On Tue, Nov 27, 2018 at 10:17 PM 배석진 wrote:
> >> we saw hundreds of not closed tcp session with FIN_WAIT1 and LAST_ACK.
> >
> > These sessions should have a timer, and eventually disappear.
>
> FIN_WAIT2 and TIME_WAIT have a timer.
> but FIN_WAIT1 and LAST_ACK are have too?
What harm is caused
Since commit 509db2833e0d ("bpf: error handling when map_lookup_elem
isn't supported") when map lookup isn't supported, the map_lookup_elem
function should return ERR_PTR(-EOPNOTSUPP).
Fixes: f1a2e44a3aec ("bpf: add queue and stack maps")
Signed-off-by: Prashant Bhole
---
This set fixes map_lookup_elem return value for queue/stack map.
Also adds verifier tests to check whether verifier prevents lookup on
these maps.
Note that patch 2 isn't dependant on patch 1. The verifier prevents
lookup on queue/stack map because key size is zero.
Prashant Bhole (2):
bpf:
This patch adds tests to check whether bpf verifier prevents lookup
on queue/stack maps
Signed-off-by: Prashant Bhole
---
tools/testing/selftests/bpf/test_verifier.c | 52 +
1 file changed, 52 insertions(+)
diff --git a/tools/testing/selftests/bpf/test_verifier.c
Previously when unbinding a slave the 802.3ad implementation only told
partner that the port is not suitable for aggregation by setting the port
aggregation state from aggregatable to individual. This is not enough. If the
physical layer still stays up and we only unbinded this port from the bond
CONFIG_FTRACE_SYSCALLS=y is required for get_cgroup_id_user test case
this test reads a file from debug trace path
/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id
Signed-off-by: Naresh Kamboju
---
tools/testing/selftests/bpf/config | 1 +
1 file changed, 1 insertion(+)
diff
Le 26/11/2018 à 23:08, David Ahern a écrit :
> On 11/26/18 2:27 PM, Joe Stringer wrote:
>> @@ -2405,6 +2407,9 @@ enum bpf_func_id {
>> /* BPF_FUNC_perf_event_output for sk_buff input context. */
>> #define BPF_F_CTXLEN_MASK (0xfULL << 32)
>>
>> +/* BPF_FUNC_sk_lookup_tcp and
> -Original Message-
> From: Ioana Ciocoi Radulescu
> Sent: Monday, November 26, 2018 18:27
> To: netdev@vger.kernel.org; da...@davemloft.net
> Cc: Ioana Ciornei ; dsah...@gmail.com; Camelia
> Alexandra Groza
> Subject: [PATCH v2 net-next 1/8] dpaa2-eth: Add basic XDP support
>
> We keep
Neal pointed out that non sack flows might suffer from ACK compression
added in the following patch ("tcp: implement coalescing on backlog queue")
Instead of tweaking tcp_add_backlog() we can take into
account how many ACK were coalesced, this information
will be available in
In case GRO is not as efficient as it should be or disabled,
we might have a user thread trapped in __release_sock() while
softirq handler flood packets up to the point we have to drop.
This patch balances work done from user thread and softirq,
to give more chances to __release_sock() to
Jean-Louis Dupond reported poor iscsi TCP receive performance
that we tracked to backlog drops.
Apparently we fail to send window updates reflecting the
fact that we are under stress.
Note that we might lack a proper window increase when
backlog is fully processed, since __release_sock() clears
On Tue, Nov 27, 2018 at 07:30:49PM +0900, Xin Long wrote:
> On Mon, Nov 26, 2018 at 10:59 PM Neil Horman wrote:
> >
> > On Mon, Nov 26, 2018 at 10:46:33PM +0900, Xin Long wrote:
> > > On Mon, Nov 26, 2018 at 9:54 PM Neil Horman wrote:
> > > >
> > > > On Mon, Nov 26, 2018 at 07:22:05PM +0800, Xin
From: Dmitry Bogdanov
The last set of csum offload fixes had a leak:
Checksum enabled status bits from rx descriptor were incorrectly
interpreted. Consequently all the other valid logic worked on zero bits.
