Daniel Borkmann says:
====================
pull-request: bpf 2018-02-20
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) Fix a memory leak in LPM trie's map_free() callback function, where
the trie structure itself was not freed since initial implementation.
Also a synchronize_rcu() was needed in order to wait for outstanding
programs accessing the trie to complete, from Yonghong.
2) Fix sock_map_alloc()'s error path in order to correctly propagate
the -EINVAL error in case of too large allocation requests. This
was just recently introduced when fixing close hooks via ULP layer,
fix from Eric.
3) Do not use GFP_ATOMIC in __cpu_map_entry_alloc(). Reason is that this
will not work with the recent __ptr_ring_init_queue_alloc() conversion
to kvmalloc_array(), where in case of fallback to vmalloc() that GFP
flag is invalid, from Jason.
4) Fix two recent syzkaller warnings: i) fix bpf_prog_array_copy_to_user()
when a prog query with a big number of ids was performed where we'd
otherwise trigger a warning from allocator side, ii) fix a missing
mlock precharge on arraymaps, from Daniel.
5) Two fixes for bpftool in order to avoid breaking JSON output when used
in batch mode, from Quentin.
6) Move a pr_debug() in libbpf in order to avoid having an otherwise
uninitialized variable in bpf_program__reloc_text(), from Jeremy.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer says:
====================
virtio_net: several bugs in XDP code for driver virtio_net
The virtio_net driver actually violates the original memory model of
XDP causing hard to debug crashes. Per request of John Fastabend,
instead of removing the XDP feature I'm fixing as much as possible.
While testing virtio_net with XDP_REDIRECT I found 4 different bugs.
Patch-1: not enough tail-room for build_skb in receive_mergeable()
only option is to disable XDP_REDIRECT in receive_mergeable()
Patch-2: XDP in receive_small() basically never worked (check wrong flag)
Patch-3: fix memory leak for XDP_REDIRECT in error cases
Patch-4: avoid crash when ndo_xdp_xmit is called on dev not ready for XDP
In the longer run, we should consider introducing a separate receive
function when attaching an XDP program, and also change the memory
model to be compatible with XDP when attaching an XDP prog.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When a driver implements the ndo_xdp_xmit() function, there is
(currently) no generic way to determine whether it is safe to call.
It is e.g. unsafe to call the drivers ndo_xdp_xmit, if it have not
allocated the needed XDP TX queues yet. This is the case for
virtio_net, which first allocates the XDP TX queues once an XDP/bpf
prog is attached (in virtnet_xdp_set()).
Thus, a crash will occur for virtio_net when redirecting to another
virtio_net device's ndo_xdp_xmit, which have not attached a XDP prog.
The sample xdp_redirect_map tries to attach a dummy XDP prog to take
this into account, but it can also easily fail if the virtio_net (or
actually underlying vhost driver) have not allocated enough extra
queues for the device.
Allocating more queue this is currently a manual config.
Hint for libvirt XML add:
<driver name='vhost' queues='16'>
<host mrg_rxbuf='off'/>
<guest tso4='off' tso6='off' ecn='off' ufo='off'/>
</driver>
The solution in this patch is to check that the device have loaded an
XDP/bpf prog before proceeding. This is similar to the check
performed in driver ixgbe.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
XDP_REDIRECT calling xdp_do_redirect() can fail for multiple reasons
(which can be inspected by tracepoints). The current semantics is that
on failure the driver calling xdp_do_redirect() must handle freeing or
recycling the page associated with this frame. This can be seen as an
optimization, as drivers usually have an optimized XDP_DROP code path
for frame recycling in place already.
The virtio_net driver didn't handle when xdp_do_redirect() failed.
This caused a memory leak as the page refcnt wasn't decremented on
failures.
The function __virtnet_xdp_xmit() did handle one type of failure,
when the xmit queue virtqueue_add_outbuf() is full, which "hides"
releasing a refcnt on the page. Instead the function __virtnet_xdp_xmit()
must follow API of xdp_do_redirect(), which on errors leave it up to
the caller to free the page, of the failed send operation.
