2019-05-27 08:55:01 +02:00
|
|
|
|
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 23:24:36 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-16 19:58:40 +00:00
|
|
|
|
|
|
|
|
|
2024-10-01 15:35:57 -04:00
|
|
|
|
2006-01-11 12:17:47 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-08 15:59:53 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-18 20:17:49 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-10-19 16:08:53 -04:00
|
|
|
|
2010-06-13 03:28:59 +00:00
|
|
|
|
2012-02-24 08:31:31 +01:00
|
|
|
|
2012-01-09 13:44:23 -08:00
|
|
|
|
2012-05-03 02:25:55 -04:00
|
|
|
|
2020-07-22 09:40:27 +02:00
|
|
|
|
net: ioctl: Use kernel memory on protocol ioctl callbacks
Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback. This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.
Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).
This changes the "struct proto" ioctl format in the following way:
int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
+ int *karg);
(Important to say that this patch does not touch the "struct proto_ops"
protocols)
So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:
1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
to userspace
3) Read an input from userspace, and return a buffer to userspace.
The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:
* Protocol RAW:
* cmd = SIOCGETVIFCNT:
* input and output = struct sioc_vif_req
* cmd = SIOCGETSGCNT
* input and output = struct sioc_sg_req
* Explanation: for the SIOCGETVIFCNT case, userspace passes the input
argument, which is struct sioc_vif_req. Then the callback populates
the struct, which is copied back to userspace.
* Protocol RAW6:
* cmd = SIOCGETMIFCNT_IN6
* input and output = struct sioc_mif_req6
* cmd = SIOCGETSGCNT_IN6
* input and output = struct sioc_sg_req6
* Protocol PHONET:
* cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
* input int (4 bytes)
* Nothing is copied back to userspace.
For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.
The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-09 08:27:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-12-24 11:46:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
2007-09-12 12:01:34 +02:00
|
|
|
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:46:52 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-04-29 13:40:24 +00:00
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 00:12:34 -07:00
|
|
|
|
2011-11-22 05:10:51 +00:00
|
|
|
|
2015-06-15 11:26:18 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
bpf: Introduce bpf sk local storage
After allowing a bpf prog to
- directly read the skb->sk ptr
- get the fullsock bpf_sock by "bpf_sk_fullsock()"
- get the bpf_tcp_sock by "bpf_tcp_sock()"
- get the listener sock by "bpf_get_listener_sock()"
- avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock"
into different bpf running context.
this patch is another effort to make bpf's network programming
more intuitive to do (together with memory and performance benefit).
When bpf prog needs to store data for a sk, the current practice is to
define a map with the usual 4-tuples (src/dst ip/port) as the key.
If multiple bpf progs require to store different sk data, multiple maps
have to be defined. Hence, wasting memory to store the duplicated
keys (i.e. 4 tuples here) in each of the bpf map.
[ The smallest key could be the sk pointer itself which requires
some enhancement in the verifier and it is a separate topic. ]
Also, the bpf prog needs to clean up the elem when sk is freed.
Otherwise, the bpf map will become full and un-usable quickly.
The sk-free tracking currently could be done during sk state
transition (e.g. BPF_SOCK_OPS_STATE_CB).
The size of the map needs to be predefined which then usually ended-up
with an over-provisioned map in production. Even the map was re-sizable,
while the sk naturally come and go away already, this potential re-size
operation is arguably redundant if the data can be directly connected
to the sk itself instead of proxy-ing through a bpf map.
This patch introduces sk->sk_bpf_storage to provide local storage space
at sk for bpf prog to use. The space will be allocated when the first bpf
prog has created data for this particular sk.
The design optimizes the bpf prog's lookup (and then optionally followed by
an inline update). bpf_spin_lock should be used if the inline update needs
to be protected.
BPF_MAP_TYPE_SK_STORAGE:
-----------------------
To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in
this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can
be created to fit different bpf progs' needs. The map enforces
BTF to allow printing the sk-local-storage during a system-wise
sk dump (e.g. "ss -ta") in the future.
The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete
a "sk-local-storage" data from a particular sk.
Think of the map as a meta-data (or "type") of a "sk-local-storage". This
particular "type" of "sk-local-storage" data can then be stored in any sk.
The main purposes of this map are mostly:
1. Define the size of a "sk-local-storage" type.
2. Provide a similar syscall userspace API as the map (e.g. lookup/update,
map-id, map-btf...etc.)
3. Keep track of all sk's storages of this "type" and clean them up
when the map is freed.
sk->sk_bpf_storage:
------------------
The main lookup/update/delete is done on sk->sk_bpf_storage (which
is a "struct bpf_sk_storage"). When doing a lookup,
the "map" pointer is now used as the "key" to search on the
sk_storage->list. The "map" pointer is actually serving
as the "type" of the "sk-local-storage" that is being
requested.
To allow very fast lookup, it should be as fast as looking up an
array at a stable-offset. At the same time, it is not ideal to
set a hard limit on the number of sk-local-storage "type" that the
system can have. Hence, this patch takes a cache approach.
The last search result from sk_storage->list is cached in
sk_storage->cache[] which is a stable sized array. Each
"sk-local-storage" type has a stable offset to the cache[] array.
In the future, a map's flag could be introduced to do cache
opt-out/enforcement if it became necessary.
The cache size is 16 (i.e. 16 types of "sk-local-storage").
Programs can share map. On the program side, having a few bpf_progs
running in the networking hotpath is already a lot. The bpf_prog
should have already consolidated the existing sock-key-ed map usage
to minimize the map lookup penalty. 16 has enough runway to grow.
All sk-local-storage data will be removed from sk->sk_bpf_storage
during sk destruction.
bpf_sk_storage_get() and bpf_sk_storage_delete():
------------------------------------------------
Instead of using bpf_map_(lookup|update|delete)_elem(),
the bpf prog needs to use the new helper bpf_sk_storage_get() and
bpf_sk_storage_delete(). The verifier can then enforce the
ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to
"create" new elem if one does not exist in the sk. It is done by
the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be
provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE.
The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together,
it has eliminated the potential use cases for an equivalent
bpf_map_update_elem() API (for bpf_prog) in this patch.
Misc notes:
----------
1. map_get_next_key is not supported. From the userspace syscall
perspective, the map has the socket fd as the key while the map
can be shared by pinned-file or map-id.
Since btf is enforced, the existing "ss" could be enhanced to pretty
print the local-storage.
Supporting a kernel defined btf with 4 tuples as the return key could
be explored later also.
2. The sk->sk_lock cannot be acquired. Atomic operations is used instead.
e.g. cmpxchg is done on the sk->sk_bpf_storage ptr.
Please refer to the source code comments for the details in
synchronization cases and considerations.
3. The mem is charged to the sk->sk_omem_alloc as the sk filter does.
Benchmark:
---------
Here is the benchmark data collected by turning on
the "kernel.bpf_stats_enabled" sysctl.
Two bpf progs are tested:
One bpf prog with the usual bpf hashmap (max_entries = 8192) with the
sk ptr as the key. (verifier is modified to support sk ptr as the key
That should have shortened the key lookup time.)
Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE.
Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for
each egress skb and then bump the cnt. netperf is used to drive
data with 4096 connected UDP sockets.
BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run)
27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633
loaded_at 2019-04-15T13:46:39-0700 uid 0
xlated 344B jited 258B memlock 4096B map_ids 16
btf_id 5
BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run)
30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739
loaded_at 2019-04-15T13:47:54-0700 uid 0
xlated 168B jited 156B memlock 4096B map_ids 17
btf_id 6
Here is a high-level picture on how are the objects organized:
sk
┌──────┐
│ │
│ │
│ │
│*sk_bpf_storage─────▶ bpf_sk_storage
└──────┘ ┌───────┐
┌───────────┤ list │
│ │ │
│ │ │
│ │ │
│ └───────┘
│
│ elem
│ ┌────────┐
├─▶│ snode │
│ ├────────┤
│ │ data │ bpf_map
│ ├────────┤ ┌─────────┐
│ │map_node│◀─┬─────┤ list │
│ └────────┘ │ │ │
│ │ │ │
│ elem │ │ │
│ ┌────────┐ │ └─────────┘
└─▶│ snode │ │
├────────┤ │
bpf_map │ data │ │
┌─────────┐ ├────────┤ │
│ list ├───────▶│map_node│ │
│ │ └────────┘ │
│ │ │
│ │ elem │
└─────────┘ ┌────────┐ │
┌─▶│ snode │ │
│ ├────────┤ │
│ │ data │ │
│ ├────────┤ │
│ │map_node│◀─┘
│ └────────┘
│
│
│ ┌───────┐
sk └──────────│ list │
┌──────┐ │ │
│ │ │ │
│ │ │ │
│ │ └───────┘
│*sk_bpf_storage───────▶bpf_sk_storage
└──────┘
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-26 16:39:39 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-06-17 12:00:03 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-07-10 17:13:17 +03:00
|
|
|
|
net: ioctl: Use kernel memory on protocol ioctl callbacks
Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback. This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.
Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).
This changes the "struct proto" ioctl format in the following way:
int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
+ int *karg);
(Important to say that this patch does not touch the "struct proto_ops"
protocols)
So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:
1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
to userspace
3) Read an input from userspace, and return a buffer to userspace.
The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:
* Protocol RAW:
* cmd = SIOCGETVIFCNT:
* input and output = struct sioc_vif_req
* cmd = SIOCGETSGCNT
* input and output = struct sioc_sg_req
* Explanation: for the SIOCGETVIFCNT case, userspace passes the input
argument, which is struct sioc_vif_req. Then the callback populates
the struct, which is copied back to userspace.
* Protocol RAW6:
* cmd = SIOCGETMIFCNT_IN6
* input and output = struct sioc_mif_req6
* cmd = SIOCGETSGCNT_IN6
* input and output = struct sioc_sg_req6
* Protocol PHONET:
* cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
* input int (4 bytes)
* Nothing is copied back to userspace.
For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.
The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-09 08:27:42 -07:00
|
|
|
|
2013-06-10 11:39:50 +03:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
2025-04-25 10:11:33 +02:00
|
|
|
|
|
|
|
|
|
2022-04-06 14:37:54 -07:00
|
|
|
|
|
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2011-12-11 21:47:04 +00:00
|
|
|
|
|
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
2022-04-28 11:58:18 +01:00
|
|
|
|
|
|
|
|
|
2014-04-23 14:26:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-04 23:44:36 +09:00
|
|
|
|
2014-04-23 14:26:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-04 23:44:36 +09:00
|
|
|
|
2014-04-23 14:26:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:12 -07:00
|
|
|
|
|
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:12 -07:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-02 13:01:22 +02:00
|
|
|
|
2021-07-29 10:20:39 +08:00
|
|
|
|
2018-05-02 13:01:22 +02:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2009-08-05 10:42:58 -07:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2009-08-05 10:42:58 -07:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2009-08-05 10:42:58 -07:00
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-19 01:49:00 -07:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
2018-08-02 18:14:33 +02:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
|
|
|
|
|
2018-08-02 18:14:33 +02:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
|
|
|
|
|
2018-08-02 18:14:33 +02:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
2006-07-03 00:25:12 -07:00
|
|
|
|
|
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
2006-07-03 00:25:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2006-07-03 00:25:12 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2025-08-19 17:40:30 +00:00
|
|
|
|
2012-04-30 08:13:50 +02:00
|
|
|
|
2025-08-19 17:40:30 +00:00
|
|
|
|
2012-04-30 08:13:50 +02:00
|
|
|
|
2025-08-19 17:40:30 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2018-05-08 09:06:59 -07:00
|
|
|
|
|
|
|
|
|
2012-07-31 16:44:19 -07:00
|
|
|
|
2012-07-31 16:44:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-08 09:06:59 -07:00
|
|
|
|
2012-07-31 16:44:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-08 09:06:59 -07:00
|
|
|
|
netvm: prevent a stream-specific deadlock
This patch series is based on top of "Swap-over-NBD without deadlocking
v15" as it depends on the same reservation of PF_MEMALLOC reserves logic.
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. In diskless systems this is not an option so if swap if
required then swapping over the network is considered. The two likely
scenarios are when blade servers are used as part of a cluster where the
form factor or maintenance costs do not allow the use of disks and thin
clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap but this is not always an option. There is no
guarantee that the network attached storage (NAS) device is running Linux
or supports NBD. However, it is likely that it supports NFS so there are
users that want support for swapping over NFS despite any performance
concern. Some distributions currently carry patches that support swapping
over NFS but it would be preferable to support it in the mainline kernel.
Patch 1 avoids a stream-specific deadlock that potentially affects TCP.
Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC
reserves.
Patch 3 adds three helpers for filesystems to handle swap cache pages.
For example, page_file_mapping() returns page->mapping for
file-backed pages and the address_space of the underlying
swap file for swap cache pages.
Patch 4 adds two address_space_operations to allow a filesystem
to pin all metadata relevant to a swapfile in memory. Upon
successful activation, the swapfile is marked SWP_FILE and
the address space operation ->direct_IO is used for writing
and ->readpage for reading in swap pages.
Patch 5 notes that patch 3 is bolting
filesystem-specific-swapfile-support onto the side and that
the default handlers have different information to what
is available to the filesystem. This patch refactors the
code so that there are generic handlers for each of the new
address_space operations.
Patch 6 adds an API to allow a vector of kernel addresses to be
translated to struct pages and pinned for IO.
Patch 7 adds support for using highmem pages for swap by kmapping
the pages before calling the direct_IO handler.
Patch 8 updates NFS to use the helpers from patch 3 where necessary.
Patch 9 avoids setting PF_private on PG_swapcache pages within NFS.
Patch 10 implements the new swapfile-related address_space operations
for NFS and teaches the direct IO handler how to manage
kernel addresses.
Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO
where appropriate.
Patch 12 fixes a NULL pointer dereference that occurs when using
swap-over-NFS.
With the patches applied, it is possible to mount a swapfile that is on an
NFS filesystem. Swap performance is not great with a swap stress test
taking roughly twice as long to complete than if the swap device was
backed by NBD.
This patch: netvm: prevent a stream-specific deadlock
It could happen that all !SOCK_MEMALLOC sockets have buffered so much data
that we're over the global rmem limit. This will prevent SOCK_MEMALLOC
buffers from receiving data, which will prevent userspace from running,
which is needed to reduce the buffered data.
Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once
this change it applied, it is important that sockets that set
SOCK_MEMALLOC do not clear the flag until the socket is being torn down.
If this happens, a warning is generated and the tokens reclaimed to avoid
accounting errors until the bug is fixed.
[davem@davemloft.net: Warning about clearing SOCK_MEMALLOC]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:44:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-06-10 21:02:04 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
netvm: prevent a stream-specific deadlock
This patch series is based on top of "Swap-over-NBD without deadlocking
v15" as it depends on the same reservation of PF_MEMALLOC reserves logic.
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. In diskless systems this is not an option so if swap if
required then swapping over the network is considered. The two likely
scenarios are when blade servers are used as part of a cluster where the
form factor or maintenance costs do not allow the use of disks and thin
clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap but this is not always an option. There is no
guarantee that the network attached storage (NAS) device is running Linux
or supports NBD. However, it is likely that it supports NFS so there are
users that want support for swapping over NFS despite any performance
concern. Some distributions currently carry patches that support swapping
over NFS but it would be preferable to support it in the mainline kernel.
Patch 1 avoids a stream-specific deadlock that potentially affects TCP.
Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC
reserves.
Patch 3 adds three helpers for filesystems to handle swap cache pages.
For example, page_file_mapping() returns page->mapping for
file-backed pages and the address_space of the underlying
swap file for swap cache pages.
Patch 4 adds two address_space_operations to allow a filesystem
to pin all metadata relevant to a swapfile in memory. Upon
successful activation, the swapfile is marked SWP_FILE and
the address space operation ->direct_IO is used for writing
and ->readpage for reading in swap pages.
Patch 5 notes that patch 3 is bolting
filesystem-specific-swapfile-support onto the side and that
the default handlers have different information to what
is available to the filesystem. This patch refactors the
code so that there are generic handlers for each of the new
address_space operations.
Patch 6 adds an API to allow a vector of kernel addresses to be
translated to struct pages and pinned for IO.
Patch 7 adds support for using highmem pages for swap by kmapping
the pages before calling the direct_IO handler.
Patch 8 updates NFS to use the helpers from patch 3 where necessary.
Patch 9 avoids setting PF_private on PG_swapcache pages within NFS.
Patch 10 implements the new swapfile-related address_space operations
for NFS and teaches the direct IO handler how to manage
kernel addresses.
Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO
where appropriate.
Patch 12 fixes a NULL pointer dereference that occurs when using
swap-over-NFS.
With the patches applied, it is possible to mount a swapfile that is on an
NFS filesystem. Swap performance is not great with a swap stress test
taking roughly twice as long to complete than if the swap device was
backed by NBD.
This patch: netvm: prevent a stream-specific deadlock
It could happen that all !SOCK_MEMALLOC sockets have buffered so much data
that we're over the global rmem limit. This will prevent SOCK_MEMALLOC
buffers from receiving data, which will prevent userspace from running,
which is needed to reduce the buffered data.
Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once
this change it applied, it is important that sockets that set
SOCK_MEMALLOC do not clear the flag until the socket is being torn down.
If this happens, a warning is generated and the tokens reclaimed to avoid
accounting errors until the bug is fixed.
[davem@davemloft.net: Warning about clearing SOCK_MEMALLOC]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:44:41 -07:00
|
|
|
|
2015-06-10 21:02:04 -04:00
|
|
|
|
2012-07-31 16:44:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 16:44:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-08 15:59:53 -07:00
|
|
|
|
2012-07-31 16:44:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-08 15:59:53 -07:00
|
|
|
|
2021-11-15 11:02:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-08 15:59:53 -07:00
|
|
|
|
2012-07-31 16:44:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-27 18:48:21 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-27 18:48:22 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-27 18:48:21 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-04-16 22:31:14 +02:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-09 21:08:24 -07:00
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
|
|
|
|
|
2019-10-09 21:08:24 -07:00
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-04-16 22:31:14 +02:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:49 +02:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:49 +02:00
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
|
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
2021-10-08 11:00:53 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-24 16:58:54 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-24 16:58:54 -07:00
|
|
|
|
2007-07-09 13:16:00 -07:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
2008-05-02 16:20:10 -07:00
|
|
|
|
2007-05-24 16:58:54 -07:00
|
|
|
|
2012-05-16 19:58:40 +00:00
|
|
|
|
|
|
|
|
|
2008-05-02 16:20:10 -07:00
|
|
|
|
2007-05-24 16:58:54 -07:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-13 09:44:54 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-26 13:51:37 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-28 12:04:18 +00:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2011-11-28 12:04:18 +00:00
|
|
|
|
|
|
|
|
|
2015-10-26 13:51:37 +01:00
|
|
|
|
|
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2024-03-21 16:44:10 +08:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2011-06-17 12:00:03 +00:00
|
|
|
|
2009-10-14 20:40:11 -07:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
netvm: prevent a stream-specific deadlock
This patch series is based on top of "Swap-over-NBD without deadlocking
v15" as it depends on the same reservation of PF_MEMALLOC reserves logic.
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. In diskless systems this is not an option so if swap if
required then swapping over the network is considered. The two likely
scenarios are when blade servers are used as part of a cluster where the
form factor or maintenance costs do not allow the use of disks and thin
clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap but this is not always an option. There is no
guarantee that the network attached storage (NAS) device is running Linux
or supports NBD. However, it is likely that it supports NFS so there are
users that want support for swapping over NFS despite any performance
concern. Some distributions currently carry patches that support swapping
over NFS but it would be preferable to support it in the mainline kernel.
Patch 1 avoids a stream-specific deadlock that potentially affects TCP.
Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC
reserves.
Patch 3 adds three helpers for filesystems to handle swap cache pages.
For example, page_file_mapping() returns page->mapping for
file-backed pages and the address_space of the underlying
swap file for swap cache pages.
Patch 4 adds two address_space_operations to allow a filesystem
to pin all metadata relevant to a swapfile in memory. Upon
successful activation, the swapfile is marked SWP_FILE and
the address space operation ->direct_IO is used for writing
and ->readpage for reading in swap pages.
Patch 5 notes that patch 3 is bolting
filesystem-specific-swapfile-support onto the side and that
the default handlers have different information to what
is available to the filesystem. This patch refactors the
code so that there are generic handlers for each of the new
address_space operations.
Patch 6 adds an API to allow a vector of kernel addresses to be
translated to struct pages and pinned for IO.
Patch 7 adds support for using highmem pages for swap by kmapping
the pages before calling the direct_IO handler.
Patch 8 updates NFS to use the helpers from patch 3 where necessary.
Patch 9 avoids setting PF_private on PG_swapcache pages within NFS.
Patch 10 implements the new swapfile-related address_space operations
for NFS and teaches the direct IO handler how to manage
kernel addresses.
Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO
where appropriate.
Patch 12 fixes a NULL pointer dereference that occurs when using
swap-over-NFS.
With the patches applied, it is possible to mount a swapfile that is on an
NFS filesystem. Swap performance is not great with a swap stress test
taking roughly twice as long to complete than if the swap device was
backed by NBD.
This patch: netvm: prevent a stream-specific deadlock
It could happen that all !SOCK_MEMALLOC sockets have buffered so much data
that we're over the global rmem limit. This will prevent SOCK_MEMALLOC
buffers from receiving data, which will prevent userspace from running,
which is needed to reduce the buffered data.
Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once
this change it applied, it is important that sockets that set
SOCK_MEMALLOC do not clear the flag until the socket is being torn down.
If this happens, a warning is generated and the tokens reclaimed to avoid
accounting errors until the bug is fixed.
[davem@davemloft.net: Warning about clearing SOCK_MEMALLOC]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:44:41 -07:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2009-10-14 20:40:11 -07:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2008-12-17 22:11:38 -08:00
|
|
|
|
2010-05-11 23:19:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
2015-03-01 14:58:30 +02:00
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2014-04-11 16:15:36 -04:00
|
|
|
|
2009-10-14 20:40:11 -07:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
|
|
|
|
|
2026-04-09 14:56:20 +00:00
|
|
|
|
|
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
2022-04-07 14:20:49 +08:00
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
|
|
|
|
|
2026-04-09 14:56:22 +00:00
|
|
|
|
|
|
|
|
|
2026-04-09 14:56:20 +00:00
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
2022-04-07 14:20:49 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-04-09 14:56:20 +00:00
|
|
|
|
2022-04-07 14:20:49 +08:00
|
|
|
|
2026-04-09 14:56:20 +00:00
|
|
|
|
2022-04-07 14:20:49 +08:00
|
|
|
|
2026-04-09 14:56:20 +00:00
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
2022-04-07 14:20:49 +08:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2016-07-12 18:18:57 -04:00
|
|
|
|
2016-11-02 17:14:41 -07:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2026-04-09 14:56:24 +00:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2026-04-09 14:56:24 +00:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 16:44:10 +08:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
2010-04-27 15:13:20 -07:00
|
|
|
|
|
|
|
|
|
2006-11-16 14:06:06 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-07 14:18:42 -07:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2019-09-19 12:09:40 -04:00
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
2010-03-04 18:01:40 +00:00
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2010-03-04 18:01:40 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2016-11-02 17:14:41 -07:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2025-07-16 18:26:53 +02:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2016-07-12 18:18:57 -04:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2021-02-01 17:41:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
2010-04-08 23:03:29 +00:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
2025-06-30 12:19:25 +00:00
|
|
|
|
2021-02-01 17:41:32 +00:00
|
|
|
|
|
|
|
|
|
2009-10-19 23:46:20 +00:00
|
|
|
|
2023-09-21 20:28:18 +00:00
|
|
|
|
2011-08-01 16:19:00 +00:00
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-06-30 12:19:25 +00:00
|
|
|
|
2021-02-01 17:41:32 +00:00
|
|
|
|
|
|
|
|
|
2006-03-28 01:08:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:13 +02:00
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: core: enable SO_BINDTODEVICE for non-root users
Currently, SO_BINDTODEVICE requires CAP_NET_RAW. This change allows a
non-root user to bind a socket to an interface if it is not already
bound. This is useful to allow an application to bind itself to a
specific VRF for outgoing or incoming connections. Currently, an
application wanting to manage connections through several VRF need to
be privileged.
Previously, IP_UNICAST_IF and IPV6_UNICAST_IF were added for
Wine (76e21053b5bf3 and c4062dfc425e9) specifically for use by
non-root processes. However, they are restricted to sendmsg() and not
usable with TCP. Allowing SO_BINDTODEVICE would allow TCP clients to
get the same privilege. As for TCP servers, outside the VRF use case,
SO_BINDTODEVICE would only further restrict connections a server could
accept.
