SMC supports two variants: SMC-R and SMC-D. For data transport, SMC-R
uses RDMA devices, SMC-D uses so-called Internal Shared Memory (ISM)
devices. An ISM device only allows shared memory communication between
SMC instances on the same machine. For example, this allows virtual
machines on the same host to communicate via SMC without RDMA devices.
This patch adds the base infrastructure for SMC-D and ISM devices to
the existing SMC code. It contains the following:
* ISM driver interface:
This interface allows an ISM driver to register ISM devices in SMC. In
the process, the driver provides a set of device ops for each device.
SMC uses these ops to execute SMC specific operations on or transfer
data over the device.
* Core SMC-D link group, connection, and buffer support:
Link groups, SMC connections and SMC buffers (in smc_core) are
extended to support SMC-D.
* SMC type checks:
Some type checks are added to prevent using SMC-R specific code for
SMC-D and vice versa.
To actually use SMC-D, additional changes to pnetid, CLC, CDC, etc. are
required. These are added in follow-up patches.
Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The SMC protocol requires to send a separate consumer cursor update,
if it cannot be piggybacked to updates of the producer cursor.
Currently the decision to send a separate consumer cursor update
just considers the amount of data already received by the socket
program. It does not consider the amount of data already arrived, but
not yet consumed by the receiver. Basing the decision on the
difference between already confirmed and already arrived data
(instead of difference between already confirmed and already consumed
data), may lead to a somewhat earlier consumer cursor update send in
fast unidirectional traffic scenarios, and thus to better throughput.
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
s390 hardware supports the definition of a so-call Physical NETwork
IDentifier (short PNETID) per network device port. These PNETIDS
can be used to identify network devices that are attached to the same
physical network (broadcast domain).
On s390 try to use the PNETID of the ethernet device port used for
initial connecting, and derive the IB device port used for SMC RDMA
traffic.
On platforms without PNETID support fall back to the existing
solution of a configured pnet table.
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For SMC it is important to know the current port state of RoCE devices.
Monitoring port states has been triggered, when a RoCE device was added
to the pnet table. To support future alternatives to the pnet table the
monitoring of ports is made independent of the existence of a pnet table.
It starts once the smc_ib_device is established.
Due to this change smc_ib_remember_port_attr() is now a local function
and shuffling its location and the location of its used functions
makes any forward references obsolete.
And the duplicate SMC_MAX_PORTS definition is removed.
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Petr Machata says:
====================
Fixes for running mirror-to-gretap tests on veth
The forwarding selftests infrastructure makes it possible to run the
individual tests on a purely software netdevices. Names of interfaces to
run the test with can be passed as command line arguments to a test.
lib.sh then creates veth pairs backing the interfaces if none exist in
the system.
However, the tests need to recognize that they might be run on a soft
device. Many mirror-to-gretap tests are buggy in this regard. This patch
set aims to fix the problems in running mirror-to-gretap tests on veth
devices.
In patch #1, a service function is split out of setup_wait().
In patch #2, installing a trap is made optional.
In patch #3, tc filters in several tests are tweaked to work with veth.
In patch #4, the logic for waiting for neighbor is fixed for veth.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When running the test on soft devices, there's no mechanism to
gratuitously start resolving the neighbor for remote tunnel endpoint.
So instead of passively waiting, wait for the device to be up, and then
probe the neighbor with a ping.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When running mirror_gre_bridge_1d_vlan tests on veth, several issues
cause spurious failures:
- vlan_ethtype should be ip, not ipv6 even in mirror-to-ip6gretap case,
because the overlay packet is still IPv4.
- Similarly ip_proto matches the innermost IP protocol, so can't be used
to filter out GRE packet. Drop the corresponding condition.
- Because the above fixes the filters to match in slow path as well,
they need to be made skip_hw so as not to double-count packets.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are several cases where traffic that would normally be forwarded
in silicon needs to be observed in slow path. That's achieved by
trapping such traffic, and the functions trap_install() and
trap_uninstall() realize that. However, such treatment is obviously
wrong if the device in question is actually a soft device not backed by
an ASIC.
Therefore try to trap if possible, but fall back to inserting a continue
if not.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Split out of setup_wait() a function setup_wait_dev() that waits for a
single device. This gives tests the opportunity to wait for a selected
device after they tinkered with its upness.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
alloc_skb_with_frags uses __GFP_NORETRY for non-sleeping allocations
which is just a noop and a little bit confusing.
