Try to carry error messages to the user via the netlink extended
ack message attribute.
Signed-off-by: Jakub Kicinski
---
drivers/net/virtio_net.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 82f1c3a7334
Drivers usually have a number of restrictions for running XDP
- most common being buffer sizes, LRO and number of rings.
Even though some drivers try to be helpful and print error
messages experience shows that users don't often consult
kernel logs on netlink errors. Try to use the new extended
ac
Try to carry error messages to the user via the netlink extended
ack message attribute.
Signed-off-by: Jakub Kicinski
---
drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 ++-
.../net/ethernet/netronome/nfp/nfp_net_common.c| 22 +-
.../net/ethernet/netronome/nfp/nf
As we propagate extended ack reporting throughout various paths in
the kernel it may be that the same function is called with the
extended ack parameter passed as NULL. One place where that happens
is in drivers which have a centralized reconfiguration function
called both from ndos and from ethto
Hi!
This series is an attempt to make XDP more user friendly by
enabling exploiting the recently added netlink extended ACK
reporting to carry messages to user space.
David Ahern's iproute2 ext ack patches for ip link are sufficient
to show the errors like this:
# ip link set dev p4p1 xdp obj
From:
Date: Sun, 30 Apr 2017 19:47:14 +0300
> From: Ido Schimmel
>
> When a netdev is enslaved to a VRF master, its router interface (RIF)
> needs to be destroyed (if exists) and a new one created using the
> corresponding virtual router (VR).
>
> From the driver's perspective, the above is eq
From: Johan Hedberg
Date: Sun, 30 Apr 2017 17:09:28 +0300
> Here's one last batch of Bluetooth patches in the bluetooth-next tree
> targeting the 4.12 kernel.
>
> - Remove custom ECDH implementation and use new KPP API instead
> - Add protocol checks to hci_ldisc
> - Add module license to HCI
From: Saeed Mahameed
Date: Sun, 30 Apr 2017 16:20:01 +0300
> This series contains two sets of patches to the mlx5 driver,
> 1. Nine patches (mostly from Hadar) to add 'mlx5 neigh update' feature.
> 2. Six misc patches.
>
> For more details please see below.
>
> Sorry for the last minute submiss
From: Yuval Mintz
Date: Sun, 30 Apr 2017 12:14:44 +0300
> After removing the PTP related initialization from slowpath start,
> the remaining PTT entry is required only in case CONFIG_RFS_ACCEL is set.
> Otherwise, it leads to a warning due to it being unused.
>
> Fixes: d179bd1699fc ("qed: Acqui
From: Yuval Mintz
Date: Sun, 30 Apr 2017 11:49:04 +0300
> This series contains multiple small corrections to the RoCE logic
> in qed plus some debug information and inter-module parameter
> meant to prevent issues further along.
>
> - #1, #6 Share information with protocol driver
>[either n
From: Alexei Starovoitov
Date: Sat, 29 Apr 2017 22:52:42 -0700
> From: Yonghong Song
>
> llvm 4.0 and above generates the code like below:
>
> 440: (b7) r1 = 15
> 441: (05) goto pc+73
> 515: (79) r6 = *(u64 *)(r10 -152)
> 516: (bf) r7 = r10
> 517: (07) r7 += -112
> 518: (bf) r2 = r7
> 519:
From: Abhishek Shah
Date: Sun, 30 Apr 2017 11:04:21 +0530
> This patch allows users to enable/disable internal TX and/or RX
> clock delay for BCM5481x series PHYs so as to satisfy RGMII timing
> specifications.
>
> On a particular platform, whether TX and/or RX clock delay is required
> depends
From: Colin King
Date: Sat, 29 Apr 2017 22:38:57 +0100
> From: Colin Ian King
>
> trivial fix to spelling mistakes in printk message.
>
> Signed-off-by: Colin Ian King
Applied.
Please, Gao, submit this as a proper, numbered, patch series
with a proper header posting.
That way you can explain why you took this strategy to fix
this problem, compared to your original approach.
Thanks.
From: Al Viro
Date: Sat, 29 Apr 2017 21:48:23 +0100
> On Sat, Apr 29, 2017 at 05:37:38PM +0800, Ding Tianhong wrote:
>
>> Looks good, if so, we don't need the csum_error any more,
>
> Acked-by: Al Viro
>
> Dave, I could put that through my tree, but I think it would be better off
> in net.git
From: Scott Wood
Date: Fri, 28 Apr 2017 19:17:41 -0500
> The bnx2x driver is not providing proper alignment on the receive buffers it
> passes to build_skb(), causing skb_shared_info to be misaligned.
