aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/igb
Commit message (Collapse)AuthorAge
...
| * igb: Allow asymmetric configuration of MTU versus Rx frame sizeAlexander Duyck2016-02-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since the igb driver is using page based receive there is no point in limiting the Rx capabilities of the device. The driver can receive 9K jumbo frames at all times. The only changes needed due to MTU changes are updates for the FIFO sizes and flow-control watermarks. Update the maximum frame size to reflect the 9.5K limitation of the hardware, and replace all instances of max_frame_size with MAX_JUMBO_FRAME_SIZE when referring to an Rx FIFO or frame. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb: Refactor VFTA configurationAlexander Duyck2016-02-15
| | | | | | | | | | | | | | | | | | | | | | This patch starts the clean-up process on the VFTA configuration. Specifically in this patch I attempt to address and simplify several items while also updating the code to bring it more inline with what is already in ixgbe. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb: clean up code for setting MAC addressAlexander Duyck2016-02-15
| | | | | | | | | | | | | | | | | | | | | | Drop a bunch of hand written byte swapping code in favor of just doing the byte swapping ourselves. The registers are little endian registers storing a big endian value so if we read the MAC address array as little endian then we will get the CPU registers into the proper layout. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb/igbvf: don't give upMitch Williams2016-02-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The driver shouldn't just give up if it fails to get the hardware mailbox lock. This can happen in a situation where the PF-VF communication channel is heavily loaded and causes complete communications failure between the PF and VF drivers. Add a counter and a delay. The driver will now retry ten times, waiting one millisecond between retries. Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb: Unpair the queues when changing the number of queuesShota Suzuki2016-02-15
| | | | | | | | | | | | | | | | | | | | | | | | | | By the commit 72ddef0506da ("igb: Fix oops caused by missing queue pairing"), the IGB_FLAG_QUEUE_PAIRS flag can now be set when changing the number of queues by "ethtool -L", but it is never cleared unless the igb driver is reloaded. This patch clears it if queue pairing becomes unnecessary as a result of "ethtool -L". Signed-off-by: Shota Suzuki <suzuki_shota_t3@lab.ntt.co.jp> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb: Remove unnecessary flag setting in igb_set_flag_queue_pairs()Shota Suzuki2016-02-15
| | | | | | | | | | | | | | | | | | | | | | | | If VFs are enabled (max_vfs >= 1), both max_rss_queues and adapter->rss_queues are set to 2 in the case of e1000_82576. In this case, IGB_FLAG_QUEUE_PAIRS is always set in the default block as a result of fall-through, thus setting it in the e1000_82576 block is not necessary. Signed-off-by: Shota Suzuki <suzuki_shota_t3@lab.ntt.co.jp> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | mm: introduce page reference manipulation functionsJoonsoo Kim2016-03-17
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The success of CMA allocation largely depends on the success of migration and key factor of it is page reference count. Until now, page reference is manipulated by direct calling atomic functions so we cannot follow up who and where manipulate it. Then, it is hard to find actual reason of CMA allocation failure. CMA allocation should be guaranteed to succeed so finding offending place is really important. In this patch, call sites where page reference is manipulated are converted to introduced wrapper function. This is preparation step to add tracepoint to each page reference manipulation function. With this facility, we can easily find reason of CMA allocation failure. There is no functional change in this patch. In addition, this patch also converts reference read sites. It will help a second step that renames page._count to something else and prevents later attempt to direct access to it (Suggested by Andrew). Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* sctp: Rename NETIF_F_SCTP_CSUM to NETIF_F_SCTP_CRCTom Herbert2015-12-15
