST_F(tls, poll_wait)
+{
+        char const *test_str = "test_poll_wait";
+        int send_len = strlen(test_str) + 1;
+        struct pollfd fd = { 0, 0, 0 };
+        char recv_mem[15];
+
+        fd.fd = self->cfd;
+        fd.events = POLLIN;
+        EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+        /* Set timeout to inf. secs */
+        EXPECT_EQ(poll(&fd, 1, -1), 1);
+        EXPECT_EQ(fd.revents & POLLIN, 1);
+        EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+}
+
+TEST_F(tls, blocking)
+{
+        size_t data = 100000;
+        int res = fork();
+
+        EXPECT_NE(res, -1);
+
+        if (res) {
+                /* parent */
+                size_t left = data;
+                char buf[16384];
+                int status;
+                int pid2;
+
+                while (left) {
+                        int res = send(self->fd, buf,
+                                       left > 16384 ? 16384 : left, 0);
+
+                        EXPECT_GE(res, 0);
+                        left -= res;
+                }
+
+                pid2 = wait(&status);
+                EXPECT_EQ(status, 0);
+                EXPECT_EQ(res, pid2);
+        } else {
+                /* child */
+                size_t left = data;
+                char buf[16384];
+
+                while (left) {
+                        int res = recv(self->cfd, buf,
+                                       left > 16384 ? 16384 : left, 0);
+
+                        EXPECT_GE(res, 0);
+                        left -= res;
+                }
+        }
+}
+
+TEST_F(tls, nonblocking)
+{
+        size_t data = 100000;
+        int sendbuf = 100;
+        int flags;
+        int res;
+
+        flags = fcntl(self->fd, F_GETFL, 0);
+        fcntl(self->fd, F_SETFL, flags | O_NONBLOCK);
+        fcntl(self->cfd, F_SETFL, flags | O_NONBLOCK);
+
+        /* Ensure nonblocking behavior by imposing a small send
+         * buffer.
+         */
+        EXPECT_EQ(setsockopt(self->fd, SOL_SOCKET, SO_SNDBUF,
+                             &sendbuf, sizeof(sendbuf)), 0);
+
+        res = fork();
+        EXPECT_NE(res, -1);
+
+        if (res) {
+                /* parent */
+                bool eagain = false;
+                size_t left = data;
+                char buf[16384];
+                int status;
+                int pid2;
+
+                while (left) {
+                        int res = send(self->fd, buf,
+                                       left > 16384 ? 16384 : left, 0);
+
+                        if (res == -1 && errno == EAGAIN) {
+                                eagain = true;
+                                usleep(10000);
+                                continue;
+                        }
+                        EXPECT_GE(res, 0);
+                        left -= res;
+                }
+
+                EXPECT_TRUE(eagain);
+                pid2 = wait(&status);
+
+                EXPECT_EQ(status, 0);
+                EXPECT_EQ(res, pid2);
+        } else {
+                /* child */
+                bool eagain = false;
+                size_t left = data;
+                char buf[16384];
+
+                while (left) {
+                        int res = recv(self->cfd, buf,
+                                       left > 16384 ? 16384 : left, 0);
+
+                        if (res == -1 && errno == EAGAIN) {
+                                eagain = true;
+                                usleep(10000);
+                                continue;
+                        }
+                        EXPECT_GE(res, 0);
+                        left -= res;
+                }
+                EXPECT_TRUE(eagain);
+        }
+}
+
+TEST_F(tls, control_msg)
+{
+        if (self->notls)
+                return;
+
+        char cbuf[CMSG_SPACE(sizeof(char))];
+        char const *test_str = "test_read";
+        int cmsg_len = sizeof(char);
+        char record_type = 100;
+        struct cmsghdr *cmsg;
+        struct msghdr msg;
+        int send_len = 10;
+        struct iovec vec;
+        char buf[10];
+
+        vec.iov_base = (char *)test_str;
+        vec.iov_len = 10;
+        memset(&msg, 0, sizeof(struct msghdr));
+        msg.msg_iov = &vec;
+        msg.msg_iovlen = 1;
+        msg.msg_control = cbuf;
+        msg.msg_controllen = sizeof(cbuf);
+        cmsg = CMSG_FIRSTHDR(&msg);
+        cmsg->cmsg_level = SOL_TLS;
+        /* test sending non-record types. */
+        cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+        cmsg->cmsg_len = CMSG_LEN(cmsg_len);
+        *CMSG_DATA(cmsg) = record_type;
+        msg.msg_controllen = cmsg->cmsg_len;
+
+        EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+        /* Should fail because we didn't provide a control message */
+        EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+        vec.iov_base = buf;
+        EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+        cmsg = CMSG_FIRSTHDR(&msg);
+        EXPECT_NE(cmsg, NULL);
+        EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+        EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+        record_type = *((unsigned char *)CMSG_DATA(cmsg));
+        EXPECT_EQ(record_type, 100);
+        EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index c15f270e121d..65541c21a544 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# Usage: configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
@@ -40,20 +40,18 @@ mkdir $T
 
 c=$1
 buildloc=$2
+resdir=$3
 builddir=
-if test -n $buildloc
+if echo $buildloc | grep -q '^O='
 then
-        if echo $buildloc | grep -q '^O='
+        builddir=`echo $buildloc | sed -e 's/^O=//'`
+        if test ! -d $builddir
         then
-                builddir=`echo $buildloc | sed -e 's/^O=//'`
-                if test ! -d $builddir
-                then
-                        mkdir $builddir
-                fi
-        else
-                echo Bad build directory: \"$buildloc\"
-                exit 2
+                mkdir $builddir
         fi
+else
+        echo Bad build directory: \"$buildloc\"
+        exit 2
 fi
 
 sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
@@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
 grep '^grep' < $T/u.sh > $T/upd.sh
 echo "cat - $c" >> $T/upd.sh
 make mrproper
-make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
+make $buildloc distclean > $resdir/Make.distclean 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
+yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 34d126734cde..9115fcdb5617 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir
+# Usage: kvm-build.sh config-template build-dir resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -29,6 +29,7 @@ then
         exit 1
 fi
 builddir=${2}
+resdir=${3}
 
 T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
@@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
 
