RE: [PATCH net 1/2] r8152: fix the sw rx checksum is unavailable

Ansis Atteka [mailto:aatt...@nicira.com] > Sent: Tuesday, January 03, 2017 8:41 AM [...] > Hayes, in your iperf reproduction environment did you > 1) connect sender and receiver directly with an Ethernet cable? > 2) use iperf's TCP mode instead of UDP mode, because I believe that > with UDP mode

Re: patch 4.8 "net: handle no dst on skb in icmp6_send"

On Mon, Jan 09, 2017 at 07:53:49AM +, Bronek Kozicki wrote: > On 08/01/2017 22:50, David Miller wrote: > > From: Bronek Kozicki > > Date: Sun, 8 Jan 2017 21:46:18 + > > > > > Hello, > > > > > > any particular reason why this fix > > >

Re: patch 4.8 "net: handle no dst on skb in icmp6_send"

On 08/01/2017 22:50, David Miller wrote: From: Bronek Kozicki Date: Sun, 8 Jan 2017 21:46:18 + Hello, any particular reason why this fix https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=79dc7e3f1cd323be4c81aa1a94faa1b3ed987fb2 was missed from

Re: [RFC v2 00/10] HFI Virtual Network Interface Controller (VNIC)

On Thu, Dec 15, 2016 at 11:28:06AM -0500, Doug Ledford wrote: > On 12/15/2016 9:52 AM, ira.weiny wrote: > > 2) With more than 60% of the code being MAD related, and another > significant chunk being hfi related, and only a minor bit (20% maybe?) > being net related, Hi Doug and Ira, I may admit

[PATCH v2] ipv4: make tcp_notsent_lowat sysctl knob behave as true unsigned int

> cat /proc/sys/net/ipv4/tcp_notsent_lowat -1 > echo 4294967295 > /proc/sys/net/ipv4/tcp_notsent_lowat -bash: echo: write error: Invalid argument > echo -2147483648 > /proc/sys/net/ipv4/tcp_notsent_lowat > cat /proc/sys/net/ipv4/tcp_notsent_lowat -2147483648 but in documentation we have

Re: [PATCH net-next v2] net: dsa: make "label" property optional for dsa2

Mon, Jan 09, 2017 at 12:15:52AM CET, vivien.dide...@savoirfairelinux.com wrote: >In the new DTS bindings for DSA (dsa2), the "ethernet" and "link" >phandles are respectively mandatory and exclusive to CPU port and DSA >link device tree nodes. > >Simplify dsa2.c a bit by checking the presence of

Re: [PATCH 2/3] xen: modify xenstore watch event interface

On 06/01/17 22:57, Boris Ostrovsky wrote: > On 01/06/2017 10:05 AM, Juergen Gross wrote: >> Today a Xenstore watch event is delivered via a callback function >> declared as: >> >> void (*callback)(struct xenbus_watch *, >> const char **vec, unsigned int len); >> >> As all watch

UNSUBSCIBE

-Original Message- From: netfilter-announce [mailto:netfilter-announce-boun...@lists.netfilter.org] On Behalf Of Pablo Neira Ayuso Sent: dinsdag 20 december 2016 21:47 To: netfilter-de...@vger.kernel.org Cc: l...@lwn.net; netdev@vger.kernel.org; netfil...@vger.kernel.org;

Re: [PATCH net-next] net:add one common config ARCH_WANT_RELAX_ORDER to support relax ordering.

On 2017/1/6 23:41, Alexander Duyck wrote: > On Fri, Jan 6, 2017 at 1:52 AM, Mao Wenan wrote: >> Relax ordering(RO) is one feature of 82599 NIC, to enable this feature can >> enhance the performance for some cpu architecure, such as SPARC and so on. >> Currently it only

[PATCH v2 net-next] net:add one common config ARCH_WANT_RELAX_ORDER to support relax ordering.

Relax ordering(RO) is one feature of 82599 NIC, to enable this feature can enhance the performance for some cpu architecure, such as SPARC and so on. Currently it only supports one special cpu architecture(SPARC) in 82599 driver to enable RO feature, this is not very common for other cpu

[GIT] Networking

1) Fix dumping of nft_quota entries, from Pablo Neira Ayuso. 2) Fix out of bounds access in nf_tables discovered by KASAN, from Florian Westphal. 3) Fix IRQ enabling in dp83867 driver, from Grygorii Strashko. 4) Fix unicast filtering in be2net driver, from Ivan Vecera. 5) tg3_get_stats64()

Re: [PATCH net 0/2] net: dsa: bcm_sf2: Couple fixes

From: Florian Fainelli Date: Sat, 7 Jan 2017 21:01:55 -0800 > Here are a couple of fixes for bcm_sf2, please queue these up for > -stable as well, thank you very much! Series applied and queued up for -stable, thanks.