When an application is restricted to a VRF (with `ip vrf exec`), the
socket is bound to an interface at creation and therefore, a
non-privileged call to SO_BINDTODEVICE to escape the VRF fails.
When an application bound a socket to SO_BINDTODEVICE and transmit it
to a non-privileged process through a Unix socket, a tentative to
change the bound device also fails.
Before:
>>> import socket
>>> s=socket.socket(socket.AF_INET, socket.SOCK_STREAM)
>>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
PermissionError: [Errno 1] Operation not permitted
After:
>>> import socket
>>> s=socket.socket(socket.AF_INET, socket.SOCK_STREAM)
>>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0")
>>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
PermissionError: [Errno 1] Operation not permitted
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-31 15:20:10 +02:00
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:55:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-30 23:09:00 +02:00
|
|
|
|
2020-05-28 07:12:13 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-30 23:09:00 +02:00
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:13 +02:00
|
|
|
|
2020-05-30 23:09:00 +02:00
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:13 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:48 +02:00
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-26 02:26:21 +09:00
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:48 +02:00
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
|
|
|
|
|
2009-11-05 22:37:11 -08:00
|
|
|
|
|
|
|
|
|
2009-11-05 21:03:39 -08:00
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
2009-11-05 21:03:39 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
|
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:55:44 -07:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:55:44 -07:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:55:44 -07:00
|
|
|
|
2013-06-26 17:23:42 +02:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-12 16:02:00 +00:00
|
|
|
|
2015-04-01 17:07:44 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-30 10:12:44 +00:00
|
|
|
|
|
|
|
|
|
2015-04-01 17:07:44 +02:00
|
|
|
|
2023-08-16 08:15:39 +00:00
|
|
|
|
2015-04-01 17:07:44 +02:00
|
|
|
|
|
|
|
|
|
2023-09-12 16:02:00 +00:00
|
|
|
|
2015-04-01 17:07:44 +02:00
|
|
|
|
|
|
|
|
|
2020-06-17 22:23:25 -07:00
|
|
|
|
2015-04-01 17:07:44 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:17 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-19 04:06:46 +00:00
|
|
|
|
2020-05-28 07:12:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:11 +02:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:18 +00:00
|
|
|
|
2020-05-28 07:12:11 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:12 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
2020-05-28 07:12:12 +02:00
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
2020-05-28 07:12:12 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:14 +02:00
|
|
|
|
|
|
|
|
|
2024-10-17 21:34:35 +08:00
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:14 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-03 16:24:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-11 16:10:53 +01:00
|
|
|
|
|
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-31 13:52:12 +00:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-12-07 09:37:01 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
|
|
|
|
|
2021-11-15 11:02:33 -08:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-12-07 09:37:01 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
2022-02-17 09:05:02 -08:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-31 13:52:11 +00:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
2025-02-11 18:17:31 +01:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-02-20 15:29:30 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:16 +02:00
|
|
|
|
|
|
|
|
|
2026-04-07 17:14:38 -07:00
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-04-07 17:14:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-31 17:00:30 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:15 +00:00
|
|
|
|
2021-05-31 17:00:30 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-06-26 13:26:48 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-31 17:00:30 -04:00
|
|
|
|
2020-06-26 13:26:48 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-06-08 23:34:07 -07:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:08 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:15 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
2022-06-10 20:30:16 -07:00
|
|
|
|
|
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
2023-08-31 13:52:09 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
2023-07-28 15:03:08 +00:00
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2026-02-21 16:37:42 -08:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-07 21:03:30 +00:00
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-29 11:31:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:18:04 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
2022-08-16 23:17:11 -07:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
2007-09-14 16:41:03 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-09-21 20:28:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-13 09:44:54 +01:00
|
|
|
|
2023-09-21 20:28:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:14 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:15 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:16 +00:00
|
|
|
|
2025-05-19 13:57:55 -07:00
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:16 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: implement lockless setsockopt(SO_PEEK_OFF)
syzbot reported a lockdep violation [1] involving af_unix
support of SO_PEEK_OFF.
Since SO_PEEK_OFF is inherently not thread safe (it uses a per-socket
sk_peek_off field), there is really no point to enforce a pointless
thread safety in the kernel.
After this patch :
- setsockopt(SO_PEEK_OFF) no longer acquires the socket lock.
- skb_consume_udp() no longer has to acquire the socket lock.
- af_unix no longer needs a special version of sk_set_peek_off(),
because it does not lock u->iolock anymore.
As a followup, we could replace prot->set_peek_off to be a boolean
and avoid an indirect call, since we always use sk_set_peek_off().
[1]
WARNING: possible circular locking dependency detected
6.8.0-rc4-syzkaller-00267-g0f1dd5e91e2b #0 Not tainted
syz-executor.2/30025 is trying to acquire lock:
ffff8880765e7d80 (&u->iolock){+.+.}-{3:3}, at: unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789
but task is already holding lock:
ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1691 [inline]
ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sockopt_lock_sock net/core/sock.c:1060 [inline]
ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sk_setsockopt+0xe52/0x3360 net/core/sock.c:1193
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (sk_lock-AF_UNIX){+.+.}-{0:0}:
lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
lock_sock_nested+0x48/0x100 net/core/sock.c:3524
lock_sock include/net/sock.h:1691 [inline]
__unix_dgram_recvmsg+0x1275/0x12c0 net/unix/af_unix.c:2415
sock_recvmsg_nosec+0x18e/0x1d0 net/socket.c:1046
____sys_recvmsg+0x3c0/0x470 net/socket.c:2801
___sys_recvmsg net/socket.c:2845 [inline]
do_recvmmsg+0x474/0xae0 net/socket.c:2939
__sys_recvmmsg net/socket.c:3018 [inline]
__do_sys_recvmmsg net/socket.c:3041 [inline]
__se_sys_recvmmsg net/socket.c:3034 [inline]
__x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034
do_syscall_64+0xf9/0x240
entry_SYSCALL_64_after_hwframe+0x6f/0x77
-> #0 (&u->iolock){+.+.}-{3:3}:
check_prev_add kernel/locking/lockdep.c:3134 [inline]
check_prevs_add kernel/locking/lockdep.c:3253 [inline]
validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869
__lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137
lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
__mutex_lock_common kernel/locking/mutex.c:608 [inline]
__mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752
unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789
sk_setsockopt+0x207e/0x3360
do_sock_setsockopt+0x2fb/0x720 net/socket.c:2307
__sys_setsockopt+0x1ad/0x250 net/socket.c:2334
__do_sys_setsockopt net/socket.c:2343 [inline]
__se_sys_setsockopt net/socket.c:2340 [inline]
__x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340
do_syscall_64+0xf9/0x240
entry_SYSCALL_64_after_hwframe+0x6f/0x77
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(sk_lock-AF_UNIX);
lock(&u->iolock);
lock(sk_lock-AF_UNIX);
lock(&u->iolock);
*** DEADLOCK ***
1 lock held by syz-executor.2/30025:
#0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1691 [inline]
#0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sockopt_lock_sock net/core/sock.c:1060 [inline]
#0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sk_setsockopt+0xe52/0x3360 net/core/sock.c:1193
stack backtrace:
CPU: 0 PID: 30025 Comm: syz-executor.2 Not tainted 6.8.0-rc4-syzkaller-00267-g0f1dd5e91e2b #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x1e7/0x2e0 lib/dump_stack.c:106
check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2187
check_prev_add kernel/locking/lockdep.c:3134 [inline]
check_prevs_add kernel/locking/lockdep.c:3253 [inline]
validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869
__lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137
lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
__mutex_lock_common kernel/locking/mutex.c:608 [inline]
__mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752
unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789
sk_setsockopt+0x207e/0x3360
do_sock_setsockopt+0x2fb/0x720 net/socket.c:2307
__sys_setsockopt+0x1ad/0x250 net/socket.c:2334
__do_sys_setsockopt net/socket.c:2343 [inline]
__se_sys_setsockopt net/socket.c:2340 [inline]
__x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340
do_syscall_64+0xf9/0x240
entry_SYSCALL_64_after_hwframe+0x6f/0x77
RIP: 0033:0x7f78a1c7dda9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f78a0fde0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007f78a1dac050 RCX: 00007f78a1c7dda9
RDX: 000000000000002a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00007f78a1cca47a R08: 0000000000000004 R09: 0000000000000000
R10: 0000000020000180 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000006e R14: 00007f78a1dac050 R15: 00007ffe5cd81ae8
Fixes: 859051dd165e ("bpf: Implement cgroup sockaddr hooks for unix sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Daan De Meyer <daan.j.demeyer@gmail.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2024-02-19 14:12:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-10 17:14:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-06-20 15:55:35 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-06-20 15:55:36 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-21 20:28:11 +00:00
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2007-11-15 03:03:19 -08:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2018-06-12 10:05:55 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2013-01-22 09:49:50 +00:00
|
|
|
|
net: restrict SO_REUSEPORT to inet sockets
After blamed commit, crypto sockets could accidentally be destroyed
from RCU call back, as spotted by zyzbot [1].
Trying to acquire a mutex in RCU callback is not allowed.
Restrict SO_REUSEPORT socket option to inet sockets.
v1 of this patch supported TCP, UDP and SCTP sockets,
but fcnal-test.sh test needed RAW and ICMP support.
[1]
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:562
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 24, name: ksoftirqd/1
preempt_count: 100, expected: 0
RCU nest depth: 0, expected: 0
1 lock held by ksoftirqd/1/24:
#0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire include/linux/rcupdate.h:337 [inline]
#0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_do_batch kernel/rcu/tree.c:2561 [inline]
#0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_core+0xa37/0x17a0 kernel/rcu/tree.c:2823
Preemption disabled at:
[<ffffffff8161c8c8>] softirq_handle_begin kernel/softirq.c:402 [inline]
[<ffffffff8161c8c8>] handle_softirqs+0x128/0x9b0 kernel/softirq.c:537
CPU: 1 UID: 0 PID: 24 Comm: ksoftirqd/1 Not tainted 6.13.0-rc3-syzkaller-00174-ga024e377efed #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:94 [inline]
dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
__might_resched+0x5d4/0x780 kernel/sched/core.c:8758
__mutex_lock_common kernel/locking/mutex.c:562 [inline]
__mutex_lock+0x131/0xee0 kernel/locking/mutex.c:735
crypto_put_default_null_skcipher+0x18/0x70 crypto/crypto_null.c:179
aead_release+0x3d/0x50 crypto/algif_aead.c:489
alg_do_release crypto/af_alg.c:118 [inline]
alg_sock_destruct+0x86/0xc0 crypto/af_alg.c:502
__sk_destruct+0x58/0x5f0 net/core/sock.c:2260
rcu_do_batch kernel/rcu/tree.c:2567 [inline]
rcu_core+0xaaa/0x17a0 kernel/rcu/tree.c:2823
handle_softirqs+0x2d4/0x9b0 kernel/softirq.c:561
run_ksoftirqd+0xca/0x130 kernel/softirq.c:950
smpboot_thread_fn+0x544/0xa30 kernel/smpboot.c:164
kthread+0x2f0/0x390 kernel/kthread.c:389
ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
</TASK>
Fixes: 8c7138b33e5c ("net: Unpublish sk from sk_reuseport_cb before call_rcu")
Reported-by: syzbot+b3e02953598f447d4d2a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6772f2f4.050a0220.2f3838.04cb.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20241231160527.3994168-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-31 16:05:27 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-22 09:49:50 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-11-15 03:03:19 -08:00
|
|
|
|
net: call sk_dst_reset when set SO_DONTROUTE
after set SO_DONTROUTE to 1, the IP layer should not route packets if
the dest IP address is not in link scope. But if the socket has cached
the dst_entry, such packets would be routed until the sk_dst_cache
expires. So we should clean the sk_dst_cache when a user set
SO_DONTROUTE option. Below are server/client python scripts which
could reprodue this issue:
server side code:
==========================================================================
import socket
import struct
import time
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.bind(('0.0.0.0', 9000))
s.listen(1)
sock, addr = s.accept()
sock.setsockopt(socket.SOL_SOCKET, socket.SO_DONTROUTE, struct.pack('i', 1))
while True:
sock.send(b'foo')
time.sleep(1)
==========================================================================
client side code:
==========================================================================
import socket
import time
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect(('server_address', 9000))
while True:
data = s.recv(1024)
print(data)
==========================================================================
Signed-off-by: yupeng <yupeng0921@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-05 18:56:28 -08:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-26 20:07:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 10:46:44 -07:00
|
|
|
|
2005-08-09 19:30:51 -07:00
|
|
|
|
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values
SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or
underflow their input value. This patch aims at providing explicit
handling of these extreme cases, to get a clear behaviour even with
values bigger than INT_MAX / 2 or lower than INT_MIN / 2.
For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here,
but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE
(with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max').
Overflow of positive values
===========================
When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds
INT_MAX / 2, the buffer size is set to its minimum value because
'val * 2' overflows, and max_t() considers that it's smaller than
SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with
net.core.wmem_max > INT_MAX / 2.
SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe
for the maximum buffer size by setting an arbitrary large number that
gets capped to the maximum allowed/possible size. Having the upper
half of the positive integer space to potentially reduce the buffer
size to its minimum value defeats this purpose.
This patch caps the base value to INT_MAX / 2, so that bigger values
don't overflow and keep setting the buffer size to its maximum.
Underflow of negative values
============================
For negative numbers, SO_SNDBUF always considers them bigger than
net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX].
Therefore such values are set to net.core.wmem_max and we're back to
the behaviour of positive integers described above (return maximum
buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF
otherwise).
However, SO_SNDBUFFORCE behaves differently. The user value is
directly multiplied by two and compared with SOCK_MIN_SNDBUF. If
'val * 2' doesn't underflow or if it underflows to a value smaller
than SOCK_MIN_SNDBUF then buffer size is set to its minimum value.
Otherwise the buffer size is set to the underflowed value.
This patch treats negative values passed to SO_SNDBUFFORCE as null, to
prevent underflows. Therefore negative values now always set the buffer
size to its minimum value.
Even though SO_SNDBUF behaves inconsistently by setting buffer size to
the maximum value when passed a negative number, no attempt is made to
modify this behaviour. There may exist some programs that rely on using
negative numbers to set the maximum buffer size. Avoiding overflows
because of extreme net.core.wmem_max values is the most we can do here.
Summary of altered behaviours
=============================
val : user-space value passed to setsockopt()
val_uf : the underflowed value resulting from doubling val when
val < INT_MIN / 2
wmem_max : short for net.core.wmem_max
val_cap : min(val, wmem_max)
min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF)
max_len : maximal possible buffer length, regardless of wmem_max (that
is, INT_MAX - 1)
^^^^ : altered behaviour
SO_SNDBUF:
+-------------------------+-------------+------------+----------------+
| CONDITION | OLD RESULT | NEW RESULT | COMMENT |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | No overflow, |
| wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original |
| | | | behaviour |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | Cap wmem_max |
| INT_MAX/2 < wmem_max | min_len | max_len | to prevent |
| | | ^^^^^^^ | overflow |
+-------------------------+-------------+------------+----------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+-------------------------+-------------+------------+----------------+
| min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case |
| val_cap <= INT_MAX/2 | | | |
+-------------------------+-------------+------------+----------------+
| min_len < val && | | | Cap val_cap |
| INT_MAX/2 < val_cap | min_len | max_len | again to |
| (implies that | | ^^^^^^^ | prevent |
| INT_MAX/2 < wmem_max) | | | overflow |
+-------------------------+-------------+------------+----------------+
SO_SNDBUFFORCE:
+------------------------------+---------+---------+------------------+
| CONDITION | BEFORE | AFTER | COMMENT |
| | PATCH | PATCH | |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | min_len | min_len | Underflow with |
| val_uf <= min_len | | | no consequence |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to |
| val_uf > min_len | | ^^^^^^^ | avoid underflow |
+------------------------------+---------+---------+------------------+
| INT_MIN/2 <= val < 0 | min_len | min_len | No underflow |
+------------------------------+---------+---------+------------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+------------------------------+---------+---------+------------------+
| min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case |
+------------------------------+---------+---------+------------------+
| INT_MAX/2 < val | min_len | max_len | Cap val to |
| | | ^^^^^^^ | prevent overflow |
+------------------------------+---------+---------+------------------+
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 04:30:34 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
|
|
|
|
|
2012-04-26 20:07:59 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values
SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or
underflow their input value. This patch aims at providing explicit
handling of these extreme cases, to get a clear behaviour even with
values bigger than INT_MAX / 2 or lower than INT_MIN / 2.
For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here,
but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE
(with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max').
Overflow of positive values
===========================
When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds
INT_MAX / 2, the buffer size is set to its minimum value because
'val * 2' overflows, and max_t() considers that it's smaller than
SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with
net.core.wmem_max > INT_MAX / 2.
SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe
for the maximum buffer size by setting an arbitrary large number that
gets capped to the maximum allowed/possible size. Having the upper
half of the positive integer space to potentially reduce the buffer
size to its minimum value defeats this purpose.
This patch caps the base value to INT_MAX / 2, so that bigger values
don't overflow and keep setting the buffer size to its maximum.
Underflow of negative values
============================
For negative numbers, SO_SNDBUF always considers them bigger than
net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX].
Therefore such values are set to net.core.wmem_max and we're back to
the behaviour of positive integers described above (return maximum
buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF
otherwise).
However, SO_SNDBUFFORCE behaves differently. The user value is
directly multiplied by two and compared with SOCK_MIN_SNDBUF. If
'val * 2' doesn't underflow or if it underflows to a value smaller
than SOCK_MIN_SNDBUF then buffer size is set to its minimum value.
Otherwise the buffer size is set to the underflowed value.
This patch treats negative values passed to SO_SNDBUFFORCE as null, to
prevent underflows. Therefore negative values now always set the buffer
size to its minimum value.
Even though SO_SNDBUF behaves inconsistently by setting buffer size to
the maximum value when passed a negative number, no attempt is made to
modify this behaviour. There may exist some programs that rely on using
negative numbers to set the maximum buffer size. Avoiding overflows
because of extreme net.core.wmem_max values is the most we can do here.
Summary of altered behaviours
=============================
val : user-space value passed to setsockopt()
val_uf : the underflowed value resulting from doubling val when
val < INT_MIN / 2
wmem_max : short for net.core.wmem_max
val_cap : min(val, wmem_max)
min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF)
max_len : maximal possible buffer length, regardless of wmem_max (that
is, INT_MAX - 1)
^^^^ : altered behaviour
SO_SNDBUF:
+-------------------------+-------------+------------+----------------+
| CONDITION | OLD RESULT | NEW RESULT | COMMENT |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | No overflow, |
| wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original |
| | | | behaviour |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | Cap wmem_max |
| INT_MAX/2 < wmem_max | min_len | max_len | to prevent |
| | | ^^^^^^^ | overflow |
+-------------------------+-------------+------------+----------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+-------------------------+-------------+------------+----------------+
| min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case |
| val_cap <= INT_MAX/2 | | | |
+-------------------------+-------------+------------+----------------+
| min_len < val && | | | Cap val_cap |
| INT_MAX/2 < val_cap | min_len | max_len | again to |
| (implies that | | ^^^^^^^ | prevent |
| INT_MAX/2 < wmem_max) | | | overflow |
+-------------------------+-------------+------------+----------------+
SO_SNDBUFFORCE:
+------------------------------+---------+---------+------------------+
| CONDITION | BEFORE | AFTER | COMMENT |
| | PATCH | PATCH | |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | min_len | min_len | Underflow with |
| val_uf <= min_len | | | no consequence |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to |
| val_uf > min_len | | ^^^^^^^ | avoid underflow |
+------------------------------+---------+---------+------------------+
| INT_MIN/2 <= val < 0 | min_len | min_len | No underflow |
+------------------------------+---------+---------+------------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+------------------------------+---------+---------+------------------+
| min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case |
+------------------------------+---------+---------+------------------+
| INT_MAX/2 < val | min_len | max_len | Cap val to |
| | | ^^^^^^^ | prevent overflow |
+------------------------------+---------+---------+------------------+
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 04:30:34 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-26 20:07:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 10:46:44 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values
SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or
underflow their input value. This patch aims at providing explicit
handling of these extreme cases, to get a clear behaviour even with
values bigger than INT_MAX / 2 or lower than INT_MIN / 2.
For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here,
but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE
(with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max').
Overflow of positive values
===========================
When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds
INT_MAX / 2, the buffer size is set to its minimum value because
'val * 2' overflows, and max_t() considers that it's smaller than
SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with
net.core.wmem_max > INT_MAX / 2.
SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe
for the maximum buffer size by setting an arbitrary large number that
gets capped to the maximum allowed/possible size. Having the upper
half of the positive integer space to potentially reduce the buffer
size to its minimum value defeats this purpose.
This patch caps the base value to INT_MAX / 2, so that bigger values
don't overflow and keep setting the buffer size to its maximum.
Underflow of negative values
============================
For negative numbers, SO_SNDBUF always considers them bigger than
net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX].
Therefore such values are set to net.core.wmem_max and we're back to
the behaviour of positive integers described above (return maximum
buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF
otherwise).
However, SO_SNDBUFFORCE behaves differently. The user value is
directly multiplied by two and compared with SOCK_MIN_SNDBUF. If
'val * 2' doesn't underflow or if it underflows to a value smaller
than SOCK_MIN_SNDBUF then buffer size is set to its minimum value.
Otherwise the buffer size is set to the underflowed value.
This patch treats negative values passed to SO_SNDBUFFORCE as null, to
prevent underflows. Therefore negative values now always set the buffer
size to its minimum value.
Even though SO_SNDBUF behaves inconsistently by setting buffer size to
the maximum value when passed a negative number, no attempt is made to
modify this behaviour. There may exist some programs that rely on using
negative numbers to set the maximum buffer size. Avoiding overflows
because of extreme net.core.wmem_max values is the most we can do here.
Summary of altered behaviours
=============================
val : user-space value passed to setsockopt()
val_uf : the underflowed value resulting from doubling val when
val < INT_MIN / 2
wmem_max : short for net.core.wmem_max
val_cap : min(val, wmem_max)
min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF)
max_len : maximal possible buffer length, regardless of wmem_max (that
is, INT_MAX - 1)
^^^^ : altered behaviour
SO_SNDBUF:
+-------------------------+-------------+------------+----------------+
| CONDITION | OLD RESULT | NEW RESULT | COMMENT |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | No overflow, |
| wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original |
| | | | behaviour |
+-------------------------+-------------+------------+----------------+
| val < 0 && | | | Cap wmem_max |
| INT_MAX/2 < wmem_max | min_len | max_len | to prevent |
| | | ^^^^^^^ | overflow |
+-------------------------+-------------+------------+----------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+-------------------------+-------------+------------+----------------+
| min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case |
| val_cap <= INT_MAX/2 | | | |
+-------------------------+-------------+------------+----------------+
| min_len < val && | | | Cap val_cap |
| INT_MAX/2 < val_cap | min_len | max_len | again to |
| (implies that | | ^^^^^^^ | prevent |
| INT_MAX/2 < wmem_max) | | | overflow |
+-------------------------+-------------+------------+----------------+
SO_SNDBUFFORCE:
+------------------------------+---------+---------+------------------+
| CONDITION | BEFORE | AFTER | COMMENT |
| | PATCH | PATCH | |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | min_len | min_len | Underflow with |
| val_uf <= min_len | | | no consequence |
+------------------------------+---------+---------+------------------+
| val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to |
| val_uf > min_len | | ^^^^^^^ | avoid underflow |
+------------------------------+---------+---------+------------------+
| INT_MIN/2 <= val < 0 | min_len | min_len | No underflow |
+------------------------------+---------+---------+------------------+
| 0 <= val <= min_len/2 | min_len | min_len | Ordinary case |
+------------------------------+---------+---------+------------------+
| min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case |
+------------------------------+---------+---------+------------------+
| INT_MAX/2 < val | min_len | max_len | Cap val to |
| | | ^^^^^^^ | prevent overflow |
+------------------------------+---------+---------+------------------+
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 04:30:34 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-28 07:12:16 +02:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2017-01-09 16:55:12 +01:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-05-23 08:47:19 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-19 04:06:46 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-08-19 04:06:46 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-08-19 04:06:46 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2019-02-02 07:34:50 -08:00
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2019-02-02 07:34:50 -08:00
|
|
|
|
2021-07-02 07:41:01 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2021-06-03 16:24:28 -07:00
|
|
|
|
2019-02-02 07:34:51 -08:00
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
2021-07-07 13:01:00 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-08-08 13:58:09 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2023-08-08 13:58:09 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-16 10:33:35 -07:00
|
|
|
|
2019-10-09 15:32:35 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-08-08 13:58:09 +00:00
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
2014-12-01 15:06:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2014-12-01 15:06:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
|
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
|
|
|
|
|
2020-07-17 08:23:13 +02:00
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-13 15:00:01 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-10-17 21:21:26 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2013-01-16 22:55:49 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-30 19:08:16 -08:00
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
|
|
|
|
|
2008-01-30 19:08:16 -08:00
|
|
|
|
2021-05-31 17:00:30 -04:00
|
|
|
|
2018-11-08 08:13:35 -06:00
|
|
|
|
2021-05-31 17:00:30 -04:00
|
|
|
|
|
|
|
|
|
2008-01-30 19:08:16 -08:00
|
|
|
|
2022-04-27 16:02:37 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[AF_UNIX]: Datagram getpeersec
This patch implements an API whereby an application can determine the
label of its peer's Unix datagram sockets via the auxiliary data mechanism of
recvmsg.
