Michael Qiu [Wed, 10 Dec 2014 10:46:42 +0000 (18:46 +0800)]
eal: fix build with icc
lib/librte_eal/linuxapp/eal/eal.c(461): error #2259: non-pointer
conversion from "long long" to "void *" may lose significant bits
RTE_PTR_ALIGN_CEIL((uintptr_t)addr, RTE_PGSIZE_16M);
The root cause is that "RTE_PGSIZE_16M" is defined as unsigned long long.
But in i686 platform "void *" is 32-bit.
It is safe to cast to size_t and make it works in both 32 & 64-bit
platform.
Signed-off-by: Michael Qiu <michael.qiu@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Michael Qiu [Wed, 10 Dec 2014 10:46:41 +0000 (18:46 +0800)]
eal: fix build for 32-bit system
lib/librte_eal/linuxapp/eal/eal_memory.c:324:4: error: comparison
is always false due to limited range of data type [-Werror=type-limits]
|| (hugepage_sz == RTE_PGSIZE_16G)) {
^
This was introuduced by commit
b77b5639:
mem: add huge page sizes for IBM Power
The root cause is that size_t is 32-bit in i686 platform,
but RTE_PGSIZE_16M and RTE_PGSIZE_16G are always 64-bit.
Force hugepage_sz to always 64-bit to avoid this issue.
Signed-off-by: Michael Qiu <michael.qiu@intel.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Jia Yu [Fri, 7 Nov 2014 17:28:09 +0000 (09:28 -0800)]
lib: fix cache alignment of structures
Include rte_memory.h for lib files that use __rte_cache_aligned
attribute.
Consider the following code:
struct per_core_foo {
...
} __rte_cache_aligned;
struct global_foo {
struct per_core_foo foo[RTE_MAX_CORE];
};
If __rte_cache_aligned is not defined (rte_memory.h is not included),
the code compiles but the structure is not aligned... it defines the
structure and creates a global variable called __rte_cache_aligned.
And this can lead to really bad things if this code is in a .h that
is included by files that may or may not include rte_memory.h
Signed-off-by: Jia Yu <jyu@vmware.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Sergio Gonzalez Monroy [Wed, 22 Oct 2014 16:36:22 +0000 (17:36 +0100)]
mk: fix build 32-bits shared libraries with 64-bits system
Incompatible libraries error when building shared libraries for 32bits on
a 64bits system.
Fix issue by passing CPU_CFLAGS to CC when LINK_USING_CC is enabled.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Hiroshi Shimamoto [Wed, 3 Dec 2014 23:33:54 +0000 (23:33 +0000)]
mk: fix build shared libraries
Only CPU_LDFLAGS is used in mk/rte.sharelib.mk.
It should be LDFLAGS to build the library with correct linkage options.
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Reviewed-by: Hayato Momma <h-momma@ce.jp.nec.com>
Thomas Monjalon [Sat, 6 Dec 2014 10:24:04 +0000 (11:24 +0100)]
version: 1.8.0-rc3
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Huawei Xie [Wed, 12 Nov 2014 22:34:07 +0000 (06:34 +0800)]
examples/vhost: use factorized default Rx/Tx configuration
Refer to Pablo's commit (
81f7ecd934372fc):
"use factorized default Rx/Tx configuration
For apps that were using default rte_eth_rxconf and rte_eth_txconf
structures, these have been removed and now they are obtained by
calling rte_eth_dev_info_get, just before setting up RX/TX queues."
Move zero copy's deferred start set up ahead.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Huawei Xie [Wed, 12 Nov 2014 22:34:06 +0000 (06:34 +0800)]
examples/vhost: support new VMDQ API for i40e
In Niantic, if VMDQ mode is set, all queues are allocated to VMDQ in DPDK.
In I40E, only configured part of continous queues are allocated to VMDQ.
The rte_eth_dev_info structure is extended to provide VMDQ queue base,
queue number, and VMDQ pool base information.
This patch support the new VMDQ API in vhost example.
FIXME in PMD:
* added mac address will be flushed at rte_eth_dev_start.
* we don't support selectively setting up queues well.
Test report: http://dpdk.org/ml/archives/dev/2014-December/009427.html
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Tested-by: Jingguo Fu <jingguox.fu@intel.com>
Huawei Xie [Tue, 2 Dec 2014 09:02:06 +0000 (17:02 +0800)]
i40e: use macros for vlan filtering registers
Add two macros I40E_VFTA_IDX and I40E_VFTA_BIT for vlan filter search and set.
Add vlan_id check in vlan filter search and set function.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Huawei Xie [Tue, 2 Dec 2014 09:02:05 +0000 (17:02 +0800)]
i40e: fix vlan filtering
">> 5" rather than ">> 4"
vlan id is a 12 bit value.
VFTA is 128 x 32 bit array (128 double word array) which could store 2^12 vlan bits.
Each bit represents whether corresponding vlan tag is set in the VSI.
Use high 7 bits as the index for the double word array.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Konstantin Ananyev [Fri, 5 Dec 2014 15:20:34 +0000 (15:20 +0000)]
ixgbe: do not override buffer length
The template mbuf_initializer is hard coded with a buflen which
might have been set differently by the application at the time of
mbuf pool creation.
- move buf_len fields out of rearm_data marker.
- make ixgbe_recv_pkts_vec() not touch buf_len field at all
(as all other RX functions behave).
