If CONFIG_INET is not set, building fails:

kernel/bpf/verifier.o: In function `check_mem_access':
verifier.c: undefined reference to `bpf_xdp_sock_is_valid_access'
kernel/bpf/verifier.o: In function `convert_ctx_accesses':
verifier.c: undefined reference to `bpf_xdp_sock_convert_ctx_access'
Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: fada7fdc ("bpf: Allow bpf_map_lookup_elem() on an xskmap")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

This lets us test that both BPF_PROG_TYPE_CGROUP_SOCK_ADDR and
BPF_PROG_TYPE_SOCK_OPS can access underlying bpf_sock.

Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Add sk to struct bpf_sock_addr and struct bpf_sock_ops.

Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

And let it use bpf_sk_storage_{get,delete} helpers to access socket
storage. Kernel context (struct bpf_sock_ops_kern) already has sk
member, so I just expose it to the BPF hooks. I use
PTR_TO_SOCKET_OR_NULL and return NULL in !is_fullsock case.

I also export bpf_tcp_sock to make it possible to access tcp socket stats.

Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

And let it use bpf_sk_storage_{get,delete} helpers to access socket
storage. Kernel context (struct bpf_sock_addr_kern) already has sk
member, so I just expose it to the BPF hooks. Using PTR_TO_SOCKET
instead of PTR_TO_SOCK_COMMON should be safe because the hook is
called on bind/connect.

Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

This patch adds a test for the new sockopt SO_REUSEPORT_DETACH_BPF.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

SO_DETACH_REUSEPORT_BPF is needed for the test in the next patch.
It is defined in the socket.h.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

There is SO_ATTACH_REUSEPORT_[CE]BPF but there is no DETACH.
This patch adds SO_DETACH_REUSEPORT_BPF sockopt.  The same
sockopt can be used to undo both SO_ATTACH_REUSEPORT_[CE]BPF.

reseport_detach_prog() is added and it is mostly a mirror
of the existing reuseport_attach_prog().  The differences are,
it does not call reuseport_alloc() and returns -ENOENT when
there is no old prog.

Cc: Craig Gallek <kraig@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Kernel internally checks that either key or value type ID is specified,
before using btf_fd. Do the same in libbpf's map creation code for
determining when to retry map creation w/o BTF.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: fba01a06 ("libbpf: use negative fd to specify missing BTF")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

The "len" variable needs to be signed for the error handling to work
properly.

Fixes: 596092ef ("selftests/bpf: enable all available cgroup v2 controllers")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Recent commit included libbpf.h in selftests/bpf/bpf_util.h.
Since some samples use bpf_util.h and samples/bpf/Makefile doesn't
have libbpf.h path included, build was failing. Let's add the path
in samples/bpf/Makefile.
Signed-off-by: Prashant Bhole <prashantbhole.linux@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Compiling kernel/bpf/core.c with W=1 causes a flood of warnings:

kernel/bpf/core.c:1198:65: warning: initialized field overwritten [-Woverride-init]
 1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
      |                                                                 ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
 1087 |  INSN_3(ALU, ADD,  X),   \
      |  ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
 1202 |   BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
      |   ^~~~~~~~~~~~
kernel/bpf/core.c:1198:65: note: (near initialization for 'public_insntable[12]')
 1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
      |                                                                 ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
 1087 |  INSN_3(ALU, ADD,  X),   \
      |  ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
 1202 |   BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
      |   ^~~~~~~~~~~~

98 copies of the above.

The attached patch silences the warnings, because we *know* we're overwriting
the default initializer. That leaves bpf/core.c with only 6 other warnings,
which become more visible in comparison.
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Hechao Li says:

====================
Getting number of possible CPUs is commonly used for per-CPU BPF maps
and perf_event_maps. Add a new API libbpf_num_possible_cpus() that
helps user with per-CPU related operations and remove duplicate
implementations in bpftool and selftests.