> skb_shared_info contains an atomic, and while PPC normally supports
> unaligned accesses, it d
From: Eric Anholt
Date: Fri, 28 Apr 2017 15:22:03 -0700
> Cygnus is a small family of SoCs, of which we currently have
> devicetree for BCM11360 and BCM58300. The 11360's B53 is mostly the
> same as 58xx, just requiring a tiny bit of setup that was previously
> missing.
>
> v2: Reorder the entr
From: Arkadi Sharshevsky
Date: Fri, 28 Apr 2017 22:39:07 +0300
> Commit 7e26bf45e4cb ("net: bridge: allow SW learn to take over HW fdb
> entries") added the ability to "take over an entry which was previously
> learned via HW when it shows up from a SW port".
>
> However, if an entry was learned
From: David Ahern
Date: Fri, 28 Apr 2017 11:06:25 -0700
> NETDEV_CHANGEINFODATA was added by d4261e5650004 ("bonding: create
> netlink event when bonding option is changed"). RTM_NEWLINK
> messages are already created on changelink events, so this event
> is just a duplicate. Remove it.
>
> Cc:
From: Cong Wang
Date: Fri, 28 Apr 2017 10:04:29 -0700
> After commit 1215e51edad1 ("ipv4: fix a deadlock in ip_ra_control")
> we always take RTNL lock for ip_ra_control() which is the only place
> we update the list ip_ra_chain, so the ip_ra_lock is no longer needed.
>
> As Eric points out, BH d
From: Dan Carpenter
Date: Fri, 28 Apr 2017 16:03:48 +0300
> We recently added a check to see if nla_nest_start() fails. There are
> two issues with that. First, if it fails then I don't think we should
> call nla_nest_cancel(). Second, it's slightly convoluted but the
> current code returns su
From: Jesper Dangaard Brouer
Date: Fri, 28 Apr 2017 16:25:04 +0200
> The struct bpf_map_def was extended in commit fb30d4b71214 ("bpf: Add tests
> for map-in-map") with member unsigned int inner_map_idx. This changed the
> size
> of the maps section in the generated ELF _kern.o files.
>
> Unfo
From: Dan Carpenter
Date: Fri, 28 Apr 2017 15:57:15 +0300
> Presumably we never hit this return, but static checkers complain that
> we need to unlock so we may as well fix that.
>
> Signed-off-by: Dan Carpenter
Applied.
From: Dan Carpenter
Date: Fri, 28 Apr 2017 15:56:09 +0300
> My static checker complains that we're holding a mutex on this error
> path. Let's goto exit instead of returning directly.
>
> Fixes: b0bccb69eba3 ("qed: Change locking scheme for VF channel")
> Signed-off-by: Dan Carpenter
Applied.
From: Yankejian
Date: Fri, 28 Apr 2017 14:49:45 +0800
> From: lipeng
>
> This patchset add support defered dsaf probe when mdio and
> mbigen module is not insmod.
>
> For more details, please refer to individual patch.
Series applied, thanks.
From: Jakub Kicinski
Date: Thu, 27 Apr 2017 21:06:14 -0700
> This series optimizes the nfp XDP TX performance a little bit.
> I run quick tests on an Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz.
> Single core/queue performance for both touch and drop and touch and
> forward is above 20Mpps @64B
From: Karim Eshapa
Date: Fri, 28 Apr 2017 03:48:59 +0200
> Use time_before_eq for time comparison more safe and dealing
> with timer wrapping to be future-proof.
>
> Signed-off-by: Karim Eshapa
Subject line has way too many subsystem prefixes, simply
"benet: " is sufficient.
And in situations
From: Girish Moodalbail
Date: Thu, 27 Apr 2017 14:11:53 -0700
> Creating a geneve link with 'udpcsum' set results in a creation of link
> for which UDP checksum will NOT be computed on outbound packets, as can
> be seen below.
>
> 11: gen0: mtu 1500 qdisc noop state DOWN
> link/ether c2:85:
From: Willem de Bruijn
Date: Thu, 27 Apr 2017 20:37:58 -0400
> From: Willem de Bruijn
>
> Avoid hashing the tx napi struct into napi_hash[], which is used for
> busy polling receive queues.
