2019-05-19 13:08:55 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-05-05 16:16:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
|
|
|
|
|
2021-03-27 04:42:38 +05:30
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-12-24 11:46:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-10-19 16:08:53 -04:00
|
|
|
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 17:04:11 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv4: Convert ->flowi4_tos to dscp_t.
Convert the ->flowic_tos field of struct flowi_common from __u8 to
dscp_t, rename it ->flowic_dscp and propagate these changes to struct
flowi and struct flowi4.
We've had several bugs in the past where ECN bits could interfere with
IPv4 routing, because these bits were not properly cleared when setting
->flowi4_tos. These bugs should be fixed now and the dscp_t type has
been introduced to ensure that variables carrying DSCP values don't
accidentally have any ECN bits set. Several variables and structure
fields have been converted to dscp_t already, but the main IPv4 routing
structure, struct flowi4, is still using a __u8. To avoid any future
regression, this patch converts it to dscp_t.
There are many users to convert at once. Fortunately, around half of
->flowi4_tos users already have a dscp_t value at hand, which they
currently convert to __u8 using inet_dscp_to_dsfield(). For all of
these users, we just need to drop that conversion.
But, although we try to do the __u8 <-> dscp_t conversions at the
boundaries of the network or of user space, some places still store
TOS/DSCP variables as __u8 in core networking code. Those can hardly be
converted either because the data structure is part of UAPI or because
the same variable or field is also used for handling ECN in other parts
of the code. In all of these cases where we don't have a dscp_t
variable at hand, we need to use inet_dsfield_to_dscp() when
interacting with ->flowi4_dscp.
Changes since v1:
* Fix space alignment in __bpf_redirect_neigh_v4() (Ido).
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/29acecb45e911d17446b9a3dbdb1ab7b821ea371.1756128932.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-08-25 15:37:43 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-01-08 22:36:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-08 19:17:37 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-08-24 20:10:43 -07:00
|
|
|
|
2024-08-29 09:54:55 +03:00
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 19:49:02 -07:00
|
|
|
|
tcp: add datapath logic for PSP with inline key exchange
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>
2025-09-16 17:09:31 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-05-08 23:19:42 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-07-09 21:22:10 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-10-07 16:48:45 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-19 09:20:53 +08:00
|
|
|
|
|
|
|
|
|
net: add support for ipv4 big tcp
Similar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.
Firstly, allow sk->sk_gso_max_size to be set to a value greater than
GSO_LEGACY_MAX_SIZE by not trimming gso_max_size in sk_trim_gso_size()
for IPv4 TCP sockets.
Then on TX path, set IP header tot_len to 0 when skb->len > IP_MAX_MTU
in __ip_local_out() to allow to send BIG TCP packets, and this implies
that skb->len is the length of a IPv4 packet; On RX path, use skb->len
as the length of the IPv4 packet when the IP header tot_len is 0 and
skb->len > IP_MAX_MTU in ip_rcv_core(). As the API iph_set_totlen() and
skb_ip_totlen() are used in __ip_local_out() and ip_rcv_core(), we only
need to update these APIs.
Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows
the merged packet size >= GRO_LEGACY_MAX_SIZE in skb_gro_receive(). In
GRO complete, set IP header tot_len to 0 when the merged packet size
greater than IP_MAX_MTU in iph_set_totlen() so that it can be processed
on RX path.
Note that by checking skb_is_gso_tcp() in API iph_totlen(), it makes
this implementation safe to use iph->len == 0 indicates IPv4 BIG TCP
packets.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-01-28 10:58:39 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
2016-09-10 12:09:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-12-01 10:05:10 +08:00
|
|
|
|
|
|
|
|
|
2015-09-15 20:04:16 -05:00
|
|
|
|
2025-06-30 12:19:31 +00:00
|
|
|
|
2015-10-07 16:48:35 -05:00
|
|
|
|
2015-04-05 22:19:04 -04:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:46 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:45 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
2015-10-07 16:48:35 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:38 -05:00
|
|
|
|
2008-01-11 19:14:00 -08:00
|
|
|
|
2023-03-16 15:31:55 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-08-16 08:15:46 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-12-12 21:55:08 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-25 07:39:16 -07:00
|
|
|
|
2020-09-09 17:50:47 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-03-16 15:31:55 +00:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2015-10-07 16:48:42 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2007-03-10 19:40:39 -03:00
|
|
|
|
2007-04-20 22:47:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2020-09-09 17:50:47 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2011-05-04 12:03:30 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-01-26 17:10:21 -08:00
|
|
|
|
|
|
|
|
|
2015-09-25 07:39:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-26 17:10:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-05 17:23:53 +02:00
|
|
|
|
2022-01-26 17:10:21 -08:00
|
|
|
|
|
|
|
|
|
2015-09-25 07:39:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
|
|
|
|
|
2022-01-28 08:06:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:18 +00:00
|
|
|
|
2017-07-03 09:51:50 -04:00
|
|
|
|
2023-07-28 15:03:15 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:46 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-08-09 20:12:12 -07:00
|
|
|
|
|
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-06-02 05:19:30 +00:00
|
|
|
|
2024-04-29 13:30:09 +00:00
|
|
|
|
2025-06-30 12:19:31 +00:00
|
|
|
|
2007-10-23 21:07:32 -07:00
|
|
|
|
2011-07-14 07:53:20 -07:00
|
|
|
|
ipv4: Add helpers for neigh lookup for nexthop
A common theme in the output path is looking up a neigh entry for a
nexthop, either the gateway in an rtable or a fallback to the daddr
in the skb:
nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
To allow the nexthop to be an IPv6 address we need to consider the
family of the nexthop and then call __ipv{4,6}_neigh_lookup_noref based
on it.
To make this simpler, add a ip_neigh_gw4 helper similar to ip_neigh_gw6
added in an earlier patch which handles:
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
And then add a second one, ip_neigh_for_gw, that calls either
ip_neigh_gw4 or ip_neigh_gw6 based on the address family of the gateway.
