- 09 May, 2015 40 commits
-
-
Eric Dumazet authored
With the advent of small rto timers in datacenter TCP, (ip route ... rto_min x), the following can happen : 1) Qdisc is full, transmit fails. TCP sets a timer based on icsk_rto to retry the transmit, without exponential backoff. With low icsk_rto, and lot of sockets, all cpus are servicing timer interrupts like crazy. Intent of the code was to retry with a timer between 200 (TCP_RTO_MIN) and 500ms (TCP_RESOURCE_PROBE_INTERVAL) 2) Receivers can send zero windows if they don't drain their receive queue. TCP sends zero window probes, based on icsk_rto current value, with exponential backoff. With /proc/sys/net/ipv4/tcp_retries2 being 15 (or even smaller in some cases), sender can abort in less than one or two minutes ! If receiver stops the sender, it obviously doesn't care of very tight rto. Probability of dropping the ACK reopening the window is not worth the risk. Lets change the base timer to be at least 200ms (TCP_RTO_MIN) for these events (but not normal RTO based retransmits) A followup patch adds a new SNMP counter, as it would have helped a lot diagnosing this issue. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
Yuchung Cheng <ycheng@google.com> Acked-by:
Neal Cardwell <ncardwell@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Richard Alpe authored
The legacy netlink API treated EPERM (permission denied) as "operation not supported". Reported-by:
Tomi Ollila <tomi.ollila@iki.fi> Signed-off-by:
Richard Alpe <richard.alpe@ericsson.com> Reviewed-by:
Erik Hugne <erik.hugne@ericsson.com> Reviewed-by:
Ying Xue <ying.xue@windriver.com> Signed-off-by:
-
Richard Alpe authored
Add the ability to get or set the broadcast link window through the new netlink API. The functionality was unintentionally missing from the new netlink API. Adding this means that we also fix the breakage in the old API when coming through the compat layer. Fixes: 37e2d484 (tipc: convert legacy nl link prop set to nl compat) Reported-by:
-
Richard Alpe authored
Default link properties can be set for media or bearer. This functionality was missed when introducing the NL compatibility layer. This patch implements this functionality in the compat netlink layer. It works the same way as it did in the old API. We search for media and bearers matching the "link name". If we find a matching media or bearer the link tolerance, priority or window is used as default for new links on that media or bearer. Fixes: 37e2d484 (tipc: convert legacy nl link prop set to nl compat) Reported-by:
-
Hariprasad Shenai authored
Implements t4_init_rss_mode() to initialize the rss_mode for all the ports. If Tunnel All Lookup isn't specified in the global RSS Configuration, then we need to specify a default Ingress Queue for any ingress packets which aren't hashed. We'll use our first ingress queue. Signed-off-by:
Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by:
-
David S. Miller authored
Sathya Perla says: ==================== be2net: patch-set The following patch-set has two new feature additions, and a few minor fixes and cleanups. Pls consider applying to the net-next tree. Thanks. v2 changes: a) dropped the "don't enable pause by default" patch b) described how the "spoof check" works in patch 1's commit log c) I had to update our email addresses from "@emulex" to "@avagotech". I'll send a separate patch updating the maintainers Patch 1 adds support for the "spoofchk" knob for VFs. When it is enabled, "spoof checking" is done for both MAC-address and VLAN. For each VF, the HW ensures that the source MAC address (or vlan) of every outgoing packet of the VF exists in the MAC-list (or vlan-list) configured for RX filtering for that VF. If not, the packet is dropped and an error is reported to the driver in the TX completion. Patch 2 improves interrupt moderation on Skyhawk-R chip by using the EQ-DB mechanism to set a "re-arm to interrupt" delay. Currently interrupt moderation is adjusted by calculating and configuring an EQ-delay every second. This is done via a FW-cmd. This patch