__GFP_NORETRY was added by ed98df3361 ("net: use __GFP_NORETRY for
high order allocations") to prevent from the OOM killer. Yet this was
not enough because fb05e7a89f ("net: don't wait for order-3 page
allocation") didn't want an excessive reclaim for non-costly orders
so it made it completely NOWAIT while it preserved __GFP_NORETRY in
place which is now redundant.
Drop the pointless __GFP_NORETRY because this function is used as
copy&paste source for other places.
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Radhey Shyam Pandey says:
====================
Fixes coding style in xilinx_emaclite.c
This patchset fixes checkpatch and kernel-doc warnings in
xilinx emaclite driver. No functional change.
Changes from v2:
-In 2/5 patch refactor if-else to make failure path return early.
-In 2/5 patch coalesce the format onto a single line and add the
missing space after the comma.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes below checkpatch checks-
CHECK: spaces preferred around that '*' (ctx:VxV)
CHECK: No space is necessary after a cast
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes below checkpatch warnings-
WARNING: Block comments use a trailing */ on a separate line
WARNING: Block comments use * on subsequent lines
WARNING: networking block comments don't use an empty /* line,
use /* Comment
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes below kernel-doc warnings:
Function parameter or member 'maxlen' not described in 'xemaclite_recv_data'
Function parameter or member 'address'not described in 'xemaclite_set_mac_address'
Excess function parameter 'addr' description in 'xemaclite_set_mac_address'
No description found for return value of 'xemaclite_interrupt'
No description found for return value of 'xemaclite_mdio_write'
Function parameter or member 'dev' not described in 'xemaclite_mdio_setup'
Excess function parameter 'ofdev' description in 'xemaclite_mdio_setup'
No description found for return value of 'xemaclite_open'
No description found for return value of 'xemaclite_close'
Excess function parameter 'match' description in 'xemaclite_of_probe'
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove else as it is not required with if doing a return.
It also coalesce the format onto a single line and add the
missing space after the comma. Fixes below checkpatch warning-
WARNING: else is not generally useful after a break or return
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch hardcoded function name with a reference to __func__ making
the code more maintainable. Address below checkpatch warning:
WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_read',
this function's name, in a string
+ "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_write',
this function's name, in a string
+ "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Maxime Chevallier says:
====================
net: mvpp2: Add big-endian support
This series allows to use PPv2 on system built as big endian.
The first patch fixes the way we represent TX and RX descriptors, so that
they used fixed little endianness as expected by the PPv2 controller.
The second reworks the way we handle the software representation of the
Header Parser entries, so that we don't use a union of arrays.
The last two patches fixes some incorrect byte swapping logic, that wen't
un-noticed on little-endian.
This whole series doesn't fix any existing bug for little-endian systems, and
since big-endian never worked for this driver, I didn't include 'fixes' tags.
This was tested on MacchiatoBin (Armada 8040).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When checking the skb->protocol field, we have to make sure we use the
proper endianness using htons, and not swab16.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vlan IDs must not be swapped when creating Header Parser entries. This
has no effect on little-endian systems, but is wrong for big-endian.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
PPv2's Header Parser use some large TCAM and SRAM entries, that are
duplicated in software so that we can write them to hardware only when
we are done modifying them.
Currently, PPv2 uses a union containing arrays of u32 and u8 to represent
these entries, to facilitate byte per byte access. This representation is
broken when we want to support big endian, and this makes the code
confusing to read.
This patch drops the union, and simply stores the TCAM and SRAM entries
as u32 arrays, each entry corresponding to a 32-bit register.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PPv2 controller always expect descriptors to be in little endian. We
must therefore force descriptors to use that format, and convert to the
host endianness when necessary.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur says:
====================
DPAA fixes
A couple of fixes for the DPAA drivers, addressing an issue
with short UDP or TCP frames (with padding) that were marked
as having a wrong checksum and dropped by the FMan hardware
and a problem with the buffer used for the scatter-gather
table being too small as per the hardware requirements.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The DPAA HW requires that at least 256 bytes from the start of the
first scatter-gather table entry are allocated and accessible. The
hardware reads the maximum size the table can have in one access,
thus requiring that the allocation and mapping to be done for the
maximum size of 256B even if there is a smaller number of entries
in the table.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The FMan hardware parser needs to be configured to remove the
short frame padding from the checksum calculation, otherwise
short UDP and TCP frames are likely to be marked as having a
bad checksum.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Driver performs the internal reload when it receives tx-timeout event from
the OS. Internal reload might fail in some scenarios e.g., fatal HW issues.