Update the output paths in the VRF driver and core v4 code to use
ip_neigh_for_gw simplifying the family based lookup and making both
ready for a v6 nexthop.
ipv4_neigh_lookup has a different need - the potential to resolve a
passed in address in addition to any gateway in the rtable or skb. Since
this is a one-off, add ip_neigh_gw4 and ip_neigh_gw6 diectly. The
difference between __neigh_create used by the helpers and neigh_create
called by ipv4_neigh_lookup is taking a refcount, so add rcu_read_lock_bh
and bump the refcnt on the neigh entry.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-05 16:30:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-04-27 02:45:02 -07:00
|
|
|
|
2015-09-15 20:04:01 -05:00
|
|
|
|
2009-04-27 02:45:02 -07:00
|
|
|
|
2015-09-15 20:04:01 -05:00
|
|
|
|
2007-04-30 00:48:20 -07:00
|
|
|
|
2023-08-25 15:55:05 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-09 01:40:57 -07:00
|
|
|
|
2021-08-02 11:52:35 +03:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-24 20:10:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-17 19:58:14 -07:00
|
|
|
|
2016-08-24 20:10:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-21 04:01:14 +00:00
|
|
|
|
ipv4: Add helpers for neigh lookup for nexthop
A common theme in the output path is looking up a neigh entry for a
nexthop, either the gateway in an rtable or a fallback to the daddr
in the skb:
nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
To allow the nexthop to be an IPv6 address we need to consider the
family of the nexthop and then call __ipv{4,6}_neigh_lookup_noref based
on it.
To make this simpler, add a ip_neigh_gw4 helper similar to ip_neigh_gw6
added in an earlier patch which handles:
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
And then add a second one, ip_neigh_for_gw, that calls either
ip_neigh_gw4 or ip_neigh_gw6 based on the address family of the gateway.
Update the output paths in the VRF driver and core v4 code to use
ip_neigh_for_gw simplifying the family based lookup and making both
ready for a v6 nexthop.
ipv4_neigh_lookup has a different need - the potential to resolve a
passed in address in addition to any gateway in the rtable or skb. Since
this is a one-off, add ip_neigh_gw4 and ip_neigh_gw6 diectly. The
difference between __neigh_create used by the helpers and neigh_create
called by ipv4_neigh_lookup is taking a refcount, so add rcu_read_lock_bh
and bump the refcnt on the neigh entry.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-05 16:30:34 -07:00
|
|
|
|
2012-08-06 03:55:29 +00:00
|
|
|
|
2017-02-06 23:14:12 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv4: Add helpers for neigh lookup for nexthop
A common theme in the output path is looking up a neigh entry for a
nexthop, either the gateway in an rtable or a fallback to the daddr
in the skb:
nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
To allow the nexthop to be an IPv6 address we need to consider the
family of the nexthop and then call __ipv{4,6}_neigh_lookup_noref based
on it.
To make this simpler, add a ip_neigh_gw4 helper similar to ip_neigh_gw6
added in an earlier patch which handles:
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
And then add a second one, ip_neigh_for_gw, that calls either
ip_neigh_gw4 or ip_neigh_gw6 based on the address family of the gateway.
Update the output paths in the VRF driver and core v4 code to use
ip_neigh_for_gw simplifying the family based lookup and making both
ready for a v6 nexthop.
ipv4_neigh_lookup has a different need - the potential to resolve a
passed in address in addition to any gateway in the rtable or skb. Since
this is a one-off, add ip_neigh_gw4 and ip_neigh_gw6 diectly. The
difference between __neigh_create used by the helpers and neigh_create
called by ipv4_neigh_lookup is taking a refcount, so add rcu_read_lock_bh
and bump the refcnt on the neigh entry.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-05 16:30:34 -07:00
|
|
|
|
|
|
|
|
|
2023-03-21 04:01:14 +00:00
|
|
|
|
2011-07-29 19:00:53 +00:00
|
|
|
|
|
|
|
|
|
2023-03-21 04:01:14 +00:00
|
|
|
|
2011-07-16 17:26:00 -07:00
|
|
|
|
2012-05-13 21:56:26 +00:00
|
|
|
|
|
|
|
|
|
2022-02-26 12:18:29 +08:00
|
|
|
|
2023-08-07 01:54:08 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
|
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2020-01-13 18:42:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-02 16:36:17 -04:00
|
|
|
|
2016-07-18 14:49:33 +03:00
|
|
|
|
2018-03-01 17:13:37 +11:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2016-11-09 15:04:39 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2016-11-09 15:04:39 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-27 04:42:38 +05:30
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
2020-03-26 15:33:14 +08:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2014-10-20 13:49:17 +02:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-01-13 18:42:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
2018-07-29 20:42:53 -07:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-01-13 18:42:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-28 16:59:38 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-05-22 16:32:50 +02:00
|
|
|
|
|
|
|
|
|
2006-01-06 23:05:36 -08:00
|
|
|
|
|
|
|
|
|
2015-04-03 09:17:27 +01:00
|
|
|
|
2006-02-15 15:10:22 -08:00
|
|
|
|
2015-10-07 16:48:35 -05:00
|
|
|
|
2006-02-15 15:10:22 -08:00
|
|
|
|
2006-01-06 23:05:36 -08:00
|
|
|
|
2016-06-29 21:47:03 +03:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
net: ip: always refragment ip defragmented packets
Conntrack reassembly records the largest fragment size seen in IPCB.
However, when this gets forwarded/transmitted, fragmentation will only
be forced if one of the fragmented packets had the DF bit set.
In that case, a flag in IPCB will force fragmentation even if the
MTU is large enough.
This should work fine, but this breaks with ip tunnels.
Consider client that sends a UDP datagram of size X to another host.
The client fragments the datagram, so two packets, of size y and z, are
sent. DF bit is not set on any of these packets.
Middlebox netfilter reassembles those packets back to single size-X
packet, before routing decision.
packet-size-vs-mtu checks in ip_forward are irrelevant, because DF bit
isn't set. At output time, ip refragmentation is skipped as well
because x is still smaller than the mtu of the output device.
If ttransmit device is an ip tunnel, the packet size increases to
x+overhead.
Also, tunnel might be configured to force DF bit on outer header.
In this case, packet will be dropped (exceeds MTU) and an ICMP error is
generated back to sender.
But sender already respects the announced MTU, all the packets that
it sent did fit the announced mtu.
Force refragmentation as per original sizes unconditionally so ip tunnel
will encapsulate the fragments instead.
The only other solution I see is to place ip refragmentation in
the ip_tunnel code to handle this case.
