Enable the "wake-on-filer" (aka. wake on user defined packet)
wake on lan capability for the eTSEC ethernet nodes.
Cc: Li Yang <leoli@freescale.com>
Cc: Zhao Chenhui <chenhui.zhao@freescale.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the "fsl,wake-on-filer" property for eTSEC nodes to
indicate that the system has the power management
infrastructure needed to be able to wake up the system
via FGPI (filer, aka. h/w rx parser) interrupt.
Cc: Li Yang <leoli@freescale.com>
Cc: Zhao Chenhui <chenhui.zhao@freescale.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Benc says:
====================
openvswitch: add IPv6 tunneling support
This builds on the previous work that added IPv6 support to lwtunnels and
adds IPv6 tunneling support to ovs.
To use IPv6 tunneling, there needs to be a metadata based tunnel net_device
created and added to the ovs bridge. Currently, only vxlan is supported by
the kernel, with geneve to follow shortly. There's no need nor intent to add
a support for this into the vport-vxlan (etc.) compat layer.
v3: dropped the last two patches added in v2.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add netlink attributes for IPv6 tunnel addresses. This enables IPv6 support
for tunnels.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Store tunnel protocol (AF_INET or AF_INET6) in sw_flow_key. This field now
also acts as an indicator whether the flow contains tunnel data (this was
previously indicated by tun_key.u.ipv4.dst being set but with IPv6 addresses
in an union with IPv4 ones this won't work anymore).
The new field was added to a hole in sw_flow_key.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
When KASAN is enabled the frame size grows > 2048 bytes and we get a
warning, so make it smaller.
net/bridge/br_netlink.c: In function 'br_fill_info':
>> net/bridge/br_netlink.c:1110:1: warning: the frame size of 2160 bytes
>> is larger than 2048 bytes [-Wframe-larger-than=]
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for filtering neighbor dumps by device by adding the
NDA_IFINDEX attribute to the dump request.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-10-03
This series contains updates to i40e and i40evf, some of which are to
resolve more Red Hat bugzilla issues.
Jiang Liu updates the i40e and i40evf drivers to use numa_mem_id()
instead of numa_node_id() to get the nearest node with memory which
better supports memoryless nodes.
Anjali fixes an issue from Dan Carpenter <dan.carpenter@oracle.com>,
to resolve a memory leak in X722 RSS configuration path, where we should
free the memory allocated before exiting.
Shannon modifies the drivers to ensure we have the spinlocks before we
clear the ARQ and ASQ management registers. In addition, we widen the
locked portion insert a sanity check to ensure we are working with safe
register values.
Mitch fixes an issue where under certain circumstances, we can get an
extra VF_RESOURCES message from the PF driver at runtime. When this
occurs, we need to parse it because our VSI may have changed and that
will affect the relationship with the PF driver. But this parsing also
blows away our current MAC address, so resolve the issue by restoring
the current MAC address from the netdev struct after we parse the
resource message.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add additional error reporting to the generic DSA code, so it's easier
to debug when things go wrong. This was useful when initially bringing
up 88e6176 on a new board.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The link status is polled by the generic phy layer, there's no need to
duplicate that polling with additional polling. This additional polling
adds additional MDIO traffic, and races with the generic phy layer,
resulting in missing or duplicated link status messages.
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit allows installing a custom reg_update_bits function for cases where
the hardware provides a mechanism to set or clear register bits without a
read/modify/write cycle. Such is the case with the Microchip ENCX24J600.
If a custom reg_update_bits function is provided, it will only be used against
volatile registers.
Signed-off-by: Jon Ringle <jringle@gridpoint.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
This fixes
net/built-in.o: In function `fib_rebalance':
fib_semantics.c:(.text+0x9df14): undefined reference to `__divdi3'
and
net/built-in.o: In function `fib_rebalance':
net/ipv4/fib_semantics.c:572: undefined reference to `__aeabi_ldivmod'
Fixes: 0e884c78ee ("ipv4: L3 hash-based multipath")
Signed-off-by: Peter Nørlund <pch@ordbogen.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
8K message sizes are pretty important usecase for RDS current
workloads so we make provison to have 8K mrs available from the pool.