-configinit.sh $T/config O=$builddir
+configinit.sh $T/config O=$builddir $resdir
 retval=$?
 if test $retval -gt 1
 then
         exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1
 retval=$?
-if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out
 then
         echo Kernel build error
-        egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+        egrep "Stop|Error|error:|warning:" < $resdir/Make.out
         echo Run aborted.
         exit 3
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 477ecb1293ab..0fa8a61ccb7b 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -70,4 +70,5 @@ else
         else
                 print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
         fi
+        echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c27e97824163..c9bab57a77eb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -39,6 +39,7 @@ do
                         head -1 $resdir/log
                 fi
                 TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+                rm -f $i/console.log.*.diags
                 kvm-recheck-${TORTURE_SUITE}.sh $i
                 if test -f "$i/console.log"
                 then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index c5b0f94341d9..f7247ee00514 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -98,14 +98,15 @@ then
         ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
         # Arch-independent indicator
         touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $builddir
+elif kvm-build.sh $T/Kc2 $builddir $resdir
 then
         # Had to build a kernel for this test.
         QEMU="`identify_qemu $builddir/vmlinux`"
         BOOT_IMAGE="`identify_boot_image $QEMU`"
-        cp $builddir/Make*.out $resdir
         cp $builddir/vmlinux $resdir
         cp $builddir/.config $resdir
+        cp $builddir/Module.symvers $resdir > /dev/null || :
+        cp $builddir/System.map $resdir > /dev/null || :
         if test -n "$BOOT_IMAGE"
         then
                 cp $builddir/$BOOT_IMAGE $resdir
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 56610dbbdf73..5a7a62d76a50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum)
         print "needqemurun="
         jn=1
         for (j = first; j < pastlast; j++) {
-                builddir=KVM "/b" jn
+                builddir=KVM "/b1"
                 cpusr[jn] = cpus[j];
                 if (cfrep[cf[j]] == "") {
                         cfr[jn] = cf[j];
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 17293436f551..84933f6aed77 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -163,6 +163,13 @@ then
         print_warning Summary: $summary
         cat $T.diags >> $file.diags
 fi
+for i in $file.*.diags
+do
+        if test -f "$i"
+        then
+                cat $i >> $file.diags
+        fi
+done
 if ! test -s $file.diags
 then
         rm -f $file.diags
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
index 5d2cc0bd50a0..5c3213cc3ad7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -1,5 +1,5 @@
-rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30
+rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
deleted file mode 100644
index 883149b5f2d1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 24ec91041957..7bab8246392b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -39,7 +39,7 @@ rcutorture_param_onoff () {
         if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
         then
                 echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-                echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+                echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30
         fi
 }
 
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 615252331813..642d4e12abea 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -90,6 +90,30 @@ unsigned int yield_mod_cnt, nr_abort;
 #error "Unsupported architecture"
 #endif
 
+#elif defined(__s390__)
+
+#define RSEQ_INJECT_INPUT \
+        , [loop_cnt_1]"m"(loop_cnt[1]) \
+        , [loop_cnt_2]"m"(loop_cnt[2]) \
+        , [loop_cnt_3]"m"(loop_cnt[3]) \
+        , [loop_cnt_4]"m"(loop_cnt[4]) \
+        , [loop_cnt_5]"m"(loop_cnt[5]) \
+        , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG  "r12"
+
+#define RSEQ_INJECT_CLOBBER \
+        , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+        "l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+        "ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+        "je 333f\n\t" \
+        "222:\n\t" \
+        "ahi %%" INJECT_ASM_REG ", -1\n\t" \
+        "jnz 222b\n\t" \
+        "333:\n\t"
+
 #elif defined(__ARMEL__)
 
 #define RSEQ_INJECT_INPUT \
@@ -114,6 +138,26 @@ unsigned int yield_mod_cnt, nr_abort;
         "bne 222b\n\t" \
         "333:\n\t"
 
+#elif defined(__AARCH64EL__)
+
+#define RSEQ_INJECT_INPUT \
+        , [loop_cnt_1] "Qo" (loop_cnt[1]) \
+        , [loop_cnt_2] "Qo" (loop_cnt[2]) \
+        , [loop_cnt_3] "Qo" (loop_cnt[3]) \
+        , [loop_cnt_4] "Qo" (loop_cnt[4]) \
+        , [loop_cnt_5] "Qo" (loop_cnt[5]) \
+        , [loop_cnt_6] "Qo" (loop_cnt[6])
+
+#define INJECT_ASM_REG  RSEQ_ASM_TMP_REG32
+
+#define RSEQ_INJECT_ASM(n) \
+        "       ldr     " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n"       \
+        "       cbz     " INJECT_ASM_REG ", 333f\n"                     \
+        "222:\n"                                                        \
+        "       sub     " INJECT_ASM_REG ", " INJECT_ASM_REG ", #1\n"   \
+        "       cbnz    " INJECT_ASM_REG ", 222b\n"                     \
+        "333:\n"
+
 #elif __PPC__
 
