From: Mahesh Bandewar
1. scope correction for few functions that are used in single file.
2. Adjust variables that are used in fast-path to fit into single cacheline
3. Update rcv_frame() to skip shared check for frames coming over wire
Signed-off-by: Mahesh Bandewar
This change enables congestion control to update cwnd based on
not only packet cumulatively acked but also packets delivered
out-of-order. This makes congestion control robust against packet
reordering because it may raise cwnd as long as packets are being
delivered once reordering has been
A small refactoring that gets number of packets cumulatively acked
from tcp_clean_rtx_queue() directly.
Signed-off-by: Yuchung Cheng
Signed-off-by: Neal Cardwell
Signed-off-by: Eric Dumazet
---
net/ipv4/tcp_input.c | 7 +++
1
This patch changes the accounting of how many packets are
newly acked or sacked when the sender receives an ACK.
The current approach basically computes
newly_acked_sacked = (prior_packets - prior_sacked) -
(tp->packets_out - tp->sacked_out)
where prior_packets and
Quoting Tycho Andersen (tycho.ander...@canonical.com):
> Operations with the GENL_ADMIN_PERM flag fail permissions checks because
> this flag means we call netlink_capable, which uses the init user ns.
>
> Instead, let's introduce a new flag, GENL_UNS_ADMIN_PERM for operations
> which should be
The retransmission and F-RTO transmission currently happen inside
recovery state processing (tcp_fastretrans_alert) but before
congestion control. This refactoring moves the logic after both
s.t. we can determine how much to send (cwnd) before deciding what to
send.
Signed-off-by: Yuchung Cheng
Refactor and consolidate cwnd and rate updates into a new function
tcp_cong_control().
Signed-off-by: Yuchung Cheng
Signed-off-by: Neal Cardwell
Signed-off-by: Eric Dumazet
---
net/ipv4/tcp_input.c | 31
Redundant Data Bundling (RDB) is a mechanism for TCP aimed at reducing
the latency for applications sending time-dependent data.
Latency-sensitive applications or services, such as online games and
remote desktop, produce traffic with thin-stream characteristics,
characterized by small packets
RDB is a mechanism that enables a TCP sender to bundle redundant
(already sent) data with TCP packets containing new data. By bundling
(retransmitting) already sent data with each TCP packet containing new
data, the connection will be more resistant to sporadic packet loss
which reduces the
Signed-off-by: Edward Cree
---
include/uapi/linux/ethtool.h | 70
1 file changed, 64 insertions(+), 6 deletions(-)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 57fa390..3b6af3e 100644
---
Use sunvnet perf trace macros to monitor LDC message exchange state.
Signed-off-by: Sowmini Varadhan
---
drivers/net/ethernet/sun/sunvnet.c | 24 ++--
1 files changed, 22 insertions(+), 2 deletions(-)
diff --git
Add perf event macros for support of tracing and instrumentation
of LDC state machine
Signed-off-by: Sowmini Varadhan
---
include/trace/events/sunvnet.h | 139
1 files changed, 139 insertions(+), 0 deletions(-)
create mode
Added some perf tracepoints to help track and debug sunvnet
descriptor state at run-time.
Sowmini Varadhan (2):
sunvnet: Add support for perf LDC event tracing
sunvnet: perf tracepoint invocations to trace LDC state machine
drivers/net/ethernet/sun/sunvnet.c | 24 ++-
On 02.02.2016 18:34, David Herrmann wrote:
Hi
On Sun, Jan 10, 2016 at 7:54 AM, Willy Tarreau wrote:
It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.
From: Mahesh Bandewar
The mode argument was erronusly defined as u32 but it has always
been u16.
Signed-off-by: Mahesh Bandewar
---
drivers/net/ipvlan/ipvlan.h | 1 -
drivers/net/ipvlan/ipvlan_main.c | 9 ++---
2 files changed, 6 insertions(+),
From: Mahesh Bandewar
Scrub skb before hitting the iptable hooks to ensure packets hit
these hooks.