Based on number of SG's in the RDS message, we pick a pool to use.
Also to make sure that we don't under utlise mrs when say 8k messages
are dominating which could lead to 8k pull being exhausted, we fall-back
to 1m pool till 8k pool recovers for use.
This helps to at least push ~55 kB/s bidirectional data which
is a nice improvement.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
All HCA drivers seems to popullate max_mr caps and few of
them do both max_mr and max_fmr.
Hence update RDS code to make use of max_mr.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Fix below warning by marking rds_ib_fmr_wq static
net/rds/ib_rdma.c:87:25: warning: symbol 'rds_ib_fmr_wq' was not declared. Should it be static?
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
rds_ib_mr already keeps the pool handle which it associates
with. Lets use that instead of round about way of fetching
it from rds_ib_device.
No functional change.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
RDS IB mr pool has its own workqueue 'rds_ib_fmr_wq', so we need
to use queue_delayed_work() to kick the work. This was hurting
the performance since pool maintenance was less often triggered
from other path.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Just in case we are still handling the QP receive completion while the
rds_ibdev is released, drop the connection instead of crashing the kernel.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Similar to what we did with receive CQ completion handling, we split
the transmit completion handler so that it lets us implement batched
work completion handling.
We re-use the cq_poll routine and makes use of RDS_IB_SEND_OP to
identify the send vs receive completion event handler invocation.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
For better performance, we split the receive completion IRQ handler. That
lets us acknowledge several WCE events in one call. We also limit the WC
to max 32 to avoid latency. Acknowledging several completions in one call
instead of several calls each time will provide better performance since
less mutual exclusion locks are being performed.
In next patch, send completion is also split which re-uses the poll_cq()
and hence the code is moved to ib_cm.c
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
In Transport indepedent rds_sendmsg(), we shouldn't make decisions based
on RDS_LL_SEND_FULL which is used to manage the ring for RDMA based
transports. We can safely issue rds_send_xmit() and the using its
return value take decision on deferred work. This will also fix
the scenario where at times we are seeing connections stuck with
the LL_SEND_FULL bit getting set and never cleared.
We kick krdsd after any time we see -ENOMEM or -EAGAIN from the
ring allocation code.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Current process gives up if its send work over the batch limit.
The work queue will get kicked to finish off any other requests.
This fixes remainder condition from commit 443be0e5af ("RDS: make
sure not to loop forever inside rds_send_xmit").
The restart condition is only for the case where we reached to
over_batch code for some other reason so just retrying again
before giving up.
While at it, make sure we use already available 'send_batch_count'
parameter instead of magic value. The batch count threshold value
of 1024 came via commit 443be0e5af ("RDS: make sure not to loop
forever inside rds_send_xmit"). The idea is to process as big a
batch as we can but at the same time we don't hold other waiting
processes for send. Hence back-off after the send_batch_count
limit (1024) to avoid soft-lock ups.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
The function returns always non-negative values.
The problem has been detected using proposed semantic patch
scripts/coccinelle/tests/assign_signed_to_unsigned.cocci [1].
[1]: http://permalink.gmane.org/gmane.linux.kernel/2046107
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Commit ea317b267e ("bpf: Add new bpf map type to store the pointer
to struct perf_event") added perf_event.h to the main eBPF header, so
it gets included for all users. perf_event.h is actually only needed
from array map side, so lets sanitize this a bit.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For ARMv7 with UDIV instruction support, generate an UDIV instruction
followed by an MLS instruction.
For other ARM variants, generate code calling a C wrapper similar to
the jit_udiv() function used for BPF_ALU | BPF_DIV instructions.