Re: [PATCH V4 net-next 1/3] vhost: better detection of available buffers

On 2017年01月07日 03:55, Michael S. Tsirkin wrote: On Fri, Jan 06, 2017 at 10:13:15AM +0800, Jason Wang wrote: This patch tries to do several tweaks on vhost_vq_avail_empty() for a better performance: - check cached avail index first which could avoid userspace memory access. - using unlikely()

Re: [PATCH net-next v2] net: dsa: make "label" property optional for dsa2

Hi Andrew, Andrew Lunn writes: >> Until the printing of netdev_phys_item_id structures is fixed in >> net/core/net-sysfs.c, an external helper can be used like this: > > As Florian pointed out, this cannot be changed. It is now part of the > ABI. We have to live with it printing

Re: [PATCH V4 net-next 3/3] tun: rx batching

On 2017年01月07日 03:47, Michael S. Tsirkin wrote: +static int tun_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec) +{ + struct tun_struct *tun = netdev_priv(dev); + + ec->rx_max_coalesced_frames = tun->rx_batched; + + return 0; +} +

Re: [PATCH net-next 0/6] convert tc_verd to integer bitfields

From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:32 -0500 > The skb tc_verd field takes up two bytes but uses far fewer bits. > Convert the remaining use cases to bitfields that fit in existing > holes (depending on config options) and potentially save the two

Re: [PATCH net-next] net: dsa: select NET_SWITCHDEV

On 01/08/17 17:18, Florian Fainelli wrote: > On 01/08/2017 03:17 PM, Vivien Didelot wrote: >> DSA wraps SWITCHDEV, thus select it instead of depending on it. >> >> Signed-off-by: Vivien Didelot > > Reviewed-by: Florian Fainelli > but

Re: [PATCH v2] phy state machine: failsafe leave invalid RUNNING state

On 01/06/2017 03:14 AM, Zefir Kurtisi wrote: > While in RUNNING state, phy_state_machine() checks for link changes by > comparing phydev->link before and after calling phy_read_status(). > This works as long as it is guaranteed that phydev->link is never > changed outside the

Re: [PATCH net-next] net: dsa: select NET_SWITCHDEV

On 01/08/2017 03:17 PM, Vivien Didelot wrote: > DSA wraps SWITCHDEV, thus select it instead of depending on it. > > Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli -- Florian

Re: [PATCH v2] PCI: lock each enable/disable num_vfs operation in sysfs

On Fri, Jan 06, 2017 at 01:59:08PM -0800, Emil Tantilov wrote: >Enabling/disabling SRIOV via sysfs by echo-ing multiple values >simultaneously: > >echo 63 > /sys/class/net/ethX/device/sriov_numvfs& >echo 63 > /sys/class/net/ethX/device/sriov_numvfs > >sleep 5 > >echo 0 >

Re: [PATCH net-next] net: dsa: select NET_SWITCHDEV

On Sun, Jan 08, 2017 at 06:17:24PM -0500, Vivien Didelot wrote: > DSA wraps SWITCHDEV, thus select it instead of depending on it. > > Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Andrew

Re: [PATCH net-next v2] net: dsa: make "label" property optional for dsa2

> Until the printing of netdev_phys_item_id structures is fixed in > net/core/net-sysfs.c, an external helper can be used like this: Hi Vivien As Florian pointed out, this cannot be changed. It is now part of the ABI. We have to live with it printing little endian numbers as big endian. > #

Re: [PATCH v5] net: stmmac: fix maxmtu assignment to be within valid range

From: "Kweh, Hock Leong" Date: Sat, 7 Jan 2017 17:32:03 +0800 > From: "Kweh, Hock Leong" > > There is no checking valid value of maxmtu when getting it from > device tree. This resolution added the checking condition to > ensure the

[PATCH net-next] net: dsa: select NET_SWITCHDEV

DSA wraps SWITCHDEV, thus select it instead of depending on it. Signed-off-by: Vivien Didelot --- net/dsa/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 2ae9bb357523..675acbf1502d 100644

