- 09 Feb, 2015 9 commits
-
-
Mitch Williams authored
During VF deallocation, we need to lock out the VF reset code. However, we cannot depend on simply masking the interrupt, as this does not lock out the service task, which can still call the reset routine. Instead, leave the interrupt enabled, but add locking around the VF disable and reset routines. For the disable code, we wait to get the lock, as the reset code will take a finite amount of time to run. For the reset code, we just return if we fail to get the lock. Since we know that the VFs are being disabled, we don't need to handle the reset. This fixes a panic when disabling SR-IOV. Change-ID: Iea0a6cdef35c331f48c6d5b2f8e6f0e86322e7d8 Signed-off-by:
Mitch Williams <mitch.a.williams@intel.com> Tested-by:
Jim Young <james.m.young@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Mitch Williams authored
When enabling 64 VFs and loading the VF driver in the host kernel, we can easily overrun the PF's admin receive queue. Double the size of this queue, and increase the work limit to allow the PF to handle more requests in a single pass through the service task. Change-ID: I0efbbdc61954bffad422a2f33c4b948a59370bf5 Signed-off-by:
-
Mitch Williams authored
Delay a minimum of 10ms after VF reset, to allow the hardware's internal FIFOs to flush. Change-ID: I8a02ddb28c9f0d7303a1eb21d0b2443e5b4c1cda Signed-off-by:
-
John W Linville authored
This I40E_FCOE block increments v_budget before it has been initialized, then v_budget gets overwritten a few lines later. This patch just reorders the code hunks in what I believe was the intended sequence. Coverity: CID 12600999Signed-off-by:
John W Linville <linville@tuxdriver.com> Tested-by:
-
Rickard Strandqvist authored
Remove the function i40e_rx_is_fip() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by:
Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se> Tested-by:
-
Shrikrishna Khare authored
The hex constant chosen for VMXNET3_REV1_MAGIC is offensive, replace it with its decimal equivalent. Signed-off-by:
Shrikrishna Khare <skhare@vmware.com> Reviewed-by:
Shreyas Bhatewara <sbhatewara@vmware.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
Receive Flow Steering is a nice solution but suffers from hash collisions when a mix of connected and unconnected traffic is received on the host, when flow hash table is populated. Also, clearing flow in inet_release() makes RFS not very good for short lived flows, as many packets can follow close(). (FIN , ACK packets, ...) This patch extends the information stored into global hash table to not only include cpu number, but upper part of the hash value. I use a 32bit value, and dynamically split it in two parts. For host with less than 64 possible cpus, this gives 6 bits for the cpu number, and 26 (32-6) bits for the upper part of the hash. Since hash bucket selection use low order bits of the hash, we have a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big enough. If the hash found in flow table does not match, we fallback to RPS (if it is enabled for the rxqueue). This means that a packet for an non connected flow can avoid the IPI through a unrelated/victim CPU. This also means we no longer have to clear the table at socket close time, and this helps short lived flows performance. Signed-off-by:
Eric Dumazet <edumazet@google.com> Acked-by:
Tom Herbert <therbert@google.com> Signed-off-by:
-
Sabrina Dubroca authored
Remove trailing underscore. Signed-off-by:
Sabrina Dubroca <sd@queasysnail.net> Signed-off-by:
-
Sabrina Dubroca authored
encap.sport and encap.dport are __be16, use nla_{get,put}_be16 instead of nla_{get,put}_u16. Fixes the sparse warnings: warning: incorrect type in assignment (different base types) expected restricted __be32 [addressable] [usertype] o_key got restricted __be16 [addressable] [usertype] i_flags warning: incorrect type in assignment (different base types) expected restricted __be16 [usertype] sport got unsigned short warning: incorrect type in assignment (different base types) expected restricted __be16 [usertype] dport got unsigned short warning: incorrect type in argument 3 (different base types) expected unsigned short [unsigned] [usertype] value got restricted __be16 [usertype] sport warning: incorrect type in argument 3 (different base types) expected unsigned short [unsigned] [usertype] value got restricted __be16 [usertype] dport Signed-off-by:
