- 11 Sep, 2016 40 commits
-
-
David S. Miller authored
David Ahern says: ==================== net: Convert vrf to tx hook The motivation for this series is that ICMP Unreachable - Fragmentation Needed packets are not handled properly for VRFs. Specifically, the FIB lookup in __ip_rt_update_pmtu fails so no nexthop exception is created with the reduced MTU. As a result connections stall if packets larger than the smallest MTU in the path are generated. While investigating that problem I also noticed that the MSS for all connections in a VRF is based on the VRF device's MTU and not the route the packets ultimately go through. VRF currently uses a dst to direct packets to the device. The first FIB lookup returns this dst and then the lookup in the VRF driver gets the actual output route. A side effect of this design is that the VRF dst is cached on sockets and then used for calculations like the MSS. This series fixes this problem by removing the hook in the FIB lookups that returns the dst pointing to the VRF device to the VRF and always doing the actual FIB lookup. This allows the real dst to be used throughout the stack (for example the MSS). Packets are diverted to the VRF device on Tx using an l3mdev hook in the output path similar to to what is done for Rx. The end result is a simpler implementation for VRF with fewer intrusions into the network stack and symmetrical packet handling for Rx and Tx paths. Comparison of netperf performance for a build without l3mdev (best case performance), the old vrf driver and the VRF driver from this series. Data are collected using VMs with virtio + vhost. The netperf client runs in the VM and netserver runs in the host. 1-byte RR tests are done as these packets exaggerate the performance hit due to the extra lookups done for l3mdev and VRF. Command: netperf -cC -H ${ip} -l 60 -t {TCP,UDP}_RR [-J red] TCP_RR UDP_RR IPv4 IPv6 IPv4 IPv6 no l3mdev 29,996 30,601 31,638 24,336 vrf old 27,417 27,626 29,159 24,801 vrf new 28,036 28,372 30,110 24,857 l3mdev, no vrf 29,534 30,465 30,670 24,346 * Transactions per second as reported by netperf * netperf modified to take a bind-to-device argument -- the -J red option 1. 'no l3mdev' == NET_L3_MASTER_DEV is unset so code is compiled out 2. 'vrf old' == data for existing implementation 3. 'vrf new' == data with this series 4. 'l3mdev, no vrf' == NET_L3_MASTER_DEV is enabled but traffic is not going through a VRF About the series - patch 1 adds the flow update (changing oif or iif to L3 master device and setting the flag to skip the oif check) to ipv4 and ipv6 paths just before hitting the rules. This catches all code paths in a single spot. - patch 2 adds the Tx hook to push the packet to the l3mdev if relevant - patch 3 adds some checks so the vrf device can act as a vrf-local loopback. These changes were not needed before since the vrf dst was returned from the lookup. - patches 4 and 5 flip the ipv4 and ipv6 stacks to the tx hook leaving the route lookup to be the real one. The dst flip happens at the beginning of the L3 output path so the VRFs can have device based features such as netfilter, tc and tcpdump. - patches 6-11 remove no longer needed l3mdev code v2 - properly handle IPv6 link scope addresses - keep the device xmit path and associated dst which is switched in by the l3_out hook. packets still need to go through the xmit path in case the user puts a qdisc on the vrf device and to allow tc rules. version 1 short circuited the tx handling and only covered netfilter and tcpdump. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
David Ahern authored
No longer used Signed-off-by:
David Ahern <dsa@cumulusnetworks.com> Signed-off-by:
-
David Ahern authored
No longer used Signed-off-by:
-
David Ahern authored
No longer used Signed-off-by:
-
David Ahern authored
No longer needed Signed-off-by:
-
David Ahern authored
No longer needed Signed-off-by:
-
David Ahern authored
A previous patch added l3mdev flow update making these hooks redundant. Remove them. Signed-off-by:
-
David Ahern authored
Flip the IPv6 output path to use the l3mdev tx out hook. The VRF dst is not returned on the first FIB lookup. Instead, the dst on the skb is switched at the beginning of the IPv6 output processing to send the packet to the VRF driver on xmit. Link scope addresses (linklocal and multicast) need special handling: specifically the oif the flow struct can not be changed because we want the lookup tied to the enslaved interface. ie., the source address and the returned route MUST point to the interface scope passed in. Convert the existing vrf_get_rt6_dst to handle only link scope addresses. Signed-off-by:
-
David Ahern authored
Flip the IPv4 output path to use the l3mdev tx out hook. The VRF dst is not returned on the first FIB lookup. Instead, the dst on the skb is switched at the beginning of the IPv4 output processing to send the packet to the VRF driver on xmit. Signed-off-by:
-
David Ahern authored
Allow an L3 master device to act as the loopback for that L3 domain. For IPv4 the device can also have the address 127.0.0.1. Signed-off-by:
-
David Ahern authored
This patch adds the infrastructure to the output path to pass an skb to an l3mdev device if it has a hook registered. This is the Tx parallel to l3mdev_ip{6}_rcv in the receive path and is the basis for removing the existing hook that returns the vrf dst on the fib lookup. Signed-off-by: -
David Ahern authored
Add l3mdev hook to set FLOWI_FLAG_SKIP_NH_OIF flag and update oif/iif in flow struct if its oif or iif points to a device enslaved to an L3 Master device. Only 1 needs to be converted to match the l3mdev FIB rule. This moves the flow adjustment for l3mdev to a single point catching all lookups. It is redundant for existing hooks (those are removed in later patches) but is needed for missed lookups such as PMTU updates. Signed-off-by:
-
Markus Elfring authored
Adjust the indentation for a call of the macro "DPRINTK" in this function. Signed-off-by:
Markus Elfring <elfring@users.sourceforge.net> Signed-off-by:
-
Markus Elfring authored
* The script "checkpatch.pl" can point information out like the following. WARNING: Prefer kcalloc over kzalloc with multiply Thus fix the affected source code place. * Replace the specification of a data type by a pointer dereference to make the corresponding size determination a bit safer according to the Linux coding style convention. * Delete the local variable "size" which became unnecessary with this refactoring. Signed-off-by:
-
Markus Elfring authored
Replace the specification of a data structure by a pointer dereference as the parameter for the operator "sizeof" to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Markus Elfring authored
* A multiplication for the size determination of a memory allocation indicated that an array data structure should be processed. Thus use the corresponding function "kmalloc_array". This issue was detected by using the Coccinelle software. * Replace the specification of a data type by a pointer dereference to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Markus Elfring authored
The script "checkpatch.pl" can point out that assignments should usually not be performed within condition checks. Thus move an assignment for a local variable to a separate statement in this function. Signed-off-by:
-
Markus Elfring authored
* The script "checkpatch.pl" can point out that assignments should usually not be performed within condition checks. Thus move an assignment for a local variable to a separate statement in this function. * Replace the specification of a data structure by a pointer dereference as the parameter for the operator "sizeof" to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Markus Elfring authored
Replace the specification of a data structure by a reference for a field in a local variable as the parameter for the operator "sizeof" to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Markus Elfring authored
Replace the specification of a data structure by a pointer dereference as the parameter for the operator "sizeof" to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Markus Elfring authored
* A multiplication for the size determination of a memory allocation indicated that an array data structure should be processed. Thus use the corresponding function "kmalloc_array". This issue was detected by using the Coccinelle software. * Replace the specification of a data type by a pointer dereference to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
-
Eric Dumazet authored
Willem noticed that we could avoid an rbtree lookup if the the attempt to coalesce incoming skb to the last skb failed for some reason. Since most ooo additions are at the tail, this is definitely worth adding a test and fast path. Suggested-by:
Willem de Bruijn <willemb@google.com> Signed-off-by:
Eric Dumazet <edumazet@google.com> Cc: Yaogong Wang <wygivan@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by:
-
Thadeu Lima de Souza Cascardo authored
When userspace tries to create datapaths and the module is not loaded, it will simply fail. With this patch, the module will be automatically loaded. Signed-off-by:
Thadeu Lima de Souza Cascardo <cascardo@redhat.com> Acked-by:
Pravin B Shelar <pshelar@ovn.org> Signed-off-by:
-
Stephen Hemminger authored
These functions are used by other code misc-next tree. This reverts commit 30d1de08. Signed-off-by:
Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by:
-
David S. Miller authored