 #define RSEQ_INJECT_INPUT \
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
new file mode 100644
index 000000000000..954f34671ca6
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -0,0 +1,594 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm64.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
+ */
+
+#define RSEQ_SIG        0xd428bc00      /* BRK #0x45E0 */
+
+#define rseq_smp_mb()   __asm__ __volatile__ ("dmb ish" ::: "memory")
+#define rseq_smp_rmb()  __asm__ __volatile__ ("dmb ishld" ::: "memory")
+#define rseq_smp_wmb()  __asm__ __volatile__ ("dmb ishst" ::: "memory")
+
+#define rseq_smp_load_acquire(p)                                                \
+__extension__ ({                                                                \
+        __typeof(*p) ____p1;                                                    \
+        switch (sizeof(*p)) {                                                   \
+        case 1:                                                                 \
+                asm volatile ("ldarb %w0, %1"                                   \
+                        : "=r" (*(__u8 *)p)                                     \
+                        : "Q" (*p) : "memory");                                 \
+                break;                                                          \
+        case 2:                                                                 \
+                asm volatile ("ldarh %w0, %1"                                   \
+                        : "=r" (*(__u16 *)p)                                    \
+                        : "Q" (*p) : "memory");                                 \
+                break;                                                          \
+        case 4:                                                                 \
+                asm volatile ("ldar %w0, %1"                                    \
+                        : "=r" (*(__u32 *)p)                                    \
+                        : "Q" (*p) : "memory");                                 \
+                break;                                                          \
+        case 8:                                                                 \
+                asm volatile ("ldar %0, %1"                                     \
+                        : "=r" (*(__u64 *)p)                                    \
+                        : "Q" (*p) : "memory");                                 \
+                break;                                                          \
+        }                                                                       \
+        ____p1;                                                                 \
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()      rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)                                            \
+do {                                                                            \
+        switch (sizeof(*p)) {                                                   \
+        case 1:                                                                 \
+                asm volatile ("stlrb %w1, %0"                                   \
+                                : "=Q" (*p)                                     \
+                                : "r" ((__u8)v)                                 \
+                                : "memory");                                    \
+                break;                                                          \
+        case 2:                                                                 \
+                asm volatile ("stlrh %w1, %0"                                   \
+                                : "=Q" (*p)                                     \
+                                : "r" ((__u16)v)                                \
+                                : "memory");                                    \
+                break;                                                          \
+        case 4:                                                                 \
+                asm volatile ("stlr %w1, %0"                                    \
+                                : "=Q" (*p)                                     \
+                                : "r" ((__u32)v)                                \
+                                : "memory");                                    \
+                break;                                                          \
+        case 8:                                                                 \
+                asm volatile ("stlr %1, %0"                                     \
+                                : "=Q" (*p)                                     \
+                                : "r" ((__u64)v)                                \
+                                : "memory");                                    \
+                break;                                                          \
+        }                                                                       \
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#define RSEQ_ASM_TMP_REG32      "w15"
+#define RSEQ_ASM_TMP_REG        "x15"
+#define RSEQ_ASM_TMP_REG_2      "x14"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip,                \
+                                post_commit_offset, abort_ip)                   \
+        "       .pushsection    __rseq_table, \"aw\"\n"                         \
+        "       .balign 32\n"                                                   \
+        __rseq_str(label) ":\n"                                                 \
+        "       .long   " __rseq_str(version) ", " __rseq_str(flags) "\n"       \
+        "       .quad   " __rseq_str(start_ip) ", "                             \
+                          __rseq_str(post_commit_offset) ", "                   \
+                          __rseq_str(abort_ip) "\n"                             \
+        "       .popsection\n"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip)        \
+        __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,                      \
+                                (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)                        \
+        RSEQ_INJECT_ASM(1)                                                      \
+        "       adrp    " RSEQ_ASM_TMP_REG ", " __rseq_str(cs_label) "\n"       \
+        "       add     " RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG                \
+                        ", :lo12:" __rseq_str(cs_label) "\n"                    \
+        "       str     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(rseq_cs) "]\n"     \
+        __rseq_str(label) ":\n"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, abort_label)                               \
+        "       b       222f\n"                                                 \
+        "       .inst   "       __rseq_str(RSEQ_SIG) "\n"                       \
+        __rseq_str(label) ":\n"                                                 \
+        "       b       %l[" __rseq_str(abort_label) "]\n"                      \
+        "222:\n"
+
+#define RSEQ_ASM_OP_STORE(value, var)                                           \
+        "       str     %[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_STORE_RELEASE(value, var)                                   \
+        "       stlr    %[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)                  \
+        RSEQ_ASM_OP_STORE(value, var)                                           \
+        __rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(value, var, post_commit_label)          \
+        RSEQ_ASM_OP_STORE_RELEASE(value, var)                                   \
+        __rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_CMPEQ(var, expect, label)                                   \
+        "       ldr     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"         \
+        "       sub     " RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG                \
+                        ", %[" __rseq_str(expect) "]\n"                         \
+        "       cbnz    " RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPEQ32(var, expect, label)                                 \
+        "       ldr     " RSEQ_ASM_TMP_REG32 ", %[" __rseq_str(var) "]\n"       \
+        "       sub     " RSEQ_ASM_TMP_REG32 ", " RSEQ_ASM_TMP_REG32            \
+                        ", %w[" __rseq_str(expect) "]\n"                        \
+        "       cbnz    " RSEQ_ASM_TMP_REG32 ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPNE(var, expect, label)                                   \
+        "       ldr     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"         \
+        "       sub     " RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG                \
+                        ", %[" __rseq_str(expect) "]\n"                         \
+        "       cbz     " RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)                      \
+        RSEQ_INJECT_ASM(2)                                                      \
+        RSEQ_ASM_OP_CMPEQ32(current_cpu_id, cpu_id, label)
+
+#define RSEQ_ASM_OP_R_LOAD(var)                                                 \
+        "       ldr     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_STORE(var)                                                \
+        "       str     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_LOAD_OFF(offset)                                          \
+        "       ldr     " RSEQ_ASM_TMP_REG ", [" RSEQ_ASM_TMP_REG               \
+                        ", %[" __rseq_str(offset) "]]\n"
+
+#define RSEQ_ASM_OP_R_ADD(count)                                                \
+        "       add     " RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG                \
+                        ", %[" __rseq_str(count) "]\n"
+
+#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)                       \
+        "       str     " RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"         \
+        __rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)                                 \
+        "       cbz     %[" __rseq_str(len) "], 333f\n"                         \
+        "       mov     " RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(len) "]\n"       \
+        "222:   sub     " RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", #1\n"   \
+        "       ldrb    " RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(src) "]"        \
+                        ", " RSEQ_ASM_TMP_REG_2 "]\n"                           \
+        "       strb    " RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(dst) "]"        \
+                        ", " RSEQ_ASM_TMP_REG_2 "]\n"                           \
+        "       cbnz    " RSEQ_ASM_TMP_REG_2 ", 222b\n"                         \
+        "333:\n"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+                RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [v]                   "Qo" (*v),
+                  [expect]              "r" (expect),
+                  [newv]                "r" (newv)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+                               off_t voffp, intptr_t *load, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2])
+#endif
+                RSEQ_ASM_OP_R_LOAD(v)
+                RSEQ_ASM_OP_R_STORE(load)
+                RSEQ_ASM_OP_R_LOAD_OFF(voffp)
+                RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [v]                   "Qo" (*v),
+                  [expectnot]           "r" (expectnot),
+                  [load]                "Qo" (*load),
+                  [voffp]               "r" (voffp)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+                RSEQ_ASM_OP_R_LOAD(v)
+                RSEQ_ASM_OP_R_ADD(count)
+                RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+                RSEQ_INJECT_ASM(4)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [v]                   "Qo" (*v),
+                  [count]               "r" (count)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+                                 intptr_t *v2, intptr_t newv2,
+                                 intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+                RSEQ_ASM_OP_STORE(newv2, v2)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [expect]              "r" (expect),
+                  [v]                   "Qo" (*v),
+                  [newv]                "r" (newv),
+                  [v2]                  "Qo" (*v2),
+                  [newv2]               "r" (newv2)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+                                         intptr_t *v2, intptr_t newv2,
+                                         intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+                RSEQ_ASM_OP_STORE(newv2, v2)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [expect]              "r" (expect),
+                  [v]                   "Qo" (*v),
+                  [newv]                "r" (newv),
+                  [v2]                  "Qo" (*v2),
+                  [newv2]               "r" (newv2)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+                              intptr_t *v2, intptr_t expect2,
+                              intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+                RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail])
+                RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+                RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3])
+#endif
+                RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [v]                   "Qo" (*v),
+                  [expect]              "r" (expect),
+                  [v2]                  "Qo" (*v2),
+                  [expect2]             "r" (expect2),
+                  [newv]                "r" (newv)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2, error3
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+error3:
+        rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+                                 void *dst, void *src, size_t len,
+                                 intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+                RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [expect]              "r" (expect),
+                  [v]                   "Qo" (*v),
+                  [newv]                "r" (newv),
+                  [dst]                 "r" (dst),
+                  [src]                 "r" (src),
+                  [len]                 "r" (len)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+                                         void *dst, void *src, size_t len,
