[dpdk-dev] [PATCH v2 15/21] net/qede/base: fix remove the unneeded conversion to LE

2017-03-17 Thread Rasesh Mody
Remove the unneeded conversion to LE when writing to the 32-bit XSDM_REG_OPERATION_GEN register Fixes: ec94dbc57362 ("qede: add base driver") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_dev.c |5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/

[dpdk-dev] [PATCH v2 14/21] net/qede/base: fix to remove redundant memset

2017-03-17 Thread Rasesh Mody
Fixes: 22d07d939c3c ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_vf.c |2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/qede/base/ecore_vf.c b/drivers/net/qede/base/ecore_vf.c index 97a0cbe..9e1be1a 100644 --- a/drivers/net/qede/base/ecor

[dpdk-dev] [PATCH v2 11/21] net/qede/base: fix printout

2017-03-17 Thread Rasesh Mody
Fixes: ec94dbc57362 ("qede: add base driver") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_mcp.c |4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/qede/base/ecore_mcp.c b/drivers/net/qede/base/ecore_mcp.c index 4863ff9..e0d247b 100644 --- a/driv

[dpdk-dev] [PATCH v2 13/21] net/qede/base: fix out-of-bound memory access

2017-03-17 Thread Rasesh Mody
Fix out-of-bound memory access on Management FW interaction for resource allocation Fixes: 252b88b58f70 ("net/qede/base: add selftest and query sensor info") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_mcp.c | 10 ++ 1 file changed, 6 insertions(+), 4 deletions(-) diff

[dpdk-dev] [PATCH v2 19/21] net/qede/base: fix sriov typo

2017-03-17 Thread Rasesh Mody
Typo in ecore_sriov.c; Ending line with , instead of ; Fixes: 379cbb2c446a ("net/qede/base: semantic change") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_sriov.c |4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/qede/base/ecore_sriov.c b/driv

[dpdk-dev] [PATCH v2 18/21] net/qede/base: refactor return path

2017-03-17 Thread Rasesh Mody
No need to return - base on return at end of function. Fixes: 22d07d939c3c ("net/qede/base: update") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_vf.c |1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/qede/base/ecore_vf.c b/drivers/net/qede/base/ecore_vf.c index 9e

[dpdk-dev] [PATCH v2 16/21] net/qede/base: fix first VF index calculation

2017-03-17 Thread Rasesh Mody
When a server doesn't support ARI, VF offsets begin at a much higher number. As a result, ecore miscalculates the first_vf_in_pf and initialization fails since base driver incorrectly learns there are no SBs for its VF [as its VFs are out of range]. Fixes: 22d07d939c3c ("net/qede/base: update") S

[dpdk-dev] [PATCH v2 12/21] net/qede/base: fix DORQ attention mask

2017-03-17 Thread Rasesh Mody
Fix Doorbell Queue(DORQ) attention mask Fixes: e6051bd6b07d ("qede: add interrupt handling support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_int.c |2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/qede/base/ecore_int.c b/drivers/net/qede/base

[dpdk-dev] [PATCH v2 10/21] net/qede/base: add attention bits for AH chip

2017-03-17 Thread Rasesh Mody
add attention bits for CHIP_NUM_AH_xxx Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_int.c | 77 +++-- 1 file changed, 65 insertions(+), 12 deletions(-) diff --git a/drivers/net/qede/base/ecore_int.c b/drivers/net/qede/base/ecore_int.c index 3d6c2

[dpdk-dev] [PATCH v2 09/21] net/qede/base: fix to prevent VF promisc config

2017-03-17 Thread Rasesh Mody
VFs are seeing the number of MACs available to them as '0', and as a result configure themselves as PROMISC. This fix is to prevent that. Fixes: 86a2265e59d7 ("qede: add SRIOV support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_vf.c | 16 +++- drivers/net/qede

[dpdk-dev] [PATCH v2 06/21] net/qede/base: fix VF init after malicious VF FLR

2017-03-17 Thread Rasesh Mody
Fix VF init after malicious VF FLR. Fixes: 40c926ba2626 ("net/qede/base: support to initiate PF FLR") Fixes: 86a2265e59d7 ("qede: add SRIOV support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_sriov.c |7 +++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/qede