Fixes: d6b915e29f4ad ("ip_fragment: don't forward defragmented DF packet")
Reported-by: Christian Perle <christian.perle@secunet.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-06 00:15:23 +01:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2014-05-05 15:00:43 +02:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2019-05-28 16:59:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-26 12:18:29 +08:00
|
|
|
|
2019-05-28 16:59:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-26 02:21:16 -04:00
|
|
|
|
2019-06-27 21:06:39 -07:00
|
|
|
|
|
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
|
|
|
|
|
2019-05-28 16:59:38 -07:00
|
|
|
|
|
|
|
|
|
2019-06-27 21:06:39 -07:00
|
|
|
|
2020-03-12 15:50:22 -07:00
|
|
|
|
2019-06-27 21:06:39 -07:00
|
|
|
|
|
|
|
|
|
2019-05-28 16:59:38 -07:00
|
|
|
|
2022-02-26 12:18:29 +08:00
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-26 02:21:16 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-27 21:06:39 -07:00
|
|
|
|
|
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:47 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-01-06 20:37:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-23 10:41:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-11-23 10:41:23 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-03-23 04:07:29 +01:00
|
|
|
|
2015-09-15 20:04:16 -05:00
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-20 22:47:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-15 20:04:16 -05:00
|
|
|
|
|
|
|
|
|
2016-11-23 16:52:29 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-09-15 20:04:16 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-02-15 15:10:22 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:47 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2025-07-30 16:21:18 +05:30
|
|
|
|
|
|
|
|
|
2006-01-05 12:20:59 -08:00
|
|
|
|
2025-07-30 16:21:18 +05:30
|
|
|
|
|
|
|
|
|
2006-01-05 12:20:59 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-30 16:21:18 +05:30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-02-01 17:41:30 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-11-30 19:00:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-26 14:52:51 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-30 19:00:53 +00:00
|
|
|
|
|
|
|
|
|
2014-04-15 12:58:34 -04:00
|
|
|
|
2018-07-02 18:21:11 +08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:42 -05:00
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2011-05-06 16:24:06 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-05-10 11:31:49 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-10 11:31:49 +00:00
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2011-05-06 22:30:20 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2015-04-03 09:17:27 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-29 13:30:09 +00:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2024-12-16 18:21:51 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-12-16 18:21:51 +01:00
|
|
|
|
ipv4: Convert ->flowi4_tos to dscp_t.
Convert the ->flowic_tos field of struct flowi_common from __u8 to
dscp_t, rename it ->flowic_dscp and propagate these changes to struct
flowi and struct flowi4.
We've had several bugs in the past where ECN bits could interfere with
IPv4 routing, because these bits were not properly cleared when setting
->flowi4_tos. These bugs should be fixed now and the dscp_t type has
been introduced to ensure that variables carrying DSCP values don't
accidentally have any ECN bits set. Several variables and structure
fields have been converted to dscp_t already, but the main IPv4 routing
structure, struct flowi4, is still using a __u8. To avoid any future
regression, this patch converts it to dscp_t.
There are many users to convert at once. Fortunately, around half of
->flowi4_tos users already have a dscp_t value at hand, which they
currently convert to __u8 using inet_dscp_to_dsfield(). For all of
these users, we just need to drop that conversion.
But, although we try to do the __u8 <-> dscp_t conversions at the
boundaries of the network or of user space, some places still store
TOS/DSCP variables as __u8 in core networking code. Those can hardly be
converted either because the data structure is part of UAPI or because
the same variable or field is also used for handling ECN in other parts
of the code. In all of these cases where we don't have a dscp_t
variable at hand, we need to use inet_dsfield_to_dscp() when
interacting with ->flowi4_dscp.
Changes since v1:
* Fix space alignment in __bpf_redirect_neigh_v4() (Ido).
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/29acecb45e911d17446b9a3dbdb1ab7b821ea371.1756128932.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-08-25 15:37:43 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 00:00:52 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-16 18:21:51 +01:00
|
|
|
|
2011-03-12 00:00:52 -05:00
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2019-09-17 10:39:49 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2007-03-10 19:40:39 -03:00
|
|
|
|
2007-04-20 22:47:35 -07:00
|
|
|
|
2018-07-02 18:21:11 +08:00
|
|
|
|
2014-05-04 16:39:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-11-30 19:00:53 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
|
|
|
|
|
2022-01-28 08:06:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:42 -05:00
|
|
|
|
2015-03-25 17:07:44 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-04-15 12:58:34 -04:00
|
|
|
|
2023-07-28 15:03:18 +00:00
|
|
|
|
2023-07-28 15:03:15 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-10-07 16:48:46 -05:00
|
|
|
|
2010-05-10 11:31:49 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-05-10 11:31:49 +00:00
|
|
|
|
2015-10-07 16:48:42 -05:00
|
|
|
|
2022-02-26 12:18:29 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-07-02 18:21:11 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2020-06-19 12:12:34 -07:00
|
|
|
|
|
|
|
|
|
2023-09-22 03:42:16 +00:00
|
|
|
|
2020-06-19 12:12:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-04-29 16:39:30 +03:00
|
|
|
|
2009-06-02 05:19:30 +00:00
|
|
|
|
2010-07-01 23:48:22 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-09 15:19:14 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2018-07-23 16:50:48 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-14 16:44:01 -07:00
|
|
|
|
sk_buff: add skb extension infrastructure
This adds an optional extension infrastructure, with ispec (xfrm) and
bridge netfilter as first users.
objdiff shows no changes if kernel is built without xfrm and br_netfilter
support.
The third (planned future) user is Multipath TCP which is still
out-of-tree.
MPTCP needs to map logical mptcp sequence numbers to the tcp sequence
numbers used by individual subflows.
This DSS mapping is read/written from tcp option space on receive and
written to tcp option space on transmitted tcp packets that are part of
and MPTCP connection.
Extending skb_shared_info or adding a private data field to skb fclones
doesn't work for incoming skb, so a different DSS propagation method would
be required for the receive side.
mptcp has same requirements as secpath/bridge netfilter:
1. extension memory is released when the sk_buff is free'd.
2. data is shared after cloning an skb (clone inherits extension)
3. adding extension to an skb will COW the extension buffer if needed.
The "MPTCP upstreaming" effort adds SKB_EXT_MPTCP extension to store the
mapping for tx and rx processing.
Two new members are added to sk_buff:
1. 'active_extensions' byte (filling a hole), telling which extensions
are available for this skb.
This has two purposes.
a) avoids the need to initialize the pointer.
b) allows to "delete" an extension by clearing its bit
value in ->active_extensions.
While it would be possible to store the active_extensions byte
in the extension struct instead of sk_buff, there is one problem
with this:
When an extension has to be disabled, we can always clear the
bit in skb->active_extensions. But in case it would be stored in the
extension buffer itself, we might have to COW it first, if
we are dealing with a cloned skb. On kmalloc failure we would
be unable to turn an extension off.
