The decompression code parses a huffman tree and counts the number of
symbols for a given bit length. In rare cases, there may be >= 256
symbols with a given bit length, causing the unsigned char to overflow.
This causes a decompression failure later when the code tries and fails to
find the bit length for a given symbol.
Since the maximum number of symbols is 258, use unsigned short instead.
Link: https://lkml.kernel.org/r/20240717162016.1514077-1-ross.lagerwall@citrix.com
Fixes: bc22c17e12 ("bzip2/lzma: library support for gzip, bzip2 and lzma decompression")
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Cc: Alain Knaff <alain@knaff.lu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Commit 3bd786f76d ("mm: convert do_set_pte() to set_pte_range()")
replaced do_set_pte() with set_pte_range() and that introduced a
regression in the following faulting path of non-anonymous vmas which
caused the PTE for the faulting address to be marked as old instead of
young.
handle_pte_fault()
do_pte_missing()
do_fault()
do_read_fault() || do_cow_fault() || do_shared_fault()
finish_fault()
set_pte_range()
The polarity of prefault calculation is incorrect. This leads to prefault
being incorrectly set for the faulting address. The following check will
incorrectly mark the PTE old rather than young. On some architectures
this will cause a double fault to mark it young when the access is
retried.
if (prefault && arch_wants_old_prefaulted_pte())
entry = pte_mkold(entry);
On a subsequent fault on the same address, the faulting path will see a
non NULL vmf->pte and instead of reaching the do_pte_missing() path, PTE
will then be correctly marked young in handle_pte_fault() itself.
Due to this bug, performance degradation in the fault handling path will
be observed due to unnecessary double faulting.
Link: https://lkml.kernel.org/r/20240710014539.746200-1-rtummala@nvidia.com
Fixes: 3bd786f76d ("mm: convert do_set_pte() to set_pte_range()")
Signed-off-by: Ram Tummala <rtummala@nvidia.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf and netfilter.
A lot of networking people were at a conference last week, busy
catching COVID, so relatively short PR.
Current release - regressions:
- tcp: process the 3rd ACK with sk_socket for TFO and MPTCP
Current release - new code bugs:
- l2tp: protect session IDR and tunnel session list with one lock,
make sure the state is coherent to avoid a warning
- eth: bnxt_en: update xdp_rxq_info in queue restart logic
- eth: airoha: fix location of the MBI_RX_AGE_SEL_MASK field
Previous releases - regressions:
- xsk: require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len,
the field reuses previously un-validated pad
Previous releases - always broken:
- tap/tun: drop short frames to prevent crashes later in the stack
- eth: ice: add a per-VF limit on number of FDIR filters
- af_unix: disable MSG_OOB handling for sockets in sockmap/sockhash"
* tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (34 commits)
tun: add missing verification for short frame
tap: add missing verification for short frame
mISDN: Fix a use after free in hfcmulti_tx()
gve: Fix an edge case for TSO skb validity check
bnxt_en: update xdp_rxq_info in queue restart logic
tcp: process the 3rd ACK with sk_socket for TFO/MPTCP
selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test
xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len
bpf: Fix a segment issue when downgrading gso_size
net: mediatek: Fix potential NULL pointer dereference in dummy net_device handling
MAINTAINERS: make Breno the netconsole maintainer
MAINTAINERS: Update bonding entry
net: nexthop: Initialize all fields in dumped nexthops
net: stmmac: Correct byte order of perfect_match
selftests: forwarding: skip if kernel not support setting bridge fdb learning limit
tipc: Return non-zero value from tipc_udp_addr2str() on error
netfilter: nft_set_pipapo_avx2: disable softinterrupts
ice: Fix recipe read procedure
ice: Add a per-VF limit on number of FDIR filters
net: bonding: correctly annotate RCU in bond_should_notify_peers()
...
Pull printk updates from Petr Mladek:
- trivial printk changes
The bigger "real" printk work is still being discussed.
* tag 'printk-for-6.11-trivial' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux:
vsprintf: add missing MODULE_DESCRIPTION() macro
printk: Rename console_replay_all() and update context
Pull sysctl constification from Joel Granados:
"Treewide constification of the ctl_table argument of proc_handlers
using a coccinelle script and some manual code formatting fixups.
