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 23033fad5b ("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: 12dcd86b75 ("igb: fix stats handling") (this added the spin_lock)
Signed-off-by: Bernhard Kaindl <bk-linux@use.startmail.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This makes sure any RMRR mappings stay in place when the
driver is unbound from the device.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Tested-by: Jerry Hoemann <jerry.hoemann@hp.com>
This patch consolidates the logic behind dynamically setting TXDCTL.WTHRESH
depending on interrupt throttle rate (ITR) setting regardless of BQL.
Previously TXDCTL.WTHRESH was dynamically being set only with BQL being
enabled, but we have to set it regardless of BQL when ITR is low to avoid
Tx stalls/hangs.
CC: John Greene <jogreene@redhat.com>
Reported by: Masayuki Gouji <gouji.masayuki@jp.fujitsu.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This event closes an important gap in the bus notifiers.
There is already the BUS_NOTIFY_DEL_DEVICE event, but that
is sent when the device is still bound to its device driver.
This is too early for the IOMMU code to destroy any mappings
for the device, as they might still be in use by the driver.
The new BUS_NOTIFY_REMOVED_DEVICE event introduced with this
patch closes this gap as it is sent when the device is
already unbound from its device driver and almost completly
removed from the driver core.
With this event the IOMMU code can safely destroy any
mappings and other data structures when a device is removed.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Jerry Hoemann <jerry.hoemann@hp.com>
This patch removes couple of wait loops on autoneg that are not needed.
During validation we noticed that the loops always time out, so there
should be no user impact.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Convert the normal packet completion path to dev_consume_skb_any() so
packet drop profiling via dropwatch or perf top -G -e skb_kfree_skb
is not cluttered with false hits.
Compile tested only. There is a dev_kfree_skb_any() in the routine
ixgbe_ptp_tx_hwtstamp() in ixgbe_ptp.c that looks like a conversion
candidate but I wasn't familiar enough with the code to pull the
trigger.
Signed-off-by: Rick Jones <rick.jones2@hp.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The L2CAP connection's channel list lock (conn->chan_lock) must never be
taken while already holding a channel lock (chan->lock) in order to
avoid lock-inversion and lockdep warnings. So far the l2cap_chan_connect
function has acquired the chan->lock early in the function and then
later called l2cap_chan_add(conn, chan) which will try to take the
conn->chan_lock. This violates the correct order of taking the locks and
may lead to the following type of lockdep warnings:
-> #1 (&conn->chan_lock){+.+...}:
[<c109324d>] lock_acquire+0x9d/0x140
[<c188459c>] mutex_lock_nested+0x6c/0x420
[<d0aab48e>] l2cap_chan_add+0x1e/0x40 [bluetooth]
[<d0aac618>] l2cap_chan_connect+0x348/0x8f0 [bluetooth]
[<d0cc9a91>] lowpan_control_write+0x221/0x2d0 [bluetooth_6lowpan]
-> #0 (&chan->lock){+.+.+.}:
[<c10928d8>] __lock_acquire+0x1a18/0x1d20
[<c109324d>] lock_acquire+0x9d/0x140
[<c188459c>] mutex_lock_nested+0x6c/0x420
[<d0ab05fd>] l2cap_connect_cfm+0x1dd/0x3f0 [bluetooth]
[<d0a909c4>] hci_le_meta_evt+0x11a4/0x1260 [bluetooth]
[<d0a910eb>] hci_event_packet+0x3ab/0x3120 [bluetooth]
[<d0a7cb08>] hci_rx_work+0x208/0x4a0 [bluetooth]
CPU0 CPU1
---- ----
lock(&conn->chan_lock);
lock(&chan->lock);
lock(&conn->chan_lock);
lock(&chan->lock);
Before calling l2cap_chan_add() the channel is not part of the
conn->chan_l list, and can therefore only be accessed by the L2CAP user
(such as l2cap_sock.c). We can therefore assume that it is the
responsibility of the user to handle mutual exclusion until this point
(which we can see is already true in l2cap_sock.c by it in many places
touching chan members without holding chan->lock).