>
> Signed-off-by: Willem de Bruijn
Applied.
From: David Howells
Date: Thu, 27 Apr 2017 22:40:23 +0100
> Initialise init_net.count to 1 for its pointer from init_nsproxy lest
> someone tries to do a get_net() and a put_net() in a process in which
> current->ns_proxy->net_ns points to the initial network namespace.
>
> Signed-off-by: David
From: Jiri Benc
Date: Thu, 27 Apr 2017 21:24:34 +0200
> This patchset fixes a bug with metadata based tunnels when booted with
> ipv6.disable=1.
Series applied, thanks.
From: Andy Shevchenko
Date: Thu, 27 Apr 2017 16:37:01 +0300
> From: Andy Shevchenko
>
> Replace pattern
>
> int status;
> ...
> status = func(...);
> return status;
>
> by
>
> return func(...);
>
> No functional change intented.
>
> Signed-off-by: Andy Shevchenko
Applied.
From: Andy Shevchenko
Date: Thu, 27 Apr 2017 16:36:59 +0300
> From: Andy Shevchenko
>
> Use scnprintf() when printing version instead of custom open coded variants.
>
> Signed-off-by: Andy Shevchenko
Applied.
From: Andy Shevchenko
Date: Thu, 27 Apr 2017 16:37:00 +0300
> From: Andy Shevchenko
>
> Reuse bnx2x_null_format_ver() in functions where it's appropriated
> instead of open coded variant.
>
> Signed-off-by: Andy Shevchenko
Applied.
From: Marc Kleine-Budde
Date: Thu, 27 Apr 2017 09:54:33 +0200
> this is a pull request of 1 patch for net-next/master.
>
> This patch by Oliver Hartkopp fixes the build of the broad cast manager
> with CONFIG_PROC_FS disabled.
Pulled, thanks!
From: Chenbo Feng
Date: Wed, 26 Apr 2017 16:41:23 -0700
> From: Chenbo Feng
>
> The description inside uapi/linux/bpf.h about bpf_get_socket_uid
> helper function is no longer valid. It returns overflowuid rather
> than 0 when failed.
>
> Signed-off-by: Chenbo Feng
Applied.
From: Davide Caratti
Date: Wed, 26 Apr 2017 19:07:35 +0200
> avoid direct access to sk->sk_state when tcp_poll() is called on a socket
> using active TCP fastopen with deferred connect. Use local variable
> 'state', which stores the result of sk_state_load(), like it was done in
> commit 00fd38d9
From: Eric Dumazet
Date: Wed, 26 Apr 2017 09:09:23 -0700
> From: Eric Dumazet
>
> While testing a fix [1] in ___pskb_trim(), addressing the WARN_ON_ONCE()
> in skb_try_coalesce() reported by Andrey, I found that we had an skb
> with skb->sk set but no skb->destructor.
>
> This invalidated heur
From: Alexandre Belloni
Date: Wed, 26 Apr 2017 12:06:28 +0200
> Since 83a77e9ec415, the phydev irq is explicitly set to PHY_POLL when
> there is no pdata. It doesn't work on DT enabled platforms because the
> phydev irq is already set by libphy before.
>
> Fixes: 83a77e9ec415 ("net: macb: Added
This work adds BPF_XADD for BPF_W/BPF_DW to the arm64 JIT and therefore
completes JITing of all BPF instructions, meaning we can thus also remove
the 'notyet' label and do not need to fall back to the interpreter when
BPF_XADD is used in a program!
This now also brings arm64 JIT in line with x86_6
On 04/29/2017 10:34 PM, Abhishek Shah wrote:
> This patch allows users to enable/disable internal TX and/or RX
> clock delay for BCM5481x series PHYs so as to satisfy RGMII timing
> specifications.
>
> On a particular platform, whether TX and/or RX clock delay is required
> depends on how PHY co
On 4/28/17 3:40 PM, Jesper Dangaard Brouer wrote:
> [...]
>> diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
>> index 0d449d8032d1..d4433a47e6c3 100644
>> --- a/samples/bpf/bpf_load.c
>> +++ b/samples/bpf/bpf_load.c
>> @@ -563,7 +563,7 @@ struct ksym *ksym_search(long key)
>> retu
On 4/30/17 12:04 AM, Stephen Hemminger wrote:
> On Sat, 29 Apr 2017 20:48:50 -0700
> David Ahern wrote:
>
>> Kernel now supports more than 2 labels. Increase ip to
>> handle up to 16 labels.