Signed-off-by: Mahesh Bandewar
---
drivers/net/ipvlan/ipvlan_core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
The existing mechanism for detecting thin streams (tcp_stream_is_thin)
is based on a static limit of less than 4 packets in flight. This treats
streams differently depending on the connections RTT, such that a stream
on a high RTT link may never be considered thin, whereas the same
application
With SWInt and TxDescUnavail interrupts now have full support interrupts
(maybe).
This new interrupts is tested on my hardware RTL 8102.For another hardware need
to
be tested.
Signed-off-by: Corcodel Marian
---
drivers/net/ethernet/realtek/r8169.c | 2 +-
1 file
On 02.02.2016 20:29, Linus Torvalds wrote:
On Tue, Feb 2, 2016 at 10:29 AM, Hannes Frederic Sowa
wrote:
Anyway, can someone provide a high-level description of what exactly
this patch is supposed to do? Which operation should be limited, who
should inflight FDs be
This patch set refactors the sequence of congestion control,
loss recovery, and transmission logic in TCP ack processing.
The design goal is to decouple and sequence them in the following order:
0. ACK accounting: free or tag sent packets [unchanged]
1. loss recovery: identify lost/ecn
From: Phil Turnbull
If nlh->nlmsg_len is zero then an infinite loop is triggered because
'skb_pull(skb, msglen);' pulls zero bytes.
The calculation in nlmsg_len() underflows if 'nlh->nlmsg_len <
NLMSG_HDRLEN' which bypasses the length validation and will later
trigger
Currently the cwnd is reduced and increased in various different
places. The reduction happens in various places in the recovery
state processing (tcp_fastretrans_alert) while the increase
happens afterward.
A better sequence is to identify lost packets and update
the congestion control state
Signed-off-by: Edward Cree
---
drivers/net/ethernet/sfc/ethtool.c | 176 +
1 file changed, 176 insertions(+)
diff --git a/drivers/net/ethernet/sfc/ethtool.c
b/drivers/net/ethernet/sfc/ethtool.c
index 0347976..49fac36 100644
---
On Tue, Feb 2, 2016 at 12:49 PM, Willy Tarreau wrote:
> On Tue, Feb 02, 2016 at 12:44:54PM -0800, Linus Torvalds wrote:
>>
>> Umm. I think the "struct cred" may change in between, can't it?
>
> You mean for example in case of setuid() or something like this ?
Yeah. I'd be worried
Hello,
On Mon, 1 Feb 2016, Salam Noureddine wrote:
> @@ -1572,8 +1582,12 @@ rollback:
> call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
> dev);
> call_netdevice_notifier(nb,
On 02.02.2016 21:44, Linus Torvalds wrote:
On Tue, Feb 2, 2016 at 12:32 PM, Hannes Frederic Sowa
wrote:
Unfortunately we never transfer a scm_cookie via the skbs but merely use it
to initialize unix_skb_parms structure in skb->cb and destroy it afterwards.
Ok, I
NEED TO CLEAN UP PATCH (likely still contains bugs...)
When enabling Receive Packet Steering (RPS) like :
echo 32768 > /proc/sys/net/core/rps_sock_flow_entries
for N in $(seq 0 7) ; do
echo 4096 > /sys/class/net/${DEV}/queues/rx-$N/rps_flow_cnt
echo f >
On Tuesday 02 February 2016 15:01:33 Franklin S Cooper Jr. wrote:
>
> Yes. Here is a boot log on the latest master with the below
> three patches reverted.
> http://pastebin.com/W7RWSHpE (Working)
>
> I reverted these three patches. The two latest patches seem
> to be trying to correct/expand
On Tuesday 02 February 2016 10:50:41 Franklin S Cooper Jr. wrote:
> Latest mainline is currently failing to boot for Keystone 2
> Hawking but I'm assuming its true for other Keystone 2
> boards. Bisect shows that this issue popped up after the
> patch "netcp: try to reduce type confusion in
On Tue, Feb 02, 2016 at 09:32:56PM +0100, Hannes Frederic Sowa wrote:
> But "struct pid *" in unix_skb_parms should be enough to get us to
> corresponding "struct cred *" so we can decrement the correct counter
> during skb destruction.