-
- 08 Feb, 2015 31 commits
-
-
Jon Paul Maloy authored
In commit c637c103 ("tipc: resolve race problem at unicast message reception") we introduced a time limit for how long the function tipc_sk_eneque() would be allowed to execute its loop. Unfortunately, the test for when this limit is passed was put in the wrong place, resulting in a lost message when the test is true. We fix this by moving the test to before we dequeue the next buffer from the input queue. Signed-off-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
-
Michael Büsch authored
rt6_probe allocates a struct __rt6_probe_work and schedules a work handler rt6_probe_deferred. But rt6_probe_deferred kfree's the struct work_struct instead of struct __rt6_probe_work. This works, because struct work_struct is the first element of struct __rt6_probe_work. Change it to kfree struct __rt6_probe_work to not implicitly depend on struct work_struct being the first element. This does not affect the generated code. Signed-off-by:
Michael Buesch <m@bues.ch> Signed-off-by:
-
David S. Miller authored
Neal Cardwellsays: ==================== tcp: mitigate TCP ACK loops due to out-of-window validation dupacks This patch series mitigates "ack loop" DoS scenarios by rate-limiting outgoing duplicate ACKs sent in response to incoming "out of window" segments. Background ----------- There are several cases in which the TCP RFCs specify that a TCP endpoint should send a pure duplicate ACK in response to a pure duplicate ACK that appears to be invalid due to being "out of window": (1) RFC 793 (section 3.9, page 69) specifies that endpoints should send a duplicate ACK in response to an ACK when the incoming sequence number is invalid due to being outside the receive window: "If an incoming segment is not acceptable, an acknowledgment should be sent in reply". (2) RFC 793 (section 3.9, page 72) says: "If the ACK acknowledges something not yet sent (SEG.ACK > SND.NXT) then send an ACK". (3) RFC 1323 (section 4.2.1, page 18) specifies that endpoints should send a duplicate ACK in response to an ACK when the PAWS check for the incoming timestamp value fails: "If .... SEG.TSval < TS.Recent and if TS.Recent is valid ... Send an acknowledgement in reply" The problem ------------ Normally, this is not a problem. However, a buggy middlebox or malicious man-in-the-middle can inject a few packets into the conversation that advance each endpoint's notion of the current window (sequence, ACK, or timestamp), without either side noticing. In this case, from then on each side can think the other is sending invalid segments. Thus an infinite feedback loop of duplicate ACKs can ensue, as each endpoint receives a duplicate ACK, decides that it is invalid (due to sequence number, ACK number, or timestamp), and then sends a dupack in reply, which the other side decides is invalid, responding with a dupack... ad infinitum. This ping-pong feedback loop can happen at a very high rate. This phenomenon can and does happen in practice. It has been seen in datacenter and Internet contexts at Google, and has been documented by Anil Agarwal in the Nov 2013 tcpm thread "TCP mismatched sequence numbers issue", and Avery Fay in the Feb 2015 Linux netdev thread "Invalid timestamp? causing tight ack loop (hundreds of thousands of packets / sec)". This patch series ------------------ This patch series mitigates such ack loops by rate-limiting outgoing duplicate ACKs sent in response to incoming TCP packets that are for an existing connection but that are invalid due to any of the reasons mentioned above: sequence number (1), ACK field (2), or timestamp value (3). The rate limit for such duplicate ACKs is specified by a new sysctl, tcp_invalid_ratelimit, which