+                                         intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+                RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+                RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "Qo" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [expect]              "r" (expect),
+                  [v]                   "Qo" (*v),
+                  [newv]                "r" (newv),
+                  [dst]                 "r" (dst),
+                  [src]                 "r" (src),
+                  [len]                 "r" (len)
+                  RSEQ_INJECT_INPUT
+                : "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
new file mode 100644
index 000000000000..1069e85258ce
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -0,0 +1,513 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#define RSEQ_SIG        0x53053053
+
+#define rseq_smp_mb()   __asm__ __volatile__ ("bcr 15,0" ::: "memory")
+#define rseq_smp_rmb()  rseq_smp_mb()
+#define rseq_smp_wmb()  rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)                                        \
+__extension__ ({                                                        \
+        __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);                       \
+        rseq_barrier();                                                 \
+        ____p1;                                                         \
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()      rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)                                    \
+do {                                                                    \
+        rseq_barrier();                                                 \
+        RSEQ_WRITE_ONCE(*p, v);                                         \
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L                  "lg"
+#define LONG_S                  "stg"
+#define LONG_LT_R               "ltgr"
+#define LONG_CMP                "cg"
+#define LONG_CMP_R              "cgr"
+#define LONG_ADDI               "aghi"
+#define LONG_ADD_R              "agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,                  \
+                                start_ip, post_commit_offset, abort_ip) \
+                ".pushsection __rseq_table, \"aw\"\n\t"                 \
+                ".balign 32\n\t"                                        \
+                __rseq_str(label) ":\n\t"                               \
+                ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+                ".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+                ".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,                  \
+                                start_ip, post_commit_offset, abort_ip) \
+                ".pushsection __rseq_table, \"aw\"\n\t"                 \
+                ".balign 32\n\t"                                        \
+                __rseq_str(label) ":\n\t"                               \
+                ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+                ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+                ".popsection\n\t"
+
+#define LONG_L                  "l"
+#define LONG_S                  "st"
+#define LONG_LT_R               "ltr"
+#define LONG_CMP                "c"
+#define LONG_CMP_R              "cr"
+#define LONG_ADDI               "ahi"
+#define LONG_ADD_R              "ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+        __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,              \
+                                (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)                \
+                RSEQ_INJECT_ASM(1)                                      \
+                "larl %%r0, " __rseq_str(cs_label) "\n\t"               \
+                LONG_S " %%r0, %[" __rseq_str(rseq_cs) "]\n\t"          \
+                __rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)              \
+                RSEQ_INJECT_ASM(2)                                      \
+                "c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+                "jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)             \
+                ".pushsection __rseq_failure, \"ax\"\n\t"               \
+                ".long " __rseq_str(RSEQ_SIG) "\n\t"                    \
+                __rseq_str(label) ":\n\t"                               \
+                teardown                                                \
+                "j %l[" __rseq_str(abort_label) "]\n\t"                 \
+                ".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)         \
+                ".pushsection __rseq_failure, \"ax\"\n\t"               \
+                __rseq_str(label) ":\n\t"                               \
+                teardown                                                \
+                "j %l[" __rseq_str(cmpfail_label) "]\n\t"               \
+                ".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[cmpfail]\n\t"
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[error2]\n\t"
+#endif
+                /* final store */
+                LONG_S " %[newv], %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  [v]                   "m" (*v),
+                  [expect]              "r" (expect),
+                  [newv]                "r" (newv)
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0"
+                  RSEQ_INJECT_CLOBBER
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+                               off_t voffp, intptr_t *load, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                LONG_L " %%r1, %[v]\n\t"
+                LONG_CMP_R " %%r1, %[expectnot]\n\t"
+                "je %l[cmpfail]\n\t"
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                LONG_L " %%r1, %[v]\n\t"
+                LONG_CMP_R " %%r1, %[expectnot]\n\t"
+                "je %l[error2]\n\t"
+#endif
+                LONG_S " %%r1, %[load]\n\t"
+                LONG_ADD_R " %%r1, %[voffp]\n\t"
+                LONG_L " %%r1, 0(%%r1)\n\t"
+                /* final store */
+                LONG_S " %%r1, %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(5)
+                RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  /* final store input */
+                  [v]                   "m" (*v),
+                  [expectnot]           "r" (expectnot),
+                  [voffp]               "r" (voffp),
+                  [load]                "m" (*load)
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0", "r1"
+                  RSEQ_INJECT_CLOBBER
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+                LONG_L " %%r0, %[v]\n\t"
+                LONG_ADD_R " %%r0, %[count]\n\t"
+                /* final store */
+                LONG_S " %%r0, %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(4)
+                RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  /* final store input */
+                  [v]                   "m" (*v),
+                  [count]               "r" (count)
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0"
+                  RSEQ_INJECT_CLOBBER
+                : abort
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+                                 intptr_t *v2, intptr_t newv2,
+                                 intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[cmpfail]\n\t"
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[error2]\n\t"
+#endif
+                /* try store */
+                LONG_S " %[newv2], %[v2]\n\t"
+                RSEQ_INJECT_ASM(5)
+                /* final store */
+                LONG_S " %[newv], %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  /* try store input */
+                  [v2]                  "m" (*v2),
+                  [newv2]               "r" (newv2),
+                  /* final store input */
+                  [v]                   "m" (*v),
+                  [expect]              "r" (expect),
+                  [newv]                "r" (newv)
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0"
+                  RSEQ_INJECT_CLOBBER
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+                                         intptr_t *v2, intptr_t newv2,
+                                         intptr_t newv, int cpu)
+{
+        return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+                              intptr_t *v2, intptr_t expect2,
+                              intptr_t newv, int cpu)
+{
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[cmpfail]\n\t"
+                RSEQ_INJECT_ASM(4)
+                LONG_CMP " %[expect2], %[v2]\n\t"
+                "jnz %l[cmpfail]\n\t"
+                RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz %l[error2]\n\t"
+                LONG_CMP " %[expect2], %[v2]\n\t"
+                "jnz %l[error3]\n\t"
+#endif
+                /* final store */
+                LONG_S " %[newv], %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(6)
+                RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  /* cmp2 input */
+                  [v2]                  "m" (*v2),
+                  [expect2]             "r" (expect2),
+                  /* final store input */
+                  [v]                   "m" (*v),
+                  [expect]              "r" (expect),
+                  [newv]                "r" (newv)
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0"
+                  RSEQ_INJECT_CLOBBER
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2, error3
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("1st expected value comparison failed");
+error3:
+        rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+                                 void *dst, void *src, size_t len,
+                                 intptr_t newv, int cpu)
+{
+        uint64_t rseq_scratch[3];
+
+        RSEQ_INJECT_C(9)
+
+        __asm__ __volatile__ goto (
+                RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+                LONG_S " %[src], %[rseq_scratch0]\n\t"
+                LONG_S " %[dst], %[rseq_scratch1]\n\t"
+                LONG_S " %[len], %[rseq_scratch2]\n\t"
+                /* Start rseq by storing table entry pointer into rseq_cs. */
+                RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+                RSEQ_INJECT_ASM(3)
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz 5f\n\t"
+                RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+                LONG_CMP " %[expect], %[v]\n\t"
+                "jnz 7f\n\t"
+#endif
+                /* try memcpy */
+                LONG_LT_R " %[len], %[len]\n\t"
+                "jz 333f\n\t"
+                "222:\n\t"
+                "ic %%r0,0(%[src])\n\t"
+                "stc %%r0,0(%[dst])\n\t"
+                LONG_ADDI " %[src], 1\n\t"
+                LONG_ADDI " %[dst], 1\n\t"
+                LONG_ADDI " %[len], -1\n\t"
+                "jnz 222b\n\t"
+                "333:\n\t"
+                RSEQ_INJECT_ASM(5)
+                /* final store */
+                LONG_S " %[newv], %[v]\n\t"
+                "2:\n\t"
+                RSEQ_INJECT_ASM(6)
+                /* teardown */
+                LONG_L " %[len], %[rseq_scratch2]\n\t"
+                LONG_L " %[dst], %[rseq_scratch1]\n\t"
+                LONG_L " %[src], %[rseq_scratch0]\n\t"
+                RSEQ_ASM_DEFINE_ABORT(4,
+                        LONG_L " %[len], %[rseq_scratch2]\n\t"
+                        LONG_L " %[dst], %[rseq_scratch1]\n\t"
+                        LONG_L " %[src], %[rseq_scratch0]\n\t",
+                        abort)
+                RSEQ_ASM_DEFINE_CMPFAIL(5,
+                        LONG_L " %[len], %[rseq_scratch2]\n\t"
+                        LONG_L " %[dst], %[rseq_scratch1]\n\t"
+                        LONG_L " %[src], %[rseq_scratch0]\n\t",
+                        cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+                RSEQ_ASM_DEFINE_CMPFAIL(6,
+                        LONG_L " %[len], %[rseq_scratch2]\n\t"
+                        LONG_L " %[dst], %[rseq_scratch1]\n\t"
+                        LONG_L " %[src], %[rseq_scratch0]\n\t",
+                        error1)
+                RSEQ_ASM_DEFINE_CMPFAIL(7,
+                        LONG_L " %[len], %[rseq_scratch2]\n\t"
+                        LONG_L " %[dst], %[rseq_scratch1]\n\t"
+                        LONG_L " %[src], %[rseq_scratch0]\n\t",
+                        error2)
+#endif
+                : /* gcc asm goto does not allow outputs */
+                : [cpu_id]              "r" (cpu),
+                  [current_cpu_id]      "m" (__rseq_abi.cpu_id),
+                  [rseq_cs]             "m" (__rseq_abi.rseq_cs),
+                  /* final store input */
+                  [v]                   "m" (*v),
+                  [expect]              "r" (expect),
+                  [newv]                "r" (newv),
+                  /* try memcpy input */
+                  [dst]                 "r" (dst),
+                  [src]                 "r" (src),
+                  [len]                 "r" (len),
+                  [rseq_scratch0]       "m" (rseq_scratch[0]),
+                  [rseq_scratch1]       "m" (rseq_scratch[1]),
+                  [rseq_scratch2]       "m" (rseq_scratch[2])
+                  RSEQ_INJECT_INPUT
+                : "memory", "cc", "r0"
+                  RSEQ_INJECT_CLOBBER
+                : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+                  , error1, error2
+#endif
+        );
+        return 0;
+abort:
+        RSEQ_INJECT_FAILED
+        return -1;
+cmpfail:
+        return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+        rseq_bug("cpu_id comparison failed");
+error2:
+        rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+                                         void *dst, void *src, size_t len,
+                                         intptr_t newv, int cpu)
+{
+        return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+                                            newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 86ce22417e0d..c72eb70f9b52 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -71,10 +71,14 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-x86.h>
 #elif defined(__ARMEL__)
 #include <rseq-arm.h>
+#elif defined (__AARCH64EL__)
+#include <rseq-arm64.h>
 #elif defined(__PPC__)
 #include <rseq-ppc.h>
 #elif defined(__mips__)
 #include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
 #else
 #error unsupported target
 #endif
diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index 3a0336782d2d..49a6f8c3fdae 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -17,6 +17,10 @@ REQUIREMENTS
 *  The kernel must have veth support available, as a veth pair is created
    prior to running the tests.
 