>
> So:
>
> We increment current task's unix_inflight and
On Tue, Feb 2, 2016 at 12:32 PM, Hannes Frederic Sowa
wrote:
>
> Unfortunately we never transfer a scm_cookie via the skbs but merely use it
> to initialize unix_skb_parms structure in skb->cb and destroy it afterwards.
Ok, I obviously didn't check very closely.
>
Introduce napi_gro_receive_list() which takes a full SKB-list
for processing by the stack.
It also take over invoking eth_type_trans().
One purpose is to disconnect the icache usage/sharing between
driver level RX (NAPI loop) and upper RX network stack.
Another advantage is that the stack now
Normal TX completion uses napi_consume_skb(), thus also make dummy driver
use this, as it make it easier to see the effect of bulk freeing SKBs.
---
drivers/net/dummy.c |3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index
The current logic in bond_arp_rcv will accept an incoming ARP for
validation if (a) the receiving slave is either "active" (which includes
the currently active slave, or the current ARP slave) or, (b) there is a
currently active slave, and it has received an ARP since it became active.
Hi Willy,
On 02.02.2016 21:39, Willy Tarreau wrote:
On Tue, Feb 02, 2016 at 09:32:56PM +0100, Hannes Frederic Sowa wrote:
But "struct pid *" in unix_skb_parms should be enough to get us to
corresponding "struct cred *" so we can decrement the correct counter
during skb destruction.
So:
We
On Tue, 2016-02-02 at 20:23 +0100, Bendik Rønning Opstad wrote:
> RDB is a mechanism that enables a TCP sender to bundle redundant
> (already sent) data with TCP packets containing new data. By bundling
> (retransmitting) already sent data with each TCP packet containing new
> data, the connection
On 02/02/2016 02:41 PM, Arnd Bergmann wrote:
> On Tuesday 02 February 2016 10:50:41 Franklin S Cooper Jr. wrote:
>> Latest mainline is currently failing to boot for Keystone 2
>> Hawking but I'm assuming its true for other Keystone 2
>> boards. Bisect shows that this issue popped up after the
>>
Use the newly introduced napi_alloc_skb_hint() API, to get the underlying
slab bulk allocation sizes to align with what mlx5 driver need for refilling
its RX ring queue.
Signed-off-by: Jesper Dangaard Brouer
---
drivers/net/ethernet/mellanox/mlx5/core/en.h |3 ++-
The default bulk alloc size arbitrarily choosen (to be 8) might
not suit all use-cases, this introduce a function napi_alloc_skb_hint()
that allow the caller to specify a bulk size hint they are expecting.
It is a hint because __napi_alloc_skb() limits the bulk size to
the array size.
One user is
On Tue, Feb 02, 2016 at 12:53:20PM -0800, Linus Torvalds wrote:
> On Tue, Feb 2, 2016 at 12:49 PM, Willy Tarreau wrote:
> > On Tue, Feb 02, 2016 at 12:44:54PM -0800, Linus Torvalds wrote:
> >>
> >> Umm. I think the "struct cred" may change in between, can't it?
> >
> > You mean for
There are several techniques/concepts combined in this optimization.
It is both a data-cache and instruction-cache optimization.
First of all, this is primarily about delaying touching
packet-data, which happend in eth_type_trans, until the prefetch
have had time to fetch. Thus, hopefully
Bulk alloc and free of SKBs happen transparently by the API calls
napi_alloc_skb() and napi_consume_skb().
