skb_gro_receive() can currently copy frags between the source and GRO
skb, without checking the zerocopy status, and in particular the
SKBFL_MANAGED_FRAG_REFS flag.
When SKBFL_MANAGED_FRAG_REFS is set, the skb doesn't hold a reference
on the pages in shinfo->frags. Appending those frags to another skb's
frags without fixing up the page refcount can lead to UAF.
When either the last skb in the GRO chain (the one we would append
frags to) or the source skb is zerocopy, don't merge the skbs.
Fixes: 753f1ca4e1 ("net: introduce managed frags infrastructure")
Reported-by: Huzaifa Sidhpurwala <huzaifas@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/c3b7f906bbfcbdfd7b4fa9d6c18a438870df85be.1779307748.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Two frag-transfer helpers (__pskb_copy_fclone() and skb_shift()) fail
to propagate the SKBFL_SHARED_FRAG bit in skb_shinfo()->flags when
moving frags from source to destination. __pskb_copy_fclone() defers
the rest of the shinfo metadata to skb_copy_header() after copying
frag descriptors, but that helper only carries over gso_{size,segs,
type} and never touches skb_shinfo()->flags; skb_shift() moves frag
descriptors directly and leaves flags untouched. As a result, the
destination skb keeps a reference to the same externally-owned or
page-cache-backed pages while reporting skb_has_shared_frag() as
false.
The mismatch is harmful in any in-place writer that uses
skb_has_shared_frag() to decide whether shared pages must be detoured
through skb_cow_data(). ESP input is one such writer (esp4.c,
esp6.c), and a single nft 'dup to <local>' rule -- or any other
nf_dup_ipv4() / xt_TEE caller -- is enough to land a pskb_copy()'d
skb in esp_input() with the marker stripped, letting an unprivileged
user write into the page cache of a root-owned read-only file via
authencesn-ESN stray writes.
Set SKBFL_SHARED_FRAG on the destination whenever frag descriptors
were actually moved from the source. skb_copy() and skb_copy_expand()
share skb_copy_header() too but linearize all paged data into freshly
allocated head storage and emerge with nr_frags == 0, so
skb_has_shared_frag() returns false on its own; they need no change.
The same omission exists in skb_gro_receive() and skb_gro_receive_list().
The former moves the incoming skb's frag descriptors into the
accumulator's last sub-skb via two paths (a direct frag-move loop and
the head_frag + memcpy path); the latter chains the incoming skb whole
onto p's frag_list. Downstream skb_segment() reads only
skb_shinfo(p)->flags, and skb_segment_list() reuses each sub-skb's
shinfo as the nskb -- both p and lp must carry the marker.
The same omission also exists in tcp_clone_payload(), which builds an
MTU probe skb by moving frag descriptors from skbs on sk_write_queue
into a freshly allocated nskb. The helper falls into the same family
and warrants the same fix for consistency; no TCP TX-side in-place
writer is currently known to reach a user page through this gap, but
a future consumer depending on the marker would regress silently.
The same omission exists in skb_segment(): the per-iteration flag
merge takes only head_skb's flag, and the inner switch that rebinds
frag_skb to list_skb on head_skb-frags exhaustion does not fold the
new frag_skb's flag into nskb. Fold frag_skb's flag at both sites
so segments drawing frags from frag_list members carry the marker.
Fixes: cef401de7b ("net: fix possible wrong checksum generation")
Fixes: f4c50a4034 ("xfrm: esp: avoid in-place decrypt on shared skb frags")
Suggested-by: Sabrina Dubroca <sd@queasysnail.net>
Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
Suggested-by: Ben Hutchings <ben@decadent.org.uk>
Suggested-by: Lin Ma <malin89@huawei.com>
Suggested-by: Jingguo Tan <tanjingguo@huawei.com>
Suggested-by: Aaron Esau <aaron1esau@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Tested-by: Rajat Gupta <rajat.gupta@oss.qualcomm.com>
Link: https://patch.msgid.link/ageeJfJHwgzmKXbh@v4bel
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The udp GRO complete stage assumes that all the packets inserted the RX
have the `encapsulation` flag zeroed. Such assumption is not true, as a
few H/W NICs can set such flag when H/W offloading the checksum for
an UDP encapsulated traffic, the tun driver can inject GSO packets with
UDP encapsulation and the problematic layout can also be created via
a veth based setup.