This is a prerequisite to moving the static ctl_table structs into
read-only data section which will ensure that proc_handler function
pointers cannot be modified"
* tag 'constfy-sysctl-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl:
sysctl: treewide: constify the ctl_table argument of proc_handlers
Pull EFI fixes from Ard Biesheuvel:
- Wipe screen_info after allocating it from the heap - used by arm32
and EFI zboot, other EFI architectures allocate it statically
- Revert to allocating boot_params from the heap on x86 when entering
via the native PE entrypoint, to work around a regression on older
Dell hardware
* tag 'efi-fixes-for-v6.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi:
x86/efistub: Revert to heap allocated boot_params for PE entrypoint
efi/libstub: Zero initialize heap allocated struct screen_info
Pull kgdb updates from Daniel Thompson:
"Three small changes this cycle:
- Clean up an architecture abstraction that is no longer needed
because all the architectures have converged.
- Actually use the prompt argument to kdb_position_cursor() instead
of ignoring it (functionally this fix is a nop but that was due to
luck rather than good judgement)
- Fix a -Wformat-security warning"
* tag 'kgdb-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/danielt/linux:
kdb: Get rid of redundant kdb_curr_task()
kdb: Use the passed prompt in kdb_position_cursor()
kdb: address -Wformat-security warnings
Pull MIPS updates from Thomas Bogendoerfer:
- Use improved timer sync for Loongson64
- Fix address of GCR_ACCESS register
- Add missing MODULE_DESCRIPTION
* tag 'mips_6.11_1' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
mips: sibyte: add missing MODULE_DESCRIPTION() macro
MIPS: SMP-CPS: Fix address for GCR_ACCESS register for CM3 and later
MIPS: Loongson64: Switch to SYNC_R4K
Pull parisc updates from Helge Deller:
"The gettimeofday() and clock_gettime() syscalls are now available as
vDSO functions, and Dave added a patch which allows to use NVMe cards
in the PCI slots as fast and easy alternative to SCSI discs.
Summary:
- add gettimeofday() and clock_gettime() vDSO functions
- enable PCI_MSI_ARCH_FALLBACKS to allow PCI to PCIe bridge adaptor
with PCIe NVME card to function in parisc machines
- allow users to reduce kernel unaligned runtime warnings
- minor code cleanups"
* tag 'parisc-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Add support for CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
parisc: Use max() to calculate parisc_tlb_flush_threshold
parisc: Fix warning at drivers/pci/msi/msi.h:121
parisc: Add 64-bit gettimeofday() and clock_gettime() vDSO functions
parisc: Add 32-bit gettimeofday() and clock_gettime() vDSO functions
parisc: Clean up unistd.h file
Pull UML updates from Richard Weinberger:
- Support for preemption
- i386 Rust support
- Huge cleanup by Benjamin Berg
- UBSAN support
- Removal of dead code
* tag 'uml-for-linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux: (41 commits)
um: vector: always reset vp->opened
um: vector: remove vp->lock
um: register power-off handler
um: line: always fill *error_out in setup_one_line()
um: remove pcap driver from documentation
um: Enable preemption in UML
um: refactor TLB update handling
um: simplify and consolidate TLB updates
um: remove force_flush_all from fork_handler
um: Do not flush MM in flush_thread
um: Delay flushing syscalls until the thread is restarted
um: remove copy_context_skas0
um: remove LDT support
um: compress memory related stub syscalls while adding them
um: Rework syscall handling
um: Add generic stub_syscall6 function
um: Create signal stack memory assignment in stub_data
um: Remove stub-data.h include from common-offsets.h
um: time-travel: fix signal blocking race/hang
um: time-travel: remove time_exit()
...
Pull driver core updates from Greg KH:
"Here is the big set of driver core changes for 6.11-rc1.
Lots of stuff in here, with not a huge diffstat, but apis are evolving
which required lots of files to be touched. Highlights of the changes
in here are:
- platform remove callback api final fixups (Uwe took many releases
to get here, finally!)