The mlx5 driver have an extra high benefit of these changes,
because it already have a loop refilling its RX ring queue. I
considered if the alloc API should be allowed to request larger
On Tue, Feb 2, 2016 at 6:42 PM, John Fastabend
> [..] I added
> flower support to the driver with about 100lines of code fwiw I'll
> send the patch out later today,
that would be very helpful, would appreciate if you post the code that
supports flower to the list or @
On 02.02.2016 18:17, David Herrmann wrote:
Remove a write-only stack variable from unix_attach_fds(). This is a
left-over from the security fix in:
commit 712f4aad406bb1ed67f3f98d04c044191f0ff593
Author: willy tarreau
Date: Sun Jan 10 07:54:56 2016 +0100
On Tue, Feb 02, 2016 at 12:44:54PM -0800, Linus Torvalds wrote:
> On Tue, Feb 2, 2016 at 12:32 PM, Hannes Frederic Sowa
> wrote:
> > But "struct pid *" in unix_skb_parms should be enough to get us to
> > corresponding "struct cred *" so we can decrement the correct
Discovered that network stack were hitting the kmem_cache/SLUB
slowpath when freeing SKBs. Doing bulk free with kmem_cache_free_bulk
can speedup this slowpath.
NAPI context is a bit special, lets take advantage of that for bulk
free'ing SKBs.
In NAPI context we are running in softirq, which
The network stack defers SKBs free, in-case free happens in IRQ or
when IRQs are disabled. This happens in __dev_kfree_skb_irq() that
writes SKBs that were free'ed during IRQ to the softirq completion
queue (softnet_data.completion_queue).
These SKBs are naturally delayed, and cleaned up during
This patchset is relevant for my NetDev 1.1 "Network Performance BoF" [1].
The first 4 patches, is a repost[2], for the first real use-case of
kmem_cache bulk alloc and free API. They were adjusted slightly to
accomodate my last slab API changes. They should be ready for
inclusion in net-next,
Think twice before applying
- This patch can potentially introduce added latency in some workloads
This patch introduce bulk alloc of SKBs and allow reuse of SKBs
free'ed in same softirq cycle. SKBs are normally free'ed during TX
completion, but most high speed drivers also cleanup TX ring
There is an opportunity to bulk free SKBs during reclaiming of
resources after DMA transmit completes in ixgbe_clean_tx_irq. Thus,
bulk freeing at this point does not introduce any added latency.
Simply use napi_consume_skb() which were recently introduced. The
napi_budget parameter is needed
Always, when sending an updated version of a patch which is part of a
series, always resubmit the entire series rather than just the patch
which is changing.
Thanks.
Hi Byeoungwook,
On Wed, Feb 3, 2016 at 2:48 AM, Byeoungwook Kim wrote:
> rtl_*_delay() functions were reused same codes about addr variable.
> So i have converted to rtl_addr_delay() from code about addr variable.
>
> Conditional codes in rtl_addr_delay() were improved in
We simulates a link down period for RNDIS_STATUS_NETWORK_CHANGE message to
trigger DHCP renew. User daemons may need multiple seconds to trigger the
link down event. (e.g. ifplugd: 5sec, network-manager: 4sec.) So update
this link down period to 10 sec to properly trigger DHCP renew.
Hi folks,
Sometimes it is useful to ask, "what is the route for 1.2.3.4/32 if we
*exclude* routes that go out through eth8?" Currently, the only way of
doing this is to read the entire routing table in userspace, and then
reimplement all of the logic for the various tables and metrics and
complex
Signed-off-by: Jacob Keller
---
ethtool-copy.h | 8 +++-
ethtool.c | 36 +++-
2 files changed, 42 insertions(+), 2 deletions(-)
diff --git a/ethtool-copy.h b/ethtool-copy.h
index d23ffc4c38b4..620dcea06d25 100644
---
Ethtool supports a few operations for modifying and controlling
a device's RSS table. Sometimes, changes in other features of the device
may require (or desire) changes to the RSS table. Currently there is no
method to indicate to the driver whether the current RSS table settings
should be
Add support for the new dynamic flag from set_rxfh and get_rxfh. For now
the only known dynamic reason to change RSS is when number of queues is
changed. The default mode for the driver will be dynamic, indicating
that the driver is free to change its own default setting as it sees
fit. Since the
From: Nikolay Aleksandrov
Add functions which check if the speed/duplex are defined.