+*  The kernel must have the appropriate infrastructure enabled to run all tdc
+   unit tests. See the config file in this directory for minimum required
+   features. As new tests will be added, config options list will be updated.
+
 *  All tc-related features being tested must be built in or available as
    modules.  To check what is required in current setup run:
    ./tdc.py -c
@@ -109,8 +113,8 @@ COMMAND LINE ARGUMENTS
 Run tdc.py -h to see the full list of available arguments.
 
 usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]]
-              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v]
-              [-d DEVICE] [-n NS] [-V]
+              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] [-N]
+              [-d DEVICE] [-P] [-n] [-V]
 
 Linux TC unit tests
 
@@ -118,8 +122,10 @@ optional arguments:
   -h, --help            show this help message and exit
   -p PATH, --path PATH  The full path to the tc executable to use
   -v, --verbose         Show the commands that are being run
+  -N, --notap           Suppress tap results for command under test
   -d DEVICE, --device DEVICE
                         Execute the test case in flower category
+  -P, --pause           Pause execution just before post-suite stage
 
 selection:
   select which test cases: files plus directories; filtered by categories
@@ -146,10 +152,10 @@ action:
   -i, --id              Generate ID numbers for new test cases
 
 netns:
-  options for nsPlugin(run commands in net namespace)
+  options for nsPlugin (run commands in net namespace)
 
-  -n NS, --namespace NS
-                        Run commands in namespace NS
+  -n, --namespace
+                        Run commands in namespace as specified in tdc_config.py
 