Fixes: 186b3c998c ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When configuring virtio_net to use the code path 'receive_small()',
in-order to get correct XDP_REDIRECT support, I discovered TCP packets
would get silently dropped when loading an XDP program action XDP_PASS.
The bug seems to be that receive_small() when XDP is loaded check that
hdr->hdr.flags is zero, which seems wrong as hdr.flags contains the
flags VIRTIO_NET_HDR_F_* :
#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 /* Use csum_start, csum_offset */
#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */
TCP got dropped as it had the VIRTIO_NET_HDR_F_DATA_VALID flag set.
The flags that are relevant here are the VIRTIO_NET_HDR_GSO_* flags
stored in hdr->hdr.gso_type. Thus, the fix is just check that none of
the gso_type flags have been set.
Fixes: bb91accf27 ("virtio-net: XDP support for small buffers")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The virtio_net code have three different RX code-paths in receive_buf().
Two of these code paths can handle XDP, but one of them is broken for
at least XDP_REDIRECT.
Function(1): receive_big() does not support XDP.
Function(2): receive_small() support XDP fully and uses build_skb().
Function(3): receive_mergeable() broken XDP_REDIRECT uses napi_alloc_skb().
The simple explanation is that receive_mergeable() is broken because
it uses napi_alloc_skb(), which violates XDP given XDP assumes packet
header+data in single page and enough tail room for skb_shared_info.
The longer explaination is that receive_mergeable() tries to
work-around and satisfy these XDP requiresments e.g. by having a
function xdp_linearize_page() that allocates and memcpy RX buffers
around (in case packet is scattered across multiple rx buffers). This
does currently satisfy XDP_PASS, XDP_DROP and XDP_TX (but only because
we have not implemented bpf_xdp_adjust_tail yet).
The XDP_REDIRECT action combined with cpumap is broken, and cause hard
to debug crashes. The main issue is that the RX packet does not have
the needed tail-room (SKB_DATA_ALIGN(skb_shared_info)), causing
skb_shared_info to overlap the next packets head-room (in which cpumap
stores info).
Reproducing depend on the packet payload length and if RX-buffer size
happened to have tail-room for skb_shared_info or not. But to make
this even harder to troubleshoot, the RX-buffer size is runtime
dynamically change based on an Exponentially Weighted Moving Average
(EWMA) over the packet length, when refilling RX rings.
This patch only disable XDP_REDIRECT support in receive_mergeable()
case, because it can cause a real crash.
IMHO we should consider NOT supporting XDP in receive_mergeable() at
all, because the principles behind XDP are to gain speed by (1) code
simplicity, (2) sacrificing memory and (3) where possible moving
runtime checks to setup time. These principles are clearly being
violated in receive_mergeable(), that e.g. runtime track average
buffer size to save memory consumption.
In the longer run, we should consider introducing a separate receive
function when attaching an XDP program, and also change the memory
model to be compatible with XDP when attaching an XDP prog.
Fixes: 186b3c998c ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJajJahAAoJEEg/ir3gV/o+PTQIALd4/l5VEU1vWqXp6PPaIaRP
fCt4CKXkeIozyOhkiaYLcNAvPnsJRi54a/PGyUbHwxadkjuOhS8WETyQwMf8gbKF
g+LTDseqKjWcu6fUMqe7TmjrNHSo2VErjOjHw1+7emKSkBZuc8zBBND9PqHtOQY6
f1KoUY6IBs22dwqzynxkC5A62VQbTYd0FPnf1n9wN8ubFXSb37KUgKoW4kmMFmLe
JsYEcsAKxpfepnP+EYLyDrVcT1LA9edi5DI5uxSfNgas6bTtjRPhtyZCznDF8rly
jEWv3O2c+HhchuysoACTLiTllviHGj0Myv+rGb0ouhjZWMtulgPPQ04lbYjjr84=
=uF0v
-----END PGP SIGNATURE-----
Merge tag 'mlx5-fixes-2018-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
Mellanox, mlx5 fixes 2018-02-20
The following pull request includes some fixes for the mlx5 core and
netdevice driver.
Please pull and let me know if there's any issue.