Some performance numbers reported by the test_bpf module (the duration
per filter run is reported in nanoseconds, between "jitted:<x>" and
"PASS":
ARMv7 QEMU nojit: test_bpf: #3 DIV_MOD_KX jited:0 2196 PASS
ARMv7 QEMU jit: test_bpf: #3 DIV_MOD_KX jited:1 104 PASS
ARMv5 QEMU nojit: test_bpf: #3 DIV_MOD_KX jited:0 2176 PASS
ARMv5 QEMU jit: test_bpf: #3 DIV_MOD_KX jited:1 1104 PASS
ARMv5 kirkwood nojit: test_bpf: #3 DIV_MOD_KX jited:0 1103 PASS
ARMv5 kirkwood jit: test_bpf: #3 DIV_MOD_KX jited:1 311 PASS
Signed-off-by: Nicolas Schichan <nschichan@freebox.fr>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mark Craske says:
====================
Improve ASIX RX memory allocation error handling
The ASIX RX handler algorithm is weak on error handling.
There is a design flaw in the ASIX RX handler algorithm because the
implementation for handling RX Ethernet frames for the DUB-E100 C1 can
have Ethernet frames spanning multiple URBs. This means that payload data
from more than 1 URB is sometimes needed to fill the socket buffer with a
complete Ethernet frame. When the URB with the start of an Ethernet frame
is received then an attempt is made to allocate a socket buffer. If the
memory allocation fails then the algorithm sets the buffer pointer member
to NULL and the function exits (no crash yet). Subsequently, the RX hander
is called again to process the next URB which assumes there is a socket
buffer available and the kernel crashes when there is no buffer.
This patchset implements an improvement to the RX handling algorithm to
avoid a crash when no memory is available for the socket buffer.
The patchset will apply cleanly to the net-next master branch but the
created kernel has not been tested. The driver was tested on ARM kernels
v3.8 and v3.14 for a commercial product.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Avoid a loss of synchronisation of the Ethernet Data header 32-bit
word due to a failure to get a netdev socket buffer.
The ASIX RX handling algorithm returned 0 upon a failure to get
an allocation of a netdev socket buffer. This causes the URB
processing to stop which potentially causes a loss of synchronisation
with the Ethernet Data header 32-bit word. Therefore, subsequent
processing of URBs may be rejected due to a loss of synchronisation.
This may cause additional good Ethernet frames to be discarded
along with outputting of synchronisation error messages.
Implement a solution which checks whether a netdev socket buffer
has been allocated before trying to copy the Ethernet frame into
the netdev socket buffer. But continue to process the URB so that
synchronisation is maintained. Therefore, only a single Ethernet
frame is discarded when no netdev socket buffer is available.
Signed-off-by: Dean Jenkins <Dean_Jenkins@mentor.com>
Signed-off-by: Mark Craske <Mark_Craske@mentor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When RX Ethernet frames span multiple URB socket buffers,
the data stream may suffer a discontinuity which will cause
the current Ethernet frame in the netdev socket buffer
to be incomplete. This frame needs to be discarded instead
of appending unrelated data from the current URB socket buffer
to the Ethernet frame in the netdev socket buffer. This avoids
creating a corrupted Ethernet frame in the netdev socket buffer.
A discontinuity can occur when the previous URB socket buffer
held an incomplete Ethernet frame due to truncation or a
URB socket buffer containing the end of the Ethernet frame
was missing.
Therefore, add a sanity test for when an Ethernet frame
spans multiple URB socket buffers to check that the remaining
bytes of the currently received Ethernet frame point to
a good Data header 32-bit word of the next Ethernet
frame. Upon error, reset the remaining bytes variable to
zero and discard the current netdev socket buffer.
Assume that the Data header is located at the start of
the current socket buffer and attempt to process the next
Ethernet frame from there. This avoids unnecessarily
discarding a good URB socket buffer that contains a new
Ethernet frame.
Signed-off-by: Dean Jenkins <Dean_Jenkins@mentor.com>
Signed-off-by: Mark Craske <Mark_Craske@mentor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code is checking that the Ethernet frame will fit into a
netdev allocated socket buffer within the constraints of MTU size,
Ethernet header length plus VLAN header length.