[dpdk-dev] [PATCH v2 07/21] net/qede/base: fix numbering L2 VF queues

2017-03-17 Thread Rasesh Mody
There are some constellations where Due to lack of resource allocation in MFW, There would be an insufficient number of L2 queues for all the VFs. This introduces a new feature ECORE_VF_L2_QUE which correctly numbers the number of VF queues. Notice it might be larger than the actual number of VFs

[dpdk-dev] [PATCH v2 03/21] net/qede/base: fix forcing driver default resc allocation

2017-03-17 Thread Rasesh Mody
Remove the forcing of the driver's default resource allocation. Fixes: 77f7222124de ("net/qede: add PCI ids for new chip variant") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_dev.c | 18 ++ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/n

[dpdk-dev] [PATCH v2 02/21] net/qede/base: fix to set pointers to NULL after freeing

2017-03-17 Thread Rasesh Mody
Set pointers to NULL after freeing the allocations. Change OSAL_FREE macro to take care of this and cleanup relevant code. Fixes: 26ae839d06e9 ("qede: add DCBX support") Fixes: ec94dbc57362 ("qede: add base driver") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/bcm_osal.h|6 +

[dpdk-dev] [PATCH v2 08/21] net/qede/base: fix index printing of multi-bit attentions

2017-03-17 Thread Rasesh Mody
Fix the logic for identifying which bit amongst the Multi-bit attention sources is set. Fixes: e6051bd6b07d ("qede: add interrupt handling support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_int.c | 18 +++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff

[dpdk-dev] [PATCH v2 04/21] net/qede/base: fix TM block ILT initialization

2017-03-17 Thread Rasesh Mody
Fix Timer(TM) block Internal Lookup Table(or ILT for logical to physical address translation) initialization for SRIOV's coexistence with other protocols. Fixes: ec94dbc57362 ("qede: add base driver") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_cxt.c | 17 + 1 f

[dpdk-dev] [PATCH v2 05/21] net/qede/base: fix printout

2017-03-17 Thread Rasesh Mody
Prints in ecore_get_dev_info showed only chip revision, and did that as number instead of letter. I.e., BB A0 --> BB0, BB B0 --> BB1, AH A0 --> AH0, AH A1 --> AH0. Correct the printing scheme into {AH, BB} {A, B}{0, 1} Fixes: ec94dbc57362 ("qede: add base driver") Signed-off-by: Rasesh Mody --

[dpdk-dev] [PATCH v2 01/21] net/qede/base: fix incorrect typecasting of flag

2017-03-17 Thread Rasesh Mody
dcbx-update-flag is incorrectly converted to boolean before assigining it to ramrod data, fix this typecasting. Also, added more debug messages in the dcbx code paths. Fixes: 26ae839d06e9 ("qede: add DCBX support") Signed-off-by: Rasesh Mody --- drivers/net/qede/base/ecore_dcbx.c | 42 +++

Re: [dpdk-dev] [PATCH] net/i40e: enable statistic reset for VF

2017-03-17 Thread Thomas Monjalon
2017-03-17 21:14, Vincent Jardin: > Please, can you bring it to the next tech board? This dispersion of VF/PF > make the DPDK unusable into open products with many parties since behavior > becomes VF/PF specific. Already requested earlier in this thread: http://dpdk.org/ml/archives/dev/2

Re: [dpdk-dev] [PATCH] net/i40e: enable statistic reset for VF

2017-03-17 Thread Vincent Jardin
Le 17 mars 2017 11:15:22 AM Thomas Monjalon a écrit : 2017-03-17 09:45, Zhang, Helin: From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] >2017-03-17 03:28, Zhang, Helin: >> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] >> > 2017-02-23 13:27, Qi Zhang: >> > > static void >

Re: [dpdk-dev] [PATCH] mk: optimize directory dependencies

2017-03-17 Thread Robin Jarry
Hi Olivier, Thanks again for this. I only have minor cosmetic remarks: Le 17 mars 2017 18:13, "Olivier Matz" a écrit: > diff --git a/app/pdump/Makefile b/app/pdump/Makefile > index 536198f..8ec6bd6 100644 > --- a/app/pdump/Makefile > +++ b/app/pdump/Makefile > @@ -42,7 +42,6 @@ CFLAGS += $(WERRO