uses the EQ_DB facility to calculate and set the interrupt delay every 1ms. This helps moderating interrupts better when the traffic is bursty. Patch 3 adds L3/L4 error accounting to BE3 VFs, by passing L3/4 error packets to the network stack. Patch 4 adds an extra FW-cmd error value check in the driver to identify an "out of vlan filters" scenario. Patch 5 stops enabling pause by default as this setting fails in some HW-configs where priority pause is enabled in FW. If the user tries to do the same, an appropriate error is returned via ethtool. Patch 5 posts the full RXQ in be_open() to prevent packet drops due to bursty traffic when the interface is enabled. Patch 6 refactors the be_check_ufi_compatibility() routine, that checks to see if a UFI file meant for a lower rev of a chip is being flashed on a higher rev, to make it simpler. Patch 7 replaces the usage of !be_physfn() macro with be_virtfn() that is already avialble in the driver. Patch 8 updates the year in the copyright text to 2015. Path 9 bumps up the driver version to 10.6.02. ==================== Signed-off-by: -
Sathya Perla authored
Signed-off-by:
Sathya Perla <sathya.perla@avagotech.com> Signed-off-by:
-
Vasundhara Volam authored
Signed-off-by:
Vasundhara Volam <vasundhara.volam@avagotech.com> Signed-off-by:
-
Kalesh AP authored
Use be_virtfn() to determine a VF instead of !be_physfn() for better readability. Signed-off-by:
-
Vasundhara Volam authored
The code in be_check_ufi_compatibility() checks to see if a UFI file meant for a lower rev of a chip is being flashed on a higher rev, which is disallowed. This patch re-writes the code needed for this check in a much simpler manner. Signed-off-by:
-
Suresh Reddy authored
When an RXQ is created in be_open(), the driver currently posts only 64 buffers. This sometimes results in packet drops when there is a traffic burst as soon as the interface is enabled. This patch fixes this problem by posting the full RXQ on interface enable. Signed-off-by:
Suresh Reddy <Suresh.Reddy@avagotech.com> Signed-off-by:
-
Kalesh AP authored
When the FW runs out of vlan filters it can either return an INSUFFICIENT_RESOURCES error or an INSUFFICIENT_VLANS error. The driver currently checks only for the former error value. This patch adds a check for the latter value too. Signed-off-by:
Kalesh AP <kalesh.purayil@emulex.com> Signed-off-by:
-
Somnath Kotur authored
Currently pkts with L3 or L4 errors received on PFs are not dropped by the adapter, but instead sent to the stack. This helps the network stack to better reflect error statistics. This was not being done on BE3 VFs. This patch fixes this for BE3 VFs. Signed-off-by:
Somnath Kotur <somnath.kotur@avagotech.com> Signed-off-by:
-
Padmanabh Ratnakar authored
Currently adaptive interrupt moderation is set by calculating and configuring an EQ-delay every second. This is done via a FW-cmd. But, on Skyhawk-R a "re-arm to interrupt" delay can be set while ringing the EQ-DB. This patch uses this facility to calculate and set the interrupt delay every 1ms. This helps moderating interrupts better when the traffic is bursty. Signed-off-by:
Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com> Signed-off-by:
-
Kalesh AP authored
This patch adds support for spoofchk configuration for VFs. When it is enabled, "spoof checking" is done for both MAC-address and VLAN. For each VF, the HW ensures that the source MAC address (or vlan) of every outgoing packet exists in the MAC-list (or vlan-list) configured for RX filtering for that VF. If not, the packet is dropped and an error is reported to the driver in the TX completion; this is reflected in the "tx_spoof_check_err" ethtool counter. This feature is supported in Skyhawk FW version 10.6.31.0 and above. Signed-off-by:
-
David S. Miller authored