Patch purpose:
This patch enables a security-aware application to retrieve the
security context of the peer of a Unix datagram socket. The application
can then use this security context to determine the security context for
processing on behalf of the peer who sent the packet.
Patch design and implementation:
The design and implementation is very similar to the UDP case for INET
sockets. Basically we build upon the existing Unix domain socket API for
retrieving user credentials. Linux offers the API for obtaining user
credentials via ancillary messages (i.e., out of band/control messages
that are bundled together with a normal message). To retrieve the security
context, the application first indicates to the kernel such desire by
setting the SO_PASSSEC option via getsockopt. Then the application
retrieves the security context using the auxiliary data mechanism.
An example server application for Unix datagram socket should look like this:
toggle = 1;
toggle_len = sizeof(toggle);
setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len);
recvmsg(sockfd, &msg_hdr, 0);
if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) {
cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr);
if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) &&
cmsg_hdr->cmsg_level == SOL_SOCKET &&
cmsg_hdr->cmsg_type == SCM_SECURITY) {
memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext));
}
}
sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow
a server socket to receive security context of the peer.
Testing:
We have tested the patch by setting up Unix datagram client and server
applications. We verified that the server can retrieve the security context
using the auxiliary data mechanism of recvmsg.
Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com>
Acked-by: Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 12:27:47 -07:00
|
|
|
|
2024-12-13 09:44:57 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
2011-10-07 03:30:20 +00:00
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
2011-11-09 10:15:42 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-02-11 15:39:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-03-28 11:19:25 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
af_unix: Move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.
Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.
Also, as mentioned in commit 16e572626961 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.
Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
While at it, other SOCK_XXX flags in net.h are grouped as enum.
Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-24 08:20:52 -07:00
|
|
|
|
af_unix: Introduce SO_PASSRIGHTS.
As long as recvmsg() or recvmmsg() is used with cmsg, it is not
possible to avoid receiving file descriptors via SCM_RIGHTS.
This behaviour has occasionally been flagged as problematic, as
it can be (ab)used to trigger DoS during close(), for example, by
passing a FUSE-controlled fd or a hung NFS fd.
For instance, as noted on the uAPI Group page [0], an untrusted peer
could send a file descriptor pointing to a hung NFS mount and then
close it. Once the receiver calls recvmsg() with msg_control, the
descriptor is automatically installed, and then the responsibility
for the final close() now falls on the receiver, which may result
in blocking the process for a long time.
Regarding this, systemd calls cmsg_close_all() [1] after each
recvmsg() to close() unwanted file descriptors sent via SCM_RIGHTS.
However, this cannot work around the issue at all, because the final
fput() may still occur on the receiver's side once sendmsg() with
SCM_RIGHTS succeeds. Also, even filtering by LSM at recvmsg() does
not work for the same reason.
Thus, we need a better way to refuse SCM_RIGHTS at sendmsg().
Let's introduce SO_PASSRIGHTS to disable SCM_RIGHTS.
Note that this option is enabled by default for backward
compatibility.
Link: https://uapi-group.org/kernel-features/#disabling-reception-of-scm_rights-for-af_unix-sockets #[0]
Link: https://github.com/systemd/systemd/blob/v257.5/src/basic/fd-util.c#L612-L628 #[1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-24 08:20:52 -07:00
|
|
|
|
2015-10-08 19:33:21 -07:00
|
|
|
|
soreuseport: Fix socket selection for SO_INCOMING_CPU.
Kazuho Oku reported that setsockopt(SO_INCOMING_CPU) does not work
with setsockopt(SO_REUSEPORT) since v4.6.
With the combination of SO_REUSEPORT and SO_INCOMING_CPU, we could
build a highly efficient server application.
setsockopt(SO_INCOMING_CPU) associates a CPU with a TCP listener
or UDP socket, and then incoming packets processed on the CPU will
likely be distributed to the socket. Technically, a socket could
even receive packets handled on another CPU if no sockets in the
reuseport group have the same CPU receiving the flow.
The logic exists in compute_score() so that a socket will get a higher
score if it has the same CPU with the flow. However, the score gets
ignored after the blamed two commits, which introduced a faster socket
selection algorithm for SO_REUSEPORT.
This patch introduces a counter of sockets with SO_INCOMING_CPU in
a reuseport group to check if we should iterate all sockets to find
a proper one. We increment the counter when
* calling listen() if the socket has SO_INCOMING_CPU and SO_REUSEPORT
* enabling SO_INCOMING_CPU if the socket is in a reuseport group
Also, we decrement it when
* detaching a socket out of the group to apply SO_INCOMING_CPU to
migrated TCP requests
* disabling SO_INCOMING_CPU if the socket is in a reuseport group
When the counter reaches 0, we can get back to the O(1) selection
algorithm.
The overall changes are negligible for the non-SO_INCOMING_CPU case,
and the only notable thing is that we have to update sk_incomnig_cpu
under reuseport_lock. Otherwise, the race prevents transitioning to
the O(n) algorithm and results in the wrong socket selection.
cpu1 (setsockopt) cpu2 (listen)
+-----------------+ +-------------+
lock_sock(sk1) lock_sock(sk2)
reuseport_update_incoming_cpu(sk1, val)
.
| /* set CPU as 0 */
|- WRITE_ONCE(sk1->incoming_cpu, val)
|
| spin_lock_bh(&reuseport_lock)
| reuseport_grow(sk2, reuse)
| .
| |- more_socks_size = reuse->max_socks * 2U;
| |- if (more_socks_size > U16_MAX &&
| | reuse->num_closed_socks)
| | .
| | |- RCU_INIT_POINTER(sk1->sk_reuseport_cb, NULL);
| | `- __reuseport_detach_closed_sock(sk1, reuse)
| | .
| | `- reuseport_put_incoming_cpu(sk1, reuse)
| | .
| | | /* Read shutdown()ed sk1's sk_incoming_cpu
| | | * without lock_sock().
| | | */
| | `- if (sk1->sk_incoming_cpu >= 0)
| | .
| | | /* decrement not-yet-incremented
| | | * count, which is never incremented.
| | | */
| | `- __reuseport_put_incoming_cpu(reuse);
| |
| `- spin_lock_bh(&reuseport_lock)
|
|- spin_lock_bh(&reuseport_lock)
|
|- reuse = rcu_dereference_protected(sk1->sk_reuseport_cb, ...)
|- if (!reuse)
| .
| | /* Cannot increment reuse->incoming_cpu. */
| `- goto out;
|
`- spin_unlock_bh(&reuseport_lock)
Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: c125e80b8868 ("soreuseport: fast reuseport TCP socket selection")
Reported-by: Kazuho Oku <kazuhooku@gmail.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-10-21 13:44:34 -07:00
|
|
|
|
2015-10-08 19:33:21 -07:00
|
|
|
|
|
|
|
|
|
2016-02-24 10:02:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-03 16:29:40 -04:00
|
|
|
|
|
|
|
|
|
2018-02-15 10:49:34 -08:00
|
|
|
|
2021-11-15 11:02:33 -08:00
|
|
|
|
2018-11-30 15:32:39 -05:00
|
|
|
|
|
|
|
|
|
2022-03-07 23:31:26 +01:00
|
|
|
|
2018-02-15 10:49:34 -08:00
|
|
|
|
2022-03-07 23:31:26 +01:00
|
|
|
|
2018-02-15 10:49:34 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-07 09:40:57 -08:00
|
|
|
|
|
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
2020-07-23 08:08:50 +02:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:23 -07:00
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-29 11:31:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 10:05:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
2020-05-28 07:12:13 +02:00
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
|
|
|
|
|
2021-08-04 10:55:56 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2022-08-16 23:17:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2022-08-16 23:17:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-01-03 09:17:14 -08:00
|
|
|
|
|
|
|
|
|
2010-06-13 03:28:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-23 16:39:45 -06:00
|
|
|
|
|
|
|
|
|
2010-06-13 03:28:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:29:12 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-09-01 17:27:56 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2017-04-05 19:00:55 -07:00
|
|
|
|
2019-02-28 15:17:28 -08:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2019-02-02 07:34:44 -08:00
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2010-01-15 01:08:58 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2009-02-23 15:38:41 -08:00
|
|
|
|
net: 4 bytes kernel memory disclosure in SO_BSDCOMPAT gsopt try #2
In function sock_getsockopt() located in net/core/sock.c, optval v.val
is not correctly initialized and directly returned in userland in case
we have SO_BSDCOMPAT option set.
This dummy code should trigger the bug:
int main(void)
{
unsigned char buf[4] = { 0, 0, 0, 0 };
int len;
int sock;
sock = socket(33, 2, 2);
getsockopt(sock, 1, SO_BSDCOMPAT, &buf, &len);
printf("%x%x%x%x\n", buf[0], buf[1], buf[2], buf[3]);
close(sock);
}
Here is a patch that fix this bug by initalizing v.val just after its
declaration.
Signed-off-by: Clément Lecigne <clement.lecigne@netasq.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-12 16:59:09 -08:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-07-28 15:03:13 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-07-28 15:03:14 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-01-22 09:49:50 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-08-04 07:28:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-08-04 07:28:29 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2014-05-23 08:47:19 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-07-28 15:03:18 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2023-08-19 04:06:46 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2007-03-25 22:14:49 -07:00
|
|
|
|
2019-02-02 07:34:50 -08:00
|
|
|
|
2007-03-25 22:14:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2019-02-02 07:34:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2023-12-22 00:19:01 +01:00
|
|
|
|
2021-06-30 16:11:59 +08:00
|
|
|
|
2023-12-22 00:19:01 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-02-02 07:34:54 -08:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:12 +00:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-07-28 15:03:11 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
[AF_UNIX]: Datagram getpeersec
This patch implements an API whereby an application can determine the
label of its peer's Unix datagram sockets via the auxiliary data mechanism of
recvmsg.
Patch purpose:
This patch enables a security-aware application to retrieve the
security context of the peer of a Unix datagram socket. The application
can then use this security context to determine the security context for
processing on behalf of the peer who sent the packet.
Patch design and implementation:
The design and implementation is very similar to the UDP case for INET
sockets. Basically we build upon the existing Unix domain socket API for
retrieving user credentials. Linux offers the API for obtaining user
credentials via ancillary messages (i.e., out of band/control messages
that are bundled together with a normal message). To retrieve the security
context, the application first indicates to the kernel such desire by
setting the SO_PASSSEC option via getsockopt. Then the application
retrieves the security context using the auxiliary data mechanism.
An example server application for Unix datagram socket should look like this:
toggle = 1;
toggle_len = sizeof(toggle);
setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len);
recvmsg(sockfd, &msg_hdr, 0);
if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) {
cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr);
if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) &&
cmsg_hdr->cmsg_level == SOL_SOCKET &&
cmsg_hdr->cmsg_type == SCM_SECURITY) {
memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext));
}
}
sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow
a server socket to receive security context of the peer.
Testing:
We have tested the patch by setting up Unix datagram client and server
applications. We verified that the server can retrieve the security context
using the auxiliary data mechanism of recvmsg.
Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com>
Acked-by: Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 12:27:47 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2025-05-19 13:57:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
af_unix: Move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.
Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.
Also, as mentioned in commit 16e572626961 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.
Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
While at it, other SOCK_XXX flags in net.h are grouped as enum.
Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:57 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2023-06-08 22:26:25 +02:00
|
|
|
|
2025-05-19 13:57:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
af_unix: Move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.
Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.
Also, as mentioned in commit 16e572626961 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.
Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
While at it, other SOCK_XXX flags in net.h are grouped as enum.
Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:57 -07:00
|
|
|
|
2023-06-08 22:26:25 +02:00
|
|
|
|
|
|
|
|
|
af_unix: Introduce SO_PASSRIGHTS.
As long as recvmsg() or recvmmsg() is used with cmsg, it is not
possible to avoid receiving file descriptors via SCM_RIGHTS.
This behaviour has occasionally been flagged as problematic, as
it can be (ab)used to trigger DoS during close(), for example, by
passing a FUSE-controlled fd or a hung NFS fd.
For instance, as noted on the uAPI Group page [0], an untrusted peer
could send a file descriptor pointing to a hung NFS mount and then
close it. Once the receiver calls recvmsg() with msg_control, the
descriptor is automatically installed, and then the responsibility
for the final close() now falls on the receiver, which may result
in blocking the process for a long time.
Regarding this, systemd calls cmsg_close_all() [1] after each
recvmsg() to close() unwanted file descriptors sent via SCM_RIGHTS.
However, this cannot work around the issue at all, because the final
fput() may still occur on the receiver's side once sendmsg() with
SCM_RIGHTS succeeds. Also, even filtering by LSM at recvmsg() does
not work for the same reason.
Thus, we need a better way to refuse SCM_RIGHTS at sendmsg().
Let's introduce SO_PASSRIGHTS to disable SCM_RIGHTS.
Note that this option is enabled by default for backward
compatibility.
Link: https://uapi-group.org/kernel-features/#disabling-reception-of-scm_rights-for-af_unix-sockets #[0]
Link: https://github.com/systemd/systemd/blob/v257.5/src/basic/fd-util.c#L612-L628 #[1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-08 22:26:25 +02:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2010-06-13 03:30:14 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
2010-06-13 03:30:14 +00:00
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2010-06-13 03:30:14 +00:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-06-08 22:26:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-25 10:11:33 +02:00
|
|
|
|
2023-06-08 22:26:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-07 10:12:25 +02:00
|
|
|
|
2023-06-08 22:26:26 +02:00
|
|
|
|
2025-04-25 10:11:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-08 22:26:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
net: introduce SO_PEERGROUPS getsockopt
This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to
retrieve the auxiliary groups of the remote peer. It is designed to
naturally extend SO_PEERCRED. That is, the underlying data is from the
same credentials. Regarding its syntax, it is based on SO_PEERSEC. That
is, if the provided buffer is too small, ERANGE is returned and @optlen
is updated. Otherwise, the information is copied, @optlen is set to the
actual size, and 0 is returned.
While SO_PEERCRED (and thus `struct ucred') already returns the primary
group, it lacks the auxiliary group vector. However, nearly all access
controls (including kernel side VFS and SYSVIPC, but also user-space
polkit, DBus, ...) consider the entire set of groups, rather than just
the primary group. But this is currently not possible with pure
SO_PEERCRED. Instead, user-space has to work around this and query the
system database for the auxiliary groups of a UID retrieved via
SO_PEERCRED.
Unfortunately, there is no race-free way to query the auxiliary groups
of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space
solution is to use getgrouplist(3p), which itself falls back to NSS and
whatever is configured in nsswitch.conf(3). This effectively checks
which groups we *would* assign to the user if it logged in *now*. On
normal systems it is as easy as reading /etc/group, but with NSS it can
resort to quering network databases (eg., LDAP), using IPC or network
communication.
Long story short: Whenever we want to use auxiliary groups for access
checks on IPC, we need further IPC to talk to the user/group databases,
rather than just relying on SO_PEERCRED and the incoming socket. This
is unfortunate, and might even result in dead-locks if the database
query uses the same IPC as the original request.
So far, those recursions / dead-locks have been avoided by using
primitive IPC for all crucial NSS modules. However, we want to avoid
re-inventing the wheel for each NSS module that might be involved in
user/group queries. Hence, we would preferably make DBus (and other IPC
that supports access-management based on groups) work without resorting
to the user/group database. This new SO_PEERGROUPS ioctl would allow us
to make dbus-daemon work without ever calling into NSS.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Simon McVittie <simon.mcvittie@collabora.co.uk>
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 10:47:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2023-07-28 17:48:13 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2023-08-08 13:58:09 +00:00
|
|
|
|
2018-02-12 20:00:20 +01:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-28 17:48:13 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-19 13:57:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
af_unix: Move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.
Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.
Also, as mentioned in commit 16e572626961 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.
Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.
While at it, other SOCK_XXX flags in net.h are grouped as enum.
Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2025-05-19 13:57:57 -07:00
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-10 12:31:21 -04:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2008-01-30 19:08:16 -08:00
|
|
|
|
2023-07-28 15:03:15 +00:00
|
|
|
|
2008-01-30 19:08:16 -08:00
|
|
|
|
|
|
|
|
|
2022-04-27 16:02:37 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-13 09:44:57 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
|
|
|
|
|
|
|
|
|
2011-11-09 10:15:42 +01:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2011-11-09 10:15:42 +01:00
|
|
|
|
|
|
|
|
|
2012-02-21 07:31:34 +00:00
|
|
|
|
2023-08-08 13:58:09 +00:00
|
|
|
|
2012-02-21 07:31:34 +00:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:16 +00:00
|
|
|
|
2012-02-21 07:31:34 +00:00
|
|
|
|
2012-02-24 14:48:34 -05:00
|
|
|
|
2012-05-16 05:57:07 +00:00
|
|
|
|
2012-02-24 14:48:34 -05:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
2012-10-18 23:55:56 +00:00
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
|
|
|
|
|
sk-filter: Add ability to get socket filter program (v2)
The SO_ATTACH_FILTER option is set only. I propose to add the get
ability by using SO_ATTACH_FILTER in getsockopt. To be less
irritating to eyes the SO_GET_FILTER alias to it is declared. This
ability is required by checkpoint-restore project to be able to
save full state of a socket.
There are two issues with getting filter back.
First, kernel modifies the sock_filter->code on filter load, thus in
order to return the filter element back to user we have to decode it
into user-visible constants. Fortunately the modification in question
is interconvertible.
Second, the BPF_S_ALU_DIV_K code modifies the command argument k to
speed up the run-time division by doing kernel_k = reciprocal(user_k).
Bad news is that different user_k may result in same kernel_k, so we
can't get the original user_k back. Good news is that we don't have
to do it. What we need to is calculate a user2_k so, that
reciprocal(user2_k) == reciprocal(user_k) == kernel_k
i.e. if it's re-loaded back the compiled again value will be exactly
the same as it was. That said, the user2_k can be calculated like this
user2_k = reciprocal(kernel_k)
with an exception, that if kernel_k == 0, then user2_k == 1.
The optlen argument is treated like this -- when zero, kernel returns
the amount of sock_fprog elements in filter, otherwise it should be
large enough for the sock_fprog array.
changes since v1:
* Declared SO_GET_FILTER in all arch headers
* Added decode of vlan-tag codes
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-01 02:01:48 +00:00
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
sk-filter: Add ability to get socket filter program (v2)
The SO_ATTACH_FILTER option is set only. I propose to add the get
ability by using SO_ATTACH_FILTER in getsockopt. To be less
irritating to eyes the SO_GET_FILTER alias to it is declared. This
ability is required by checkpoint-restore project to be able to
save full state of a socket.
There are two issues with getting filter back.
First, kernel modifies the sock_filter->code on filter load, thus in
order to return the filter element back to user we have to decode it
into user-visible constants. Fortunately the modification in question
is interconvertible.
Second, the BPF_S_ALU_DIV_K code modifies the command argument k to
speed up the run-time division by doing kernel_k = reciprocal(user_k).
Bad news is that different user_k may result in same kernel_k, so we
can't get the original user_k back. Good news is that we don't have
to do it. What we need to is calculate a user2_k so, that
reciprocal(user2_k) == reciprocal(user_k) == kernel_k
i.e. if it's re-loaded back the compiled again value will be exactly
the same as it was. That said, the user2_k can be calculated like this
user2_k = reciprocal(kernel_k)
with an exception, that if kernel_k == 0, then user2_k == 1.
The optlen argument is treated like this -- when zero, kernel returns
the amount of sock_fprog elements in filter, otherwise it should be
large enough for the sock_fprog array.
changes since v1:
* Declared SO_GET_FILTER in all arch headers
* Added decode of vlan-tag codes
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-01 02:01:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-26 05:21:08 +00:00
|
|
|
|
2013-01-16 22:55:49 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-01-17 17:09:45 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-03-28 11:19:25 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-01 11:10:25 +08:00
|
|
|
|
2013-07-10 17:13:36 +03:00
|
|
|
|
2023-07-28 15:03:17 +00:00
|
|
|
|
2013-06-14 16:33:57 +03:00
|
|
|
|
net: Introduce preferred busy-polling
The existing busy-polling mode, enabled by the SO_BUSY_POLL socket
option or system-wide using the /proc/sys/net/core/busy_read knob, is
an opportunistic. That means that if the NAPI context is not
scheduled, it will poll it. If, after busy-polling, the budget is
exceeded the busy-polling logic will schedule the NAPI onto the
regular softirq handling.
One implication of the behavior above is that a busy/heavy loaded NAPI
context will never enter/allow for busy-polling. Some applications
prefer that most NAPI processing would be done by busy-polling.
This series adds a new socket option, SO_PREFER_BUSY_POLL, that works
in concert with the napi_defer_hard_irqs and gro_flush_timeout
knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were
introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral
feature"), and allows for a user to defer interrupts to be enabled and
instead schedule the NAPI context from a watchdog timer. When a user
enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled,
and the NAPI context is being processed by a softirq, the softirq NAPI
processing will exit early to allow the busy-polling to be performed.
If the application stops performing busy-polling via a system call,
the watchdog timer defined by gro_flush_timeout will timeout, and
regular softirq handling will resume.
In summary; Heavy traffic applications that prefer busy-polling over
softirq processing should use this option.
Example usage:
$ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs
$ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout
Note that the timeout should be larger than the userspace processing
window, otherwise the watchdog will timeout and fall back to regular
softirq processing.
Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/bpf/20201130185205.196029-2-bjorn.topel@gmail.com
2020-11-30 19:51:56 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-14 16:33:57 +03:00
|
|
|
|
|
|
|
|
|
2013-09-24 08:20:52 -07:00
|
|
|
|
2023-07-28 15:03:10 +00:00
|
|
|
|
2019-02-28 15:17:28 -08:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:10 +00:00
|
|
|
|
2019-02-28 15:17:28 -08:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:10 +00:00
|
|
|
|
|
|
|
|
|
2019-02-28 15:17:28 -08:00
|
|
|
|
2013-09-24 08:20:52 -07:00
|
|
|
|
|
|
|
|
|
net: introduce SO_INCOMING_CPU
Alternative to RPS/RFS is to use hardware support for multiple
queues.
Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.
Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.
We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.
After accept(), connect(), or even file descriptor passing around
processes, applications can use :
int cpu;
socklen_t len = sizeof(cpu);
getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);
And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-11 05:54:28 -08:00
|
|
|
|
2019-10-30 13:00:04 -07:00
|
|
|
|
net: introduce SO_INCOMING_CPU
Alternative to RPS/RFS is to use hardware support for multiple
queues.
Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.
Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.
We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.
After accept(), connect(), or even file descriptor passing around
processes, applications can use :
int cpu;
socklen_t len = sizeof(cpu);
getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);
And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-11 05:54:28 -08:00
|
|
|
|
|
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-02-14 18:17:51 +00:00
|
|
|
|
2017-03-24 10:08:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-04-05 19:00:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-03 16:29:40 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-07-03 15:43:00 -07:00
|
|
|
|
|
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
2022-05-13 11:55:44 -07:00
|
|
|
|
net: introduce SO_BINDTOIFINDEX sockopt
This introduces a new generic SOL_SOCKET-level socket option called
SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a
network interface index as argument, rather than the network interface
name.
User-space often refers to network-interfaces via their index, but has
to temporarily resolve it to a name for a call into SO_BINDTODEVICE.