Signed-off-by: Nikolay Aleksandrov
Acked-by: Michael S. Tsirkin
---
v2: new patch
v3: added Michael's ack
v4: no change
From: Nikolay Aleksandrov
Hi,
Patch 1 adds ethtool speed/duplex validation functions which check if the
value is defined. Patch 2 adds support for ethtool (get|set)_settings and
uses the validation functions to check the user-supplied values.
v2: split in 2 patches
This patch series proposes the addition of a dynamic flag to the
ethtool {SG}RXFH operations. The primary reasoning for this is so that
drivers may indicate when they destroyed configured RSS settings, and
can determine when they have more liberty to remove user's settings.
The default mode shall
On Tue, Feb 2, 2016 at 11:30 AM, Kenneth Klette Jonassen
wrote:
>
> On Sat, Oct 17, 2015 at 6:57 AM, Yuchung Cheng wrote:
> > Currently ca_seq_rtt_us does not use Kern's check. Fix that by
> > checking if any packet acked is a retransmit, for both RTT used
From: Nikolay Aleksandrov
This patch allows the user to set and retrieve speed and duplex of the
virtio_net device via ethtool. Having this functionality is very helpful
for simulating different environments and also enables the virtio_net
device to participate in
Hi Jesper,
[auto build test WARNING on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Jesper-Dangaard-Brouer/net-mitigating-kmem_cache-slowpath-and-BoF-discussion-patches/20160203-051706
reproduce: make htmldocs
All warnings (new ones prefixed by >>):
On 02/02/2016 03:26 PM, Arnd Bergmann wrote:
> On Tuesday 02 February 2016 15:01:33 Franklin S Cooper Jr. wrote:
>>
>> Yes. Here is a boot log on the latest master with the below
>> three patches reverted.
>> http://pastebin.com/W7RWSHpE (Working)
>>
>> I reverted these three patches. The two
On Tuesday 02 February 2016 16:59:34 Franklin Cooper wrote:
> On 02/02/2016 03:26 PM, Arnd Bergmann wrote:
> > On Tuesday 02 February 2016 15:01:33 Franklin S Cooper Jr. wrote:
> >>
> >> Yes. Here is a boot log on the latest master with the below
> >> three patches reverted.
> >>
On Tue, Feb 02, 2016 at 10:12:01PM +0100, Jesper Dangaard Brouer wrote:
> Think twice before applying
> - This patch can potentially introduce added latency in some workloads
>
> This patch introduce bulk alloc of SKBs and allow reuse of SKBs
> free'ed in same softirq cycle. SKBs are normally
From: Roopa Prabhu
'ip monitor all' is broken on older kernels.
This patch fixes 'ip monitor all' to match
'all' and not 'all-nsid'.
It moves parsing arg 'all-nsid' to after parsing
'all'.
Before:
$ip monitor all
NETLINK_LISTEN_ALL_NSID: Protocol not available
On Tue, Feb 2, 2016 at 12:01 PM, Julian Anastasov wrote:
>> +#ifdef CONFIG_NET_NS
>> +static inline void net_add_event_list(struct list_head *head, struct net
>> *net)
>> +{
>> + if (!list_empty(>event_list))
>
> Above check looks inverted, it works may be
> because
Please excuse URL mangling, my bugzilla address appears to route through
stupid corporate firewall.