Shradha Shah says: ==================== sfc: Enabling EF10 Vf's, set up vswitching and bind the SFC driver to the VF's This set of patches makes way for the implementation of EF10 SR-IOV driver starting with some cleanup code. NIC specific SR-IOV functions are moved to their own header and netdev_ops are made generic instead of being NIC specific Next in line comes the patch to enable VF's using sriov_configure. VEB vswitching hierarchy is set up next followed by patches to prepare sfc driver to bind to enabled VF's This is followed by patch to support use of shared RSS contexts which makes VF's use shared RSS contexts in all cases. Patch series ends with a patch to bind the sfc driver to the enabled VF's which creates network interfaces corresponding to the VF's. Coming up soon are the patches to set_vf_mac, set_vf_config, set_vf_vlan, vf_spoofcheck, etc. These patches have been tested with and without CONFIG_SFC_SRIOV. In the case of CONFIG_SFC_SRIOV=y enabling of VF's using sriov_configure is also tested. The enabled VF's bind to the installed sfc driver succesfully to create network interfaces. In the case of CONFIG_SFC_SRIOV=n enabling of VF's using sriov_configure returns the correct error message: "Function not implemented". ==================== Signed-off-by: -
Shradha Shah authored
Add the device ID of the VF to the PCI device ID table. Added a boolean flag is_vf in efx_nic_type to differentiate between a VF and PF at probe time. This flag is useful in later patches while setting MAC address specially in the PCI-passthrough case. Signed-off-by:
Shradha Shah <sshah@solarflare.com> Signed-off-by:
-
Jon Cooper authored
Allow PFs to allocate shared RSS contexts if we exhaust our exclusive RSS contexts. Make VFs use shared RSS contexts in all cases. Spruce up error handling so that the shadow copy of the RSS table is updated after successful update, rather than in all cases, so that we report the actual contents of the RSS table after a failure to set it, rather than what we'd like it to be. Populate context_size parameter when vacuously allocating RSS context of size 1. Signed-off-by:
-
Edward Cree authored
* Accept EPERM in some simple cases, the following cases are handled: 1) efx_mcdi_read_assertion() Unprivileged PCI functions aren't allowed to GET_ASSERTS. We return success as it's up to the primary PF to deal with asserts. 2) efx_mcdi_mon_probe() in efx_ef10_probe() Unprivileged PCI functions aren't allowed to read sensor info, and worrying about sensor data is the primary PF's job. 3) phy_op->reconfigure() in efx_init_port() and efx_reset_up() Unprivileged functions aren't allowed to MC_CMD_SET_LINK, they just have to accept the settings (including flow-control, which is what efx_init_port() is worried about) they've been given. 4) Fallback to GET_WORKAROUNDS in efx_ef10_probe() Unprivileged PCI functions aren't allowed to set workarounds. So if efx_mcdi_set_workaround() fails EPERM, use efx_mcdi_get_workarounds() to find out if workaround_35388 is enabled. 5) If DRV_ATTACH gets EPERM, try without specifying fw-variant Unprivileged PCI functions have to use a FIRMWARE_ID of 0xffffffff (MC_CMD_FW_DONT_CARE). 6) Don't try to exit_assertion unless one had fired Previously we called efx_mcdi_exit_assertion even if efx_mcdi_read_assertion had received MC_CMD_GET_ASSERTS_FLAGS_NO_FAILS. This is unnecessary, and the resulting MC_CMD_REBOOT, even if the AFTER_ASSERTION flag made it a no-op, would fail EPERM for unprivileged PCI functions. So make efx_mcdi_read_assertion return whether an assert happened, and only call efx_mcdi_exit_assertion if it has. Signed-off-by:
-
Shradha Shah authored
To be able to use MC_CMD_VADAPTOR_SET_MAC, vadaptors must be manually allocated and freed as automatic vadaptors will disappear when their reference_count reaches zero, which must happen before the MAC address is changed. Vadaptors are allocated and freed in the vswitching_probe/remove functions for PFs and VFs, and this means that vadaptors are restored correctly following an MC reboot or other reset when required. Signed-off-by:
-
Shradha Shah authored
