- 18 Jun, 2015 2 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queueDavid S. Miller authored
Jeff Kirsher says: ==================== This series contains updates to fm10k only. Alex provides two fixes for the fm10k, first folds the fm10k_pull_tail() call into fm10k_add_rx_frag(), this way the fragment does not have to be modified after it is added to the skb. The second fixes missing braces to an if statement. The remaining patches are from Jacob which contain improvements and fixes for fm10k. First fix makes it so that invalid address will simply be skipped and allows synchronizing the full list to proceed with using iproute2 tool. Fixed a possible kernel panic by using the correct transmit timestamp function. Simplified the code flow for setting the IN_PROGRESS bit of the shinfo for an skb that we will be timestamping. Fix a bug in the timestamping transmit enqueue code responsible for a NULL pointer dereference and invalid access of the skb list by freeing the clone in the cases where we did not add it to the queue. Update the PF code so that it resets the empty TQMAP/RQMAP regirsters post-VFLR to prevent innocent VF drivers from triggering malicious driver events. The SYSTIME_CFG.Adjust direction bit is actually supposed to indicate that the adjustment is positive, so fix the code to align correctly with the hardware and documentation. Cleanup local variable that is no longer used after a previous refactor of the code. Fix the code flow so that we actually clear the enabled flag as part of our removal of the LPORT. v2: - updated patch 07 description based on feedback from Sergei Shtylyov - updated patch 09 & 10 to use %d in error message based on feedback from Sergei Shtylyov ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Romain Perier authored
These kind of informations are only useful for debugging and should not be displayed in normal modules message. Signed-off-by:
Romain Perier <romain.perier@gmail.com> Signed-off-by:
-
- 17 Jun, 2015 17 commits
-
-
Alexander Duyck authored
While reviewing the code I noticed that one of the commits added an if statement followed by a for loop, but the if statement was missing the braces around the loop. This change corrects the coding style error. Signed-off-by:
Alexander Duyck <alexander.h.duyck@redhat.com> Acked-by:
Jacob Keller <jacob.e.keller@intel.com> Tested-by:
Krishneil Singh <Krishneil.k.singh@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Jacob Keller authored
When a VF issues an LPORT_STATE request to enable a port that is already enabled, the PF will first disable the VF LPORT. Then it should re-enable the VF again with the new requested settings. This ensures that any switch rules are cleared by deleting the LPORT on the switch. However, the flow is bugged because we actually check if the VF is enabled at the end, and thus don't re-enable it. Fix the flow so that we actually clear the enabled flags as part of our removal of the LPORT. Signed-off-by:
-
Jacob Keller authored
The reference to err_no was left around after a previous code refactor. We never use the value, and it doesn't seem to be used in side a hidden macro reference. Discovered via cppcheck. Signed-off-by:
-
Jacob Keller authored
The SYSTIME_CFG.Adjust Direction bit is actually supposed to indicate that the adjustment is positive. Fix the code to align correctly with hardware and documentation. Signed-off-by:
-
Jacob Keller authored
This patch adds the __attribute__((packed)) indicator to some structures which are overlayed onto a TLV message. These structures must be packed as small as possible in order to correctly align when copied into the mailbox buffer. Without doing so, the receiving mailbox code incorrectly parses the values and we get invalid message responses from the switch manager software. Signed-off-by:
-
Jacob Keller authored