-stable 4.10.y:
('net/mlx5e: Fix loopback self test when GRO is off')
-stable 4.12.y:
('net/mlx5e: Specify numa node when allocating drop rq')
-stable 4.13.y:
('net/mlx5e: Verify inline header size do not exceed SKB linear size')
-stable 4.15.y:
('net/mlx5e: Fix TCP checksum in LRO buffers')
('net/mlx5: Fix error handling when adding flow rules')
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains large batch with Netfilter fixes for
your net tree, mostly due to syzbot report fixups and pr_err()
ratelimiting, more specifically, they are:
1) Get rid of superfluous unnecessary check in x_tables before vmalloc(),
we don't hit BUG there anymore, patch from Michal Hock, suggested by
Andrew Morton.
2) Race condition in proc file creation in ipt_CLUSTERIP, from Cong Wang.
3) Drop socket lock that results in circular locking dependency, patch
from Paolo Abeni.
4) Drop packet if case of malformed blob that makes backpointer jump
in x_tables, from Florian Westphal.
5) Fix refcount leak due to race in ipt_CLUSTERIP in
clusterip_config_find_get(), from Cong Wang.
6) Several patches to ratelimit pr_err() for x_tables since this can be
a problem where CAP_NET_ADMIN semantics can protect us in untrusted
namespace, from Florian Westphal.
7) Missing .gitignore update for new autogenerated asn1 state machine
for the SNMP NAT helper, from Zhu Lingshan.
8) Missing timer initialization in xt_LED, from Paolo Abeni.
9) Do not allow negative port range in NAT, also from Paolo.
10) Lock imbalance in the xt_hashlimit rate match mode, patch from
Eric Dumazet.
11) Initialize workqueue before timer in the idletimer match,
from Eric Dumazet.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
GCC-8 shows a warning for the x86 oprofile code that copies per-CPU
data from CPU 0 to all other CPUs, which when building a non-SMP
kernel turns into a memcpy() with identical source and destination
pointers:
arch/x86/oprofile/nmi_int.c: In function 'mux_clone':
arch/x86/oprofile/nmi_int.c:285:2: error: 'memcpy' source argument is the same as destination [-Werror=restrict]
memcpy(per_cpu(cpu_msrs, cpu).multiplex,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
per_cpu(cpu_msrs, 0).multiplex,
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
sizeof(struct op_msr) * model->num_virt_counters);
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
arch/x86/oprofile/nmi_int.c: In function 'nmi_setup':
arch/x86/oprofile/nmi_int.c:466:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]
arch/x86/oprofile/nmi_int.c:470:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]
I have analyzed a number of such warnings now: some are valid and the
GCC warning is welcome. Others turned out to be false-positives, and
GCC was changed to not warn about those any more. This is a corner case
that is a false-positive but the GCC developers feel it's better to keep
warning about it.
In this case, it seems best to work around it by telling GCC
a little more clearly that this code path is never hit with
an IS_ENABLED() configuration check.
Cc:stable as we also want old kernels to build cleanly with GCC-8.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Sebor <msebor@gcc.gnu.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: oprofile-list@lists.sf.net
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20180220205826.2008875-1-arnd@arndb.de
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84095
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commits adding PCI IDs for Intel Braswell and Kaby Lake PCH-H lacked the
respective Kconfig and Documentation/i2c/busses/i2c-i801 change. Add
them now.
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
One I2C bus on my Atom E3845 board has been broken since 4.9.
It has two devices, both declared by ACPI and with built-in drivers.
There are two back-to-back transactions originating from the kernel, one
targeting each device. The first transaction works, the second one locks
up the I2C controller. The controller never recovers.
These kernel logs show up whenever an I2C transaction is attempted after
this failure.
i2c-designware-pci 0000:00:18.3: timeout in disabling adapter
i2c-designware-pci 0000:00:18.3: timeout waiting for bus ready
Waiting for the I2C controller status to indicate that it is enabled
before programming it fixes the issue.
I have tested this patch on 4.14 and 4.15.