Re: [PATCH v2 03/12] net: ethernet: aquantia: Add ring support code

Hi, Alexander, After a brief review, I have the following minor comments: ... ... > diff --git a/drivers/net/ethernet/aquantia/aq_ring.c > b/drivers/net/ethernet/aquantia/aq_ring.c > new file mode 100644 > index 000..a7ef6aa > --- /dev/null > +++ b/drivers/net/ethernet/aquantia/aq_ring.c >

[PATCH net-next v2] net: dsa: make "label" property optional for dsa2

In the new DTS bindings for DSA (dsa2), the "ethernet" and "link" phandles are respectively mandatory and exclusive to CPU port and DSA link device tree nodes. Simplify dsa2.c a bit by checking the presence of such phandle instead of checking the redundant "label" property. Then the Linux

Re: [PATCH v2] phy state machine: failsafe leave invalid RUNNING state

From: Zefir Kurtisi Date: Fri, 6 Jan 2017 12:14:48 +0100 > While in RUNNING state, phy_state_machine() checks for link changes by > comparing phydev->link before and after calling phy_read_status(). > This works as long as it is guaranteed that phydev->link is never >

Re: [PATCH net-next] mdio: Demote print from info to debug in mdio_device_register

From: Florian Fainelli Date: Fri, 6 Jan 2017 22:27:59 -0800 > While it is useful to know which MDIO device is being registered, demote > the dev_info() to a dev_dbg(). > > Signed-off-by: Florian Fainelli Applied.

Re: [PATCH net-next v2 1/2] net: make ndo_get_stats64 a void function

From: Stephen Hemminger Date: Fri, 6 Jan 2017 19:12:52 -0800 > The network device operation for reading statistics is only called > in one place, and it ignores the return value. Having a structure > return value is potentially confusing because some future driver

Re: [PATCH net-next 2/2] net: remove useless memset's in drivers get_stats64

From: Stephen Hemminger Date: Fri, 6 Jan 2017 19:12:53 -0800 > In dev_get_stats() the statistic structure storage has already been > zeroed. Therefore network drivers do not need to call memset() again. > > Signed-off-by: Stephen Hemminger

[PATCH net-next 0/4] net: dsa: Make dsa_switch_ops const

Hi all, This patch series allows us to annotate dsa_switch_ops with a const qualifier. Florian Fainelli (4): net: dsa: b53: Export most operations to other drivers net: dsa: bcm_sf2: Declare our own dsa_switch_ops net: dsa: Encapsulate legacy switch drivers into dsa_switch_driver net:

[PATCH net-next 1/4] net: dsa: b53: Export most operations to other drivers

In preparation for making dsa_switch_ops const, export b53 operations utilized by other drivers such as bcm_sf2. Signed-off-by: Florian Fainelli --- drivers/net/dsa/b53/b53_common.c | 79 +++- drivers/net/dsa/b53/b53_priv.h | 33

[PATCH net-next 4/4] net: dsa: Make dsa_switch_ops const

Now that we have properly encapsulated and made drivers utilize exported functions, we can switch dsa_switch_ops to be a annotated with const. Signed-off-by: Florian Fainelli --- drivers/net/dsa/b53/b53_common.c | 2 +- drivers/net/dsa/bcm_sf2.c| 2 +-

[PATCH net-next 2/4] net: dsa: bcm_sf2: Declare our own dsa_switch_ops

Utilize the b53 exported functions to fill our bcm_sf2_ops structure, also making it clear what we utilize and what we specifically override. Signed-off-by: Florian Fainelli --- drivers/net/dsa/bcm_sf2.c | 53 +-- 1 file changed,

[PATCH net-next 3/4] net: dsa: Encapsulate legacy switch drivers into dsa_switch_driver

In preparation for making struct dsa_switch_ops const, encapsulate it within a dsa_switch_driver which has a list pointer and a pointer to dsa_switch_ops. This allows us to take the list_head pointer out of dsa_switch_ops, which is written to by {un,}register_switch_driver. Signed-off-by: Florian

Re: patch 4.8 "net: handle no dst on skb in icmp6_send"

From: Bronek Kozicki Date: Sun, 8 Jan 2017 21:46:18 + > Hello, > > any particular reason why this fix > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=79dc7e3f1cd323be4c81aa1a94faa1b3ed987fb2 > was missed from stable 4.8 line? Apparently the bug