Since the hci_conn and by exctension l2cap_conn creation in the
l2cap_chan_connect() function depend on chan details we cannot simply
add a mutex_lock(&conn->chan_lock) in the beginning of the function
(since the conn object doesn't yet exist there). What we can do however
is move the chan->lock taking later into the function where we already
have the conn object and can that way take conn->chan_lock first.
This patch implements the above strategy and does some other necessary
changes such as using __l2cap_chan_add() which assumes conn->chan_lock
is held, as well as adding a second needed label so the unlocking
happens as it should.
Reported-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Tested-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Pin configurations can be per-pin or per-group. Make sure that the
per-group case is covered by the bindings.
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Add printk levels to some places in the powerpc port.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add printk levels to powernv platform code, and convert to
pr_err() etc while here.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
There is no need for yet another copy of the command line, just
use boot_command_line like everyone else.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Use pr_fmt to give some context to the error messages in the
module code, and convert open coded debug printk to pr_debug.
Use pr_err for error messages.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The STMPE driver assumes that the passed in IRQ type is
for rising or falling IRQs, not both, even though the
hardware actually supports this perfectly well. Likewise
the check for level IRQs is done against just high or low
level types, not for the case where it is combined with
other IRQs.
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Fill in the si_addr_lsb siginfo field so the hwpoison code can
pass to userspace the length of memory that has been corrupted.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
do_page_fault was missing knowledge of HWPOISON, and we would oops
if userspace tried to access a poisoned page:
kernel BUG at arch/powerpc/mm/fault.c:180!
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Exit out early for a kernel fault, avoiding indenting of
most of the function.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The number of Tx queues was not being updated due to some issues when
generating the patches. This change makes sure to add the lines necessary
to update the number of Tx queues correctly.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change reduces the buffer size to 2K for all page sizes. The basic
idea is that since most frames only have a 1500 MTU supporting a buffer
size larger than this is somewhat wasteful. As such I have reduced the
size to 2K for all page sizes which will allow for more uses per page.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The defines for xkey3, xkey6 and xkey9 are not used in the code. They're
probably left overs from merging the three source files for 128, 192 and
256 bit AES. They can safely be removed.
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Chandramouli Narayanan <mouli@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The "by8" CTR AVX implementation fails to propperly handle counter
overflows. That was the reason it got disabled in commit 7da4b29d49
("crypto: aesni - disable "by8" AVX CTR optimization").
Fix the overflow handling by incrementing the counter block as a double
quad word, i.e. a 128 bit, and testing for overflows afterwards. We need
to use VPTEST to do so as VPADD* does not set the flags itself and
silently drops the carry bit.
As this change adds branches to the hot path, minor performance
regressions might be a side effect. But, OTOH, we now have a conforming
implementation -- the preferable goal.
A tcrypt test on a SandyBridge system (i7-2620M) showed almost identical
numbers for the old and this version with differences within the noise
range. A dm-crypt test with the fixed version gave even slightly better
results for this version. So the performance impact might not be as big
as expected.
Tested-by: Romain Francoise <romain@orebokech.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Chandramouli Narayanan <mouli@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
as pr_* macros are more preffered over printk, so printk replaced with corresponding pr_* macros
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Unroll clear_page 8 times. A simple microbenchmark which
allocates and frees a zeroed page:
for (i = 0; i < iterations; i++) {
unsigned long p = __get_free_page(GFP_KERNEL | __GFP_ZERO);
free_page(p);
}
improves 20% on POWER8.
This assumes cacheline sizes won't grow beyond 512 bytes or
page sizes wont drop below 1kB, which is unlikely, but we could
add a runtime check during early init if it makes people nervous.
Michael found that some versions of gcc produce quite bad code
(all multiplies), so we give gcc a hand by using shifts and adds.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
A few regression fixes, the runpm ones dating back to 3.15. Also a fairly severe TMDS regression that effected a lot of GF8/9/GT2xx users.