The parent PF creates vports for all its child VFs and adds MAC addresses to these. When the VF driver loads, it can make an MCDI call to get the MAC address that the parent PF assigned it. The parent PF also assigns a mac address to its own vport because implicit creation of a vAdaptor will only work on evb ports with MAC addresses assigned. The vport MAC address needs to be stored in the PF's nic_data struct as it can later be changed on the vadaptor (and its net_dev struct). When removing a vport the original MAC address must be deleted. A new flag is needed in the VF data structure to identify whether a vport has been assigned to the VF. This is to determine whether it needs to be un-assigned before freeing the vport. Also, attempting to un-assign a vport which is not assigned will result in an EALREADY error. Signed-off-by:
-
Shradha Shah authored
Added efx_nic_type structure for VF. Mapped a different BAR for VF as it uses BAR 0 for memory. Added functions sriov_init and sriov_fini. Signed-off-by:
-
Daniel Pieczko authored
Use MC_CMD_GET_FUNCTION_INFO to record the PF number in nic_data. This will be needed when assigned vports to VFs. Signed-off-by:
-
Daniel Pieczko authored
Adds functions to allocate and free vswitches and vports; vadaptors are automatically allocated and freed when TX/RX queues are initialised and finalised. This vswitching structure is only created if the firmware supports it, so a check that full-featured firmware is running is performed first. If the MC resets, the vswitching infrastructure will need to be recreated, so mark the "must_probe_vswitching" flag when an MC reboot is detected. Don't try to create a vswitch if vf-count=0 This allocation of vswitches and vports does not currently support configuring VLAN tags, but that can be added in a future change. Signed-off-by:
-
Daniel Pieczko authored
The default port ID of EVB_PORT_ID_ASSIGNED is a "magic" number for the MCFW to select the physical port of the PF. If other vswitches and vports are created on top of the default firmware configuration, the ID of the newly created vport is then required when passed to MCDI commands. Currently, this doesn't happen so the vport_id is never changed, but a subsequent patch will change this behaviour so that other vswitches and vports are created. The vport_id recorded in nic_data is only relevant for PFs. VFs will have their vports created by their parent PF, and in that case the parent PF will record the vport ID of each VF. For a VF, nic_data->vport_id is expected to remain at the default value. Signed-off-by:
-
Daniel Pieczko authored
The (future) code to add/remove vswitches and vports will be dependent on the firmware variant. To simplify the checking of the firmware variant, record values for rx_dpcpu_fw_id and tx_dpcpu_fw_id in EF10 nic_data. There was only one place where this was previously used: efx_mcdi_print_fwver() in ethtool.c. The MC_CMD_GET_CAPABILITIES can be replaced and the values from nic_data used instead. Note that the printing of "?" if the MC command fails or if the outlength is incorrect no longer apply, because errors are returned in efx_ef10_init_datapath_caps() in both of these cases. Signed-off-by:
-
Shradha Shah authored
The TX_DOMAIN field is currently reserved but its safer to set it to 0 for future compatibility. Signed-off-by:
-
Shradha Shah authored
This patch adds support for the use of sriov_configure on EF10 to enable Virtual Functions while the driver is loaded. Signed-off-by:
-
Daniel Pieczko authored
The efx_vf struct contains Siena-specific fields for VFs, so rename to siena_vf. Also move it into the siena_nic_data struct, as EF10 will track its VFs in its own ef10_nic_data, storing much less information about them since VFDI is no longer used. Signed-off-by:
-
Shradha Shah authored
sfc: Own header for nic-specific sriov functions, single instance of netdev_ops and sriov removed from Falcon code By putting all the efx_{siena,ef10}_sriov_* declarations in {siena,ef10}_sriov.h, ensure they cannot be called from nic-generic code. Also fixes up an instance of this, where mcdi.c was calling efx_siena_sriov_flr. The single instance of netdev_ops should call general high level functions that can then call something adapter specific in efx_nic_type. We should only do adapter specialisation via efx_nic_type. Removal of sriov functionality from the Falcon code means that tests are needed for the presence of some callbacks. Signed-off-by: -