Re: [PATCH v3 3/3] nfc: trf7970a: Prevent repeated polling from crashing the kernel

On Tue, Jan 3, 2017 at 4:21 PM, Mark Greer wrote: > On Tue, Jan 03, 2017 at 01:35:18PM -0500, Geoff Lansberry wrote: >> On Tue, Jan 3, 2017 at 11:33 AM, Mark Greer wrote: >> > On Tue, Dec 27, 2016 at 09:18:32AM -0500, Geoff Lansberry wrote: > >> >>

Re: [net-next 0/8][pull request] 100GbE Intel Wired LAN Driver Updates 2017-01-08

From: Jeff Kirsher Date: Sun, 8 Jan 2017 02:10:26 -0800 > This series contains updates to fm10k only. Pulled, thanks Jeff.

Re: [PATCH net-next] net: ipmr: Remove nowait arg to ipmr_get_route

From: David Ahern Date: Fri, 6 Jan 2017 17:39:06 -0800 > ipmr_get_route has 1 caller and the nowait arg is 0. Remove the arg and > simplify ipmr_get_route accordingly. > > Signed-off-by: David Ahern Applied.

Re: [PATCH net-next] net: ipv4: Remove flow arg from ip_mkroute_input

From: David Ahern Date: Fri, 6 Jan 2017 17:39:58 -0800 > fl4 arg is not used; remove it. > > Signed-off-by: David Ahern Applied.

Re: [PATCH net-next] liquidio: simplify octeon_flush_iq()

From: Felix Manlunas Date: Fri, 6 Jan 2017 17:16:12 -0800 > From: Derek Chickles > > Because every call to octeon_flush_iq() has a hardcoded 1 for the > pending_thresh argument, simplify that function by removing that argument. > This

Re: [PATCH net-next] liquidio: store the L4 hash of rx packets in skb

From: Felix Manlunas Date: Fri, 6 Jan 2017 16:55:42 -0800 > > + if (rh->r_dh.has_hash) { > + u32 hash = be32_to_cpu(*(u32 *)(skb->data + r_dh_off)); Is the checksum defined to be in the first 4-bytes of the 8-byte DHLEN unit, or the

patch 4.8 "net: handle no dst on skb in icmp6_send"

Hello, any particular reason why this fix https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=79dc7e3f1cd323be4c81aa1a94faa1b3ed987fb2 was missed from stable 4.8 line? Apparently the bug being fixed has its own

Re: [PATCH net] bpf: change back to orig prog on too many passes

From: Daniel Borkmann Date: Sat, 7 Jan 2017 00:26:33 +0100 > If after too many passes still no image could be emitted, then > swap back to the original program as we do in all other cases > and don't use the one with blinding. > > Fixes: 959a75791603 ("bpf, x86: add

Re: [PATCH net 1/2] net: dsa: bcm_sf2: Do not clobber b53_switch_ops

On Sat, Jan 07, 2017 at 09:01:56PM -0800, Florian Fainelli wrote: > We make the bcm_sf2 driver override ds->ops which points to > b53_switch_ops since b53_switch_alloc() did the assignent. This is all > well and good until a second b53 switch comes in, and ends up using the > bcm_sf2 operations.

Re: [PATCH net 1/2] net: dsa: bcm_sf2: Do not clobber b53_switch_ops

> Agreed, and this was my initial approach, but I also wanted a minimal > fix for David to pull into "net" while we can properly resolve this for > "net-next" see below. O.K, so in that case, this is fine. > Making the ops const was my initial approach but there are several > challenges to

[PATCH] net: ethernet: ti: cpsw: extend limits for cpsw_get/set_ringparam

Allow to set number of descs close to possible values. In case of minimum limit it's equal to number of channels to be able to set at least one desc per channel. For maximum limit leave enough descs number for tx channels. Signed-off-by: Ivan Khoronzhuk --- Based on

Re: [PATCH net 1/2] net: dsa: bcm_sf2: Do not clobber b53_switch_ops

Le 01/08/17 à 09:41, Andrew Lunn a écrit : > On Sat, Jan 07, 2017 at 09:01:56PM -0800, Florian Fainelli wrote: >> We make the bcm_sf2 driver override ds->ops which points to >> b53_switch_ops since b53_switch_alloc() did the assignent. This is all >> well and good until a second b53 switch comes