| | | | | | | | | | | | The SCTP checksum is really a CRC and is very different from the standards 1's complement checksum that serves as the checksum for IP protocols. This offload interface is also very different. Rename NETIF_F_SCTP_CSUM to NETIF_F_SCTP_CRC to highlight these differences. The term CSUM should be reserved in the stack to refer to the standard 1's complement IP checksum. Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* igb: Explicitly label self-test result indicesJoe Schultz2015-12-14
| | | | | | | | | | | Previously, the ethtool self-test gstrings/data arrays were accessed via hardcoded indices, which made the code difficult to follow. This patch replaces the hardcoded values with enum-based labels. Signed-off-by: Joe Schultz <jschultz@xes-inc.com> Signed-off-by: Aaron Sierra <asierra@xes-inc.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: Improve cable length function for I210, etc.Joe Schultz2015-12-14
| | | | | | | | | | | | | Previously, the PHY-specific code to get the cable length for the I210 internal and related PHYs was reporting the cable length of a single pair and reporting it as the min, max, and total cable length. Update it so that all four pairs are checked so the true min, max, and average cable lengths are reported. Signed-off-by: Joe Schultz <jschultz@xes-inc.com> Signed-off-by: Aaron Sierra <asierra@xes-inc.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: Don't add PHY address to PCDL addressAaron Sierra2015-12-14
| | | | | | | | There is no reason to add the PHY address into the PCDL register address. Signed-off-by: Aaron Sierra <asierra@xes-inc.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: Remove GS40G specific defines/functionsAaron Sierra2015-12-14
| | | | | | | | | | | | | | | | | | | The I210 internal PHY can be accessed just as well with the access functions shared by 82580, I350, and I354 devices. A side effect of relying on the common functions, is that I210 cable length support is folded back into the common case which effectively reverts the following commit: commit 59f301046b276f87483b3afa3201a4273def06a9 Author: Carolyn Wyborny <carolyn.wyborny@intel.com> Date: Wed Oct 10 04:42:59 2012 +0000 igb: Update get cable length function for i210/i211 Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Signed-off-by: Aaron Sierra <asierra@xes-inc.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: improve handling of disconnected adaptersJarod Wilson2015-12-13
| | | | | | | | | | | | Clean up array_rd32 so that it uses igb_rd32 the same as rd32, per the suggestion of Alexander Duyck, and use io_addr in more places, so that we don't have the need to call E1000_REMOVED (which simply looks for a null hw_addr) nearly as much. Signed-off-by: Jarod Wilson <jarod@redhat.com> Acked-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: fix NULL derefs due to skipped SR-IOV enablingJan Beulich2015-12-13
| | | | | | | | | | | | | | | | | | The combined effect of commits 6423fc3416 ("igb: do not re-init SR-IOV during probe") and ceee3450b3 ("igb: make sure SR-IOV init uses the right number of queues") causes VFs no longer getting set up, leading to NULL pointer dereferences due to the adapter's ->vf_data being NULL while ->vfs_allocated_count is non-zero. The first commit not only neglected the side effect of igb_sriov_reinit() that the second commit tried to account for, but also that of setting IGB_FLAG_HAS_MSIX, without which igb_enable_sriov() is effectively a no-op. Calling igb_{,re}set_interrupt_capability() as done here seems to address this, but I'm not sure whether this is better than sinply reverting the other two commits. Signed-off-by: Jan Beulich <jbeulich@suse.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: use the correct i210 register for EEMNGCTLTodd Fujinaka2015-12-13