That caused rx checksum offloads never to trigger.
Tested by dumping rx descriptors and
There are no such structs flow_dissector_key_flow_vlan or
flow_dissector_key_flow_tags, the actual structs used are struct
flow_dissector_key_vlan and struct flow_dissector_key_tags. So correct the
comments against FLOW_DISSECTOR_KEY_VLAN, FLOW_DISSECTOR_KEY_FLOW_LABEL and
Tell the compiler that most TCP flows are using SACK these days.
There is no need to add the unlikely() clause in tcp_is_reno(),
the compiler is able to infer it.
Signed-off-by: Eric Dumazet
---
include/net/tcp.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
While working on the SACK compression issue Jean-Louis Dupond
reported, we found that his linux box was suffering very hard
from tail drops on the socket backlog queue.
First patch hints the compiler about sack flows being the norm.
Second patch changes non-sack code in preparation of the ack
On 10/11/18 05:21, Jakub Kicinski wrote:
> From: John Hurley
>
> Previously, TC block tunnel decap rules were only offloaded when a
> callback was triggered through registration of the rules egress device.
> This meant that the driver had no access to the ingress netdev and so
> could not verify
Toni Peltonen wrote:
>Previously when unbinding a slave the 802.3ad implementation only told
>partner that the port is not suitable for aggregation by setting the port
>aggregation state from aggregatable to individual. This is not enough. If the
>physical layer still stays up and we only
On Mon, Nov 26, 2018 at 02:16:16PM -0800, John Fastabend wrote:
> After being able to add metadata to messages with sk_msg_push_data we
> have also found it useful to be able to "pop" this metadata off before
> sending it to applications in some cases. This series adds a new helper
>
On Tue, Nov 27, 2018 at 7:57 AM, Eric Dumazet wrote:
> While working on the SACK compression issue Jean-Louis Dupond
> reported, we found that his linux box was suffering very hard
> from tail drops on the socket backlog queue.
>
> First patch hints the compiler about sack flows being the norm.
>
On Mon, Nov 26, 2018 at 09:17:13PM -0800, Yonghong Song wrote:
> Commit 2667a2626f4d ("bpf: btf: Add BTF_KIND_FUNC
> and BTF_KIND_FUNC_PROTO") checked the name validity
> for BTF_KIND_FUNC/BTF_KIND_FUNC_PROTO types such that:
> . BTF_KIND_FUNC must have a valid identifier name
> . BTF_KIND_PROTO
From: Daniel Borkmann
Date: Tue, 27 Nov 2018 10:16:17 +0100
> The following pull-request contains BPF updates for your *net* tree.
>
> The main changes are:
>
> 1) Fix several bugs in BPF sparc JIT, that is, convergence for fused
>branches, initialization of frame pointer register, and
Trace events are already present for the receive entry points, to indicate
how the reception entered the stack.
This patch adds the corresponding exit trace events that will bound the
reception such that all events occurring between the entry and the exit
can be considered as part of the
On Tue, 27 Nov 2018 at 06:49, Nicolas Dichtel wrote:
>
> Le 26/11/2018 à 23:08, David Ahern a écrit :
> > On 11/26/18 2:27 PM, Joe Stringer wrote:
> >> @@ -2405,6 +2407,9 @@ enum bpf_func_id {
> >> /* BPF_FUNC_perf_event_output for sk_buff input context. */
> >> #define BPF_F_CTXLEN_MASK
On Tue, 27 Nov 2018 16:04:29 +, Edward Cree wrote:
> On 10/11/18 05:21, Jakub Kicinski wrote:
> > From: John Hurley
> >
> > Previously, TC block tunnel decap rules were only offloaded when a
> > callback was triggered through registration of the rules egress device.