Re: [PATCH net 2/2] net: dsa: bcm_sf2: Utilize nested MDIO read/write

On Sat, Jan 07, 2017 at 09:01:57PM -0800, Florian Fainelli wrote: > We are implementing a MDIO bus which is behind another one, so use the > nested version of the accessors to get lockdep annotations correct. > > Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus") >

Re: [PATCH net 1/2] net: dsa: bcm_sf2: Do not clobber b53_switch_ops

On Sat, Jan 07, 2017 at 09:01:56PM -0800, Florian Fainelli wrote: > We make the bcm_sf2 driver override ds->ops which points to > b53_switch_ops since b53_switch_alloc() did the assignent. This is all > well and good until a second b53 switch comes in, and ends up using the > bcm_sf2 operations.

Re: [PATCH net-next] net/sched: cls_flower: Add user specified data

Mon, Jan 02, 2017 at 11:21:41PM CET, j...@mojatatu.com wrote: >On 17-01-02 01:23 PM, John Fastabend wrote: > >> >> Additionally I would like to point out this is an arbitrary length binary >> blob (for undefined use, without even a specified encoding) that gets pushed >> between user space and

Re: [PATCH net-next] net/sched: cls_flower: Add user specified data

Mon, Jan 02, 2017 at 07:23:27PM CET, john.fastab...@gmail.com wrote: >On 17-01-02 06:59 AM, Jamal Hadi Salim wrote: >> >> We have been using a cookie as well for actions (which we have been >> using but have been too lazy to submit so far). I am going to port >> it over to the newer kernels and

Re: [PATCH net-next] net/sched: cls_flower: Add user specified data

Mon, Jan 02, 2017 at 03:59:49PM CET, j...@mojatatu.com wrote: > >We have been using a cookie as well for actions (which we have been >using but have been too lazy to submit so far). I am going to port >it over to the newer kernels and post it. Hard to deal with something we can't look at :) >In

Re: [for-next V2 06/10] net/mlx5: Add interface to get reference to a UAR

On Sun, Jan 08, 2017 at 05:54:47PM +0200, Saeed Mahameed wrote: > From: Eli Cohen > > A reference to a UAR is required to generate CQ or EQ doorbells. Since > CQ or EQ doorbells can all be generated using the same UAR area without > any effect on performance, we are just

[PATCH] cls_u32: don't bother explicitly initializing ->divisor to zero

This struct member is already initialized to zero upon root_ht's allocation via kzalloc(). Signed-off-by: Alexandru Moise <00moses.alexande...@gmail.com> --- net/sched/cls_u32.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ae83c3ae..a6ec3e4b

Re: [PATCH net-next 2/2] net/sched: act_csum: compute crc32c on SCTP packets

On Fri, 2017-01-06 at 10:23 +0100, Nicolas Dichtel wrote: > Le 05/01/2017 à 17:59, Davide Caratti a écrit : > > @@ -21,7 +21,8 @@ enum { > >   TCA_CSUM_UPDATE_FLAG_IGMP= 4, > >   TCA_CSUM_UPDATE_FLAG_TCP = 8, > >   TCA_CSUM_UPDATE_FLAG_UDP = 16, > > -

[PATCH 0/4] net: ethernet: ti: cpsw: correct common res usage

This series is intended to remove unneeded redundancies connected with common resource usage function. Based on net-next/master Tested on am572x idk Ivan Khoronzhuk (4): net: ethernet: ti: cpsw: remove dual check from common res usage function net: ethernet: ti: cpsw: don't disable

[PATCH 2/4] net: ethernet: ti: cpsw: don't disable interrupts in ndo_open

If any interface is running the interrupts are disabled anyway. It make sense to disable interrupts if any of interfaces is running, but in this place, obviously, it didn't have any effect. So, no need in redundant check and interrupt disable. Signed-off-by: Ivan Khoronzhuk

[PATCH 1/4] net: ethernet: ti: cpsw: remove dual check from common res usage function

Common res usage is possible only in case an interface is running. In case of not dual emac here can be only one interface, so while ndo_open and switch mode, only one interface can be opened, thus if open is called no any interface is running ... and no common res are used. So remove check on

[PATCH 4/4] net: ethernet: ti: cpsw: don't duplicate common res in rx handler

No need to duplicate the same function in rx handler to get info if any interface is running. Signed-off-by: Ivan Khoronzhuk --- drivers/net/ethernet/ti/cpsw.c | 40 1 file changed, 16 insertions(+), 24 deletions(-) diff