* 'linux-3.17' of git://anongit.freedesktop.org/git/nouveau/linux-2.6:
drm/nouveau: make sure display hardware is reinitialised on runtime resume
drm/nouveau: punt fbcon resume out to a workqueue
drm/nouveau: fix regression on original nv50 board
drm/nv50/disp: fix dpms regression on certain boards
Pull networking fixes from David Miller:
1) Don't halt the firmware in r8152 driver, from Hayes Wang.
2) Handle full sized 802.1ad frames in bnx2 and tg3 drivers properly,
from Vlad Yasevich.
3) Don't sleep while holding tx_clean_lock in netxen driver, fix from
Manish Chopra.
4) Certain kinds of ipv6 routes can end up endlessly failing the route
validation test, causing it to be re-looked up over and over again.
This particularly kills input route caching in TCP sockets. Fix
from Hannes Frederic Sowa.
5) netvsc_start_xmit() has a use-after-free access to skb->len, fix
from K Y Srinivasan.
6) Fix matching of inverted containers in ematch module, from Ignacy
Gawędzki.
7) Aggregation of GRO frames via SKB ->frag_list for linear skbs isn't
handled properly, regression fix from Eric Dumazet.
8) Don't test return value of ipv4_neigh_lookup(), which returns an
error pointer, against NULL. From WANG Cong.
9) Fix an old regression where we mistakenly allow a double add of the
same tunnel. Fixes from Steffen Klassert.
10) macvtap device delete and open can run in parallel and corrupt lists
etc., fix from Vlad Yasevich.
11) Fix build error with IPV6=m NETFILTER_XT_TARGET_TPROXY=y, from Pablo
Neira Ayuso.
12) rhashtable_destroy() triggers lockdep splats, fix also from Pablo.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (32 commits)
bna: Update Maintainer Email
r8152: disable power cut for RTL8153
r8152: remove clearing bp
bnx2: Correctly receive full sized 802.1ad fragmes
tg3: Allow for recieve of full-size 8021AD frames
r8152: fix setting RTL8152_UNPLUG
netxen: Fix bug in Tx completion path.
netxen: Fix BUG "sleeping function called from invalid context"
ipv6: remove rt6i_genid
hyperv: Fix a bug in netvsc_start_xmit()
net: stmmac: fix stmmac_pci_probe failed when CONFIG_HAVE_CLK is selected
ematch: Fix matching of inverted containers.
gro: fix aggregation for skb using frag_list
neigh: check error pointer instead of NULL for ipv4_neigh_lookup()
ip6_gre: Return an error when adding an existing tunnel.
ip6_vti: Return an error when adding an existing tunnel.
ip6_tunnel: Return an error when adding an existing tunnel.
ip6gre: add a rtnl link alias for ip6gretap
net/mlx4_core: Allow not to specify probe_vf in SRIOV IB mode
r8152: fix the carrier off when autoresuming
...
It has come to my attention (thanks Martin) that 'discard_zeroes_data'
is only a hint. Some devices in some cases don't do what it
says on the label.
The use of DISCARD in RAID5 depends on reads from discarded regions
being predictably zero. If a write to a previously discarded region
performs a read-modify-write cycle it assumes that the parity block
was consistent with the data blocks. If all were zero, this would
be the case. If some are and some aren't this would not be the case.
This could lead to data corruption after a device failure when
data needs to be reconstructed from the parity.
As we cannot trust 'discard_zeroes_data', ignore it by default
and so disallow DISCARD on all raid4/5/6 arrays.
As many devices are trustworthy, and as there are benefits to using
DISCARD, add a module parameter to over-ride this caution and cause
DISCARD to work if discard_zeroes_data is set.
If a site want to enable DISCARD on some arrays but not on others they
should select DISCARD support at the filesystem level, and set the
raid456 module parameter.
raid456.devices_handle_discard_safely=Y
As this is a data-safety issue, I believe this patch is suitable for
-stable.