specifies the minimal space between such outbound duplicate ACKs, in milliseconds. The default is 500 (500ms), and 0 disables the mechanism. We rate-limit these duplicate ACK responses rather than blocking them entirely or resetting the connection, because legitimate connections can rely on dupacks in response to some out-of-window segments. For example, zero window probes are typically sent with a sequence number that is below the current window, and ZWPs thus expect to thus elicit a dupack in response. Testing: this approach has been in use at Google for a while. ==================== Signed-off-by: -
Neal Cardwell authored
Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is represented by a tcp_timewait_sock, we rate limit dupacks in response to incoming packets (a) with TCP timestamps that fail PAWS checks, or (b) with sequence numbers that are out of the acceptable window. We do not send a dupack in response to out-of-window packets if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a dupack in response to an out-of-window packet. Reported-by:
Avery Fay <avery@mixpanel.com> Signed-off-by:
Neal Cardwell <ncardwell@google.com> Signed-off-by:
Yuchung Cheng <ycheng@google.com> Signed-off-by:
-
Neal Cardwell authored
Ensure that in state ESTABLISHED, where the connection is represented by a tcp_sock, we rate limit dupacks in response to incoming packets (a) with TCP timestamps that fail PAWS checks, or (b) with sequence numbers or ACK numbers that are out of the acceptable window. We do not send a dupack in response to out-of-window packets if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a dupack in response to an out-of-window packet. There is already a similar (although global) rate-limiting mechanism for "challenge ACKs". When deciding whether to send a challence ACK, we first consult the new per-connection rate limit, and then the global rate limit. Reported-by:
-
Neal Cardwell authored
In the SYN_RECV state, where the TCP connection is represented by tcp_request_sock, we now rate-limit SYNACKs in response to a client's retransmitted SYNs: we do not send a SYNACK in response to client SYN if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a SYNACK in response to a client's retransmitted SYN. This allows the vast majority of legitimate client connections to proceed unimpeded, even for the most aggressive platforms, iOS and MacOS, which actually retransmit SYNs 1-second intervals for several times in a row. They use SYN RTO timeouts following the progression: 1,1,1,1,1,2,4,8,16,32. Reported-by:
-
Neal Cardwell authored
Helpers for mitigating ACK loops by rate-limiting dupacks sent in response to incoming out-of-window packets. This patch includes: - rate-limiting logic - sysctl to control how often we allow dupacks to out-of-window packets - SNMP counter for cases where we rate-limited our dupack sending The rate-limiting logic in this patch decides to not send dupacks in response to out-of-window segments if (a) they are SYNs or pure ACKs and (b) the remote endpoint is sending them faster than the configured rate limit. We rate-limit our responses rather than blocking them entirely or resetting the connection, because legitimate connections can rely on dupacks in response to some out-of-window segments. For example, zero window probes are typically sent with a sequence number that is below the current window, and ZWPs thus expect to thus elicit a dupack in response. We allow dupacks in response to TCP segments with data, because these may be spurious retransmissions for which the remote endpoint wants to receive DSACKs. This is safe because segments with data can't realistically be part of ACK loops, which by their nature consist of each side sending pure/data-less ACKs to each other. The dupack interval is controlled by a new sysctl knob, tcp_invalid_ratelimit, given in milliseconds, in case an administrator needs to dial this upward in the face of a high-rate DoS attack. The name and units are chosen to be analogous to the existing analogous knob for ICMP, icmp_ratelimit. The default value for tcp_invalid_ratelimit is 500ms, which allows at most one such dupack per 500ms. This is chosen to be 2x faster than the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule 2.4). We allow the extra 2x factor because network delay variations can cause packets sent at 1 second intervals to be compressed and arrive much closer. Reported-by:
-
Pravin B Shelar authored
Flow alloc needs to initialize unmasked key pointer. Otherwise it can crash kernel trying to free random unmasked-key pointer. general protection fault: 0000 [#1] SMP 3.19.0-rc6-net-next+ #457 Hardware name: Supermicro X7DWU/X7DWU, BIOS 1.1 04/30/2008 RIP: 0010:[<ffffffff8111df0e>] [<ffffffff8111df0e>] kfree+0xac/0x196 Call Trace: [<ffffffffa060bd87>] flow_free+0x21/0x59 [openvswitch] [<ffffffffa060bde0>] ovs_flow_free+0x21/0x23 [openvswitch] [<ffffffffa0605b4a>] ovs_packet_cmd_execute+0x2f3/0x35f [openvswitch] [<ffffffffa0605995>] ? ovs_packet_cmd_execute+0x13e/0x35f [openvswitch] [<ffffffff811fe6fb>] ? nla_parse+0x4f/0xec [<ffffffff8139a2fc>] genl_family_rcv_msg+0x26d/0x2c9 [<ffffffff8107620f>] ? __lock_acquire+0x90e/0x9aa [<ffffffff8139a3be>] genl_rcv_msg+0x66/0x89 [<ffffffff8139a358>] ? genl_family_rcv_msg+0x2c9/0x2c9 [<ffffffff81399591>] netlink_rcv_skb+0x3e/0x95 [<ffffffff81399898>] ? genl_rcv+0x18/0x37 [<ffffffff813998a7>] genl_rcv+0x27/0x37 [<ffffffff81399033>] netlink_unicast+0x103/0x191 [<ffffffff81399382>] netlink_sendmsg+0x2c1/0x310 [<ffffffff811007ad>] ? might_fault+0x50/0xa0 [<ffffffff8135c773>] do_sock_sendmsg+0x5f/0x7a [<ffffffff8135c799>] sock_sendmsg+0xb/0xd [<ffffffff8135cacf>] ___sys_sendmsg+0x1a3/0x218 [<ffffffff8113e54b>] ? get_close_on_exec+0x86/0x86 [<ffffffff8115a9d0>] ? fsnotify+0x32c/0x348 [<ffffffff8115a720>] ? fsnotify+0x7c/0x348 [<ffffffff8113e5f5>] ? __fget+0xaa/0xbf [<ffffffff8113e54b>] ? get_close_on_exec+0x86/0x86 [<ffffffff8135cccd>] __sys_sendmsg+0x3d/0x5e [<ffffffff8135cd02>] SyS_sendmsg+0x14/0x16 [<ffffffff81411852>] system_call_fastpath+0x12/0x17 Fixes: 74ed7ab9("openvswitch: Add support for unique flow IDs.") CC: Joe Stringer <joestringer@nicira.com> Reported-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
Pravin B Shelar <pshelar@nicira.com> Acked-by:
-
David S. Miller authored
Hariprasad Shenai says: ==================== Add support to dump some hw debug info This patch series adds support to dump sensor info, dump Transport Processor event trace, dump Upper Layer Protocol RX module command trace, dump mailbox contents and dump Transport Processor congestion control configuration. Will send a separate patch series for all the hw stats patches, by moving them to ethtool. The patches series is created against 'net-next' tree. And includes patches on cxgb4 driver. We have included all the maintainers of respective drivers. Kindly review the change and let us know in case of any review comments. V2: Dopped all hw stats related patches. Added a new patch which adds support to dump congestion control table. ==================== Signed-off-by: -
Hariprasad Shenai authored
Dump Transport Processor modules congestion control configuration Signed-off-by:
Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by:
-
Hariprasad Shenai authored
Adds support to dump the current contents of mailbox and the driver which owns it. Signed-off-by:
-
Hariprasad Shenai authored
Dump Upper Layer Protocol RX module command trace Signed-off-by:
-
Hariprasad Shenai authored
Dump Transport Processor event trace. Signed-off-by:
-
Hariprasad Shenai authored
Dump out various chip sensor information. Currently Chip Temperature and Core Voltage. Signed-off-by:
-
David S. Miller authored