v2: Save errno before calling pr_warning in case it is changed.
v3: Make sure libbpf_num_possible_cpus never returns 0 so that user only
    has to check if ret value < 0.
v4: Fix error code when reading 0 bytes from possible CPU file.
v5: Fix selftests compliation issue.
v6: Split commit to reuse libbpf_num_possible_cpus() into two commits:
    One commit to remove bpf_util.h from test BPF C programs.
    One commit to reuse libbpf_num_possible_cpus() in bpftools
    and bpf_util.h.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Use the newly added bpf_num_possible_cpus() in bpftool and selftests
and remove duplicate implementations.
Signed-off-by: Hechao Li <hechaol@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Though currently there is no problem including bpf_util.h in kernel
space BPF C programs, in next patch in this stack, I will reuse
libbpf_num_possible_cpus() in bpf_util.h thus include libbpf.h in it,
which will cause BPF C programs compile error. Therefore I will first
remove bpf_util.h from all test BPF programs.

This can also make it clear that bpf_util.h is a user-space utility
while bpf_helpers.h is a kernel space utility.
Signed-off-by: Hechao Li <hechaol@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Adding a new API libbpf_num_possible_cpus() that helps user with
per-CPU map operations.
Signed-off-by: Hechao Li <hechaol@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

An error "implicit declaration of function 'reallocarray'" can be thrown
with the following steps:

$ cd tools/testing/selftests/bpf
$ make clean && make CC=<Path to GCC 4.8.5>
$ make clean && make CC=<Path to GCC 7.x>

The cause is that the feature folder generated by GCC 4.8.5 is not
removed, leaving feature-reallocarray being 1, which causes reallocarray
not defined when re-compliing with GCC 7.x. This diff adds feature
folder to EXTRA_CLEAN to avoid this problem.

v2: Rephrase the commit message.
Signed-off-by: Hechao Li <hechaol@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Fix signature of bpf_probe_read and bpf_probe_write_user to mark source
pointer as const. This causes warnings during compilation for
applications relying on those helpers.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Quentin reports that commit 07c3bbdb ("samples: bpf: print
a warning about headers_install") is producing the false
positive when make is invoked locally, from the samples/bpf/
directory.

When make is run locally it hits the "all" target, which
will recursively invoke make through the full build system.

Speed up the "local" run which doesn't actually build anything,
and avoid false positives by skipping all the probes if not in
kbuild environment (cover both the new warning and the BTF
probes).
Reported-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Jonathan Lemon says:

====================
Currently, the AF_XDP code uses a separate map in order to
determine if an xsk is bound to a queue.  Have the xskmap
lookup return a XDP_SOCK pointer on the kernel side, which
the verifier uses to extract relevant values.

Patches:
 1 - adds XSK_SOCK type
 2 - sync bpf.h with tools
 3 - add tools selftest
 4 - update lib/bpf, removing qidconf

v4->v5:
 - xskmap lookup now returns XDP_SOCK type instead of pointer to element.
 - no changes lib/bpf/xsk.c

v3->v4:
 - Clarify error handling path.

v2->v3:
 - Use correct map type.
====================
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Use the recent change to XSKMAP bpf_map_lookup_elem() to test if
there is a xsk present in the map instead of duplicating the work
with qidconf.

Fix things so callers using XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD
bypass any internal bpf maps, so xsk_socket__{create|delete} works
properly.

Clean up error handling path.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Song Liu <songliubraving@fb.com>
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Check that bpf_map_lookup_elem lookup and structure
access operats correctly.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Sync uapi/linux/bpf.h
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Currently, the AF_XDP code uses a separate map in order to
determine if an xsk is bound to a queue.  Instead of doing this,
have bpf_map_lookup_elem() return a xdp_sock.

Rearrange some xdp_sock members to eliminate structure holes.

Remove selftest - will be added back in later patch.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Currently bpf_skb_cgroup_id() is not supported for CGROUP_SKB
programs. An attempt to load such a program generates an error
like this:

    libbpf:
    0: (b7) r6 = 0
    ...
    9: (85) call bpf_skb_cgroup_id#79
    unknown func bpf_skb_cgroup_id#79

There are no particular reasons for denying it, and we have some
use cases where it might be useful.