> > This meant that the
On 11/27/2018 09:56 AM, Toni Peltonen wrote:
> Previously when unbinding a slave the 802.3ad implementation only told
> partner that the port is not suitable for aggregation by setting the port
> aggregation state from aggregatable to individual. This is not enough. If the
> physical layer still
On 11/27/18 7:24 AM, Naresh Kamboju wrote:
> CONFIG_FTRACE_SYSCALLS=y is required for get_cgroup_id_user test case
> this test reads a file from debug trace path
> /sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id
>
> Signed-off-by: Naresh Kamboju
Acked-by: Yonghong Song
>
On Tue, Nov 27, 2018 at 2:58 PM Willem de Bruijn
wrote:
>
> On Tue, Nov 27, 2018 at 1:41 PM Maxim Mikityanskiy
> wrote:
> >
> > Hi everyone,
> >
> > We are experiencing an issue with Mellanox mlx5 driver, and I tracked it
> > down to
> > the packet_snd function in net/packet/af_packet.c.
> >
>
On Tue, Nov 27, 2018 at 10:57 AM Eric Dumazet wrote:
>
> Neal pointed out that non sack flows might suffer from ACK compression
> added in the following patch ("tcp: implement coalescing on backlog queue")
>
> Instead of tweaking tcp_add_backlog() we can take into
> account how many ACK were
On 11/26/2018 8:02 PM, Stephen Hemminger wrote:
> On Mon, 26 Nov 2018 17:56:10 -0800
> "Nambiar, Amritha" wrote:
>
>> On 11/26/2018 4:43 PM, David Ahern wrote:
>>> On 11/26/18 5:23 PM, Nambiar, Amritha wrote:
> Can tc flower use something similar to ip ru with single port or port
>
On 11/27/2018 01:19 PM, Neal Cardwell wrote:
> On Tue, Nov 27, 2018 at 10:57 AM Eric Dumazet wrote:
>>
>> Neal pointed out that non sack flows might suffer from ACK compression
>> added in the following patch ("tcp: implement coalescing on backlog queue")
>>
>> Instead of tweaking
On Tue, Nov 27, 2018 at 1:41 PM Maxim Mikityanskiy wrote:
>
> Hi everyone,
>
> We are experiencing an issue with Mellanox mlx5 driver, and I tracked it down
> to
> the packet_snd function in net/packet/af_packet.c.
>
> Brief description: when a socket is created by calling `socket(AF_PACKET,
>
On Tue, Nov 27, 2018 at 10:01:40AM -0800, Joe Stringer wrote:
> On Tue, 27 Nov 2018 at 06:49, Nicolas Dichtel
> wrote:
> >
> > Le 26/11/2018 à 23:08, David Ahern a écrit :
> > > On 11/26/18 2:27 PM, Joe Stringer wrote:
> > >> @@ -2405,6 +2407,9 @@ enum bpf_func_id {
> > >> /*
On 2018-11-27 12:11, Xin Long wrote:
> sctp_assoc_update_frag_point() should be called whenever asoc->pathmtu
> changes, but we missed one place in sctp_association_init(). It would
> cause frag_point is zero when sending data.
>
> As says in Jakub's reproducer, if sp->pathmtu is set by
On Tue, Nov 27, 2018 at 10:57 AM Eric Dumazet wrote:
>
> In case GRO is not as efficient as it should be or disabled,
> we might have a user thread trapped in __release_sock() while
> softirq handler flood packets up to the point we have to drop.
>
> This patch balances work done from user thread
On Tue, Nov 27, 2018 at 10:57 AM Eric Dumazet wrote:
>
> Tell the compiler that most TCP flows are using SACK these days.
>
> There is no need to add the unlikely() clause in tcp_is_reno(),
> the compiler is able to infer it.
>
> Signed-off-by: Eric Dumazet
> ---
Acked-by: Neal Cardwell
Nice.
So far the two functions consider neither member eee_enabled nor
eee_active. Therefore network drivers have to do this in some kind
of glue code. I think this can be avoided.
Getting EEE parameters:
When not advertising any EEE mode, we can't consider EEE to be enabled.
Therefore interpret "EEE
>From: Intel-wired-lan [mailto:intel-wired-lan-boun...@osuosl.org] On Behalf Of
>Sokolowski, Jan
>Sent: Tuesday, November 27, 2018 12:20 AM
>To: intel-wired-...@osuosl.org
>Cc: netdev@vger.kernel.org
>Subject: [Intel-wired-lan] [PATCH] i40e: fix kerneldoc for xsk methods
>
>One method,
On Tue, Nov 27, 2018 at 07:11:50PM +0800, Xin Long wrote:
> sctp_assoc_update_frag_point() should be called whenever asoc->pathmtu
> changes, but we missed one place in sctp_association_init(). It would
> cause frag_point is zero when sending data.