- Rust bindings for basic firmware apis and initial driver-core
interactions.
It's not all that useful for a "write a whole driver in rust" type
of thing, but the firmware bindings do help out the phy rust
drivers, and the driver core bindings give a solid base on which
others can start their work.
There is still a long way to go here before we have a multitude of
rust drivers being added, but it's a great first step.
- driver core const api changes.
This reached across all bus types, and there are some fix-ups for
some not-common bus types that linux-next and 0-day testing shook
out.
This work is being done to help make the rust bindings more safe,
as well as the C code, moving toward the end-goal of allowing us to
put driver structures into read-only memory. We aren't there yet,
but are getting closer.
- minor devres cleanups and fixes found by code inspection
- arch_topology minor changes
- other minor driver core cleanups
All of these have been in linux-next for a very long time with no
reported problems"
* tag 'driver-core-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (55 commits)
ARM: sa1100: make match function take a const pointer
sysfs/cpu: Make crash_hotplug attribute world-readable
dio: Have dio_bus_match() callback take a const *
zorro: make match function take a const pointer
driver core: module: make module_[add|remove]_driver take a const *
driver core: make driver_find_device() take a const *
driver core: make driver_[create|remove]_file take a const *
firmware_loader: fix soundness issue in `request_internal`
firmware_loader: annotate doctests as `no_run`
devres: Correct code style for functions that return a pointer type
devres: Initialize an uninitialized struct member
devres: Fix memory leakage caused by driver API devm_free_percpu()
devres: Fix devm_krealloc() wasting memory
driver core: platform: Switch to use kmemdup_array()
driver core: have match() callback in struct bus_type take a const *
MAINTAINERS: add Rust device abstractions to DRIVER CORE
device: rust: improve safety comments
MAINTAINERS: add Danilo as FIRMWARE LOADER maintainer
MAINTAINERS: add Rust FW abstractions to FIRMWARE LOADER
firmware: rust: improve safety comments
...
Pull watchdog updates from Wim Van Sebroeck:
- make watchdog_class const
- rework of the rzg2l_wdt driver
- other small fixes and improvements
* tag 'linux-watchdog-6.11-rc1' of git://www.linux-watchdog.org/linux-watchdog:
dt-bindings: watchdog: dlg,da9062-watchdog: Drop blank space
watchdog: rzn1: Convert comma to semicolon
watchdog: lenovo_se10_wdt: Convert comma to semicolon
dt-bindings: watchdog: renesas,wdt: Document RZ/G3S support
watchdog: rzg2l_wdt: Add suspend/resume support
watchdog: rzg2l_wdt: Rely on the reset driver for doing proper reset
watchdog: rzg2l_wdt: Remove comparison with zero
watchdog: rzg2l_wdt: Remove reset de-assert from probe
watchdog: rzg2l_wdt: Check return status of pm_runtime_put()
watchdog: rzg2l_wdt: Use pm_runtime_resume_and_get()
watchdog: rzg2l_wdt: Make the driver depend on PM
watchdog: rzg2l_wdt: Restrict the driver to ARCH_RZG2L and ARCH_R9A09G011
watchdog: imx7ulp_wdt: keep already running watchdog enabled
watchdog: starfive: Add missing clk_disable_unprepare()
watchdog: Make watchdog_class const
Pull dma-mapping fix from Christoph Hellwig:
- fix the order of actions in dmam_free_coherent (Lance Richardson)
* tag 'dma-mapping-6.11-2024-07-24' of git://git.infradead.org/users/hch/dma-mapping:
dma: fix call order in dmam_free_coherent
Dongli Zhang says:
====================
tap/tun: harden by dropping short frame
This is to harden all of tap/tun to avoid any short frame smaller than the
Ethernet header (ETH_HLEN).
While the xen-netback already rejects short frame smaller than ETH_HLEN ...
914 static void xenvif_tx_build_gops(struct xenvif_queue *queue,
915 int budget,
916 unsigned *copy_ops,
917 unsigned *map_ops)
918 {
... ...