During initialization, the VF counts its rings by walking the TQDLOC registers. This works only if the TQMAP/RQMAP registers are set to map all of the out-of-bound rings back to the first one. This allows the VF to cleanly detect when it has run out of queues. Update the PF code so that it resets the empty TQMAP/RQMAP registers post-VFLR to prevent innocent VF drivers from triggering malicious driver events. Signed-off-by:
Matthew Vick <matthew.vick@intel.com> Signed-off-by:
-
Jacob Keller authored
Currently, we don't notify the switch at all when the PF administratively sets a new VLAN or MAC address. This causes the old addresses to remain valid on the switch table. Since the PF is overriding any configuration done directly by the VF, we choose to simply re-create the LPORT for the VF. This does mean that all rules for the VF will be dropped when we set something directly via the PF, but it prevents some weird issues where the MAC/VLAN table retains some stale configuration. Signed-off-by:
-
Jacob Keller authored
This patch cleans up the use of dma_get_required_mask and uses the simpler dma_set_mask_and_coherent function instead of doing these as separate steps. I removed the dma_get_required_mask call because based on some minimal testing it appears that either (a) we're not doing the right thing with the call or (b) we don't need it anyways. If the value returned is <48bits, we'll end up trying with 48 bits anyways. If it's over 48bits, fm10k can't support that anyways, and we should try 48bits. If 48bits fails, we'll fallback to 32bits. This cleans up some very funky code. Signed-off-by:
-
Jacob Keller authored
Also use %d for error values, since printing in hexadecimal is probably not helpful. Signed-off-by:
-
Jacob Keller authored
l2_accel was checked for NULL at the top of fm10k_dfwd_del_station, and we return if it is not defined. Due to this, we already know it can't be null here so a separate check is meaningless. Discovered via cppcheck. Signed-off-by:
-
Jacob Keller authored
The value will never be negative, and we use the %u print format. Thus, use unsigned int for the loop counter. Issue found using cppcheck. Signed-off-by:
-
Jacob Keller authored
This prevents a memory leak in fm10k_set_ringparams. The leak occurs because we go down, change ring parameters, and then come up. However, fm10k_down on its own is not clearing the Rx rings. Since fm10k_up assumes the rings are clean we basically drop the buffers and leak a bunch of memory. Eventually we hit dirty page faults and reboot the system. This issue does not occur elsewhere because other flows that involve fm10k_down go through fm10k_close which immediately called fm10k_free_all_rx_resources which properly cleans the rings. Signed-off-by:
-
Jacob Keller authored
This patch resolves a bug in the ts_tx_enqueue code responsible for a NULL pointer dereference and invalid access of the skb list. We incorrectly freed the actual skb we found instead of our copy. Thus the skb queue is essentially invalidated. Resolve this by freeing our clone in the cases where we did not add it to the queue. This also avoids the skb memory leak caused by failure to free the clone. [ 589.719320] BUG: unable to handle kernel NULL pointer dereference at (null) [ 589.722344] IP: [<ffffffffa0310e60>] fm10k_ts_tx_subtask+0xb0/0x160 [fm10k] [ 589.723796] PGD 0 [ 589.725228] Oops: 0000 [#1] SMP Signed-off-by:
-
Jacob Keller authored
This patch simplifies the code flow for setting the IN_PROGRESS bit of the shinfo for an skb we will be timestamping. Reported-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
-
Jacob Keller authored