Fixes: commit 2702ea7dbe ("i2c: designware: wait for disable/enable only if necessary")
Cc: linux-stable <stable@vger.kernel.org> #4.13+
Signed-off-by: Ben Gardner <gardner.ben@gmail.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Attempt to deter usage, this is not a public interface. It is entirely
possible to implement a conformant mutex without having this owner
field (in fact, we used to have that).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The DOC: line acts as an identifier for the :doc: include. Fixes:
./drivers/gpu/drm/tve200/tve200_drv.c:1: warning: no structured comments found
Cc: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180220142008.9330-1-jani.nikula@intel.com
So far, if the filter was too large to fit in the allocated skb, the
kernel did not return any error and stopped dumping. Modify the dumper
so that it returns -EMSGSIZE when a filter fails to dump and it is the
first filter in the skb. If we are not first, we will get a next chance
with more room.
I understand this is pretty near to being an API change, but the
original design (silent truncation) can be considered a bug.
Note: The error case can happen pretty easily if you create a filter
with 32 actions and have 4kb pages. Also recent versions of iproute try
to be clever with their buffer allocation size, which in turn leads to
Signed-off-by: Roman Kapl <code@rkapl.cz>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This uses the EDID info from the Sony PlayStation VR headset,
when connected directly, to mark it as non-desktop.
Since the connection box (product id b403) defaults to HDMI
pass-through to the TV, it is not marked as non-desktop.
Signed-off-by: Philipp Zabel <philipp.zabel@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This uses the EDID info from Lenovo Explorer (LEN-b800), Acer AH100
(ACR-7fce), and Samsung Odyssey (SEC-144a) to mark them as non-desktop.
The other entries are for the HP Windows Mixed Reality Headset (HPN-3515),
the Fujitsu Windows Mixed Reality headset (FUJ-1970), the Dell Visor
(DEL-7fce), and the ASUS HC102 (AUS-c102). They are not tested with real
hardware, but listed as HMD monitors alongside the tested headsets in the
Microsoft HololensSensors driver package.
Signed-off-by: Philipp Zabel <philipp.zabel@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This uses the EDID info from Oculus Rift DK1 (OVR-0001), DK2 (OVR-0003),
and CV1 (OVR-0004) to mark them as non-desktop.
Signed-off-by: Philipp Zabel <philipp.zabel@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Fix some issues found by a static checker:
When allocating an AFU interrupt, if the driver cannot copy the output
parameters to userland, the errno value was not set to EFAULT
Remove a (now) useless cast.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The notify_resume() callback in eeh_ops is NULL on powernv, leading to
crashes:
NIP (null)
LR eeh_report_resume+0x218/0x220
Call Trace:
eeh_report_resume+0x1f0/0x220 (unreliable)
eeh_pe_dev_traverse+0x98/0x170
eeh_handle_normal_event+0x3f4/0x650
eeh_handle_event+0x54/0x380
eeh_event_handler+0x14c/0x210
kthread+0x168/0x1b0
ret_from_kernel_thread+0x5c/0xb4
Fix it by adding a check before calling it.
Fixes: 856e1eb9bd ("PCI/AER: Add uevents in AER and EEH error/resume")
Signed-off-by: Juan J. Alvarez <jjalvare@linux.vnet.ibm.com>
Reviewed-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Carol L. Soto <clsoto@us.ibm.com>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Tested-by: Mauro S. M. Rodrigues <maurosr@linux.vnet.ibm.com>
Acked-by: Michael Neuling <mikey@neuling.org>
[mpe: Rewrite change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
. it fixes potential issues[1] by using monotonic timestamp
instead of 'struct timeval'
. correct HDMI_I2S_PIN_SEL_1 definition and setting value.