1007 if (unlikely(txreq.size < ETH_HLEN)) {
1008 netdev_dbg(queue->vif->dev,
1009 "Bad packet size: %d\n", txreq.size);
1010 xenvif_tx_err(queue, &txreq, extra_count, idx);
1011 break;
1012 }
... the short frame may not be dropped by vhost-net/tap/tun.
This fixes CVE-2024-41090 and CVE-2024-41091.
====================
Link: https://patch.msgid.link/20240724170452.16837-1-dongli.zhang@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The cited commit missed to check against the validity of the frame length
in the tun_xdp_one() path, which could cause a corrupted skb to be sent
downstack. Even before the skb is transmitted, the
tun_xdp_one-->eth_type_trans() may access the Ethernet header although it
can be less than ETH_HLEN. Once transmitted, this could either cause
out-of-bound access beyond the actual length, or confuse the underlayer
with incorrect or inconsistent header length in the skb metadata.
In the alternative path, tun_get_user() already prohibits short frame which
has the length less than Ethernet header size from being transmitted for
IFF_TAP.
This is to drop any frame shorter than the Ethernet header size just like
how tun_get_user() does.
CVE: CVE-2024-41091
Inspired-by: https://lore.kernel.org/netdev/1717026141-25716-1-git-send-email-si-wei.liu@oracle.com/
Fixes: 043d222f93 ("tuntap: accept an array of XDP buffs through sendmsg()")
Cc: stable@vger.kernel.org
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Si-Wei Liu <si-wei.liu@oracle.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240724170452.16837-3-dongli.zhang@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The cited commit missed to check against the validity of the frame length
in the tap_get_user_xdp() path, which could cause a corrupted skb to be
sent downstack. Even before the skb is transmitted, the
tap_get_user_xdp()-->skb_set_network_header() may assume the size is more
than ETH_HLEN. Once transmitted, this could either cause out-of-bound
access beyond the actual length, or confuse the underlayer with incorrect
or inconsistent header length in the skb metadata.
In the alternative path, tap_get_user() already prohibits short frame which
has the length less than Ethernet header size from being transmitted.
This is to drop any frame shorter than the Ethernet header size just like
how tap_get_user() does.
CVE: CVE-2024-41090
Link: https://lore.kernel.org/netdev/1717026141-25716-1-git-send-email-si-wei.liu@oracle.com/
Fixes: 0efac27791 ("tap: accept an array of XDP buffs through sendmsg()")
Cc: stable@vger.kernel.org
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240724170452.16837-2-dongli.zhang@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The NIC requires each TSO segment to not span more than 10
descriptors. NIC further requires each descriptor to not exceed
16KB - 1 (GVE_TX_MAX_BUF_SIZE_DQO).
The descriptors for an skb are generated by
gve_tx_add_skb_no_copy_dqo() for DQO RDA queue format.
gve_tx_add_skb_no_copy_dqo() loops through each skb frag and
generates a descriptor for the entire frag if the frag size is
not greater than GVE_TX_MAX_BUF_SIZE_DQO. If the frag size is
greater than GVE_TX_MAX_BUF_SIZE_DQO, it is split into descriptor(s)
of size GVE_TX_MAX_BUF_SIZE_DQO and a descriptor is generated for
the remainder (frag size % GVE_TX_MAX_BUF_SIZE_DQO).
gve_can_send_tso() checks if the descriptors thus generated for an
skb would meet the requirement that each TSO-segment not span more
than 10 descriptors. However, the current code misses an edge case
when a TSO segment spans multiple descriptors within a large frag.
This change fixes the edge case.
gve_can_send_tso() relies on the assumption that max gso size (9728)
is less than GVE_TX_MAX_BUF_SIZE_DQO and therefore within an skb
fragment a TSO segment can never span more than 2 descriptors.
Fixes: a57e5de476 ("gve: DQO: Add TX path")
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Reviewed-by: Jeroen de Borst <jeroendb@google.com>
Cc: stable@vger.kernel.org
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240724143431.3343722-1-pkaligineedi@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When the netdev_rx_queue_restart() restarts queues, the bnxt_en driver
updates(creates and deletes) a page_pool.