2. extension pointer, located at the end of the sk_buff.
If the active_extensions byte is 0, the pointer is undefined,
it is not initialized on skb allocation.
This adds extra code to skb clone and free paths (to deal with
refcount/free of extension area) but this replaces similar code that
manages skb->nf_bridge and skb->sp structs in the followup patches of
the series.
It is possible to add support for extensions that are not preseved on
clones/copies.
To do this, it would be needed to define a bitmask of all extensions that
need copy/cow semantics, and change __skb_ext_copy() to check
->active_extensions & SKB_EXT_PRESERVE_ON_CLONE, then just set
->active_extensions to 0 on the new clone.
This isn't done here because all extensions that get added here
need the copy/cow semantics.
v2:
Allocate entire extension space using kmem_cache.
Upside is that this allows better tracking of used memory,
downside is that we will allocate more space than strictly needed in
most cases (its unlikely that all extensions are active/needed at same
time for same skb).
The allocated memory (except the small extension header) is not cleared,
so no additonal overhead aside from memory usage.
Avoid atomic_dec_and_test operation on skb_ext_put()
by using similar trick as kfree_skbmem() does with fclone_ref:
If recount is 1, there is no concurrent user and we can free right away.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-18 17:15:16 +01:00
|
|
|
|
2016-09-09 08:43:16 -04:00
|
|
|
|
2005-10-22 13:39:21 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-06-09 00:29:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2015-05-22 16:32:50 +02:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-22 16:32:51 +02:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2015-05-22 16:32:51 +02:00
|
|
|
|
|
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
|
|
|
|
|
2015-09-15 20:04:00 -05:00
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-02 11:24:18 -07:00
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
2019-10-19 09:26:37 -07:00
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-19 09:26:37 -07:00
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:35 +02:00
|
|
|
|
2021-08-23 11:17:59 +08:00
|
|
|
|
2019-05-29 13:25:35 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-19 09:26:37 -07:00
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-09 14:18:32 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
2019-10-16 18:00:56 -07:00
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-27 22:40:40 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-20 22:47:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-06-29 21:47:03 +03:00
|
|
|
|
2015-05-22 16:32:51 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-01-09 10:01:15 +01:00
|
|
|
|
2005-12-13 23:14:27 -08:00
|
|
|
|
2017-07-14 12:04:16 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-08-23 00:13:46 -07:00
|
|
|
|
2010-09-21 08:47:45 +00:00
|
|
|
|
2016-11-19 04:08:08 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-21 20:33:34 -07:00
|
|
|
|
2017-07-14 12:04:16 +03:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-06-09 00:19:37 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-14 12:04:16 +03:00
|
|
|
|
2010-09-21 08:47:45 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-09-21 08:47:45 +00:00
|
|
|
|
2005-05-18 22:52:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-09-21 08:47:45 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
2021-08-30 17:16:40 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:35 +02:00
|
|
|
|
ipv4: fix ip option filtering for locally generated fragments
During IP fragmentation we sanitize IP options. This means overwriting
options which should not be copied with NOPs. Only the first fragment
has the original, full options.
ip_fraglist_prepare() copies the IP header and options from previous
fragment to the next one. Commit 19c3401a917b ("net: ipv4: place control
buffer handling away from fragmentation iterators") moved sanitizing
options before ip_fraglist_prepare() which means options are sanitized
and then overwritten again with the old values.
Fixing this is not enough, however, nor did the sanitization work
prior to aforementioned commit.
ip_options_fragment() (which does the sanitization) uses ipcb->opt.optlen
for the length of the options. ipcb->opt of fragments is not populated
(it's 0), only the head skb has the state properly built. So even when
called at the right time ip_options_fragment() does nothing. This seems
to date back all the way to v2.5.44 when the fast path for pre-fragmented
skbs had been introduced. Prior to that ip_options_build() would have been
called for every fragment (in fact ever since v2.5.44 the fragmentation
handing in ip_options_build() has been dead code, I'll clean it up in
-next).
In the original patch (see Link) caixf mentions fixing the handling
for fragments other than the second one, but I'm not sure how _any_
fragment could have had their options sanitized with the code
as it stood.
Tested with python (MTU on lo lowered to 1000 to force fragmentation):
import socket
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
s.setsockopt(socket.IPPROTO_IP, socket.IP_OPTIONS,
bytearray([7,4,5,192, 20|0x80,4,1,0]))
s.sendto(b'1'*2000, ('127.0.0.1', 1234))
Before:
IP (tos 0x0, ttl 64, id 1053, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost.36500 > localhost.search-agent: UDP, length 2000
IP (tos 0x0, ttl 64, id 1053, offset 968, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost > localhost: udp
IP (tos 0x0, ttl 64, id 1053, offset 1936, flags [none], proto UDP (17), length 100, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost > localhost: udp
After:
IP (tos 0x0, ttl 96, id 42549, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost.51607 > localhost.search-agent: UDP, bad length 2000 > 960
IP (tos 0x0, ttl 96, id 42549, offset 968, flags [+], proto UDP (17), length 996, options (NOP,NOP,NOP,NOP,RA value 256))
localhost > localhost: udp
IP (tos 0x0, ttl 96, id 42549, offset 1936, flags [none], proto UDP (17), length 100, options (NOP,NOP,NOP,NOP,RA value 256))
localhost > localhost: udp
RA (20 | 0x80) is now copied as expected, RR (7) is "NOPed out".
Link: https://lore.kernel.org/netdev/20220107080559.122713-1-ooppublic@163.com/
Fixes: 19c3401a917b ("net: ipv4: place control buffer handling away from fragmentation iterators")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: caixf <ooppublic@163.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2022-01-21 16:57:31 -08:00
|
|
|
|
|
|
|
|
|
2021-08-23 11:17:59 +08:00
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
ipv4: fix ip option filtering for locally generated fragments
During IP fragmentation we sanitize IP options. This means overwriting
options which should not be copied with NOPs. Only the first fragment
has the original, full options.
ip_fraglist_prepare() copies the IP header and options from previous
fragment to the next one. Commit 19c3401a917b ("net: ipv4: place control
buffer handling away from fragmentation iterators") moved sanitizing
options before ip_fraglist_prepare() which means options are sanitized
and then overwritten again with the old values.