Begin forwarded message:
Date: Tue, 2 Feb 2016 18:38:41 +
From: "bugzilla-dae...@bugzilla.kernel.org"
To: "shemmin...@linux-foundation.org"
On 03.02.2016 01:57, Hannes Frederic Sowa wrote:
On 02.02.2016 23:11, Linus Torvalds wrote:
But I'm OK with that patch as is if you prefer it that way (maybe you
want
to use the cred to then test for root separately etc, out maybe there
already was done use of cred as cred that I just missed
On 02/02/2016 05:26 PM, Arnd Bergmann wrote:
> On Tuesday 02 February 2016 16:59:34 Franklin Cooper wrote:
>> On 02/02/2016 03:26 PM, Arnd Bergmann wrote:
>>> On Tuesday 02 February 2016 15:01:33 Franklin S Cooper Jr. wrote:
Yes. Here is a boot log on the latest master with the below
Hi Ariel,
I'm trying to update the bnx2x driver in Ubuntu trusty (3.13 kernel)
release to use the 7.51.10 firmware; can you help me determine which
commits need to be backported?
Some reference is in Launchpad bug 1454286:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1454286
basically,
On 02.02.2016 23:11, Linus Torvalds wrote:
[ sorry for the html mail, I'm out grocery shopping ]
On Feb 2, 2016 13:55, "Hannes Frederic Sowa"
wrote:
I slightly tested the attached patch.
Looks fine. I do wonder: if the only thing we use that "struct cred" for is
The commit referenced in the Fixes tag incorrectly accounted the number
of in-flight fds over a unix domain socket to the original opener
of the file-descriptor. This allows another process to arbitrary
deplete the original file-openers resource limit for the maximum of
open files. Instead the
From: Eric Dumazet
Silence lockdep false positive about rcu_dereference() being
used in the wrong context.
First one should use rcu_dereference_protected() as we own the spinlock.
Second one should be a normal assignation, as no barrier is needed.
Fixes: 18367681a10bd
On (02/01/16 19:56), Alexander Duyck wrote:
> > @@ -394,7 +407,7 @@ ip_proto_again:
> >data, hlen, &_eth);
> > if (!eth)
> > goto out_bad;
> > - proto = eth->h_proto;
>
This series adds support for steering IPv6 flows using the ethtool NFC
interface, and implements it for sfc devices.
Tested using an in-development patch to the ethtool utility.
Edward Cree (2):
ethtool: add IPv6 to the NFC API
sfc: implement IPv6 NFC (and IPV4_USER_FLOW)
On Sat, Oct 17, 2015 at 6:57 AM, Yuchung Cheng wrote:
> Currently ca_seq_rtt_us does not use Kern's check. Fix that by
> checking if any packet acked is a retransmit, for both RTT used
> for RTT estimation and congestion control.
>
*snip*
This patch (commit 9e45a3e) puzzles
On Tue, Feb 2, 2016 at 10:29 AM, Hannes Frederic Sowa
wrote:
>>
>> Anyway, can someone provide a high-level description of what exactly
>> this patch is supposed to do? Which operation should be limited, who
>> should inflight FDs be accounted on, and which rlimit
===
[ INFO: suspicious RCU usage. ]
4.5.0-rc2-think+ #2 Tainted: GW
---
net/ipv6/ip6_flowlabel.c:543 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks =
On 02/02/2016 09:40 PM, kbuild test robot wrote:
drivers/net/wireless/realtek/rtlwifi/core.c:59:2-3: Unneeded semicolon
Remove unneeded semicolon.
Generated by: scripts/coccinelle/misc/semicolon.cocci
CC: Byeoungwook Kim
Signed-off-by: Fengguang Wu
Replace 'goto' with 'return' to remove unnecessary check at label:
err_undo_flags.
Signed-off-by: Zhang Shengju
---
drivers/net/bonding/bond_main.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c
3.13.11-ckt34 -stable review patch. If anyone has any objections, please let
me know.
---8<
From: Vijay Pandurangan
[ Upstream commit ce8c839b74e3017996fad4e1b7ba2e2625ede82f ]
Packets that arrive from real
Hello,
On Mon, 1 Feb 2016, Salam Noureddine wrote:
> +#ifdef CONFIG_NET_NS
> +static inline void net_add_event_list(struct list_head *head, struct net
> *net)
> +{
> + if (!list_empty(>event_list))
Above check looks inverted, it works may be
because
The driver decrements its vlan count without checking if it is really
present in its list. This results in an invalid vlan count and impacts
subsequent vlan add/rem ops. The function be_vlan_rem_vid() should be
updated to fix this.