 valgrind:
   options for valgrindPlugin (run command under test under Valgrind)
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
new file mode 100644
index 000000000000..203302065458
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/config
@@ -0,0 +1,48 @@
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_INGRESS=m
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_CLS_U32_PERF=y
+CONFIG_CLS_U32_MARK=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+CONFIG_NET_EMATCH_CMP=m
+CONFIG_NET_EMATCH_NBYTE=m
+CONFIG_NET_EMATCH_U32=m
+CONFIG_NET_EMATCH_META=m
+CONFIG_NET_EMATCH_TEXT=m
+CONFIG_NET_EMATCH_IPSET=m
+CONFIG_NET_EMATCH_IPT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_GACT_PROB=y
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_SAMPLE=m
+CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_ACT_SIMP=m
+CONFIG_NET_ACT_SKBEDIT=m
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_BPF=m
+CONFIG_NET_ACT_CONNMARK=m
+CONFIG_NET_ACT_SKBMOD=m
+CONFIG_NET_ACT_IFE=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_IFE_SKBMARK=m
+CONFIG_NET_IFE_SKBPRIO=m
+CONFIG_NET_IFE_SKBTCINDEX=m
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_SCH_FIFO=y
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 70952bd98ff9..13147a1f5731 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -17,7 +17,7 @@
         "cmdUnderTest": "$TC actions add action connmark",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pipe",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pipe",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -41,7 +41,7 @@
         "cmdUnderTest": "$TC actions add action connmark pass index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pass.*index 1 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 1 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -65,7 +65,7 @@
         "cmdUnderTest": "$TC actions add action connmark drop index 100",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 100",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 drop.*index 100 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 drop.*index 100 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -89,7 +89,7 @@
         "cmdUnderTest": "$TC actions add action connmark pipe index 455",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 455",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pipe.*index 455 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pipe.*index 455 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -113,7 +113,7 @@
         "cmdUnderTest": "$TC actions add action connmark reclassify index 7",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 reclassify.*index 7 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 reclassify.*index 7 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -137,7 +137,7 @@
         "cmdUnderTest": "$TC actions add action connmark continue index 17",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 continue.*index 17 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 continue.*index 17 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -161,7 +161,7 @@
         "cmdUnderTest": "$TC actions add action connmark jump 10 index 17",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 jump 10.*index 17 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 jump 10.*index 17 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -185,7 +185,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 100 pipe index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 100 pipe.*index 1 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 100 pipe.*index 1 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -209,7 +209,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 65536 reclassify index 21",
         "expExitCode": "255",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 65536 reclassify.*index 21 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 65536 reclassify.*index 21 ref",
         "matchCount": "0",
         "teardown": [
             "$TC actions flush action connmark"
@@ -233,7 +233,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 655 unsupp_arg pass index 2",
         "expExitCode": "255",
         "verifyCmd": "$TC actions get action connmark index 2",
-        "matchPattern": "action order [0-9]+:  connmark zone 655 unsupp_arg pass.*index 2 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 655 unsupp_arg pass.*index 2 ref",
         "matchCount": "0",
         "teardown": [
             "$TC actions flush action connmark"
@@ -258,7 +258,7 @@
         "cmdUnderTest": "$TC actions replace action connmark zone 555 reclassify index 555",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 555",
-        "matchPattern": "action order [0-9]+:  connmark zone 555 reclassify.*index 555 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 555 reclassify.*index 555 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -282,7 +282,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 555 pipe index 5 cookie aabbccddeeff112233445566778800a1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 5",
-        "matchPattern": "action order [0-9]+:  connmark zone 555 pipe.*index 5 ref.*cookie aabbccddeeff112233445566778800a1",
+        "matchPattern": "action order [0-9]+: connmark zone 555 pipe.*index 5 ref.*cookie aabbccddeeff112233445566778800a1",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index 3a2f51fc7fd4..a022792d392a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -336,6 +336,30 @@
         ]
     },
     {
+        "id": "b10b",
+        "name": "Add all 7 csum actions",
+        "category": [
+            "actions",
+            "csum"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action csum",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action csum icmp ip4h sctp igmp udplite udp tcp index 7",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action csum index 7",
+        "matchPattern": "action order [0-9]*: csum \\(iph, icmp, igmp, tcp, udp, udplite, sctp\\).*index 7 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action csum"
+        ]
+    },
+    {
         "id": "ce92",
         "name": "Add csum udp action with cookie",
         "category": [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index 6e4edfae1799..db49fd0f8445 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -44,7 +44,8 @@
         "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
         "matchCount": "1",
         "teardown": [
-            "$TC actions flush action mirred"
+            "$TC actions flush action mirred",
+            "$TC actions flush action gact"
         ]
     },
     {
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
new file mode 100644
index 000000000000..0080dc2fd41c
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -0,0 +1,593 @@
+[
+    {
+        "id": "7565",
+        "name": "Add nat action on ingress with default control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.1.1 200.200.200.1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.1.1/32 200.200.200.1 pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "fd79",
+        "name": "Add nat action on ingress with pipe control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 2.2.2.1 pipe index 77",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 77",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 2.2.2.1 pipe.*index 77 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "eab9",
+        "name": "Add nat action on ingress with continue control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.10.10 192.168.20.20 continue index 1000",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1000",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.10.10/32 192.168.20.20 continue.*index 1000 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "c53a",
+        "name": "Add nat action on ingress with reclassify control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.10.10 192.168.20.20 reclassify index 1000",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1000",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.10.10/32 192.168.20.20 reclassify.*index 1000 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "76c9",
+        "name": "Add nat action on ingress with jump control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 12.18.10.10 12.18.20.20 jump 10 index 22",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 22",
+        "matchPattern": "action order [0-9]+:  nat ingress 12.18.10.10/32 12.18.20.20 jump 10.*index 22 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "24c6",
+        "name": "Add nat action on ingress with drop control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 722",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 722",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 722 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "2120",
+        "name": "Add nat action on ingress with maximum index value",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 4294967295",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 pass.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "3e9d",
+        "name": "Add nat action on ingress with invalid index value",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 index 4294967295555",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 4294967295555",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 pass.*index 4294967295555 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "f6c9",
+        "name": "Add nat action on ingress with invalid IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 1.1888.2.2 index 7",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 7",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 1.1888.2.2 pass.*index 7 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "be25",
+        "name": "Add nat action on ingress with invalid argument",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 1.18.2.2 another_arg index 12",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 1.18.2.2 pass.*another_arg.*index 12 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "a7bd",
+        "name": "Add nat action on ingress with DEFAULT IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress default 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "ee1e",
+        "name": "Add nat action on ingress with ANY IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress any 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "1de8",
+        "name": "Add nat action on ingress with ALL IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress all 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "8dba",
+        "name": "Add nat action on egress with default control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "19a7",
+        "name": "Add nat action on egress with pipe control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "f1d9",
+        "name": "Add nat action on egress with continue control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "6d4a",
+        "name": "Add nat action on egress with reclassify control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "b313",
+        "name": "Add nat action on egress with jump control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 jump 777",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 jump 777",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "d9fc",
+        "name": "Add nat action on egress with drop control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "a895",
+        "name": "Add nat action on egress with DEFAULT IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress default 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "2572",
+        "name": "Add nat action on egress with ANY IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress any 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "37f3",
+        "name": "Add nat action on egress with ALL IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "6054",
+        "name": "Add nat action on egress with cookie",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10 cookie aa1bc2d3eeff112233445566778800a1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "79d6",
+        "name": "Add nat action on ingress with cookie",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.1.1 10.10.10.1 reclassify index 1 cookie 112233445566778899aabbccddeeff11",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.1.1/32 10.10.10.1 reclassify.*index 1 ref.*cookie 112233445566778899aabbccddeeff11",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 37ecc2716fee..5aaf593b914a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -17,7 +17,7 @@
         "cmdUnderTest": "$TC actions add action skbedit mark 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 1",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -65,7 +65,7 @@
         "cmdUnderTest": "$TC actions add action skbedit prio 99",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority :99",
+        "matchPattern": "action order [0-9]*: skbedit  priority :99",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -113,7 +113,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 909",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -161,7 +161,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype host",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -185,7 +185,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
+        "matchPattern": "action order [0-9]*: skbedit  ptype otherhost",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -233,7 +233,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype host pipe index 11",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 11",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host pipe.*index 11 ref",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host pipe.*index 11 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -257,7 +257,7 @@
         "cmdUnderTest": "$TC actions add action skbedit mark 56789 reclassify index 90",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 90",