David S. Miller authored
Andrew Lunn says: ==================== More Marvell DSA refactring and fixup This patch setup continues the refactoring and cleanup of the Marvell DSA drivers. Patch #1 Centralizes the duplicated parts of port setup and global setup into the shared mv88e6xxx. Patch #2 Centralizes looping over the ports setting them up Patch #3 Uses mnemonics for the remaining register access in the drivers. Patch #4 The 6172 is actually a member of the 6352 family. This moves the probe code into the correct driver. Patch #5 Adds more members of the 6171 family to the 6171 driver. The new devices are untested. Patch #6 The 6185 is a member of the 6131 family. Add it to the probe code of the 6131 driver. Patch #7 and Patch #8 Simply the mutex's in mv88e6xxx.c. The SMI bus is the bottleneck, not the granularity of the mutex's so simply the code down to a single mutex. Patch #8 Fixes a false positive lockdep splat, due to nested uses of MDIO busses. Patch #9 Fixes another false positive lockdep splat with the transmit queue because of stacked Ethernet devices. ==================== Signed-off-by: -
Andrew Lunn authored
DSA stacks an Ethernet device on top of an Ethernet device. This can cause false positive lockdep splats for the transmit queue: Acked-by:
Florian Fainelli <f.fainelli@gmail.com> ============================================= [ INFO: possible recursive locking detected ] 4.0.0-rc7-01838-g70621a215fc7 #386 Not tainted --------------------------------------------- kworker/0:0/4 is trying to acquire lock: (_xmit_ETHER#2){+.-...}, at: [<c040e95c>] sch_direct_xmit+0xa8/0x1fc but task is already holding lock: (_xmit_ETHER#2){+.-...}, at: [<c03f4208>] __dev_queue_xmit+0x4d4/0x56c other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(_xmit_ETHER#2); lock(_xmit_ETHER#2); To avoid this, walk the tq queues of the dsa slaves and set a lockdep class. Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
-
Andrew Lunn authored
DSA can have nested MDIO busses, where the Ethernet MDIO bus is used to access an MDIO bus within the switch which has the PHYs connected to it. This nesting causes lockdep to give false positives. Use mutex_lock_nested() to avoid this. Signed-off-by:
-
Andrew Lunn authored
The SMI bus is the bottleneck in all switch operations, not the granularity of locks. Replace the stats mutex by the SMI mutex to make the locking concept simpler. The REG_READ/REG_WRITE macros cannot be used while holding the SMI mutex, since they try to acquire it. Replace with calls to the appropriate function which does not try to get the mutex. Signed-off-by:
-
Andrew Lunn authored
The SMI bus is the bottleneck in all switch operations, not the granularity of locks. Replace the PHY mutex by the SMI mutex to make the locking concept simpler. The REG_READ/REG_WRITE macros cannot be used while holding the SMI mutex, since they try to acquire it. Replace with calls to the appropriate function which does not try to get the mutex. Signed-off-by:
-
Andrew Lunn authored
The mv88e6185 is part of the family that the mv88e6131 driver supports. Add it to the probe function, and set the number of ports. Signed-off-by:
-
Andrew Lunn authored
The 6171 is one member of the family 6171/6175/6350/6351. Add the other family members to the driver. Not tested on these new devices. Signed-off-by:
-
Andrew Lunn authored
The mv88e6172 is part of the mv88e6352 family of devices. Move support for it out of the mv88e6171 driver into the mv88e6352, which results in some simplifications to the code. Signed-off-by:
-
Andrew Lunn authored
Use defines for registers, shifts and bits in the remaining register accesses in the individual drivers, in order to aid readability. Signed-off-by:
-
Andrew Lunn authored
Now that setting up a port is identical for all switches, centralisers the code looping over all the ports to set them up. Signed-off-by:
-