>>
>> Signed-off-by: David Ahern
>> ---
>> include/utils.h | 8
>> lib/utils.c | 2 +-
>> 2
From: K. Y. Srinivasan
Fix the rescind handling. This patch addresses the following rescind
scenario that is currently not handled correctly:
If a rescind were to be received while the offer is still being
peocessed, we will be blocked indefinitely since the rescind message
is handled on the sam
From: K. Y. Srinivasan
The current code unconditionally sends an IPI. If we are running on the
correct CPU and are in interrupt level, we don't need an IPI.
Make this adjustment.
Signed-off-by: K. Y. Srinivasan
---
drivers/hv/hyperv_vmbus.h |4
1 files changed, 4 insertions(+), 0 dele
From: K. Y. Srinivasan
ENOBUFS is a more approrpiate error code to be returned
when the hypervisor cannot post the message because of
insufficient buffers. Make the adjustment.
Signed-off-by: K. Y. Srinivasan
---
drivers/hv/connection.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(
From: Vitaly Kuznetsov
Paths can be up to PATH_MAX long and PATH_MAX is usually greater than 256.
While on it, simplify path reconstruction to a simple snprintf(), define
and reuse KVP_NET_DIR.
Suggested-by: Tomas Hozza
Signed-off-by: Vitaly Kuznetsov
Signed-off-by: K. Y. Srinivasan
---
tool
From: Long Li
The host may send multiple negotiation packets
(due to timeout) before the KVP user-mode daemon
is connected. KVP user-mode daemon is connected.
We need to defer processing those packets
until the daemon is negotiated and connected.
It's okay for guest to respond
to all negotiation
From: Alex Ng
If a FREEZE operation takes too long, the driver may time out and move on
to another operation. The daemon is unaware of this and attempts to
notify the driver that the FREEZE succeeded. This results in an error from
the driver and the daemon leaves the filesystem in frozen state.
From: K. Y. Srinivasan
Miscellaneous fixes to vmbus and util drivers.
Alex Ng (1):
Tools: hv: vss: Thaw the filesystem and continue if freeze call has
timed out
K. Y. Srinivasan (3):
Drivers: hv: vmbus: Fix error code returned by vmbus_post_msg()
Drivers: hv: util: Make hv_poll_channe
On 17-04-29 06:04 PM, Alexei Starovoitov wrote:
> On 4/28/17 3:58 AM, Jesper Dangaard Brouer wrote:
>> On Thu, 27 Apr 2017 16:31:14 -0700
>> Alexei Starovoitov wrote:
>>
>>> On 4/27/17 1:41 AM, Jesper Dangaard Brouer wrote:
When registering/attaching a XDP/bpf program, we would just send the
From: Alexei Starovoitov
Date: Sat, 29 Apr 2017 23:44:59 -0700
> '-g' still doesn't seem to work:
> /w/binutils-gdb/bld/binutils/objdump: invalid relocation type 10
> /w/binutils-gdb/bld/binutils/objdump: BFD (GNU Binutils)
> 2.28.51.20170429 assertion fail ../../bfd/elf64-bpf.c:139
>0: 18 01
From: Ido Schimmel
When a netdev is enslaved to a VRF master, its router interface (RIF)
needs to be destroyed (if exists) and a new one created using the
corresponding virtual router (VR).
>From the driver's perspective, the above is equivalent to an inetaddr
event sent for this netdev. Therefo
On Fri, 2017-04-28 at 10:04 -0700, Cong Wang wrote:
> After commit 1215e51edad1 ("ipv4: fix a deadlock in ip_ra_control")
> we always take RTNL lock for ip_ra_control() which is the only place
> we update the list ip_ra_chain, so the ip_ra_lock is no longer needed.
>
> As Eric points out, BH does
On Fri, 28 Apr 2017 16:09:13 -0400 (EDT)
David Miller wrote:
> From: Stephen Hemminger
> Date: Wed, 26 Apr 2017 16:58:30 -0700
>
> > This fixes a race where vmbus callback for new packet arriving
> > could occur before NAPI is initialized. Happens more on WS2008
> > which takes longer to setup
This is mainly a synchronization point, I still need to look
more deeply into Alexei's -g issue.