Re: [dpdk-dev] [PATCH v1] NXP DPAA2 External Mempool Driver

2017-03-17 Thread Olivier Matz
On Fri, 17 Mar 2017 17:12:59 +, Hemant Agrawal wrote: > > -Original Message- > > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > > Sent: Friday, March 17, 2017 7:13 PM > > To: Hemant Agrawal > > Cc: dev@dpdk.org; olivier.m...@6wind.com; Shreyansh Jain > > ; ferruh.yi...@in

Re: [dpdk-dev] [PATCH 3/3] net/mlx5: rebuild flows on updating RETA

2017-03-17 Thread Yongseok Koh
Hi Nelio, On Fri, Mar 17, 2017 at 02:11:43AM -0700, Nélio Laranjeiro wrote: > On Thu, Mar 16, 2017 at 03:40:56PM -0700, Yongseok Koh wrote: > > Currently mlx5_dev_rss_reta_update() just updates tables in the host, > > therefore it isn't immediately effective until restarting the device by > > call

Re: [dpdk-dev] [PATCH 1/3] lib/librte_ether: remove requirement of aligned RETA size

2017-03-17 Thread Yongseok Koh
On Thu, Mar 16, 2017 at 03:40:54PM -0700, Yongseok Koh wrote: > In rte_eth_check_reta_mask(), it is required to align the size of the RETA > table to RTE_RETA_GROUP_SIZE but as the size can be less than the limit, > this should be removed. The change is also applied to a command of testpmd. > > Si

[dpdk-dev] [PATCH] mk: optimize directory dependencies

2017-03-17 Thread Olivier Matz
Before this patch, the management of dependencies between directories had several issues: - the generation of .depdirs, done at configuration is slow: it can take more than one minute on some slow targets (usually ~10s on a standard PC without -j). - for instance, it is possible to express a

Re: [dpdk-dev] [PATCH v1] NXP DPAA2 External Mempool Driver

2017-03-17 Thread Hemant Agrawal
> -Original Message- > From: Thomas Monjalon [mailto:thomas.monja...@6wind.com] > Sent: Friday, March 17, 2017 7:13 PM > To: Hemant Agrawal > Cc: dev@dpdk.org; olivier.m...@6wind.com; Shreyansh Jain > ; ferruh.yi...@intel.com > Subject: Re: [PATCH v1] NXP DPAA2 External Mempool Driver >

[dpdk-dev] [PATCH] mk: fix message when test application is not built

2017-03-17 Thread Olivier Matz
To build the tests, we should use "make test-build". Fixes: 64592d97c1ae ("mk: do not build tests by default") Signed-off-by: Olivier Matz --- mk/rte.sdktest.mk | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mk/rte.sdktest.mk b/mk/rte.sdktest.mk index 9cc7d59..daeea90 1

[dpdk-dev] [PATCH] mk: remove invalid phony target

2017-03-17 Thread Olivier Matz
There was a typo in the .PHONY for the test-build target. If we fix the typo, the test-build target does not work, because it won't match the '%' target anymore. So just remove the .PHONY. Fixes: 64592d97c1ae ("mk: do not build tests by default") Signed-off-by: Olivier Matz --- mk/rte.sdkroot.

Re: [dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Olivier Matz
Hi Stephen, On Fri, 17 Mar 2017 09:15:28 -0700, Stephen Hemminger wrote: > On Fri, 17 Mar 2017 16:51:15 +0100 > Olivier Matz wrote: > > > +static int > > +rte_log_lookup(const char *name) > > +{ > > + size_t i; > > + > > + for (i = 0; i < rte_logs.dynamic_types_len; i++) { > > +

Re: [dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Stephen Hemminger
On Fri, 17 Mar 2017 16:51:15 +0100 Olivier Matz wrote: > +static int > +__rte_log_register(const char *name, int id) > +{ > + char *dup_name = NULL; > + > + dup_name = strdup(name); Useless initialization! Many people were taught to always initialize variables. But that was before compi