>
> As says in Jakub's reproducer, if
On 11/27/18 11:02 AM, Alexei Starovoitov wrote:
> On Mon, Nov 26, 2018 at 09:17:13PM -0800, Yonghong Song wrote:
>> Commit 2667a2626f4d ("bpf: btf: Add BTF_KIND_FUNC
>> and BTF_KIND_FUNC_PROTO") checked the name validity
>> for BTF_KIND_FUNC/BTF_KIND_FUNC_PROTO types such that:
>> .
Function btf_name_valid_identifier() have been implemented in
bpf-next commit 2667a2626f4d ("bpf: btf: Add BTF_KIND_FUNC and
BTF_KIND_FUNC_PROTO"). Backport this function so later patch
can use it.
Fixes: 69b693f0aefa ("bpf: btf: Introduce BPF Type Format (BTF)")
Signed-off-by: Yonghong Song
---
From: Martin KaFai Lau
There are two unit test cases, which should encode
TYPEDEF type, but instead encode PTR type.
The error is flagged out after enforcing name
checking in the previous patch.
Fixes: c0fa1b6c3efc ("bpf: btf: Add BTF tests")
Signed-off-by: Martin KaFai Lau
Signed-off-by:
This patch set added name checking for PTR, ARRAY, VOLATILE, TYPEDEF,
CONST, RESTRICT, STRUCT, UNION, ENUM and FWD types. Such a strict
name checking makes BTF more sound in the kernel and future
BTF-to-header-file converesion ([1]) less fragile.
Patch #1 implemented btf_name_valid_identifier()
The following additional unit testcases are added to test_btf:
...
BTF raw test[42] (typedef (invalid name, name_off = 0)): OK
BTF raw test[43] (typedef (invalid name, invalid identifier)): OK
BTF raw test[44] (ptr type (invalid name, name_off <> 0)): OK
BTF raw test[45] (volatile type (invalid
This patch added name checking for the following types:
. BTF_KIND_PTR, BTF_KIND_ARRAY, BTF_KIND_VOLATILE,
BTF_KIND_CONST, BTF_KIND_RESTRICT:
the name must be null
. BTF_KIND_STRUCT, BTF_KIND_UNION: the struct/member name
is either null or a valid identifier
. BTF_KIND_ENUM: the
On Tue, Nov 27, 2018 at 10:57 AM Eric Dumazet wrote:
>
> Jean-Louis Dupond reported poor iscsi TCP receive performance
> that we tracked to backlog drops.
>
> Apparently we fail to send window updates reflecting the
> fact that we are under stress.
>
> Note that we might lack a proper window
From: John Hurley
Calling nfp_compile_flow_metadata both assigns a stats context and
increments a ref counter on (or allocates) a mask id table entry. These
are released by the nfp_modify_flow_metadata call on flow deletion,
however, if a flow add fails after metadata is set then the flow entry
On 11/27/2018 01:58 PM, Neal Cardwell wrote:
> I wonder if technically perhaps the logic should skip coalescing if
> the tail or skb has the TCP_FLAG_URG bit set? It seems if skbs are
> coalesced, and some have urgent data and some do not, then the
> TCP_FLAG_URG bit will be accumulated into
On 2018-11-19 08:20, Xin Long wrote:
> On Mon, Nov 19, 2018 at 5:49 AM Jakub Audykowicz
> wrote:
>> Calling send on a connected SCTP socket results in kernel panic if
>> spp_pathmtu was configured manually before an association is established
>> and it was not reconfigured to another value once
In the linux/bpf.h UAPI header, we must absolutely avoid any
non-fixed-sized types.
Otherwise we have serious problems on 32-bit.
Unfortunately I discovered today that we have take on two such cases,
sk_msg_md and sk_reuseport_md, both of which start with two void
pointers.