But it doesn't update xdp_rxq_info, so the xdp_rxq_info is still
connected to an old page_pool.
So, bnxt_rx_ring_info->page_pool indicates a new page_pool, but
bnxt_rx_ring_info->xdp_rxq is still connected to an old page_pool.
An old page_pool is no longer used so it is supposed to be
deleted by page_pool_destroy() but it isn't.
Because the xdp_rxq_info is holding the reference count for it and the
xdp_rxq_info is not updated, an old page_pool will not be deleted in
the queue restart logic.
Before restarting 1 queue:
./tools/net/ynl/samples/page-pool
enp10s0f1np1[6] page pools: 4 (zombies: 0)
refs: 8192 bytes: 33554432 (refs: 0 bytes: 0)
recycling: 0.0% (alloc: 128:8048 recycle: 0:0)
After restarting 1 queue:
./tools/net/ynl/samples/page-pool
enp10s0f1np1[6] page pools: 5 (zombies: 0)
refs: 10240 bytes: 41943040 (refs: 0 bytes: 0)
recycling: 20.0% (alloc: 160:10080 recycle: 1920:128)
Before restarting queues, an interface has 4 page_pools.
After restarting one queue, an interface has 5 page_pools, but it
should be 4, not 5.
The reason is that queue restarting logic creates a new page_pool and
an old page_pool is not deleted due to the absence of an update of
xdp_rxq_info logic.
Fixes: 2d694c27d3 ("bnxt_en: implement netdev_queue_mgmt_ops")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: David Wei <dw@davidwei.uk>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://patch.msgid.link/20240721053554.1233549-1-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Daniel Borkmann says:
====================
pull-request: bpf 2024-07-25
We've added 14 non-merge commits during the last 8 day(s) which contain
a total of 19 files changed, 177 insertions(+), 70 deletions(-).
The main changes are:
1) Fix af_unix to disable MSG_OOB handling for sockets in BPF sockmap and
BPF sockhash. Also add test coverage for this case, from Michal Luczaj.
2) Fix a segmentation issue when downgrading gso_size in the BPF helper
bpf_skb_adjust_room(), from Fred Li.
3) Fix a compiler warning in resolve_btfids due to a missing type cast,
from Liwei Song.
4) Fix stack allocation for arm64 to align the stack pointer at a 16 byte
boundary in the fexit_sleep BPF selftest, from Puranjay Mohan.
5) Fix a xsk regression to require a flag when actuating tx_metadata_len,
from Stanislav Fomichev.
6) Fix function prototype BTF dumping in libbpf for prototypes that have
no input arguments, from Andrii Nakryiko.
7) Fix stacktrace symbol resolution in perf script for BPF programs
containing subprograms, from Hou Tao.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test
xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len
bpf: Fix a segment issue when downgrading gso_size
tools/resolve_btfids: Fix comparison of distinct pointer types warning in resolve_btfids
bpf, events: Use prog to emit ksymbol event for main program
selftests/bpf: Test sockmap redirect for AF_UNIX MSG_OOB
selftests/bpf: Parametrize AF_UNIX redir functions to accept send() flags
selftests/bpf: Support SOCK_STREAM in unix_inet_redir_to_connected()
af_unix: Disable MSG_OOB handling for sockets in sockmap/sockhash
bpftool: Fix typo in usage help
libbpf: Fix no-args func prototype BTF dumping syntax
MAINTAINERS: Update powerpc BPF JIT maintainers
MAINTAINERS: Update email address of Naveen
selftests/bpf: fexit_sleep: Fix stack allocation for arm64
====================
Link: https://patch.msgid.link/20240725114312.32197-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The 'Fixes' commit recently changed the behaviour of TCP by skipping the
processing of the 3rd ACK when a sk->sk_socket is set. The goal was to
skip tcp_ack_snd_check() in tcp_rcv_state_process() not to send an
unnecessary ACK in case of simultaneous connect(). Unfortunately, that
had an impact on TFO and MPTCP.
I started to look at the impact on MPTCP, because the MPTCP CI found
some issues with the MPTCP Packetdrill tests [1]. Then Paolo Abeni
suggested me to look at the impact on TFO with "plain" TCP.