In such cases OS still see the link, which would result in undesirable
functionalities such as re-generation of tx-timeouts.
The patch addresses this issue by indicating the link-down to OS when
tx-timeout is detected, and keeping the link in down state till the
internal reload is successful.
Please consider applying it to 'net' branch.
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Static checkers complain that id_tbl->table points to longs and 4 bytes
is smaller than sizeof(long). But the since other side is dividing by
32 instead of sizeof(long), that means the current code works fine.
Anyway, it's more conventional to use the BITS_TO_LONGS() macro when
we're allocating a bitmap.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code assumes that there is 4 bytes in a pointer and it doesn't
allocate enough memory.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sk_rmem_alloc is larger than the receive buffer and we can't
schedule more memory for it, the skb will be dropped.
In above situation, if this skb is put into the ofo queue,
LINUX_MIB_TCPOFODROP is incremented to track it.
While if this skb is put into the receive queue, there's no record.
So a new SNMP counter is introduced to track this behavior.
LINUX_MIB_TCPRCVQDROP: Number of packets meant to be queued in rcv queue
but dropped because socket rcvbuf limit hit.
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fast Open key could be stored in different endian based on the CPU.
Previously hosts in different endianness in a server farm using
the same key config (sysctl value) would produce different cookies.
This patch fixes it by always storing it as little endian to keep
same API for LE hosts.
Reported-by: Daniele Iamartino <danielei@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds support for CBS reconfiguration using the TC application.
A new callback was added to TC ops struct and another one to DMA ops to
reconfigure the channel mode.
Tested in GMAC5.10.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Two regression fixes, and a new syscall wire-up.
A fix for the recent conversion to time64_t in the powermac RTC routines, which
caused time to go backward.
Another fix for fallout from the split PMD PTL conversion.
Wire up the new io_pgetevents() syscall.
Thanks to:
Aneesh Kumar K.V, Arnd Bergmann, Breno Leitao, Mathieu Malaterre.
-----BEGIN PGP SIGNATURE-----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=kHJC
-----END PGP SIGNATURE-----
Merge tag 'powerpc-4.18-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc fixes from Michael Ellerman:
"Two regression fixes, and a new syscall wire-up:
- A fix for the recent conversion to time64_t in the powermac RTC
routines, which caused time to go backward.
- Another fix for fallout from the split PMD PTL conversion.
- Wire up the new io_pgetevents() syscall.
Thanks to: Aneesh Kumar K.V, Arnd Bergmann, Breno Leitao, Mathieu
Malaterre"
* tag 'powerpc-4.18-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/powermac: Fix rtc read/write functions
powerpc/mm/32: Fix pgtable_page_dtor call
powerpc: Wire up io_pgetevents
and fixes interrupt property for DA850 SoC GPIO as defined in
device-tree.
Both of these are not introduced with v4.18 merge but have
existed prior.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=AENA
-----END PGP SIGNATURE-----
Merge tag 'davinci-fixes-for-v4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci into fixes
This fixes polarity of SD card write-protect pin on DA850 EVM
and fixes interrupt property for DA850 SoC GPIO as defined in
device-tree.
Both of these are not introduced with v4.18 merge but have
existed prior.
* tag 'davinci-fixes-for-v4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci:
ARM: dts: da850: Fix interrups property for gpio
ARM: davinci: board-da850-evm: fix WP pin polarity for MMC/SD
Signed-off-by: Olof Johansson <olof@lixom.net>
- Added power capabilities for the mmc host controller on the
hikey and hikey960 boards to avoid broken wifi.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=mr1l
-----END PGP SIGNATURE-----
Merge tag 'hisi-fixes-for-4.18' of git://github.com/hisilicon/linux-hisi into fixes
ARM64: hisi fixes for 4.18
- Added power capabilities for the mmc host controller on the
hikey and hikey960 boards to avoid broken wifi.