skb_complete_tx_timestamp is intended for use by PHY drivers which implement a different method of returning timestamps. This method is intended to be used after a PHY driver accepts a cloned packet via its phy_driver.txtstamp function. It is not correct to use in the standard ethernet driver such as fm10k. This patch fixes the following possible kernel panic. [ 2744.552896] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W OE 3.19.3-200.fc21.x86_64 #1 [ 2744.552899] Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.03.8x23.060520140825 06/05/2014 [ 2744.552901] 0000000000000000 2f4c8b10ea3f9848 ffff88081ee03a38 ffffffff8176e215 [ 2744.552906] 0000000000000000 0000000000000000 ffff88081ee03a78 ffffffff8109bc1a [ 2744.552910] ffff88081ee03c50 ffff88080e55fc00 ffff88080e55fc00 ffffffff81647c50 [ 2744.552914] Call Trace: [ 2744.552917] <IRQ> [<ffffffff8176e215>] dump_stack+0x45/0x57 [ 2744.552931] [<ffffffff8109bc1a>] warn_slowpath_common+0x8a/0xc0 [ 2744.552936] [<ffffffff81647c50>] ? skb_queue_purge+0x20/0x40 [ 2744.552941] [<ffffffff8109bd4a>] warn_slowpath_null+0x1a/0x20 [ 2744.552946] [<ffffffff81646911>] skb_release_head_state+0xe1/0xf0 [ 2744.552950] [<ffffffff81647b26>] skb_release_all+0x16/0x30 [ 2744.552954] [<ffffffff81647ba6>] kfree_skb+0x36/0x90 [ 2744.552958] [<ffffffff81647c50>] skb_queue_purge+0x20/0x40 [ 2744.552964] [<ffffffff81751f8d>] packet_sock_destruct+0x1d/0x90 [ 2744.552968] [<ffffffff81642053>] __sk_free+0x23/0x140 [ 2744.552973] [<ffffffff81642189>] sk_free+0x19/0x20 [ 2744.552977] [<ffffffff81647d60>] skb_complete_tx_timestamp+0x50/0x60 [ 2744.552988] [<ffffffffa02eee40>] fm10k_ts_tx_hwtstamp+0xd0/0x100 [fm10k] [ 2744.552994] [<ffffffffa02e054e>] fm10k_1588_msg_pf+0x12e/0x140 [fm10k] [ 2744.553002] [<ffffffffa02edf1d>] fm10k_tlv_msg_parse+0x8d/0xc0 [fm10k] [ 2744.553010] [<ffffffffa02eb2d0>] fm10k_mbx_dequeue_rx+0x60/0xb0 [fm10k] [ 2744.553016] [<ffffffffa02ebf98>] fm10k_sm_mbx_process+0x178/0x3c0 [fm10k] [ 2744.553022] [<ffffffffa02e09ca>] fm10k_msix_mbx_pf+0xfa/0x360 [fm10k] [ 2744.553030] [<ffffffff811030a7>] ? get_next_timer_interrupt+0x1f7/0x270 [ 2744.553036] [<ffffffff810f2a47>] handle_irq_event_percpu+0x77/0x1a0 [ 2744.553041] [<ffffffff810f2bab>] handle_irq_event+0x3b/0x60 [ 2744.553045] [<ffffffff810f5d6e>] handle_edge_irq+0x6e/0x120 [ 2744.553054] [<ffffffff81017414>] handle_irq+0x74/0x140 [ 2744.553061] [<ffffffff810bb54a>] ? atomic_notifier_call_chain+0x1a/0x20 [ 2744.553066] [<ffffffff8177777f>] do_IRQ+0x4f/0xf0 [ 2744.553072] [<ffffffff8177556d>] common_interrupt+0x6d/0x6d [ 2744.553074] <EOI> [<ffffffff81609b16>] ? cpuidle_enter_state+0x66/0x160 [ 2744.553084] [<ffffffff81609b01>] ? cpuidle_enter_state+0x51/0x160 [ 2744.553087] [<ffffffff81609cf7>] cpuidle_enter+0x17/0x20 [ 2744.553092] [<ffffffff810de101>] cpu_startup_entry+0x321/0x3c0 [ 2744.553098] [<ffffffff81764497>] rest_init+0x77/0x80 [ 2744.553103] [<ffffffff81d4f02c>] start_kernel+0x4a4/0x4c5 [ 2744.553107] [<ffffffff81d4e120>] ? early_idt_handlers+0x120/0x120 [ 2744.553110] [<ffffffff81d4e4d7>] x86_64_start_reservations+0x2a/0x2c [ 2744.553114] [<ffffffff81d4e62b>] x86_64_start_kernel+0x152/0x175 Signed-off-by:
-
Jacob Keller authored
This change fixes an issue with adding an invalid multicast address using the iproute2 tool (ip maddr add <MADDR> dev <dev>). The iproute2 tool and the kernel do not validate or filter the multicast addresses when adding them to the multicast list. Thus, when synchronizing this list with an invalid entry, the action will be aborted with an error since the fm10k driver currently validates the list. Consequently, multicast entries beyond the invalid one will not be processed and communicated with the switch via the mailbox. This change makes it so that invalid addresses will simply be skipped and allows synchronizing the full list to proceed. Signed-off-by:
Ngai-Mint Kwan <ngai-mint.kwan@intel.com> Signed-off-by:
-
Alexander Duyck authored
This change folds the fm10k_pull_tail call into fm10k_add_rx_frag. The advantage to doing this is that the fragment doesn't have to be modified after it is added to the skb. Signed-off-by:
-
- 16 Jun, 2015 21 commits
-
-
Alexei Starovoitov authored
Accessing current->pid/uid from cls_bpf may lead to misleading results and should not be used when TC classifiers need accurate information about pid/uid. Signed-off-by:
Alexei Starovoitov <ast@plumgrid.com> Signed-off-by:
-
Edward Cree authored