Saeed Mahameed says: ==================== Mellanox 100G mlx5 seamless error recovery This series from Mohamad improves the driver load/unload flows to seamlessly handle pci errors and device internal errors recovery reset flows. Current pci and internal error handling is too heavy and is done with a full restart of the driver by unregistering mlx5 interfaces (mlx5e netedevs and mlx5_ib) which will cause losing all the current interfaces and mlx5 core configurations. To improve this, we add new callback functions of mlx5 interface object (attach/detach) to be called upon reset flows when errors are detected rather than calling register and unregister interfaces. On their side, interfaces such as (mlx5e and mlx5_ib) can choose to implement those callback, if not, the old heavy reset will be called for that interface. For non-interface mlx5 modules such as sriov and eswitch, we refactored and reorganized the code in a way that the software state objects are created only once on driver load. Those software state objects are kept upon reset recovery flows and only freed once on driver unload. On seamless soft reset flows, only hardware resources are released on stop and re-allocated on start according to the current soft state. In this series only mlx5e interface implements attach/detach callbacks so that the netdevice will be kept alive on reset. On detach only hardware resources are released and the netdevice will be marked as detached to the stack. Once attached again it will re-allocate the hardware resources according to the current netdevice state, and all the configurations and the software state will be kept or restored after recovery. Note: I will be out of office all next week, in case of any updates or V2 is required, Tariq will post the new series, I hope it is ok. ==================== Signed-off-by: -
Mohamad Haj Yahia authored
Hide the exposed (external) mlx5_dev_list and mlx5_intf_mutex and expose an organized modular API to manage and manipulate mlx5 devices list. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
-
Mohamad Haj Yahia authored
When detaching the mlx5e interface clear all the vlans rules from the vlan flow table. When attaching it back restore all the active vlans rules to the HW. Signed-off-by:
-
Mohamad Haj Yahia authored
Needed to support seamless and lightweight PCI/Internal error recovery. Implement the attach/detach interface callbacks. In attach callback we only allocate HW resources. In detach callback we only deallocate HW resources. All SW/kernel objects initialzing/destroying is kept in add/remove callbacks. Signed-off-by:
-
Mohamad Haj Yahia authored
Save the user configuration in the vport sturct. Restore saved old configuration upon vport enable. Signed-off-by:
-
Mohamad Haj Yahia authored
Init/cleanup sriov/eswitch in the core software context init/cleanup flows. Attach/detach sriov/eswitch in the core load/unload flows. Signed-off-by:
-
Mohamad Haj Yahia authored
Needed for lightweight and modular internal/pci error handling. Implement eswitch attach function which allocates/starts hw related resources. Implement eswitch detach function which releases/stops hw related resources. Init/cleanup function only handle eswitch software context allocation and destruction. Signed-off-by:
-
Mohamad Haj Yahia authored
Needed for lightweight and modular internal/pci error handling. Implement sriov attach function which enables pre-saved number of vfs on the device side. Implement sriov detach function which disable the current vfs on the device side. Init/cleanup function only handles sriov software context allocation and destruction. Signed-off-by:
-
Mohamad Haj Yahia authored
Gather all software context creating/destroying in one function and call it once in the first load and in the last unload. load/unload functions will now receive indication if we need to create/destroy the software contexts. In internal/pci error do the unload/load flows without releasing the software objects. In this way we perserve the sw core state and it help us restoring old driver state after PCI error/shutdown. Signed-off-by:
-
Mohamad Haj Yahia authored
Add attach/detach callbacks to interface API. This is crucial for implementing seamless reset flow which releases the hardware and it's resources upon detach while keeping software structures and state (e.g netdev) then reset and reallocate the hardware needed resources upon attach. Signed-off-by:
-
Mohamad Haj Yahia authored
Simplify the code and makes it look modular and symmetric. Split sriov enable/disable to two levels: device level and pci level. When user enable/disable sriov (via sriov_configure driver callback) we will enable/disable both device and pci sriov. When driver load/unload we will enable/disable (on demand) only device sriov while keeping the PCI sriov enabled for next driver load. On internal/pci error, VFs will be kept enabled on PCI and the reset is done only in device level. Signed-off-by:
-
Mohamad Haj Yahia authored
In case of device in internal error state there is no need to wait for vf pages since they will be reclaimed manually later in the unload flow. Signed-off-by:
-
David S. Miller authored
Javier Martinez Canillas says: ==================== net: use IS_ENABLED() instead of checking for built-in or module This trivial series replace the open coding to check for a Kconfig symbol being built-in or module, with IS_ENABLED() macro that does exactly that. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. ==================== Signed-off-by: -
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Neil Horman <nhorman@tuxdriver.com> Signed-off-by:
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
-
