- 02 Sep, 2014 40 commits
-
-
David S. Miller authored
Sathya Perla says: ==================== be2net: patch set v2 changes: add a new line after variable declaration in patch 12. *** Patch 1 adds a few new log messages to help debugging in failure cases. Patch 2 uses new macros for parsing RX/TX completions and TX wrbs to help shorten the lines. Patch 3 adds a description for the RX counter rx_input_fifo_overflow_drop. Patch 4 adds TX completion error statistics reporting via ethtool. Patch 5 adds a dma_mapping_error counter and its reporting via ethtool. Patch 6 fixes up log messages in the Lancer FW download path. Patch 7 replaces gotos with direct return statements. Patch 8 cleans up be_change_mtu() code by using a new macro BE_MAX_MTU Patch 9 makes be_cmd_get_regs() routine to return an integer status similar to other FW cmd routines in be_cmds.c Patch 10 gets rid of TX budget as enforcing a budget on TX completion processing in NAPI is neither suggested nor it provides a performance benefit. Patch 11 defines and uses a new macro for_all_tx_queues_on_eq() similar to the RX processing code. Patch 12 queries max_tx_qs from the FW for BE3 super-nic profiles. For those profiles, the driver cannot assume a constant BE3_MAX_TX_QS value, as the value may change for each function. Please consider applying this patch set to the net-next tree. Thanks! ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Suresh Reddy authored
In the BE3 super-nic profile, the max_tx_qs value can vary for each function. So the driver needs to query this value from FW instead of using the pre-defined constant BE3_MAX_TX_QS. Signed-off-by:
Suresh Reddy <Suresh.Reddy@emulex.com> Signed-off-by:
Sathya Perla <sathya.perla@emulex.com> Signed-off-by:
-
Sathya Perla authored
Replace the for() loop that traverses all the TX queues on an EQ with the macro for_all_tx_queues_on_eq(). With this expalnatory name, the one line comment is not required anymore. Signed-off-by:
-
Sathya Perla authored
Enforcing a budget on the TX completion processing in NAPI doesn't benefit performance in anyway. Just get rid of it. Signed-off-by:
-
Vasundhara Volam authored
There are a few failure cases in be_cmd_get_regs() that ideally must return an error value. This style is used across all the routines in be_cmds.c with this routine being an exception. This patch fixes this. Signed-off-by:
Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by:
-
Kalesh AP authored
This patch defines a new macro BE_MAX_MTU to make the code in be_change_mtu() more readable. Signed-off-by:
Kalesh AP <kalesh.purayil@emulex.com> Signed-off-by:
-
Kalesh AP authored
In cases where there is no extra code to handle an error, this patch replaces gotos with a direct return statement. Signed-off-by:
-
Kalesh AP authored
Log messages in the Lancer FW download path have issues such as: - a single message spanning multiple lines - the success message is logged even in failure cases - status codes are already logged in the FW cmd routines This patch fixes these issues. Signed-off-by:
-
Vasundhara Volam authored
Add a dma_mapping_error counter to count the number of packets dropped due to DMA mapping errors. Signed-off-by:
-
Kalesh AP authored
HW reports TX completion errors in TX completion. This patch adds these counters to ethtool statistics. Signed-off-by:
-
Sathya Perla authored
Signed-off-by:
-
Sathya Perla authored
The AMAP_GET/SET_BITS() macro calls take structure name as a parameter and hence are long and span more than one line. Replace these calls with a wrapper macros for RX/Tx compls and TX wrb. This results in fewer lines and more readable code in be_main.c Signed-off-by:
-
Sathya Perla authored
This patch adds the following log messages to help debugging failure cases: 1) log FW version number: this is useful when driver initialization fails and the FW version number cannot be queried via ethtool 2) per function resource limits for BEx chips: these values are currently being printed only for Skyhawk and Lancer 3) PCI BAR mapping failure 4) function_mode/caps queried from FW: this helps catch any FW bugs that could advertise wrong capabilities to the driver Signed-off-by:
-
Willem de Bruijn authored
