xsk_build_skb() allocates a page and adds it to the skb via
skb_add_rx_frag() and specifies 0 for truesize. This leads to a warning
in skb_add_rx_frag() with CONFIG_DEBUG_NET enabled because size is
larger than truesize.
Increasing truesize requires to add the same amount to socket's
sk_wmem_alloc counter in order not to underflow the counter during
release in the destructor (sock_wfree()).
Pass the size of the allocated page as truesize to skb_add_rx_frag().
Add this mount to socket's sk_wmem_alloc counter.
Fixes: cf24f5a5fe ("xsk: add support for AF_XDP multi-buffer on Tx path")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20240202163221.2488589-1-bigeasy@linutronix.de
Add missing xsk_buff_free() call when __xsk_rcv_zc() failed to produce
descriptor to XSK Rx queue.
Fixes: 24ea50127e ("xsk: support mbuf on ZC RX")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-2-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In xsk_poll(), checking available events and setting mask bits should
be executed only when a socket has been bound. Setting mask bits for
unbound socket is meaningless.
Currently, it checks events even when xsk_check_common() failed.
To prevent this, we move goto location (skip_tx) after that checking.
Fixes: 1596dae2f1 ("xsk: check IFF_UP earlier in Tx path")
Signed-off-by: Yewon Choi <woni9911@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20231201061048.GA1510@libra05
For XDP_COPY mode, add a UMEM option XDP_UMEM_TX_SW_CSUM
to call skb_checksum_help in transmit path. Might be useful
to debugging issues with real hardware. I also use this mode
in the selftests.
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-9-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Accept only the flags that the kernel knows about to make
sure we can extend this field in the future. Note that only
in XDP_COPY mode we propagate the error signal back to the user
(via sendmsg). For zerocopy mode we silently skip the metadata
for the descriptors that have wrong flags (since we process
the descriptors deep in the driver).
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-8-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This change actually defines the (initial) metadata layout
that should be used by AF_XDP userspace (xsk_tx_metadata).
The first field is flags which requests appropriate offloads,
followed by the offload-specific fields. The supported per-device
offloads are exported via netlink (new xsk-flags).
The offloads themselves are still implemented in a bit of a
framework-y fashion that's left from my initial kfunc attempt.
I'm introducing new xsk_tx_metadata_ops which drivers are
supposed to implement. The drivers are also supposed
to call xsk_tx_metadata_request/xsk_tx_metadata_complete in
the right places. Since xsk_tx_metadata_{request,_complete}
are static inline, we don't incur any extra overhead doing
indirect calls.
The benefit of this scheme is as follows:
- keeps all metadata layout parsing away from driver code
- makes it easy to grep and see which drivers implement what
- don't need any extra flags to maintain to keep track of what
offloads are implemented; if the callback is implemented - the offload
is supported (used by netlink reporting code)
Two offloads are defined right now:
1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset
2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata
area upon completion (tx_timestamp field)
XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes
SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass
metadata pointer).
The struct is forward-compatible and can be extended in the future
by appending more fields.
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
For zerocopy mode, tx_desc->addr can point to an arbitrary offset
and carry some TX metadata in the headroom. For copy mode, there
is no way currently to populate skb metadata.
Introduce new tx_metadata_len umem config option that indicates how many
bytes to treat as metadata. Metadata bytes come prior to tx_desc address
(same as in RX case).
The size of the metadata has mostly the same constraints as XDP:
- less than 256 bytes
- 8-byte aligned (compared to 4-byte alignment on xdp, due to 8-byte
timestamp in the completion)
- non-zero
This data is not interpreted in any way right now.
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231127190319.1190813-2-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In the previous implementation, when multiple xsk sockets were
associated with a single xsk_buff_pool, a situation could arise
where the xsk_tx_list maintained data at the front for one xsk
socket while starving the xsk sockets at the back of the list.
This could result in issues such as the inability to transmit packets,
increased latency, and jitter. To address this problem, we introduce
a new variable called tx_budget_spent, which limits each xsk to transmit
a maximum of MAX_PER_SOCKET_BUDGET tx descriptors. This allocation ensures
equitable opportunities for subsequent xsk sockets to send tx descriptors.
The value of MAX_PER_SOCKET_BUDGET is set to 32.
Signed-off-by: Albert Huang <huangjie.albert@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20231023125732.82261-1-huangjie.albert@bytedance.com
A few drivers were missing a xdp_do_flush() invocation after
XDP_REDIRECT.
