The combined effect of commits 6423fc34 ("igb: do not re-init SR-IOV
during probe") and ceee3450 ("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: NJan Beulich <jbeulich@suse.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NJarod Wilson <jarod@redhat.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

As per Eric Dumazet's previous patches:
(see commit (24d2e4a5) - 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: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NArnd Bergmann <arnd@arndb.de>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Reviewed-by: NRichard Cochran <richardcochran@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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: NStefan Assmann <sassmann@kpanic.de>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Commit c48a11c7 ("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: c48a11c7 ("netvm: propagate page->pfmemalloc to skb")
Signed-off-by: NMichal Hocko <mhocko@suse.com>
Debugged-by: NVlastimil Babka <vbabka@suse.com>
Debugged-by: NJiri Bohac <jbohac@suse.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
Acked-by: NMel Gorman <mgorman@suse.de>
Cc: <stable@vger.kernel.org>	[3.6+]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

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: NTodd Fujinaka <todd.fujinaka@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NJia-Ju Bai <baijiaju1990@163.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NJia-Ju Bai <baijiaju1990@163.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NAlex Williamson <alex.williamson@redhat.com>
Acked-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NStefan Assmann <sassmann@kpanic.de>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Signed-off-by: NVasily Averin <vvs@virtuozzo.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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 cd14ef54 ("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: 907b7835 ("igb: Add ethtool support to configure number of channels")
CC: stable <stable@vger.kernel.org>
Signed-off-by: NShota Suzuki <suzuki_shota_t3@lab.ntt.co.jp>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Signed-off-by: NTodd Fujinaka <todd.fujinaka@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Bump version of igb to igb-5.2.18
Signed-off-by: NTodd Fujinaka <todd.fujinaka@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

adapter->tx_ring is set to NULL where rx_ring should be.

Fixes: 5536d210 ("igb: Combine q_vector and ring allocation into a single function")
Signed-off-by: NToshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: 02ef6e1d ("igb: Fix queue allocation method to accommodate changing during runtime")
Signed-off-by: NToshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

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: NTodd Fujinaka <todd.fujinaka@intel.com>
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

As datasheets for igb (I210, I350, 82576, etc.) say, maclen can be from
14 to 127, which is enough for reasonable number of vlan tags.
My netperf test showed I350's TSO works pretty fine with multiple vlans.
Signed-off-by: NToshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use netif_carrier_off() first, since that will prevent the stack from
queuing more packets to this IF. This operation is fast, and should
behave much nicer when trying to bring down an interface under load.
Reported-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Signed-off-by: NTodd Fujinaka <todd.fujinaka@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Commit 5ac6f91d changed the igb driver to expose a zero (empty) mac
address to the VF on reset rather than a random one.

However, that behavioral change also requires igbvf driver changes
which can be hard especially when we want to talk to proprietary
guest OSs.

Looking at the code previous to the commit in Linux that made igbvf
work with empty mac addresses (8d56b6d5), we can see that on reset
failure the driver will try to generate a new mac address with both
the old and the new code.

Furthermore, ixgbe does send reset failure when it detects an empty
mac address (35055928).

So I think it's safe to make igb behave the same. With this patch I
can successfully run a Windows 8.1 guest with an empty mac address
and an assigned igbvf device that has no mac address set by the host.

If anyone is aware of a guest driver that chokes on NACK returns of
VF RESET commands, please speak up.
Signed-off-by: NAlexander Graf <agraf@suse.de>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The i210 device offers a number of special PTP Hardware Clock features on
the Software Defined Pins (SDPs). This patch adds support for two of the
possible functions, namely time stamping external events, and periodic
output signals.

The assignment of PHC functions to the four SDP can be freely chosen by
the user.
Signed-off-by: NRichard Cochran <richardcochran@gmail.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The i210 device can produce an interrupt on the full second. This
patch allows using this interrupt to generate an internal PPS event
for adjusting the kernel system time.
Signed-off-by: NRichard Cochran <richardcochran@gmail.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The code that handles the time sync interrupt is repeated in three
different places. This patch refactors the identical code blocks into
a single helper function.
Signed-off-by: NRichard Cochran <richardcochran@gmail.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch cleans up the page reuse code getting it into a state where all
the workarounds needed are in place as well as cleaning up a few minor
oversights such as using __free_pages instead of put_page to drop a locally
allocated page.

It also cleans up how we clear the descriptor status bits.  Previously they
were zeroed as a part of clearing the hdr_addr.  However the hdr_addr is a
64 bit field and 64 bit writes can be a bit more expensive on on 32 bit
systems.  Since we are no longer using the header split feature the upper
32 bits of the address no longer need to be cleared.  As a result we can
just clear the status bits and leave the length and VLAN fields as-is which
should provide more information in debugging.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The same macros are used for rx as well. So rename it.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that dma_rmb is used when reading the Rx
descriptor.  The advantage of dma_rmb is that it allows for a much
lower cost barrier on x86, powerpc, arm, and arm64 architectures than a
traditional memory barrier when dealing with reads that only have to
synchronize to coherent memory.

