- 29 Jul, 2018 27 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linuxDavid S. Miller authored
Saeed Mahameed says: ==================== mlx5e-updates-2018-07-27 (Vxlan updates) This series from Gal and Saeed provides updates to mlx5 vxlan implementation. Gal, started with three cleanups to reflect the actual hardware vxlan state - reflect 4789 UDP port default addition to software database - check maximum number of vxlan UDP ports - cleanup an unused member in vxlan work Then Gal provides performance optimization by replacing the vxlan radix tree with a hash table. Measuring mlx5e_vxlan_lookup_port execution time: Radix Tree Hash Table --------------- ------------ ------------ Single Stream 161 ns 79 ns (51% improvement) Multi Stream 259 ns 136 ns (47% improvement) Measuring UDP stream packet rate, single fully utilized TX core: Radix Tree: 498,300 PPS Hash Table: 555,468 PPS (11% improvement) Next, from Saeed, vxlan refactoring to allow sharing the vxlan table between different mlx5 netdevice instances like PF and VF representors, this is done by making mlx5 vxlan interface more generic and decoupling it from PF netdevice structures and logic, then moving it into mlx5 core as a low level interface so it can be used by VF representors, which is illustrated in the last patch of the serious. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Petr Machata authored
There are two problems in this test case: - When indexing in bash associative array, the subscript is interpreted as string, not as a variable name to be expanded. - The keys stored to t0s and t1s are not DSCP values, but priority + base (i.e. the logical DSCP value, not the full bitfield value). In combination these two bugs conspire to make the test just work, except it doesn't really test anything and always passes. Fix the above two problems in obvious manner. Signed-off-by:
Petr Machata <petrm@mellanox.com> Signed-off-by:
-
David S. Miller authored
Stephen Hemminger says: ==================== mtu related changes While looking at other MTU issues, noticed a couple oppurtunties for improving user experience. ==================== Signed-off-by: -
Stephen Hemminger authored
If an invalid MTU value is set through rtnetlink return extra error information instead of putting message in kernel log. For other cases where there is no visible API, keep the error report in the log. Example: # ip li set dev enp12s0 mtu 10000 Error: mtu greater than device maximum. # ifconfig enp12s0 mtu 10000 SIOCSIFMTU: Invalid argument # dmesg | tail -1 [ 2047.795467] enp12s0: mtu greater than device maximum Signed-off-by:
Stephen Hemminger <stephen@networkplumber.org> Signed-off-by:
-
Stephen Hemminger authored
Report the minimum and maximum MTU allowed on a device via netlink so that it can be displayed by tools like ip link. Signed-off-by:
-
Stephen Hemminger authored
When changing MTU, RTNL is held so use rtnl_dereference instead of rcu_dereference. Signed-off-by:
-
Jakub Kicinski authored
Commit ee205981 ("net/dcb: Add dscp to priority selector type") added a define for the new DSCP selector type created by IEEE 802.1Qcd, but missed the comment enumerating all selector types. Update the comment. Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by:
-
Ivan Khoronzhuk authored
Seems it was missed while adding for first net dev in dual-emac mode. Signed-off-by:
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Reviewed-by:
Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by:
-
David S. Miller authored
Xin Long says: ==================== route: add support and selftests for directed broadcast forwarding Patch 1/2 is the feature and 2/2 is the selftest. Check the changelog on each of them to know the details. v1->v2: - fix a typo in changelog. - fix an uapi break that Davide noticed. - flush route cache when bc_forwarding is changed. - add the selftest for this patch as Ido's suggestion. v2->v3: - fix an incorrect 'if check' in devinet_conf_proc as David Ahern noticed. - extend the selftest after one David Ahern fix for vrf. v3->v4: - improve the output log in the selftest as David Ahern suggested. ==================== Signed-off-by: -
Xin Long authored
As Ido's suggestion, this patch is to add a selftest for directed broadcast forwarding with vrf. It does the assertion by checking the src IP of the echo-reply packet in ping_test_from. Signed-off-by:
Xin Long <lucien.xin@gmail.com> Signed-off-by:
-
Xin Long authored
This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled. Note that this feature could be done by iptables -j TEE, but it would cause some problems: - target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts. - this duplicates the directed broadcasts so this may cause side effects to applications. Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path. Note that route cache needs to be flushed when bc_forwarding is changed. Signed-off-by: -
Vincent Bernat authored
When freebind feature is set of an IPv6 socket, any source address can be used when sending UDP datagrams using IPv6 PKTINFO ancillary message. Global non-local bind feature was added in commit 35a256fe ("ipv6: Nonlocal bind") for IPv6. This commit also allows IPv6 source address spoofing when non-local bind feature is enabled. Signed-off-by:
Vincent Bernat <vincent@bernat.im> Signed-off-by:
-
David S. Miller authored
Merge tag 'linux-can-next-for-4.19-20180727' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next Marc Kleine-Budde says: ==================== pull-request: can-next 2018-01-16 this is a pull request for net-next/master consisting of 38 patches. Dan Murphy's patch fixes the path to a file in the comment of the CAN Error Message Frame Mask structure. A patch by Colin Ian King fixes a typo in the cc770 driver. The next patch is by me an sorts the Kconfigand Makefile entries of the CAN-USB driver subdir alphabetically. The patch by Jakob Unterwurzacher adds support for the UCAN USB-CAN adapter. YueHaibing's patch replaces a open coded skb_put()+memset() by skb_put_zero() in the CAN-dev infrastructure. Zhu Yi provides a patch to enable multi-queue CAN devices. Three patches by Luc Van Oostenryck fix the return value of several driver's xmit function, I contribute a patch for the a fourth driver. Fabio Estevam's patch switches the flexcan driver to SPDX identifier. Two patches by Jia-Ju Bai replace the mdelay() by a usleep_range() in the sja1000 drivers. The next 6 patches are by Anssi Hannula and refactor the xilinx CAN driver and add support for the xilinx CAN FD core. A patch by Gustavo A. R. Silva adds fallthrough annotation to the peak_usb driver. 5 patches by Stephane Grosjean for the peak CANFD driver do some cleanups and provide more improvements for further firmware releases. The remaining 13 patches are by Jimmy Assarsson and the first clean up the kvaser_usb driver, so that the later patches add support for the Kvaser USB hydra family. ==================== Signed-off-by:
-
YueHaibing authored
There are no in-tree callers of qed_set_gft_event_id_cm_hdr. Signed-off-by:
YueHaibing <yuehaibing@huawei.com> Signed-off-by:
-
YueHaibing authored
There are no in-tree callers. Signed-off-by:
-
David S. Miller authored
Doron Roberts-Kedes says: ==================== tls: Fix improper revert in zerocopy_from_iter This series fixes the improper iov_iter_revert introcded in "tls: Fix zerocopy_from_iter iov handling". ==================== Signed-off-by: -
Doron Roberts-Kedes authored
The current code is problematic because the iov_iter is reverted and never advanced in the non-error case. This patch skips the revert in the non-error case. This patch also fixes the amount by which the iov_iter is reverted. Currently, iov_iter is reverted by size, which can be greater than the amount by which the iter was actually advanced. Instead, only revert by the amount that the iter was advanced. Fixes: 47187998 ("tls: Fix zerocopy_from_iter iov handling") Signed-off-by:
Doron Roberts-Kedes <doronrk@fb.com> Signed-off-by:
-
Doron Roberts-Kedes authored
tls_push_record either returns 0 on success or a negative value on failure. This patch removes code that would only be executed if tls_push_record were to return a positive value. Signed-off-by:
-
David S. Miller authored
Gregory CLEMENT says: ==================== A fix and a few improvements on mvneta This series brings some improvements for the mvneta driver and also adds a fix. Compared to the v2, the main change is another patch fixing a bug in mtu_change. Changelog: v1 -> v2 - In patch 2, use EXPORT_SYMBOL_GPL for mvneta_bm_get and mvneta_bm_put to be used in module, reported by kbuild test robot. - In patch 4, add the counter to the driver's ethtool state, suggested by David Miller. - In patch 6, use a single if, suggested by Marcin Wojtas v2 -> v3 - Adding a patch fixing the mtu change issue - Removing the inline keyword for mvneta_rx_refill() and let the comiler decided, suggested by David Miller. ==================== Signed-off-by: -
Yelena Krivosheev authored
With system having a small memory (around 256MB), the state "cannot allocate memory to refill with new buffer" is reach pretty quickly. By this patch we changed buffer allocation method to a better handling of this use case by avoiding memory allocation issues. Signed-off-by:
Yelena Krivosheev <yelena@marvell.com> [gregory: extract from a larger patch] Signed-off-by:
Gregory CLEMENT <gregory.clement@bootlin.com> Signed-off-by:
-
Yelena Krivosheev authored
If the checksum offload feature is not set, then there is no point to check the status of the hardware. [gregory: extract from a larger patch] Signed-off-by:
-
Gregory CLEMENT authored
Instead of trying to allocate the exact amount of memory for each descriptor use a page for each of them, it allows to simplify the allocation management and increase the performance of the driver. Based on the work of Yelena Krivosheev <yelena@marvell.com> Signed-off-by:
-
Gregory CLEMENT authored
In order to improve the diagnostic in case of error, make the distinction between refill error and skb allocation error. Also make the information available through the ethtool state. Based on the work of Yelena Krivosheev <yelena@marvell.com> Signed-off-by:
-
Yelena Krivosheev authored
The initial values were too small leading to poor performance when using the software buffer management. Signed-off-by:
-
Gregory CLEMENT authored