Add three helper functions each for one of the per-CPU lists. Return
true if the per-CPU list is non-empty and flush the list.
Add xdp_do_check_flushed() which invokes each helper functions and
creates a warning if one of the functions had a non-empty list.
Hide everything behind CONFIG_DEBUG_NET.
Suggested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20231016125738.Yt79p1uF@linutronix.de
This is a followup of 8bf43be799 ("net: annotate data-races
around sk->sk_priority").
sk->sk_priority can be read and written without holding the socket lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Userspace applications indicate their multi-buffer capability to xsk
using XSK_USE_SG socket bind flag. For sockets using shared umem the
bind flag may contain XSK_USE_SG only for the first socket. For any
subsequent socket the only option supported is XDP_SHARED_UMEM.
Add option XDP_UMEM_SG_FLAG in umem config flags to store the
multi-buffer handling capability when indicated by XSK_USE_SG option in
bing flag by the first socket. Use this to derive multi-buffer capability
for subsequent sockets in xsk core.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Fixes: 81470b5c3c ("xsk: introduce XSK_USE_SG bind flag for xsk socket")
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230907035032.2627879-1-tirthendu.sarkar@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, xsk_build_skb() is a function that builds skb in two possible
ways and then is ended with common error handling.
We can distinguish four possible error paths and handling in xsk_build_skb():
1. sock_alloc_send_skb fails: Retry (skb is NULL).
2. skb_store_bits fails : Free skb and retry.
3. MAX_SKB_FRAGS exceeded: Free skb, cleanup and drop packet.
4. alloc_page fails for frag: Retry page allocation w/o freeing skb
1] and 3] can happen in xsk_build_skb_zerocopy(), which is one of the
two code paths responsible for building skb. Common error path in
xsk_build_skb() assumes that in case errno != -EAGAIN, skb is a valid
pointer, which is wrong as kernel test robot reports that in
xsk_build_skb_zerocopy() other errno values are returned for skb being
NULL.
To fix this, set -EOVERFLOW as error when MAX_SKB_FRAGS are exceeded
and packet needs to be dropped in both xsk_build_skb() and
xsk_build_skb_zerocopy() and use this to distinguish against all other
error cases. Also, add explicit kfree_skb() for 3] so that handling
of 1], 2], and 3] becomes identical where allocation needs to be retried.
Fixes: cf24f5a5fe ("xsk: add support for AF_XDP multi-buffer on Tx path")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Closes: https://lore.kernel.org/r/202307210434.OjgqFcbB-lkp@intel.com
Link: https://lore.kernel.org/bpf/20230823144713.2231808-1-tirthendu.sarkar@intel.com
Fix a refcount underflow problem reported by syzbot that can happen
when a system is running out of memory. If xp_alloc_tx_descs() fails,
and it can only fail due to not having enough memory, then the error
path is triggered. In this error path, the refcount of the pool is
decremented as it has incremented before. However, the reference to
the pool in the socket was not nulled. This means that when the socket
is closed later, the socket teardown logic will think that there is a
pool attached to the socket and try to decrease the refcount again,
leading to a refcount underflow.
I chose this fix as it involved adding just a single line. Another
option would have been to move xp_get_pool() and the assignment of
xs->pool to after the if-statement and using xs_umem->pool instead of
xs->pool in the whole if-statement resulting in somewhat simpler code,
but this would have led to much more churn in the code base perhaps
making it harder to backport.
Fixes: ba3beec2ec ("xsk: Fix possible crash when multiple sockets are created")
Reported-by: syzbot+8ada0057e69293a05fd4@syzkaller.appspotmail.com
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230809142843.13944-1-magnus.karlsson@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRdM/uy1Ege0+EN1fNar9k/UBDW4wUCZMvevwAKCRBar9k/UBDW
42Z0AP90hLZ9OmoghYAlALHLl8zqXuHCV8OeFXR5auqG+kkcCwEAx6h99vnh4zgP
Tngj6Yid60o39/IZXXblhV37HfSiyQ8=
=/kVE
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Martin KaFai Lau says:
====================
pull-request: bpf-next 2023-08-03
We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 84 files changed, 4026 insertions(+), 562 deletions(-).