In addition I have updated the code so that it just checks to see if any
bits have been set instead of just the DD bit since the DD bit will always
be set as a part of a descriptor write-back so we just need to check for a
non-zero value being present at that memory location rather than just
checking for any specific bit.  This allows the code itself to appear much
cleaner and allows the compiler more room to optimize.

Cc: Matthew Vick <matthew.vick@intel.com>
Cc: Don Skidmore <donald.c.skidmore@intel.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change replaces calls to netdev_alloc_skb_ip_align with
napi_alloc_skb.  The advantage of napi_alloc_skb is currently the fact that
the page allocation doesn't make use of any irq disable calls.

There are few spots where I couldn't replace the calls as the buffer
allocation routine is called as a part of init which is outside of the
softirq context.

Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Update the Intel Ethernet drivers to use eth_skb_pad() and skb_put_padto
instead of doing their own implementations of the function.

Also this cleans up two other spots where skb_pad was called but the length
and tail pointers were being manipulated directly instead of just having
the padding length added via __skb_put.

Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit b2b49ccb (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so #ifdef blocks
depending on CONFIG_PM_RUNTIME within #ifdef blocks depending on
CONFIG_PM may be dropped now.

Do that in the e1000e and igb network drivers.
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds some checks in order to prevent panic's on surprise
removal of devices during S0, S3, S4.  Without this patch, Thunderbolt
type device removal will panic the system.
Signed-off-by: NYanir Lubetkin <yanirx.lubetkin@intel.com>
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use of well known RSS key increases attack surface.
Switch to a random one, using generic helper so that all
ports share a common key.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Intel drivers were pretty much just using the plain vanilla GFP flags
in their calls to __skb_alloc_page so this change makes it so that they use
dev_alloc_page which just uses GFP_ATOMIC for the gfp_flags value.

Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Matthew Vick <matthew.vick@intel.com>
Cc: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Incoming packet is dropped silently by sk_filter(), if the skb was
allocated from pfmemalloc reserves and the corresponding socket is
not marked with the SOCK_MEMALLOC flag.

Igb driver allocates pages for DMA with __skb_alloc_page(), which
calls alloc_pages_node() with the __GFP_MEMALLOC flag. So, in case
of OOM condition, igb can get pages with pfmemalloc flag set.

If an incoming packet hits the pfmemalloc page and is large enough
(small packets are copying into the memory, allocated with
netdev_alloc_skb_ip_align(), so they are not affected), it will be
dropped.

This behavior is ok under high memory pressure, but the problem is
that the igb driver reuses these mapped pages. So, packets are still
dropping even if all memory issues are gone and there is a plenty
of free memory.

In my case, some TCP sessions hang on a small percentage (< 0.1%)
of machines days after OOMs.

Fix this by avoiding reuse of such pages.
Signed-off-by: NRoman Gushchin <klamm@yandex-team.ru>
Tested-by: Aaron Brown "aaron.f.brown@intel.com"
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is illegal to use atomic_set(&page->_count, 2) even if we 'own'
the page. Other entities in the kernel need to use get_page_unless_zero()
to get a reference to the page before testing page properties, so we could
loose a refcount increment.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bump version
Signed-off-by: NTodd Fujinaka <todd.fujinaka@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Convert two more Intel NIC drivers to dev_consume_skb_any() to help
make dropped packet profiling sane.
Signed-off-by: NRick Jones <rick.jones2@hp.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Tested-by: NJim Young <jamesx.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Remove a source of latency spikes (in my case up to 10ms) by not calling
code that uses mdelay() for feeding a phy statistic (rx errors for idle
symbols - not data -> idle_errors) while being called with a spinlock held.

As idle_errors isn't read, this patch only removes unused code and data.

Later, more complicated changes may be applied to address the spinlock and
allow for some PHY diagnostics by harvesting this PHY stats register fully.

This patch is designed to fix the issue and be safe for longterm/stable.

For the Intel e1000e driver, the same change was applied in 2008 with
commit 23033fad ("e1000e: remove phy read from inside spinlock").

The mdelay is triggered by HW/SW semaphores, thus it depends on the HW.

I've HW that triggers it even when idle. Others may trigger it only e.g.
when Ethernet ports aquire or loose the link or on ifconfig up / down.
We've noticed this first from delays in frame rx/tx due to the mdelay().

Example command for checking if the issue is triggered: cyclictest -Smp1
(Look for occasional "Max:" values > 4000 or use -b 4000 to stop if greater)

It was observed with I350 ports connected to other I350 ports, but not
if driver and EEPROM was modified to run the I350 in EEPROM-less mode.

phy_stats.idle_errors and .receive_errors (isn't touched) occupy 64 not
used bits in the adapter struct: Their allocation may be removed as well.

Cc: Carolyn Wyborny <carolyn.wyborny@intel.com>
Cc: Todd Fujinaka <todd.fujinaka@intel.com>
Fixes: 12dcd86b ("igb: fix stats handling") (this added the spin_lock)
Signed-off-by: NBernhard Kaindl <bk-linux@use.startmail.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>