sk->sk_error_queue is dequeued in four locations. All share the exact same logic. Deduplicate. Also collapse the two critical sections for dequeue (at the top of the recv handler) and signal (at the bottom). This moves signal generation for the next packet forward, which should be harmless. It also changes the behavior if the recv handler exits early with an error. Previously, a signal for follow-up packets on the errqueue would then not be scheduled. The new behavior, to always signal, is arguably a bug fix. For rxrpc, the change causes the same function to be called repeatedly for each queued packet (because the recv handler == sk_error_report). It is likely that all packets will fail for the same reason (e.g., memory exhaustion). This code runs without sk_lock held, so it is not safe to trust that sk->sk_err is immutable inbetween releasing q->lock and the subsequent test. Introduce int err just to avoid this potential race. Signed-off-by:
Willem de Bruijn <willemb@google.com> Signed-off-by:
-
Willem de Bruijn authored
Expand Documentation/networking/timestamping.txt with new interfaces and bytestream timestamping. Also minor cleanup of the other text. Import txtimestamp.c test of the new features. Signed-off-by:
-
David S. Miller authored
Tom Herbert says: ==================== net: Checksum offload changes - Part VI I am working on overhauling RX checksum offload. Goals of this effort are: - Specify what exactly it means when driver returns CHECKSUM_UNNECESSARY - Preserve CHECKSUM_COMPLETE through encapsulation layers - Don't do skb_checksum more than once per packet - Unify GRO and non-GRO csum verification as much as possible - Unify the checksum functions (checksum_init) - Simplify code What is in this seventh patch set: - Add skb->csum. This allows a device or GRO to indicate that an invalid checksum was detected. - Checksum unncessary to checksum complete conversions. With these changes, I believe that the third goal of the overhaul is now mostly achieved. In the case of no encapsulation or one layer of encapsulation, there should only be at most one skb_checksum over each packet (between GRO and normal path). In the case of two layers of encapsulation, it is still possible with the right combination of non-zero and zero UDP checksums to have >1 skb_checksum. For instance: IP>GRE(with csum)>IP>UDP(zero csum)>VXLAN>IP>UDP(non-zero csum), would likely necessiate an skb_checksum in GRO and normal path. This doesn't seem like a common scenario at all so I'm inclined to not address this now, if multiple layers of encapsulation becomes popular we can reassess. Note that checksum conversion shows a nice improvement for RX VXLAN when outer UDP checksum is enabled (12.65% CPU compared to 20.94%). This is not only from the fact that we don't need checksum calculation on the host, but also allows GRO for VXLAN in this case. Checksum conversion does not help send side (which still needs to perform a checksum on host). For that we will implement remote checksum offload in a later patch (http://tools.ietf.org/html/draft-herbert-remotecsumoffload-00). Please review carefully and test if possible, mucking with basic checksum functions is always a little precarious :-) ==================== Signed-off-by:
-
Tom Herbert authored
Signed-off-by:
Tom Herbert <therbert@google.com> Signed-off-by:
-
Tom Herbert authored
Signed-off-by:
-
Tom Herbert authored
Call skb_checksum_try_convert and skb_gro_checksum_try_convert after checksum is found present and validated in the GRE header for normal and GRO paths respectively. In GRO path, call skb_gro_checksum_try_convert Signed-off-by:
-
Tom Herbert authored
Add support for doing CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion in UDP tunneling path. In the normal UDP path, we call skb_checksum_try_convert after locating the UDP socket. The check is that checksum conversion is enabled for the socket (new flag in UDP socket) and that checksum field is non-zero. In the UDP GRO path, we call skb_gro_checksum_try_convert after checksum is validated and checksum field is non-zero. Since this is already in GRO we assume that checksum conversion is always wanted. Signed-off-by:
-
Tom Herbert authored