Due to the above, in the problematic scenarios, udp4_gro_complete() uses
the wrong network offset (inner instead of outer) to compute the outer
UDP header pseudo checksum, leading to csum validation errors later on
in packet processing.
Address the issue always clearing the encapsulation flag at GRO completion
time. Such flag will be set again as needed for encapsulated packets by
udp_gro_complete().
Fixes: 5ef31ea5d0 ("net: gro: fix udp bad offset in socket lookup by adding {inner_}network_offset to napi_gro_cb")
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/562638dbebb3b15424220e26a180274b387e2a88.1770032084.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Some network drivers assume this field is zero after napi_get_frags().
We must clear it in napi_reuse_skb() otherwise the following can happen:
1) A packet is received, and skb_shinfo(skb)->hwtstamps is populated
because a bit in the receive descriptor announced hwtstamp
availability for this packet.
2) Packet is given to gro layer via napi_gro_frags().
3) Packet is merged to a prior one held in GRO queues.
4) skb is saved after some cleanup in napi->skb via a call
to napi_reuse_skb().
5) Next packet is received 10 seconds later, gets the recycled skb
from napi_get_frags().
6) The receive descriptor does not announce hwtstamp availability.
Driver does not clear shinfo->hwtstamps.
7) We have in shinfo->hwtstamps an old timestamp.
Fixes: ac45f602ee ("net: infrastructure for hardware time stamping")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20251015063221.4171986-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add validation points and state propagation to support PSP key
exchange inline, on TCP connections. The expectation is that
application will use some well established mechanism like TLS
handshake to establish a secure channel over the connection and
if both endpoints are PSP-capable - exchange and install PSP keys.
Because the connection can existing in PSP-unsecured and PSP-secured
state we need to make sure that there are no race conditions or
retransmission leaks.
On Tx - mark packets with the skb->decrypted bit when PSP key
is at the enqueue time. Drivers should only encrypt packets with
this bit set. This prevents retransmissions getting encrypted when
original transmission was not. Similarly to TLS, we'll use
sk->sk_validate_xmit_skb to make sure PSP skbs can't "escape"
via a PSP-unaware device without being encrypted.
On Rx - validation is done under socket lock. This moves the validation
point later than xfrm, for example. Please see the documentation patch
for more details on the flow of securing a connection, but for
the purpose of this patch what's important is that we want to
enforce the invariant that once connection is secured any skb
in the receive queue has been encrypted with PSP.
Add GRO and coalescing checks to prevent PSP authenticated data from
being combined with cleartext data, or data with non-matching PSP
state. On Rx, check skb's with psp_skb_coalesce_diff() at points
before psp_sk_rx_policy_check(). After skb's are policy checked and on
the socket receive queue, skb_cmp_decrypted() is sufficient for
checking for coalescable PSP state. On Tx, tcp_write_collapse_fence()
should be called when transitioning a socket into PSP Tx state to
prevent data sent as cleartext from being coalesced with PSP
encapsulated data.
This change only adds the validation points, for ease of review.
Subsequent change will add the ability to install keys, and flesh
the enforcement logic out
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Co-developed-by: Daniel Zahka <daniel.zahka@gmail.com>
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250917000954.859376-5-daniel.zahka@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Make GRO init and cleanup functions global to be able to use GRO
without a NAPI instance. Taking into account already global gro_flush(),
it's now fully usable standalone.
New functions are not exported, since they're not supposed to be used
outside of the kernel core code.
Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In fact, these two are not tied closely to each other. The only
requirements to GRO are to use it in the BH context and have some
sane limits on the packet batches, e.g. NAPI has a limit of its
budget (64/8/etc.).
Move purely GRO fields into a new structure, &gro_node. Embed it
into &napi_struct and adjust all the references.
gro_node::cached_napi_id is effectively the same as
napi_struct::napi_id, but to be used on GRO hotpath to mark skbs.
napi_struct::napi_id is now a fully control path field.
Three Ethernet drivers use napi_gro_flush() not really meant to be
exported, so move it to <net/gro.h> and add that include there.
napi_gro_receive() is used in more than 100 drivers, keep it
in <linux/netdevice.h>.
This does not make GRO ready to use outside of the NAPI context
yet.
Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In certain cases, napi_get_frags() returns an skb that points to an old
received fragment, This skb may have its skb->ip_summed, csum, and other
fields set from previous fragment handling.
Some network drivers set skb->ip_summed to either CHECKSUM_COMPLETE or
CHECKSUM_UNNECESSARY when getting skb from napi_get_frags(), while
others only set skb->ip_summed when RX checksum offload is enabled on
the device, and do not set any value for skb->ip_summed when hardware
checksum offload is disabled, assuming that the skb->ip_summed
initiated to zero by napi_reuse_skb, ionic driver for example will
ignore/unset any value for the ip_summed filed if HW checksum offload is
disabled, and if we have a situation where the user disables the
checksum offload during a traffic that could lead to the following
errors shown in the kernel logs:
<IRQ>
dump_stack_lvl+0x34/0x48
__skb_gro_checksum_complete+0x7e/0x90
tcp6_gro_receive+0xc6/0x190
ipv6_gro_receive+0x1ec/0x430
dev_gro_receive+0x188/0x360
? ionic_rx_clean+0x25a/0x460 [ionic]
napi_gro_frags+0x13c/0x300
? __pfx_ionic_rx_service+0x10/0x10 [ionic]
ionic_rx_service+0x67/0x80 [ionic]
ionic_cq_service+0x58/0x90 [ionic]
ionic_txrx_napi+0x64/0x1b0 [ionic]
__napi_poll+0x27/0x170
net_rx_action+0x29c/0x370
handle_softirqs+0xce/0x270
__irq_exit_rcu+0xa3/0xc0
common_interrupt+0x80/0xa0
</IRQ>
This inconsistency sometimes leads to checksum validation issues in the
upper layers of the network stack.
To resolve this, this patch clears the skb->ip_summed value for each
reused skb in by napi_reuse_skb(), ensuring that the caller is responsible
for setting the correct checksum status. This eliminates potential
checksum validation issues caused by improper handling of
skb->ip_summed.
Fixes: 76620aafd6 ("gro: New frags interface to avoid copying shinfo")
Signed-off-by: Mohammad Heib <mheib@redhat.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250225112852.2507709-1-mheib@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Sabrina reported the following splat:
WARNING: CPU: 0 PID: 1 at net/core/dev.c:6935 netif_napi_add_weight_locked+0x8f2/0xba0
Modules linked in:
CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.14.0-rc1-net-00092-g011b03359038 #996
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014
RIP: 0010:netif_napi_add_weight_locked+0x8f2/0xba0
Code: e8 c3 e6 6a fe 48 83 c4 28 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc c7 44 24 10 ff ff ff ff e9 8f fb ff ff e8 9e e6 6a fe <0f> 0b e9 d3 fe ff ff e8 92 e6 6a fe 48 8b 04 24 be ff ff ff ff 48
RSP: 0000:ffffc9000001fc60 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff88806ce48128 RCX: 1ffff11001664b9e
RDX: ffff888008f00040 RSI: ffffffff8317ca42 RDI: ffff88800b325cb6
RBP: ffff88800b325c40 R08: 0000000000000001 R09: ffffed100167502c
R10: ffff88800b3a8163 R11: 0000000000000000 R12: ffff88800ac1c168
R13: ffff88800ac1c168 R14: ffff88800ac1c168 R15: 0000000000000007