I hit this because
Neal pointed out that non sack flows might suffer from ACK compression
added in the following patch ("tcp: implement coalescing on backlog queue")
Instead of tweaking tcp_add_backlog() we can take into
account how many ACK were coalesced, this information
will be available in
In case GRO is not as efficient as it should be or disabled,
we might have a user thread trapped in __release_sock() while
softirq handler flood packets up to the point we have to drop.
This patch balances work done from user thread and softirq,
to give more chances to __release_sock() to
While working on the SACK compression issue Jean-Louis Dupond
reported, we found that his linux box was suffering very hard
from tail drops on the socket backlog queue.
First patch hints the compiler about sack flows being the norm.
Second patch changes non-sack code in preparation of the ack
Jean-Louis Dupond reported poor iscsi TCP receive performance
that we tracked to backlog drops.
Apparently we fail to send window updates reflecting the
fact that we are under stress.
Note that we might lack a proper window increase when
backlog is fully processed, since __release_sock() clears
Tell the compiler that most TCP flows are using SACK these days.
There is no need to add the unlikely() clause in tcp_is_reno(),
the compiler is able to infer it.
Signed-off-by: Eric Dumazet
Acked-by: Neal Cardwell
Acked-by: Yuchung Cheng
---
include/net/tcp.h | 2 +-
1 file changed, 1
From: Sharath Chandra Vurukala
Date: Mon, 26 Nov 2018 15:05:50 +0530
> when the tcp_retranmission_timer expires and tcp_retranmsit_skb is
> called if the retranmsission fails due to local congestion,
> backoff should not incremented.
>
> tcp_retransmit_skb() returns non-zero negative value in
From: Nicolas Dichtel
Date: Mon, 26 Nov 2018 15:42:01 +0100
>
> The goal of this series is to ease the interpretation of nsid received in
> netlink messages from other netns (when the user uses
> NETLINK_F_LISTEN_ALL_NSID).
>
> After this series, with a patched iproute2:
...
> v3 -> v4:
> -
From: Bryan Whitehead
Date: Mon, 26 Nov 2018 12:04:57 -0500
> The lan743x driver, when under heavy traffic load, has been noticed
> to sometimes hang, or cause a kernel panic.
>
> Debugging reveals that the TX napi poll routine was returning
> the wrong value, 'weight'. Most other drivers
On Mon, Nov 26, 2018 at 1:35 AM, Sharath Chandra Vurukala
wrote:
> when the tcp_retranmission_timer expires and tcp_retranmsit_skb is
> called if the retranmsission fails due to local congestion,
> backoff should not incremented.
>
> tcp_retransmit_skb() returns non-zero negative value in some
Added support for filtering based on port ranges.
UAPI changes have been accepted into net-next.
Example:
1. Match on a port range:
-
$ tc filter add dev enp4s0 protocol ip parent :\
prio 1 flower ip_proto tcp dst_port 20-30 skip_hw\
action drop
$ tc -s filter
From: Petr Oros
Date: Thu, 22 Nov 2018 15:24:07 +0100
> @@ -4700,8 +4700,11 @@ int be_update_queues(struct be_adapter *adapter)
> struct net_device *netdev = adapter->netdev;
> int status;
>
> - if (netif_running(netdev))
> + if (netif_running(netdev)) {
> + /*
From: Heiner Kallweit
Date: Fri, 23 Nov 2018 19:41:29 +0100
> After switching the r8169 driver to use phylib some user reported that
> their network is broken. This was caused by the genphy PHY driver being
> used instead of the dedicated PHY driver for the RTL8211B. Users
> reported that
Most linux hosts never setup TCP MD5 keys. We can avoid a
cache line miss (accessing tp->md5ig_info) on RX and TX
using a jump label.
Signed-off-by: Eric Dumazet
---
include/net/tcp.h | 18 +++---
net/ipv4/tcp.c| 5 -
net/ipv4/tcp_ipv4.c | 11 +++
From: Ido Schimmel
Date: Sun, 25 Nov 2018 09:43:53 +
> The driver is using 802.1Q filtering identifiers (FIDs) to represent the
> different VLANs in the VLAN-aware bridge (only one is supported).