The main changes are:
1) Add SO_REUSEPORT support for TC bpf_sk_assign from Lorenz Bauer,
Daniel Borkmann
2) Support new insns from cpu v4 from Yonghong Song
3) Non-atomically allocate freelist during prefill from YiFei Zhu
4) Support defragmenting IPv(4|6) packets in BPF from Daniel Xu
5) Add tracepoint to xdp attaching failure from Leon Hwang
6) struct netdev_rx_queue and xdp.h reshuffling to reduce
rebuild time from Jakub Kicinski
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
net: invert the netdevice.h vs xdp.h dependency
net: move struct netdev_rx_queue out of netdevice.h
eth: add missing xdp.h includes in drivers
selftests/bpf: Add testcase for xdp attaching failure tracepoint
bpf, xdp: Add tracepoint to xdp attaching failure
selftests/bpf: fix static assert compilation issue for test_cls_*.c
bpf: fix bpf_probe_read_kernel prototype mismatch
riscv, bpf: Adapt bpf trampoline to optimized riscv ftrace framework
libbpf: fix typos in Makefile
tracing: bpf: use struct trace_entry in struct syscall_tp_t
bpf, devmap: Remove unused dtab field from bpf_dtab_netdev
bpf, cpumap: Remove unused cmap field from bpf_cpu_map_entry
netfilter: bpf: Only define get_proto_defrag_hook() if necessary
bpf: Fix an array-index-out-of-bounds issue in disasm.c
net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
docs/bpf: Fix malformed documentation
bpf: selftests: Add defrag selftests
bpf: selftests: Support custom type and proto for client sockets
bpf: selftests: Support not connecting client socket
netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link
...
====================
Link: https://lore.kernel.org/r/20230803174845.825419-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
struct netdev_rx_queue is touched in only a few places
and having it defined in netdevice.h brings in the dependency
on xdp.h, because struct xdp_rxq_info gets embedded in
struct netdev_rx_queue.
In prep for removal of xdp.h from netdevice.h move all
the netdev_rx_queue stuff to a new header.
We could technically break the new header up to avoid
the sysfs.h include but it's so rarely included it
doesn't seem to be worth it at this point.
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20230803010230.1755386-3-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
sk->sk_mark is often read while another thread could change the value.
Fixes: 4a19ec5800 ("[NET]: Introducing socket mark socket option.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Given that skb_shared_info relies on skb_frag_t, in order to support
xskb chaining, introduce xdp_buff_xsk::xskb_list_node and
xsk_buff_pool::xskb_list.
This is needed so ZC drivers can add frags as xskb nodes which will make
it possible to handle it both when producing AF_XDP Rx descriptors as
well as freeing/recycling all the frags that a single frame carries.
Speaking of latter, update xsk_buff_free() to take care of list nodes.
For the former (adding as frags), introduce xsk_buff_add_frag() for ZC
drivers usage that is going to be used to add a frag to xskb list from
pool.
xsk_buff_get_frag() will be utilized by XDP_TX and, on contrary, will
return xdp_buff.
One of the previous patches added a wrapper for ZC Rx so implement xskb
list walk and production of Rx descriptors there.
On bind() path, bail out if socket wants to use ZC multi-buffer but
underlying netdev does not support it.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-12-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
For transmitting an AF_XDP packet, allocate skb while processing the
first desc and copy data to it. The 'XDP_PKT_CONTD' flag in 'options'
field of the desc indicates the EOP status of the packet. If the current
desc is not EOP, store the skb, release the current desc and go
on to read the next descs.
Allocate a page for each subsequent desc, copy data to it and add it as
a frag in the skb stored in xsk. On processing EOP, transmit the skb
with frags. Addresses contained in descs have been already queued in
consumer queue and skb destructor updated the completion count.
On transmit failure cancel the releases, clear the descs from the
completion queue and consume the skb for retrying packet transmission.
For any invalid descriptor (invalid length/address/options) in the middle
of a packet, all pending descriptors will be dropped by xsk core along
with the invalid one and the next descriptor is treated as the start of
a new packet.
Maximum supported frames for a packet is MAX_SKB_FRAGS + 1. If it is
exceeded, all descriptors accumulated so far are dropped.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-9-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In Tx path, xsk core reserves space for each desc to be transmitted in
the completion queue and it's address contained in it is stored in the
skb destructor arg. After successful transmission the skb destructor
submits the addr marking completion.
To handle multiple descriptors per packet, now along with reserving
space for each descriptor, the corresponding address is also stored in
completion queue. The number of pending descriptors are stored in skb
destructor arg and is used by the skb destructor to update completions.