So let's add it to the list of allowed helpers.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

It seems like periodically someone posts patches to "fix"
header includes.  The issue is that samples expect the
include path to have the uAPI headers (from usr/) first,
and then tools/ headers, so that locally installed uAPI
headers take precedence.  This means that if users didn't
run headers_install they will see all sort of strange
compilation errors, e.g.:

  HOSTCC  samples/bpf/test_lru_dist
  samples/bpf/test_lru_dist.c:39:8: error: redefinition of ‘struct list_head’
   struct list_head {
          ^~~~~~~~~
   In file included from samples/bpf/test_lru_dist.c:9:0:
   ../tools/include/linux/types.h:69:8: note: originally defined here
    struct list_head {
           ^~~~~~~~~

Try to detect this situation, and print a helpful warning.

v2: just use HOSTCC (Jiong).
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

The variable err is assigned with the value -EINVAL that is never
read and it is re-assigned a new value later on.  The assignment is
redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

There is a spelling mistake in the help information, fix this.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-05-31

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

Lots of exciting new features in the first PR of this developement cycle!
The main changes are:

1) misc verifier improvements, from Alexei.

2) bpftool can now convert btf to valid C, from Andrii.

3) verifier can insert explicit ZEXT insn when requested by 32-bit JITs.
   This feature greatly improves BPF speed on 32-bit architectures. From Jiong.

4) cgroups will now auto-detach bpf programs. This fixes issue of thousands
   bpf programs got stuck in dying cgroups. From Roman.

5) new bpf_send_signal() helper, from Yonghong.

6) cgroup inet skb programs can signal CN to the stack, from Lawrence.

7) miscellaneous cleanups, from many developers.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

xdping allows us to get latency estimates from XDP.  Output looks
like this:

./xdping -I eth4 192.168.55.8
Setting up XDP for eth4, please wait...
XDP setup disrupts network connectivity, hit Ctrl+C to quit

Normal ping RTT data
[Ignore final RTT; it is distorted by XDP using the reply]
PING 192.168.55.8 (192.168.55.8) from 192.168.55.7 eth4: 56(84) bytes of data.
64 bytes from 192.168.55.8: icmp_seq=1 ttl=64 time=0.302 ms
64 bytes from 192.168.55.8: icmp_seq=2 ttl=64 time=0.208 ms
64 bytes from 192.168.55.8: icmp_seq=3 ttl=64 time=0.163 ms
64 bytes from 192.168.55.8: icmp_seq=8 ttl=64 time=0.275 ms

4 packets transmitted, 4 received, 0% packet loss, time 3079ms
rtt min/avg/max/mdev = 0.163/0.237/0.302/0.054 ms

XDP RTT data:
64 bytes from 192.168.55.8: icmp_seq=5 ttl=64 time=0.02808 ms
64 bytes from 192.168.55.8: icmp_seq=6 ttl=64 time=0.02804 ms
64 bytes from 192.168.55.8: icmp_seq=7 ttl=64 time=0.02815 ms
64 bytes from 192.168.55.8: icmp_seq=8 ttl=64 time=0.02805 ms

The xdping program loads the associated xdping_kern.o BPF program
and attaches it to the specified interface.  If run in client
mode (the default), it will add a map entry keyed by the
target IP address; this map will store RTT measurements, current
sequence number etc.  Finally in client mode the ping command
is executed, and the xdping BPF program will use the last ICMP
reply, reformulate it as an ICMP request with the next sequence
number and XDP_TX it.  After the reply to that request is received
we can measure RTT and repeat until the desired number of
measurements is made.  This is why the sequence numbers in the
normal ping are 1, 2, 3 and 8.  We XDP_TX a modified version
of ICMP reply 4 and keep doing this until we get the 4 replies
we need; hence the networking stack only sees reply 8, where
we have XDP_PASSed it upstream since we are done.

In server mode (-s), xdping simply takes ICMP requests and replies
to them in XDP rather than passing the request up to the networking
stack.  No map entry is required.

xdping can be run in native XDP mode (the default, or specified
via -N) or in skb mode (-S).

A test program test_xdping.sh exercises some of these options.

Note that native XDP does not seem to XDP_TX for veths, hence -N
is not tested.  Looking at the code, it looks like XDP_TX is
supported so I'm not sure if that's expected.  Running xdping in
native mode for ixgbe as both client and server works fine.