For MPTCP, when receiving the 3rd ACK of a request adding a new path
(MP_JOIN), sk->sk_socket will be set, and point to the MPTCP sock that
has been created when the MPTCP connection got established before with
the first path. The newly added 'goto' will then skip the processing of
the segment text (step 7) and not go through tcp_data_queue() where the
MPTCP options are validated, and some actions are triggered, e.g.
sending the MPJ 4th ACK [2] as demonstrated by the new errors when
running a packetdrill test [3] establishing a second subflow.
This doesn't fully break MPTCP, mainly the 4th MPJ ACK that will be
delayed. Still, we don't want to have this behaviour as it delays the
switch to the fully established mode, and invalid MPTCP options in this
3rd ACK will not be caught any more. This modification also affects the
MPTCP + TFO feature as well, and being the reason why the selftests
started to be unstable the last few days [4].
For TFO, the existing 'basic-cookie-not-reqd' test [5] was no longer
passing: if the 3rd ACK contains data, and the connection is accept()ed
before receiving them, these data would no longer be processed, and thus
not ACKed.
One last thing about MPTCP, in case of simultaneous connect(), a
fallback to TCP will be done, which seems fine:
`../common/defaults.sh`
0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_MPTCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+0 > S 0:0(0) <mss 1460, sackOK, TS val 100 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 < S 0:0(0) win 1000 <mss 1460, sackOK, TS val 407 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 > S. 0:0(0) ack 1 <mss 1460, sackOK, TS val 330 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 < S. 0:0(0) ack 1 win 65535 <mss 1460, sackOK, TS val 700 ecr 100, nop, wscale 8, mpcapable v1 flags[flag_h] key[skey=2]>
+0 > . 1:1(0) ack 1 <nop, nop, TS val 845707014 ecr 700, nop, nop, sack 0:1>
Simultaneous SYN-data crossing is also not supported by TFO, see [6].
Kuniyuki Iwashima suggested to restrict the processing to SYN+ACK only:
that's a more generic solution than the one initially proposed, and
also enough to fix the issues described above.
Later on, Eric Dumazet mentioned that an ACK should still be sent in
reaction to the second SYN+ACK that is received: not sending a DUPACK
here seems wrong and could hurt:
0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+0 > S 0:0(0) <mss 1460, sackOK, TS val 1000 ecr 0,nop,wscale 8>
+0 < S 0:0(0) win 1000 <mss 1000, sackOK, nop, nop>
+0 > S. 0:0(0) ack 1 <mss 1460, sackOK, TS val 3308134035 ecr 0,nop,wscale 8>
+0 < S. 0:0(0) ack 1 win 1000 <mss 1000, sackOK, nop, nop>
+0 > . 1:1(0) ack 1 <nop, nop, sack 0:1> // <== Here
So in this version, the 'goto consume' is dropped, to always send an ACK
when switching from TCP_SYN_RECV to TCP_ESTABLISHED. This ACK will be
seen as a DUPACK -- with DSACK if SACK has been negotiated -- in case of
simultaneous SYN crossing: that's what is expected here.
Link: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/9936227696 [1]
Link: https://datatracker.ietf.org/doc/html/rfc8684#fig_tokens [2]
Link: https://github.com/multipath-tcp/packetdrill/blob/mptcp-net-next/gtests/net/mptcp/syscalls/accept.pkt#L28 [3]
Link: https://netdev.bots.linux.dev/contest.html?executor=vmksft-mptcp-dbg&test=mptcp-connect-sh [4]
Link: https://github.com/google/packetdrill/blob/master/gtests/net/tcp/fastopen/server/basic-cookie-not-reqd.pkt#L21 [5]
Link: https://github.com/google/packetdrill/blob/master/gtests/net/tcp/fastopen/client/simultaneous-fast-open.pkt [6]
Fixes: 23e89e8ee7 ("tcp: Don't drop SYN+ACK for simultaneous connect().")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240724-upstream-net-next-20240716-tcp-3rd-ack-consume-sk_socket-v3-1-d48339764ce9@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