Introduce 'skb' in xdp_sock to store a partially built packet when
__xsk_generic_xmit() must return before it sees the EOP descriptor for
the current packet so that packet building can resume in next call of
__xsk_generic_xmit().
Helper functions are introduced to set and get the pending descriptors
in the skb destructor arg. Also, wrappers are introduced for storing
descriptor addresses, submitting and cancelling (for unsuccessful
transmissions) the number of completions.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-7-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add multi-buffer support for AF_XDP by extending the XDP multi-buffer
support to be reflected in user-space when a packet is redirected to
an AF_XDP socket.
In the XDP implementation, the NIC driver builds the xdp_buff from the
first frag of the packet and adds any subsequent frags in the skb_shinfo
area of the xdp_buff. In AF_XDP core, XDP buffers are allocated from
xdp_sock's pool and data is copied from the driver's xdp_buff and frags.
Once an allocated XDP buffer is full and there is still data to be
copied, the 'XDP_PKT_CONTD' flag in'options' field of the corresponding
xdp ring descriptor is set and passed to the application. When application
sees the aforementioned flag set it knows there is pending data for this
packet that will be carried in the following descriptors. If there is no
more data to be copied, the flag in 'options' field is cleared for that
descriptor signalling EOP to the application.
If application reads a batch of descriptors using for example the libxdp
interfaces, it is not guaranteed that the batch will end with a full
packet. It might end in the middle of a packet and the rest of the frames
of that packet will arrive at the beginning of the next batch.
AF_XDP ensures that only a complete packet (along with all its frags) is
sent to application.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-6-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
If the data in xdp_buff exceeds the xsk frame length, the packet needs
to be dropped. This check is currently being done in __xsk_rcv(). Move
the described logic to xsk_rcv_check() so that such a xdp_buff will
only be dropped if the application does not support multi-buffer
(absence of XDP_USE_SG bind flag). This is applicable for all cases:
copy mode, zero copy mode as well as skb mode.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-5-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, __xsk_rcv_zc() is a function that is responsible for
producing AF_XDP Rx descriptors. It is used by both copy and zero-copy
mode. Both of these modes are going to differ when multi-buffer support
is going to be added. ZC will work on a chain of xdp_buff_xsk structs
whereas copy-mode is going to utilize skb_shared_info contents. This
means that ZC-specific changes would affect the copy mode.
Let's modify __xsk_rcv_zc() to work directly on xdp_buff_xsk so the
callsites have to retrieve this from xdp_buff. Also, introduce
xsk_rcv_zc() which will carry all the needed later changes for
supporting multi-buffer on ZC side that do not apply to copy mode.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-4-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
As of now xsk core drops any xdp_buff with data size greater than the
xsk frame_size as set by the af_xdp application. With multi-buffer
support introduced in the next patch xsk core can now split those
buffers into multiple descriptors provided the af_xdp application can
handle them. Such capability of the application needs to be independent
of the xdp_prog's frag support capability since there are cases where
even a single xdp_buffer may need to be split into multiple descriptors
owing to a smaller xsk frame size.
For e.g., with NIC rx_buffer size set to 4kB, a 3kB packet will
constitute of a single buffer and so will be sent as such to AF_XDP layer
irrespective of 'xdp.frags' capability of the XDP program. Now if the xsk
frame size is set to 2kB by the AF_XDP application, then the packet will
need to be split into 2 descriptors if AF_XDP application can handle
multi-buffer, else it needs to be dropped.
Applications can now advertise their frag handling capability to xsk core
so that xsk core can decide if it should drop or split xdp_buffs that
exceed xsk frame size. This is done using a new 'XSK_USE_SG' bind flag
for the xdp socket.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-3-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Use the 'options' field in xdp_desc as a packet continuity marker. Since
'options' field was unused till now and was expected to be set to 0, the
'eop' descriptor will have it set to 0, while the non-eop descriptors
will have to set it to 1. This ensures legacy applications continue to
work without needing any change for single-buffer packets.
Add helper functions and extend xskq_prod_reserve_desc() to use the
'options' field.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-2-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Initial creation of an AF_XDP socket requires CAP_NET_RAW capability. A
privileged process might create the socket and pass it to a non-privileged
process for later use. However, that process will be able to bind the socket
to any network interface. Even though it will not be able to receive any
traffic without modification of the BPF map, the situation is not ideal.
Sockets already have a mechanism that can be used to restrict what interface
they can be attached to. That is SO_BINDTODEVICE.
To change the SO_BINDTODEVICE binding the process will need CAP_NET_RAW.