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Jean-Mickael Guerin <jean-mickael.guerin@6wind.com>
Jean-Mickael Guerin [Thu, 4 Dec 2014 14:26:20 +0000 (15:26 +0100)]
ixgbe: fix setup of mbuf initializer template
Add a compiler barrier to make sure all fields covered by
the marker rearm_data are assigned before the read.
Fixes:
0ff3324da2 ("ixgbe: rework vector pmd following mbuf changes")
Signed-off-by: Jean-Mickael Guerin <jean-mickael.guerin@6wind.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Bruce Richardson [Fri, 5 Dec 2014 15:57:12 +0000 (15:57 +0000)]
enic: fix uninitialized variable
The variable notify_pa is only initialized inside one branch of
an if statement, triggering a compiler error with clang 3.3 on FreeBSD.
CC vnic/vnic_dev.o
lib/librte_pmd_enic/vnic/vnic_dev.c:777:6: fatal error: variable 'notify_pa'
is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
if (!vnic_dev_in_reset(vdev)) {
Fix this issue by adding "= 0" to the variable definition.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Bruce Richardson [Fri, 5 Dec 2014 15:57:11 +0000 (15:57 +0000)]
enic: fix initialization error with clang
This patch fixes the following compiler error raised by clang 3.3
on FreeBSD 10:
CC enic_clsf.o
lib/librte_pmd_enic/enic_clsf.c:99:25: fatal error: missing field 'u' initializer [-Wmissing-field-initializers]
struct filter fltr = {0};
It fixes it by changing the initializer to set a named field to zero,
thereby automatically setting the rest of the unnamed fields also to
zero.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
John W. Linville [Thu, 4 Dec 2014 21:42:05 +0000 (16:42 -0500)]
af_packet: add compile-time checks for kernel-specific options
This allows the PMD to compile with kernels that don't support the
options in question. The "#if defined(...)" lines are a bit ugly,
but I don't know of any better way to accomplish the task.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Bruce Richardson [Mon, 24 Nov 2014 15:50:39 +0000 (15:50 +0000)]
doc: add freebsd ports
Since the DPDK is now part of the BSD ports collection, we should
recommend installing from ports as the best way to get it up and
running.
In order to achieve this, while still keeping the document readable, the
chapter on system requirements has been moved to instead be a section
within the chapter on compiling the DPDK outside of the ports
collection. This move is necessary, since it covered a lot of detail on
installing other ports required to build DPDK. These steps are not
needed when installing DPDK itself from ports.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Bruce Richardson [Mon, 24 Nov 2014 15:48:56 +0000 (15:48 +0000)]
doc: adjust line lengths in freebsd guide
The FreeBSD GSG rst files had very inconsistent line lengths for text
within paragraph blocks. Sometimes a line would be very short, while often
lines would be quite long.
This patch adjusts the formatting of the rst files so that lines break
at approx the 80-character mark, as is standard in the DPDK source code.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Bruce Richardson [Mon, 24 Nov 2014 14:23:52 +0000 (14:23 +0000)]
doc: auto-generate date in guides
The index.html file for each of the "guide" docs had a hard-coded
date value in them of June 2014. Rather than update each of these
for each revision, just use the |today| directive to insert the date
at which the document was generated.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Pablo de Lara [Mon, 1 Dec 2014 11:40:48 +0000 (11:40 +0000)]
doc: fix testpmd guide
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Pablo de Lara [Mon, 1 Dec 2014 11:40:47 +0000 (11:40 +0000)]
doc: reorder testpmd commands
Moved commands in testpmd UG to set queue rates
to match order in testpmd command help.
Created new section "Filters" to match that
same section in testpmd UG, and moved all
commands related to it there.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Pablo de Lara [Mon, 1 Dec 2014 11:40:46 +0000 (11:40 +0000)]
doc: fix testpmd commands
tx_checksum set function does not use bitmask anymore, but strings
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Pablo de Lara [Mon, 1 Dec 2014 11:40:45 +0000 (11:40 +0000)]
doc: new testpmd commands
Added info in testpmd functions section for the following commands:
- tunnel_filter add
- tunnel_filter rm
- rx_vxlan_port add
- rx_vxlan_port rm
- port stop/start queue
- set port mac address filter (for VF)
- tx_checksum set
- tso set
- tso show
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Siobhan Butler [Tue, 2 Dec 2014 21:11:42 +0000 (21:11 +0000)]
doc: add vhost library
As Vhost will be a library in DPDK 1.8, adding a new section to
Programmer's Guide to describe its use.
Signed-off-by: Siobhan Butler <siobhan.a.butler@intel.com>
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Siobhan Butler [Tue, 2 Dec 2014 14:02:46 +0000 (14:02 +0000)]
doc: add distributor application
New distributor sample app user guide section for sample app user guide.
Signed-off-by: Siobhan Butler <siobhan.a.butler@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Declan Doherty [Mon, 1 Dec 2014 17:10:12 +0000 (17:10 +0000)]
doc: update bonding
Adding details for link status interrupts and link status polling.