This might pose problems when the network-device is renamed
asynchronously by other parts of the system. When this happens, the
SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong
device.
In most cases user-space only ever operates on devices which they
either manage themselves, or otherwise have a guarantee that the device
name will not change (e.g., devices that are UP cannot be renamed).
However, particularly in libraries this guarantee is non-obvious and it
would be nice if that race-condition would simply not exist. It would
make it easier for those libraries to operate even in situations where
the device-name might change under the hood.
A real use-case that we recently hit is trying to start the network
stack early in the initrd but make it survive into the real system.
Existing distributions rename network-interfaces during the transition
from initrd into the real system. This, obviously, cannot affect
devices that are up and running (unless you also consider moving them
between network-namespaces). However, the network manager now has to
make sure its management engine for dormant devices will not run in
parallel to these renames. Particularly, when you offload operations
like DHCP into separate processes, these might setup their sockets
early, and thus have to resolve the device-name possibly running into
this race-condition.
By avoiding a call to resolve the device-name, we no longer depend on
the name and can run network setup of dormant devices in parallel to
the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this
race.
Reviewed-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 14:42:14 +01:00
|
|
|
|
|
|
|
|
|
2021-06-23 15:56:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-08-04 10:55:56 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
2023-07-28 15:03:08 +00:00
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
|
|
|
|
|
2022-01-31 16:31:22 +03:00
|
|
|
|
2025-05-19 13:57:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:09 +00:00
|
|
|
|
|
|
|
|
|
2022-01-31 16:31:22 +03:00
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2015-03-23 18:04:13 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2022-09-01 17:28:02 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-22 12:27:49 -07:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.
When I ran the repro [0] and waited a few seconds, I observed two
LOCKDEP splats: a warning immediately followed by a null-ptr-deref. [1]
Reproduction Steps:
1) Mount CIFS
2) Add an iptables rule to drop incoming FIN packets for CIFS
3) Unmount CIFS
4) Unload the CIFS module
5) Remove the iptables rule
At step 3), the CIFS module calls sock_release() for the underlying
TCP socket, and it returns quickly. However, the socket remains in
FIN_WAIT_1 because incoming FIN packets are dropped.
At this point, the module's refcnt is 0 while the socket is still
alive, so the following rmmod command succeeds.
# ss -tan
State Recv-Q Send-Q Local Address:Port Peer Address:Port
FIN-WAIT-1 0 477 10.0.2.15:51062 10.0.0.137:445
# lsmod | grep cifs
cifs 1159168 0
This highlights a discrepancy between the lifetime of the CIFS module
and the underlying TCP socket. Even after CIFS calls sock_release()
and it returns, the TCP socket does not die immediately in order to
close the connection gracefully.
While this is generally fine, it causes an issue with LOCKDEP because
CIFS assigns a different lock class to the TCP socket's sk->sk_lock
using sock_lock_init_class_and_name().
Once an incoming packet is processed for the socket or a timer fires,
sk->sk_lock is acquired.
Then, LOCKDEP checks the lock context in check_wait_context(), where
hlock_class() is called to retrieve the lock class. However, since
the module has already been unloaded, hlock_class() logs a warning
and returns NULL, triggering the null-ptr-deref.
If LOCKDEP is enabled, we must ensure that a module calling
sock_lock_init_class_and_name() (CIFS, NFS, etc) cannot be unloaded
while such a socket is still alive to prevent this issue.
Let's hold the module reference in sock_lock_init_class_and_name()
and release it when the socket is freed in sk_prot_free().
Note that sock_lock_init() clears sk->sk_owner for svc_create_socket()
that calls sock_lock_init_class_and_name() for a listening socket,
which clones a socket by sk_clone_lock() without GFP_ZERO.
[0]:
CIFS_SERVER="10.0.0.137"
CIFS_PATH="//${CIFS_SERVER}/Users/Administrator/Desktop/CIFS_TEST"
DEV="enp0s3"
CRED="/root/WindowsCredential.txt"
MNT=$(mktemp -d /tmp/XXXXXX)
mount -t cifs ${CIFS_PATH} ${MNT} -o vers=3.0,credentials=${CRED},cache=none,echo_interval=1
iptables -A INPUT -s ${CIFS_SERVER} -j DROP
for i in $(seq 10);
do
umount ${MNT}
rmmod cifs
sleep 1
done
rm -r ${MNT}
iptables -D INPUT -s ${CIFS_SERVER} -j DROP
[1]:
DEBUG_LOCKS_WARN_ON(1)
WARNING: CPU: 10 PID: 0 at kernel/locking/lockdep.c:234 hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Not tainted 6.14.0 #36
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
...
Call Trace:
<IRQ>
__lock_acquire (kernel/locking/lockdep.c:4853 kernel/locking/lockdep.c:5178)
lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
_raw_spin_lock_nested (kernel/locking/spinlock.c:379)
tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)
...
BUG: kernel NULL pointer dereference, address: 00000000000000c4
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Tainted: G W 6.14.0 #36
Tainted: [W]=WARN
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:__lock_acquire (kernel/locking/lockdep.c:4852 kernel/locking/lockdep.c:5178)
Code: 15 41 09 c7 41 8b 44 24 20 25 ff 1f 00 00 41 09 c7 8b 84 24 a0 00 00 00 45 89 7c 24 20 41 89 44 24 24 e8 e1 bc ff ff 4c 89 e7 <44> 0f b6 b8 c4 00 00 00 e8 d1 bc ff ff 0f b6 80 c5 00 00 00 88 44
RSP: 0018:ffa0000000468a10 EFLAGS: 00010046
RAX: 0000000000000000 RBX: ff1100010091cc38 RCX: 0000000000000027
RDX: ff1100081f09ca48 RSI: 0000000000000001 RDI: ff1100010091cc88
RBP: ff1100010091c200 R08: ff1100083fe6e228 R09: 00000000ffffbfff
R10: ff1100081eca0000 R11: ff1100083fe10dc0 R12: ff1100010091cc88
R13: 0000000000000001 R14: 0000000000000000 R15: 00000000000424b1
FS: 0000000000000000(0000) GS:ff1100081f080000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c4 CR3: 0000000002c4a003 CR4: 0000000000771ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
<IRQ>
lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
_raw_spin_lock_nested (kernel/locking/spinlock.c:379)
tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)
ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1))
ip_local_deliver_finish (./include/linux/rcupdate.h:878 net/ipv4/ip_input.c:234)
ip_sublist_rcv_finish (net/ipv4/ip_input.c:576)
ip_list_rcv_finish (net/ipv4/ip_input.c:628)
ip_list_rcv (net/ipv4/ip_input.c:670)
__netif_receive_skb_list_core (net/core/dev.c:5939 net/core/dev.c:5986)
netif_receive_skb_list_internal (net/core/dev.c:6040 net/core/dev.c:6129)
napi_complete_done (./include/linux/list.h:37 ./include/net/gro.h:519 ./include/net/gro.h:514 net/core/dev.c:6496)
e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3815)
__napi_poll.constprop.0 (net/core/dev.c:7191)
net_rx_action (net/core/dev.c:7262 net/core/dev.c:7382)
handle_softirqs (kernel/softirq.c:561)
__irq_exit_rcu (kernel/softirq.c:596 kernel/softirq.c:435 kernel/softirq.c:662)
irq_exit_rcu (kernel/softirq.c:680)
common_interrupt (arch/x86/kernel/irq.c:280 (discriminator 14))
</IRQ>
<TASK>
asm_common_interrupt (./arch/x86/include/asm/idtentry.h:693)
RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:744)
Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d c3 2b 15 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90
RSP: 0018:ffa00000000ffee8 EFLAGS: 00000202
RAX: 000000000000640b RBX: ff1100010091c200 RCX: 0000000000061aa4
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff812f30c5
RBP: 000000000000000a R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000002 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
? do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118)
do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
cpu_startup_entry (kernel/sched/idle.c:422 (discriminator 1))
start_secondary (arch/x86/kernel/smpboot.c:315)
common_startup_64 (arch/x86/kernel/head_64.S:421)
</TASK>
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CR2: 00000000000000c4
Fixes: ed07536ed673 ("[PATCH] lockdep: annotate nfs/nfsd in-kernel sockets")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20250407163313.22682-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-04-07 09:33:11 -07:00
|
|
|
|
|
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-12-06 20:35:24 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
|
|
|
|
|
2009-07-15 23:13:10 +00:00
|
|
|
|
|
|
|
|
|
2024-08-22 13:57:34 +01:00
|
|
|
|
net: optimize INET input path further
Followup of commit b178bb3dfc30 (net: reorder struct sock fields)
Optimize INET input path a bit further, by :
1) moving sk_refcnt close to sk_lock.
This reduces number of dirtied cache lines by one on 64bit arches (and
64 bytes cache line size).
2) moving inet_daddr & inet_rcv_saddr at the beginning of sk
(same cache line than hash / family / bound_dev_if / nulls_node)
This reduces number of accessed cache lines in lookups by one, and dont
increase size of inet and timewait socks.
inet and tw sockets now share same place-holder for these fields.
Before patch :
offsetof(struct sock, sk_refcnt) = 0x10
offsetof(struct sock, sk_lock) = 0x40
offsetof(struct sock, sk_receive_queue) = 0x60
offsetof(struct inet_sock, inet_daddr) = 0x270
offsetof(struct inet_sock, inet_rcv_saddr) = 0x274
After patch :
offsetof(struct sock, sk_refcnt) = 0x44
offsetof(struct sock, sk_lock) = 0x48
offsetof(struct sock, sk_receive_queue) = 0x68
offsetof(struct inet_sock, inet_daddr) = 0x0
offsetof(struct inet_sock, inet_rcv_saddr) = 0x4
compute_score() (udp or tcp) now use a single cache line per ignored
item, instead of two.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-11-30 19:04:07 +00:00
|
|
|
|
2009-07-15 23:13:10 +00:00
|
|
|
|
2007-11-01 00:29:45 -07:00
|
|
|
|
|
|
|
|
|
2020-02-18 17:10:13 +00:00
|
|
|
|
2007-11-01 00:29:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-29 00:02:17 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: optimize INET input path further
Followup of commit b178bb3dfc30 (net: reorder struct sock fields)
Optimize INET input path a bit further, by :
1) moving sk_refcnt close to sk_lock.
This reduces number of dirtied cache lines by one on 64bit arches (and
64 bytes cache line size).
2) moving inet_daddr & inet_rcv_saddr at the beginning of sk
(same cache line than hash / family / bound_dev_if / nulls_node)
This reduces number of accessed cache lines in lookups by one, and dont
increase size of inet and timewait socks.
inet and tw sockets now share same place-holder for these fields.
Before patch :
offsetof(struct sock, sk_refcnt) = 0x10
offsetof(struct sock, sk_lock) = 0x40
offsetof(struct sock, sk_receive_queue) = 0x60
offsetof(struct inet_sock, inet_daddr) = 0x270
offsetof(struct inet_sock, inet_rcv_saddr) = 0x274
After patch :
offsetof(struct sock, sk_refcnt) = 0x44
offsetof(struct sock, sk_lock) = 0x48
offsetof(struct sock, sk_receive_queue) = 0x68
offsetof(struct inet_sock, inet_daddr) = 0x0
offsetof(struct inet_sock, inet_rcv_saddr) = 0x4
compute_score() (udp or tcp) now use a single cache line per ignored
item, instead of two.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-11-30 19:04:07 +00:00
|
|
|
|
|
|
|
|
|
2024-03-04 13:29:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: optimize INET input path further
Followup of commit b178bb3dfc30 (net: reorder struct sock fields)
Optimize INET input path a bit further, by :
1) moving sk_refcnt close to sk_lock.
This reduces number of dirtied cache lines by one on 64bit arches (and
64 bytes cache line size).
2) moving inet_daddr & inet_rcv_saddr at the beginning of sk
(same cache line than hash / family / bound_dev_if / nulls_node)
This reduces number of accessed cache lines in lookups by one, and dont
increase size of inet and timewait socks.
inet and tw sockets now share same place-holder for these fields.
Before patch :
offsetof(struct sock, sk_refcnt) = 0x10
offsetof(struct sock, sk_lock) = 0x40
offsetof(struct sock, sk_receive_queue) = 0x60
offsetof(struct inet_sock, inet_daddr) = 0x270
offsetof(struct inet_sock, inet_rcv_saddr) = 0x274
After patch :
offsetof(struct sock, sk_refcnt) = 0x44
offsetof(struct sock, sk_lock) = 0x48
offsetof(struct sock, sk_receive_queue) = 0x68
offsetof(struct inet_sock, inet_daddr) = 0x0
offsetof(struct inet_sock, inet_rcv_saddr) = 0x4
compute_score() (udp or tcp) now use a single cache line per ignored
item, instead of two.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-11-30 19:04:07 +00:00
|
|
|
|
2007-11-01 00:29:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
|
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-07-08 19:36:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
Patch series "add init_on_alloc/init_on_free boot options", v10.
Provide init_on_alloc and init_on_free boot options.
These are aimed at preventing possible information leaks and making the
control-flow bugs that depend on uninitialized values more deterministic.
Enabling either of the options guarantees that the memory returned by the
page allocator and SL[AU]B is initialized with zeroes. SLOB allocator
isn't supported at the moment, as its emulation of kmem caches complicates
handling of SLAB_TYPESAFE_BY_RCU caches correctly.
Enabling init_on_free also guarantees that pages and heap objects are
initialized right after they're freed, so it won't be possible to access
stale data by using a dangling pointer.
As suggested by Michal Hocko, right now we don't let the heap users to
disable initialization for certain allocations. There's not enough
evidence that doing so can speed up real-life cases, and introducing ways
to opt-out may result in things going out of control.
This patch (of 2):
The new options are needed to prevent possible information leaks and make
control-flow bugs that depend on uninitialized values more deterministic.
This is expected to be on-by-default on Android and Chrome OS. And it
gives the opportunity for anyone else to use it under distros too via the
boot args. (The init_on_free feature is regularly requested by folks
where memory forensics is included in their threat models.)
init_on_alloc=1 makes the kernel initialize newly allocated pages and heap
objects with zeroes. Initialization is done at allocation time at the
places where checks for __GFP_ZERO are performed.
init_on_free=1 makes the kernel initialize freed pages and heap objects
with zeroes upon their deletion. This helps to ensure sensitive data
doesn't leak via use-after-free accesses.
Both init_on_alloc=1 and init_on_free=1 guarantee that the allocator
returns zeroed memory. The two exceptions are slab caches with
constructors and SLAB_TYPESAFE_BY_RCU flag. Those are never
zero-initialized to preserve their semantics.
Both init_on_alloc and init_on_free default to zero, but those defaults
can be overridden with CONFIG_INIT_ON_ALLOC_DEFAULT_ON and
CONFIG_INIT_ON_FREE_DEFAULT_ON.
If either SLUB poisoning or page poisoning is enabled, those options take
precedence over init_on_alloc and init_on_free: initialization is only
applied to unpoisoned allocations.
Slowdown for the new features compared to init_on_free=0, init_on_alloc=0:
hackbench, init_on_free=1: +7.62% sys time (st.err 0.74%)
hackbench, init_on_alloc=1: +7.75% sys time (st.err 2.14%)
Linux build with -j12, init_on_free=1: +8.38% wall time (st.err 0.39%)
Linux build with -j12, init_on_free=1: +24.42% sys time (st.err 0.52%)
Linux build with -j12, init_on_alloc=1: -0.13% wall time (st.err 0.42%)
Linux build with -j12, init_on_alloc=1: +0.57% sys time (st.err 0.40%)
The slowdown for init_on_free=0, init_on_alloc=0 compared to the baseline
is within the standard error.
The new features are also going to pave the way for hardware memory
tagging (e.g. arm64's MTE), which will require both on_alloc and on_free
hooks to set the tags for heap objects. With MTE, tagging will have the
same cost as memory initialization.
Although init_on_free is rather costly, there are paranoid use-cases where
in-memory data lifetime is desired to be minimized. There are various
arguments for/against the realism of the associated threat models, but
given that we'll need the infrastructure for MTE anyway, and there are
people who want wipe-on-free behavior no matter what the performance cost,
it seems reasonable to include it in this series.
[glider@google.com: v8]
Link: http://lkml.kernel.org/r/20190626121943.131390-2-glider@google.com
[glider@google.com: v9]
Link: http://lkml.kernel.org/r/20190627130316.254309-2-glider@google.com
[glider@google.com: v10]
Link: http://lkml.kernel.org/r/20190628093131.199499-2-glider@google.com
Link: http://lkml.kernel.org/r/20190617151050.92663-2-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.cz> [page and dmapool parts
Acked-by: James Morris <jamorris@linux.microsoft.com>]
Cc: Christoph Lameter <cl@linux.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Sandeep Patil <sspatil@android.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jann Horn <jannh@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-11 20:59:19 -07:00
|
|
|
|
2016-08-23 11:39:29 -07:00
|
|
|
|
2010-12-16 14:26:56 -08:00
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
|
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
sock, cgroup: add sock->sk_cgroup
In cgroup v1, dealing with cgroup membership was difficult because the
number of membership associations was unbound. As a result, cgroup v1
grew several controllers whose primary purpose is either tagging
membership or pull in configuration knobs from other subsystems so
that cgroup membership test can be avoided.
net_cls and net_prio controllers are examples of the latter. They
allow configuring network-specific attributes from cgroup side so that
network subsystem can avoid testing cgroup membership; unfortunately,
these are not only cumbersome but also problematic.
Both net_cls and net_prio aren't properly hierarchical. Both inherit
configuration from the parent on creation but there's no interaction
afterwards. An ancestor doesn't restrict the behavior in its subtree
in anyway and configuration changes aren't propagated downwards.
Especially when combined with cgroup delegation, this is problematic
because delegatees can mess up whatever network configuration
implemented at the system level. net_prio would allow the delegatees
to set whatever priority value regardless of CAP_NET_ADMIN and net_cls
the same for classid.
While it is possible to solve these issues from controller side by
implementing hierarchical allowable ranges in both controllers, it
would involve quite a bit of complexity in the controllers and further
obfuscate network configuration as it becomes even more difficult to
tell what's actually being configured looking from the network side.
While not much can be done for v1 at this point, as membership
handling is sane on cgroup v2, it'd be better to make cgroup matching
behave like other network matches and classifiers than introducing
further complications.
In preparation, this patch updates sock->sk_cgrp_data handling so that
it points to the v2 cgroup that sock was created in until either
net_prio or net_cls is used. Once either of the two is used,
sock->sk_cgrp_data reverts to its previous role of carrying prioidx
and classid. This is to avoid adding yet another cgroup related field
to struct sock.
As the mode switching can happen at most once per boot, the switching
mechanism is aimed at lowering hot path overhead. It may leak a
finite, likely small, number of cgroup refs and report spurious
prioidx or classid on switching; however, dynamic updates of prioidx
and classid have always been racy and lossy - socks between creation
and fd installation are never updated, config changes don't update
existing sockets at all, and prioidx may index with dead and recycled
cgroup IDs. Non-critical inaccuracies from small race windows won't
make any noticeable difference.
This patch doesn't make use of the pointer yet. The following patch
will implement netfilter match for cgroup2 membership.
v2: Use sock_cgroup_data to avoid inflating struct sock w/ another
cgroup specific field.
v3: Add comments explaining why sock_data_prioidx() and
sock_data_classid() use different fallback values.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
CC: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-07 17:38:53 -05:00
|
|
|
|
2016-10-07 17:00:58 -07:00
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.
When I ran the repro [0] and waited a few seconds, I observed two
LOCKDEP splats: a warning immediately followed by a null-ptr-deref. [1]
Reproduction Steps:
1) Mount CIFS
2) Add an iptables rule to drop incoming FIN packets for CIFS
3) Unmount CIFS
4) Unload the CIFS module
5) Remove the iptables rule
At step 3), the CIFS module calls sock_release() for the underlying
TCP socket, and it returns quickly. However, the socket remains in
FIN_WAIT_1 because incoming FIN packets are dropped.
At this point, the module's refcnt is 0 while the socket is still
alive, so the following rmmod command succeeds.
# ss -tan
State Recv-Q Send-Q Local Address:Port Peer Address:Port
FIN-WAIT-1 0 477 10.0.2.15:51062 10.0.0.137:445
# lsmod | grep cifs
cifs 1159168 0
This highlights a discrepancy between the lifetime of the CIFS module
and the underlying TCP socket. Even after CIFS calls sock_release()
and it returns, the TCP socket does not die immediately in order to
close the connection gracefully.
While this is generally fine, it causes an issue with LOCKDEP because
CIFS assigns a different lock class to the TCP socket's sk->sk_lock
using sock_lock_init_class_and_name().
Once an incoming packet is processed for the socket or a timer fires,
sk->sk_lock is acquired.
Then, LOCKDEP checks the lock context in check_wait_context(), where
hlock_class() is called to retrieve the lock class. However, since
the module has already been unloaded, hlock_class() logs a warning
and returns NULL, triggering the null-ptr-deref.
If LOCKDEP is enabled, we must ensure that a module calling
sock_lock_init_class_and_name() (CIFS, NFS, etc) cannot be unloaded
while such a socket is still alive to prevent this issue.
Let's hold the module reference in sock_lock_init_class_and_name()
and release it when the socket is freed in sk_prot_free().
Note that sock_lock_init() clears sk->sk_owner for svc_create_socket()
that calls sock_lock_init_class_and_name() for a listening socket,
which clones a socket by sk_clone_lock() without GFP_ZERO.
[0]:
CIFS_SERVER="10.0.0.137"
CIFS_PATH="//${CIFS_SERVER}/Users/Administrator/Desktop/CIFS_TEST"
DEV="enp0s3"
CRED="/root/WindowsCredential.txt"
MNT=$(mktemp -d /tmp/XXXXXX)
mount -t cifs ${CIFS_PATH} ${MNT} -o vers=3.0,credentials=${CRED},cache=none,echo_interval=1
iptables -A INPUT -s ${CIFS_SERVER} -j DROP
for i in $(seq 10);
do
umount ${MNT}
rmmod cifs
sleep 1
done
rm -r ${MNT}
iptables -D INPUT -s ${CIFS_SERVER} -j DROP
[1]:
DEBUG_LOCKS_WARN_ON(1)
WARNING: CPU: 10 PID: 0 at kernel/locking/lockdep.c:234 hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Not tainted 6.14.0 #36
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
...
Call Trace:
<IRQ>
__lock_acquire (kernel/locking/lockdep.c:4853 kernel/locking/lockdep.c:5178)
lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
_raw_spin_lock_nested (kernel/locking/spinlock.c:379)
tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)
...