New in this version from v3:
- Remove tailcall from opcode table
- Rearrange relocations so that numbers match with LLVM ones
- Emit relocs properly so that dwarf2 debug info tests pass
- Handle n
Hi,
On Sun, Apr 30, 2017 at 10:14:20AM -0500, Adam Ford wrote:
> On Wed, Apr 5, 2017 at 1:30 PM, Rob Herring wrote:
> > This series adds serdev support to the HCI LL protocol used on TI BT
> > modules and enables support on HiKey board with with the WL1835 module.
> > With this the custom TI UIM
From: Alexei Starovoitov
Date: Sat, 29 Apr 2017 23:44:59 -0700
> On 4/29/17 7:37 PM, David Miller wrote:
>> BTW, should I just remove tailcall from the opcode table altogether?
>
> yeah. tailcall is not a special opcode from user space point of view.
> Only after normal call with func_id=bpf_tai
From: Jeff Kirsher
Date: Sun, 30 Apr 2017 06:24:38 -0700
> This series contains updates to i40e and i40evf only.
...
> The following are changes since commit
> c08bac03d2894113bdb114e66e6ada009defb120:
> Merge branch '10GbE' of
> git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-que
From: Jeff Kirsher
Date: Sun, 30 Apr 2017 05:36:10 -0700
> This series contains updates to e1000e only.
>
> Jarod Wilson fixes an issue where the workaround for 82574 & 82583
> is needed for i218 as well, so set the appropriate flags.
>
> Sasha adds support for the upcoming new i219 devices for
From: Andy Shevchenko
Date: Sun, 30 Apr 2017 15:58:18 +0300
> On Sun, Apr 30, 2017 at 11:16 AM, Mintz, Yuval wrote:
>>> From: Andy Shevchenko
>>>
>>> Use scnprintf() when printing version instead of custom open coded variants.
>>>
>>> Signed-off-by: Andy Shevchenko
>>
>> Hi Andy this seems cor
From: Alexei Starovoitov
Date: Sat, 29 Apr 2017 23:44:59 -0700
> On 4/29/17 7:37 PM, David Miller wrote:
>> From: David Miller
>> Date: Sat, 29 Apr 2017 22:24:50 -0400 (EDT)
>>
>>> Some of your bugs should be fixed by this patch below, I'll add
>>> test cases soon:
>>
>> Ok, here are all the loc
From: Alexei Starovoitov
Date: Sat, 29 Apr 2017 23:35:30 -0700
> On 4/29/17 11:38 AM, David Miller wrote:
>> or, taking it one step further, do the following since we know this
>> maps to a 32-bit FD:
>>
>> mov32 r1, %map(hash_map)
>
> hence this approach won't work without serious elf lo
On Wed, Apr 5, 2017 at 1:30 PM, Rob Herring wrote:
> This series adds serdev support to the HCI LL protocol used on TI BT
> modules and enables support on HiKey board with with the WL1835 module.
> With this the custom TI UIM daemon and btattach are no longer needed.
Without UIM daemon, what inst
On 17-04-30 09:51 AM, Jamal Hadi Salim wrote:
[..]
1. As things stand, without this patch-set, flower does not differentiate
between a packet truncated at the end of the IP header and a packet
with
zero ports. Likewise for icmp type and code of zero.
The first three patches of this se
From: Jamal Hadi Salim
Generic bitflags attribute content sent to the kernel by user.
With this type the user can either set or unset a flag in the
kernel.
The nla_flag_values is a bitmap that defines the values being set
The nla_flag_selector is a bitmask that defines which value is legit
A ch
From: Boris Pismenny
syntax:
ip xfrm state offload dev dir
Example to add inbound offload:
ip xfrm state offload dev mlx0 dir in
Example to add outbound offload:
ip xfrm state offload dev mlx0 dir out
Signed-off-by: Boris Pismenny
Signed-off-by: Ilan Tayari
---
ip/ipxfrm
Hi Dave,
Here's one last batch of Bluetooth patches in the bluetooth-next tree
targeting the 4.12 kernel.
- Remove custom ECDH implementation and use new KPP API instead
- Add protocol checks to hci_ldisc
- Add module license to HCI UART Nokia H4+ driver
- Minor fix for 32bit user space - 64
Jiri,
With "goto chain X" this will have to be more generalized. Maybe
we have 0xAXXX Where "A" recognizes the extension with
current values ACT_JUMP(0x1) and GOTO_CHAIN(maybe 0x2)
and the rest "XXX" is a free floating parameter values
which carry the goto count for ACT_JUMP and GOTO_CHAI
On 17-04-28 10:14 AM, Simon Horman wrote:
On Fri, Apr 28, 2017 at 09:41:00AM -0400, Jamal Hadi Salim wrote:
On 17-04-28 09:11 AM, Simon Horman wrote:
[..]