[PATCH 3/4] net: ethernet: ti: cpsw: don't duplicate ndev_running

No need to create additional vars to identify if interface is running. So simplify code by removing redundant var and checking usage counter instead. Signed-off-by: Ivan Khoronzhuk --- drivers/net/ethernet/ti/cpsw.c | 14 -- 1 file changed, 4

Re: [PATCH] net: ethernet: ti: cpsw: remove dual check from common res usage function

Please ignore it, I've included it in new series On Sun, Jan 08, 2017 at 03:56:27PM +0200, Ivan Khoronzhuk wrote: > Common res usage is possible only in case an interface is > running. In case of not dual emac here can be only one interface, > so while ndo_open and switch mode, only one interface

Re: [PATCH net-next 6/7] net/mlx5: E-Switch, Add control for inline mode

On Sun, Jan 8, 2017 at 11:56 AM, Jiri Pirko wrote: > Mon, Nov 21, 2016 at 02:06:00PM CET, sae...@mellanox.com wrote: >>From: Roi Dayan >> >>Implement devlink show and set of HW inline-mode. >>The supported modes: none, link, network, transport. >>We currently

[for-next V2 08/10] IB/mlx5: Allow future extension of libmlx5 input data

From: Eli Cohen Current check requests that new fields in struct mlx5_ib_alloc_ucontext_req_v2 that are not known to the driver be zero. This was introduced so new libraries passing additional information to the kernel through struct mlx5_ib_alloc_ucontext_req_v2 will be

[for-next V2 09/10] IB/mlx5: Support 4k UAR for libmlx5

From: Eli Cohen Add fields to structs to convey to kernel an indication whether the library supports multi UARs per page and return to the library the size of a UAR based on the queried value. Signed-off-by: Eli Cohen Reviewed-by: Matan Barak

[for-next V2 10/10] net/mlx5: Activate support for 4K UARs

From: Eli Cohen Activate 4K UAR support for firmware versions that support it. Signed-off-by: Eli Cohen Reviewed-by: Matan Barak Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed ---

[for-next V2 03/10] mlx5: Fix naming convention with respect to UARs

From: Eli Cohen This establishes a solid naming conventions for UARs. A UAR (User Access Region) can have size identical to a system page or can be fixed 4KB depending on a value queried by firmware. Each UAR always has 4 blue flame register which are used to post doorbell to

[for-next V2 07/10] IB/mlx5: Use blue flame register allocator in mlx5_ib

From: Eli Cohen Make use of the blue flame registers allocator at mlx5_ib. Since blue flame was not really supported we remove all the code that is related to blue flame and we let all consumers to use the same blue flame register. Once blue flame is supported we will add the

[for-next V2 05/10] net/mlx5: Introduce blue flame register allocator

From: Eli Cohen Here is an implementation of an allocator that allocates blue flame registers. A blue flame register is used for generating send doorbells. A blue flame register can be used to generate either a regular doorbell or a blue flame doorbell where the data to be

[for-next V2 06/10] net/mlx5: Add interface to get reference to a UAR

From: Eli Cohen A reference to a UAR is required to generate CQ or EQ doorbells. Since CQ or EQ doorbells can all be generated using the same UAR area without any effect on performance, we are just getting a reference to any available UAR, If one is not available we allocate

[for-next V2 02/10] IB/mlx5: Fix error handling order in create_kernel_qp

From: Eli Cohen Make sure order of cleanup is exactly the opposite of initialization. Fixes: 9603b61de1ee ('mlx5: Move pci device handling from mlx5_ib to mlx5_core') Signed-off-by: Eli Cohen Reviewed-by: Matan Barak Signed-off-by:

[for-next V2 00/10][pull request] Mellanox 100G mlx5 4K UAR support

Hi Dave and Doug, Following the mlx5-odp submission, you can find here the 2nd mlx5 submission for 4.11 as a pull-request including mlx5 4K UAR support from Eli Cohen (details below). For you Doug, this pull request will provide you with both mlx5 odp and mlx5 4k UAR since it is based on Dave's

[for-next V2 04/10] IB/mlx5: Fix retrieval of index to first hi class bfreg

From: Eli Cohen First the function retrieving the index of the first hi latency class blue flame register. High latency class bfregs are located right above medium latency class bfregs. Fixes: c1be5232d21d ('IB/mlx5: Fix micro UAR allocator') Signed-off-by: Eli Cohen