BUG: kernel NULL pointer dereference, address: 00000000000000c4
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Tainted: G W 6.14.0 #36
Tainted: [W]=WARN
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:__lock_acquire (kernel/locking/lockdep.c:4852 kernel/locking/lockdep.c:5178)
Code: 15 41 09 c7 41 8b 44 24 20 25 ff 1f 00 00 41 09 c7 8b 84 24 a0 00 00 00 45 89 7c 24 20 41 89 44 24 24 e8 e1 bc ff ff 4c 89 e7 <44> 0f b6 b8 c4 00 00 00 e8 d1 bc ff ff 0f b6 80 c5 00 00 00 88 44
RSP: 0018:ffa0000000468a10 EFLAGS: 00010046
RAX: 0000000000000000 RBX: ff1100010091cc38 RCX: 0000000000000027
RDX: ff1100081f09ca48 RSI: 0000000000000001 RDI: ff1100010091cc88
RBP: ff1100010091c200 R08: ff1100083fe6e228 R09: 00000000ffffbfff
R10: ff1100081eca0000 R11: ff1100083fe10dc0 R12: ff1100010091cc88
R13: 0000000000000001 R14: 0000000000000000 R15: 00000000000424b1
FS: 0000000000000000(0000) GS:ff1100081f080000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c4 CR3: 0000000002c4a003 CR4: 0000000000771ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
<IRQ>
lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
_raw_spin_lock_nested (kernel/locking/spinlock.c:379)
tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)
ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1))
ip_local_deliver_finish (./include/linux/rcupdate.h:878 net/ipv4/ip_input.c:234)
ip_sublist_rcv_finish (net/ipv4/ip_input.c:576)
ip_list_rcv_finish (net/ipv4/ip_input.c:628)
ip_list_rcv (net/ipv4/ip_input.c:670)
__netif_receive_skb_list_core (net/core/dev.c:5939 net/core/dev.c:5986)
netif_receive_skb_list_internal (net/core/dev.c:6040 net/core/dev.c:6129)
napi_complete_done (./include/linux/list.h:37 ./include/net/gro.h:519 ./include/net/gro.h:514 net/core/dev.c:6496)
e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3815)
__napi_poll.constprop.0 (net/core/dev.c:7191)
net_rx_action (net/core/dev.c:7262 net/core/dev.c:7382)
handle_softirqs (kernel/softirq.c:561)
__irq_exit_rcu (kernel/softirq.c:596 kernel/softirq.c:435 kernel/softirq.c:662)
irq_exit_rcu (kernel/softirq.c:680)
common_interrupt (arch/x86/kernel/irq.c:280 (discriminator 14))
</IRQ>
<TASK>
asm_common_interrupt (./arch/x86/include/asm/idtentry.h:693)
RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:744)
Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d c3 2b 15 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90
RSP: 0018:ffa00000000ffee8 EFLAGS: 00000202
RAX: 000000000000640b RBX: ff1100010091c200 RCX: 0000000000061aa4
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff812f30c5
RBP: 000000000000000a R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000002 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
? do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118)
do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
cpu_startup_entry (kernel/sched/idle.c:422 (discriminator 1))
start_secondary (arch/x86/kernel/smpboot.c:315)
common_startup_64 (arch/x86/kernel/head_64.S:421)
</TASK>
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CR2: 00000000000000c4
Fixes: ed07536ed673 ("[PATCH] lockdep: annotate nfs/nfsd in-kernel sockets")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20250407163313.22682-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-04-07 09:33:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-10-12 21:17:49 -07:00
|
|
|
|
2005-05-01 08:59:25 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-08 21:09:13 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-10-08 23:24:22 -07:00
|
|
|
|
2015-05-08 21:09:13 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-11-01 00:38:43 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-11-01 00:38:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-14 23:54:56 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-09 08:09:05 +00:00
|
|
|
|
2007-11-01 00:38:43 -07:00
|
|
|
|
2025-10-14 23:54:56 +00:00
|
|
|
|
2015-05-08 21:10:31 -05:00
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
2021-12-09 23:44:22 -08:00
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
2022-10-20 23:20:18 +00:00
|
|
|
|
2025-02-20 13:18:54 +00:00
|
|
|
|
2022-10-20 23:20:18 +00:00
|
|
|
|
|
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
|
|
|
|
|
2015-05-08 21:10:31 -05:00
|
|
|
|
2025-10-13 15:22:31 +00:00
|
|
|
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 00:12:34 -07:00
|
|
|
|
2016-10-07 17:00:58 -07:00
|
|
|
|
2016-09-19 14:44:38 -07:00
|
|
|
|
2015-12-07 17:38:52 -05:00
|
|
|
|
|
|
|
|
|
2020-06-22 23:26:04 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-09-27 15:23:38 -07:00
|
|
|
|
2007-11-01 00:36:26 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-01 08:52:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-01 08:52:12 -07:00
|
|
|
|
2025-02-20 13:18:54 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-02-22 17:04:49 -08:00
|
|
|
|
2017-06-30 13:08:00 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-10-17 21:21:51 -07:00
|
|
|
|
2011-08-01 16:19:00 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-11-28 12:04:18 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
bpf: Introduce bpf sk local storage
After allowing a bpf prog to
- directly read the skb->sk ptr
- get the fullsock bpf_sock by "bpf_sk_fullsock()"
- get the bpf_tcp_sock by "bpf_tcp_sock()"
- get the listener sock by "bpf_get_listener_sock()"
- avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock"
into different bpf running context.
this patch is another effort to make bpf's network programming
more intuitive to do (together with memory and performance benefit).
When bpf prog needs to store data for a sk, the current practice is to
define a map with the usual 4-tuples (src/dst ip/port) as the key.
If multiple bpf progs require to store different sk data, multiple maps
have to be defined. Hence, wasting memory to store the duplicated
keys (i.e. 4 tuples here) in each of the bpf map.
[ The smallest key could be the sk pointer itself which requires
some enhancement in the verifier and it is a separate topic. ]
Also, the bpf prog needs to clean up the elem when sk is freed.
Otherwise, the bpf map will become full and un-usable quickly.
The sk-free tracking currently could be done during sk state
transition (e.g. BPF_SOCK_OPS_STATE_CB).
The size of the map needs to be predefined which then usually ended-up
with an over-provisioned map in production. Even the map was re-sizable,
while the sk naturally come and go away already, this potential re-size
operation is arguably redundant if the data can be directly connected
to the sk itself instead of proxy-ing through a bpf map.
This patch introduces sk->sk_bpf_storage to provide local storage space
at sk for bpf prog to use. The space will be allocated when the first bpf
prog has created data for this particular sk.
The design optimizes the bpf prog's lookup (and then optionally followed by
an inline update). bpf_spin_lock should be used if the inline update needs
to be protected.
BPF_MAP_TYPE_SK_STORAGE:
-----------------------
To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in
this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can
be created to fit different bpf progs' needs. The map enforces
BTF to allow printing the sk-local-storage during a system-wise
sk dump (e.g. "ss -ta") in the future.
The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete
a "sk-local-storage" data from a particular sk.
Think of the map as a meta-data (or "type") of a "sk-local-storage". This
particular "type" of "sk-local-storage" data can then be stored in any sk.
The main purposes of this map are mostly:
1. Define the size of a "sk-local-storage" type.
2. Provide a similar syscall userspace API as the map (e.g. lookup/update,
map-id, map-btf...etc.)
3. Keep track of all sk's storages of this "type" and clean them up
when the map is freed.
sk->sk_bpf_storage:
------------------
The main lookup/update/delete is done on sk->sk_bpf_storage (which
is a "struct bpf_sk_storage"). When doing a lookup,
the "map" pointer is now used as the "key" to search on the
sk_storage->list. The "map" pointer is actually serving
as the "type" of the "sk-local-storage" that is being
requested.
To allow very fast lookup, it should be as fast as looking up an
array at a stable-offset. At the same time, it is not ideal to
set a hard limit on the number of sk-local-storage "type" that the
system can have. Hence, this patch takes a cache approach.
The last search result from sk_storage->list is cached in
sk_storage->cache[] which is a stable sized array. Each
"sk-local-storage" type has a stable offset to the cache[] array.
In the future, a map's flag could be introduced to do cache
opt-out/enforcement if it became necessary.
The cache size is 16 (i.e. 16 types of "sk-local-storage").
Programs can share map. On the program side, having a few bpf_progs
running in the networking hotpath is already a lot. The bpf_prog
should have already consolidated the existing sock-key-ed map usage
to minimize the map lookup penalty. 16 has enough runway to grow.
All sk-local-storage data will be removed from sk->sk_bpf_storage
during sk destruction.
bpf_sk_storage_get() and bpf_sk_storage_delete():
------------------------------------------------
Instead of using bpf_map_(lookup|update|delete)_elem(),
the bpf prog needs to use the new helper bpf_sk_storage_get() and
bpf_sk_storage_delete(). The verifier can then enforce the
ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to
"create" new elem if one does not exist in the sk. It is done by
the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be
provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE.
The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together,
it has eliminated the potential use cases for an equivalent
bpf_map_update_elem() API (for bpf_prog) in this patch.
Misc notes:
----------
1. map_get_next_key is not supported. From the userspace syscall
perspective, the map has the socket fd as the key while the map
can be shared by pinned-file or map-id.
Since btf is enforced, the existing "ss" could be enhanced to pretty
print the local-storage.
Supporting a kernel defined btf with 4 tuples as the return key could
be explored later also.
2. The sk->sk_lock cannot be acquired. Atomic operations is used instead.
e.g. cmpxchg is done on the sk->sk_bpf_storage ptr.
Please refer to the source code comments for the details in
synchronization cases and considerations.
3. The mem is charged to the sk->sk_omem_alloc as the sk filter does.
Benchmark:
---------
Here is the benchmark data collected by turning on
the "kernel.bpf_stats_enabled" sysctl.
Two bpf progs are tested:
One bpf prog with the usual bpf hashmap (max_entries = 8192) with the
sk ptr as the key. (verifier is modified to support sk ptr as the key
That should have shortened the key lookup time.)
Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE.
Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for
each egress skb and then bump the cnt. netperf is used to drive
data with 4096 connected UDP sockets.
BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run)
27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633
loaded_at 2019-04-15T13:46:39-0700 uid 0
xlated 344B jited 258B memlock 4096B map_ids 16
btf_id 5
BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run)
30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739
loaded_at 2019-04-15T13:47:54-0700 uid 0
xlated 168B jited 156B memlock 4096B map_ids 17
btf_id 6
Here is a high-level picture on how are the objects organized:
sk
┌──────┐
│ │
│ │
│ │
│*sk_bpf_storage─────▶ bpf_sk_storage
└──────┘ ┌───────┐
┌───────────┤ list │
│ │ │
│ │ │
│ │ │
│ └───────┘
│
│ elem
│ ┌────────┐
├─▶│ snode │
│ ├────────┤
│ │ data │ bpf_map
│ ├────────┤ ┌─────────┐
│ │map_node│◀─┬─────┤ list │
│ └────────┘ │ │ │
│ │ │ │
│ elem │ │ │
│ ┌────────┐ │ └─────────┘
└─▶│ snode │ │
├────────┤ │
bpf_map │ data │ │
┌─────────┐ ├────────┤ │
│ list ├───────▶│map_node│ │
│ │ └────────┘ │
│ │ │
│ │ elem │
└─────────┘ ┌────────┐ │
┌─▶│ snode │ │
│ ├────────┤ │
│ │ data │ │
│ ├────────┤ │
│ │map_node│◀─┘
│ └────────┘
│
│
│ ┌───────┐
sk └──────────│ list │
┌──────┐ │ │
│ │ │ │
│ │ │ │
│ │ └───────┘
│*sk_bpf_storage───────▶bpf_sk_storage
└──────┘
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-26 16:39:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-05-16 19:58:40 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-03-15 13:21:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
2010-06-13 03:30:14 +00:00
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
2025-02-20 13:18:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 00:33:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
2025-02-20 13:18:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:12 -07:00
|
|
|
|
|
|
|
|
|
2019-09-27 16:00:31 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-06-15 11:26:18 -04:00
|
|
|
|
|
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-18 04:47:55 -07:00
|
|
|
|
2015-06-15 11:26:18 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-30 13:08:00 +03:00
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-26 22:57:18 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-08 17:07:07 -05:00
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-08 17:07:07 -05:00
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
|
|
|
|
|
2011-11-08 17:07:07 -05:00
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2020-02-18 17:10:13 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
2014-07-30 20:34:12 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2020-02-18 17:10:13 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
net: Set sk_prot_creator when cloning sockets to the right proto
sk->sk_prot and sk->sk_prot_creator can differ when the app uses
IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one).
Which is why sk_prot_creator is there to make sure that sk_prot_free()
does the kmem_cache_free() on the right kmem_cache slab.
Now, if such a socket gets transformed back to a listening socket (using
connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through
sk_clone_lock() when a new connection comes in. But sk_prot_creator will
still point to the IPv6 kmem_cache (as everything got copied in
sk_clone_lock()). When freeing, we will thus put this
memory back into the IPv6 kmem_cache although it was allocated in the
IPv4 cache. I have seen memory corruption happening because of this.
With slub-debugging and MEMCG_KMEM enabled this gives the warning
"cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP"
A C-program to trigger this:
void main(void)
{
int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
int new_fd, newest_fd, client_fd;
struct sockaddr_in6 bind_addr;
struct sockaddr_in bind_addr4, client_addr1, client_addr2;
struct sockaddr unsp;
int val;
memset(&bind_addr, 0, sizeof(bind_addr));
bind_addr.sin6_family = AF_INET6;
bind_addr.sin6_port = ntohs(42424);
memset(&client_addr1, 0, sizeof(client_addr1));
client_addr1.sin_family = AF_INET;
client_addr1.sin_port = ntohs(42424);
client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1");
memset(&client_addr2, 0, sizeof(client_addr2));
client_addr2.sin_family = AF_INET;
client_addr2.sin_port = ntohs(42421);
client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1");
memset(&unsp, 0, sizeof(unsp));
unsp.sa_family = AF_UNSPEC;
bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr));
listen(fd, 5);
client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1));
new_fd = accept(fd, NULL, NULL);
close(fd);
val = AF_INET;
setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val));
connect(new_fd, &unsp, sizeof(unsp));
memset(&bind_addr4, 0, sizeof(bind_addr4));
bind_addr4.sin_family = AF_INET;
bind_addr4.sin_port = ntohs(42421);
bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4));
listen(new_fd, 5);
client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2));
newest_fd = accept(new_fd, NULL, NULL);
close(new_fd);
close(client_fd);
close(new_fd);
}
As far as I can see, this bug has been there since the beginning of the
git-days.
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-26 17:38:50 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
2021-11-15 19:16:56 +09:00
|
|
|
|
2021-12-09 23:44:22 -08:00
|
|
|
|
2021-11-15 19:16:56 +09:00
|
|
|
|
2022-10-20 23:20:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-02-20 13:18:54 +00:00
|
|
|
|
2022-10-20 23:20:18 +00:00
|
|
|
|
|
|
|
|
|
2021-11-15 19:16:56 +09:00
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2025-10-13 15:22:31 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-09-29 10:25:11 -07:00
|
|
|
|
2025-08-26 12:50:29 +00:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:18 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:18 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net, sk_msg: Clear sk_user_data pointer on clone if tagged
sk_user_data can hold a pointer to an object that is not intended to be
shared between the parent socket and the child that gets a pointer copy on
clone. This is the case when sk_user_data points at reference-counted
object, like struct sk_psock.
One way to resolve it is to tag the pointer with a no-copy flag by
repurposing its lowest bit. Based on the bit-flag value we clear the child
sk_user_data pointer after cloning the parent socket.
The no-copy flag is stored in the pointer itself as opposed to externally,
say in socket flags, to guarantee that the pointer and the flag are copied
from parent to child socket in an atomic fashion. Parent socket state is
subject to change while copying, we don't hold any locks at that time.
This approach relies on an assumption that sk_user_data holds a pointer to
an object aligned at least 2 bytes. A manual audit of existing users of
rcu_dereference_sk_user_data helper confirms our assumption.
Also, an RCU-protected sk_user_data is not likely to hold a pointer to a
char value or a pathological case of "struct { char c; }". To be safe, warn
when the flag-bit is set when setting sk_user_data to catch any future
misuses.
It is worth considering why clearing sk_user_data unconditionally is not an
option. There exist users, DRBD, NVMe, and Xen drivers being among them,
that rely on the pointer being copied when cloning the listening socket.
Potentially we could distinguish these users by checking if the listening
socket has been created in kernel-space via sock_create_kern, and hence has
sk_kern_sock flag set. However, this is not the case for NVMe and Xen
drivers, which create sockets without marking them as belonging to the
kernel.
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200218171023.844439-3-jakub@cloudflare.com
2020-02-18 17:10:14 +00:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2025-04-09 19:36:46 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2025-04-09 19:36:46 -07:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
2025-04-09 19:36:46 -07:00
|
|
|
|
|
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-04-07 16:42:18 +08:00
|
|
|
|
2021-01-27 07:27:31 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
|
|
|
|
|
2025-04-09 19:36:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
|
|
|
|
|
2025-04-09 19:36:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2025-10-23 23:16:53 +00:00
|
|
|
|
2005-08-09 20:10:12 -07:00
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
2022-05-13 11:33:57 -07:00
|
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:33:57 -07:00
|
|
|
|
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
|
|
|
|
|
|
|
|
|
2022-05-13 11:33:57 -07:00
|
|
|
|
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
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-13 11:33:57 -07:00
|
|
|
|
|
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
|
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
2015-05-26 08:55:28 -07:00
|
|
|
|
|
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-12 08:39:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 11:02:34 -08:00
|
|
|
|
2025-03-12 08:39:07 +00:00
|
|
|
|
|
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
2007-05-31 22:15:50 -07:00
|
|
|
|
2021-11-15 11:02:35 -08:00
|
|
|
|
|
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
2017-08-01 12:49:10 +03:00
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
[NET]: Add per-connection option to set max TSO frame size
Update: My mailer ate one of Jarek's feedback mails... Fixed the
parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the
whitespace issue due to a patch import botch. Changed the types from
u32 to unsigned int to be more consistent with other variables in the
area. Also brought the patch up to the latest net-2.6.26 tree.
Update: Made gso_max_size container 32 bits, not 16. Moved the
location of gso_max_size within netdev to be less hotpath. Made more
consistent names between the sock and netdev layers, and added a
define for the max GSO size.
Update: Respun for net-2.6.26 tree.
Update: changed max_gso_frame_size and sk_gso_max_size from signed to
unsigned - thanks Stephen!
This patch adds the ability for device drivers to control the size of
the TSO frames being sent to them, per TCP connection. By setting the
netdevice's gso_max_size value, the socket layer will set the GSO
frame size based on that value. This will propogate into the TCP
layer, and send TSO's of that size to the hardware.
This can be desirable to help tune the bursty nature of TSO on a
per-adapter basis, where one may have 1 GbE and 10 GbE devices
coexisting in a system, one running multiqueue and the other not, etc.
This can also be desirable for devices that cannot support full 64 KB
TSO's, but still want to benefit from some level of segmentation
offloading.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 03:43:19 -07:00
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
2021-11-19 07:43:32 -08:00
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
[NET]: Add per-connection option to set max TSO frame size
Update: My mailer ate one of Jarek's feedback mails... Fixed the
parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the
whitespace issue due to a patch import botch. Changed the types from
u32 to unsigned int to be more consistent with other variables in the
area. Also brought the patch up to the latest net-2.6.26 tree.
Update: Made gso_max_size container 32 bits, not 16. Moved the
location of gso_max_size within netdev to be less hotpath. Made more
consistent names between the sock and netdev layers, and added a
define for the max GSO size.
Update: Respun for net-2.6.26 tree.
Update: changed max_gso_frame_size and sk_gso_max_size from signed to
unsigned - thanks Stephen!
This patch adds the ability for device drivers to control the size of
the TSO frames being sent to them, per TCP connection. By setting the
netdevice's gso_max_size value, the socket layer will set the GSO
frame size based on that value. This will propogate into the TCP
layer, and send TSO's of that size to the hardware.
This can be desirable to help tune the bursty nature of TSO on a
per-adapter basis, where one may have 1 GbE and 10 GbE devices
coexisting in a system, one running multiqueue and the other not, etc.
This can also be desirable for devices that cannot support full 64 KB
TSO's, but still want to benefit from some level of segmentation
offloading.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 03:43:19 -07:00
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
2015-05-26 08:55:28 -07:00
|
|
|
|
2023-05-30 14:39:41 +03:00
|
|
|
|
2025-08-28 19:58:20 +00:00
|
|
|
|
2007-04-20 17:12:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-09-24 10:49:24 +00:00
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
2022-04-28 11:58:18 +01:00
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-09-24 10:49:24 +00:00
|
|
|
|
2022-04-28 11:58:18 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-28 11:58:18 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-09-24 10:49:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-30 13:08:00 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-09-24 10:49:24 +00:00
|
|
|
|
|
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
2009-09-24 10:49:24 +00:00
|
|
|
|
|
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
2017-06-30 13:08:00 +03:00
|
|
|
|
net: No more expensive sock_hold()/sock_put() on each tx
One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.
This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.
We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.
We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.
As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.
skb_set_owner_w() doesnt call sock_hold() anymore
sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.
Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.
Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 02:55:43 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 10:56:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-30 13:08:00 +03:00
|
|
|
|
2016-05-02 10:56:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
|
|
|
|
|
net: control skb->ooo_okay from skb_set_owner_w()
15 years after Tom Herbert added skb->ooo_okay, only TCP transport
benefits from it.
We can support other transports directly from skb_set_owner_w().
If no other TX packet for this socket is in a host queue (qdisc, NIC queue)
there is no risk of self-inflicted reordering, we can set skb->ooo_okay.
This allows netdev_pick_tx() to choose a TX queue based on XPS settings,
instead of reusing the queue chosen at the time the first packet was sent
for connected sockets.
Tested:
500 concurrent UDP_RR connected UDP flows, host with 32 TX queues,
512 cpus, XPS setup.
super_netperf 500 -t UDP_RR -H <host> -l 1000 -- -r 100,100 -Nn &
This patch saves between 10% and 20% of cycles, depending on how
process scheduler migrates threads among cpus.
Using following bpftrace script, we can see the effect on Qdisc/NIC tx queues
being better used (less cache line misses).
bpftrace -e '
k:__dev_queue_xmit { @start[cpu] = nsecs; }
kr:__dev_queue_xmit {
if (@start[cpu]) {
$delay = nsecs - @start[cpu];
delete(@start[cpu]);
@__dev_queue_xmit_ns = hist($delay);
}
}
END { clear(@start); }'
Before:
@__dev_queue_xmit_ns:
[128, 256) 6 | |
[256, 512) 116283 | |
[512, 1K) 1888205 |@@@@@@@@@@@ |
[1K, 2K) 8106167 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[2K, 4K) 8699293 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[4K, 8K) 2600676 |@@@@@@@@@@@@@@@ |
[8K, 16K) 721688 |@@@@ |
[16K, 32K) 122995 | |
[32K, 64K) 10639 | |
[64K, 128K) 119 | |
[128K, 256K) 1 | |
After:
@__dev_queue_xmit_ns:
[128, 256) 3 | |
[256, 512) 651112 |@@ |
[512, 1K) 8109938 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[1K, 2K) 16081031 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K) 2411692 |@@@@@@@ |
[4K, 8K) 98994 | |
[8K, 16K) 1536 | |
[16K, 32K) 587 | |
[32K, 64K) 2 | |
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-10-13 15:22:32 +00:00
|
|
|
|
|
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
|
|
|
|
|
2024-10-10 17:48:15 +00:00
|
|
|
|
|
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
2024-10-10 17:48:15 +00:00
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-22 13:57:34 +01:00
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
|
|
|
|
|
net: control skb->ooo_okay from skb_set_owner_w()
15 years after Tom Herbert added skb->ooo_okay, only TCP transport
benefits from it.
We can support other transports directly from skb_set_owner_w().
If no other TX packet for this socket is in a host queue (qdisc, NIC queue)
there is no risk of self-inflicted reordering, we can set skb->ooo_okay.
This allows netdev_pick_tx() to choose a TX queue based on XPS settings,
instead of reusing the queue chosen at the time the first packet was sent
for connected sockets.
Tested:
500 concurrent UDP_RR connected UDP flows, host with 32 TX queues,
512 cpus, XPS setup.
super_netperf 500 -t UDP_RR -H <host> -l 1000 -- -r 100,100 -Nn &
This patch saves between 10% and 20% of cycles, depending on how
process scheduler migrates threads among cpus.
Using following bpftrace script, we can see the effect on Qdisc/NIC tx queues
being better used (less cache line misses).
bpftrace -e '
k:__dev_queue_xmit { @start[cpu] = nsecs; }
kr:__dev_queue_xmit {
if (@start[cpu]) {
$delay = nsecs - @start[cpu];
delete(@start[cpu]);
@__dev_queue_xmit_ns = hist($delay);
}
}
END { clear(@start); }'
Before:
@__dev_queue_xmit_ns:
[128, 256) 6 | |
[256, 512) 116283 | |
[512, 1K) 1888205 |@@@@@@@@@@@ |
[1K, 2K) 8106167 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[2K, 4K) 8699293 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[4K, 8K) 2600676 |@@@@@@@@@@@@@@@ |
[8K, 16K) 721688 |@@@@ |
[16K, 32K) 122995 | |
[32K, 64K) 10639 | |
[64K, 128K) 119 | |
[128K, 256K) 1 | |
After:
@__dev_queue_xmit_ns:
[128, 256) 3 | |
[256, 512) 651112 |@@ |
[512, 1K) 8109938 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[1K, 2K) 16081031 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K) 2411692 |@@@@@@@ |
[4K, 8K) 98994 | |
[8K, 16K) 1536 | |
[16K, 32K) 587 | |
[32K, 64K) 2 | |
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-10-13 15:22:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-01 15:36:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-07 17:03:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-03 13:21:39 -07:00
|
|
|
|
2019-08-07 17:03:59 -07:00
|
|
|
|
2024-04-03 13:21:39 -07:00
|
|
|
|
2019-08-07 17:03:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-02 10:56:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-11 15:24:41 -07:00
|
|
|
|
2016-05-02 10:56:27 -07:00
|
|
|
|
2013-07-30 17:55:08 -07:00
|
|
|
|
|
|
|
|
|
2017-05-11 15:24:41 -07:00
|
|
|
|
2016-05-02 10:56:27 -07:00
|
|
|
|
|
|
|
|
|
2021-05-11 10:35:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-30 17:55:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-07-10 22:45:17 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-07-10 22:45:17 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-03-10 19:03:46 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-04 13:31:35 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-03-29 15:53:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
bpf: tcp: Support arbitrary SYN Cookie.