Adding details for mode 4 / mode 5
Tidying up rst document to conform to 80 character line limit
Adding diagrams to explain bonding modes
Removed link_bonding.png file
Signed-off-by: Declan Doherty <declan.doherty@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Bruce Richardson [Wed, 3 Dec 2014 16:56:59 +0000 (16:56 +0000)]
examples/multi_process: fix resilience by enabling Rx drop
The symmetric_mp example app is set up to allow two processes to
share a NIC port, with each pulling packets from one queue. In order
to have the app continue working when one of the process dies, the
drop_en bit should be set in the NIC configuration. Without this bit
set, the NIC will stall once any queue fills. With the bit set, once
a queue fills, all subsequent packets for that queue are discarded
allowing other queues to continue operating as normal.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Bruce Richardson [Thu, 4 Dec 2014 14:24:12 +0000 (14:24 +0000)]
table: fix lookup with incomplete bitmask
When a lookup was done on a table_array structure with an incomplete
bitmask, the results was always zero hits. This was because the
pkts_mask value was cleared as we process each entry, and the result
was assigned at the end of the loop, when pkts_mask was zero.
Changing the assignment to occur at the start, before the pkts_mask
gets cleared, fixes this issue.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Jingjing Wu [Thu, 4 Dec 2014 15:40:23 +0000 (23:40 +0800)]
i40e: setup flow director only if enabled
In order not to affect the FVL's performance by default setting, this
patch moves the flow director initialization from i40e_pf_setup to
i40e_dev_configure according to the mode in fdir configure info.
Then the resources used for flow director will be only setup if it is enabled.
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
Jijiang Liu [Tue, 2 Dec 2014 15:06:07 +0000 (23:06 +0800)]
mbuf: replace inner fields by outer fields semantic
Replace the inner_l2_len and the inner_l3_len field with the
outer_l2_len and outer_l3_len field, and rework csum forward engine
and i40e PMD due to these changes.
Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Jijiang Liu [Tue, 2 Dec 2014 15:06:06 +0000 (23:06 +0800)]
mbuf: add Tx offloading flags for tunnels
Replace PKT_TX_VXLAN_CKSUM with PKT_TX_UDP_TUNNEL_PKT in order to indicate
a packet is an UDP tunneling packet, and introduce 3 TX offload flags for
outer IP TX checksum, which are PKT_TX_OUTER_IP_CKSUM, PKT_TX_OUTER_IPV4
and PKT_TX_OUTER_IPV6 respectively.
Rework csum forward engine and i40e PMD due to these changes.
Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Jijiang Liu [Tue, 2 Dec 2014 15:06:05 +0000 (23:06 +0800)]
mbuf: remove aliasing of Tx offloading flags with Rx ones
The reason of redefining the PKT_TX_IPV4 and the PKT_TX_IPV6 is listed below,
It will avoid to send a packet with a bad info:
- we receive a Ether/IP6/IP4/L4/data packet
- the driver sets PKT_RX_IPV6_HDR
- the stack decapsulates IP6
- the stack sends the packet, it has the PKT_TX_IPV6 flag but it's an IPv4 packet.
Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Thomas Monjalon [Wed, 3 Dec 2014 20:12:00 +0000 (21:12 +0100)]
app/testpmd: fix endianness detection
Use endianness detection factorized in EAL.
The comment about arpa/inet.h is not valid anymore since
commit
d07180f211c08 ("net: fix conflict with libc").
The macro _htons could also be moved in rte_byteorder.h
by providing some constant byte swapping.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Thomas Monjalon [Wed, 3 Dec 2014 20:01:19 +0000 (21:01 +0100)]
eal: detect endianness
There is no standard to check endianness.
So we need to try different checks.
Previous trials were done in testpmd (see commits
51f694dd40f56 and
64741f237cf29) without full success.
This one is not guaranteed to work everywhere so it could
evolve when exceptions are found.
If endianness is not detected, there is a fallback on x86
to little endian. It could be forced before doing detection
but it would add some arch-dependent code in the generic header.
The option CONFIG_RTE_ARCH_BIG_ENDIAN introduced for IBM Power only
(commit
a982ec81d84d53) can be removed. A compile-time check is better.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
Alan Carew [Fri, 5 Dec 2014 14:19:07 +0000 (15:19 +0100)]
cmdline: fix overflow on bsd
When using test-pmd with flow director in FreeBSD, the application will
segfault/Bus error while parsing the command-line. This is due to how
each commands result structure is represented during parsing, where the offsets
for each tokens value is stored in a character array(char result_buf[BUFSIZ])
in cmdline_parse()(./lib/librte_cmdline/cmdline_parse.c).
The overflow occurs where BUFSIZ is less than the size of a commands result
structure, in this case "struct cmd_pkt_filter_result"
(app/test-pmd/cmdline.c) is 1088 bytes and BUFSIZ on FreeBSD is 1024 bytes as
opposed to 8192 bytes on Linux.
The problem can be reproduced by running test-pmd on FreeBSD:
./testpmd -c 0x3 -n 4 -- -i --portmask=0x3 --pkt-filter-mode=perfect
And adding a filter:
add_perfect_filter 0 udp src 192.168.0.0 1024 dst 192.168.0.0 1024 flexbytes
0x800 vlan 0 queue 0 soft 0x17
This patch removes the OS dependency on BUFSIZ and defines and uses a
library #define CMDLINE_PARSE_RESULT_BUFSIZE 8192
Added boundary checking to ensure this buffer size cannot overflow, with
an error message being produced.