[for-next V2 01/10] IB/mlx5: Fix kernel to user leak prevention logic

From: Eli Cohen The logic was broken as it failed to update the response length for architectures with PAGE_SIZE larger than 4kB. As a result further extension of the ucontext response struct would fail. Fixes: d69e3bcf7976 ('IB/mlx5: Mmap the HCA's core clock register to

[PATCH stable 4.1] openvswitch: gre: filter gre packets

OVS can only process L2 packets. But OVS GRE receive handler can accept IP-GRE packets. When such packet is processed by OVS datapath it can trigger following assert failure due to insufficient linear data in skb. Following patch filters received packets to avoid this issue. [68240.441681]

[PATCH] net: ethernet: ti: cpsw: remove dual check from common res usage function

Common res usage is possible only in case an interface is running. In case of not dual emac here can be only one interface, so while ndo_open and switch mode, only one interface can be opened, thus if open is called no any interface is running ... and no common res are used. So remove check on

GREETINGS

Hello my name is Ms. Thandi Robert, from Ivory Coast. My parents were brutally mulled by the former president Laurent Gbagbo because of political crisis as the only survival of my family. I got your email while searching for a reliable personality in my private study on the internet. I am in

[PATCH v3 net-next 2/4] siphash: implement HalfSipHash1-3 for hash tables

HalfSipHash, or hsiphash, is a shortened version of SipHash, which generates 32-bit outputs using a weaker 64-bit key. It has *much* lower security margins, and shouldn't be used for anything too sensitive, but it could be used as a hashtable key function replacement, if the output is never

[PATCH v3 net-next 4/4] syncookies: use SipHash in place of SHA1

SHA1 is slower and less secure than SipHash, and so replacing syncookie generation with SipHash makes natural sense. Some BSDs have been doing this for several years in fact. The speedup should be similar -- and even more impressive -- to the speedup from the sequence number fix in this series.

[PATCH v3 net-next 1/4] siphash: add cryptographically secure PRF

SipHash is a 64-bit keyed hash function that is actually a cryptographically secure PRF, like HMAC. Except SipHash is super fast, and is meant to be used as a hashtable keyed lookup function, or as a general PRF for short input use cases, such as sequence numbers or RNG chaining. For the first

[PATCH v3 net-next 3/4] secure_seq: use SipHash in place of MD5

This gives a clear speed and security improvement. Siphash is both faster and is more solid crypto than the aging MD5. Rather than manually filling MD5 buffers, for IPv6, we simply create a layout by a simple anonymous struct, for which gcc generates rather efficient code. For IPv4, we pass the

[PATCH v3 net-next 0/4] Introduce The SipHash PRF

This patch series introduces SipHash into the kernel. SipHash is a cryptographically secure PRF, which serves a variety of functions, and is introduced in patch #1. The following patch #2 introduces HalfSipHash, an optimization suitable for hash tables only. Finally, the last two patches in this

Re: [PATCH v2 net-next 0/4] Introduce The SipHash PRF

Hi Eric, Thanks for round two. I'll address these. Comments are inline below. On Sat, Jan 7, 2017 at 8:54 PM, Eric Biggers wrote: > Hi Jason, thanks for doing this! Yes, I had gotten a little lost in the > earlier > discussions about the 'random' driver and other

Re: [PATCH v2 net-next 3/4] secure_seq: use SipHash in place of MD5

Hi David, On Sat, Jan 7, 2017 at 10:37 PM, David Miller wrote: > This and the next patch are a real shame, performance wise, on cpus > that have single-instruction SHA1 and MD5 implementations. Sparc64 > has both, and I believe x86_64 can do SHA1 these days. > > It took so

Re: [PATCH v5 3/3] stmmac: adding new glue driver dwmac-dwc-qos-eth

> On 06 Jan 2017, at 11:48 , Joao Pinto wrote: > > This patch adds a new glue driver called dwmac-dwc-qos-eth which > was based in the dwc_eth_qos as is. To assure retro-compatibility a slight > tweak was also added to stmmac_platform. > > Signed-off-by: Joao Pinto

Re: [PATCH net-next 4/7] devlink: Add E-Switch inline mode control

On 1/8/2017 12:54 PM, Jiri Pirko wrote: I believe that this is an e-switch requirement so it should be same for all connected VFs, right? yes