This patch adds a new kfunc available at TC hook to support arbitrary
SYN Cookie.
The basic usage is as follows:
struct bpf_tcp_req_attrs attrs = {
.mss = mss,
.wscale_ok = wscale_ok,
.rcv_wscale = rcv_wscale, /* Server's WScale < 15 */
.snd_wscale = snd_wscale, /* Client's WScale < 15 */
.tstamp_ok = tstamp_ok,
.rcv_tsval = tsval,
.rcv_tsecr = tsecr, /* Server's Initial TSval */
.usec_ts_ok = usec_ts_ok,
.sack_ok = sack_ok,
.ecn_ok = ecn_ok,
}
skc = bpf_skc_lookup_tcp(...);
sk = (struct sock *)bpf_skc_to_tcp_sock(skc);
bpf_sk_assign_tcp_reqsk(skb, sk, attrs, sizeof(attrs));
bpf_sk_release(skc);
bpf_sk_assign_tcp_reqsk() takes skb, a listener sk, and struct
bpf_tcp_req_attrs and allocates reqsk and configures it. Then,
bpf_sk_assign_tcp_reqsk() links reqsk with skb and the listener.
The notable thing here is that we do not hold refcnt for both reqsk
and listener. To differentiate that, we mark reqsk->syncookie, which
is only used in TX for now. So, if reqsk->syncookie is 1 in RX, it
means that the reqsk is allocated by kfunc.
When skb is freed, sock_pfree() checks if reqsk->syncookie is 1,
and in that case, we set NULL to reqsk->rsk_listener before calling
reqsk_free() as reqsk does not hold a refcnt of the listener.
When the TCP stack looks up a socket from the skb, we steal the
listener from the reqsk in skb_steal_sock() and create a full sk
in cookie_v[46]_check().
The refcnt of reqsk will finally be set to 1 in tcp_get_cookie_sock()
after creating a full sk.
Note that we can extend struct bpf_tcp_req_attrs in the future when
we add a new attribute that is determined in 3WHS.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240115205514.68364-6-kuniyu@amazon.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-01-15 12:55:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-03-29 15:53:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-07-08 14:57:47 -07:00
|
|
|
|
2005-10-07 07:46:04 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-08-03 16:29:37 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-14 10:49:00 +00:00
|
|
|
|
2017-08-03 16:29:37 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2005-10-07 07:46:04 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-12-14 10:49:00 +00:00
|
|
|
|
2022-08-23 10:46:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2025-02-28 18:01:31 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-10-14 17:02:37 -04:00
|
|
|
|
|
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
2020-08-06 23:18:13 -07:00
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-11-19 17:13:11 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-29 20:03:10 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-20 13:03:51 +00:00
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-09-01 17:27:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-09-01 17:27:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-20 13:03:51 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-02-04 16:55:54 -08:00
|
|
|
|
|
|
|
|
|
2013-08-08 14:38:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-01 17:27:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
2013-08-08 14:38:47 -07:00
|
|
|
|
2015-11-29 20:03:10 -08:00
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-09-17 04:49:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-02-04 16:55:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-10-20 06:54:41 +00:00
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
|
|
|
|
|
2016-04-02 23:08:09 -04:00
|
|
|
|
|
|
|
|
|
2024-10-01 05:57:14 -07:00
|
|
|
|
|
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
|
|
|
|
|
2022-01-31 15:33:57 -08:00
|
|
|
|
|
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-02-02 07:34:46 -08:00
|
|
|
|
2024-01-04 09:57:44 +01:00
|
|
|
|
2016-04-02 23:08:09 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-07-03 15:42:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-01 05:57:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-07-11 16:51:26 -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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-08 00:48:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-08 14:56:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
2015-10-08 14:56:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-20 06:54:41 +00:00
|
|
|
|
2016-04-02 23:08:06 -04:00
|
|
|
|
|
|
|
|
|
2015-10-08 14:56:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-07 13:29:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-01 13:32:47 +00:00
|
|
|
|
|
|
|
|
|
2017-06-07 13:29:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-09 12:55:53 -07:00
|
|
|
|
|
|
|
|
|
2017-06-07 13:29:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-14 16:22:21 -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
|
|
|
|
2013-10-17 16:27:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-08 04:00:00 -07:00
|
|
|
|
2013-10-17 16:27:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-27 20:49:34 -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
|
|
|
|
|
|
|
|
|
2016-03-17 14:19:26 -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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-17 16:27:07 -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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-27 20:49:34 -07:00
|
|
|
|
2019-06-14 16:22:21 -07:00
|
|
|
|
|
|
|
|
|
2015-11-06 16:28:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-27 20:49:34 -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
|
|
|
|
2014-08-27 20:49:34 -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
|
|
|
|
|
|
|
|
|
2014-08-27 20:49:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-17 16:27:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +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
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-23 09:27:15 +00:00
|
|
|
|
2010-09-08 03:48:48 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-01 23:24:26 -07:00
|
|
|
|
2010-09-08 03:48:48 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-29 14:16:52 -07:00
|
|
|
|
net: call cond_resched() less often in __release_sock()
While stress testing TCP I had unexpected retransmits and sack packets
when a single cpu receives data from multiple high-throughput flows.
super_netperf 4 -H srv -T,10 -l 3000 &
Tcpdump extract:
00:00:00.000007 IP6 clnt > srv: Flags [.], seq 26062848:26124288, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26124288:26185728, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26185728:26243072, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26243072:26304512, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26304512:26365952, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000007 IP6 clnt > srv: Flags [P.], seq 26365952:26423296, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26423296:26484736, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26484736:26546176, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26546176:26603520, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 57344
00:00:00.003932 IP6 clnt > srv: Flags [P.], seq 26603520:26619904, ack 1, win 66, options [nop,nop,TS val 651464844 ecr 3100753141], length 16384
00:00:00.006602 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651471419 ecr 3100759716], length 4096
00:00:00.013000 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651484421 ecr 3100772718], length 4096
00:00:00.000416 IP6 srv > clnt: Flags [.], ack 26619904, win 1393, options [nop,nop,TS val 3100773185 ecr 651484421,nop,nop,sack 1 {24862720:24866816}], length 0
After analysis, it appears this is because of the cond_resched()
call from __release_sock().
When current thread is yielding, while still holding the TCP socket lock,
it might regain the cpu after a very long time.
Other peer TLP/RTO is firing (multiple times) and packets are retransmit,
while the initial copy is waiting in the socket backlog or receive queue.
In this patch, I call cond_resched() only once every 16 packets.
Modern TCP stack now spends less time per packet in the backlog,
especially because ACK are no longer sent (commit 133c4c0d3717
"tcp: defer regular ACK while processing socket backlog")
Before:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19046186 0.0
TcpRetransSegs 1471 0.0
TcpExtTCPTimeouts 1397 0.0
TcpExtTCPLossProbes 1356 0.0
TcpExtTCPDSACKRecv 1352 0.0
TcpExtTCPSpuriousRTOs 114 0.0
TcpExtTCPDSACKRecvSegs 1352 0.0
After:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19218936 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250903174811.1930820-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-09-03 17:48:10 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-29 14:16:52 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-29 14:16:52 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: call cond_resched() less often in __release_sock()
While stress testing TCP I had unexpected retransmits and sack packets
when a single cpu receives data from multiple high-throughput flows.
super_netperf 4 -H srv -T,10 -l 3000 &
Tcpdump extract:
00:00:00.000007 IP6 clnt > srv: Flags [.], seq 26062848:26124288, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26124288:26185728, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26185728:26243072, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26243072:26304512, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26304512:26365952, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000007 IP6 clnt > srv: Flags [P.], seq 26365952:26423296, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26423296:26484736, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26484736:26546176, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26546176:26603520, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 57344
00:00:00.003932 IP6 clnt > srv: Flags [P.], seq 26603520:26619904, ack 1, win 66, options [nop,nop,TS val 651464844 ecr 3100753141], length 16384
00:00:00.006602 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651471419 ecr 3100759716], length 4096
00:00:00.013000 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651484421 ecr 3100772718], length 4096
00:00:00.000416 IP6 srv > clnt: Flags [.], ack 26619904, win 1393, options [nop,nop,TS val 3100773185 ecr 651484421,nop,nop,sack 1 {24862720:24866816}], length 0
After analysis, it appears this is because of the cond_resched()
call from __release_sock().
When current thread is yielding, while still holding the TCP socket lock,
it might regain the cpu after a very long time.
Other peer TLP/RTO is firing (multiple times) and packets are retransmit,
while the initial copy is waiting in the socket backlog or receive queue.
In this patch, I call cond_resched() only once every 16 packets.
Modern TCP stack now spends less time per packet in the backlog,
especially because ACK are no longer sent (commit 133c4c0d3717
"tcp: defer regular ACK while processing socket backlog")
Before:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19046186 0.0
TcpRetransSegs 1471 0.0
TcpExtTCPTimeouts 1397 0.0
TcpExtTCPLossProbes 1356 0.0
TcpExtTCPDSACKRecv 1352 0.0
TcpExtTCPSpuriousRTOs 114 0.0
TcpExtTCPDSACKRecvSegs 1352 0.0
After:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19218936 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250903174811.1930820-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-09-03 17:48:10 +00:00
|
|
|
|
2016-04-29 14:16:52 -07:00
|
|
|
|
2012-04-30 16:07:09 +00:00
|
|
|
|
2022-06-08 09:04:31 -07:00
|
|
|
|
2018-07-29 20:42:53 -07:00
|
|
|
|
2008-10-07 14:18:42 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
net: call cond_resched() less often in __release_sock()
While stress testing TCP I had unexpected retransmits and sack packets
when a single cpu receives data from multiple high-throughput flows.
super_netperf 4 -H srv -T,10 -l 3000 &
Tcpdump extract:
00:00:00.000007 IP6 clnt > srv: Flags [.], seq 26062848:26124288, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26124288:26185728, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26185728:26243072, ack 1, win 66, options [nop,nop,TS val 651460834 ecr 3100749131], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26243072:26304512, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26304512:26365952, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 61440
00:00:00.000007 IP6 clnt > srv: Flags [P.], seq 26365952:26423296, ack 1, win 66, options [nop,nop,TS val 651460844 ecr 3100749141], length 57344
00:00:00.000006 IP6 clnt > srv: Flags [.], seq 26423296:26484736, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [.], seq 26484736:26546176, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 61440
00:00:00.000005 IP6 clnt > srv: Flags [P.], seq 26546176:26603520, ack 1, win 66, options [nop,nop,TS val 651460853 ecr 3100749150], length 57344
00:00:00.003932 IP6 clnt > srv: Flags [P.], seq 26603520:26619904, ack 1, win 66, options [nop,nop,TS val 651464844 ecr 3100753141], length 16384
00:00:00.006602 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651471419 ecr 3100759716], length 4096
00:00:00.013000 IP6 clnt > srv: Flags [.], seq 24862720:24866816, ack 1, win 66, options [nop,nop,TS val 651484421 ecr 3100772718], length 4096
00:00:00.000416 IP6 srv > clnt: Flags [.], ack 26619904, win 1393, options [nop,nop,TS val 3100773185 ecr 651484421,nop,nop,sack 1 {24862720:24866816}], length 0
After analysis, it appears this is because of the cond_resched()
call from __release_sock().
When current thread is yielding, while still holding the TCP socket lock,
it might regain the cpu after a very long time.
Other peer TLP/RTO is firing (multiple times) and packets are retransmit,
while the initial copy is waiting in the socket backlog or receive queue.
In this patch, I call cond_resched() only once every 16 packets.
Modern TCP stack now spends less time per packet in the backlog,
especially because ACK are no longer sent (commit 133c4c0d3717
"tcp: defer regular ACK while processing socket backlog")
Before:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19046186 0.0
TcpRetransSegs 1471 0.0
TcpExtTCPTimeouts 1397 0.0
TcpExtTCPLossProbes 1356 0.0
TcpExtTCPDSACKRecv 1352 0.0
TcpExtTCPSpuriousRTOs 114 0.0
TcpExtTCPDSACKRecvSegs 1352 0.0
After:
clnt:/# nstat -n;sleep 10;nstat|egrep "TcpOutSegs|TcpRetransSegs|TCPFastRetrans|TCPTimeouts|Probes|TCPSpuriousRTOs|DSACK"
TcpOutSegs 19218936 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250903174811.1930820-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-09-03 17:48:10 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-29 14:16:52 -07:00
|
|
|
|
|
|
|
|
|
2010-03-04 18:01:40 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2016-04-29 14:16:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-11 17:05:30 +00:00
|
|
|
|
|
|
|
|
|
2023-09-13 12:58:35 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-29 14:16:53 -07:00
|
|
|
|
|
|
|
|
|
2022-07-05 16:59:26 -07:00
|
|
|
|
2016-04-29 14:16:53 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2005-05-01 08:59:25 -07:00
|
|
|
|
|
|
|
|
|
2015-07-24 18:19:25 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-24 18:19:25 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-11-11 10:20:50 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2016-11-11 10:20:50 -08:00
|
|
|
|
2015-11-29 20:03:10 -08:00
|
|
|
|
2016-11-11 10:20:50 -08:00
|
|
|
|
2015-11-29 20:03:10 -08:00
|
|
|
|
2016-11-11 10:20:50 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2023-10-19 20:00:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
2022-06-10 20:30:16 -07:00
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-19 20:00:24 +08:00
|
|
|
|
2025-08-15 20:16:15 +00:00
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
|
|
|
|
|
2025-05-27 11:04:19 +08:00
|
|
|
|
2023-10-19 20:00:24 +08:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2023-10-19 20:00:25 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2017-11-07 00:29:27 -08:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2017-11-07 00:29:27 -08:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2017-11-07 00:29:27 -08:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2017-11-07 00:29:27 -08:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2017-11-07 00:29:27 -08:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2019-02-12 12:26:27 -08:00
|
|
|
|
2008-11-25 21:16:35 -08:00
|
|
|
|
2023-10-19 20:00:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-25 21:16:35 -08:00
|
|
|
|
2023-10-19 20:00:25 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-08-17 12:40:03 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2021-08-17 12:40:03 -07:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:12 +00:00
|
|
|
|
2011-06-17 12:00:03 +00:00
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2025-08-15 20:16:13 +00:00
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-31 13:52:09 +00:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
2023-08-31 13:52:09 +00:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2025-08-15 20:16:15 +00:00
|
|
|
|
2025-08-15 20:16:16 +00:00
|
|
|
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 15:21:14 -08:00
|
|
|
|
net: Allow opt-out from global protocol memory accounting.
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
2025-10-14 23:54:55 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-16 17:12:22 +08:00
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-06-08 23:34:07 -07:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-06-08 23:34:07 -07:00
|
|
|
|
2023-08-31 13:52:09 +00:00
|
|
|
|
2016-10-21 13:55:45 +02:00
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
|
|
|
|
|
2025-11-21 18:02:00 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
|
|
|
|
|
2023-07-28 15:03:16 +00:00
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-31 00:11:19 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-11-03 16:26:10 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2025-11-03 16:26:11 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2024-05-09 09:20:08 -06:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2018-02-12 20:00:20 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-07-28 16:22:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2020-06-09 16:11:29 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-04 12:36:04 +01:00
|
|
|
|
2020-06-09 16:11:29 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-26 13:55:39 +08:00
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-26 13:55:39 +08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
2024-03-28 14:40:32 +00:00
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2020-01-20 10:29:17 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
2023-01-19 16:45:16 -08:00
|
|
|
|
|
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
2015-11-26 13:55:39 +08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
|
|
|
|
|
2024-03-28 14:40:32 +00:00
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-28 11:58:17 +01:00
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
2015-11-26 13:55:39 +08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2024-03-28 14:40:32 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-04-29 11:01:49 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2022-04-28 11:58:19 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
2022-04-28 11:58:19 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-17 13:37:12 +00:00
|
|
|
|
2022-04-28 11:58:19 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-28 14:40:32 +00:00
|
|
|
|
2022-04-28 11:58:19 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-09 18:00:01 +02:00
|
|
|
|
2007-11-26 20:10:50 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-05 10:17:26 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-09-24 08:30:01 +08:00
|
|
|
|
|
|
|
|
|
2025-04-05 10:17:26 +02:00
|
|
|
|
2020-09-24 08:30:01 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-02-04 17:39:20 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net/socket: use per af lockdep classes for sk queues
Currently the sock queue's spin locks get their lockdep
classes by the default init_spin_lock() initializer:
all socket families get - usually, see below - a single
class for rx, another specific class for tx, etc.
This can lead to false positive lockdep splat, as
reported by Andrey.
Moreover there are two separate initialization points
for the sock queues, one in sk_clone_lock() and one
in sock_init_data(), so that e.g. the rx queue lock
can get one of two possible, different classes, depending
on the socket being cloned or not.
This change tries to address the above, setting explicitly
a per address family lockdep class for each queue's
spinlock. Also, move the duplicated initialization code to a
single location.
v1 -> v2:
- renamed the init helper
rfc -> v1:
- no changes, tested with several different workload
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 13:54:08 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-10-16 17:29:36 -07:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2022-08-23 10:46:44 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: Introduce sk_use_task_frag in struct sock.
Sockets that can be used while recursing into memory reclaim, like
those used by network block devices and file systems, mustn't use
current->task_frag: if the current process is already using it, then
the inner memory reclaim call would corrupt the task_frag structure.
To avoid this, sk_page_frag() uses ->sk_allocation to detect sockets
that mustn't use current->task_frag, assuming that those used during
memory reclaim had their allocation constraints reflected in
->sk_allocation.
This unfortunately doesn't cover all cases: in an attempt to remove all
usage of GFP_NOFS and GFP_NOIO, sunrpc stopped setting these flags in
->sk_allocation, and used memalloc_nofs critical sections instead.
This breaks the sk_page_frag() heuristic since the allocation
constraints are now stored in current->flags, which sk_page_frag()
can't read without risking triggering a cache miss and slowing down
TCP's fast path.
This patch creates a new field in struct sock, named sk_use_task_frag,
which sockets with memory reclaim constraints can set to false if they
can't safely use current->task_frag. In such cases, sk_page_frag() now
always returns the socket's page_frag (->sk_frag). The first user is
sunrpc, which needs to avoid using current->task_frag but can keep
->sk_allocation set to GFP_KERNEL otherwise.
Eventually, it might be possible to simplify sk_page_frag() by only
testing ->sk_use_task_frag and avoid relying on the ->sk_allocation
heuristic entirely (assuming other sockets will set ->sk_use_task_frag
according to their constraints in the future).
The new ->sk_use_task_frag field is placed in a hole in struct sock and
belongs to a cache line shared with ->sk_shutdown. Therefore it should
be hot and shouldn't have negative performance impacts on TCP's fast
path (sk_shutdown is tested just before the while() loop in
tcp_sendmsg_locked()).
Link: https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-12-16 07:45:26 -05:00
|
|
|
|
2008-06-17 22:41:38 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-10 20:10:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2019-07-05 20:14:16 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: core: Add a UID field to struct sock.
Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.
Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().
Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:
1. Whenever sk_socket is non-null: sk_uid is the same as the UID
in sk_socket, i.e., matches the return value of sock_i_uid.
Specifically, the UID is set when userspace calls socket(),
fchown(), or accept().
2. When sk_socket is NULL, sk_uid is defined as follows:
- For a socket that no longer has a sk_socket because
userspace has called close(): the previous UID.
- For a cloned socket (e.g., an incoming connection that is
established but on which userspace has not yet called
accept): the UID of the socket it was cloned from.
- For a socket that has never had an sk_socket: UID 0 inside
the user namespace corresponding to the network namespace
the socket belongs to.
Kernel sockets created by sock_create_kern are a special case
of #1 and sk_uid is the user that created them. For kernel
sockets created at network namespace creation time, such as the
per-processor ICMP and TCP sockets, this is the user that created
the network namespace.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04 02:23:41 +09:00
|
|
|
|
2019-02-22 17:08:22 +08:00
|
|
|
|
net: core: Add a UID field to struct sock.
Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.
Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().
Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:
1. Whenever sk_socket is non-null: sk_uid is the same as the UID
in sk_socket, i.e., matches the return value of sock_i_uid.
Specifically, the UID is set when userspace calls socket(),
fchown(), or accept().
2. When sk_socket is NULL, sk_uid is defined as follows:
- For a socket that no longer has a sk_socket because
userspace has called close(): the previous UID.
- For a cloned socket (e.g., an incoming connection that is
established but on which userspace has not yet called
accept): the UID of the socket it was cloned from.
- For a socket that has never had an sk_socket: UID 0 inside
the user namespace corresponding to the network namespace
the socket belongs to.
Kernel sockets created by sock_create_kern are a special case
of #1 and sk_uid is the user that created them. For kernel
sockets created at network namespace creation time, such as the
per-processor ICMP and TCP sockets, this is the user that created
the network namespace.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-04 02:23:41 +09:00
|
|
|
|
2023-02-04 17:39:20 +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
|
|
|
|
|
|
|
|
|
2012-02-21 07:31:34 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-13 03:30:14 +00:00
|
|
|
|
|
|
|
|
|
2021-09-29 15:57:50 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-30 14:03:06 +02:00
|
|
|
|
2018-12-27 18:55:09 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-03 16:29:39 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-08-01 11:10:25 +08:00
|
|
|
|
2013-06-10 11:39:50 +03:00
|
|
|
|
2022-08-23 10:46:52 -07:00
|
|
|
|
2013-06-10 11:39:50 +03:00
|
|
|
|
|
|
|
|
|
net: extend sk_pacing_rate to unsigned long
sk_pacing_rate has beed introduced as a u32 field in 2013,
effectively limiting per flow pacing to 34Gbit.
We believe it is time to allow TCP to pace high speed flows
on 64bit hosts, as we now can reach 100Gbit on one TCP flow.
This patch adds no cost for 32bit kernels.
The tcpi_pacing_rate and tcpi_max_pacing_rate were already
exported as 64bit, so iproute2/ss command require no changes.
Unfortunately the SO_MAX_PACING_RATE socket option will stay
32bit and we will need to add a new option to let applications
control high pacing rates.
State Recv-Q Send-Q Local Address:Port Peer Address:Port
ESTAB 0 1787144 10.246.9.76:49992 10.246.9.77:36741
timer:(on,003ms,0) ino:91863 sk:2 <->
skmem:(r0,rb540000,t66440,tb2363904,f605944,w1822984,o0,bl0,d0)
ts sack bbr wscale:8,8 rto:201 rtt:0.057/0.006 mss:1448
rcvmss:536 advmss:1448
cwnd:138 ssthresh:178 bytes_acked:256699822585 segs_out:177279177
segs_in:3916318 data_segs_out:177279175
bbr:(bw:31276.8Mbps,mrtt:0,pacing_gain:1.25,cwnd_gain:2)
send 28045.5Mbps lastrcv:73333
pacing_rate 38705.0Mbps delivery_rate 22997.6Mbps
busy:73333ms unacked:135 retrans:0/157 rcv_space:14480
notsent:2085120 minrtt:0.013
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15 09:37:53 -07:00
|
|
|
|
|
|
|
|
|
2019-12-16 18:51:03 -08:00
|
|
|
|
2015-10-08 19:33:21 -07:00
|
|
|
|
2018-06-29 21:26:57 -07:00
|
|
|
|
|
|
|
|
|
2009-07-15 23:13:10 +00:00
|
|
|
|
|
|
|
|
|
2020-04-21 19:04:05 +02:00
|
|
|
|
2009-07-15 23:13:10 +00:00
|
|
|
|
|
|
|
|
|
2017-06-30 13:08:01 +03:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2023-02-04 17:39:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-05-27 11:30:05 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-02-23 09:27:15 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: core: Correct the sock::sk_lock.owned lockdep annotations
lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the
sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It
is just lockdep wise equivalent. In fact it's an open coded trivial mutex
implementation with some interesting features.
sock::sk_lock.slock is a regular spinlock protecting the 'mutex'
representation sock::sk_lock.owned which is a plain boolean. If 'owned' is
true, then some other task holds the 'mutex', otherwise it is uncontended.