Suggested-by: Olivier Matz <olivier.matz@6wind.com>
http://git.droids-corp.org/?p=libcmdline.git;a=commitdiff;h=
b1d5b169352e57df3fc14c51ffad4b83f3e5613f
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Tested-by: Bruce Richardson <bruce.richardson@intel.com>
Thomas Monjalon [Thu, 4 Dec 2014 15:13:45 +0000 (16:13 +0100)]
cmdline: revert fix overflow on bsd
Revert commit
a0547e0a751100 because it is an old version
of the patch and was applied by error.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Thomas Monjalon [Tue, 2 Dec 2014 13:38:31 +0000 (14:38 +0100)]
enic: fix warnings
A lot of warnings were not seen because $(WERROR_FLAGS) was not set
in the Makefile. But they appear with toolchains that enforce more checks.
-Wno-deprecated seems useless.
-Wno-strict-aliasing is added to avoid false positives.
This patch cleans up unused variable, unused functions, wrong types,
static declarations, etc. A lot of functions have unused parameters;
it suggests that more clean-up could be needed.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Sujith Sankar <ssujith@cisco.com>
Chao Zhu [Thu, 4 Dec 2014 10:14:08 +0000 (18:14 +0800)]
kni: fix build on IBM Power
Because of different cache line size, the alignment of struct
rte_kni_mbuf in rte_kni_common.h doesn't work on IBM Power. This patch
changed from 64 to RTE_CACHE_LINE_SIZE micro to do the alignment.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Alan Carew [Mon, 20 Oct 2014 15:23:13 +0000 (16:23 +0100)]
cmdline: fix overflow on bsd
When using test-pmd with flow director in FreeBSD, the application will
segfault/Bus error while parsing the command-line. This is due to how
each commands result structure is represented during parsing, where the offsets
for each tokens value is stored in a character array(char result_buf[BUFSIZ])
in cmdline_parse()(./lib/librte_cmdline/cmdline_parse.c).
The overflow occurs where BUFSIZ is less than the size of a commands result
structure, in this case "struct cmd_pkt_filter_result"
(app/test-pmd/cmdline.c) is 1088 bytes and BUFSIZ on FreeBSD is 1024 bytes as
opposed to 8192 bytes on Linux.
This patch removes the OS dependency on BUFSIZ and defines and uses a
library #define CMDLINE_PARSE_RESULT_BUFSIZE 8192
The problem can be reproduced by running test-pmd on FreeBSD:
./testpmd -c 0x3 -n 4 -- -i --portmask=0x3 --pkt-filter-mode=perfect
And adding a filter:
add_perfect_filter 0 udp src 192.168.0.0 1024 dst 192.168.0.0 1024 flexbytes
0x800 vlan 0 queue 0 soft 0x17
Signed-off-by: Alan Carew <alan.carew@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Takayuki Usui [Wed, 3 Dec 2014 01:37:26 +0000 (10:37 +0900)]
kni: create interface in current network namespace
With this patch, KNI interface (e.g. vEth0) is created in the
network namespace where the DPDK application is running.
Otherwise, all interfaces are created in the default namespace
in the host.
put_net() is required, since get_net_ns_by_pid() increments
the reference counter of the network namespace with get_net().
Signed-off-by: Takayuki Usui <takayuki@midokura.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Helin Zhang [Wed, 3 Dec 2014 01:13:27 +0000 (09:13 +0800)]
i40e: fix build with 16-byte descriptors
The compile error will occur as below when set 'RTE_LIBRTE_I40E_16BYTE_RX_DESC=y'.
'fd_id' should be used to replace 'fd', as 'fd' is not defined in that structure
at all. In addition, local variable of 'flexbl' and 'flexbh' must be used only if
32 bytes RX descriptor is selected.
error logs:
lib/librte_pmd_i40e/i40e_rxtx.c: In function i40e_rxd_build_fdir:
lib/librte_pmd_i40e/i40e_rxtx.c:431:28: error: volatile union <anonymous> has no member named fd
lib/librte_pmd_i40e/i40e_rxtx.c:427:19: error: unused variable flexbl [-Werror=unused-variable]
lib/librte_pmd_i40e/i40e_rxtx.c:427:11: error: unused variable flexbh [-Werror=unused-variable]
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Dennis Marinus [Tue, 2 Dec 2014 00:39:06 +0000 (16:39 -0800)]
table: fix maybe-uninitialized variable with gcc lto
This patch fixes a maybe-uninitialized warning when compiling DPDK with
GCC 4.9 + Link Time Optimization.
Signed-off-by: Dennis Marinus <dmarinus@amazon.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Thomas Monjalon [Mon, 1 Dec 2014 17:11:02 +0000 (18:11 +0100)]
ixgbe: fix build with bypass and debug enabled
Since commit
aae1047905621 ("use the right debug macro"),
DEBUGOUT was replaced by PMD_DRV_LOG which requires at least
2 arguments. But the level argument was missing.
Commit
7a10de5e27 fixed the logs but not the macros FUNC_PTR_OR_*
which are not preprocessed if RTE_LIBRTE_IXGBE_DEBUG_DRIVER is disabled.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Bruce Richardson [Mon, 1 Dec 2014 11:38:55 +0000 (11:38 +0000)]
app/testpmd: fix macro check for little endian
Compiling with clang on FreeBSD gave a compilation error:
app/test-pmd/csumonly.c:84:5: fatal error: '__BYTE_ORDER' is not defined, evaluates to 0 [-Wundef]
Querying the preprocessor defines show both the define and value used
are incorrect.