-        "matchPattern": "action order [0-9]*:  skbedit mark 56789 reclassify.*index 90 ref",
+        "matchPattern": "action order [0-9]*: skbedit  mark 56789 reclassify.*index 90 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -281,7 +281,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 3 pass index 271",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 271",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 3 pass.*index 271 ref",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 3 pass.*index 271 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -305,7 +305,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 3 drop index 271",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 271",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 3 drop.*index 271 ref",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 3 drop.*index 271 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -329,7 +329,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 8 jump 9 index 2",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 2",
-        "matchPattern": "action order [0-9]*:  skbedit priority :8 jump 9.*index 2 ref",
+        "matchPattern": "action order [0-9]*: skbedit  priority :8 jump 9.*index 2 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -353,7 +353,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 16 continue index 32",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 32",
-        "matchPattern": "action order [0-9]*:  skbedit priority :16 continue.*index 32 ref",
+        "matchPattern": "action order [0-9]*: skbedit  priority :16 continue.*index 32 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -377,7 +377,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 16 continue index 32 cookie deadbeef",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 32",
-        "matchPattern": "action order [0-9]*:  skbedit priority :16 continue.*index 32 ref.*cookie deadbeef",
+        "matchPattern": "action order [0-9]*: skbedit  priority :16 continue.*index 32 ref.*cookie deadbeef",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -405,7 +405,7 @@
         "cmdUnderTest": "$TC actions list action skbedit",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchPattern": "action order [0-9]*: skbedit",
         "matchCount": "4",
         "teardown": [
             "$TC actions flush action skbedit"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
new file mode 100644
index 000000000000..10b2d894e436
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -0,0 +1,917 @@
+[
+    {
+        "id": "2b11",
+        "name": "Add tunnel_key set action with mandatory parameters",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "dc6b",
+        "name": "Add tunnel_key set action with missing mandatory src_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set dst_ip 20.20.20.2 id 100",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*dst_ip 20.20.20.2.*key_id 100",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "7f25",
+        "name": "Add tunnel_key set action with missing mandatory dst_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 id 100",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*key_id 100",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "ba4e",
+        "name": "Add tunnel_key set action with missing mandatory id parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "a5e0",
+        "name": "Add tunnel_key set action with invalid src_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 300.168.100.1 dst_ip 192.168.200.1 id 7 index 1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 300.168.100.1.*dst_ip 192.168.200.1.*key_id 7.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "eaa8",
+        "name": "Add tunnel_key set action with invalid dst_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.800.1 id 10 index 11",
+        "expExitCode": "1",
+        "verifyCmd": "$TC actions get action tunnel_key index 11",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 192.168.100.1.*dst_ip 192.168.800.1.*key_id 10.*index 11 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "3b09",
+        "name": "Add tunnel_key set action with invalid id parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 112233445566778899 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 112233445566778899.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "9625",
+        "name": "Add tunnel_key set action with invalid dst_port parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 dst_port 998877 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 11.*dst_port 998877.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "05af",
+        "name": "Add tunnel_key set action with optional dst_port parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.200.1 id 789 dst_port 4000 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 10",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.100.1.*dst_ip 192.168.200.1.*key_id 789.*dst_port 4000.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "da80",
+        "name": "Add tunnel_key set action with index at 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*id 11.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "d407",
+        "name": "Add tunnel_key set action with index exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295678",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295678",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*index 4294967295678 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "5cba",
+        "name": "Add tunnel_key set action with id value at 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 4294967295 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 4294967295.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "e84a",
+        "name": "Add tunnel_key set action with id value exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42949672955 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42949672955.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "9c19",
+        "name": "Add tunnel_key set action with dst_port value at 16-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "3bd9",
+        "name": "Add tunnel_key set action with dst_port value exceeding 16-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535789 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535789.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "68e2",
+        "name": "Add tunnel_key unset action",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key unset index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*unset.*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "6192",
+        "name": "Add tunnel_key unset continue action",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key unset continue index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*unset continue.*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "061d",
+        "name": "Add tunnel_key set continue action with cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "8acb",
+        "name": "Add tunnel_key set continue action with invalid cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "a07e",
+        "name": "Add tunnel_key action with no set/unset command specified",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "b227",
+        "name": "Add tunnel_key action with csum option",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1 csum index 99",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 99",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*csum pipe.*index 99",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "58a7",
+        "name": "Add tunnel_key action with nocsum option",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7823 nocsum index 234",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 234",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7823.*nocsum pipe.*index 234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "2575",
+        "name": "Add tunnel_key action with not-supported parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 foobar 999 index 4",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*foobar 999.*index 4",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "7a88",
+        "name": "Add tunnel_key action with cookie parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 index 4 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 4",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*dst_port 0.*csum pipe.*index 4 ref.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "4f20",
+        "name": "Add tunnel_key action with a single geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "e33d",
+        "name": "Add tunnel_key action with multiple geneve options parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "0778",
+        "name": "Add tunnel_key action with invalid class geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 824212:80:00880022 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 824212:80:00880022.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "4ae8",
+        "name": "Add tunnel_key action with invalid type geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:4224:00880022 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:4224:00880022.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "4039",
+        "name": "Add tunnel_key action with short data length geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "26a6",
+        "name": "Add tunnel_key action with non-multiple of 4 data length geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288428822 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288428822.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "f44d",
+        "name": "Add tunnel_key action with incomplete geneve options parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42: index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "7afc",
+        "name": "Replace tunnel_key set action with all parameters",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 csum id 1 index 1"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 nocsum id 11 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*nocsum pipe.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "364d",
+        "name": "Replace tunnel_key set action with all parameters and cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie aabbccddeeff112233445566778800a"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie a1b1c1d1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie a1b1c1d1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "937c",
+        "name": "Fetch all existing tunnel_key actions",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+            "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 jump 10 index 2",
+            "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+            "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+        ],
+        "cmdUnderTest": "$TC actions list action tunnel_key",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*nocsum pipe.*index 1.*set.*src_ip 11.10.10.1.*dst_ip 21.20.20.2.*key_id 2.*dst_port 3129.*csum jump 10.*index 2.*set.*src_ip 12.10.10.1.*dst_ip 22.20.20.2.*key_id 3.*dst_port 3130.*csum pass.*index 3.*set.*src_ip 13.10.10.1.*dst_ip 23.20.20.2.*key_id 4.*dst_port 3131.*nocsum continue.*index 4",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "6783",
+        "name": "Flush all existing tunnel_key actions",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+            "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 reclassify index 2",
+            "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+            "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+        ],
+        "cmdUnderTest": "$TC actions flush action tunnel_key",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+:.*",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
new file mode 100644
index 000000000000..3b97cfd7e0f8
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
@@ -0,0 +1,1049 @@
+[
+    {
+        "id": "901f",
+        "name": "Add fw filter with prio at 32-bit maxixum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 65535 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65535 protocol all fw",
+        "matchPattern": "pref 65535 fw.*handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "51e2",
+        "name": "Add fw filter with prio exceeding 32-bit maxixum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 65536 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65536 protocol all fw",
+        "matchPattern": "pref 65536 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d987",
+        "name": "Add fw filter with action ok",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "affe",
+        "name": "Add fw filter with action continue",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "28bc",
+        "name": "Add fw filter with action pipe",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8da2",
+        "name": "Add fw filter with action drop",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol all prio 1 fw",
+        "matchPattern": "handle 0x1.*gact action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9436",
+        "name": "Add fw filter with action reclassify",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "95bb",
+        "name": "Add fw filter with action jump 10",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action jump 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action jump 10",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3d74",
+        "name": "Add fw filter with action goto chain 5",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action goto chain 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action goto chain 5",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "eb8f",
+        "name": "Add fw filter with invalid action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action pump",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pump",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6a79",