| | | | | | | | | | | The i210 has two EEPROM access registers that are located in non-standard offsets: EEARBC and EEMNGCTL. EEARBC was fixed previously and EEMNGCTL should also be corrected. Reported-by: Roman Hodek <roman.aud@siemens.com> Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: don't unmap NULL hw_addrJarod Wilson2015-12-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I've got a startech thunderbolt dock someone loaned me, which among other things, has the following device in it: 08:00.0 Ethernet controller: Intel Corporation I210 Gigabit Network Connection (rev 03) This hotplugs just fine (kernel 4.2.0 plus a patch or two here): [ 863.020315] igb: Intel(R) Gigabit Ethernet Network Driver - version 5.2.18-k [ 863.020316] igb: Copyright (c) 2007-2014 Intel Corporation. [ 863.028657] igb 0000:08:00.0: enabling device (0000 -> 0002) [ 863.062089] igb 0000:08:00.0: added PHC on eth0 [ 863.062090] igb 0000:08:00.0: Intel(R) Gigabit Ethernet Network Connection [ 863.062091] igb 0000:08:00.0: eth0: (PCIe:2.5Gb/s:Width x1) e8:ea:6a:00:1b:2a [ 863.062194] igb 0000:08:00.0: eth0: PBA No: 000200-000 [ 863.062196] igb 0000:08:00.0: Using MSI-X interrupts. 4 rx queue(s), 4 tx queue(s) [ 863.064889] igb 0000:08:00.0 enp8s0: renamed from eth0 But disconnecting it is another story: [ 1002.807932] igb 0000:08:00.0: removed PHC on enp8s0 [ 1002.807944] igb 0000:08:00.0 enp8s0: PCIe link lost, device now detached [ 1003.341141] ------------[ cut here ]------------ [ 1003.341148] WARNING: CPU: 0 PID: 199 at lib/iomap.c:43 bad_io_access+0x38/0x40() [ 1003.341149] Bad IO access at port 0x0 () [ 1003.342767] Modules linked in: snd_usb_audio snd_usbmidi_lib snd_rawmidi igb dca firewire_ohci firewire_core crc_itu_t rfcomm ctr ccm arc4 iwlmvm mac80211 fuse xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw iptable_filter bnep dm_mirror dm_region_hash dm_log dm_mod coretemp x86_pkg_temp_thermal intel_powerclamp kvm_intel snd_hda_codec_hdmi kvm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel drbg [ 1003.342793] ansi_cprng aesni_intel hp_wmi aes_x86_64 iTCO_wdt lrw iTCO_vendor_support ppdev gf128mul sparse_keymap glue_helper ablk_helper cryptd snd_hda_codec_realtek snd_hda_codec_generic microcode snd_hda_intel uvcvideo iwlwifi snd_hda_codec videobuf2_vmalloc videobuf2_memops snd_hda_core videobuf2_core snd_hwdep btusb v4l2_common btrtl snd_seq btbcm btintel videodev cfg80211 snd_seq_device rtsx_pci_ms bluetooth pcspkr input_leds i2c_i801 media parport_pc memstick rfkill sg lpc_ich snd_pcm 8250_fintek parport joydev snd_timer snd soundcore hp_accel ie31200_edac mei_me lis3lv02d edac_core input_polldev mei hp_wireless shpchp tpm_infineon sch_fq_codel nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables autofs4 xfs libcrc32c sd_mod sr_mod cdrom rtsx_pci_sdmmc mmc_core crc32c_intel serio_raw rtsx_pci [ 1003.342822] nouveau ahci libahci mxm_wmi e1000e xhci_pci hwmon ptp drm_kms_helper pps_core xhci_hcd ttm wmi video ipv6 [ 1003.342839] CPU: 0 PID: 199 Comm: kworker/0:2 Not tainted 4.2.0-2.el7_UNSUPPORTED.x86_64 #1 [ 1003.342840] Hardware name: Hewlett-Packard HP ZBook 15 G2/2253, BIOS M70 Ver. 01.07 02/26/2015 [ 1003.342843] Workqueue: pciehp-3 pciehp_power_thread [ 1003.342844] ffffffff81a90655 ffff8804866d3b48 ffffffff8164763a 0000000000000000 [ 1003.342846] ffff8804866d3b98 ffff8804866d3b88 ffffffff8107134a ffff8804866d3b88 [ 1003.342847] ffff880486f46000 ffff88046c8a8000 ffff880486f46840 ffff88046c8a8098 [ 1003.342848] Call Trace: [ 1003.342852] [<ffffffff8164763a>] dump_stack+0x45/0x57 [ 1003.342855] [<ffffffff8107134a>] warn_slowpath_common+0x8a/0xc0 [ 1003.342857] [<ffffffff810713c6>] warn_slowpath_fmt+0x46/0x50 [ 1003.342859] [<ffffffff8133719e>] ? pci_disable_msix+0x3e/0x50 [ 1003.342860] [<ffffffff812f6328>] bad_io_access+0x38/0x40 [ 1003.342861] [<ffffffff812f6567>] pci_iounmap+0x27/0x40 [ 1003.342865] [<ffffffffa0b728d7>] igb_remove+0xc7/0x160 [igb] [ 1003.342867] [<ffffffff8132189f>] pci_device_remove+0x3f/0xc0 [ 1003.342869] [<ffffffff81433426>] __device_release_driver+0x96/0x130 [ 1003.342870] [<ffffffff814334e3>] device_release_driver+0x23/0x30 [ 1003.342871] [<ffffffff8131b404>] pci_stop_bus_device+0x94/0xa0 [ 1003.342872] [<ffffffff8131b3ad>] pci_stop_bus_device+0x3d/0xa0 [ 1003.342873] [<ffffffff8131b3ad>] pci_stop_bus_device+0x3d/0xa0 [ 1003.342874] [<ffffffff8131b516>] pci_stop_and_remove_bus_device+0x16/0x30 [ 1003.342876] [<ffffffff81333f5b>] pciehp_unconfigure_device+0x9b/0x180 [ 1003.342877] [<ffffffff81333a73>] pciehp_disable_slot+0x43/0xb0 [ 1003.342878] [<ffffffff81333b6d>] pciehp_power_thread+0x8d/0xb0 [ 1003.342885] [<ffffffff810881b2>] process_one_work+0x152/0x3d0 [ 