For normal path, added skb_checksum_try_convert which is called to attempt to convert CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE. The primary condition to allow this is that ip_summed is CHECKSUM_NONE and csum_valid is true, which will be the state after consuming a CHECKSUM_UNNECESSARY. For GRO path, added skb_gro_checksum_try_convert which is the GRO analogue of skb_checksum_try_convert. The primary condition to allow this is that NAPI_GRO_CB(skb)->csum_cnt == 0 and NAPI_GRO_CB(skb)->csum_valid is set. This implies that we have consumed all available CHECKSUM_UNNECESSARY checksums in the GRO path. Signed-off-by:
-
Tom Herbert authored
This flag indicates that an invalid checksum was detected in the packet. __skb_mark_checksum_bad helper function was added to set this. Checksums can be marked bad from a driver or the GRO path (the latter is implemented in this patch). csum_bad is checked in __skb_checksum_validate_complete (i.e. calling that when ip_summed == CHECKSUM_NONE). csum_bad works in conjunction with ip_summed value. In the case that ip_summed is CHECKSUM_NONE and csum_bad is set, this implies that the first (or next) checksum encountered in the packet is bad. When ip_summed is CHECKSUM_UNNECESSARY, the first checksum after the last one validated is bad. For example, if ip_summed == CHECKSUM_UNNECESSARY, csum_level == 1, and csum_bad is set-- then the third checksum in the packet is bad. In the normal path, the packet will be dropped when processing the protocol layer of the bad checksum: __skb_decr_checksum_unnecessary called twice for the good checksums changing ip_summed to CHECKSUM_NONE so that __skb_checksum_validate_complete is called to validate the third checksum and that will fail since csum_bad is set. Signed-off-by:
-
hayeswang authored
The variable "rx_buf_sz" is used by both tx and rx buffers. Replace it with "agg_buf_sz". Signed-off-by:
Hayes Wang <hayeswang@realtek.com> Signed-off-by:
-
Florian Fainelli authored
drivers/net/phy/mdio-bcm-unimac.c:195:37-38: unimac_mdio_ids is not NULL terminated at line 195 Make sure of_device_id tables are NULL terminated Generated by: scripts/coccinelle/misc/of_table.cocci Signed-off-by:
Fengguang Wu <fengguang.wu@intel.com> Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Florian Fainelli authored
net/dsa/dsa.c:624:20: sparse: symbol 'dsa_pack_type' was not declared. Should it be static? Fixes: 3e8a72d1 ("net: dsa: reduce number of protocol hooks") Signed-off-by:
-
Nikolay Aleksandrov authored
This patch adds support for slave_changelink to the bonding and uses it to give the ability to change the queue_id of the enslaved devices via netlink. It sets slave_maxtype and uses bond_changelink as a prototype for bond_slave_changelink. Example/test command after the iproute2 patch: ip link set eth0 type bond_slave queue_id 10 CC: David S. Miller <davem@davemloft.net> CC: Jay Vosburgh <j.vosburgh@gmail.com> CC: Veaceslav Falico <vfalico@gmail.com> CC: Andy Gospodarek <andy@greyhouse.net> Suggested-by:
Jiri Pirko <jiri@resnulli.us> Signed-off-by:
Nikolay Aleksandrov <nikolay@redhat.com> Acked-by:
-
stephen hemminger authored
Fix places where there is space before tab, long lines, and awkward if(){, double spacing etc. Add blank line after declaration/initialization. Signed-off-by:Stephen Hemminger <stephen@networkplumber.org> Signed-off-by:
-
Florian Fainelli authored
When Broadcom tags are enabled, e.g: when interfaced to an Ethernet switch, make sure that we tell the RXCHK engine that it should be expecting a 4-bytes Broadcom tag after the Ethernet MAC Source Address. Use netdev_uses_dsa() to check for that condition since that will tell us if a switch is attached to our network interface. Fixes: 80105bef ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by:
-
Jesper Dangaard Brouer authored
Then testing the TX limits of the stack, then it is useful to be-able to disable the do_gettimeofday() timetamping on every packet. This implements a pktgen flag NO_TIMESTAMP which will disable this call to do_gettimeofday(). The performance change on (my system E5-2695) with skb_clone=0, goes from TX 2,423,751 pps to 2,567,165 pps with flag NO_TIMESTAMP. Thus, the cost of do_gettimeofday() or saving is approx 23 nanosec. Signed-off-by:
Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by:
-
Dmitry Kravkov authored
Set correct bit for packed description. Introduced in e42780b6 bnx2x: Utilize FW 7.10.51 Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Dmitry Kravkov <Dmitry.Kravkov@qlogic.com> Signed-off-by:
-
Dmitry Kravkov authored
Fixes incorrectly defined struct in FW HSI for BE platform. Affects tunneling, tx-switching and anti-spoofing. Introduced in e42780b6 bnx2x: Utilize FW 7.10.51 Reported-by:
-
Erik Hugne authored
TIPC name table updates are distributed asynchronously in a cluster, entailing a risk of certain race conditions. E.g., if two nodes simultaneously issue conflicting (overlapping) publications, this may not be detected until both publications have reached a third node, in which case one of the publications will be silently dropped on that node. Hence, we end up with an inconsistent name table. In most cases this conflict is just a temporary race, e.g., one node is issuing a publication under the assumption that a previous, conflicting, publication has already been withdrawn by the other node. However, because of the (rtt related) distributed update delay, this may not yet hold true on all nodes. The symptom of this failure is a syslog message: "tipc: Cannot publish {%u,%u,%u}, overlap error". In this commit we add a resiliency queue at the receiving end of the name table distributor. When insertion of an arriving publication fails, we retain it in this queue for a short amount of time, assuming that another update will arrive very soon and clear the conflict. If so happens, we insert the publication, otherwise we drop it. The (configurable) retention value defaults to 2000 ms. Knowing from experience that the situation described above is extremely rare, there is no risk that the queue will accumulate any large number of items. Signed-off-by:Erik Hugne <erik.hugne@ericsson.com> Signed-off-by:
Jon Maloy <jon.maloy@ericsson.com> Acked-by:
Ying Xue <ying.xue@windriver.com> Signed-off-by:
-
Erik Hugne authored
We need to perform the same actions when processing deferred name table updates, so this functionality is moved to a separate function. Signed-off-by:
-
hayeswang authored
Because the Tx has the features of stopping queue and aggregation, We don't need many tx buffers. Change the tx number from 10 to 4 to reduce the usage of the memory. This could save 16K * 6 bytes memory. Signed-off-by:
-
David S. Miller authored
David Miller says: ==================== net: Make dev_hard_start_xmit() work fundamentally on lists After this patch set, dev_hard_start_xmit() will work fundemantally on any and all SKB lists. This opens the path for a clean implementation of pulling multiple packets out during qdisc_restart(), and then passing that blob in one shot to dev_hard_start_xmit(). There were two main architectural blockers to this: 1) The GSO handling, we kept the original GSO head SKB around simply because dev_hard_start_xmit() had no way to communicate to the caller how far into the segmented list it was able to go. Now it can, so the head GSO can be liberated immediately. All of the special GSO head SKB destructor et al. handling goes away too. 2) Validate of VLAN, CSUM, and segmentation characteristics was being performed inside of dev_hard_start_xmit(). If want to truly batch, we have to let the higher levels to this. In particular, this is now dequeue_skb()'s job. And with those two issues out of the way, it should now be trivial to build experiments on top of this patch set, all of the framework should be there now. You could do something as simple as: skb = q->dequeue(q); if (skb) skb = validate_xmit_skb(skb, qdisc_dev(q)); if (skb) { struct sk_buff *new, *head = skb; int limit = 5; do { new = q->dequeue(q); if (new) new = validate_xmit_skb(new, qdisc_dev(q)); if (new) { skb->next = new; skb = new; } } while (new && --limit); skb = head; } inside of the else branch of dequeue_skb(). Signed-off-by: -
David S. Miller authored
Now fundamentally we can process lists of SKBs as cheaply as single packets. Signed-off-by: -
David S. Miller authored
Just maintain the list properly by returning the head of the remaining SKB list from dev_hard_start_xmit(). Signed-off-by: -
David S. Miller authored
Signed-off-by: -
David S. Miller authored
dev_hard_start_xmit() does two things, it first validates and canonicalizes the SKB, then it actually sends it. Make a set of helper functions for doing the first part. Signed-off-by: -
David S. Miller authored
Signed-off-by:
-