DISCARD support for RAID456 was added in 3.7
Cc: Shaohua Li <shli@kernel.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Heinz Mauelshagen <heinzm@redhat.com>
Cc: stable@vger.kernel.org (3.7+)
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Fixes: 620125f2bf
Signed-off-by: NeilBrown <neilb@suse.de>
Linus commit 05c63c2ff2 modified the
runtime suspend/resume paths to skip over display-related tasks to
avoid locking issues on resume.
Unfortunately, this resulted in the display hardware being left in
a partially initialised state, preventing subsequent modesets from
completing.
This commit unifies the (many) suspend/resume paths, bringing back
display (and fbcon) handling in the runtime paths.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Preparation for some runtime pm fixes. Currently we skip over fbcon
suspend/resume in the runtime path, which causes issues on resume if
fbcon tries to write to the framebuffer before the BAR subdev has
been resumed to restore the BAR1 VM setup.
As we might be woken up via a sysfs connector, we are unable to call
fb_set_suspend() in the resume path as it could make its way down to
a modeset and cause all sorts of locking hilarity.
To solve this, we'll just delay the fbcon resume to a workqueue.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Xorg (and any non-DRM client really) doesn't have permission to directly
touch VRAM on nv50 and up, which the fence code prior to g84 depends on.
It's less invasive to temporarily grant it premission to do so, as it
previously did, than it is to rework fencenv50 to use the VM. That
will come later on.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
bcmgenet_put_tx_csum() needs to return skb pointer back to the caller
because it reallocates a new one in case of lack of skb headroom.
Signed-off-by: Petri Gynther <pgynther@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch demonstrates the effect of delaying update of HW tailptr.
(based on earlier patch by Jesper)
burst=1 is the default. It sends one packet with xmit_more=false
burst=2 sends one packet with xmit_more=true and
2nd copy of the same packet with xmit_more=false
burst=3 sends two copies of the same packet with xmit_more=true and
3rd copy with xmit_more=false
Performance with ixgbe (usec 30):
burst=1 tx:9.2 Mpps
burst=2 tx:13.5 Mpps
burst=3 tx:14.5 Mpps full 10G line rate
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for being able to propagate port states to e.g: notifiers
or other kernel parts, do not manipulate the port state directly, but
instead use a helper function which will allow us to do a bit more than
just setting the state.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes the following crash:
[ 63.976822] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[ 63.980094] CPU: 1 PID: 15 Comm: ksoftirqd/1 Not tainted 3.17.0-rc6+ #648
[ 63.980094] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 63.980094] task: ffff880117dea690 ti: ffff880117dfc000 task.ti: ffff880117dfc000
[ 63.980094] RIP: 0010:[<ffffffff817e6d07>] [<ffffffff817e6d07>] u32_destroy_key+0x27/0x6d
[ 63.980094] RSP: 0018:ffff880117dffcc0 EFLAGS: 00010202
[ 63.980094] RAX: ffff880117dea690 RBX: ffff8800d02e0820 RCX: 0000000000000000
[ 63.980094] RDX: 0000000000000001 RSI: 0000000000000002 RDI: 6b6b6b6b6b6b6b6b
[ 63.980094] RBP: ffff880117dffcd0 R08: 0000000000000000 R09: 0000000000000000
[ 63.980094] R10: 00006c0900006ba8 R11: 00006ba100006b9d R12: 0000000000000001