$ clang -dM -E - < /dev/null | grep BYTE
\#define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__
Changing the check to __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ then
resolves the issue.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Bruce Richardson [Mon, 1 Dec 2014 11:38:54 +0000 (11:38 +0000)]
app/testpmd: fix out-of-range error on bsd
The definition value for IPPROTO_DIVERT protocol uses a value
which is out of range of the uint8_t type, giving clang compiler
errors on FreeBSD.
app/test-pmd/icmpecho.c:231:7: fatal error: overflow converting case value
to switch condition type (258 to 2) [-Wswitch]
case IPPROTO_DIVERT: /**< divert pseudo-protocol */
This is fixed by having the code to return the protocol name
use the uint16_t type for the protocol value input.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Sujith Sankar [Sat, 29 Nov 2014 07:17:37 +0000 (12:47 +0530)]
enic: fix build with clang
This patch fixes the warnings and error reported by clang compiler on Linux.
Reported-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Olivier Matz [Mon, 1 Dec 2014 10:36:13 +0000 (11:36 +0100)]
ixgbe: fix bitfield assignation with clang
Commit
1224decaa44 ("support TCP segmentation offload")
changed the way the bitfields are assigned in ixgbe, example:
tx_offload_mask.l2_len = ~0;
This result in a compilation error with clang:
error: implicit truncation from 'int' to bitfield
changes value from -1 to 127 [-Werror,-Wbitfield-constant-conversion]
Replacing the '=' with a '|=' fixes the issue.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Sergio Gonzalez Monroy [Thu, 30 Oct 2014 10:57:42 +0000 (10:57 +0000)]
mk: fix linking with some linux toolchains
Ubuntu/Debian toolchain passes --as-needed flag to the linker by default.
Add --no-as-needed flag by default in linuxapp exec-env to ensure correct
linking.
The problem arises because librte_eal doesn't add a DT_NEEDED entry for
librte_mempool despite the fact that it references symbols in that library.
It does this because we don't explicitly link with -lrte_mempool when we
build librte_eal.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
David Marchand [Fri, 28 Nov 2014 15:42:44 +0000 (16:42 +0100)]
scripts: fix newline in configuration with bsd sed
Use of \n in sed expression is not portable and triggered an invalid
configuration on BSD (at least).
Replace with an explicit newline.
Reported-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Sujith Sankar [Fri, 28 Nov 2014 09:38:19 +0000 (15:08 +0530)]
enic: fix build by using standard integer types
ENIC PMD was giving compilation errors on ppc_64-power8-linuxapp-gcc because
of types such as u_int32_t. This patch replaces all those with uint32_t and
similar ones.
Reported-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Pablo de Lara [Fri, 28 Nov 2014 15:10:16 +0000 (15:10 +0000)]
bond: fix build with gcc 4.3
GCC 4.3 complains that slow_pkts array in bond_ethdev_tx_burst_8023ad
may be used uninitialized, so it has been initialized to NULL.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Balazs Nemeth [Fri, 28 Nov 2014 09:21:45 +0000 (09:21 +0000)]
ixgbe: fix mbuf failure statistics in vector Rx
The statistics that is reported through the rx_nombuf fields in struct
rte_eth_stats was not set when the vector PMD was used. The statistics
should report the number of mbufs that could _not_ be allocated during
rearm of the RX queue. The non-vector PMD reports it correctly. The
use of either vector PMD or non-vector PMD depends on runtime
configuration. Hence it is possible that a change in configuration
would disable this statistics. To prevent this from happening, the
statistics should be reported by both implementations.
Signed-off-by: Balazs Nemeth <balazs.nemeth@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Thomas Monjalon [Thu, 27 Nov 2014 21:18:32 +0000 (22:18 +0100)]
version: 1.8.0-rc2
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Jia Yu [Thu, 27 Nov 2014 21:23:37 +0000 (21:23 +0000)]
bond: set offload capabilities flags
Before the fix, bond device's offload capabilities are unset. This fix
takes the minimum common set of slave devices' capabilities as bond
device's capabilities. For simplicity, we ensure all slave devices
to have a capability before bond device can claim this capability,
even if some slave devices are unused (i.e. linked down, standby).
Signed-off-by: Jia Yu <jyu@vmware.com>
Signed-off-by: Declan Doherty <declan.doherty@intel.com>
Daniel Mrzyglod [Thu, 27 Nov 2014 16:33:41 +0000 (16:33 +0000)]
bond: unit tests for mode 5
This Patch add unit tests for mode 5 - tlb - to the oders
link bonding unit tests.
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Daniel Mrzyglod [Thu, 27 Nov 2014 16:33:40 +0000 (16:33 +0000)]
bond: add mode 5
Add support for mode 5 (Transmit load balancing) into pmd driver
This patch add support for Adaptive transmit load balancing (mode 5) to the
librte_pmd_bond library. This mode provides an adaptive transmit load
balancing. It dynamically changes the transmitting slave, according to the
computed load.
Further details are described here:
https://www.kernel.org/doc/Documentation/networking/bonding.txt
In implementation callback is used for sorting slave order - providing
statistics for burst function about slave bandwith usage and sort
interfaces due to usage.
Difference in this implementation vs Linux implementation:
- We Are trying send all pkts – If one interface hasn’t send packets we are
trying to send rest of packets by other slaves sorted previously by callback
function.
Some implementation details:
- Every 100ms is taken obytes statistics from every slave.
- Every 10 ms the slaves in table are sorted and updated by callback -
bandwidth and successfully transmitted bytes from previous iteration which
happens every 100 ms
- There is callback function which updates this statistics for transparency and
for rather intensive computation involved in this mode.