Signed-off-by: Sriharsha Basavapatna
From: Somnath Kotur
The CMD_SUBSYSTEM_LOWLEVEL cmds need DEV_CFG Privilege to run
which VFs don't have by default.
Self-tests need to be issued only for PFs.
Signed-off-by: Somnath Kotur
Signed-off-by: Sriharsha Basavapatna
From: Padmanabh Ratnakar
Interrupt moderation parameters need to be recalculated only
after a time interval of 1 ms. Interval calculation is wrong
when there is a rollover of jiffies. Using recommended way of interval
calculation using jiffies to fix this.
From: Padmanabh Ratnakar
After error is detected, wait for adapter to move to ready state
before destroying queues and cleanup of other resources. Also
skip performing any cleanup for non-Lancer chips and move debug
messages to correct routine.
Signed-off-by:
From: Suresh Reddy
be_set_phys_id() returns 0 to ethtool when the command fails in the FW.
This patch fixes the set_phys_id() to return -EIO in case the FW cmd fails.
Signed-off-by: Suresh Reddy
Signed-off-by: Sriharsha Basavapatna
From: Padmanabh Ratnakar
Retry error recovery MAX_ERR_RECOVERY_RETRY_COUNT times in case of
failure during error recovery.
Signed-off-by: Padmanabh Ratnakar
Signed-off-by: Sriharsha Basavapatna
From: Suresh Reddy
The driver currently logs the message "VF is not privileged to issue
opcode" by checking only the base_status field for UNAUTHORIZED_REQUEST.
Add check to look for INSUFFICIENT_PRIVILEGES in the additional status
field also as not all cmds fail with
The SRIOV resource distribution logic for RX/TX queue counts is not optimal
when a small number of VFs are enabled. It does not take into account the
VF's EQ count while computing the queue counts. Because of this, the VF
gets a large number of queues, though it doesn't have sufficient EQs,
v2 changes:
Patch-4:Changed a tab to space in be.h
Patches-6,7,8: Updated commit log summary line: benet --> be2net
Hi David,
The following patch set contains a few non-critical bug fixes. Please
consider applying this to the net-next tree. Thanks.
Patch-1 fixes
Conditional codes in rtl_addr_delay() were improved in readability and
performance by using switch codes.
Reviewed-by: Julian Calaby
Signed-off-by: Byeoungwook Kim
Signed-off-by: Fengguang Wu
---
V3 remove unneeded
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
arch/arm64/boot/dts/apm/apm-shadowcat.dtsi | 8 +++-
arch/arm64/boot/dts/apm/apm-storm.dtsi | 8
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
drivers/net/ethernet/apm/xgene/Makefile | 3 +-
drivers/net/ethernet/apm/xgene/xgene_enet_cle.c
Signed-off-by: Nikolay Borisov
---
include/net/netns/ipv4.h | 2 ++
include/net/tcp.h | 1 -
net/ipv4/sysctl_net_ipv4.c | 18 +-
net/ipv4/tcp.c | 3 ++-
net/ipv4/tcp_ipv4.c| 2 ++
net/ipv4/tcp_timer.c | 4 ++--
6 files
Signed-off-by: Nikolay Borisov
---
include/net/netns/ipv4.h| 1 +
include/net/tcp.h | 1 -
net/ipv4/inet_connection_sock.c | 7 ++-
net/ipv4/sysctl_net_ipv4.c | 14 +++---
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_timer.c
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
drivers/net/ethernet/apm/xgene/xgene_enet_cle.c | 11 +-
drivers/net/ethernet/apm/xgene/xgene_enet_main.c
This patch series continues making more of the tcp-related
sysctl knobs be per net-namespace. Most of these apply per
socket and have global defaults so should be safe and I
don't expect any breakages.
Having those per net-namespace is useful when multiple
containers are hosted and it is
1 - 100 of 263 matches
Mail list logo