[ 63.980094] R13: ffff8800d02e0898 R14: ffffffff817e6d4d R15: ffff880117387a30
[ 63.980094] FS: 0000000000000000(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000
[ 63.980094] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 63.980094] CR2: 00007f07e6732fed CR3: 000000011665b000 CR4: 00000000000006e0
[ 63.980094] Stack:
[ 63.980094] ffff88011a9cd300 ffffffff82051ac0 ffff880117dffce0 ffffffff817e6d68
[ 63.980094] ffff880117dffd70 ffffffff810cb4c7 ffffffff810cb3cd ffff880117dfffd8
[ 63.980094] ffff880117dea690 ffff880117dea690 ffff880117dfffd8 000000000000000a
[ 63.980094] Call Trace:
[ 63.980094] [<ffffffff817e6d68>] u32_delete_key_freepf_rcu+0x1b/0x1d
[ 63.980094] [<ffffffff810cb4c7>] rcu_process_callbacks+0x3bb/0x691
[ 63.980094] [<ffffffff810cb3cd>] ? rcu_process_callbacks+0x2c1/0x691
[ 63.980094] [<ffffffff817e6d4d>] ? u32_destroy_key+0x6d/0x6d
[ 63.980094] [<ffffffff810780a4>] __do_softirq+0x142/0x323
[ 63.980094] [<ffffffff810782a8>] run_ksoftirqd+0x23/0x53
[ 63.980094] [<ffffffff81092126>] smpboot_thread_fn+0x203/0x221
[ 63.980094] [<ffffffff81091f23>] ? smpboot_unpark_thread+0x33/0x33
[ 63.980094] [<ffffffff8108e44d>] kthread+0xc9/0xd1
[ 63.980094] [<ffffffff819e00ea>] ? do_wait_for_common+0xf8/0x125
[ 63.980094] [<ffffffff8108e384>] ? __kthread_parkme+0x61/0x61
[ 63.980094] [<ffffffff819e43ec>] ret_from_fork+0x7c/0xb0
[ 63.980094] [<ffffffff8108e384>] ? __kthread_parkme+0x61/0x61
tp could be freed in call_rcu callback too, the order is not guaranteed.
John Fastabend says:
====================
Its worth noting why this is safe. Any running schedulers will either
read the valid class field or it will be zeroed.
All schedulers today when the class is 0 do a lookup using the
same call used by the tcf_exts_bind(). So even if we have a running
classifier hit the null class pointer it will do a lookup and get
to the same result. This is particularly fragile at the moment because
the only way to verify this is to audit the schedulers call sites.
====================
Cc: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert says:
====================
udp: Generalize GSO for UDP tunnels
This patch set generalizes the UDP tunnel segmentation functions so
that they can work with various protocol encapsulations. The primary
change is to set the inner_protocol field in the skbuff when creating
the encapsulated packet, and then in skb_udp_tunnel_segment this data
is used to determine the function for segmenting the encapsulated
packet. The inner_protocol field is overloaded to take either an
Ethertype or IP protocol.
The inner_protocol is set on transmit using skb_set_inner_ipproto or
skb_set_inner_protocol functions. VXLAN and IP tunnels (for fou GSO)
were modified to call these.
Notes:
- GSO for GRE/UDP where GRE checksum is enabled does not work.
Handling this will require some special case code.
- Software GSO now supports many varieties of encapsulation with
SKB_GSO_UDP_TUNNEL{_CSUM}. We still need a mechanism to query
for device support of particular combinations (I intend to
add ndo_gso_check for that).
- MPLS seems to be the only previous user of inner_protocol. I don't
believe these patches can affect that. For supporting GSO with
MPLS over UDP, the inner_protocol should be set using the
helper functions in this patch.
- GSO for L2TP/UDP should also be straightforward now.
v2:
- Respin for Eric's restructuring of skbuff.
Tested GRE, IPIP, and SIT over fou as well as VLXAN. This was
done using 200 TCP_STREAMs in netperf.