The original code was checking rx->remaining each loop of the while
loop that processes multiple Ethernet frames per URB and/or Ethernet
frames that span across URBs. rx->remaining decreases per while loop
so there is no point in potentially checking multiple times that the
Ethernet frame (remaining part) will fit into the netdev socket buffer.
The modification checks that the size of the Ethernet frame will fit
the netdev socket buffer before allocating the netdev socket buffer.
This avoids grabbing memory and then deciding that the Ethernet frame
is too big and then freeing the memory.
Signed-off-by: Dean Jenkins <Dean_Jenkins@mentor.com>
Signed-off-by: Mark Craske <Mark_Craske@mentor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tidy-up the Data header 32-bit word synchronisation logic in
asix_rx_fixup_internal() by removing redundant logic tests.
The code is looking at the following cases of the Data header
32-bit word that is present before each Ethernet frame:
a) all 32 bits of the Data header word are in the URB socket buffer
b) first 16 bits of the Data header word are at the end of the URB
socket buffer
c) last 16 bits of the Data header word are at the start of the URB
socket buffer eg. split_head = true
Note that the lifetime of rx->split_head exists outside of the
function call and is accessed per processing of each URB. Therefore,
split_head being true acts on the next URB to be processed.
To check for b) the offset will be 16 bits (2 bytes) from the end of
the buffer then indicate split_head is true.
To check for c) split_head must be true because the first 16 bits
have been found.
To check for a) else c)
Note that the || logic of the old code included the state
(skb->len - offset == sizeof(u16) && rx->split_head) which is not
possible because the split_head cannot be true whilst checking for b).
This is because the split_head indicates that the first 16 bits have
been found and that is not possible whilst checking for the first 16
bits. Therefore simplify the logic.
Signed-off-by: Dean Jenkins <Dean_Jenkins@mentor.com>
Signed-off-by: Mark Craske <Mark_Craske@mentor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Data header synchronisation is easier to understand
if the variables "remaining" and "size" are renamed.
Therefore, the lifetime of the "remaining" variable exists
outside of asix_rx_fixup_internal() and is used to indicate
any remaining pending bytes of the Ethernet frame that need
to be obtained from the next socket buffer. This allows an
Ethernet frame to span across multiple socket buffers.
"size" is now local to asix_rx_fixup_internal() and contains
the size read from the Data header 32-bit word.
Add "copy_length" to hold the number of the Ethernet frame
bytes (maybe a part of a full frame) that are to be copied
out of the socket buffer.
Signed-off-by: Dean Jenkins <Dean_Jenkins@mentor.com>
Signed-off-by: Mark Craske <Mark_Craske@mentor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current ongoing effort to dump existing cBPF seccomp filters back
to user space requires to hold the pre-transformed instructions like
we do in case of socket filters from sk_attach_filter() side, so they
can be reloaded in original form at a later point in time by utilities
such as criu.
To prepare for this, simply extend the bpf_prog_create_from_user()
API to hold a flag that tells whether we should store the original
or not. Also, fanout filters could make use of that in future for
things like diag. While fanout filters already use bpf_prog_destroy(),
move seccomp over to them as well to handle original programs when
present.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Tycho Andersen <tycho.andersen@canonical.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Tycho Andersen <tycho.andersen@canonical.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This ethernet driver supports the Micorchip enc424j600/626j600 Ethernet
controller over a SPI bus interface. This driver makes use of the regmap API to
optimize access to registers by caching registers where possible.
Datasheet:
http://ww1.microchip.com/downloads/en/DeviceDoc/39935b.pdf
Signed-off-by: Jon Ringle <jringle@gridpoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit allows installing a custom reg_update_bits function for cases where
the hardware provides a mechanism to set or clear register bits without a
read/modify/write cycle. Such is the case with the Microchip ENCX24J600.