Changes since v4

- close fds on cleanup (Song Liu)

Changes since v3

- fixed seq to be __be16 (Song Liu)
- fixed fd checks in xdping.c (Song Liu)

Changes since v2

- updated commit message to explain why seq number of last
  ICMP reply is 8 not 4 (Song Liu)
- updated types of seq number, raddr and eliminated csum variable
  in xdpclient/xdpserver functions as it was not needed (Song Liu)
- added XDPING_DEFAULT_COUNT definition and usage specification of
  default/max counts (Song Liu)

Changes since v1
 - moved from RFC to PATCH
 - removed unused variable in ipv4_csum() (Song Liu)
 - refactored ICMP checks into icmp_check() function called by client
   and server programs and reworked client and server programs due
   to lack of shared code (Song Liu)
 - added checks to ensure that SKB and native mode are not requested
   together (Song Liu)
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2019-05-31

This series contains updates to the iavf driver.

Nathan Chancellor converts the use of gnu_printf to printf.

Aleksandr modifies the driver to limit the number of RSS queues to the
number of online CPUs in order to avoid creating misconfigured RSS
queues.

Gustavo A. R. Silva converts a couple of instances where sizeof() can be
replaced with struct_size().

Alice makes the remaining changes to the iavf driver to cleanup all the
old "i40evf" references in the driver to iavf, including the file names
that still contained the old driver reference.  There was no functional
changes made, just cosmetic to reduce any confusion going forward now
that the iavf driver is the virtual function driver for both i40e and
ice drivers.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

There has been quite a few progress around the two steps mentioned in the
answer to the following question:

  Q: BPF 32-bit subregister requirements

This patch updates the answer to reflect what has been done.

v2:
 - Add missing full stop. (Song Liu)
 - Minor tweak on one sentence. (Song Liu)

v1:
 - Integrated rephrase from Quentin and Jakub
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Roman Gushchin says:

====================
During my work on memcg-based memory accounting for bpf maps
I've done some cleanups and refactorings of the existing
memlock rlimit-based code. It makes it more robust, unifies
size to pages conversion, size checks and corresponding error
codes. Also it adds coverage for cgroup local storage and
socket local storage maps.

It looks like some preliminary work on the mm side might be
required to start working on the memcg-based accounting,
so I'm sending these patches as a separate patchset.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Most bpf map types doing similar checks and bytes to pages
conversion during memory allocation and charging.

Let's unify these checks by moving them into bpf_map_charge_init().
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

In order to unify the existing memlock charging code with the
memcg-based memory accounting, which will be added later, let's
rework the current scheme.

Currently the following design is used:
  1) .alloc() callback optionally checks if the allocation will likely
     succeed using bpf_map_precharge_memlock()
  2) .alloc() performs actual allocations
  3) .alloc() callback calculates map cost and sets map.memory.pages
  4) map_create() calls bpf_map_init_memlock() which sets map.memory.user
     and performs actual charging; in case of failure the map is
     destroyed
  <map is in use>
  1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which
     performs uncharge and releases the user
  2) .map_free() callback releases the memory

The scheme can be simplified and made more robust:
  1) .alloc() calculates map cost and calls bpf_map_charge_init()
  2) bpf_map_charge_init() sets map.memory.user and performs actual
    charge
  3) .alloc() performs actual allocations
  <map is in use>
  1) .map_free() callback releases the memory
  2) bpf_map_charge_finish() performs uncharge and releases the user

The new scheme also allows to reuse bpf_map_charge_init()/finish()
functions for memcg-based accounting. Because charges are performed
before actual allocations and uncharges after freeing the memory,
no bogus memory pressure can be created.

In cases when the map structure is not available (e.g. it's not
created yet, or is already destroyed), on-stack bpf_map_memory
structure is used. The charge can be transferred with the
bpf_map_charge_move() function.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Group "user" and "pages" fields of bpf_map into the bpf_map_memory
structure. Later it can be extended with "memcg" and other related
information.