Re: [dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Stephen Hemminger
On Fri, 17 Mar 2017 16:51:15 +0100 Olivier Matz wrote: > +static int > +rte_log_lookup(const char *name) > +{ > + size_t i; > + > + for (i = 0; i < rte_logs.dynamic_types_len; i++) { > + if (rte_logs.dynamic_types[i].name == NULL) > + continue; > +

Re: [dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Stephen Hemminger
On Fri, 17 Mar 2017 16:51:15 +0100 Olivier Matz wrote: > if (type < RTE_LOGTYPE_FIRST_EXT_ID) { > + if (enable) > + rte_logs.type |= type; > + else > + rte_logs.type &= (~type) No need for () around ~type

Re: [dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Stephen Hemminger
On Fri, 17 Mar 2017 16:51:15 +0100 Olivier Matz wrote: > + .dynamic_types_len = 0, > + .dynamic_types = NULL, > }; > You don't need to add elements to initializer if the are 0.

[dpdk-dev] [PATCH 8/8] net/i40e: use dynamic log type for control logs

2017-03-17 Thread Olivier Matz
This is an example of how a dynamic log type can be used in a PMD. Signed-off-by: Olivier Matz --- config/common_base | 2 -- drivers/net/i40e/i40e_ethdev.c | 18 -- drivers/net/i40e/i40e_fdir.c | 4 drivers/net/i40e/i40e_logs.h | 17 ++--- 4 fi

[dpdk-dev] [PATCH 7/8] app/testpmd: new command to dump log types

2017-03-17 Thread Olivier Matz
Signed-off-by: Olivier Matz --- app/test-pmd/cmdline.c | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c index 47f935d..697228f 100644 --- a/app/test-pmd/cmdline.c +++ b/app/test-pmd/cmdline.c @@ -7679,6 +7679,8 @@ static void

[dpdk-dev] [PATCH 5/8] eal: deprecate log functions

2017-03-17 Thread Olivier Matz
Deprecate the following functions: - rte_set_log_level(), replaced by rte_log_set_global_level() - rte_get_log_level(), replaced by rte_log_get_global_level() - rte_set_log_type(), rte_log_set_level() - rte_get_log_type(), rte_log_get_level() The new functions provide a better control of the per-t

[dpdk-dev] [PATCH 6/8] app/test: new command to dump log types

2017-03-17 Thread Olivier Matz
Signed-off-by: Olivier Matz --- test/test/commands.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/test/test/commands.c b/test/test/commands.c index 2df46b0..488dc41 100644 --- a/test/test/commands.c +++ b/test/test/commands.c @@ -158,13 +158,15 @@ static void cmd_dump_pa

[dpdk-dev] [PATCH 4/8] eal: change specific log levels at startup

2017-03-17 Thread Olivier Matz
Example of use: ./app/test-pmd --log-level='pmd\.i40e.*,8' This enables debug logs for all dynamic logs whose type starts with 'pmd.i40e'. Signed-off-by: Olivier Matz --- lib/librte_eal/bsdapp/eal/eal.c| 4 +-- lib/librte_eal/common/eal_common_options.c | 49 +

[dpdk-dev] [PATCH 3/8] eal: change several log levels matching a regexp

2017-03-17 Thread Olivier Matz
Introduce a function to set the log level of several log types that match a regular expression. Signed-off-by: Olivier Matz --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 + lib/librte_eal/common/eal_common_log.c | 21 + lib/librte_eal/common/include/rte_lo

[dpdk-dev] [PATCH 2/8] eal: dump registered log types

2017-03-17 Thread Olivier Matz
Introduce a function to dump the global level and the registered log types. Signed-off-by: Olivier Matz --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 + lib/librte_eal/common/eal_common_log.c | 34 + lib/librte_eal/common/include/rte_log.h | 10

[dpdk-dev] [PATCH 1/8] eal: support dynamic log types

2017-03-17 Thread Olivier Matz
Introduce 2 new functions to support dynamic log types: - rte_log_register(): register a log name, and return a log type id - rte_log_set_level(): set the log level of a given log type Signed-off-by: Olivier Matz --- doc/guides/contributing/coding_style.rst| 30 +++-- lib/librte_eal/bs