A default lower prio match all on udp or icmp?
I'm certainly not opposed to exploring ideas here.
The way that flower currently works is
From: Ilan Tayari
Current code silently ignores driver errors when configuring
IPSec offload xfrm_state, and falls back to host-based crypto.
Fail the xfrm_state creation if the driver has an error, because
the NIC offloading was explicitly requested by the user program.
This will communicate b
From: Ilan Tayari
Both esp_output and esp_xmit take a pointer to the ESP header
and place it in esp_info struct prior to calling esp_output_head.
Inside esp_output_head, the call to esp_output_udp_encap
makes sure to update the pointer if it gets invalid.
However, if esp_output_head itself calls
From: Jacob Keller
The flag used by the common code and PF code is I40E_FLAG_FD_ATR_ENABLED,
not *FDIR*. It turns out none of the txrx code actually shared with the
VF driver actually checks the ATR flag. This is made even more obvious
by the typo in the VF header file.
Let's just remove the fla
From: Jacob Keller
The hw_disabled_flags field was added as a way of signifying that
a feature was automatically or temporarily disabled. However, we
actually only use this for FDir features. Replace its use with new
_AUTO_DISABLED flags instead. This is more readable, because you aren't
setting
From: Alexander Duyck
This patch corrects a major oversight in that we were not reprogramming the
ports after a reset. As a result we completely lost all of the Rx tunnel
offloads on receive including Rx checksum, RSS on inner headers, and ATR.
The fix for this is pretty standard as all we need
From: Jacob Keller
When allocating a large number of VFs, the driver previously used
i40e_reset_vf in a sequence. Just as when performing a normal reset,
this accumulates a large amount of delay for handling all of the VFs in
sequence. This delay is mainly due to a hardware requirement to wait
af
From: Jacob Keller
We already set pairs to the value of adapter->num_active_queues. This
value is limited by vsi_res->num_queue_pairs and num_online_cpus(). This
means that pairs by definition is already smaller than
num_online_cpus()*2, so we don't even need to bother with this check.
Lets just
From: Arnd Bergmann
On architectures with larger pages, we get a warning about an unused variable:
drivers/net/ethernet/intel/i40evf/i40evf_main.c: In function
'i40evf_configure_rx':
drivers/net/ethernet/intel/i40evf/i40evf_main.c:690:21: error: unused variable
'netdev' [-Werror=unused-variabl
From: Jacob Keller
The delay was added because of a desire to ensure that the VF driver can
finish up removing. However, pci_disable_sriov already has its own
ssleep() call that will sleep for an entire second, so there is no
reason to add extra delay on top of this by using msleep here. In
pract
From: Jacob Keller
Avoid using the same named flags for both vsi->state and pf->state. This
makes code review easier, as it is more likely that future authors will
use the correct state field when checking bits. Previous commits already
found issues with at least one check, and possibly others ma
From: Jacob Keller
Just as we do in i40e_reset_all_vfs, save some time when freeing VFs by
amortizing the wait time for stopping queues. We can use
i40e_vsi_stop_rings_no_wait() to begin the process of stopping all the
VF rings at once. Then, once we've started the process on each VF we can
begin
From: Jacob Keller
This matches the ordering of how we free stuff during reset and remove.
It also makes logical sense because we set the interrupts based on the
number of queues. Currently this doesn't really matter in practice.
However a future patch moves the assignment of num_active_queues in
From: Jacob Keller
Instead of assuming our flags fit within an unsigned long, use
DECLARE_BITMAP which will ensure that we always allocate enough space.
Additionally, use __I40E_STATE_SIZE__ markers as the last element of the
enumeration so that the size of the BITMAP is compile-time assigned
rat
This series contains updates to i40e and i40evf only.
Jake provides majority of the changes in this series, starting with the
renaming of a flag to avoid confusion. Then renamed a variable to a
more meaningful name to clarify what is actually being done and to
reduce confusion. Amortizes the wai
From: Jacob Keller
These flags represent the state of the VF at various times. Do not
spell them as _STAT_ which can be confusing to readers who may think
these refer to statistics.