The main reason for a such change (beside cosmetics) is to pass
bpf_map_memory structure to charging functions before the actual
allocation of bpf_map.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Socket local storage maps lack the memlock precharge check,
which is performed before the memory allocation for
most other bpf map types.

Let's add it in order to unify all map types.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Cgroup local storage maps lack the memlock precharge check,
which is performed before the memory allocation for
most other bpf map types.

Let's add it in order to unify all map types.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Lawrence Brakmo says:

====================
This patchset adds support for propagating congestion notifications (cn)
to TCP from cgroup inet skb egress BPF programs.

Current cgroup skb BPF programs cannot trigger TCP congestion window
reductions, even when they drop a packet. This patch-set adds support
for cgroup skb BPF programs to send congestion notifications in the
return value when the packets are TCP packets. Rather than the
current 1 for keeping the packet and 0 for dropping it, they can
now return:
    NET_XMIT_SUCCESS    (0)    - continue with packet output
    NET_XMIT_DROP       (1)    - drop packet and do cn
    NET_XMIT_CN         (2)    - continue with packet output and do cn
    -EPERM                     - drop packet

Finally, HBM programs are modified to collect and return more
statistics.

There has been some discussion regarding the best place to manage
bandwidths. Some believe this should be done in the qdisc where it can
also be managed with a BPF program. We believe there are advantages
for doing it with a BPF program in the cgroup/skb callback. For example,
it reduces overheads in the cases where there is on primary workload and
one or more secondary workloads, where each workload is running on its
own cgroupv2. In this scenario, we only need to throttle the secondary
workloads and there is no overhead for the primary workload since there
will be no BPF program attached to its cgroup.

Regardless, we agree that this mechanism should not penalize those that
are not using it. We tested this by doing 1 byte req/reply RPCs over
loopback. Each test consists of 30 sec of back-to-back 1 byte RPCs.
Each test was repeated 50 times with a 1 minute delay between each set
of 10. We then calculated the average RPCs/sec over the 50 tests. We
compare upstream with upstream + patchset and no BPF program as well
as upstream + patchset and a BPF program that just returns ALLOW_PKT.
Here are the results:

upstream                           80937 RPCs/sec
upstream + patches, no BPF program 80894 RPCs/sec
upstream + patches, BPF program    80634 RPCs/sec

These numbers indicate that there is no penalty for these patches

The use of congestion notifications improves the performance of HBM when
using Cubic. Without congestion notifications, Cubic will not decrease its
cwnd and HBM will need to drop a large percentage of the packets.

The following results are obtained for rate limits of 1Gbps,
between two servers using netperf, and only one flow. We also show how
reducing the max delayed ACK timer can improve the performance when
using Cubic.

Command used was:
  ./do_hbm_test.sh -l -D --stats -N -r=<rate> [--no_cn] [dctcp] \
                   -s=<server running netserver>
  where:
     <rate>   is 1000
     --no_cn  specifies no cwr notifications
     dctcp    uses dctcp

                       Cubic                    DCTCP
Lim, DA      Mbps cwnd cred drops  Mbps cwnd cred drops
--------     ---- ---- ---- -----  ---- ---- ---- -----
  1G, 40       35  462 -320 67%     995    1 -212  0.05%
  1G, 40,cn   736    9  -78  0.07   995    1 -212  0.05
  1G,  5,cn   941    2 -189  0.13   995    1 -212  0.05

Notes:
  --no_cn has no effect with DCTCP
  Lim = rate limit
  DA = maximum delay ack timer
  cred = credit in packets
  drops = % packets dropped

v1->v2: Insures that only BPF_CGROUP_INET_EGRESS can return values 2 and 3
        New egress values apply to all protocols, not just TCP
        Cleaned up patch 4, Update BPF_CGROUP_RUN_PROG_INET_EGRESS callers
        Removed changes to __tcp_transmit_skb (patch 5), no longer needed
        Removed sample use of EDT
v2->v3: Removed the probe timer related changes
v3->v4: Replaced preempt_enable_no_resched() by preempt_enable()
        in BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY() macro
====================
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Adds more stats to HBM, including average cwnd and rtt of all TCP
flows, percents of packets that are ecn ce marked and distribution
of return values.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>