[dpdk-dev] [PATCH 0/8] eal: dynamic logs

2017-03-17 Thread Olivier Matz
The objective of this patchset is to introduce a framework to support dynamic log types in EAL. It also provides one example of use (in i40e). Features: - log types are identified by a string - at registration, a uniq identifier is associated to a log type - each log type can have its level change

Re: [dpdk-dev] [RFC 0/8] eal: dynamic logs

2017-03-17 Thread Olivier Matz
Hi Thomas, On Wed, 15 Mar 2017 17:35:32 +0100, Thomas Monjalon wrote: > 2017-02-06 14:29, Olivier Matz: > > The objective of this RFC patchset is to introduce a framework to > > support dynamic log types in EAL. It also provides one example of use > > (in i40e). > > > > Features: > > - log type

[dpdk-dev] [PATCH v4] eventdev: add errno-style return values

2017-03-17 Thread Gage Eads
From: "Eads, Gage" This commit adds rte_errno return values to rte_event_enqueue_burst() and rte_event_dequeue_burst(). These return values allows user software to differentiate between an invalid argument (such as an invalid queue_id or sched_type in an enqueued event) and backpressure from the

[dpdk-dev] KNI offloads

2017-03-17 Thread Alejandro Lucero
Is there any reason for this driver not supporting LSO or CSUM offloads? I know this is a virtual netdev but I think it should support those options and enabled them depending on the PMD to send or receive packets from. About giving to the KNI that info, maybe using the kernel firmware interface

Re: [dpdk-dev] [PATCH v3] eventdev: add errno-style return values

2017-03-17 Thread Eads, Gage
Ah, sorry about that! I revised the v1 patch, not the v2 patch. I'll fix and resubmit. > -Original Message- > From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com] > Sent: Thursday, March 16, 2017 10:11 PM > To: Eads, Gage > Cc: dev@dpdk.org; Richardson, Bruce ; > hemant.agra..

Re: [dpdk-dev] [PATCH v4 00/17] Wind River Systems AVP PMD vs virtio? - ivshmem is back

2017-03-17 Thread Michael S. Tsirkin
On Fri, Mar 17, 2017 at 09:48:38AM +0100, Thomas Monjalon wrote: > I think there is one interesting technological point in this thread. > We are discussing about IVSHMEM but its support by Qemu is confused. > This feature is not in the MAINTAINERS file of Qemu. > Please Qemu maintainers, what is th

Re: [dpdk-dev] [PATCH v1] NXP DPAA2 External Mempool Driver

2017-03-17 Thread Thomas Monjalon
2017-03-17 18:17, Hemant Agrawal: > (This patches has been split from DPAA2 PMD v8 series [1] as per > comments received on ML [2].) > > This patch implements the HW mempool offload driver for packets buffers > using the FSLMC provided DPBP object. > > The new pool is being configured using compi

[dpdk-dev] [PATCH v9 22/22] net/dpaa2: enable frame queue based dequeuing

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 6d291be..dc83815 100644 --- a/drivers/net/dpaa2/dpaa2_ethdev.c +++ b/drivers/net

[dpdk-dev] [PATCH v9 20/22] config: add configuration for toggling physical addressing

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- config/common_base| 1 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 1 + 2 files changed, 2 insertions(+) diff --git a/config/common_base b/config/common_base index 1c54777..4c3674e 100644 --- a/config/common_base +++ b/config/common_bas

[dpdk-dev] [PATCH v9 21/22] net/dpaa2: enable DMA Mapping during device scanning

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 16baaf0..6d291be 100644 --- a/drivers/net/dpaa2/dpaa2_ethdev.c +++ b/drivers/net/dpaa2/dpaa2_ethdev.c

[dpdk-dev] [PATCH v9 19/22] net/dpaa2: enable physical addressing for packet buffers

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 4 ++-- drivers/net/dpaa2/dpaa2_rxtx.c | 16 +--- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c index