Make xsk_bind() honor the SO_BINDTODEVICE in order to allow safer workflow
when non-privileged process is using AF_XDP.
The intended workflow is following:
1. First process creates a bare socket with socket(AF_XDP, ...).
2. First process loads the XSK program to the interface.
3. First process adds the socket fd to a BPF map.
4. First process ties socket fd to a particular interface using
SO_BINDTODEVICE.
5. First process sends socket fd to a second process.
6. Second process allocates UMEM.
7. Second process binds socket to the interface with bind(...).
8. Second process sends/receives the traffic.
All the steps above are possible today if the first process is privileged
and the second one has sufficient RLIMIT_MEMLOCK and no capabilities.
However, the second process will be able to bind the socket to any interface
it wants on step 7 and send traffic from it. With the proposed change, the
second process will be able to bind the socket only to a specific interface
chosen by the first process at step 4.
Fixes: 965a990984 ("xsk: add support for bind for Rx")
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/bpf/20230703175329.3259672-1-i.maximets@ovn.org
The remap of fill and completion rings was frowned upon as they
control the usage of UMEM which does not support concurrent use.
At the same time this would disallow the remap of these rings
into another process.
A possible use case is that the user wants to transfer the socket/
UMEM ownership to another process (via SYS_pidfd_getfd) and so
would need to also remap these rings.
This will have no impact on current usages and just relaxes the
remap limitation.
Signed-off-by: Nuno Gonçalves <nunog@fr24.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230324100222.13434-1-nunog@fr24.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY+/uBgAKCRDbK58LschI
g0ngAPwJHd1RicBuy2C4fLv0nGKZtmYZBAnTGlI2RisPxU6BRwEAwUDLHuc5K6nR
j261okOxOy/MRxdN1NhmR6Qe7nMyQAk=
=tYU+
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-02-17
We've added 64 non-merge commits during the last 7 day(s) which contain
a total of 158 files changed, 4190 insertions(+), 988 deletions(-).
The main changes are:
1) Add a rbtree data structure following the "next-gen data structure"
precedent set by recently-added linked-list, that is, by using
kfunc + kptr instead of adding a new BPF map type, from Dave Marchevsky.
2) Add a new benchmark for hashmap lookups to BPF selftests,
from Anton Protopopov.
3) Fix bpf_fib_lookup to only return valid neighbors and add an option
to skip the neigh table lookup, from Martin KaFai Lau.
4) Add cgroup.memory=nobpf kernel parameter option to disable BPF memory
accouting for container environments, from Yafang Shao.
5) Batch of ice multi-buffer and driver performance fixes,
from Alexander Lobakin.
6) Fix a bug in determining whether global subprog's argument is
PTR_TO_CTX, which is based on type names which breaks kprobe progs,
from Andrii Nakryiko.
7) Prep work for future -mcpu=v4 LLVM option which includes usage of
BPF_ST insn. Thus improve BPF_ST-related value tracking in verifier,
from Eduard Zingerman.
8) More prep work for later building selftests with Memory Sanitizer
in order to detect usages of undefined memory, from Ilya Leoshkevich.
9) Fix xsk sockets to check IFF_UP earlier to avoid a NULL pointer
dereference via sendmsg(), from Maciej Fijalkowski.
10) Implement BPF trampoline for RV64 JIT compiler, from Pu Lehui.
11) Fix BPF memory allocator in combination with BPF hashtab where it could
corrupt special fields e.g. used in bpf_spin_lock, from Hou Tao.
12) Fix LoongArch BPF JIT to always use 4 instructions for function
address so that instruction sequences don't change between passes,
from Hengqi Chen.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (64 commits)
selftests/bpf: Add bpf_fib_lookup test
bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup
riscv, bpf: Add bpf trampoline support for RV64
riscv, bpf: Add bpf_arch_text_poke support for RV64
riscv, bpf: Factor out emit_call for kernel and bpf context
riscv: Extend patch_text for multiple instructions
Revert "bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES"
selftests/bpf: Add global subprog context passing tests
selftests/bpf: Convert test_global_funcs test to test_loader framework
bpf: Fix global subprog context argument resolution logic
LoongArch, bpf: Use 4 instructions for function address in JIT
bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state
bpf: Disable bh in bpf_test_run for xdp and tc prog
xsk: check IFF_UP earlier in Tx path
Fix typos in selftest/bpf files
selftests/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
samples/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
bpftool: Use bpf_{btf,link,map,prog}_get_info_by_fd()
libbpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
libbpf: Introduce bpf_{btf,link,map,prog}_get_info_by_fd()
...