FS: 0000000000000000(0000) GS:ffff88806ce00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff888008201000 CR3: 0000000004c94001 CR4: 0000000000370ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
gro_cells_init+0x1ba/0x270
xfrm_input_init+0x4b/0x2a0
xfrm_init+0x38/0x50
ip_rt_init+0x2d7/0x350
ip_init+0xf/0x20
inet_init+0x406/0x590
do_one_initcall+0x9d/0x2e0
do_initcalls+0x23b/0x280
kernel_init_freeable+0x445/0x490
kernel_init+0x20/0x1d0
ret_from_fork+0x46/0x80
ret_from_fork_asm+0x1a/0x30
</TASK>
irq event stamp: 584330
hardirqs last enabled at (584338): [<ffffffff8168bf87>] __up_console_sem+0x77/0xb0
hardirqs last disabled at (584345): [<ffffffff8168bf6c>] __up_console_sem+0x5c/0xb0
softirqs last enabled at (583242): [<ffffffff833ee96d>] netlink_insert+0x14d/0x470
softirqs last disabled at (583754): [<ffffffff8317c8cd>] netif_napi_add_weight_locked+0x77d/0xba0
on kernel built with MAX_SKB_FRAGS=45, where SKB_WITH_OVERHEAD(1024)
is smaller than GRO_MAX_HEAD.
Such built additionally contains the revert of the single page frag cache
so that napi_get_frags() ends up using the page frag allocator, triggering
the splat.
Note that the underlying issue is independent from the mentioned
revert; address it ensuring that the small head cache will fit either TCP
and GRO allocation and updating napi_alloc_skb() and __netdev_alloc_skb()
to select kmalloc() usage for any allocation fitting such cache.
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Suggested-by: Eric Dumazet <edumazet@google.com>
Fixes: 3948b05950 ("net: introduce a config option to tweak MAX_SKB_FRAGS")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
{inet,ipv6}_gro_receive functions perform flush checks (ttl, flags,
iph->id, ...) against all packets in a loop. These flush checks are used in
all merging UDP and TCP flows.
These checks need to be done only once and only against the found p skb,
since they only affect flush and not same_flow.
This patch leverages correct network header offsets from the cb for both
outer and inner network headers - allowing these checks to be done only
once, in tcp_gro_receive and udp_gro_receive_segment. As a result,
NAPI_GRO_CB(p)->flush is not used at all. In addition, flush_id checks are
more declarative and contained in inet_gro_flush, thus removing the need
for flush_id in napi_gro_cb.
This results in less parsing code for non-loop flush tests for TCP and UDP
flows.
To make sure results are not within noise range - I've made netfilter drop
all TCP packets, and measured CPU performance in GRO (in this case GRO is
responsible for about 50% of the CPU utilization).
perf top while replaying 64 parallel IP/TCP streams merging in GRO:
(gro_receive_network_flush is compiled inline to tcp_gro_receive)
net-next:
6.94% [kernel] [k] inet_gro_receive
3.02% [kernel] [k] tcp_gro_receive
patch applied:
4.27% [kernel] [k] tcp_gro_receive
4.22% [kernel] [k] inet_gro_receive
perf top while replaying 64 parallel IP/IP/TCP streams merging in GRO (same
results for any encapsulation, in this case inet_gro_receive is top
offender in net-next)
net-next:
10.09% [kernel] [k] inet_gro_receive
2.08% [kernel] [k] tcp_gro_receive
patch applied:
6.97% [kernel] [k] inet_gro_receive
3.68% [kernel] [k] tcp_gro_receive
Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240509190819.2985-3-richardbgobert@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commits a602456 ("udp: Add GRO functions to UDP socket") and 57c67ff ("udp:
additional GRO support") introduce incorrect usage of {ip,ipv6}_hdr in the
complete phase of gro. The functions always return skb->network_header,
which in the case of encapsulated packets at the gro complete phase, is
always set to the innermost L3 of the packet. That means that calling
{ip,ipv6}_hdr for skbs which completed the GRO receive phase (both in
gro_list and *_gro_complete) when parsing an encapsulated packet's _outer_
L3/L4 may return an unexpected value.