On year ago Rob Herring wanted to remove the data pointer from the device_node structure[1]. The mvneta driver seemed to be the only one which used (abused ?) it. However, the proposal of Rob to remove this pointer from the driver introduced a regression, and I tested and fixed an alternative way, but it was never submitted as a proper patch. Now here it is: Instead of using the device_node structure ->data pointer, we store the BM private data as the driver data of the BM platform_device. The core mvneta code can retrieve it by doing a lookup on which platform_device corresponds to the BM device tree node using of_find_device_by_node(), and get its driver data [1]https://www.spinics.net/lists/netdev/msg445197.htmlSigned-off-by:
-
Yelena Krivosheev authored
It is incorrect to enable TX/RX queues (call by mvneta_port_up()) for port without link. Indeed MTU change for interface without link causes TX queues to stuck. Fixes: c5aff182 ("net: mvneta: driver for Marvell Armada 370/XP network unit") Signed-off-by:
-
Andrew Lunn authored
The mvneta Ethernet driver is used on a few different Marvell SoCs. Some SoCs have per cpu interrupts for Ethernet events. Some SoCs have a single interrupt, independent of the CPU. The driver handles this by having a per CPU napi structure when there are per CPU interrupts, and a global napi structure when there is a single interrupt. When the napi core calls mvneta_poll(), it passes the napi instance. This was not being propagated through the call chain, and instead the per-cpu napi instance was passed to napi_gro_receive() call. This breaks when there is a single global napi instance. Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Fixes: 2636ac3c ("net: mvneta: Add network support for Armada 3700 SoC") Signed-off-by:
-
- 27 Jul, 2018 13 commits
-
-
Saeed Mahameed authored
Remove uplink representor netdevice private structure lookup, and use mlx5 core handle directly from representor private structure to lookup vxlan ports. Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Reviewed-by:
Or Gerlitz <ogerlitz@mellanox.com>
-
Saeed Mahameed authored
Move vxlan logic and objects to mlx5 core dirver. Since it going to be used from different mlx5 interfaces. e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors. Signed-off-by:
-
Saeed Mahameed authored
Vxlan API can and will be called from different mlx5 modules, we should not count on mlx5e private state lock only, hence we introduce a vxlan private mutex to sync between add/del vxlan port operations. Signed-off-by:
-
Saeed Mahameed authored
For a better API mlx5_vxlan_{add/del}_port can fail, make them return error values. Signed-off-by: -
Saeed Mahameed authored
Rename vxlan functions from mlx5e_vxlan_* to mlx5_vxlan_*. Rename mlx5e_vxlan_db to mlx5_vxlan and move it from en.h to vxlan.c since it is not related to mlx5e anymore. Allocate mlx5_vxlan structure dynamically in order to make it easier to move later to core driver and to make it private in vxlan.c. This is in preparation to move vxlan API to mlx5 core. Signed-off-by:
-
Saeed Mahameed authored
The name mlx5e_vxlan will be used in downstream patch to describe mlx5 vxlan structure that will replace mlx5e_vxlan_db. Hence we rename struct mlx5e_vxlan to mlx5_vxlan_port which describes a mlx5 vxlan port. Signed-off-by:
-
Saeed Mahameed authored
Create a direct vxlan API to add and delete vxlan ports from HW. +void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port); +void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port); And move vxlan_add/del_work to en_main.c since they are netdev only logic. Signed-off-by:
-
Saeed Mahameed authored
Add direct vxlan delete function to be called from vxlan_delete_work. Needed in downstream patch. Signed-off-by:
-
Gal Pressman authored
Cleanup the sa_family member of the vxlan work, it is unused/needed anywhere in the code. Signed-off-by:
Gal Pressman <galp@mellanox.com> Signed-off-by:
-
Gal Pressman authored
The VXLAN database is accessed in the data path for each VXLAN TX skb in order to check whether the UDP port is being offloaded or not. The number of elements in the database is relatively small, we can simplify the radix-tree to a hash table and speedup the lookup process. Measuring mlx5e_vxlan_lookup_port execution time: Radix Tree Hash Table --------------- ------------ ------------ Single Stream 161 ns 79 ns (51% improvement) Multi Stream 259 ns 136 ns (47% improvement) Measuring UDP stream packet rate, single fully utilized TX core: Radix Tree: 498,300 PPS Hash Table: 555,468 PPS (11% improvement) Signed-off-by: -
Gal Pressman authored
The NIC has a limited number of offloaded VXLAN UDP ports (usually 4). Instead of letting the firmware fail when trying to add more ports than it can handle, let the driver check it on its own. Signed-off-by:
-
Gal Pressman authored
The hardware offloads 4789 UDP port (default VXLAN port) automatically. Add it to the software database as well in order to reflect the hardware state appropriately. Signed-off-by:
-
Jia-Ju Bai authored
tipc_bcast_init() is never called in atomic context. It calls kzalloc() with GFP_ATOMIC, which is not necessary. GFP_ATOMIC can be replaced with GFP_KERNEL. This is found by a static analysis tool named DCNS written by myself. Signed-off-by:
Jia-Ju Bai <baijiaju1990@gmail.com> Signed-off-by:
-