Without this change, modprobe -r sfc hits the BUG_ON() in efx_pci_remove_main(). Fixes: e7fef9b4 ("sfc: add sysfs entry to control MCDI tracing") Reported-by:
Jarod Wilson <jarod@redhat.com> Reviewed-by:
Edward Cree <ecree@solarflare.com> Signed-off-by:
-
David S. Miller authored
Craig Gallek says: ==================== Socket destruction events via netlink sock_diag This series extends the netlink sock_diag interface to broadcast socket information as they are being destroyed. The current interface is poll based and can not be used to retreive information about sockets that are destroyed between poll intervals. Only inet sockets are broadcast in this implementation, but other families could easily be added as needed in the future. If this patch set is accepted, a follow-up patch to the ss utility in the iproute2 suite will also be submitted. ==================== Signed-off-by: -
Craig Gallek authored
This get_info handler will simply dispatch to the appropriate existing inet protocol handler. This patch also includes a new netlink attribute (INET_DIAG_PROTOCOL). This attribute is currently only used for multicast messages. Without this attribute, there is no way of knowing the IP protocol used by the socket information being broadcast. This attribute is not necessary in the 'dump' variant of this protocol (though it could easily be added) because dump requests are issued for specific family/protocol pairs. Tested: ss -E (note, the -E option has not yet been merged into the upstream version of ss). Signed-off-by:
Craig Gallek <kraig@google.com> Acked-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Craig Gallek authored
Previously, there was no clear distinction between the inet protocols that used struct tcp_info to report information and those that didn't. This change adds a specific size attribute to the inet_diag_handler struct which defines these interfaces. This will make dispatching sock_diag get_info requests identical for all inet protocols in a following patch. Tested: ss -au Tested: ss -at Signed-off-by:
-
Craig Gallek authored
These groups will contain socket-destruction events for AF_INET/AF_INET6, IPPROTO_TCP/IPPROTO_UDP. Near the end of socket destruction, a check for listeners is performed. In the presence of a listener, rather than completely cleanup the socket, a unit of work will be added to a private work queue which will first broadcast information about the socket and then finish the cleanup operation. Signed-off-by:
-
David S. Miller authored
Or Gerlitz says: ==================== mlx4 driver update (+ new VF ndo) This series from Eran and Hadar is further dealing with traffic counters in the mlx4 driver, this time mostly around SRIOV. We added a new ndo to read the VF counters through the PF netdev netlink infrastructure plus mlx4 implementation for that ndo. changes from V0: - applied feedback from John to use nested netlink encoding for the VF counters so we can extend it later - add handling of single ported VFs in the mlx4_en driver new ndo - avoid chopping the FW counters from 64 to 32 bits in mlx4_en PF flow ==================== Signed-off-by: -
Eran Ben Elisha authored
Implement the ndo to gather VF statistics through the PF. All counters related to this VF are stored in a per slave list, run over the slave's list and collect all statistics. Signed-off-by:
Eran Ben Elisha <eranbe@mellanox.com> Signed-off-by:
Hadar Hen Zion <hadarh@mellanox.com> Signed-off-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
-
Eran Ben Elisha authored
Add ndo_get_vf_stats where the PF retrieves and fills the VFs traffic statistics. We encode the VF stats in a nested manner to allow for future extensions. Signed-off-by:
-
Eran Ben Elisha authored
Allow the user to observe the PF own statistics using ethtool with pf_ prefixed counter names. Those counters are the PF statistics out of the overall port statistics. Every PF QP is attached to a counter and the summary of those counters is the PF statistics. Signed-off-by:
-
Eran Ben Elisha authored
This is an infrastructure step for querying VF and PF counters. This code was in the IB driver, move it to the mlx4 core driver so it will be accessible for more use cases. Signed-off-by:
-
Eran Ben Elisha authored
As IB VFs are not capable to read the port counters through MADs, move there to read their own QP counters to gather statistics. Signed-off-by:
-
Eran Ben Elisha authored
This is an infrastructure step to attach all the QPs opened from the IB driver to a counter in order to collect VF stats from the PF using those counters. If the port's type is Ethernet, the counter policy demands two counters per port (one for RoCE and one for Ethernet). The port default counter (allocated in mlx4_core) is used for the Ethernet netdev QPs and we allocate another counter for RoCE. If the port's traffic is Infiniband, the counter policy demands one counter per port, so it can use the port's default counter. Also, Add 'allocated' flag for each counter in order to clean it at unload. Signed-off-by:
-
Eran Ben Elisha authored
Default counter per port will be allocated at the mlx4 core driver load. Every QP opened by the Ethernet driver will be attached to the port's default counter. This is an infrastructure step to collect VF statistics from the PF. Signed-off-by:
-
Eran Ben Elisha authored
Counter will get its port attribute within the resource tracker when the first QP attached to it is modified to RTR. If a QP is counter-less, an attempt to create a new counter with assigned port will be made. Signed-off-by:
-
Eran Ben Elisha authored
Each physical function has a guarantee of two counters per port, one for a default counter and one for the IB driver. Each virtual function has a guarantee of one counter per port. All other counters are free and can be obtained on demand. This is a preparation step for supporting a get_vf_stats ndo call, so we can promise a counter for every VF in order to collect their statistics from the PF context. Signed-off-by:
-
Eran Ben Elisha authored
Since virtual functions get their counters indices allocation from the PF, allocate counters indices bitmap only in case the function isn't virtual. Also, check that the device has counters to allocate before creating the indices bitmap table. Signed-off-by:
-
Eran Ben Elisha authored
Reserve the last valid counter index for "sink" counter, when a new counter cannot be allocated, the driver will use this counter. In order to avoid allocating this counter on any other flow, fix the indices bitmap allocation range, and reserve the sink counter index. Add macro for the sink counter index and replace all appearences of the index with the macro. Signed-off-by:
-
Eran Ben Elisha authored
Add resetting the counter data to the free counter flow, so the counter's data won't be accessible anymore if querying the counter. Also, on next counter allocation (to another VM for example), it will be fresh and clear. Signed-off-by:
-
Eran Ben Elisha authored
If counters are not supported by the device. The indices bitmap table is not allocated during initialization. Add the symmetrical check before cleaning the counters bitmap table or freeing a counter. Signed-off-by:
-
Scott Feldman authored
We need to delete from offload the device externally learnded fdbs when any one of these events happen: 1) Bridge ages out fdb. (When bridge is doing ageing vs. device doing ageing. If device is doing ageing, it would send SWITCHDEV_FDB_DEL directly). 2) STP state change flushes fdbs on port. 3) User uses sysfs interface to flush fdbs from bridge or bridge port: echo 1 >/sys/class/net/BR_DEV/bridge/flush echo 1 >/sys/class/net/BR_PORT/brport/flush 4) Offload driver send event SWITCHDEV_FDB_DEL to delete fdb entry. For rocker, we can now get called to delete fdb entry in wait and nowait contexts, so set NOWAIT flag when deleting fdb entry. Signed-off-by:
Scott Feldman <sfeldma@gmail.com> Signed-off-by:
-