This incorrect usage leads to a bug in GRO's UDP socket lookup.
udp{4,6}_lib_lookup_skb functions use ip_hdr/ipv6_hdr respectively. These
*_hdr functions return network_header which will point to the innermost L3,
resulting in the wrong offset being used in __udp{4,6}_lib_lookup with
encapsulated packets.
This patch adds network_offset and inner_network_offset to napi_gro_cb, and
makes sure both are set correctly.
To fix the issue, network_offsets union is used inside napi_gro_cb, in
which both the outer and the inner network offsets are saved.
Reproduction example:
Endpoint configuration example (fou + local address bind)
# ip fou add port 6666 ipproto 4
# ip link add name tun1 type ipip remote 2.2.2.1 local 2.2.2.2 encap fou encap-dport 5555 encap-sport 6666 mode ipip
# ip link set tun1 up
# ip a add 1.1.1.2/24 dev tun1
Netperf TCP_STREAM result on net-next before patch is applied:
net-next main, GRO enabled:
$ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
131072 16384 16384 5.28 2.37
net-next main, GRO disabled:
$ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
131072 16384 16384 5.01 2745.06
patch applied, GRO enabled:
$ netperf -H 1.1.1.2 -t TCP_STREAM -l 5
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
131072 16384 16384 5.01 2877.38
Fixes: a6024562ff ("udp: Add GRO functions to UDP socket")
Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add a new header, linux/skbuff_ref.h, which contains all the skb_*_ref()
helpers. Many of the consumers of skbuff.h do not actually use any of
the skb ref helpers, and we can speed up compilation a bit by minimizing
this header file.
Additionally in the later patch in the series we add page_pool support
to skb_frag_ref(), which requires some page_pool dependencies. We can
now add these dependencies to skbuff_ref.h instead of a very ubiquitous
skbuff.h
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://lore.kernel.org/r/20240410190505.1225848-2-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If packets are GROed with fraglist they might be segmented later on and
continue their journey in the stack. In skb_segment_list those skbs can
be reused as-is. This is an issue as their destructor was removed in
skb_gro_receive_list but not the reference to their socket, and then
they can't be orphaned. Fix this by also removing the reference to the
socket.
For example this could be observed,
kernel BUG at include/linux/skbuff.h:3131! (skb_orphan)
RIP: 0010:ip6_rcv_core+0x11bc/0x19a0
Call Trace:
ipv6_list_rcv+0x250/0x3f0
__netif_receive_skb_list_core+0x49d/0x8f0
netif_receive_skb_list_internal+0x634/0xd40
napi_complete_done+0x1d2/0x7d0
gro_cell_poll+0x118/0x1f0
A similar construction is found in skb_gro_receive, apply the same
change there.
Fixes: 5e10da5385 ("skbuff: allow 'slow_gro' for skb carring sock reference")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently the so-called GRO fast path is only enabled for
napi_frags_skb() callers.
After the prior patch, we no longer have to clear frag0 whenever
we pulled bytes to skb->head.
We therefore can initialize frag0 to skb->data so that GRO
fast path can be used in the following additional cases:
- Drivers using header split (populating skb->data with headers,
and having payload in one or more page fragments).
- Drivers not using any page frag (entire packet is in skb->data)
Add a likely() in skb_gro_may_pull() to help the compiler
to generate better code if possible.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
skb_gro_header_hard() is renamed to skb_gro_may_pull() to match
the convention used by common helpers like pskb_may_pull().
This means the condition is inverted:
if (skb_gro_header_hard(skb, hlen))
slow_path();
becomes:
if (!skb_gro_may_pull(skb, hlen))
slow_path();
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