+        "name": "Add fw filter with missing mandatory action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "filter protocol all pref [0-9]+ fw.*handle 0x1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8298",
+        "name": "Add fw filter with cookie",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 2 protocol all fw",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pipe.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "a88c",
+        "name": "Add fw filter with invalid cookie",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action continue cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 2 protocol all fw",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action continue.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "10f6",
+        "name": "Add fw filter with handle in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xa1b2ff prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xa1b2ff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa1b2ff.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9d51",
+        "name": "Add fw filter with handle at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4294967295 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xffffffff.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d939",
+        "name": "Add fw filter with handle exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4294967296 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "658c",
+        "name": "Add fw filter with mask in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/0xa1b2f prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa/0xa1b2f",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "86be",
+        "name": "Add fw filter with mask at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa[^/]",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "e635",
+        "name": "Add fw filter with mask exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6cab",
+        "name": "Add fw filter with handle/mask in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xa1b2cdff/0x1a2bffdc prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xa1b2cdff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa1b2cdff/0x1a2bffdc",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8700",
+        "name": "Add fw filter with handle/mask at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967295/4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xffffffff[^/]",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7d62",
+        "name": "Add fw filter with handle/mask exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967296/4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7b69",
+        "name": "Add fw filter with missing mandatory handle",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 1 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "filter protocol all.*fw.*handle.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d68b",
+        "name": "Add fw filter with invalid parent",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent aa11b1b2: handle 1 prio 1 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter dev $DEV1 parent aa11b1b2: handle 1 prio 1 protocol all fw",
+        "matchPattern": "filter protocol all pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "66e0",
+        "name": "Add fw filter with missing mandatory parent id",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 handle 1 prio 1 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "pref [0-9]+ fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0ff3",
+        "name": "Add fw filter with classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 3 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid :3.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9849",
+        "name": "Add fw filter with classid at root",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid ffff:ffff action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "pref 1 fw.*handle 0x1 classid root.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "b7ff",
+        "name": "Add fw filter with classid - keeps last 8 (hex) digits",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 98765fedcb action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid 765f:edcb.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "2b18",
+        "name": "Add fw filter with invalid classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 6789defg action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid 6789:defg.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "fade",
+        "name": "Add fw filter with flowid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10 prio 1 fw flowid 1:10 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xa classid 1:10.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "33af",
+        "name": "Add fw filter with flowid then classid (same arg, takes second)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 11 prio 1 fw flowid 10 classid 4 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 11 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xb classid :4.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8a8c",
+        "name": "Add fw filter with classid then flowid (same arg, takes second)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 11 prio 1 fw classid 4 flowid 10 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 11 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xb classid :10.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "b50d",
+        "name": "Add fw filter with handle val/mask and flowid 10:1000",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 10/0xff fw flowid 10:1000 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0xa/0xff classid 10:1000.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7207",
+        "name": "Add fw filter with protocol ip",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 handle 3 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 3 prio 1 protocol ip fw",
+        "matchPattern": "filter parent ffff: protocol ip pref 1 fw.*handle 0x3.*gact action pass.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "306d",
+        "name": "Add fw filter with protocol ipv6",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ipv6 prio 2 handle 4 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 2 protocol ipv6 fw",
+        "matchPattern": "filter parent ffff: protocol ipv6 pref 2 fw.*handle 0x4.*gact action pass.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9a78",
+        "name": "Add fw filter with protocol arp",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol arp prio 5 handle 7 fw action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 7 prio 5 protocol arp fw",
+        "matchPattern": "filter parent ffff: protocol arp pref 5 fw.*handle 0x7.*gact action drop.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "1821",
+        "name": "Add fw filter with protocol 802_3",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol 802_3 handle 1 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol 802_3 fw",
+        "matchPattern": "filter parent ffff: protocol 802_3 pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "2260",
+        "name": "Add fw filter with invalid protocol",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol igmp handle 1 prio 1 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol igmp fw",
+        "matchPattern": "filter parent ffff: protocol igmp pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "09d7",
+        "name": "Add fw filters protocol 802_3 and ip with conflicting priorities",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: protocol 802_3 prio 3 handle 7 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 3 handle 8 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 8 prio 3 protocol ip fw",
+        "matchPattern": "filter parent ffff: protocol ip pref 3 fw.*handle 0x8",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6973",
+        "name": "Add fw filters with same index, same action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: prio 6 handle 2 fw action continue index 5"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 8 handle 4 fw action continue index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 8 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 8 fw.*handle 0x4.*gact action continue.*index 5 ref 2 bind 2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "fc06",
+        "name": "Add fw filters with action police",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 4 fw action police rate 1kbit burst 10k index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0x4.*police 0x5 rate 1Kbit burst 10Kb mtu 2Kb action reclassify overhead 0b.*ref 1 bind 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "aac7",
+        "name": "Add fw filters with action police linklayer atm",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 4 fw action police rate 2mbit burst 200k linklayer atm index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0x4.*police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm.*ref 1 bind 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "5339",
+        "name": "Del entire fw filter",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff:",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref.*handle.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0e99",
+        "name": "Del single fw filter x1",
+        "__comment__": "First of two tests to check that one filter is there and the other isn't",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 prio 9 fw action pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref 7.*handle 0x5.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "f54c",
+        "name": "Del single fw filter x2",
+        "__comment__": "Second of two tests to check that one filter is there and the other isn't",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 prio 9 fw action pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref 9.*handle 0x3.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "ba94",
+        "name": "Del fw filter by prio",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 4 fw action ok",
+            "$TC filter add dev $DEV1 parent ffff: handle 2 prio 4 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: prio 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 4 fw.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4acb",
+        "name": "Del fw filter by chain",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 chain 13 fw action pipe",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 5 chain 13 fw action pipe"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: chain 13",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "fw chain 13 handle.*gact action pipe",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3424",
+        "name": "Del fw filter by action (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 2 prio 4 fw action drop"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: fw action drop",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 2 prio 4 protocol all fw",
+        "matchPattern": "handle 0x2.*gact action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "da89",
+        "name": "Del fw filter by handle (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 4 fw action continue"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 3 prio 4 protocol all fw",
+        "matchPattern": "handle 0x3.*gact action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4d95",
+        "name": "Del fw filter by protocol (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 protocol arp fw action pipe"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol arp fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 2 protocol arp fw",
+        "matchPattern": "filter parent ffff: protocol arp.*handle 0x4.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4736",
+        "name": "Del fw filter by flowid (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 fw action pipe flowid 45"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: fw flowid 45",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "handle 0x4.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3dcb",
+        "name": "Replace fw filter action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "eb4d",
+        "name": "Replace fw filter classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe classid 2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1 classid :2.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "67ec",
+        "name": "Replace fw filter index",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok index 3"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action ok index 16",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pass.*index 16",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 5fa02d86b35f..99a5ffca1088 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -12,8 +12,8 @@
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok",
         "expExitCode": "0",
         "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
-        "matchPattern": "match 7f000002/ffffffff at 12",
-        "matchCount": "0",
+        "matchPattern": "match 7f000001/ffffffff at 12",
+        "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index ca6cd146aafe..dcf73c5dab6e 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -134,6 +134,11 @@ int main(int argv, char **argc)
         printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000)));
 
         if (llabs(eppm - ppm) > 1000) {
+                if (tx1.offset || tx2.offset ||
+                    tx1.freq != tx2.freq || tx1.tick != tx2.tick) {
+                        printf("        [SKIP]\n");
+                        return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n");
+                }
                 printf("        [FAILED]\n");
                 return ksft_exit_fail();
         }