Test report: http://dpdk.org/ml/archives/dev/2014-November/008729.html
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com>
Tested-by: SunX Jiajia <sunx.jiajia@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Pawel Wodkowski [Thu, 27 Nov 2014 18:01:10 +0000 (18:01 +0000)]
bond: add mode 4
This patch set add support for dynamic link aggregation (mode 4) to the
librte_pmd_bond library. This mode provides auto negotiation/configuration
of peers and well as link status changes monitoring using out of band
LACP (link aggregation control protocol) messages. For further details of
LACP specification see the IEEE 802.3ad/802.1AX standards. It is also
described here
https://www.kernel.org/doc/Documentation/networking/bonding.txt.
In this implementation we have an array of mode 4 settings for each slave.
There is also assumption that for every port is one aggregator (it might
be unused if better is found).
Difference in this implementation vs Linux implementation:
- this implementation it is not directly based on state machines but current
state is calculated from actor and partner states (and other things too).
Some implementation details:
- during rx burst every packet Is checked if this is LACP or marker packet.
If it is LACP frame it is passed to mode 4 logic using slaves rx ring and
removed from rx buffer before it is returned
- in tx burst, packets from mode 4 (if any) are injected into each slave.
- there is a timer running in background to process/produce mode 4
frames form rx/to tx functions.
Some requirements for this mode:
- for LACP mode to work rx and tx burst functions must be invoked
at least in 100ms intervals
- provided buffer to rx burst should be at least 2x slave count size. This is
not needed but might increase performance especially during initial
handshake.
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Sujith Sankar [Thu, 27 Nov 2014 17:14:40 +0000 (22:44 +0530)]
enic: fix vfio inclusion
Inclusion of vfio.h was giving compilation errors if kernel version is less
than 3.6.0 and if RTE_EAL_VFIO was in config.
Removed inclusion of vfio.h and replaced RTE_EAL_VFIO with VFIO_PRESENT.
Reported-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Thomas Monjalon [Thu, 27 Nov 2014 17:53:49 +0000 (18:53 +0100)]
enic: fix dependencies
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
David Marchand [Thu, 27 Nov 2014 11:42:38 +0000 (12:42 +0100)]
config: disable enic driver on Power
enic driver is giving trouble because of non-standard types :
CC enic_res.o
In file included from
lib/librte_pmd_enic/enic_res.c:36:0:
lib/librte_pmd_enic/enic_compat.h:92:1: error: unknown type name ‘u_int32_t’
static inline u_int32_t ioread32(volatile void *addr)
^
Disable it on Power for now.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
David Marchand [Thu, 27 Nov 2014 11:29:05 +0000 (12:29 +0100)]
scripts: fix symbol overriding in configuration
When redefining the same symbol in configuration (basically after an inclusion),
we need to undefine the previous symbol to avoid "redefined" errors.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Thomas Monjalon [Thu, 27 Nov 2014 11:28:17 +0000 (12:28 +0100)]
net: fix conflict with libc
It was impossible to include netinet/in.h and rte_ip.h
because the IP protocols were redefined.
It is removed because useless.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Ivan Boule <ivan.boule@6wind.com>
Jia Yu [Fri, 7 Nov 2014 15:43:01 +0000 (07:43 -0800)]
app/testpmd: fix RSS flags size
Since commit
8a387fa85f02 ("ethdev: more RSS flags") in DPDK 1.7,
RSS flags have increased.
According to rss_hf definition in rte_eth_rss_conf, it shall be uint64 type.
Using uint16 will get truncated value, and cause incorrect output. This
fix corrected this issue.
Signed-off-by: Jia Yu <jyu@vmware.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Keith Wiles [Sun, 28 Sep 2014 05:28:44 +0000 (05:28 +0000)]
mempool: avoid dump crash with null pointer
Check the FILE *f and rte_mempool *mp pointers for NULL.
Signed-off-by: Keith Wiles <keith.wiles@windriver.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Sergio Gonzalez Monroy [Wed, 19 Nov 2014 12:26:06 +0000 (12:26 +0000)]
add prefix to cache line macros
CACHE_LINE_SIZE is a macro defined in machine/param.h in FreeBSD and
conflicts with DPDK macro version.
Adding RTE_ prefix to avoid conflicts.