Sathya Perla says: ==================== be2net: patch set Hi Dave, pls consider applying the following patch-set to the net-next tree. It has 5 code/style cleanup patches and 4 patches that add functionality to the driver. Patch 1 moves routines that were not needed to be in be.h to the respective src files, to avoid unnecessary compilation. Patch 2 replaces (1 << x) with BIT(x) macro Patch 3 refactors code that checks if a FW flash file is compatible with the adapter. The code is now refactored into 2 routines, the first one gets the file type from the image file and the 2nd routine checks if the file type is compatible with the adapter. Patch 4 adds compatibility checks for flashing a FW image on the new Skyhawk P2 HW revision. Patch 5 adds support for a new "offset based" flashing scheme, wherein the driver informs the FW of the offset at which each component in the flash file is to be flashed at. This helps flashing components that were previously not recognized by the running FW. Patch 6 simplifies the be_cmd_rx_filter() routine, by passing to it the filter flags already used in the FW cmd, instead of the netdev flags that were converted to the FW-cmd flags. Patch 7 introduces helper routines in be_set_rx_mode() and be_vid_config() to improve code readability. Patch 8 adds processing of port-misconfig async event sent by the FW. Patch 9 removes unnecessary swapping of a field in the TX desc. ==================== Signed-off-by: -
Sathya Perla authored
The 32-bit fields of a tx-wrb are little endian. The driver is currently using be_dws_le_to_cpu() routine to swap (cpu to le) all the fields of a tx-wrb. So, the rsvd field is also unnecessarily swapped. This patch fixes this by individually swapping the required fields. Also, the type of the fields in eth_tx_wrb{} is now changed to __le32 from u32 to avoid sparse warnings. Signed-off-by:Sathya Perla <sathya.perla@emulex.com> Signed-off-by:
-
Vasundhara Volam authored
This patch adds support for processing the port misconfigure async event generated by the FW. This event is generated typically when an optical module is incorrectly installed or is faulty. This patch also moves the port_name field to the adapter struct for logging the event. As the be_cmd_query_port_name() call is now moved to be_get_config(), it is modified to use the mailbox instead of MCCQ Signed-off-by:
-
Sathya Perla authored
This patch re-factors the filter setting (uc-list, mc-list, promisc, vlan) code in be_set_rx_mode() and be_vid_config() to make it more readable and reduce code duplication. This patch adds a separate field to track the state/mode of filtering, along with moving all the filtering related fields to one place in be be_adapter structure. Signed-off-by:
-
Sathya Perla authored
This patch passes BE_IF_FLAGS_XXX flags to be_cmd_rx_filter() routine instead of the IFF_XXX flags. Doing this gets rid of the code to convert the IFF_XXX flags to the BE_IF_FLAGS_XXX used by the FW cmd. The patch also removes code for setting if_flags_mask that was duplicated for each filter mode. Signed-off-by:
Kalesh AP <kalesh.purayil@emulex.com> Signed-off-by:
-
Vasundhara Volam authored
While sending FW update cmds to the FW, the driver specifies the "type" of each component that needs to be flashed. The FW then picks the offset in the flash area at which the componnet is to be flashed. This doesn't work when new components that the current FW doesn't recognize, need to be flashed. Recent FWs (10.2 and above) support a scheme of FW-update wherein the "offset" of the component in the flash area can be specified instead of the "type". This patch uses the "offset" based FW-update mechanism and only when it fails, it fallsback to the old "type" based update. Signed-off-by:
Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by:
-
Vasundhara Volam authored
Skyhawk-B0 FW UFI is not compatible to flash on Skyhawk-P2 ASIC. But, Skyhawk-P2 FW UFI is compatible with both B0 and P2 chips. Signed-off-by:
-
Vasundhara Volam authored
This patch re-factors the code that checks for flash file compatibility with the chip type, for better readability, as follows: - be_get_ufi_type() returns the UFI type from the flash file - be_check_ufi_compatibility() checks if the UFI type is compatible with the adapter/chip that is being flashed Signed-off-by:
-
Vasundhara Volam authored
BIT(x) is the preffered usage. Signed-off-by:
-
Sathya Perla authored