. fix bit shift typo of FIMC register definition
- two cleanups
. remove unnecessary error messages
. remove exynos_drm_rotator.h file
[1] https://patchwork.kernel.org/patch/10170205/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQIcBAABAgAGBQJai51+AAoJEFc4NIkMQxK4bkoP+weijxzZ/G+BhJXv4K9h7+zR
40SRz5F5rU+SQf5aB7xSMcIXtlkqgv1WcOdX7d6EVNSjv0qjJKn0xgX0D56mFMVq
ZaNVeDTItZhC2A8hlvML4O26W9ZUS5zu7eetVS2OhSsLQo/dEe/qW1twaKK+SDmC
Npdaipx3Hfw7pBMpbklyCJW9V6qAKlHvCSVtoWtk52XnDmXOG4wcUasfKPmDWmzR
QCyWnh1yLd9Uawa+sxrqlCNaxzT+0MppIsXjSXmRlCpEk3GPJI4bNbEe013LUAHi
UsXFDpwDf1FleHE9tAD1s569NtwCkjZCMET+VP5N0w8PlD6pT7Oyj5DrTCmSb2zJ
rUedRSDMPFBKMYBLOpAbW01NlDS3aHwtjYwC1RwiqBatGrMwVBKebtTJhofkklSj
gHrCDezffah9uvZBqRkNC2+YYefcVNCRxM+IskDNSyb81QyJV55Kf6gBWbu2+/tA
iIOjAALErPa1nQA/hMZs0LSEX86yC7/fphq+VcwApxdsDYQxEcgN3ZhQk4VfLNBI
UxvLHvoMS5EAtKgaGlvqHO2qtcyNWw+obJmy8YQuiaOO3SffA0wPewXCfY6uNgrc
6kpzJKknzVR+6qh+om+EizRe5wstVm2YeP64wKk9BbgWeXJg9kgPgL9o/GKPfGom
e8CnRpu77cxWPjK6zbHD
=QWZV
-----END PGP SIGNATURE-----
Merge tag 'exynos-drm-fixes-for-v4.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-fixes
- three fixeups
. it fixes potential issues[1] by using monotonic timestamp
instead of 'struct timeval'
. correct HDMI_I2S_PIN_SEL_1 definition and setting value.
. fix bit shift typo of FIMC register definition
- two cleanups
. remove unnecessary error messages
. remove exynos_drm_rotator.h file
[1] https://patchwork.kernel.org/patch/10170205/
* tag 'exynos-drm-fixes-for-v4.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos:
drm: exynos: Use proper macro definition for HDMI_I2S_PIN_SEL_1
drm/exynos: remove exynos_drm_rotator.h
drm/exynos: g2d: Delete an error message for a failed memory allocation in two functions
drm/exynos: fix comparison to bitshift when dealing with a mask
drm/exynos: g2d: use monotonic timestamps
If building match list or adding existing fg fails when
node is locked, function returned without unlocking it.
This happened if node version changed or adding existing fg
returned with EAGAIN after jumping to search_again_locked label.
Fixes: bd71b08ec2 ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
First use of drop counters happens in esw_apply_vport_conf function,
while they are allocated later in the flow. Fix that by moving
esw_vport_create_drop_counters function to be called before the first use.
Fixes: b8a0dbe3a9 ("net/mlx5e: E-switch, Add steering drop counters")
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
We can't allow only some of the rules sharing an FTE to ask for
header re-write, add it to the conflicting action checks.
Fixes: 0d235c3fab ('net/mlx5: Add hash table to search FTEs in a flow-group')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
The adapter uses the cache_line_128byte setting to set the bounds for
end padding. On systems where the cacheline size is greater than 128B
use 128B instead of the default of 64B. This results in fewer partial
cacheline writes. There's a 50% chance it will pad to the end of a 256B
cache line vs only 25% when using 64B.
Fixes: f32f5bd2eb ("net/mlx5: Configure cache line size for start and end padding")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When allocating a drop rq, no numa node is explicitly set which means
allocations are done on node zero. This is not necessarily the nearest
numa node to the HCA, and even worse, might even be a memoryless numa
node.
Choose the numa_node given to us by the pci device in order to properly
allocate the coherent dma memory instead of assuming zero is valid.
Fixes: 556dd1b9c3 ("net/mlx5e: Set drop RQ's necessary parameters only")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
This isn't supported when we emulate eswitch vlan push action which
is the current state of things.