====================
Link: https://lore.kernel.org/r/20230217221737.31122-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When we try to start AF_XDP on some machines with long running time, due
to the machine's memory fragmentation problem, there is no sufficient
contiguous physical memory that will cause the start failure.
If the size of the queue is 8 * 1024, then the size of the desc[] is
8 * 1024 * 8 = 16 * PAGE, but we also add struct xdp_ring size, so it is
16page+. This is necessary to apply for a 4-order memory. If there are a
lot of queues, it is difficult to these machine with long running time.
Here, that we actually waste 15 pages. 4-Order memory is 32 pages, but
we only use 17 pages.
This patch replaces __get_free_pages() by vmalloc() to allocate memory
to solve these problems.
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit e48c414ee6 ("[INET]: Generalise the TCP sock ID lookup routines")
commented out the definition of SOCK_REFCNT_DEBUG in 2005 and later another
commit 463c84b97f ("[NET]: Introduce inet_connection_sock") removed it.
Since we could track all of them through bpf and kprobe related tools
and the feature could print loads of information which might not be
that helpful even under a little bit pressure, the whole feature which
has been inactive for many years is no longer supported.
Link: https://lore.kernel.org/lkml/20230211065153.54116-1-kerneljasonxing@gmail.com/
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The flag for need_wakeup is not set for xsks with `XDP_SHARED_UMEM`
flag and of different queue ids and/or devices. They should inherit
the flag from the first socket buffer pool since no flags can be
specified once `XDP_SHARED_UMEM` is specified.
Fixes: b5aea28dca ("xsk: Add shared umem support between queue ids")
Signed-off-by: Jalal Mostafa <jalal.a.mostapha@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220921135701.10199-1-jalal.a.mostapha@gmail.com
Commit d678cbd2f8 ("xsk: Fix handling of invalid descriptors in XSK TX
batching API") fixed batch API usage against set of descriptors with
invalid ones but introduced a problem when AF_XDP SW rings are smaller
than HW ones. Mismatch of reported Tx'ed frames between HW generator and
user space app was observed. It turned out that backpressure mechanism
became a bottleneck when the amount of produced descriptors to CQ is
lower than what we grabbed from XSK Tx ring.
Say that 512 entries had been taken from XSK Tx ring but we had only 490
free entries in CQ. Then callsite (ZC driver) will produce only 490
entries onto HW Tx ring but 512 entries will be released from Tx ring
and this is what will be seen by the user space.
In order to fix this case, mix XSK Tx/CQ ring interractions by moving
around internal functions and changing call order:
* pull out xskq_prod_nb_free() from xskq_prod_reserve_addr_batch()
up to xsk_tx_peek_release_desc_batch();
** move xskq_cons_release_n() into xskq_cons_read_desc_batch()
After doing so, algorithm can be described as follows:
1. lookup Tx entries
2. use value from 1. to reserve space in CQ (*)
3. Read from Tx ring as much descriptors as value from 2
3a. release descriptors from XSK Tx ring (**)
4. Finally produce addresses to CQ
Fixes: d678cbd2f8 ("xsk: Fix handling of invalid descriptors in XSK TX batching API")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220830121705.8618-1-maciej.fijalkowski@intel.com
When application runs in busy poll mode and does not receive a single
packet but only sends them, it is currently impossible to get into
napi_busy_loop() as napi_id is only marked on Rx side in xsk_rcv_check().
In there, napi_id is being taken from xdp_rxq_info carried by xdp_buff.
From Tx perspective, we do not have access to it. What we have handy is
the xsk pool.
Xsk pool works on a pool of internal xdp_buff wrappers called xdp_buff_xsk.
AF_XDP ZC enabled drivers call xp_set_rxq_info() so each of xdp_buff_xsk
has a valid pointer to xdp_rxq_info of underlying queue. Therefore, on Tx
side, napi_id can be pulled from xs->pool->heads[0].xdp.rxq->napi_id. Hide
this pointer chase under helper function, xsk_pool_get_napi_id().
Do this only for sockets working in ZC mode as otherwise rxq pointers would
not be initialized.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220707130842.49408-1-maciej.fijalkowski@intel.com
Two points of potential failure in the generic transmit function are:
1. completion queue (cq) reservation failure.