1003.342886] [<ffffffff8108854a>] worker_thread+0x11a/0x460 [ 1003.342887] [<ffffffff81088430>] ? process_one_work+0x3d0/0x3d0 [ 1003.342890] [<ffffffff8108ddd9>] kthread+0xc9/0xe0 [ 1003.342891] [<ffffffff8108dd10>] ? kthread_create_on_node+0x180/0x180 [ 1003.342893] [<ffffffff8164e29f>] ret_from_fork+0x3f/0x70 [ 1003.342894] [<ffffffff8108dd10>] ? kthread_create_on_node+0x180/0x180 [ 1003.342895] ---[ end trace 65a77e06d5aa9358 ]--- Upon looking at the igb driver, I see that igb_rd32() attempted to read from hw_addr and failed, so it set hw->hw_addr to NULL and spit out the message in the log output above, "PCIe link lost, device now detached". Well, now that hw_addr is NULL, the attempt to call pci_iounmap is obviously not going to go well. As suggested by Mark Rustad, do something similar to what ixgbe does, and save a copy of hw_addr as adapter->io_addr, so we can still call pci_iounmap on it on teardown. Additionally, for consistency, make the pci_iomap call assignment directly to io_addr, so map and unmap match. Signed-off-by: Jarod Wilson <jarod@redhat.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: add 88E1543 initialization codeTodd Fujinaka2015-12-13
| | | | | | | | Initialize the 88E1543 PHY. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* drivers/net/intel: use napi_complete_done()Jesse Brandeburg2015-10-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As per Eric Dumazet's previous patches: (see commit (24d2e4a50737) - tg3: use napi_complete_done()) Quoting verbatim: Using napi_complete_done() instead of napi_complete() allows us to use /sys/class/net/ethX/gro_flush_timeout GRO layer can aggregate more packets if the flush is delayed a bit, without having to set too big coalescing parameters that impact latencies. </end quote> Tested configuration: low latency via ethtool -C ethx adaptive-rx off rx-usecs 10 adaptive-tx off tx-usecs 15 workload: streaming rx using netperf TCP_MAERTS igb: MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo ... Interim result: 941.48 10^6bits/s over 1.000 seconds ending at 1440193171.589 Alignment Offset Bytes Bytes Recvs Bytes Sends Local Remote Local Remote Xfered Per Per Recv Send Recv Send Recv (avg) Send (avg) 8 8 0 0 1176930056 1475.36 797726 16384.00 71905 MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo ... Interim result: 941.49 10^6bits/s over 0.997 seconds ending at 1440193142.763 Alignment Offset Bytes Bytes Recvs Bytes Sends Local Remote Local Remote Xfered Per Per Recv Send Recv Send Recv (avg) Send (avg) 8 8 0 0 1175182320 50476.00 23282 16384.00 71816 i40e: Hard to test because the traffic is incoming so fast (24Gb/s) that GRO always receives 87kB, even at the highest interrupt rate. Other drivers were only compile tested. Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* drivers/net: get rid of unnecessary initializations in .get_drvinfo()Ivan Vecera2015-10-16
| | | | | | | | | | | | Many drivers initialize uselessly n_priv_flags, n_stats, testinfo_len, eedump_len & regdump_len fields in their .get_drvinfo() ethtool op. It's not necessary as these fields is filled in ethtool_get_drvinfo(). v2: removed unused variable v3: removed another unused variable Signed-off-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: igb: avoid using timespecArnd Bergmann2015-10-05
| | | | | | | | | | | | | | | | | We want to deprecate the use of 'struct timespec' on 32-bit architectures, as it is will overflow in 2038. The igb driver uses it to read the current time, and can simply be changed to use ktime_get_real_ts64() instead. Because of hardware limitations, there is still an overflow in year 2106, which we cannot really avoid, but this documents the overflow. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: intel-wired-lan@lists.osuosl.org Reviewed-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* igb: assume MSI-X interrupts during initializationStefan Assmann2015-09-28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In igb_sw_init() the sequence of calls was changed from igb_init_queue_configuration() igb_init_interrupt_scheme() igb_probe_vfs() to igb_probe_vfs() igb_init_queue_configuration() igb_init_interrupt_scheme() This results in adapter->flags not having the IGB_FLAG_HAS_MSIX bit set during igb_probe_vfs()->igb_enable_sriov(). Therefore SR-IOV does not get enabled properly and we run into a NULL pointer if the max_vfs module parameter is specified (adapter->vf_data does not get allocated, crash on accessing the structure). [ 7.419348] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 [ 7.419367] IP: [<ffffffffa02161c6>] igb_reset+0xe6/0x5d0 [igb] [ 7.419370] PGD 0 [ 7.419373] Oops: 0002 [#1] SMP [ 7.419381] Modules linked in: ahci(+) libahci igb(+) i40e(+) vxlan ip6_udp_tunnel udp_tunnel megaraid_sas(+) ixgbe(+) mdio [ 7.419385] CPU: 0 PID: 4 Comm: kworker/0:0 Not tainted 4.2.0+ #153 [ 7.419387] Hardware name: Dell Inc. PowerEdge R720/0C4Y3R, BIOS 1.6.0 03/07/2013 [...] [ 7.419431] Call Trace: [ 7.419442] [<ffffffffa0217236>] igb_probe+0x8b6/0x1340 [igb] [ 7.419447] [<ffffffff814c7f15>] local_pci_probe+0x45/0xa0 Prevent this by setting the IGB_FLAG_HAS_MSIX bit before calling igb_probe_vfs(). The real interrupt capabilities will be checked during igb_init_interrupt_scheme() so this is safe to do. Signed-off-by: Stefan Assmann <sassmann@kpanic.de> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2015-08-28
|\
| * mm: make page pfmemalloc check more robustMichal Hocko2015-08-21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb") added checks for page->pfmemalloc to __skb_fill_page_desc(): if (page->pfmemalloc && !page->mapping) skb->pfmemalloc = true; It assumes page->mapping == NULL implies that page->pfmemalloc can be trusted. However, __delete_from_page_cache() can set set page->mapping to NULL and leave page->index value alone. Due to being in union, a non-zero page->index will be interpreted as true page->pfmemalloc. So the assumption is invalid if the networking code can see such a page. And it seems it can. We have encountered this with a NFS over loopback setup when such a page is attached to a new skbuf. There is no copying going on in this case so the page confuses __skb_fill_page_desc which interprets the index as pfmemalloc flag and the network stack drops packets that have been allocated using the reserves unless they are to be queued on sockets handling the swapping which is the case here and that leads to hangs when the nfs client waits for a response from the server which has been dropped and thus never arrive. The struct page is already heavily packed so rather than finding another hole to put it in, let's do a trick instead. We can reuse the index again but define it to an impossible value (-1UL). This is the page index so it should never see the value that large. Replace all direct users of page->pfmemalloc by page_is_pfmemalloc which will hide this nastiness from unspoiled eyes. The information will get lost if somebody wants to use page->index obviously but that was the case before and the original code expected that the information should be persisted somewhere else if that is really needed (e.g. what SLAB and SLUB do). [akpm@linux-foundation.org: fix blooper in slub] Fixes: c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb") Signed-off-by: Michal Hocko <mhocko@suse.com> Debugged-by: Vlastimil Babka <vbabka@suse.com> Debugged-by: Jiri Bohac <jbohac@suse.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Acked-by: Mel Gorman <mgorman@suse.de> Cc: <stable@vger.kernel.org> [3.6+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | igb: make sure SR-IOV init uses the right number of queuesTodd Fujinaka2015-08-18
| | | | | | | | | | | | | | | | | | | | Recent changes to igb_probe_vfs() could lead to the PF holding onto all of the queues. Reorder igb_probe_vfs() to be before gb_init_queue_configuration() and add some more error checking. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Fix a memory leak in igb_probeJia-Ju Bai2015-08-18
| | | | | | | | | | | | | | | | | | | | | | In error handling code of igb_probe, the memory adapter->shadow_vfta allocated by kcalloc in igb_sw_init is not freed. So when register_netdev or igb_init_i2c is failed, a memory leak will occur. This patch adds kfree to fix it. Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Fix a deadlock in igb_sriov_reinitJia-Ju Bai2015-08-18