Fixing this is not enough, however, nor did the sanitization work
prior to aforementioned commit.
ip_options_fragment() (which does the sanitization) uses ipcb->opt.optlen
for the length of the options. ipcb->opt of fragments is not populated
(it's 0), only the head skb has the state properly built. So even when
called at the right time ip_options_fragment() does nothing. This seems
to date back all the way to v2.5.44 when the fast path for pre-fragmented
skbs had been introduced. Prior to that ip_options_build() would have been
called for every fragment (in fact ever since v2.5.44 the fragmentation
handing in ip_options_build() has been dead code, I'll clean it up in
-next).
In the original patch (see Link) caixf mentions fixing the handling
for fragments other than the second one, but I'm not sure how _any_
fragment could have had their options sanitized with the code
as it stood.
Tested with python (MTU on lo lowered to 1000 to force fragmentation):
import socket
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
s.setsockopt(socket.IPPROTO_IP, socket.IP_OPTIONS,
bytearray([7,4,5,192, 20|0x80,4,1,0]))
s.sendto(b'1'*2000, ('127.0.0.1', 1234))
Before:
IP (tos 0x0, ttl 64, id 1053, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost.36500 > localhost.search-agent: UDP, length 2000
IP (tos 0x0, ttl 64, id 1053, offset 968, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost > localhost: udp
IP (tos 0x0, ttl 64, id 1053, offset 1936, flags [none], proto UDP (17), length 100, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost > localhost: udp
After:
IP (tos 0x0, ttl 96, id 42549, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256))
localhost.51607 > localhost.search-agent: UDP, bad length 2000 > 960
IP (tos 0x0, ttl 96, id 42549, offset 968, flags [+], proto UDP (17), length 996, options (NOP,NOP,NOP,NOP,RA value 256))
localhost > localhost: udp
IP (tos 0x0, ttl 96, id 42549, offset 1936, flags [none], proto UDP (17), length 100, options (NOP,NOP,NOP,NOP,RA value 256))
localhost > localhost: udp
RA (20 | 0x80) is now copied as expected, RR (7) is "NOPed out".
Link: https://lore.kernel.org/netdev/20220107080559.122713-1-ooppublic@163.com/
Fixes: 19c3401a917b ("net: ipv4: place control buffer handling away from fragmentation iterators")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: caixf <ooppublic@163.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2022-01-21 16:57:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:35 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-05-09 14:18:32 -07:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-02 13:41:21 -07:00
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:31 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-02 11:24:18 -07:00
|
|
|
|
2019-04-04 13:54:20 +02:00
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-09-21 08:47:45 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-19 09:26:37 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
2019-05-29 13:25:35 +02:00
|
|
|
|
|
|
|
|
|
2019-05-29 13:25:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2021-08-23 11:17:59 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-09 14:18:32 -07:00
|
|
|
|
2015-06-12 21:55:31 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-08-02 13:41:21 -07:00
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-04 01:17:19 +00:00
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2015-09-15 20:03:59 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-05-15 14:15:37 -07:00
|
|
|
|
2006-04-04 13:42:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-24 13:23:40 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-29 16:44:56 -07:00
|
|
|
|
2016-11-03 18:17:31 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-11-14 21:36:14 -08:00
|
|
|
|
2016-11-03 18:17:31 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-07-09 21:22:10 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-05-08 17:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-11-30 15:32:39 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-01 23:00:58 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-07-12 21:52:25 +01:00
|
|
|
|
2013-10-27 17:29:11 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-04-29 13:30:09 +00:00
|
|
|
|
2024-10-01 05:57:14 -07:00
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
2014-08-04 22:11:47 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-06-05 20:48:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp: generate gso with UDP_SEGMENT
Support generic segmentation offload for udp datagrams. Callers can
concatenate and send at once the payload of multiple datagrams with
the same destination.
To set segment size, the caller sets socket option UDP_SEGMENT to the
length of each discrete payload. This value must be smaller than or
equal to the relevant MTU.
A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a
per send call basis.
Total byte length may then exceed MTU. If not an exact multiple of
segment size, the last segment will be shorter.
The implementation adds a gso_size field to the udp socket, ip(v6)
cmsg cookie and inet_cork structure to be able to set the value at
setsockopt or cmsg time and to work with both lockless and corked
paths.
Initial benchmark numbers show UDP GSO about as expensive as TCP GSO.
tcp tso
3197 MB/s 54232 msg/s 54232 calls/s
6,457,754,262 cycles
tcp gso
1765 MB/s 29939 msg/s 29939 calls/s
11,203,021,806 cycles
tcp without tso/gso *
739 MB/s 12548 msg/s 12548 calls/s
11,205,483,630 cycles
udp
876 MB/s 14873 msg/s 624666 calls/s
11,205,777,429 cycles
udp gso
2139 MB/s 36282 msg/s 36282 calls/s
11,204,374,561 cycles
[*] after reverting commit 0a6b2a1dc2a2
("tcp: switch to GSO being always on")
Measured total system cycles ('-a') for one core while pinning both
the network receive path and benchmark process to that core:
perf stat -a -C 12 -e cycles \
./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4
Note the reduction in calls/s with GSO. Bytes per syscall drops
increases from 1470 to 61818.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-26 13:42:17 -04:00
|
|
|
|
2018-04-26 13:42:19 -04:00
|
|
|
|
udp: generate gso with UDP_SEGMENT
Support generic segmentation offload for udp datagrams. Callers can
concatenate and send at once the payload of multiple datagrams with
the same destination.
To set segment size, the caller sets socket option UDP_SEGMENT to the
length of each discrete payload. This value must be smaller than or
equal to the relevant MTU.
A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a
per send call basis.
Total byte length may then exceed MTU. If not an exact multiple of
segment size, the last segment will be shorter.
The implementation adds a gso_size field to the udp socket, ip(v6)
cmsg cookie and inet_cork structure to be able to set the value at
setsockopt or cmsg time and to work with both lockless and corked
paths.