Routines that are called only inside one src file must remain in that file itself. Including them in a header file that is used for exporting routine/struct definitions, causes unnecessary compilation of other src files, when such a routine is modified. Signed-off-by:
-
Roopa Prabhu authored
This patch fixes a missing bridge port check caught by smatch. setlink/dellink of attributes like vlans can come for a bridge device and there is no need to offload those today. So, this patch adds a bridge port check. (In these cases however, the BRIDGE_SELF flags will always be set and we may not hit a problem with the current code). smatch complaint: The patch 68e331c7: "bridge: offload bridge port attributes to switch asic if feature flag set" from Jan 29, 2015, leads to the following Smatch complaint: net/bridge/br_netlink.c:552 br_setlink() error: we previously assumed 'p' could be null (see line 518) net/bridge/br_netlink.c 517 518 if (p && protinfo) { ^ Check for NULL. Reported-By:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-nextDavid S. Miller authored
Jeff Kirsher says: ==================== Intel Wired LAN Driver Updates 2015-02-05 This series contains updates to fm10k, ixgbe and ixgbevf. Matthew fixes an issue where fm10k does not properly drop the upper-most four bits on of the VLAN ID due to type promotion, so resolve the issue by not masking off the bits, but by throwing an error if the VLAN ID is out-of-bounds. Then cleans up two cases where variables were not being used, but were being set, so just remove the unused variables. Don cleans up sparse errors in the x550 family file for ixgbe. Fixed up a redundant setting of the default value for set_rxpba, which was done twice accidentally. Cleaned up the probe routine to remove a redundant attempt to identify the PHY, which could lead to a panic on x550. Added support for VXLAN receive checksum offload in x550 hardware. Added the Ethertype Anti-spoofing feature for affected devices. Emil enables ixgbe and ixgbevf to allow multiple queues in SRIOV mode. Adds RSS support for x550 per VF. Fixed up a couple of issues introduced in commit 2b509c0c ("ixgbe: cleanup ixgbe_ndo_set_vf_vlan"), fixed setting of the VLAN inside ixgbe_enable_port_vlan() and disable the "hide VLAN" bit in PFQDE when port VLAN is disabled. Cleaned up the setting of vlan_features by enabling all features at once. Fixed the ordering of the shutdown patch so that we attempt to shutdown the rings more gracefully. We shutdown the main Rx filter in the case of Rx and we set the carrier_off state in the case of Tx so that packets stop being delivered from outside the driver. Then we shutdown interrupts and NAPI, then finally stop the rings from performing DMA and clean them. Added code to allow for Tx hang checking to provide more robust debug info in the event of a transmit unit hang in ixgbevf. Cleaned up ixgbevf logic dealing with link up/down by breaking down the link detection and up/down events into separate functions, similar to how these events are handled in other drivers. Combined the ixgbevf reset and watchdog tasks into a single task so that we can avoid multiple schedules of the reset task when we have a reset event needed due to either the mailbox going down or transmit packets being present on a link down. v2: Fixed up patch #03 of the series to remove the variable type change based on feedback from David Laight ==================== Signed-off-by:
-
David S. Miller authored
Hayes Wang says: ==================== r8152: adjust the code V2: Correct the subject of patch #5. Replace "link feed" with "line feed". v1: Code adjustment. ==================== Signed-off-by: -
hayeswang authored
Use BIT macro to replace (1 << bits). Signed-off-by:
Hayes Wang <hayeswang@realtek.com> Signed-off-by:
-
hayeswang authored
vlan_get_protocol() has been defined and use it to replace get_protocol(). Signed-off-by:
-
hayeswang authored
Keep NETIF_F_HW_VLAN_CTAG_RX and NETIF_F_HW_VLAN_CTAG_TX at the same line. Signed-off-by:
-
hayeswang authored
It is unnecessary to accress the hw register if the device is unplugged. Signed-off-by:
-