>
> However, the device cannot assign a VNI to such FIDs, which prevents the
> driver from
On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet wrote:
>
>
>
> On 11/27/2018 03:21 PM, Cong Wang wrote:
> > When an ethernet frame is padded to meet the minimum ethernet frame
> > size, the padding octets are not covered by the hardware checksum.
> > Fortunately the padding octets are ususally
From: Lorenzo Bianconi
Date: Mon, 26 Nov 2018 15:07:16 +0100
> Fix a possible NULL pointer dereference in nic_remove routine
> removing the nicpf module if nic_probe fails.
> The issue can be triggered with the following reproducer:
>
> $rmmod nicvf
> $rmmod nicpf
>
> [ 521.412008] Unable to
On Fri, 2018-11-16 at 09:20 -0600, Thor Thayer wrote:
> Hi Dalon,
>
> Just a few comments/questions.
>
> On 11/14/18 6:50 PM, Dalon Westergreen wrote:
> > From: Dalon Westergreen
> >
> > Add support for the mSGDMA prefetcher. The prefetcher adds support
> > for a linked list of descriptors in
From: John Hurley
For flow offload adds, if the rhash insert code fails, the flow will still
have been offloaded but the reference to it in the driver freed.
Re-order the offload setup calls to ensure that a flow will only be written
to FW if a kernel reference is held and stored in the
On Tue, Nov 27, 2018 at 3:32 PM Willem de Bruijn
wrote:
>
> On Tue, Nov 27, 2018 at 2:58 PM Willem de Bruijn
> wrote:
> >
> > On Tue, Nov 27, 2018 at 1:41 PM Maxim Mikityanskiy
> > wrote:
> > >
> > > Hi everyone,
> > >
> > > We are experiencing an issue with Mellanox mlx5 driver, and I tracked
On Tue, Nov 27, 2018 at 3:21 PM Cong Wang wrote:
> + if (proto == htons(ETH_P_IP)) {
> + struct iphdr *ipv4 = ip_p;
> +
> + pad_offset = network_depth + be16_to_cpu(ipv4->tot_len);
> + } else if (proto == htons(ETH_P_IPV6)) {
> + struct
From: yupeng
Date: Sun, 25 Nov 2018 23:35:46 -0800
> Add explaination of below counters:
> TcpExtTCPRcvCoalesce
> TcpExtTCPAutoCorking
> TcpExtTCPOrigDataSent
> TCPSynRetrans
> TCPFastOpenActiveFail
> TcpExtListenOverflows
> TcpExtListenDrops
> TcpExtTCPHystartTrainDetect
>
From: Sudarsana Reddy Kalluru
Date: Mon, 26 Nov 2018 02:26:56 -0800
> From: Sudarsana Reddy Kalluru
>
> The patch series add few enhancements to qed/qede drivers.
>
> Changes from previous versions:
> ---
> v3: Revert v2 changes as the other paths (i.e. ptp) access
On Tue, Nov 27, 2018 at 2:13 PM Eric Dumazet wrote:
>
>
>
> On 11/27/2018 01:58 PM, Neal Cardwell wrote:
>
> > I wonder if technically perhaps the logic should skip coalescing if
> > the tail or skb has the TCP_FLAG_URG bit set? It seems if skbs are
> > coalesced, and some have urgent data and
When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are ususally zero's, which don't affect
checksum. However, we have a switch which pads non-zero octets, this
causes kernel hardware
From: Xin Long
Date: Mon, 26 Nov 2018 14:52:44 +0800
> I changed to count sk_wmem_alloc by skb truesize instead of 1 to
> fix the sk_wmem_alloc leak caused by later truesize's change in
> xfrm in Commit 02968ccf0125 ("sctp: count sk_wmem_alloc by skb
> truesize in sctp_packet_transmit").
>
>
On 11/27/2018 03:21 PM, Cong Wang wrote:
> When an ethernet frame is padded to meet the minimum ethernet frame
> size, the padding octets are not covered by the hardware checksum.