Initial benchmark numbers show UDP GSO about as expensive as TCP GSO.
tcp tso
3197 MB/s 54232 msg/s 54232 calls/s
6,457,754,262 cycles
tcp gso
1765 MB/s 29939 msg/s 29939 calls/s
11,203,021,806 cycles
tcp without tso/gso *
739 MB/s 12548 msg/s 12548 calls/s
11,205,483,630 cycles
udp
876 MB/s 14873 msg/s 624666 calls/s
11,205,777,429 cycles
udp gso
2139 MB/s 36282 msg/s 36282 calls/s
11,204,374,561 cycles
[*] after reverting commit 0a6b2a1dc2a2
("tcp: switch to GSO being always on")
Measured total system cycles ('-a') for one core while pinning both
the network receive path and benchmark process to that core:
perf stat -a -C 12 -e cycles \
./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4
Note the reduction in calls/s with GSO. Bytes per syscall drops
increases from 1470 to 61818.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-26 13:42:17 -04:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-29 05:09:18 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-10-27 17:29:11 +01:00
|
|
|
|
2011-05-08 17:24:10 -07:00
|
|
|
|
2013-12-19 02:13:36 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-12-14 11:19:44 -08:00
|
|
|
|
udp: generate gso with UDP_SEGMENT
Support generic segmentation offload for udp datagrams. Callers can
concatenate and send at once the payload of multiple datagrams with
the same destination.
To set segment size, the caller sets socket option UDP_SEGMENT to the
length of each discrete payload. This value must be smaller than or
equal to the relevant MTU.
A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a
per send call basis.
Total byte length may then exceed MTU. If not an exact multiple of
segment size, the last segment will be shorter.
The implementation adds a gso_size field to the udp socket, ip(v6)
cmsg cookie and inet_cork structure to be able to set the value at
setsockopt or cmsg time and to work with both lockless and corked
paths.
Initial benchmark numbers show UDP GSO about as expensive as TCP GSO.
tcp tso
3197 MB/s 54232 msg/s 54232 calls/s
6,457,754,262 cycles
tcp gso
1765 MB/s 29939 msg/s 29939 calls/s
11,203,021,806 cycles
tcp without tso/gso *
739 MB/s 12548 msg/s 12548 calls/s
11,205,483,630 cycles
udp
876 MB/s 14873 msg/s 624666 calls/s
11,205,777,429 cycles
udp gso
2139 MB/s 36282 msg/s 36282 calls/s
11,204,374,561 cycles
[*] after reverting commit 0a6b2a1dc2a2
("tcp: switch to GSO being always on")
Measured total system cycles ('-a') for one core while pinning both
the network receive path and benchmark process to that core:
perf stat -a -C 12 -e cycles \
./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4
Note the reduction in calls/s with GSO. Bytes per syscall drops
increases from 1470 to 61818.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-26 13:42:17 -04:00
|
|
|
|
2018-04-12 12:03:13 -07:00
|
|
|
|
2006-08-29 16:44:56 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-07-12 21:52:33 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-08 00:48:24 +00:00
|
|
|
|
|
|
|
|
|
2022-07-12 21:52:33 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-23 17:39:04 +01:00
|
|
|
|
2022-07-12 21:52:33 +01:00
|
|
|
|
|
|
|
|
|
2018-11-30 15:32:39 -05:00
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
2023-08-16 08:15:38 +00:00
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
2023-06-14 09:04:16 +01:00
|
|
|
|
|
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-11-30 15:32:39 -05:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-10-01 05:57:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-02-13 03:04:28 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-15 01:52:25 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
2018-11-24 14:21:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-11-24 14:21:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
|
|
|
|
|
2011-06-22 01:05:37 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-22 01:04:37 +00:00
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 13:06:31 +01:00
|
|
|
|
2022-07-12 21:52:25 +01:00
|
|
|
|
|
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-22 01:04:37 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-06-23 14:44:38 -07:00
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-07-14 17:55:06 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:19 -04:00
|
|
|
|
2007-03-11 22:39:41 -03:00
|
|
|
|
2007-04-10 21:21:55 -07:00
|
|
|
|
|
|
|
|
|
2011-06-22 01:05:37 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-10 20:07:10 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-08-13 20:12:58 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:19 -04:00
|
|
|
|
udp: Fix __ip_append_data()'s handling of MSG_SPLICE_PAGES
__ip_append_data() can get into an infinite loop when asked to splice into
a partially-built UDP message that has more than the frag-limit data and up
to the MTU limit. Something like:
pipe(pfd);
sfd = socket(AF_INET, SOCK_DGRAM, 0);
connect(sfd, ...);
send(sfd, buffer, 8161, MSG_CONFIRM|MSG_MORE);
write(pfd[1], buffer, 8);
splice(pfd[0], 0, sfd, 0, 0x4ffe0ul, 0);
where the amount of data given to send() is dependent on the MTU size (in
this instance an interface with an MTU of 8192).
The problem is that the calculation of the amount to copy in
__ip_append_data() goes negative in two places, and, in the second place,
this gets subtracted from the length remaining, thereby increasing it.
This happens when pagedlen > 0 (which happens for MSG_ZEROCOPY and
MSG_SPLICE_PAGES), because the terms in:
copy = datalen - transhdrlen - fraggap - pagedlen;
then mostly cancel when pagedlen is substituted for, leaving just -fraggap.
This causes:
length -= copy + transhdrlen;
to increase the length to more than the amount of data in msg->msg_iter,
which causes skb_splice_from_iter() to be unable to fill the request and it
returns less than 'copied' - which means that length never gets to 0 and we
never exit the loop.
Fix this by:
(1) Insert a note about the dodgy calculation of 'copy'.
(2) If MSG_SPLICE_PAGES, clear copy if it is negative from the above
equation, so that 'offset' isn't regressed and 'length' isn't
increased, which will mean that length and thus copy should match the
amount left in the iterator.
(3) When handling MSG_SPLICE_PAGES, give a warning and return -EIO if
we're asked to splice more than is in the iterator. It might be
better to not give the warning or even just give a 'short' write.
[!] Note that this ought to also affect MSG_ZEROCOPY, but MSG_ZEROCOPY
avoids the problem by simply assuming that everything asked for got copied,
not just the amount that was in the iterator. This is a potential bug for
the future.
Fixes: 7ac7c987850c ("udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES")
Reported-by: syzbot+f527b971b4bdc8e79f9e@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/000000000000881d0606004541d1@google.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/1420063.1690904933@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-01 16:48:53 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-03 17:36:17 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp: Fix __ip_append_data()'s handling of MSG_SPLICE_PAGES
__ip_append_data() can get into an infinite loop when asked to splice into
a partially-built UDP message that has more than the frag-limit data and up
to the MTU limit. Something like:
pipe(pfd);
sfd = socket(AF_INET, SOCK_DGRAM, 0);
connect(sfd, ...);
send(sfd, buffer, 8161, MSG_CONFIRM|MSG_MORE);
write(pfd[1], buffer, 8);
splice(pfd[0], 0, sfd, 0, 0x4ffe0ul, 0);
where the amount of data given to send() is dependent on the MTU size (in
this instance an interface with an MTU of 8192).