Fixes: 8b32580df1 ('net/mlx5e: Add TC vlan action for SRIOV offloads')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Fix these gcc warnings on drivers/net/ethernet/mellanox/mlx5:
[..]/core/lib/clock.c:454:6: warning: no previous prototype for 'mlx5_init_clock' [-Wmissing-prototypes]
[..]/core/lib/clock.c:510:6: warning: no previous prototype for 'mlx5_cleanup_clock' [-Wmissing-prototypes]
[..]/core/en_main.c:3141:5: warning: no previous prototype for 'mlx5e_setup_tc' [-Wmissing-prototypes]
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Driver tries to copy at least MLX5E_MIN_INLINE bytes into the control
segment of the WQE. It assumes that the linear part contains at least
MLX5E_MIN_INLINE bytes, which can be wrong.
Cited commit verified that driver will not copy more bytes into the
inline header part that the actual size of the packet. Re-factor this
check to make sure we do not exceed the linear part as well.
This fix is aligned with the current driver's assumption that the entire
L2 will be present in the linear part of the SKB.
Fixes: 6aace17e64 ("net/mlx5e: Fix inline header size for small packets")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When GRO is off, the transport header pointer in sk_buff is
initialized to network's header.
To find the udp header, instead of using udp_hdr() which assumes
skb_network_header was set, manually calculate the udp header offset.
Fixes: 0952da791c ("net/mlx5e: Add support for loopback selftest")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When receiving an LRO packet, the checksum field is set by the hardware
to the checksum of the first coalesced packet. Obviously, this checksum
is not valid for the merged LRO packet and should be fixed. We can use
the CQE checksum which covers the checksum of the entire merged packet
TCP payload to help us calculate the checksum incrementally.
Tested by sending IPv4/6 traffic with LRO enabled, RX checksum disabled
and watching nstat checksum error counters (in addition to the obvious
bandwidth drop caused by checksum errors).
This bug is usually "hidden" since LRO packets would go through the
CHECKSUM_UNNECESSARY flow which does not validate the packet checksum.
It's important to note that previous to this patch, LRO packets provided
with CHECKSUM_UNNECESSARY are indeed packets with a correct validated
checksum (even though the checksum inside the TCP header is incorrect),
since the hardware LRO aggregation is terminated upon receiving a packet
with bad checksum.
Fixes: e586b3b0ba ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Fixes a GCC maybe-uninitialized warning introduced by 48cca7e44f.
"text" is only initialized inside the if statement so only print debug
info there.
Fixes: 48cca7e44f ("libbpf: add support for bpf_call")
Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
After introduction of commit d0869c0071, there were some instances of
RX queue entries from a previous session (before the device was closed
and reopened) returned to the NAPI polling routine. Since the corresponding
socket buffers were freed, this resulted in a panic on reopen. Include
a check for a NULL skb here to avoid this.
Fixes: d0869c0071 ("ibmvnic: Clean RX pool buffers during device close")
Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sbi_ prefix would seem to indicate an SBI interface, and save is not
very specific. After applying this patch, reading head.S makes more sense.
Signed-off-by: Michael Clark <michaeljclark@mac.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Interrupt is allowed during exception handling.
There are warning messages if the kernel enables the configuration
'CONFIG_DEBUG_ATOMIC_SLEEP=y'.
BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:23
in_atomic(): 0, irqs_disabled(): 1, pid: 43, name: ash
CPU: 0 PID: 43 Comm: ash Tainted: G W 4.15.0-rc8-00089-g89ffdae-dirty #17
Call Trace:
[<000000009abb1587>] walk_stackframe+0x0/0x7a
[<00000000d4f3d088>] ___might_sleep+0x102/0x11a
[<00000000b1fd792a>] down_read+0x18/0x28
[<000000000289ec01>] do_page_fault+0x86/0x2f6
[<00000000012441f6>] _do_fork+0x1b4/0x1e0
[<00000000f46c3e3b>] ret_from_syscall+0xa/0xe
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Zong Li <zong@andestech.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
These three kconfig cleanups were found by ulfalyzer. They're all
things we were selecting that were undefined, either because they'd been
remove upstream or are part of a future RISC-V submission.
* ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE is obselete.
* RISCV_IRQ_INTC is the old name for our interrupt controller driver,
it'll be changed for the final submission and doesn't exist now.