* tag 'hisi-fixes-for-4.18' of git://github.com/hisilicon/linux-hisi:
arm64: dts: hikey960: Define wl1837 power capabilities
arm64: dts: hikey: Define wl1835 power capabilities
Signed-off-by: Olof Johansson <olof@lixom.net>
Pull i2c fixes from Wolfram Sang:
- a revert because of bugzilla #200045 (and some documentation about
it)
- another regression fix in the i2c-gpio driver
- a leak fix for the i2c core
* 'i2c/for-current-fixed' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: gpio: initialize SCL to HIGH again
i2c: smbus: kill memory leak on emulated and failed DMA SMBus xfers
i2c: algos: bit: mention our experience about initial states
Revert "i2c: algo-bit: init the bus to a known state"
Daniel Borkmann says:
====================
This set contains three fixes that are mostly JIT and set_memory_*()
related. The third in the series in particular fixes the syzkaller
bugs that were still pending; aside from local reproduction & testing,
also 'syz test' wasn't able to trigger them anymore. I've tested this
series on x86_64, arm64 and s390x, and kbuild bot wasn't yelling either
for the rest. For details, please see patches as usual, thanks!
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Partially undo commit 9facc33687 ("bpf: reject any prog that failed
read-only lock") since it caused a regression, that is, syzkaller was
able to manage to cause a panic via fault injection deep in set_memory_ro()
path by letting an allocation fail: In x86's __change_page_attr_set_clr()
it was able to change the attributes of the primary mapping but not in
the alias mapping via cpa_process_alias(), so the second, inner call
to the __change_page_attr() via __change_page_attr_set_clr() had to split
a larger page and failed in the alloc_pages() with the artifically triggered
allocation error which is then propagated down to the call site.
Thus, for set_memory_ro() this means that it returned with an error, but
from debugging a probe_kernel_write() revealed EFAULT on that memory since
the primary mapping succeeded to get changed. Therefore the subsequent
hdr->locked = 0 reset triggered the panic as it was performed on read-only
memory, so call-site assumptions were infact wrong to assume that it would
either succeed /or/ not succeed at all since there's no such rollback in
set_memory_*() calls from partial change of mappings, in other words, we're
left in a state that is "half done". A later undo via set_memory_rw() is
succeeding though due to matching permissions on that part (aka due to the
try_preserve_large_page() succeeding). While reproducing locally with
explicitly triggering this error, the initial splitting only happens on
rare occasions and in real world it would additionally need oom conditions,
but that said, it could partially fail. Therefore, it is definitely wrong
to bail out on set_memory_ro() error and reject the program with the
set_memory_*() semantics we have today. Shouldn't have gone the extra mile
since no other user in tree today infact checks for any set_memory_*()
errors, e.g. neither module_enable_ro() / module_disable_ro() for module
RO/NX handling which is mostly default these days nor kprobes core with
alloc_insn_page() / free_insn_page() as examples that could be invoked long
after bootup and original 314beb9bca ("x86: bpf_jit_comp: secure bpf jit
against spraying attacks") did neither when it got first introduced to BPF
so "improving" with bailing out was clearly not right when set_memory_*()
cannot handle it today.
Kees suggested that if set_memory_*() can fail, we should annotate it with
__must_check, and all callers need to deal with it gracefully given those
set_memory_*() markings aren't "advisory", but they're expected to actually
do what they say. This might be an option worth to move forward in future
but would at the same time require that set_memory_*() calls from supporting
archs are guaranteed to be "atomic" in that they provide rollback if part
of the range fails, once that happened, the transition from RW -> RO could
be made more robust that way, while subsequent RO -> RW transition /must/
continue guaranteeing to always succeed the undo part.
Reported-by: syzbot+a4eb8c7766952a1ca872@syzkaller.appspotmail.com
Reported-by: syzbot+d866d1925855328eac3b@syzkaller.appspotmail.com
Fixes: 9facc33687 ("bpf: reject any prog that failed read-only lock")
Cc: Laura Abbott <labbott@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
If we would ever fail in the bpf_jit_prog() pass that writes the
actual insns to the image after we got header via bpf_jit_binary_alloc()
then we also need to make sure to free it through bpf_jit_binary_free()
again when bailing out. Given we had prior bpf_jit_prog() passes to
initially probe for clobbered registers, program size and to fill in
addrs arrray for jump targets, this is more of a theoretical one,
but at least make sure this doesn't break with future changes.
Fixes: 0546231057 ("s390/bpf: Add s390x eBPF JIT compiler backend")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Any eBPF JIT that where its underlying arch supports ARCH_HAS_SET_MEMORY
would need to use bpf_jit_binary_{un,}lock_ro() pair instead of the
set_memory_{ro,rw}() pair directly as otherwise changes to the former
might break. arm32's eBPF conversion missed to change it, so fix this
up here.
Fixes: 39c13c204b ("arm: eBPF JIT compiler")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
As suggested by Nick Piggin it seems we can drop the -ffunction-sections
compile flag, now that the kernel uses thin archives. Testing with 32-
and 64-bit kernel showed no difference in kernel size.