CACHE_LINE_MASK and CACHE_LINE_ROUNDUP are also prefixed.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
[Thomas: updated on HEAD, including PPC]
Sergio Gonzalez Monroy [Thu, 20 Nov 2014 14:06:59 +0000 (14:06 +0000)]
eal/bsd: remove unused HPET support
The HPET support in the BSD EAL was copied directly from the Linux version,
but did not actually work on FreeBSD. We replace this old code with a simple
compiler message that informs the user that we don't support HPET on BSD if
they enable such support in the build-time configuration file.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Sergio Gonzalez Monroy [Thu, 20 Nov 2014 14:06:58 +0000 (14:06 +0000)]
eal/bsd: use sysctl to get TSC frequency
BSD provides the TSC frequency value through sysctl.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Thomas Monjalon [Thu, 27 Nov 2014 10:02:11 +0000 (11:02 +0100)]
doc: no more bare metal environment
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
David Marchand [Fri, 26 Sep 2014 14:04:02 +0000 (16:04 +0200)]
examples: no more bare metal environment
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
David Marchand [Fri, 26 Sep 2014 14:04:01 +0000 (16:04 +0200)]
app: no more bare metal environment
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
David Marchand [Fri, 26 Sep 2014 14:04:00 +0000 (16:04 +0200)]
eal: no more bare metal environment
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
David Marchand [Fri, 26 Sep 2014 14:03:59 +0000 (16:03 +0200)]
mk: no more bare metal environment
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
David Marchand [Fri, 26 Sep 2014 14:03:58 +0000 (16:03 +0200)]
config: no more bare metal environment
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Thomas Monjalon [Thu, 27 Nov 2014 09:35:56 +0000 (10:35 +0100)]
mbuf: sort TCP segmentation offload flag
Due to reordering conflicts, the TSO flag was not sorted.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
David Marchand [Mon, 24 Nov 2014 15:18:51 +0000 (16:18 +0100)]
eal/linux: fix remaining checks for 64-bit architectures
RTE_ARCH_X86_64 can not be used as a way to determine if we are building for
64bits cpus. Instead, RTE_ARCH_64 should be used.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
jingjing.wu [Thu, 13 Nov 2014 12:49:55 +0000 (20:49 +0800)]
i40e: add ethertype filter
Handle the RTE_ETH_FILTER_ADD and RTE_ETH_FILTER_DELETE operations
on ethertype filter.
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
jingjing.wu [Thu, 13 Nov 2014 12:49:54 +0000 (20:49 +0800)]
ethdev: add ethertype filter
A new structure of ethertype filter is defined in rte_eth_ctrl.h
for filter_ctrl api
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Sujith Sankar [Tue, 25 Nov 2014 17:26:41 +0000 (22:56 +0530)]
enic: build integration
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
[Thomas: enable for BSD - not tested]
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Sujith Sankar [Tue, 25 Nov 2014 17:26:43 +0000 (22:56 +0530)]
enic: new driver
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Sujith Sankar [Tue, 25 Nov 2014 17:26:42 +0000 (22:56 +0530)]
enic/base: common code
VNIC common code is partially shared with ENIC kernel mode driver.
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Sujith Sankar [Tue, 25 Nov 2014 17:26:40 +0000 (22:56 +0530)]
enic: license
Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:17 +0000 (17:17 -0500)]
app/testpmd: fix build for IBM Power
This patch fixes compiling problems on IBM Power architecture and turn
on the test-pmd compiling option in configuration file. Actually, this
is an big endian compiling fix.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:16 +0000 (17:17 -0500)]
app/test: fix finding the second smallest memory segment
Curent implementation in test_memzone.c has bugs in finding the
second smallest memory segment. It's the last smallest memory segment,
but it's not the second smallest memory segment. This bug may cause test
failure in some cases. This patch fixes this bug.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:15 +0000 (17:17 -0500)]
mem: support layout of IBM Power
The mmap of hugepage files on IBM Power starts from high address to low
address. This is different from x86. This patch modified the memory
segment detection code to get the correct memory segment layout on Power
architecture. This patch also added a commond ARCH_PPC_64 definition for
64 bit systems.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:14 +0000 (17:17 -0500)]
mem: add huge page sizes for IBM Power
IBM Power architecture has different huge page sizes (16MB, 16GB) than
x86.This patch defines RTE_PGSIZE_16M and RTE_PGSIZE_16G in the
rte_page_sizes enum variable and adds huge page size support of DPDK
for IBM Power architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:13 +0000 (17:17 -0500)]
mk: define cache size for IBM Power
IBM Power architecture has different cache line size (128 bytes) than
x86 (64 bytes). This patch defines CACHE_LINE_SIZE to 128 bytes to
override the default value 64 bytes to support IBM Power Architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:12 +0000 (17:17 -0500)]
eal/linux: disable iopl operation for IBM Power
iopl() call is mostly for the i386 architecture. In Power and other
architecture, it doesn't exist. This patch modified rte_eal_iopl_init()
and make it return -1 for Power and other architecture. Thus
rte_config.flags will not contain EAL_FLG_HIGH_IOPL flag for other
architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:11 +0000 (17:17 -0500)]
eal/ppc: cpu flag checks for IBM Power
IBM Power processor doesn't have CPU flag hardware registers. This patch
uses aux vector software register to get CPU flags and add CPU flag
checking support for IBM Power architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:10 +0000 (17:17 -0500)]
eal/ppc: vector memcpy for IBM Power
The SSE based memory copy in DPDK only support x86. This patch adds
altivec based memory copy functions for IBM Power architecture. This
patch includes altivec.h which requires GCC version>= 4.8.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:09 +0000 (17:17 -0500)]
eal/ppc: spinlock operations for IBM Power
This patch adds spinlock operations for IBM Power architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:08 +0000 (17:17 -0500)]
eal/ppc: prefetch operations for IBM Power
This patch add architecture specific prefetch operations for IBM Power
architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:07 +0000 (17:17 -0500)]
eal/ppc: cpu cycle operations for IBM Power
IBM Power architecture doesn't have TSC register to get CPU cycles. This
patch implements the time base register read instead of TSC register of
x86 on IBM Power architecture.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:06 +0000 (17:17 -0500)]
eal/ppc: byte order operations for IBM Power
This patch adds architecture specific byte order operations for IBM Power
architecture. Power architecture support both big endian and little
endian. This patch also adds a RTE_ARCH_BIG_ENDIAN micro.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:05 +0000 (17:17 -0500)]
eal/ppc: atomic operations for IBM Power
This patch adds architecture specific atomic operation file for IBM
Power architecture CPU.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Chao Zhu [Tue, 25 Nov 2014 22:17:04 +0000 (17:17 -0500)]
mk: introduce IBM Power architecture
To make DPDK run on IBM Power architecture, configuration files for
Power architecuture are added. Also, the compiling related .mk files are
added.