| | | | | | | | | | | | | | | | | | | | When igb_init_interrupt_scheme in igb_sriov_reinit is failed, the lock acquired by rtnl_lock() is not released, which causes a deadlock. This patch adds rtnl_unlock() in error handling to fix it. Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Teardown SR-IOV before unregister_netdev()Alex Williamson2015-08-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the .remove() callback for a PF is called, SR-IOV support for the device is disabled, which requires unbinding and removing the VFs. The VFs may be in-use either by the host kernel or userspace, such as assigned to a VM through vfio-pci. In this latter case, the VFs may be removed either by shutting down the VM or hot-unplugging the devices from the VM. Unfortunately in the case of a Windows 2012 R2 guest, hot-unplug is broken due to the ordering of the PF driver teardown. Disabling SR-IOV prior to unregister_netdev() avoids this issue. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Acked-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: add support for 1512 PHYTodd Fujinaka2015-08-18
| | | | | | | | | | | | | | | | | | This patch adds support for Marvell PHY 1512 (required for I354). Submitted by: Maciej Szwed <maciej.szwed@intel.com> Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: implement high frequency periodic output signalsRichard Cochran2015-08-18
| | | | | | | | | | | | | | | | | | | | | | | | In addition to interrupt driven target time output events, the i210 also has two programmable clock outputs. These clocks support periods between 16 nanoseconds and 140 milliseconds. This patch implements the periodic output function using the clock outputs when possible, falling back to the target time for longer periods. Signed-off-by: Richard Cochran <richardcochran@gmail.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: do not re-init SR-IOV during probeStefan Assmann2015-08-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | During driver probing the following code path is triggered. igb_probe ->igb_sw_init ->igb_probe_vfs ->igb_pci_enable_sriov ->igb_sriov_reinit Doing the SR-IOV re-init is not necessary during probing since we're starting from scratch. Here we can call igb_enable_sriov() right away. Running igb_sriov_reinit() during igb_probe() also seems to cause occasional packet loss on some onboard 82576 NICs. Reproduced on Dell and HP servers with onboard 82576 NICs. Example: Intel Corporation 82576 Gigabit Network Connection [8086:10c9] (rev 01) Subsystem: Dell Device [1028:0481] Signed-off-by: Stefan Assmann <sassmann@kpanic.de> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: missing rtnl_unlock in igb_sriov_reinit()Vasily Averin2015-08-18
| | | | | | | | | | | | Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Fix oops caused by missing queue pairingShota Suzuki2015-08-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When initializing igb driver (e.g. 82576, I350), IGB_FLAG_QUEUE_PAIRS is set if adapter->rss_queues exceeds half of max_rss_queues in igb_init_queue_configuration(). On the other hand, IGB_FLAG_QUEUE_PAIRS is not set even if the number of queues exceeds half of max_combined in igb_set_channels() when changing the number of queues by "ethtool -L". In this case, if numvecs is larger than MAX_MSIX_ENTRIES (10), the size of adapter->msix_entries[], an overflow can occur in igb_set_interrupt_capability(), which in turn leads to an oops. Fix this problem as follows: - When changing the number of queues by "ethtool -L", set IGB_FLAG_QUEUE_PAIRS in the same way as initializing igb driver. - When increasing the size of q_vector, reallocate it appropriately. (With IGB_FLAG_QUEUE_PAIRS set, the size of q_vector gets larger.) Another possible way to fix this problem is to cap the queues at its initial number, which is the number of the initial online cpus. But this is not the optimal way because we cannot increase queues when another cpu becomes online. Note that before commit cd14ef54d25b ("igb: Change to use statically allocated array for MSIx entries"), this problem did not cause oops but just made the number of queues become 1 because of entering msi_only mode in igb_set_interrupt_capability(). Fixes: 907b7835799f ("igb: Add ethtool support to configure number of channels") CC: stable <stable@vger.kernel.org> Signed-off-by: Shota Suzuki <suzuki_shota_t3@lab.ntt.co.jp> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: bump version to igb-5.3.0Todd Fujinaka2015-07-23
| | | | | | | | | | | | Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: use ARRAY_SIZE to replace calculating sizeof(a)/sizeof(a[0])Todd Fujinaka2015-07-23
| | | | | | | | | | | | | | | | | | | | | | Use the ARRAY_SIZE macro rather than calculating sizeof(a)/sizeof(a[0]). Also directly replace the code rather than using an unnecessary define. Reported-by: Maninder Singh <maninder1.s@samsung.com> Reported-by: Joe Perches <joe@perches.com> Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: report unsupported ethtool settings in set_coalesceTodd Fujinaka2015-07-23
| | | | | | | | | | | | | | | | | | | | There are many settings possible using ethtool -C/--coalesce, but not all of them are supported in igb. Report failure when an unsupported option is set. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Fix i354 88E1112 PHY on RCC boards using AutoMediaDetectTodd Fujinaka2015-07-17
| | | | | | | | | | | | | | | | | | | | | | | | e1000_check_for_link_media_swap() checks PHY page 0 for copper and PHY page 1 for "other" (fiber) link. The switch back from page 1 to page 0 happened too soon, before e1000_check_for_link_82575() is executed, and link on fiber (other) was never detected. Check for link while still on the proper PHY page. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Pull timestamp from fragment before adding it to skbAlexander Duyck2015-07-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This change makes it so that we pull the timestamp from the fragment before we add it to the skb. By doing this we can avoid a possible issue in which the fragment can possibly be less than IGB_RX_HDR_LEN due to the timestamp being pulled after the copybreak check. While making this change I realized we could also pull the rest of the igb_pull_tail function into igb_add_rx_frag since in the case of igb, unlike ixgbe, we are able to unmap the entire buffer before calling add_rx_frag so merging the two allows for sharing of code between the two merged functions. Reported-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: only report generic filters in get_ts_infoJacob Keller2015-07-17
|/ | | | | | | Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Acked-by: Richard Cochran <richardcochran@gmail.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: bump version of igb to 5.2.18Todd Fujinaka2015-06-26
| | | | | | | | Bump version of igb to igb-5.2.18 Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* igb: disable IPv6 extension header processingTodd Fujinaka2015-06-26
| | | | | | | | | | Disable IPv6 extension header processing as per hardware errata. Also fix copyright date. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2015-06-14
|\
| * net: igb: fix the start time for periodic output signalsRichard Cochran2015-06-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When programming the start of a periodic output, the code wrongly places the seconds value into the "low" register and the nanoseconds into the "high" register. Even though this is backwards, it slipped through my testing, because the re-arming code in the interrupt service routine is correct, and the signal does appear starting with the second edge. This patch fixes the issue by programming the registers correctly. Signed-off-by: Richard Cochran <richardcochran@gmail.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2015-05-13
|\| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Four minor merge conflicts: 1) qca_spi.c renamed the local variable used for the SPI device from spi_device to spi, meanwhile the spi_set_drvdata() call got moved further up in the probe function. 2) Two changes were both adding new members to codel params structure, and thus we had overlapping changes to the initializer function. 3) 'net' was making a fix to sk_release_kernel() which is completely removed in 'net-next'. 4) In net_namespace.c, the rtnl_net_fill() call for GET operations had the command value fixed, meanwhile 'net-next' adjusted the argument signature a bit. This also matches example merge resolutions posted by Stephen Rothwell over the past two days. Signed-off-by: David S. Miller <davem@davemloft.net>
| * igb: Fix NULL assignment to incorrect variable in igb_reset_q_vectorToshiaki Makita2015-05-07