As this locking construct is obviously endangered by lock ordering issues as
any other locking primitive it got lockdep annotated via a dedicated
dependency map sock::sk_lock.dep_map which has to be updated at the lock
and unlock sites.
lock_sock_nested() is a straight forward 'mutex' lock operation:
might_sleep();
spin_lock_bh(sock::sk_lock.slock)
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
The lockdep annotation for sock::sk_lock.owned is for unknown reasons
_after_ the lock has been acquired, i.e. after the code block above and
after releasing sock::sk_lock.slock, but inside the bottom halves disabled
region:
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
The placement after the unlock is obvious because otherwise the
mutex_acquire() would nest into the spin lock held region.
But that's from the lockdep perspective still the wrong place:
1) The mutex_acquire() is issued _after_ the successful acquisition which
is pointless because in a dead lock scenario this point is never
reached which means that if the deadlock is the first instance of
exposing the wrong lock order lockdep does not have a chance to detect
it.
2) It only works because lockdep is rather lax on the context from which
the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves
and therefore non-preemptible region is obviously invalid, except for a
trylock which is clearly not the case here.
This 'works' stops working on RT enabled kernels where the bottom halves
serialization is done via a local lock, which exposes this misplacement
because the 'mutex' and the local lock nest the wrong way around and
lockdep complains rightfully about a lock inversion.
The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH]
lockdep: annotate sk_locks") which introduced this.
Fix it by moving the mutex_acquire() in front of the actual lock
acquisition, which is what the regular mutex_lock() operation does as well.
lock_sock_fast() is not that straight forward. It looks at the first glance
like a convoluted trylock operation:
spin_lock_bh(sock::sk_lock.slock)
if (!sock::sk_lock.owned)
return false;
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
return true;
But that's not the case: lock_sock_fast() is an interesting optimization
for short critical sections which can run with bottom halves disabled and
sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in
the non contended case by preventing other lockers to acquire
sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which
in turn avoids the overhead of doing the heavy processing in release_sock()
including waking up wait queue waiters.
In the contended case, i.e. when sock::sk_lock.owned == true the behavior
is the same as lock_sock_nested().
Semantically this shortcut means, that the task acquired the 'mutex' even
if it does not touch the sock::sk_lock.owned field in the non-contended
case. Not telling lockdep about this shortcut acquisition is hiding
potential lock ordering violations in the fast path.
As a consequence the same reasoning as for the above lock_sock_nested()
case vs. the placement of the lockdep annotation applies.
The current placement of the lockdep annotation was just copied from
the original lock_sock(), now renamed to lock_sock_nested(),
implementation.
Fix this by moving the mutex_acquire() in front of the actual lock
acquisition and adding the corresponding mutex_release() into
unlock_sock_fast(). Also document the fast path return case with a comment.
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-18 14:42:35 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2026-02-26 02:12:15 +00:00
|
|
|
|
|
|
|
|
|
2026-02-28 19:13:18 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-26 02:12:15 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2026-02-23 09:27:15 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-09-12 10:44:19 +02:00
|
|
|
|
net: core: Correct the sock::sk_lock.owned lockdep annotations
lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the
sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It
is just lockdep wise equivalent. In fact it's an open coded trivial mutex
implementation with some interesting features.
sock::sk_lock.slock is a regular spinlock protecting the 'mutex'
representation sock::sk_lock.owned which is a plain boolean. If 'owned' is
true, then some other task holds the 'mutex', otherwise it is uncontended.
As this locking construct is obviously endangered by lock ordering issues as
any other locking primitive it got lockdep annotated via a dedicated
dependency map sock::sk_lock.dep_map which has to be updated at the lock
and unlock sites.
lock_sock_nested() is a straight forward 'mutex' lock operation:
might_sleep();
spin_lock_bh(sock::sk_lock.slock)
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
The lockdep annotation for sock::sk_lock.owned is for unknown reasons
_after_ the lock has been acquired, i.e. after the code block above and
after releasing sock::sk_lock.slock, but inside the bottom halves disabled
region:
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
The placement after the unlock is obvious because otherwise the
mutex_acquire() would nest into the spin lock held region.
But that's from the lockdep perspective still the wrong place:
1) The mutex_acquire() is issued _after_ the successful acquisition which
is pointless because in a dead lock scenario this point is never
reached which means that if the deadlock is the first instance of
exposing the wrong lock order lockdep does not have a chance to detect
it.
2) It only works because lockdep is rather lax on the context from which
the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves
and therefore non-preemptible region is obviously invalid, except for a
trylock which is clearly not the case here.
This 'works' stops working on RT enabled kernels where the bottom halves
serialization is done via a local lock, which exposes this misplacement
because the 'mutex' and the local lock nest the wrong way around and
lockdep complains rightfully about a lock inversion.
The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH]
lockdep: annotate sk_locks") which introduced this.
Fix it by moving the mutex_acquire() in front of the actual lock
acquisition, which is what the regular mutex_lock() operation does as well.
lock_sock_fast() is not that straight forward. It looks at the first glance
like a convoluted trylock operation:
spin_lock_bh(sock::sk_lock.slock)
if (!sock::sk_lock.owned)
return false;
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
return true;
But that's not the case: lock_sock_fast() is an interesting optimization
for short critical sections which can run with bottom halves disabled and
sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in
the non contended case by preventing other lockers to acquire
sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which
in turn avoids the overhead of doing the heavy processing in release_sock()
including waking up wait queue waiters.
In the contended case, i.e. when sock::sk_lock.owned == true the behavior
is the same as lock_sock_nested().
Semantically this shortcut means, that the task acquired the 'mutex' even
if it does not touch the sock::sk_lock.owned field in the non-contended
case. Not telling lockdep about this shortcut acquisition is hiding
potential lock ordering violations in the fast path.
As a consequence the same reasoning as for the above lock_sock_nested()
case vs. the placement of the lockdep annotation applies.
The current placement of the lockdep annotation was just copied from
the original lock_sock(), now renamed to lock_sock_nested(),
implementation.
Fix this by moving the mutex_acquire() in front of the actual lock
acquisition and adding the corresponding mutex_release() into
unlock_sock_fast(). Also document the fast path return case with a comment.
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-18 14:42:35 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-08 22:44:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-02-13 15:03:16 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2026-03-10 12:44:51 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
tcp: TCP Small Queues
This introduce TSQ (TCP Small Queues)
TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.
sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.
TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.
As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.
This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.
Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.
Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)
I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.
As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.
If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.
[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
but some drivers call it in their start_xmit() handler.
These drivers should at least use BQL, or else a single TCP
session can still fill the whole NIC TX ring, since TSQ will
have no effect.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 05:50:31 +00:00
|
|
|
|
2026-03-10 12:44:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tcp: tcp_release_cb() should release socket ownership
Lars Persson reported following deadlock :
-000 |M:0x0:0x802B6AF8(asm) <-- arch_spin_lock
-001 |tcp_v4_rcv(skb = 0x8BD527A0) <-- sk = 0x8BE6B2A0
-002 |ip_local_deliver_finish(skb = 0x8BD527A0)
-003 |__netif_receive_skb_core(skb = 0x8BD527A0, ?)
-004 |netif_receive_skb(skb = 0x8BD527A0)
-005 |elk_poll(napi = 0x8C770500, budget = 64)
-006 |net_rx_action(?)
-007 |__do_softirq()
-008 |do_softirq()
-009 |local_bh_enable()
-010 |tcp_rcv_established(sk = 0x8BE6B2A0, skb = 0x87D3A9E0, th = 0x814EBE14, ?)
-011 |tcp_v4_do_rcv(sk = 0x8BE6B2A0, skb = 0x87D3A9E0)
-012 |tcp_delack_timer_handler(sk = 0x8BE6B2A0)
-013 |tcp_release_cb(sk = 0x8BE6B2A0)
-014 |release_sock(sk = 0x8BE6B2A0)
-015 |tcp_sendmsg(?, sk = 0x8BE6B2A0, ?, ?)
-016 |sock_sendmsg(sock = 0x8518C4C0, msg = 0x87D8DAA8, size = 4096)
-017 |kernel_sendmsg(?, ?, ?, ?, size = 4096)
-018 |smb_send_kvec()
-019 |smb_send_rqst(server = 0x87C4D400, rqst = 0x87D8DBA0)
-020 |cifs_call_async()
-021 |cifs_async_writev(wdata = 0x87FD6580)
-022 |cifs_writepages(mapping = 0x852096E4, wbc = 0x87D8DC88)
-023 |__writeback_single_inode(inode = 0x852095D0, wbc = 0x87D8DC88)
-024 |writeback_sb_inodes(sb = 0x87D6D800, wb = 0x87E4A9C0, work = 0x87D8DD88)
-025 |__writeback_inodes_wb(wb = 0x87E4A9C0, work = 0x87D8DD88)
-026 |wb_writeback(wb = 0x87E4A9C0, work = 0x87D8DD88)
-027 |wb_do_writeback(wb = 0x87E4A9C0, force_wait = 0)
-028 |bdi_writeback_workfn(work = 0x87E4A9CC)
-029 |process_one_work(worker = 0x8B045880, work = 0x87E4A9CC)
-030 |worker_thread(__worker = 0x8B045880)
-031 |kthread(_create = 0x87CADD90)
-032 |ret_from_kernel_thread(asm)
Bug occurs because __tcp_checksum_complete_user() enables BH, assuming
it is running from softirq context.
Lars trace involved a NIC without RX checksum support but other points
are problematic as well, like the prequeue stuff.
Problem is triggered by a timer, that found socket being owned by user.
tcp_release_cb() should call tcp_write_timer_handler() or
tcp_delack_timer_handler() in the appropriate context :
BH disabled and socket lock held, but 'owned' field cleared,
as if they were running from timer handlers.
Fixes: 6f458dfb4092 ("tcp: improve latencies of timer triggered events")
Reported-by: Lars Persson <lars.persson@axis.com>
Tested-by: Lars Persson <lars.persson@axis.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-10 09:50:11 -07:00
|
|
|
|
2026-03-10 12:44:51 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2026-03-10 12:44:51 +00:00
|
|
|
|
2006-07-03 00:25:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: introduce and use lock_sock_fast_nested()
Syzkaller reported a false positive deadlock involving
the nl socket lock and the subflow socket lock:
MPTCP: kernel_bind error, err=-98
============================================
WARNING: possible recursive locking detected
5.15.0-rc1-syzkaller #0 Not tainted
--------------------------------------------
syz-executor998/6520 is trying to acquire lock:
ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
but task is already holding lock:
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(k-sk_lock-AF_INET);
lock(k-sk_lock-AF_INET);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by syz-executor998/6520:
#0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline]
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
stack backtrace:
CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
print_deadlock_bug kernel/locking/lockdep.c:2944 [inline]
check_deadlock kernel/locking/lockdep.c:2987 [inline]
validate_chain kernel/locking/lockdep.c:3776 [inline]
__lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015
lock_acquire kernel/locking/lockdep.c:5625 [inline]
lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
lock_sock_fast+0x36/0x100 net/core/sock.c:3229
mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
inet_release+0x12e/0x280 net/ipv4/af_inet.c:431
__sock_release net/socket.c:649 [inline]
sock_release+0x87/0x1b0 net/socket.c:677
mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900
mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170
genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731
genl_family_rcv_msg net/netlink/genetlink.c:775 [inline]
genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792
netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504
genl_rcv+0x24/0x40 net/netlink/genetlink.c:803
netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340
netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929
sock_sendmsg_nosec net/socket.c:704 [inline]
sock_sendmsg+0xcf/0x120 net/socket.c:724
sock_no_sendpage+0x101/0x150 net/core/sock.c:2980
kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504
kernel_sendpage net/socket.c:3501 [inline]
sock_sendpage+0xe5/0x140 net/socket.c:1003
pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364
splice_from_pipe_feed fs/splice.c:418 [inline]
__splice_from_pipe+0x43e/0x8a0 fs/splice.c:562
splice_from_pipe fs/splice.c:597 [inline]
generic_splice_sendpage+0xd4/0x140 fs/splice.c:746
do_splice_from fs/splice.c:767 [inline]
direct_splice_actor+0x110/0x180 fs/splice.c:936
splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891
do_splice_direct+0x1b3/0x280 fs/splice.c:979
do_sendfile+0xae9/0x1240 fs/read_write.c:1249
__do_sys_sendfile64 fs/read_write.c:1314 [inline]
__se_sys_sendfile64 fs/read_write.c:1300 [inline]
__x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7f215cb69969
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005
RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08
R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c
R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000
the problem originates from uncorrect lock annotation in the mptcp
code and is only visible since commit 2dcb96bacce3 ("net: core: Correct
the sock::sk_lock.owned lockdep annotations"), but is present since
the port-based endpoint support initial implementation.
This patch addresses the issue introducing a nested variant of
lock_sock_fast() and using it in the relevant code path.
Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port")
Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-29 11:59:17 +02:00
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-23 09:27:15 +00:00
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
net: core: Correct the sock::sk_lock.owned lockdep annotations
lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the
sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It
is just lockdep wise equivalent. In fact it's an open coded trivial mutex
implementation with some interesting features.
sock::sk_lock.slock is a regular spinlock protecting the 'mutex'
representation sock::sk_lock.owned which is a plain boolean. If 'owned' is
true, then some other task holds the 'mutex', otherwise it is uncontended.
As this locking construct is obviously endangered by lock ordering issues as
any other locking primitive it got lockdep annotated via a dedicated
dependency map sock::sk_lock.dep_map which has to be updated at the lock
and unlock sites.
lock_sock_nested() is a straight forward 'mutex' lock operation:
might_sleep();
spin_lock_bh(sock::sk_lock.slock)
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
The lockdep annotation for sock::sk_lock.owned is for unknown reasons
_after_ the lock has been acquired, i.e. after the code block above and
after releasing sock::sk_lock.slock, but inside the bottom halves disabled
region:
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
The placement after the unlock is obvious because otherwise the
mutex_acquire() would nest into the spin lock held region.
But that's from the lockdep perspective still the wrong place:
1) The mutex_acquire() is issued _after_ the successful acquisition which
is pointless because in a dead lock scenario this point is never
reached which means that if the deadlock is the first instance of
exposing the wrong lock order lockdep does not have a chance to detect
it.
2) It only works because lockdep is rather lax on the context from which
the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves
and therefore non-preemptible region is obviously invalid, except for a
trylock which is clearly not the case here.
This 'works' stops working on RT enabled kernels where the bottom halves
serialization is done via a local lock, which exposes this misplacement
because the 'mutex' and the local lock nest the wrong way around and
lockdep complains rightfully about a lock inversion.
The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH]
lockdep: annotate sk_locks") which introduced this.
Fix it by moving the mutex_acquire() in front of the actual lock
acquisition, which is what the regular mutex_lock() operation does as well.
lock_sock_fast() is not that straight forward. It looks at the first glance
like a convoluted trylock operation:
spin_lock_bh(sock::sk_lock.slock)
if (!sock::sk_lock.owned)
return false;
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
return true;
But that's not the case: lock_sock_fast() is an interesting optimization
for short critical sections which can run with bottom halves disabled and
sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in
the non contended case by preventing other lockers to acquire
sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which
in turn avoids the overhead of doing the heavy processing in release_sock()
including waking up wait queue waiters.
In the contended case, i.e. when sock::sk_lock.owned == true the behavior
is the same as lock_sock_nested().
Semantically this shortcut means, that the task acquired the 'mutex' even
if it does not touch the sock::sk_lock.owned field in the non-contended
case. Not telling lockdep about this shortcut acquisition is hiding
potential lock ordering violations in the fast path.
As a consequence the same reasoning as for the above lock_sock_nested()
case vs. the placement of the lockdep annotation applies.
The current placement of the lockdep annotation was just copied from
the original lock_sock(), now renamed to lock_sock_nested(),
implementation.
Fix this by moving the mutex_acquire() in front of the actual lock
acquisition and adding the corresponding mutex_release() into
unlock_sock_fast(). Also document the fast path return case with a comment.
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-18 14:42:35 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
|
|
|
|
|
net: core: Correct the sock::sk_lock.owned lockdep annotations
lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the
sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It
is just lockdep wise equivalent. In fact it's an open coded trivial mutex
implementation with some interesting features.
sock::sk_lock.slock is a regular spinlock protecting the 'mutex'
representation sock::sk_lock.owned which is a plain boolean. If 'owned' is
true, then some other task holds the 'mutex', otherwise it is uncontended.
As this locking construct is obviously endangered by lock ordering issues as
any other locking primitive it got lockdep annotated via a dedicated
dependency map sock::sk_lock.dep_map which has to be updated at the lock
and unlock sites.
lock_sock_nested() is a straight forward 'mutex' lock operation:
might_sleep();
spin_lock_bh(sock::sk_lock.slock)
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
The lockdep annotation for sock::sk_lock.owned is for unknown reasons
_after_ the lock has been acquired, i.e. after the code block above and
after releasing sock::sk_lock.slock, but inside the bottom halves disabled
region:
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
The placement after the unlock is obvious because otherwise the
mutex_acquire() would nest into the spin lock held region.
But that's from the lockdep perspective still the wrong place:
1) The mutex_acquire() is issued _after_ the successful acquisition which
is pointless because in a dead lock scenario this point is never
reached which means that if the deadlock is the first instance of
exposing the wrong lock order lockdep does not have a chance to detect
it.
2) It only works because lockdep is rather lax on the context from which
the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves
and therefore non-preemptible region is obviously invalid, except for a
trylock which is clearly not the case here.
This 'works' stops working on RT enabled kernels where the bottom halves
serialization is done via a local lock, which exposes this misplacement
because the 'mutex' and the local lock nest the wrong way around and
lockdep complains rightfully about a lock inversion.
The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH]
lockdep: annotate sk_locks") which introduced this.
Fix it by moving the mutex_acquire() in front of the actual lock
acquisition, which is what the regular mutex_lock() operation does as well.
lock_sock_fast() is not that straight forward. It looks at the first glance
like a convoluted trylock operation:
spin_lock_bh(sock::sk_lock.slock)
if (!sock::sk_lock.owned)
return false;
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
return true;
But that's not the case: lock_sock_fast() is an interesting optimization
for short critical sections which can run with bottom halves disabled and
sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in
the non contended case by preventing other lockers to acquire
sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which
in turn avoids the overhead of doing the heavy processing in release_sock()
including waking up wait queue waiters.
In the contended case, i.e. when sock::sk_lock.owned == true the behavior
is the same as lock_sock_nested().
Semantically this shortcut means, that the task acquired the 'mutex' even
if it does not touch the sock::sk_lock.owned field in the non-contended
case. Not telling lockdep about this shortcut acquisition is hiding
potential lock ordering violations in the fast path.
As a consequence the same reasoning as for the above lock_sock_nested()
case vs. the placement of the lockdep annotation applies.
The current placement of the lockdep annotation was just copied from
the original lock_sock(), now renamed to lock_sock_nested(),
implementation.
Fix this by moving the mutex_acquire() in front of the actual lock
acquisition and adding the corresponding mutex_release() into
unlock_sock_fast(). Also document the fast path return case with a comment.
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-18 14:42:35 +02:00
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-11-17 19:43:49 +01:00
|
|
|
|
net: core: Correct the sock::sk_lock.owned lockdep annotations
lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the
sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It
is just lockdep wise equivalent. In fact it's an open coded trivial mutex
implementation with some interesting features.
sock::sk_lock.slock is a regular spinlock protecting the 'mutex'
representation sock::sk_lock.owned which is a plain boolean. If 'owned' is
true, then some other task holds the 'mutex', otherwise it is uncontended.
As this locking construct is obviously endangered by lock ordering issues as
any other locking primitive it got lockdep annotated via a dedicated
dependency map sock::sk_lock.dep_map which has to be updated at the lock
and unlock sites.
lock_sock_nested() is a straight forward 'mutex' lock operation:
might_sleep();
spin_lock_bh(sock::sk_lock.slock)
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
The lockdep annotation for sock::sk_lock.owned is for unknown reasons
_after_ the lock has been acquired, i.e. after the code block above and
after releasing sock::sk_lock.slock, but inside the bottom halves disabled
region:
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
The placement after the unlock is obvious because otherwise the
mutex_acquire() would nest into the spin lock held region.
But that's from the lockdep perspective still the wrong place:
1) The mutex_acquire() is issued _after_ the successful acquisition which
is pointless because in a dead lock scenario this point is never
reached which means that if the deadlock is the first instance of
exposing the wrong lock order lockdep does not have a chance to detect
it.
2) It only works because lockdep is rather lax on the context from which
the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves
and therefore non-preemptible region is obviously invalid, except for a
trylock which is clearly not the case here.
This 'works' stops working on RT enabled kernels where the bottom halves
serialization is done via a local lock, which exposes this misplacement
because the 'mutex' and the local lock nest the wrong way around and
lockdep complains rightfully about a lock inversion.
The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH]
lockdep: annotate sk_locks") which introduced this.
Fix it by moving the mutex_acquire() in front of the actual lock
acquisition, which is what the regular mutex_lock() operation does as well.
lock_sock_fast() is not that straight forward. It looks at the first glance
like a convoluted trylock operation:
spin_lock_bh(sock::sk_lock.slock)
if (!sock::sk_lock.owned)
return false;
while (!try_lock(sock::sk_lock.owned)) {
spin_unlock_bh(sock::sk_lock.slock);
wait_for_release();
spin_lock_bh(sock::sk_lock.slock);
}
spin_unlock(sock::sk_lock.slock);
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
return true;
But that's not the case: lock_sock_fast() is an interesting optimization
for short critical sections which can run with bottom halves disabled and
sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in
the non contended case by preventing other lockers to acquire
sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which
in turn avoids the overhead of doing the heavy processing in release_sock()
including waking up wait queue waiters.
In the contended case, i.e. when sock::sk_lock.owned == true the behavior
is the same as lock_sock_nested().
Semantically this shortcut means, that the task acquired the 'mutex' even
if it does not touch the sock::sk_lock.owned field in the non-contended
case. Not telling lockdep about this shortcut acquisition is hiding
potential lock ordering violations in the fast path.
As a consequence the same reasoning as for the above lock_sock_nested()
case vs. the placement of the lockdep annotation applies.
The current placement of the lockdep annotation was just copied from
the original lock_sock(), now renamed to lock_sock_nested(),
implementation.
Fix this by moving the mutex_acquire() in front of the actual lock
acquisition and adding the corresponding mutex_release() into
unlock_sock_fast(). Also document the fast path return case with a comment.
Reported-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-18 14:42:35 +02:00
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
|
|
|
|
|
net: introduce and use lock_sock_fast_nested()
Syzkaller reported a false positive deadlock involving
the nl socket lock and the subflow socket lock:
MPTCP: kernel_bind error, err=-98
============================================
WARNING: possible recursive locking detected
5.15.0-rc1-syzkaller #0 Not tainted
--------------------------------------------
syz-executor998/6520 is trying to acquire lock:
ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
but task is already holding lock:
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(k-sk_lock-AF_INET);
lock(k-sk_lock-AF_INET);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by syz-executor998/6520:
#0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline]
#1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline]
#2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720
stack backtrace:
CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
print_deadlock_bug kernel/locking/lockdep.c:2944 [inline]
check_deadlock kernel/locking/lockdep.c:2987 [inline]
validate_chain kernel/locking/lockdep.c:3776 [inline]
__lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015
lock_acquire kernel/locking/lockdep.c:5625 [inline]
lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
lock_sock_fast+0x36/0x100 net/core/sock.c:3229
mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738
inet_release+0x12e/0x280 net/ipv4/af_inet.c:431
__sock_release net/socket.c:649 [inline]
sock_release+0x87/0x1b0 net/socket.c:677
mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900
mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170
genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731
genl_family_rcv_msg net/netlink/genetlink.c:775 [inline]
genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792
netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504
genl_rcv+0x24/0x40 net/netlink/genetlink.c:803
netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340
netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929
sock_sendmsg_nosec net/socket.c:704 [inline]
sock_sendmsg+0xcf/0x120 net/socket.c:724
sock_no_sendpage+0x101/0x150 net/core/sock.c:2980
kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504
kernel_sendpage net/socket.c:3501 [inline]
sock_sendpage+0xe5/0x140 net/socket.c:1003
pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364
splice_from_pipe_feed fs/splice.c:418 [inline]
__splice_from_pipe+0x43e/0x8a0 fs/splice.c:562
splice_from_pipe fs/splice.c:597 [inline]
generic_splice_sendpage+0xd4/0x140 fs/splice.c:746
do_splice_from fs/splice.c:767 [inline]
direct_splice_actor+0x110/0x180 fs/splice.c:936
splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891
do_splice_direct+0x1b3/0x280 fs/splice.c:979
do_sendfile+0xae9/0x1240 fs/read_write.c:1249
__do_sys_sendfile64 fs/read_write.c:1314 [inline]
__se_sys_sendfile64 fs/read_write.c:1300 [inline]
__x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7f215cb69969
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005
RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08
R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c
R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000
the problem originates from uncorrect lock annotation in the mptcp
code and is only visible since commit 2dcb96bacce3 ("net: core: Correct
the sock::sk_lock.owned lockdep annotations"), but is present since
the port-based endpoint support initial implementation.