> Fortunately the padding octets are ususally zero's, which don't affect
> checksum. However, we have a switch
From: Ioana Ciocoi Radulescu
Date: Mon, 26 Nov 2018 16:27:28 +
> Add support for XDP programs. Only XDP_PASS, XDP_DROP and XDP_TX
> actions are supported for now. Frame header changes are also
> allowed.
>
> v2: - count the XDP packets in the rx/tx inteface stats
> - add message with
From: Sudarsana Reddy Kalluru
Date: Mon, 26 Nov 2018 22:25:55 -0800
> From: Sudarsana Reddy Kalluru
>
> The patch series populates MBI and storm firware versions in the ethtool
> driver info query.
>
> Please consider applying it to 'net-next' tree.
Series applied.
On 11/27/2018 04:07 PM, Cong Wang wrote:
> On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet wrote:
>>
>> But the padding might be added on normal packets (say 1000 bytes + 3 bytes
>> of padding) ?
>
> I never see other padding cases than ETH_ZLEN. Does ethernet standard
> require padding for
On Tue, 2018-11-27 at 10:00 +, Maxim Mikityanskiy wrote:
> Hi everyone,
>
> We are experiencing an issue with Mellanox mlx5 driver, and I tracked
> it down to
> the packet_snd function in net/packet/af_packet.c.
>
> Brief description: when a socket is created by calling
> `socket(AF_PACKET,
From: Bryan Whitehead
Date: Mon, 26 Nov 2018 12:27:10 -0500
> This driver was designed to work with both LAN7430 and LAN7431.
> The only difference between the two is the LAN7431 has support
> for external phy.
>
> This change adds LAN7431 to the list of recognized devices
> supported by this
From: Heiner Kallweit
Date: Mon, 26 Nov 2018 20:24:16 +0100
> writex() has implicit barriers, that's what makes it different from
> writex_relaxed(). Therefore these calls to mmiowb() can be removed.
>
> Signed-off-by: Heiner Kallweit
Applied.
Hello all,
nobody concern about this? minor problem? :(
we saw hundreds of not closed tcp session with FIN_WAIT1 and LAST_ACK.
and easily reproduced in wifi network because of android gms... :p
i heard that gms try connect to their server to confirm wifi connection.
and they can't recieve the
On Tue, Nov 27, 2018 at 6:08 PM Willem de Bruijn
wrote:
>
> On Tue, Nov 27, 2018 at 3:32 PM Willem de Bruijn
> wrote:
> >
> > On Tue, Nov 27, 2018 at 2:58 PM Willem de Bruijn
> > wrote:
> > >
> > > On Tue, Nov 27, 2018 at 1:41 PM Maxim Mikityanskiy
> > > wrote:
> > > >
> > > > Hi everyone,
>
On Tue, Nov 27, 2018 at 5:11 PM Saeed Mahameed wrote:
>
> On Tue, 2018-11-27 at 16:07 -0800, Cong Wang wrote:
> > On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet
> > wrote:
> > > The bug here is that mlx5 csum only includes the data in IP frame.
> > >
> > > I would simply force skb->ip_summed to
On Tue, Nov 27, 2018 at 5:25 PM Eric Dumazet wrote:
>
>
>
> On 11/27/2018 04:07 PM, Cong Wang wrote:
> > On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet wrote:
>
> >>
> >> But the padding might be added on normal packets (say 1000 bytes + 3 bytes
> >> of padding) ?
> >
> > I never see other
On Tue, Nov 27, 2018 at 5:42 PM Cong Wang wrote:
>
> On Tue, Nov 27, 2018 at 5:25 PM Eric Dumazet wrote:
> >
> >
> >
> > On 11/27/2018 04:07 PM, Cong Wang wrote:
> > > On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet
> > > wrote:
> >
> > >>
> > >> But the padding might be added on normal packets
From: Roopa Prabhu
commit c7c1a1ef51ae ("bridge: colorize output and use JSON print library")
broke previous use of -c to represent compressvlans. This restores
previous use of -c to represent compressvlans. Understand the original
motivation to use -c to represent color consistently everywhere
On Tue, Nov 27, 2018 at 11:18:02PM +0100, Jakub Audykowicz wrote:
> On 2018-11-19 08:20, Xin Long wrote:
>
> > On Mon, Nov 19, 2018 at 5:49 AM Jakub Audykowicz
> > wrote:
> >> Calling send on a connected SCTP socket results in kernel panic if
> >> spp_pathmtu was configured manually before an
From: Eric Dumazet
Date: Mon, 26 Nov 2018 14:49:12 -0800
> Only one caller needs to pull TCP headers, so lets
> move __skb_pull() to the caller side.