Change-ID: I6bc092cd472e8276896a1fd7498aced2084312df
Signed-off-by: Jacob Keller
Tested-by: Andrew Bowers
Signed
From: Jacob Keller
The .index field of i40e_udp_port_config represents the udp port number.
Rename this variable to port so that it is more obvious.
Signed-off-by: Jacob Keller
Tested-by: Andrew Bowers
Signed-off-by: Jeff Kirsher
---
drivers/net/ethernet/intel/i40e/i40e.h | 2 +-
drive
From: Tariq Toukan
CQE ownership indication is as small as a single bit.
Use u8 to speedup the comparison.
Signed-off-by: Tariq Toukan
Cc: kernel-t...@fb.com
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deleti
From: Eli Cohen
struct esw_mc_addr is a small struct that can be part of struct
mlx5_eswitch. Define it as a field and not as a pointer and save the
kzalloc call and then error flow handling.
Signed-off-by: Eli Cohen
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx5/core/es
From: Hadar Hen Zion
The nud_state and hardware address fields are protected by the neighbour
lock, we should acquire it before accessing those parameters.
Use this lock to avoid inconsistency between the neighbour validity state
and it's hardware address.
Signed-off-by: Hadar Hen Zion
Reviewe
From: Hadar Hen Zion
Add hash table to the representors which is to be used by the next patch
to save neighbours information in the driver.
In order to offload IP tunnel encapsulation rules, the driver must find
the tunnel dst neighbour according to the output device and the
destination address
From: Hadar Hen Zion
When IP tunnel encapsulation rules are offloaded, the kernel can't see
the traffic of the offloaded flow. The neighbour for the IP tunnel
destination of the offloaded flow can mistakenly become STALE and
deleted by the kernel since its 'used' value wasn't changed.
To make su
From: Hadar Hen Zion
In order to offload TC encap rules, the driver does a lookup for the IP
tunnel neighbour according to the output device and the destination IP
given by the user.
To keep tracking after the validity state of such neighbours, we keep
the neighbours information (pair of device
From: Tariq Toukan
"prefetchw()" prefetches the cacheline for write. Use it for
skb->data, as soon we'll be copying the packet header there.
Performance:
Single-stream packet-rate tested with pktgen.
Packets are dropped in tc level to zoom into driver data-path.
Larger gain is expected for small
From: Tariq Toukan
UMR operations are more frequent and important.
Check them first, and add a compiler branch predictor hint.
According to current design, ICOSQ CQ can contain at most one
pending CQE per napi. Poll function is optimized accordingly.
Performance:
Single-stream packet-rate teste
From: Hadar Hen Zion
The user can change delay_first_probe_time parameter through sysctl.
Listen to NETEVENT_DELAY_PROBE_TIME_UPDATE notifications and update the
intervals for updating the neighbours 'used' value periodic task and
for flow HW counters query periodic task.
Both of the intervals wi
From: Eran Ben Elisha
We will activate the HW LRO only on servers with PCI BW > MAX LINK BW,
or when PCI BW > 16Gbps. On other cases we do not want LRO by default as
LRO sessions might get timeout and add redundant software overhead.
Tested:
ethtool -k | grep large-receive-offload
Hi Dave,
This series contains two sets of patches to the mlx5 driver,
1. Nine patches (mostly from Hadar) to add 'mlx5 neigh update' feature.
2. Six misc patches.
For more details please see below.
Sorry for the last minute submission, originally I planned to submit before
weekend, but in order
From: Or Gerlitz
The encap entry structure isn't manipulated by the eswitch code,
hence it can/needs to be removed from the eswitch header.
Do that, and change it to have mlx5e_ prefix.
This patch doesn't change any functionality.
Signed-off-by: Or Gerlitz
Signed-off-by: Saeed Mahameed
---
From: Hadar Hen Zion
Instead of relaying on the 'flow->rule' pointer value which can be
valid or invalid (in case the FW returns an error while trying to offload
the rule), monitor the rule state using a flag.
In downstream patch which adds support to IP tunneling neigh update
flow, a TC rule co
From: Hadar Hen Zion
Passing output device parameter to the helper functions that deal with
creation of encapsulation headers is redundant. Output device parameter
can be defined inside those helpers, no need to pass it. Refactor the code by
removing the parameter from the function signature.
Th
1 - 100 of 121 matches
Mail list logo