The problem is that the calculation of the amount to copy in
__ip_append_data() goes negative in two places, and, in the second place,
this gets subtracted from the length remaining, thereby increasing it.
This happens when pagedlen > 0 (which happens for MSG_ZEROCOPY and
MSG_SPLICE_PAGES), because the terms in:
copy = datalen - transhdrlen - fraggap - pagedlen;
then mostly cancel when pagedlen is substituted for, leaving just -fraggap.
This causes:
length -= copy + transhdrlen;
to increase the length to more than the amount of data in msg->msg_iter,
which causes skb_splice_from_iter() to be unable to fill the request and it
returns less than 'copied' - which means that length never gets to 0 and we
never exit the loop.
Fix this by:
(1) Insert a note about the dodgy calculation of 'copy'.
(2) If MSG_SPLICE_PAGES, clear copy if it is negative from the above
equation, so that 'offset' isn't regressed and 'length' isn't
increased, which will mean that length and thus copy should match the
amount left in the iterator.
(3) When handling MSG_SPLICE_PAGES, give a warning and return -EIO if
we're asked to splice more than is in the iterator. It might be
better to not give the warning or even just give a 'short' write.
[!] Note that this ought to also affect MSG_ZEROCOPY, but MSG_ZEROCOPY
avoids the problem by simply assuming that everything asked for got copied,
not just the amount that was in the iterator. This is a potential bug for
the future.
Fixes: 7ac7c987850c ("udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES")
Reported-by: syzbot+f527b971b4bdc8e79f9e@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/000000000000881d0606004541d1@google.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/1420063.1690904933@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-01 16:48:53 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:19 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-11-30 15:32:40 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-06 23:14:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-17 13:13:29 -04:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-03 17:36:17 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp: Fix __ip_append_data()'s handling of MSG_SPLICE_PAGES
__ip_append_data() can get into an infinite loop when asked to splice into
a partially-built UDP message that has more than the frag-limit data and up
to the MTU limit. Something like:
pipe(pfd);
sfd = socket(AF_INET, SOCK_DGRAM, 0);
connect(sfd, ...);
send(sfd, buffer, 8161, MSG_CONFIRM|MSG_MORE);
write(pfd[1], buffer, 8);
splice(pfd[0], 0, sfd, 0, 0x4ffe0ul, 0);
where the amount of data given to send() is dependent on the MTU size (in
this instance an interface with an MTU of 8192).
The problem is that the calculation of the amount to copy in
__ip_append_data() goes negative in two places, and, in the second place,
this gets subtracted from the length remaining, thereby increasing it.
This happens when pagedlen > 0 (which happens for MSG_ZEROCOPY and
MSG_SPLICE_PAGES), because the terms in:
copy = datalen - transhdrlen - fraggap - pagedlen;
then mostly cancel when pagedlen is substituted for, leaving just -fraggap.
This causes:
length -= copy + transhdrlen;
to increase the length to more than the amount of data in msg->msg_iter,
which causes skb_splice_from_iter() to be unable to fill the request and it
returns less than 'copied' - which means that length never gets to 0 and we
never exit the loop.
Fix this by:
(1) Insert a note about the dodgy calculation of 'copy'.
(2) If MSG_SPLICE_PAGES, clear copy if it is negative from the above
equation, so that 'offset' isn't regressed and 'length' isn't
increased, which will mean that length and thus copy should match the
amount left in the iterator.
(3) When handling MSG_SPLICE_PAGES, give a warning and return -EIO if
we're asked to splice more than is in the iterator. It might be
better to not give the warning or even just give a 'short' write.
[!] Note that this ought to also affect MSG_ZEROCOPY, but MSG_ZEROCOPY
avoids the problem by simply assuming that everything asked for got copied,
not just the amount that was in the iterator. This is a potential bug for
the future.
Fixes: 7ac7c987850c ("udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES")
Reported-by: syzbot+f527b971b4bdc8e79f9e@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/000000000000881d0606004541d1@google.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/1420063.1690904933@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-08-01 16:48:53 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-02 15:38:08 +02:00
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-05-04 23:27:12 +08:00
|
|
|
|
|
|
|
|
|
2023-05-22 13:11:20 +01:00
|
|
|
|
2022-07-12 21:52:33 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-07-12 21:52:33 +01:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
2024-12-03 17:36:17 +00:00
|
|
|
|
|
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-06-22 18:09:03 +02:00
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
2018-11-30 15:32:39 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-04 14:30:01 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-01-06 14:18:41 -08:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2008-07-16 20:19:49 -07:00
|
|
|
|
2018-03-31 13:16:25 -07:00
|
|
|
|
2024-02-13 03:04:28 -08:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2018-04-16 10:16:45 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-29 17:10:17 +08:00
|
|
|
|
2026-01-30 21:03:02 +00:00
|
|
|
|
2024-01-29 17:10:17 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2011-04-21 09:45:37 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-16 10:16:45 +08:00
|
|
|
|
2018-07-06 10:12:59 -04:00
|
|
|
|
2019-12-05 20:43:46 -08:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2019-12-05 20:43:46 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2013-09-24 15:43:09 +02:00
|
|
|
|
|
|
|
|
|
2019-09-11 15:50:51 -04:00
|
|
|
|
sock: support SO_PRIORITY cmsg
The Linux socket API currently allows setting SO_PRIORITY at the
socket level, applying a uniform priority to all packets sent through
that socket. The exception to this is IP_TOS, when the priority value
is calculated during the handling of
ancillary data, as implemented in commit f02db315b8d8 ("ipv4: IP_TOS
and IP_TTL can be specified as ancillary data").
However, this is a computed
value, and there is currently no mechanism to set a custom priority
via control messages prior to this patch.
According to this patch, if SO_PRIORITY is specified as ancillary data,
the packet is sent with the priority value set through
sockc->priority, overriding the socket-level values
set via the traditional setsockopt() method. This is analogous to
the existing support for SO_MARK, as implemented in
commit c6af0c227a22 ("ip: support SO_MARK cmsg").
If both cmsg SO_PRIORITY and IP_TOS are passed, then the one that
takes precedence is the last one in the cmsg list.
This patch has the side effect that raw_send_hdrinc now interprets cmsg
IP_TOS.