GRE
IPv4, FOU, UDP checksum enabled
TCP_STREAM TSO enabled on tun interface
14.04% TX CPU utilization
13.17% RX CPU utilization
9211 Mbps
TCP_STREAM TSO disabled on tun interface
27.82% TX CPU utilization
25.41% RX CPU utilization
9336 Mbps
IPv4, FOU, UDP checksum disabled
TCP_STREAM TSO enabled on tun interface
13.14% TX CPU utilization
23.18% RX CPU utilization
9277 Mbps
TCP_STREAM TSO disabled on tun interface
30.00% TX CPU utilization
31.28% RX CPU utilization
9327 Mbps
IPIP
FOU, UDP checksum enabled
TCP_STREAM TSO enabled on tun interface
15.28% TX CPU utilization
13.92% RX CPU utilization
9342 Mbps
TCP_STREAM TSO disabled on tun interface
27.82% TX CPU utilization
25.41% RX CPU utilization
9336 Mbps
FOU, UDP checksum disabled
TCP_STREAM TSO enabled on tun interface
15.08% TX CPU utilization
24.64% RX CPU utilization
9226 Mbps
TCP_STREAM TSO disabled on tun interface
30.00% TX CPU utilization
31.28% RX CPU utilization
9327 Mbps
SIT
FOU, UDP checksum enabled
TCP_STREAM TSO enabled on tun interface
14.47% TX CPU utilization
14.58% RX CPU utilization
9106 Mbps
TCP_STREAM TSO disabled on tun interface
31.82% TX CPU utilization
30.82% RX CPU utilization
9204 Mbps
FOU, UDP checksum disabled
TCP_STREAM TSO enabled on tun interface
15.70% TX CPU utilization
27.93% RX CPU utilization
9097 Mbps
TCP_STREAM TSO disabled on tun interface
33.48% TX CPU utilization
37.36% RX CPU utilization
9197 Mbps
VXLAN
TCP_STREAM TSO enabled on tun interface
16.42% TX CPU utilization
23.66% RX CPU utilization
9081 Mbps
TCP_STREAM TSO disabled on tun interface
30.32% TX CPU utilization
30.55% RX CPU utilization
9185 Mbps
Baseline (no encp, TSO and LRO enabled)
TCP_STREAM
11.85% TX CPU utilization
15.13% RX CPU utilization
9452 Mbps
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Call skb_set_inner_protocol to set inner Ethernet protocol to
ETH_P_TEB before transmit. This is needed for GSO with UDP tunnels.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Call skb_set_inner_protocol to set inner Ethernet protocol to
protocol being encapsulation by GRE before tunnel_xmit. This is
needed for GSO if UDP encapsulation (fou) is being done.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Call skb_set_inner_ipproto to set inner IP protocol to IPPROTO_IPV4
before tunnel_xmit. This is needed if UDP encapsulation (fou) is
being done.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Call skb_set_inner_ipproto to set inner IP protocol to IPPROTO_IPV6
before tunnel_xmit. This is needed if UDP encapsulation (fou) is
being done.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_udp_segment is the function called from udp4_ufo_fragment to
segment a UDP tunnel packet. This function currently assumes
segmentation is transparent Ethernet bridging (i.e. VXLAN
encapsulation). This patch generalizes the function to
operate on either Ethertype or IP protocol.
The inner_protocol field must be set to the protocol of the inner
header. This can now be either an Ethertype or an IP protocol
(in a union). A new flag in the skbuff indicates which type is
effective. skb_set_inner_protocol and skb_set_inner_ipproto
helper functions were added to set the inner_protocol. These
functions are called from the point where the tunnel encapsulation
is occuring.
When skb_udp_tunnel_segment is called, the function to segment the
inner packet is selected based on the inner IP or Ethertype. In the
case of an IP protocol encapsulation, the function is derived from
inet[6]_offloads. In the case of Ethertype, skb->protocol is
set to the inner_protocol and skb_mac_gso_segment is called. (GRE
currently does this, but it might be possible to lookup the protocol
in offload_base and call the appropriate segmenation function
directly).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov says:
====================
bpf: add search pruning optimization and tests
patch #1 commit log explains why eBPF verifier has to examine some
instructions multiple times and describes the search pruning optimization
that improves verification speed for branchy programs and allows more
complex programs to be verified successfully.
This patch completes the core verifier logic.
patch #2 adds more verifier tests related to branches and search pruning
I'm still working on Andy's 'bitmask for stack slots' suggestion. It will be
done on top of this patch.
The current verifier algorithm is brute force depth first search with
state pruning. If anyone can come up with another algorithm that demonstrates
better results, we'll replace the algorithm without affecting user space.
Note verifier doesn't guarantee that all possible valid programs are accepted.
Overly complex programs may still be rejected.
Verifier improvements/optimizations will guarantee that if a program
was passing verification in the past, it will still be passing.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
add 4 extra tests to cover jump verification better
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