| | | | | | | | | | | | | | | | | | adapter->tx_ring is set to NULL where rx_ring should be. Fixes: 5536d2102a2d ("igb: Combine q_vector and ring allocation into a single function") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * igb: Fix oops on changing number of ringsToshiaki Makita2015-05-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When changing the number of rings by ethtool -L, q_vectors are reused, which causes oops because of uninitialized pointers. - When an rx is reused as a tx, q_vector->rx.ring is not set to NULL, which misleads igb_poll() to determine that it has an rx ring although it actually points to the tx ring. - When a tx is reused as an rx, q_vector->rx.ring->skb (q_vector->ring[0].skb) has a value that was used as tx_stats before. Fix these problems by zeroing it out on reuseing it. Fixes: 02ef6e1d0b00 ("igb: Fix queue allocation method to accommodate changing during runtime") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Don't use NETDEV_FRAG_PAGE_MAX_SIZE in descriptor calculationAlexander Duyck2015-05-12
| | | | | | | | | | | | | | | | | | | | | | This change updates igb so that it will correctly perform the descriptor count calculation. Previously it was taking NETDEV_FRAG_PAGE_MAX_SIZE into account with isn't really correct since a different value is used to determine the size of the pages used for TCP. That is actually determined by SKB_FRAG_PAGE_ORDER. Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | igb: simplify and clean up igb_enable_mas()Todd Fujinaka2015-05-04
|/ | | | | | | | | | | igb_enable_mas() should only be called for the 82575 and has no clear return so changing it to void. Also simplify the odd conditional expression. Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ptp: igb: use helpers for converting ns to timespec.Richard Cochran2015-03-31
| | | | | | | | | | This patch changes the driver to use ns_to_timespec64() and timespec64_to_ns() instead of open coding the same logic. Compile tested only. Signed-off-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'ptp-2038'David S. Miller2015-03-31
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixed two warnings in e1000e and igb, when switching to timespec64 some printf formats started to not match. In theses cases actually the new type is __kernel_time_t which is __kernel_long_t which unfortunately can be either "long" or "long long". So to solve this I cases the arguments to "long long". -DaveM Richard Cochran says: ==================== ptp: get ready for 2038 This series converts the core driver methods of the PTP Hardware Clock (PHC) subsystem to use the 64 bit version of the timespec structure, making the core API ready for the year 2038. In addition, I reviewed how each driver and device represents the time value at the hardware register level. Most of the drivers are ready, but a few will need some work before the year 2038, as shown: Patch Driver ------------------------------------------------ 12 drivers/net/ethernet/intel/igb/igb_ptp.c 15 ? drivers/net/ethernet/sfc/ptp.c 16 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c The commit log messages document how each driver is ready or why it is not ready. For patch 15, I could not easily find out the hardware representation of the time value, and so the SFC maintainers will have to review their low level code in order to resolve any remaining issues. * ChangeLog ** V3 - dp83640: use timespec64 throughout per Arnd's suggestion - tilegx: use timespec64 throughout per Chris' suggestion - add Jeff's acked-bys ** V2 - use the new methods in the posix clock code right away (patch #3) ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
| * ptp: igb: convert to the 64 bit get/set time methods.Richard Cochran2015-03-31
|/ | | | | | | | | | | | | | | For the 82576, the driver's clock is implemented using a timecounter, and so with this patch that device is ready for the year 2038. However, in the case of the i210, the device stores the number of seconds in a 32 bit register. Therefore, more work is needed on this driver before the year 2038 comes around. Compile tested only. Signed-off-by: Richard Cochran <richardcochran@gmail.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-04-11 11:25:39 -0400