Reviewed-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Ferenc Fejes <fejes@inf.elte.hu>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-3-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-13 09:44:55 +01:00
|
|
|
|
2018-07-03 15:42:49 -07:00
|
|
|
|
2018-07-06 10:12:58 -04:00
|
|
|
|
2024-10-01 05:57:15 -07:00
|
|
|
|
2024-10-01 05:57:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-22 13:11:23 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-08 17:24:10 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-06 15:02:07 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-05 21:03:24 -08:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-05 21:03:24 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-07-14 23:00:43 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-04-29 13:30:09 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-09-22 03:42:15 +00:00
|
|
|
|
2006-01-06 13:24:29 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:50:43 -07:00
|
|
|
|
2007-03-10 22:16:10 -03:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2007-03-16 17:26:39 -03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-05-04 16:39:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2014-05-04 16:39:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-09-22 03:42:15 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-01-30 21:03:02 +00:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-09-24 15:43:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-22 03:42:14 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-09-18 15:29:52 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2023-09-22 03:42:16 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-30 19:00:53 +00:00
|
|
|
|
2015-03-25 17:07:44 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-05-13 17:21:27 -04:00
|
|
|
|
2020-08-29 05:21:30 -04:00
|
|
|
|
2022-01-28 08:06:54 -08:00
|
|
|
|
2011-05-13 17:21:27 -04:00
|
|
|
|
|
|
|
|
|
sock: support SO_PRIORITY cmsg
The Linux socket API currently allows setting SO_PRIORITY at the
socket level, applying a uniform priority to all packets sent through
that socket. The exception to this is IP_TOS, when the priority value
is calculated during the handling of
ancillary data, as implemented in commit f02db315b8d8 ("ipv4: IP_TOS
and IP_TTL can be specified as ancillary data").
However, this is a computed
value, and there is currently no mechanism to set a custom priority
via control messages prior to this patch.
According to this patch, if SO_PRIORITY is specified as ancillary data,
the packet is sent with the priority value set through
sockc->priority, overriding the socket-level values
set via the traditional setsockopt() method. This is analogous to
the existing support for SO_MARK, as implemented in
commit c6af0c227a22 ("ip: support SO_MARK cmsg").
If both cmsg SO_PRIORITY and IP_TOS are passed, then the one that
takes precedence is the last one in the cmsg list.
This patch has the side effect that raw_send_hdrinc now interprets cmsg
IP_TOS.
Reviewed-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Ferenc Fejes <fejes@inf.elte.hu>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Link: https://patch.msgid.link/20241213084457.45120-3-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-13 09:44:55 +01:00
|
|
|
|
2019-09-11 15:50:51 -04:00
|
|
|
|
2024-05-09 14:18:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-24 16:07:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-04-20 20:40:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-16 08:15:38 +00:00
|
|
|
|
2024-04-30 21:39:45 +09:00
|
|
|
|
2023-04-20 20:40:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-09-17 09:57:33 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-10 02:22:47 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:46 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
ip: Report qdisc packet drops
Christoph Lameter pointed out that packet drops at qdisc level where not
accounted in SNMP counters. Only if application sets IP_RECVERR, drops
are reported to user (-ENOBUFS errors) and SNMP counters updated.
IP_RECVERR is used to enable extended reliable error message passing,
but these are not needed to update system wide SNMP stats.
This patch changes things a bit to allow SNMP counters to be updated,
regardless of IP_RECVERR being set or not on the socket.
Example after an UDP tx flood
# netstat -s
...
IP:
1487048 outgoing packets dropped
...
Udp:
...
SndbufErrors: 1487048
send() syscalls, do however still return an OK status, to not
break applications.
Note : send() manual page explicitly says for -ENOBUFS error :
"The output queue for a network interface was full.
This generally indicates that the interface has stopped sending,
but may be caused by transient congestion.
(Normally, this does not occur in Linux. Packets are just silently
dropped when a device queue overflows.) "
This is not true for IP_RECVERR enabled sockets : a send() syscall
that hit a qdisc drop returns an ENOBUFS error.
Many thanks to Christoph, David, and last but not least, Alexey !
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-02 18:05:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-10 02:22:47 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-06 15:02:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:15 -04:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:15 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:15 -04:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:15 -04:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-26 13:42:15 -04:00
|
|
|
|
2011-03-01 02:36:47 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-11-14 21:36:34 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2020-07-11 00:12:07 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-10-10 17:48:17 +00:00
|
|
|
|
|
|
|
|
|
2014-09-27 09:50:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-23 18:14:52 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-01-05 15:45:25 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2015-01-29 21:35:05 -08:00
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
2014-10-15 16:24:02 +04:00
|
|
|
|
2015-08-13 14:59:08 -06:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-01-05 15:45:25 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-07-06 10:12:54 -04:00
|
|
|
|
2011-05-09 13:22:43 -07:00
|
|
|
|
2019-06-13 21:22:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-01-05 15:45:25 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-01-05 15:45:25 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-08-13 14:59:08 -06:00
|
|
|
|
2016-11-09 09:07:26 -08:00
|
|
|
|
|
|
|
|
|
2015-08-13 14:59:08 -06:00
|
|
|
|
|
|
|
|
|
2018-05-10 16:53:51 +10:00
|
|
|
|
2024-08-29 09:54:55 +03:00
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2012-06-28 03:21:41 -07:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
|
|
|
|
|
2020-09-27 22:38:26 -04:00
|
|
|
|
2022-07-07 10:01:39 +00:00
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2025-03-05 23:38:51 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-20 22:47:35 -07:00
|
|
|
|
2007-06-04 21:32:46 -07:00
|
|
|
|
2022-08-23 10:46:44 -07:00
|
|
|
|
2020-07-01 16:00:06 -04:00
|
|
|
|
2014-10-15 16:24:02 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
|
|
|
|
|
2007-04-25 18:04:18 -07:00
|
|
|
|
2012-07-19 07:34:03 +00:00
|
|
|
|
tcp: add datapath logic for PSP with inline key exchange
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>
2025-09-16 17:09:31 -07:00
|
|
|
|
2024-10-10 17:48:17 +00:00
|
|
|
|
2025-09-30 19:24:26 -07:00
|
|
|
|
tcp: add datapath logic for PSP with inline key exchange
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>
2025-09-16 17:09:31 -07:00
|
|
|
|
2024-05-09 14:18:32 -07:00
|
|
|
|
|
|
|
|
|
2023-05-23 18:14:52 +02:00
|
|
|
|
|
|
|
|
|
2011-05-08 17:12:19 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-10-15 16:24:02 +04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-01-10 16:09:45 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|