Re: [PATCH net-next 4/7] devlink: Add E-Switch inline mode control

Sun, Jan 08, 2017 at 11:49:20AM CET, ogerl...@mellanox.com wrote: >On 1/8/2017 12:29 PM, Jiri Pirko wrote: >> Mon, Nov 21, 2016 at 02:05:58PM CET, sae...@mellanox.com wrote: >> > From: Roi Dayan >> > >> > Some HWs need the VF driver to put part of the packet headers on the >>

Re: [PATCH net-next 4/7] devlink: Add E-Switch inline mode control

On 1/8/2017 12:29 PM, Jiri Pirko wrote: Mon, Nov 21, 2016 at 02:05:58PM CET, sae...@mellanox.com wrote: From: Roi Dayan Some HWs need the VF driver to put part of the packet headers on the TX descriptor so the e-switch can do proper matching and steering. Could you please

[PATCH] net: fix accept4() flags not work

From: yuan linyu user input flags store to newsock which should be used. Signed-off-by: yuan linyu --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/socket.c b/net/socket.c index

Re: [PATCH net-next 4/7] devlink: Add E-Switch inline mode control

Mon, Nov 21, 2016 at 02:05:58PM CET, sae...@mellanox.com wrote: >From: Roi Dayan > >Some HWs need the VF driver to put part of the packet headers on the >TX descriptor so the e-switch can do proper matching and steering. Could you please elaborate a bit about possible

[net-next 3/8] fm10k: request reset when mbx->state changes

From: Ngai-Mint Kwan Multiple IES API resets can cause a race condition where the mailbox interrupt request bits can be cleared before being handled. This can leave certain mailbox messages from the PF to be untreated and the PF will enter in some inactive state. If

[net-next 1/8] fm10k-shared: use mac-> instead of hw->mac.

From: Ngai-Mint Kwan Since a pointer "mac" to fm10k_mac_info structure exists, use it to access the contents of its members. Signed-off-by: Ngai-Mint Kwan Signed-off-by: Jacob Keller Tested-by: Krishneil Singh

[net-next 2/8] fm10k: remove extraneous variable definition in fm10k_ethtool.c

From: Jacob Keller We don't need to typecast a u8 * into a char *, so just remove the extra variable. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher

[net-next 4/8] fm10k: do not clear global mailbox interrupt bits

From: Ngai-Mint Kwan Partially revert commit 5e93cbadd3e9 ("fm10k: Reset mailbox global interrupts", 2016-06-07) The register bits related to this commit are now solely being handled by the IES API. Recent changes in the IES API will allow an automatic recovery from

[net-next 5/8] fm10k: bump version number

From: Jacob Keller Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- 1 file changed, 1

[net-next 0/8][pull request] 100GbE Intel Wired LAN Driver Updates 2017-01-08

This series contains updates to fm10k only. Ngai-Mint changes the driver to use the MAC pointer in the fm10k_mac_info structure for fm10k_get_host_state_generic(). Fixed a race condition where the mailbox interrupt request bits can be cleared before being handled causing certain mailbox messages

[net-next 7/8] fm10k: report the receive timestamp in FM10K_CB(skb)->tstamp

From: Jacob Keller This was accidentally removed when we defeatured the full 1588 Clock support. We need to report the Rx descriptor timestamp value so that applications built on top of the IES API can function properly. Additionally, remove the

[net-next 6/8] fm10k: Limit dma sync of RX buffers to actual packet size

From: Scott Peterson On packet RX, we perform a dma sync for cpu before passing the packet up. Here we limit that sync to the actual length of the incoming packet, rather than always syncing the entire buffer. Signed-off-by: Scott Peterson

[net-next 8/8] fm10k: remove FM10K_FLAG_DEBUG_STATS

From: Jacob Keller The debug statistics were removed due to complications with the ethtool statistics API which are not possible to resolve without a new statistics interface. The flag was left behind, but we no longer need it. Signed-off-by: Jacob Keller

Re: [PATCH net-next 6/7] net/mlx5: E-Switch, Add control for inline mode

Mon, Nov 21, 2016 at 02:06:00PM CET, sae...@mellanox.com wrote: >From: Roi Dayan > >Implement devlink show and set of HW inline-mode. >The supported modes: none, link, network, transport. >We currently support one mode for all vports so set is done on all vports. >When eswitch

  1   2   >