Suggested-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
mlx5e netdevice driver updates:
- Boris Pismenny added the support for UDP GSO in the first two patches.
Impressive performance numbers are included in the commit message,
@Line rate with ~half of the cpu utilization compared to non offload
or no GSO at all.
- From Tariq Toukan:
- Convert large order kzalloc allocations to kvzalloc.
- Added performance diagnostic statistics to several places in data path.
From Saeed and Eran,
- Update NIC HW stats on demand only, this is to eliminate the background
thread needed to update some HW statistics in the driver cache in
order to report error and drop counters from HW in ndo_get_stats.
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJbNVbbAAoJEEg/ir3gV/o+1SMH/R/jBMgqWKzuDL+QUTCm6BNH
Gcu7OPd3CUGT3wUujJ4sgVmYzyp70GZx0f843ct3Bmwcfwh8Yu/eOju7ldoQq2ns
6oz8sL6yvg/zmMfkc7DYFHrJSGu3Qh7fje+8zKVdoGlHkIFwR07bRkQolTKL6hem
qZHbn5o2RhFYLxjlGa7E7w41hXMx27gmHk4V/YdUGzHrExGB0fGbUXkkveCYiGYk
sB/JDSi02xjmEV2Nw8dX5jdZoBivaG2kPcBRD6Gpgmb+hntjIyTqwGdoJ7jDy1vj
A5wWHboj+Q/LtUNvpbb48fc/hhciddSxeB+c/1DMHjd4TchnBmPXyXwz5/7eTj8=
=xft1
-----END PGP SIGNATURE-----
Merge tag 'mlx5e-updates-2018-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5e-updates-2018-06-28
mlx5e netdevice driver updates:
- Boris Pismenny added the support for UDP GSO in the first two patches.
Impressive performance numbers are included in the commit message,
@Line rate with ~half of the cpu utilization compared to non offload
or no GSO at all.
- From Tariq Toukan:
- Convert large order kzalloc allocations to kvzalloc.
- Added performance diagnostic statistics to several places in data path.
From Saeed and Eran,
- Update NIC HW stats on demand only, this is to eliminate the background
thread needed to update some HW statistics in the driver cache in
order to report error and drop counters from HW in ndo_get_stats.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski says:
====================
net: Geneve options support for TC act_tunnel_key
Simon & Pieter say:
This set adds Geneve Options support to the TC tunnel key action.
It provides the plumbing required to configure Geneve variable length
options. The options can be configured in the form CLASS:TYPE:DATA,
where CLASS is represented as a 16bit hexadecimal value, TYPE as an 8bit
hexadecimal value and DATA as a variable length hexadecimal value.
Additionally multiple options may be listed using a comma delimiter.
v2:
- fix sparse warnings in patches 3 and 4 (first one reported by
build bot).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow setting tunnel options using the act_tunnel_key action.
Options are expressed as class:type:data and multiple options
may be listed using a comma delimiter.
# ip link add name geneve0 type geneve dstport 0 external
# tc qdisc add dev eth0 ingress
# tc filter add dev eth0 protocol ip parent ffff: \
flower indev eth0 \
ip_proto udp \
action tunnel_key \
set src_ip 10.0.99.192 \
dst_ip 10.0.99.193 \
dst_port 6081 \
id 11 \
geneve_opts 0102:80:00800022,0102:80:00800022 \
action mirred egress redirect dev geneve0
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Check the tunnel option type stored in tunnel flags when creating options
for tunnels. Thereby ensuring we do not set geneve, vxlan or erspan tunnel
options on interfaces that are not associated with them.
Make sure all users of the infrastructure set correct flags, for the BPF
helper we have to set all bits to keep backward compatibility.
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add extended ack support for the tunnel key action by using NL_SET_ERR_MSG
during validation of user input.
Cc: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Metadata may be NULL for one of two reasons:
* Missing user input
* Failure to allocate the metadata dst
Disambiguate these case by returning -EINVAL for the former and -ENOMEM
for the latter rather than -EINVAL for both cases.
This is in preparation for using extended ack to provide more information
to users when parsing their input.
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This was introduced more than a decade ago when sg chaining was
added, but we never really caught anything with it. The scatterlist
entry size can be critical, since drivers allocate it, so remove
the magic member. Recently it's been triggering allocation stalls
and failures in NVMe.
Tested-by: Jordan Glover <Golden_Miller83@protonmail.ch>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>