2. skb allocation failure
Originally the cq reservation was performed first, followed by the skb
allocation. Commit 675716400d ("xdp: fix possible cq entry leak")
reversed the order because at the time there was no mechanism available
to undo the cq reservation which could have led to possible cq entry leaks
in the event of skb allocation failure. However if the skb allocation is
performed first and the cq reservation then fails, the xsk skb destructor
is called which blindly adds the skb address to the already full cq leading
to undefined behavior.
This commit restores the original order (cq reservation followed by skb
allocation) and uses the xskq_prod_cancel helper to undo the cq reserve
in event of skb allocation failure.
Fixes: 675716400d ("xdp: fix possible cq entry leak")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220614070746.8871-1-ciara.loftus@intel.com
xdpxceiver run on a AF_XDP ZC enabled driver revealed a problem with XSK
Tx batching API. There is a test that checks how invalid Tx descriptors
are handled by AF_XDP. Each valid descriptor is followed by invalid one
on Tx side whereas the Rx side expects only to receive a set of valid
descriptors.
In current xsk_tx_peek_release_desc_batch() function, the amount of
available descriptors is hidden inside xskq_cons_peek_desc_batch(). This
can be problematic in cases where invalid descriptors are present due to
the fact that xskq_cons_peek_desc_batch() returns only a count of valid
descriptors. This means that it is impossible to properly update XSK
ring state when calling xskq_cons_release_n().
To address this issue, pull out the contents of
xskq_cons_peek_desc_batch() so that callers (currently only
xsk_tx_peek_release_desc_batch()) will always be able to update the
state of ring properly, as total count of entries is now available and
use this value as an argument in xskq_cons_release_n(). By
doing so, xskq_cons_peek_desc_batch() can be dropped altogether.
Fixes: 9349eb3a9d ("xsk: Introduce batched Tx descriptor interfaces")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220607142200.576735-1-maciej.fijalkowski@intel.com
Inspired by patch that made xdp_do_redirect() return values for XSKMAP
more meaningful, return -ENXIO instead of -EINVAL for socket being
unbound in xsk_rcv_check() as this is the usual value that is returned
for such event. In turn, it is now possible to easily distinguish what
went wrong, which is a bit harder when for both cases checked, -EINVAL
was returned.
Return codes can be counted in a nice way via bpftrace oneliner that
Jesper has shown:
bpftrace -e 'tracepoint:xdp:xdp_redirect* {@err[-args->err] = count();}'
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20220413153015.453864-3-maciej.fijalkowski@intel.com
The error codes returned by xdp_do_redirect() when redirecting a frame
to an AF_XDP socket has not been very useful. A driver could not
distinguish between different errors. Prior this change the following
codes where used:
Socket not bound or incorrect queue/netdev: EINVAL
XDP frame/AF_XDP buffer size mismatch: ENOSPC
Could not allocate buffer (copy mode): ENOSPC
AF_XDP Rx buffer full: ENOSPC
After this change:
Socket not bound or incorrect queue/netdev: EINVAL
XDP frame/AF_XDP buffer size mismatch: ENOSPC
Could not allocate buffer (copy mode): ENOMEM
AF_XDP Rx buffer full: ENOBUFS
An AF_XDP zero-copy driver can now potentially determine if the
failure was due to a full Rx buffer, and if so stop processing more
frames, yielding to the userland AF_XDP application.
Signed-off-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20220413153015.453864-2-maciej.fijalkowski@intel.com
While checking AF_XDP copy mode combined with busy poll, strange
results were observed. rxdrop and txonly scenarios worked fine, but
l2fwd broke immediately.
After a deeper look, it turned out that for l2fwd, Tx side was exiting
early due to xsk_no_wakeup() returning true and in the end
xsk_generic_xmit() was never called. Note that AF_XDP Tx in copy mode
is syscall steered, so the current behavior is broken.
Txonly scenario only worked due to the fact that
sk_mark_napi_id_once_xdp() was never called - since Rx side is not in
the picture for this case and mentioned function is called in
xsk_rcv_check(), sk::sk_napi_id was never set, which in turn meant that
xsk_no_wakeup() was returning false (see the sk->sk_napi_id >=
MIN_NAPI_ID check in there).
To fix this, prefer busy poll in xsk_sendmsg() only when zero copy is
enabled on a given AF_XDP socket. By doing so, busy poll in copy mode
would not exit early on Tx side and eventually xsk_generic_xmit() will
be called.