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:55 +0000 (16:04 +0100)]
app/testpmd: add a verbose mode to checksum forward engine
If the user specifies 'set verbose 1' in testpmd command line,
the csum forward engine will dump some informations about received
and transmitted packets, especially which flags are set and what
values are assigned to l2_len, l3_len, l4_len and tso_segsz.
This can help someone implementing TSO or hardware checksum offload to
understand how to configure the mbufs.
Example of output for one packet:
--------------
rx: l2_len=14 ethertype=800 l3_len=20 l4_proto=6 l4_len=20
tx: m->l2_len=14 m->l3_len=20 m->l4_len=20
tx: m->tso_segsz=800
tx: flags=PKT_TX_IP_CKSUM PKT_TX_TCP_SEG
--------------
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:54 +0000 (16:04 +0100)]
app/testpmd: support TSO in checksum forward engine
Add two new commands in testpmd:
- tso set <segsize> <portid>
- tso show <portid>
These commands can be used enable TSO when transmitting TCP packets in
the csum forward engine. Ex:
set fwd csum
tx_checksum set ip hw 0
tso set 800 0
start
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:53 +0000 (16:04 +0100)]
ixgbe: support TCP segmentation offload
Implement TSO (TCP segmentation offload) in ixgbe driver. The driver is
now able to use PKT_TX_TCP_SEG mbuf flag and mbuf hardware offload infos
(l2_len, l3_len, l4_len, tso_segsz) to configure the hardware support of
TCP segmentation.
In ixgbe, when doing TSO, the IP length must not be included in the TCP
pseudo header checksum. A new function ixgbe_fix_tcp_phdr_cksum() is
used to fix the pseudo header checksum of the packet before giving it to
the hardware.
In the patch, the tx_desc_cksum_flags_to_olinfo() and
tx_desc_ol_flags_to_cmdtype() functions have been reworked to make them
clearer. This should not impact performance as gcc (version 4.8 in my
case) is smart enough to convert the tests into a code that does not
contain any branch instruction.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:52 +0000 (16:04 +0100)]
mbuf: generic support for TCP segmentation offload
Some of the NICs supported by DPDK have a possibility to accelerate TCP
traffic by using segmentation offload. The application prepares a packet
with valid TCP header with size up to 64K and deleguates the
segmentation to the NIC.
Implement the generic part of TCP segmentation offload in rte_mbuf. It
introduces 2 new fields in rte_mbuf: l4_len (length of L4 header in bytes)
and tso_segsz (MSS of packets).
To delegate the TCP segmentation to the hardware, the user has to:
- set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies
PKT_TX_TCP_CKSUM)
- set the flag PKT_TX_IPV4 or PKT_TX_IPV6
- set PKT_TX_IP_CKSUM if it's IPv4, and set the IP checksum to 0 in
the packet
- fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz
- calculate the pseudo header checksum without taking ip_len in account,
and set it in the TCP header, for instance by using
rte_ipv4_phdr_cksum(ip_hdr, ol_flags)
The API is inspired from ixgbe hardware (the next commit adds the
support for ixgbe), but it seems generic enough to be used for other
hw/drivers in the future.
This commit also reworks the way l2_len and l3_len are used in igb
and ixgbe drivers as the l2_l3_len is not available anymore in mbuf.
Signed-off-by: Mirek Walukiewicz <miroslaw.walukiewicz@intel.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:51 +0000 (16:04 +0100)]
net: new checksum functions
Introduce new functions to calculate checksums. These new functions
are derivated from the ones provided csumonly.c but slightly reworked.
There is still some room for future optimization of these functions
(maybe SSE/AVX, ...).
This API will be modified in tbe next commits by the introduction of
TSO that requires a different pseudo header checksum to be set in the
packet.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Olivier Matz [Wed, 26 Nov 2014 15:04:50 +0000 (16:04 +0100)]
app/testpmd: rework checksum forward engine
The csum forward engine was becoming too complex to be used and
extended (the next commits want to add the support of TSO):
- no explaination about what the code does
- code is not factorized, lots of code duplicated, especially between
ipv4/ipv6
- user command line api: use of bitmasks that need to be calculated by
the user
- the user flags don't have the same semantic:
- for legacy IP/UDP/TCP/SCTP, it selects software or hardware checksum
- for other (vxlan), it selects between hardware checksum or no
checksum
- the code relies too much on flags set by the driver without software
alternative (ex: PKT_RX_TUNNEL_IPV4_HDR). It is nice to be able to
compare a software implementation with the hardware offload.
This commit tries to fix these issues, and provide a simple definition
of what is done by the forward engine:
* Receive a burst of packets, and for supported packet types:
* - modify the IPs
* - reprocess the checksum in SW or HW, depending on testpmd command line
* configuration
* Then packets are transmitted on the output port.
*
* Supported packets are:
* Ether / (vlan) / IP|IP6 / UDP|TCP|SCTP .
* Ether / (vlan) / IP|IP6 / UDP / VxLAN / Ether / IP|IP6 / UDP|TCP|SCTP
*
* The network parser supposes that the packet is contiguous, which may
* not be the case in real life.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>