>
> Signed-off-by: Eric Dumazet
> Acked-by: Yuchung Cheng
> ---
> v2: sent as a standalone patch.
Applied, thanks Eric.
From: Eric Dumazet
Date: Mon, 26 Nov 2018 15:05:02 -0800
> One thing that could be done without too much impact is to provide a cbext[]
> only for TCP packets in write/rtx queue, that is not in sk_buff but
> on the struct sk_buff_fclones
>
> This extra space would not be 0-initialized at
On Tue, 2018-11-27 at 16:07 -0800, Cong Wang wrote:
> On Tue, Nov 27, 2018 at 3:48 PM Eric Dumazet
> wrote:
> >
> >
> > On 11/27/2018 03:21 PM, Cong Wang wrote:
> > > When an ethernet frame is padded to meet the minimum ethernet
> > > frame
> > > size, the padding octets are not covered by the
On Tue, Nov 27, 2018 at 5:49 PM Eric Dumazet wrote:
>
>
> Sure this patch handles short frames, but I am saying the issue is
> more generic than that.
Yeah. Let's fix one problem in one patch.
I will clarify that I am only fixing short frames in v2, as I need to update
it anyway.
Thanks!
On 11/27/2018 05:09 PM, 배석진 wrote:
> Hello all,
>
> nobody concern about this? minor problem? :(
> we saw hundreds of not closed tcp session with FIN_WAIT1 and LAST_ACK.
These sessions should have a timer, and eventually disappear.
Do you have a test to demonstrate the issue ?
I know
On Mon, Nov 26, 2018 at 4:45 AM Lorenz Bauer wrote:
>
> That's what I had initially, but that makes re-using test_attr really
> awkward. Either
> you need to reset data_out_size before every call because it is used
> to return the
> buffer size,
I think that is exactly what the user of the
On 2018/11/27 下午3:04, Toshiaki Makita wrote:
On 2018/11/26 10:37, Toshiaki Makita wrote:
On 2018/11/23 1:43, David Ahern wrote:
On 11/21/18 5:53 PM, Toshiaki Makita wrote:
We really need consistency in the counters and at a minimum, users
should be able to track packet and byte counters for
From: David Ahern
Randy reported when CONFIG_PROC_FS is not enabled:
ld: net/ipv4/af_inet.o: in function `inet_init':
af_inet.c:(.init.text+0x42d): undefined reference to `raw_init'
Fix by moving the endif up to the end of the proc entries
Fixes: 6897445fb194c ("net: provide a sysctl
On 11/27/2018 08:57 PM, Eric Dumazet wrote:
>
>
> On 11/27/2018 05:09 PM, 배석진 wrote:
>> Hello all,
>>
>> nobody concern about this? minor problem? :(
>> we saw hundreds of not closed tcp session with FIN_WAIT1 and LAST_ACK.
>
> These sessions should have a timer, and eventually disappear.
>
From: David Ahern
Date: Tue, 27 Nov 2018 20:52:24 -0800
> From: David Ahern
>
> Randy reported when CONFIG_PROC_FS is not enabled:
> ld: net/ipv4/af_inet.o: in function `inet_init':
> af_inet.c:(.init.text+0x42d): undefined reference to `raw_init'
>
> Fix by moving the endif up to the
On 2018/11/28 13:03, Jason Wang wrote:
> On 2018/11/27 下午3:04, Toshiaki Makita wrote:
>> On 2018/11/26 10:37, Toshiaki Makita wrote:
>>> On 2018/11/23 1:43, David Ahern wrote:
On 11/21/18 5:53 PM, Toshiaki Makita wrote:
>> We really need consistency in the counters and at a minimum, users
1 - 100 of 137 matches
Mail list logo