This patch addresses the issue introducing a nested variant of
lock_sock_fast() and using it in the relevant code path.
Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port")
Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-09-29 11:59:17 +02:00
|
|
|
|
2010-05-26 19:20:18 +00:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
|
|
|
|
|
2018-08-06 11:57:02 +08:00
|
|
|
|
|
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
2007-03-18 17:33:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-12-27 18:55:09 -08:00
|
|
|
|
2019-10-25 17:18:36 +08:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
2007-03-18 17:33:16 -07:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-04-23 17:25:24 +10:00
|
|
|
|
|
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
2019-04-23 17:25:24 +10:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-18 17:33:16 -07:00
|
|
|
|
2019-04-17 22:51:48 +02:00
|
|
|
|
2007-03-18 17:33:16 -07:00
|
|
|
|
2019-10-03 23:56:37 +03:00
|
|
|
|
2007-02-09 23:24:36 +09:00
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
2011-11-28 12:04:18 +00:00
|
|
|
|
|
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-10-26 13:51:37 +01:00
|
|
|
|
|
|
|
|
|
2009-02-12 05:03:38 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-12-24 04:35:35 +08:00
|
|
|
|
2014-08-31 21:30:27 -04:00
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-31 21:30:27 -04:00
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-05 16:46:40 -05:00
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-12-24 04:35:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-19 19:40:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-22 13:57:34 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-06 11:53:48 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-27 15:11:20 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-23 08:09:07 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-06 11:53:48 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-27 07:27:49 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-10-10 20:17:44 -07:00
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
2019-10-10 20:17:45 -07:00
|
|
|
|
2025-02-18 19:36:16 +01:00
|
|
|
|
2019-10-10 20:17:46 -07:00
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
2019-10-09 15:41:03 -07:00
|
|
|
|
2025-08-26 12:50:27 +00:00
|
|
|
|
2017-03-20 15:22:03 -04:00
|
|
|
|
|
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-12-14 05:51:57 -08:00
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 09:11:49 -08:00
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-01-17 03:35:32 +00:00
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
2017-12-14 05:51:57 -08:00
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
|
|
|
|
|
2010-01-17 03:35:32 +00:00
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
2017-12-14 05:51:57 -08:00
|
|
|
|
2008-03-31 19:42:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-10 09:01:27 +08:00
|
|
|
|
2012-05-16 19:58:40 +00:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-10 09:01:27 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-12-14 05:51:58 -08:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
|
|
|
|
|
2020-08-10 08:16:58 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-11 10:57:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-13 14:15:18 +02:00
|
|
|
|
|
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-06-27 15:16:42 -07:00
|
|
|
|
|
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
|
|
|
|
|
2022-02-16 09:18:01 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-06-08 23:34:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
tcp: reduce tcp sockets size by one cache line
By default, when a kmem_cache is created with SLAB_TYPESAFE_BY_RCU,
slub has to use extra storage for the freelist pointer after each
object, because slub assumes that any bit in the object
can be used by RCU readers.
Because proto_register() is also using SLAB_HWCACHE_ALIGN,
this forces slub to use one extra cache line per object.
We can instead put the slub freelist anywhere in the object,
granted the concurrent RCU readers are not supposed to
use the pointer value.
Add a new (struct sock)sk_freeptr field, in an union
with sk_rcu: No RCU readers would need to look at sk_rcu,
which is only used at free phase.
Tested:
grep . /sys/kernel/slab/TCP/{object_size,slab_size,objs_per_slab}
grep . /sys/kernel/slab/TCPv6/{object_size,slab_size,objs_per_slab}
Before:
/sys/kernel/slab/TCP/object_size:2368
/sys/kernel/slab/TCP/slab_size:2432
/sys/kernel/slab/TCP/objs_per_slab:13
/sys/kernel/slab/TCPv6/object_size:2496
/sys/kernel/slab/TCPv6/slab_size:2560
/sys/kernel/slab/TCPv6/objs_per_slab:12
After this patch, we can pack one more TCPv6 object per slab,
and object_size == slab_size.
/sys/kernel/slab/TCP/object_size:2368
/sys/kernel/slab/TCP/slab_size:2368
/sys/kernel/slab/TCP/objs_per_slab:13
/sys/kernel/slab/TCPv6/object_size:2496
/sys/kernel/slab/TCPv6/slab_size:2496
/sys/kernel/slab/TCPv6/objs_per_slab:13
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260129153458.4163797-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-01-29 15:34:58 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
tcp: reduce tcp sockets size by one cache line
By default, when a kmem_cache is created with SLAB_TYPESAFE_BY_RCU,
slub has to use extra storage for the freelist pointer after each
object, because slub assumes that any bit in the object
can be used by RCU readers.
Because proto_register() is also using SLAB_HWCACHE_ALIGN,
this forces slub to use one extra cache line per object.
We can instead put the slub freelist anywhere in the object,
granted the concurrent RCU readers are not supposed to
use the pointer value.
Add a new (struct sock)sk_freeptr field, in an union
with sk_rcu: No RCU readers would need to look at sk_rcu,
which is only used at free phase.
Tested:
grep . /sys/kernel/slab/TCP/{object_size,slab_size,objs_per_slab}
grep . /sys/kernel/slab/TCPv6/{object_size,slab_size,objs_per_slab}
Before:
/sys/kernel/slab/TCP/object_size:2368
/sys/kernel/slab/TCP/slab_size:2432
/sys/kernel/slab/TCP/objs_per_slab:13
/sys/kernel/slab/TCPv6/object_size:2496
/sys/kernel/slab/TCPv6/slab_size:2560
/sys/kernel/slab/TCPv6/objs_per_slab:12
After this patch, we can pack one more TCPv6 object per slab,
and object_size == slab_size.
/sys/kernel/slab/TCP/object_size:2368
/sys/kernel/slab/TCP/slab_size:2368
/sys/kernel/slab/TCP/objs_per_slab:13
/sys/kernel/slab/TCPv6/object_size:2496
/sys/kernel/slab/TCPv6/slab_size:2496
/sys/kernel/slab/TCPv6/objs_per_slab:13
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260129153458.4163797-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-01-29 15:34:58 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-05-16 19:58:40 +00:00
|
|
|
|
|
|
|
|
|
2008-03-28 16:39:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-18 22:46:52 -07:00
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2021-03-11 10:57:36 +08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-10 08:16:58 -04:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2007-11-07 02:23:38 -08:00
|
|
|
|
2020-08-10 08:16:58 -04:00
|
|
|
|
2021-04-22 21:41:51 +08:00
|
|
|
|
2020-08-10 08:16:58 -04:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
|
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-07 02:23:38 -08:00
|
|
|
|
2019-08-23 09:14:11 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2008-03-28 16:38:17 -07:00
|
|
|
|
2005-09-06 19:47:50 -07:00
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-09-13 14:15:18 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-03-12 16:44:07 -07:00
|
|
|
|
2020-08-10 08:16:58 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sock_diag: request _diag module only when the family or proto has been registered
Now when using 'ss' in iproute, kernel would try to load all _diag
modules, which also causes corresponding family and proto modules
to be loaded as well due to module dependencies.
Like after running 'ss', sctp, dccp, af_packet (if it works as a module)
would be loaded.
For example:
$ lsmod|grep sctp
$ ss
$ lsmod|grep sctp
sctp_diag 16384 0
sctp 323584 5 sctp_diag
inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag
libcrc32c 16384 3 nf_conntrack,nf_nat,sctp
As these family and proto modules are loaded unintentionally, it
could cause some problems, like:
- Some debug tools use 'ss' to collect the socket info, which loads all
those diag and family and protocol modules. It's noisy for identifying
issues.
- Users usually expect to drop sctp init packet silently when they
have no sense of sctp protocol instead of sending abort back.
- It wastes resources (especially with multiple netns), and SCTP module
can't be unloaded once it's loaded.
...
In short, it's really inappropriate to have these family and proto
modules loaded unexpectedly when just doing debugging with inet_diag.
This patch is to introduce sock_load_diag_module() where it loads
the _diag module only when it's corresponding family or proto has
been already registered.
Note that we can't just load _diag module without the family or
proto loaded, as some symbols used in _diag module are from the
family or proto module.
v1->v2:
- move inet proto check to inet_diag to avoid a compiling err.
v2->v3:
- define sock_load_diag_module in sock.c and export one symbol
only.
- improve the changelog.
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Phil Sutter <phil@nwl.cc>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 18:57:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-11-04 22:37:15 -08:00
|
|
|
|
2020-07-09 15:12:39 +02:00
|
|
|
|
sock_diag: request _diag module only when the family or proto has been registered
Now when using 'ss' in iproute, kernel would try to load all _diag
modules, which also causes corresponding family and proto modules
to be loaded as well due to module dependencies.
Like after running 'ss', sctp, dccp, af_packet (if it works as a module)
would be loaded.
For example:
$ lsmod|grep sctp
$ ss
$ lsmod|grep sctp
sctp_diag 16384 0
sctp 323584 5 sctp_diag
inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag
libcrc32c 16384 3 nf_conntrack,nf_nat,sctp
As these family and proto modules are loaded unintentionally, it
could cause some problems, like:
- Some debug tools use 'ss' to collect the socket info, which loads all
those diag and family and protocol modules. It's noisy for identifying
issues.
- Users usually expect to drop sctp init packet silently when they
have no sense of sctp protocol instead of sending abort back.
- It wastes resources (especially with multiple netns), and SCTP module
can't be unloaded once it's loaded.
...
In short, it's really inappropriate to have these family and proto
modules loaded unexpectedly when just doing debugging with inet_diag.
This patch is to introduce sock_load_diag_module() where it loads
the _diag module only when it's corresponding family or proto has
been already registered.
Note that we can't just load _diag module without the family or
proto loaded, as some symbols used in _diag module are from the
family or proto module.
v1->v2:
- move inet proto check to inet_diag to avoid a compiling err.
v2->v3:
- define sock_load_diag_module in sock.c and export one symbol
only.
- improve the changelog.
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Phil Sutter <phil@nwl.cc>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 18:57:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2007-07-09 13:15:14 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-09 13:15:14 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-16 00:51:59 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
2012-04-25 19:17:29 +05:30
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
2019-10-04 00:44:40 +03:00
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
2010-11-09 23:24:26 +00:00
|
|
|
|
2023-06-23 23:55:12 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2008-11-19 15:14:01 -08:00
|
|
|
|
2011-12-11 21:47:02 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-09 13:15:14 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-23 23:55:12 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-07-09 13:15:14 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-12 14:34:29 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-19 15:14:01 -08:00
|
|
|
|
|
|
|
|
|
2018-04-10 19:42:55 +02:00
|
|
|
|
|
|
|
|
|
2008-11-19 15:14:01 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-02-18 01:34:56 +00:00
|
|
|
|
2008-11-19 15:14:01 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-19 15:14:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-18 20:17:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-29 14:09:42 +02:00
|
|
|
|
2025-11-03 16:26:13 -08:00
|
|
|
|
2020-05-29 14:09:42 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: ioctl: Use kernel memory on protocol ioctl callbacks
Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback. This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.
Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).
This changes the "struct proto" ioctl format in the following way:
int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
+ int *karg);
(Important to say that this patch does not touch the "struct proto_ops"
protocols)
So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:
1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
to userspace
3) Read an input from userspace, and return a buffer to userspace.
The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:
* Protocol RAW:
* cmd = SIOCGETVIFCNT:
* input and output = struct sioc_vif_req
* cmd = SIOCGETSGCNT
* input and output = struct sioc_sg_req
* Explanation: for the SIOCGETVIFCNT case, userspace passes the input
argument, which is struct sioc_vif_req. Then the callback populates
the struct, which is copied back to userspace.
* Protocol RAW6:
* cmd = SIOCGETMIFCNT_IN6
* input and output = struct sioc_mif_req6
* cmd = SIOCGETSGCNT_IN6
* input and output = struct sioc_sg_req6
* Protocol PHONET:
* cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
* input int (4 bytes)
* Nothing is copied back to userspace.
For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.
The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-09 08:27:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-19 12:43:35 +00:00
|
|
|
|
net: ioctl: Use kernel memory on protocol ioctl callbacks
Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback. This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.
Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).
This changes the "struct proto" ioctl format in the following way:
int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
+ int *karg);
(Important to say that this patch does not touch the "struct proto_ops"
protocols)
So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:
1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
to userspace
3) Read an input from userspace, and return a buffer to userspace.
The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:
* Protocol RAW:
* cmd = SIOCGETVIFCNT:
* input and output = struct sioc_vif_req
* cmd = SIOCGETSGCNT
* input and output = struct sioc_sg_req
* Explanation: for the SIOCGETVIFCNT case, userspace passes the input
argument, which is struct sioc_vif_req. Then the callback populates
the struct, which is copied back to userspace.
* Protocol RAW6:
* cmd = SIOCGETMIFCNT_IN6
* input and output = struct sioc_mif_req6
* cmd = SIOCGETSGCNT_IN6
* input and output = struct sioc_sg_req6
* Protocol PHONET:
* cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
* input int (4 bytes)
* Nothing is copied back to userspace.
For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.
The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-09 08:27:42 -07:00
|
|
|
|
2023-06-19 12:43:35 +00:00
|
|
|
|
net: ioctl: Use kernel memory on protocol ioctl callbacks
Most of the ioctls to net protocols operates directly on userspace
argument (arg). Usually doing get_user()/put_user() directly in the
ioctl callback. This is not flexible, because it is hard to reuse these
functions without passing userspace buffers.
Change the "struct proto" ioctls to avoid touching userspace memory and
operate on kernel buffers, i.e., all protocol's ioctl callbacks is
adapted to operate on a kernel memory other than on userspace (so, no
more {put,get}_user() and friends being called in the ioctl callback).
This changes the "struct proto" ioctl format in the following way:
int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
+ int *karg);
(Important to say that this patch does not touch the "struct proto_ops"
protocols)
So, the "karg" argument, which is passed to the ioctl callback, is a
pointer allocated to kernel space memory (inside a function wrapper).
This buffer (karg) may contain input argument (copied from userspace in
a prep function) and it might return a value/buffer, which is copied
back to userspace if necessary. There is not one-size-fits-all format
(that is I am using 'may' above), but basically, there are three type of
ioctls:
1) Do not read from userspace, returns a result to userspace
2) Read an input parameter from userspace, and does not return anything
to userspace
3) Read an input from userspace, and return a buffer to userspace.
The default case (1) (where no input parameter is given, and an "int" is
returned to userspace) encompasses more than 90% of the cases, but there
are two other exceptions. Here is a list of exceptions:
* Protocol RAW:
* cmd = SIOCGETVIFCNT:
* input and output = struct sioc_vif_req
* cmd = SIOCGETSGCNT
* input and output = struct sioc_sg_req
* Explanation: for the SIOCGETVIFCNT case, userspace passes the input
argument, which is struct sioc_vif_req. Then the callback populates
the struct, which is copied back to userspace.
* Protocol RAW6:
* cmd = SIOCGETMIFCNT_IN6
* input and output = struct sioc_mif_req6
* cmd = SIOCGETSGCNT_IN6
* input and output = struct sioc_sg_req6
* Protocol PHONET:
* cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE
* input int (4 bytes)
* Nothing is copied back to userspace.
For the exception cases, functions sock_sk_ioctl_inout() will
copy the userspace input, and copy it back to kernel space.
The wrapper that prepare the buffer and put the buffer back to user is
sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now
calls sk_ioctl(), which will handle all cases.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-09 08:27:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:18 +00:00
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
2025-08-15 20:16:18 +00:00
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-09-19 20:48:50 +00:00
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-11-24 17:50:11 +00:00
|
|
|
|
|
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-09-19 20:48:49 +00:00
|
|
|
|
|
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-09-19 20:48:50 +00:00
|
|
|
|
net: reorganize "struct sock" fields
Last major reorg happened in commit 9115e8cd2a0c ("net: reorganize
struct sock for better data locality")
Since then, many changes have been done.
Before SO_PEEK_OFF support is added to TCP, we need
to move sk_peek_off to a better location.
It is time to make another pass, and add six groups,
without explicit alignment.
- sock_write_rx (following sk_refcnt) read-write fields in rx path.
- sock_read_rx read-mostly fields in rx path.
- sock_read_rxtx read-mostly fields in both rx and tx paths.
- sock_write_rxtx read-write fields in both rx and tx paths.
- sock_write_tx read-write fields in tx paths.
- sock_read_tx read-mostly fields in tx paths.
Results on TCP_RR benchmarks seem to show a gain (4 to 5 %).
It is possible UDP needs a change, because sk_peek_off
shares a cache line with sk_receive_queue.
If this the case, we can exchange roles of sk->sk_receive
and up->reader_queue queues.
After this change, we have the following layout:
struct sock {
struct sock_common __sk_common; /* 0 0x88 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */
atomic_t sk_drops; /* 0x88 0x4 */
__s32 sk_peek_off; /* 0x8c 0x4 */
struct sk_buff_head sk_error_queue; /* 0x90 0x18 */
struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */
/* --- cacheline 3 boundary (192 bytes) --- */
struct {
atomic_t rmem_alloc; /* 0xc0 0x4 */
int len; /* 0xc4 0x4 */
struct sk_buff * head; /* 0xc8 0x8 */
struct sk_buff * tail; /* 0xd0 0x8 */
} sk_backlog; /* 0xc0 0x18 */
struct {
atomic_t rmem_alloc; /* 0 0x4 */
int len; /* 0x4 0x4 */
struct sk_buff * head; /* 0x8 0x8 */
struct sk_buff * tail; /* 0x10 0x8 */
/* size: 24, cachelines: 1, members: 4 */
/* last cacheline: 24 bytes */
};
__u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */
__u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */
rcu * sk_rx_dst; /* 0xd8 0x8 */
int sk_rx_dst_ifindex; /* 0xe0 0x4 */
u32 sk_rx_dst_cookie; /* 0xe4 0x4 */
unsigned int sk_ll_usec; /* 0xe8 0x4 */
unsigned int sk_napi_id; /* 0xec 0x4 */
u16 sk_busy_poll_budget; /* 0xf0 0x2 */
u8 sk_prefer_busy_poll; /* 0xf2 0x1 */
u8 sk_userlocks; /* 0xf3 0x1 */
int sk_rcvbuf; /* 0xf4 0x4 */
rcu * sk_filter; /* 0xf8 0x8 */
/* --- cacheline 4 boundary (256 bytes) --- */
union {
rcu * sk_wq; /* 0x100 0x8 */
struct socket_wq * sk_wq_raw; /* 0x100 0x8 */
}; /* 0x100 0x8 */
union {
rcu * sk_wq; /* 0 0x8 */
struct socket_wq * sk_wq_raw; /* 0 0x8 */
};
void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */
long sk_rcvtimeo; /* 0x110 0x8 */
int sk_rcvlowat; /* 0x118 0x4 */
__u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */
__u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */
int sk_err; /* 0x11c 0x4 */
struct socket * sk_socket; /* 0x120 0x8 */
struct mem_cgroup * sk_memcg; /* 0x128 0x8 */
rcu * sk_policy[2]; /* 0x130 0x10 */
/* --- cacheline 5 boundary (320 bytes) --- */
__u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */
__u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */
socket_lock_t sk_lock; /* 0x140 0x20 */
u32 sk_reserved_mem; /* 0x160 0x4 */
int sk_forward_alloc; /* 0x164 0x4 */
u32 sk_tsflags; /* 0x168 0x4 */
__u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */
__u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */
int sk_write_pending; /* 0x16c 0x4 */
atomic_t sk_omem_alloc; /* 0x170 0x4 */
int sk_sndbuf; /* 0x174 0x4 */
int sk_wmem_queued; /* 0x178 0x4 */
refcount_t sk_wmem_alloc; /* 0x17c 0x4 */
/* --- cacheline 6 boundary (384 bytes) --- */
unsigned long sk_tsq_flags; /* 0x180 0x8 */
union {
struct sk_buff * sk_send_head; /* 0x188 0x8 */
struct rb_root tcp_rtx_queue; /* 0x188 0x8 */
}; /* 0x188 0x8 */
union {
struct sk_buff * sk_send_head; /* 0 0x8 */
struct rb_root tcp_rtx_queue; /* 0 0x8 */
};
struct sk_buff_head sk_write_queue; /* 0x190 0x18 */
u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */
u32 sk_pacing_status; /* 0x1ac 0x4 */
struct page_frag sk_frag; /* 0x1b0 0x10 */
/* --- cacheline 7 boundary (448 bytes) --- */
struct timer_list sk_timer; /* 0x1c0 0x28 */
/* XXX last struct has 4 bytes of padding */
unsigned long sk_pacing_rate; /* 0x1e8 0x8 */
atomic_t sk_zckey; /* 0x1f0 0x4 */
atomic_t sk_tskey; /* 0x1f4 0x4 */
__u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */
__u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */
unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */
/* --- cacheline 8 boundary (512 bytes) --- */
long sk_sndtimeo; /* 0x200 0x8 */
u32 sk_priority; /* 0x208 0x4 */
u32 sk_mark; /* 0x20c 0x4 */
rcu * sk_dst_cache; /* 0x210 0x8 */
netdev_features_t sk_route_caps; /* 0x218 0x8 */
u16 sk_gso_type; /* 0x220 0x2 */
u16 sk_gso_max_segs; /* 0x222 0x2 */
unsigned int sk_gso_max_size; /* 0x224 0x4 */
gfp_t sk_allocation; /* 0x228 0x4 */
u32 sk_txhash; /* 0x22c 0x4 */
u8 sk_pacing_shift; /* 0x230 0x1 */
bool sk_use_task_frag; /* 0x231 0x1 */
__u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */
u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */
u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */
u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */
u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */
/* XXX 4 bits hole, try to pack */
u8 sk_shutdown; /* 0x233 0x1 */
u16 sk_type; /* 0x234 0x2 */
u16 sk_protocol; /* 0x236 0x2 */
unsigned long sk_lingertime; /* 0x238 0x8 */
/* --- cacheline 9 boundary (576 bytes) --- */
struct proto * sk_prot_creator; /* 0x240 0x8 */
rwlock_t sk_callback_lock; /* 0x248 0x8 */
int sk_err_soft; /* 0x250 0x4 */
u32 sk_ack_backlog; /* 0x254 0x4 */
u32 sk_max_ack_backlog; /* 0x258 0x4 */
kuid_t sk_uid; /* 0x25c 0x4 */
spinlock_t sk_peer_lock; /* 0x260 0x4 */
int sk_bind_phc; /* 0x264 0x4 */
struct pid * sk_peer_pid; /* 0x268 0x8 */
const struct cred * sk_peer_cred; /* 0x270 0x8 */
ktime_t sk_stamp; /* 0x278 0x8 */
/* --- cacheline 10 boundary (640 bytes) --- */
int sk_disconnects; /* 0x280 0x4 */
u8 sk_txrehash; /* 0x284 0x1 */
u8 sk_clockid; /* 0x285 0x1 */
u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */
u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */
u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */
/* XXX 1 byte hole, try to pack */
void * sk_user_data; /* 0x288 0x8 */
void * sk_security; /* 0x290 0x8 */
struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */
void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */
void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */
void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */
int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */
/* --- cacheline 11 boundary (704 bytes) --- */
void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */
rcu * sk_reuseport_cb; /* 0x2c8 0x8 */
rcu * sk_bpf_storage; /* 0x2d0 0x8 */
struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */
netns_tracker ns_tracker; /* 0x2e8 0x8 */
/* size: 752, cachelines: 12, members: 105 */
/* sum members: 749, holes: 1, sum holes: 1 */
/* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */
/* paddings: 1, sum paddings: 4 */
/* forced alignments: 1 */
/* last cacheline: 48 bytes */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2024-02-16 16:20:06 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|