* ARCH_WANT_OPTIONAL_GPIOLIB is obselete.
The ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE symbol was removed in
commit 51a021244b ("atomic64: no need for
CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE").
Remove the ARCH_HAS_ATOMIC64_DEC_IS_POSITIVE select from RISCV.
Discovered with the
https://github.com/ulfalizer/Kconfiglib/blob/master/examples/list_undefined.py
script.
Signed-off-by: Ulf Magnusson <ulfalizer@gmail.com>
Reviewed-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
The RISCV_IRQ_INTC configuration symbol is undefined, but RISCV selects
it. Quoting Palmer Dabbelt:
It looks like this slipped through, the symbol has been renamed
RISCV_INTC.
No RISCV_INTC configuration symbol has been merged either. Just remove
the RISCV_IRQ_INTC select for now.
Signed-off-by: Ulf Magnusson <ulfalizer@gmail.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
The ARCH_WANT_OPTIONAL_GPIOLIB symbol was removed in commit 65053e1a77
("gpio: delete ARCH_[WANTS_OPTIONAL|REQUIRE]_GPIOLIB"). GPIOLIB should
just be selected explicitly if needed.
Remove the ARCH_WANT_OPTIONAL_GPIOLIB select from RISCV.
See commit 0145071b33 ("x86: Do away with
ARCH_[WANT_OPTIONAL|REQUIRE]_GPIOLIB") and commit da9a1c6767 ("arm64: do
away with ARCH_[WANT_OPTIONAL|REQUIRE]_GPIOLIB") as well.
Discovered with the
https://github.com/ulfalizer/Kconfiglib/blob/master/examples/list_undefined.py
script.
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Magnusson <ulfalizer@gmail.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=J+hj
-----END PGP SIGNATURE-----
Merge tag 'leds_for-4.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds
Pull LED maintainer update:
"LED update to MAINTAINERS, to admit the reality.
Message from Richard:
"I've been looking at some of the emails but not needed to be
involved for a while now, you're doing fine without me!" [0]
Many thanks to Richard for his work as a founder of the LED
subsystem!"
[0] https://lkml.org/lkml/2018/2/18/145
* tag 'leds_for-4.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds:
MAINTAINERS: Remove Richard Purdie from LED maintainers
BNXT_RE_FLAG_TASK_IN_PROG doesn't handle multiple work
requests posted together. Track schedule of multiple
workqueue items by maintaining a per device counter
and proceed with IB dereg only if this counter is zero.
flush_workqueue is no longer required from
NETDEV_UNREGISTER path.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
During driver unload, the driver proceeds with cleanup
without waiting for the scheduled events. So the device
pointers get freed up and driver crashes when the events
are scheduled later.
Flush the bnxt_re_task work queue before starting
device removal.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Avoid system crash when destroy_qp is invoked while
the driver is processing the poll_cq. Synchronize these
functions using the cq_lock.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Driver leaves the QP memory pinned if QP create command
fails from the FW. Avoids this scenario by adding a proper
exit path if the FW command fails.
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
More testing needs to be done before enabling this feature.
Disabling the feature temporarily
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
MIPS' struct compat_flock doesn't match the 32-bit struct flock, as it
has an extra short __unused before pad[4], which combined with alignment
increases the size to 40 bytes compared with struct flock's 36 bytes.
Since commit 8c6657cb50 ("Switch flock copyin/copyout primitives to
copy_{from,to}_user()"), put_compat_flock() writes the full compat_flock
struct to userland, which results in corruption of the userland word
after the struct flock when running 32-bit userlands on 64-bit kernels.
This was observed to cause a bus error exception when starting Firefox
on Debian 8 (Jessie).
Reported-by: Peter Mamonov <pmamonov@gmail.com>
Signed-off-by: James Hogan <jhogan@kernel.org>
Tested-by: Peter Mamonov <pmamonov@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-mips@linux-mips.org
Cc: <stable@vger.kernel.org> # 4.13+
Patchwork: https://patchwork.linux-mips.org/patch/18646/
David S. Miller