Fixes: a0731952d9 ("xsk: Add busy-poll support for {recv,send}msg()")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220406155804.434493-1-maciej.fijalkowski@intel.com
Fix a race in the xsk socket teardown code that can lead to a NULL pointer
dereference splat. The current xsk unbind code in xsk_unbind_dev() starts by
setting xs->state to XSK_UNBOUND, sets xs->dev to NULL and then waits for any
NAPI processing to terminate using synchronize_net(). After that, the release
code starts to tear down the socket state and free allocated memory.
BUG: kernel NULL pointer dereference, address: 00000000000000c0
PGD 8000000932469067 P4D 8000000932469067 PUD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 25 PID: 69132 Comm: grpcpp_sync_ser Tainted: G I 5.16.0+ #2
Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.2.10 03/09/2015
RIP: 0010:__xsk_sendmsg+0x2c/0x690
[...]
RSP: 0018:ffffa2348bd13d50 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000040 RCX: ffff8d5fc632d258
RDX: 0000000000400000 RSI: ffffa2348bd13e10 RDI: ffff8d5fc5489800
RBP: ffffa2348bd13db0 R08: 0000000000000000 R09: 00007ffffffff000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8d5fc5489800
R13: ffff8d5fcb0f5140 R14: ffff8d5fcb0f5140 R15: 0000000000000000
FS: 00007f991cff9400(0000) GS:ffff8d6f1f700000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c0 CR3: 0000000114888005 CR4: 00000000001706e0
Call Trace:
<TASK>
? aa_sk_perm+0x43/0x1b0
xsk_sendmsg+0xf0/0x110
sock_sendmsg+0x65/0x70
__sys_sendto+0x113/0x190
? debug_smp_processor_id+0x17/0x20
? fpregs_assert_state_consistent+0x23/0x50
? exit_to_user_mode_prepare+0xa5/0x1d0
__x64_sys_sendto+0x29/0x30
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
There are two problems with the current code. First, setting xs->dev to NULL
before waiting for all users to stop using the socket is not correct. The
entry to the data plane functions xsk_poll(), xsk_sendmsg(), and xsk_recvmsg()
are all guarded by a test that xs->state is in the state XSK_BOUND and if not,
it returns right away. But one process might have passed this test but still
have not gotten to the point in which it uses xs->dev in the code. In this
interim, a second process executing xsk_unbind_dev() might have set xs->dev to
NULL which will lead to a crash for the first process. The solution here is
just to get rid of this NULL assignment since it is not used anymore. Before
commit 42fddcc7c6 ("xsk: use state member for socket synchronization"),
xs->dev was the gatekeeper to admit processes into the data plane functions,
but it was replaced with the state variable xs->state in the aforementioned
commit.
The second problem is that synchronize_net() does not wait for any process in
xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() to complete, which means that the
state they rely on might be cleaned up prematurely. This can happen when the
notifier gets called (at driver unload for example) as it uses xsk_unbind_dev().
Solve this by extending the RCU critical region from just the ndo_xsk_wakeup
to the whole functions mentioned above, so that both the test of xs->state ==
XSK_BOUND and the last use of any member of xs is covered by the RCU critical
section. This will guarantee that when synchronize_net() completes, there will
be no processes left executing xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() and
state can be cleaned up safely. Note that we need to drop the RCU lock for the
skb xmit path as it uses functions that might sleep. Due to this, we have to
retest the xs->state after we grab the mutex that protects the skb xmit code
from, among a number of things, an xsk_unbind_dev() being executed from the
notifier at the same time.
Fixes: 42fddcc7c6 ("xsk: use state member for socket synchronization")
Reported-by: Elza Mathew <elza.mathew@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/bpf/20220228094552.10134-1-magnus.karlsson@gmail.com
Move desc_array from the driver to the pool. The reason behind this is
that we can then reuse this array as a temporary storage for descriptors
in all zero-copy drivers that use the batched interface. This will make
it easier to add batching to more drivers.
i40e is the only driver that has a batched Tx zero-copy
implementation, so no need to touch any other driver.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20220125160446.78976-6-maciej.fijalkowski@intel.com
This reverts commit bd0687c18e.
This patch causes a Tx only workload to go to sleep even when it does
not have to, leading to misserable performance in skb mode. It fixed
one rare problem but created a much worse one, so this need to be
reverted while I try to craft a proper solution to the original
problem.
Fixes: bd0687c18e ("xsk: Do not sleep in poll() when need_wakeup set")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211217145646.26449-1-magnus.karlsson@gmail.com