Signed-off-by: Jon Ringle <jringle@gridpoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current code invokes hang reset in case of error interrupt. We should
hang reset only in case of tx timeout. This because of the way hang reset
is implemented in firmware. Hang reset takes more firmware resources than
soft reset. Adaptor does not generate error interrupt in case of tx
timeout.
Hang reset only in case of tx timeout, in .ndo_tx_timeout. Do soft reset
otherwise. Introduce deferred work, enic_tx_hang_reset, to do hang reset.
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some of the enic adaptors are know to generate spurious interrupts. When
error interrupt is generated, driver just resets the device. This patch
resets the device only when an error is occurred.
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hariprasad Shenai says:
====================
cxgb4: Trivial fixes for cxgb4
Fixes the following issues
Don't read non existent T4/T5/T6 adapter registers for ethtool dump.
For T4, dont read mailbox control registers. Adds new devlog faility and
report correct link speed for unsupported ones.
This patch series has been created against net-next tree and includes
patches on cxgb4 driver.
We have included all the maintainers of respective drivers. Kindly review
the change and let us know in case of any review comments.
====================
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we get garbage from the firmware with weird Port Speeds,
etc. we should emit a warning regarding unsupported speeds rather than
use the bogus default of "10Mbps" which isn't even an option in the
firmware Port Information message
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The firmware team added a new Device Log Facility FW_DEVLOG_FACILITY_CF,
but the driver has been decoding Device Log messages with that Facility as
"(NULL)", fixing it.
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
T4 doesn't have the Shadow copy of the register which we can read without
side effect. So don't read mbox control register for T4 adapter
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Update T4/T5/T6 adapter register ranges so that it doesn't read non
existent registers when dumped using ethtool
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric W. Biederman says:
====================
net: Pass net through ip fragmention
This is the next installment of my work to pass struct net through the
output path so the code does not need to guess how to figure out which
network namespace it is in, and ultimately routes can have output
devices in another network namespace.
This round focuses on passing net through ip fragmentation which we seem
to call from about everywhere. That is the main ip output paths, the
bridge netfilter code, and openvswitch. This has to happend at once
accross the tree as function pointers are involved.
First some prep work is done, then ipv4 and ipv6 are converted and then
temporary helper functions are removed.
====================
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sowmini Varadhan says:
====================
RDS: RDS-TCP perf enhancements
A 3-part patchset that (a) improves current RDS-TCP perf
by 2X-3X and (b) refactors earlier robustness code for
better observability/scaling.
Patch 1 is an enhancment of earlier robustness fixes
that had used separate sockets for client and server endpoints to
resolve race conditions. It is possible to have an equivalent
solution that does not use 2 sockets. The benefit of a
single socket solution is that it results in more predictable
and observable behavior for the underlying TCP pipe of an
RDS connection
Patches 2 and 3 are simple, straightforward perf bug fixes
that align the RDS TCP socket with other parts of the kernel stack.
v2: fix kbuild-test-robot warnings, comments from Sergei Shtylov
and Santosh Shilimkar.
====================
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the same reasons as commit 2f53384424 ("tcp: allow splice() to
build full TSO packets") and commit 35f9c09fe9 ("tcp: tcp_sendpages()
should call tcp_push() once"), rds_tcp_xmit may have multiple pages to
send, so use the MSG_MORE and MSG_SENDPAGE_NOTLAST as hints to
tcp_sendpage()
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using the value of RDS_TCP_DEFAULT_BUFSIZE (128K)
clobbers efficient use of TSO because it inflates the size_goal
that is computed in tcp_sendmsg/tcp_sendpage and skews packet
latency, and the default values for these parameters actually
results in significantly better performance.
In request-response tests using rds-stress with a packet size of
100K with 16 threads (test parameters -q 100000 -a 256 -t16 -d16)
between a single pair of IP addresses achieves a throughput of
6-8 Gbps. Without this patch, throughput maxes at 2-3 Gbps under
equivalent conditions on these platforms.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