[dpdk-dev] [PATCH v9 18/22] net/dpaa2: handle non-hardware backed buffer pool

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_rxtx.c | 75 -- 1 file changed, 73 insertions(+), 2 deletions(-) diff --git a/drivers/net/dpaa2/dpaa2_rxtx.c b/drivers/net/dpaa2/dpaa2_rxtx.c index c1ea33a..a94761c 100644 --- a/drivers/net/dpaa2/dp

[dpdk-dev] [PATCH v9 17/22] net/dpaa2: enable stashing for LS2088A devices

2017-03-17 Thread Hemant Agrawal
As the hardware determines which core will process which packet, performance is boosted by direct cache warming/stashing as well as by providing biasing for core-to-flow affinity, which ensures that flow-specific data structures can remain in the core’s cache. This patch enables the one cache line

[dpdk-dev] [PATCH v9 16/22] net/dpaa2: basic stats support

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 86 ++ 2 files changed, 87 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index 0660cab..d43f

[dpdk-dev] [PATCH v9 15/22] net/dpaa2: link status update

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 107 + 2 files changed, 108 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index 0746d4b..06

[dpdk-dev] [PATCH v9 14/22] net/dpaa2: support for Rx packet parsing and packet type

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/base/dpaa2_hw_dpni_annot.h | 257 +++ drivers/net/dpaa2/dpaa2_ethdev.c | 23 +++ drivers/net/dpaa2/dpaa2_rxtx.c | 91 +- 4 files ch

[dpdk-dev] [PATCH v9 13/22] net/dpaa2: enable packet Rx and Tx operations

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 4 + drivers/net/dpaa2/dpaa2_ethdev.h | 3 + drivers/net/dpaa2/dpaa2_rxtx.c | 260 +++ 4 files changed, 268 insertions(+) create mode 100644 dr

[dpdk-dev] [PATCH v9 12/22] net/dpaa2: add MTU configuration support

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 34 ++ 2 files changed, 35 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index b7c274a..a6b7964

[dpdk-dev] [PATCH v9 11/22] net/dpaa2: add support for promiscuous mode

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 41 ++ 2 files changed, 42 insertions(+) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini index d50c62e..b7c2

[dpdk-dev] [PATCH v9 10/22] net/dpaa2: add support for L3 and L4 checksum offload

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 2 ++ drivers/net/dpaa2/dpaa2_ethdev.c | 72 +++--- 2 files changed, 70 insertions(+), 4 deletions(-) diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini in

[dpdk-dev] [PATCH v9 09/22] net/dpaa2: attach the buffer pool to dpni

2017-03-17 Thread Hemant Agrawal
This patch configures a MC-DPNI based DPAA2 PMD network port with a DPBP based buffer pool. Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 4 +++ drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 57 +++ drivers/net/dpaa2/dpaa2_ethdev.c | 62

[dpdk-dev] [PATCH v9 08/22] net/dpaa2: configure MAC address at init

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 28 drivers/net/dpaa2/dpaa2_ethdev.h | 3 +++ 2 files changed, 31 insertions(+) diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c index 266f70b..47a8788 100644 --- a/

[dpdk-dev] [PATCH v9 07/22] net/dpaa2: add RSS flow distribution

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 287 + drivers/net/dpaa2/dpaa2_ethdev.c | 31 +++- drivers/net/dpaa2/dpaa2_ethdev.h

[dpdk-dev] [PATCH v9 05/22] net/dpaa2: add mc dpni object support

2017-03-17 Thread Hemant Agrawal
This patch add support for dpni object support in MC driver. DPNI represent a network interface object in DPAA2. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile |4 + drivers/net/dpaa2/mc/dpni.c | 739 + drive

[dpdk-dev] [PATCH v9 06/22] net/dpaa2: adding eth ops to dpaa2

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- doc/guides/nics/features/dpaa2.ini | 1 + drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/dpaa2_ethdev.c | 410 - drivers/net/dpaa2/dpaa2_ethdev.h | 15 ++ 4 files changed, 426 insertions(+), 1 deletion(-)

[dpdk-dev] [PATCH v9 04/22] config: enable support for DPAA2 debug logging

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- config/common_base| 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 5 + 2 files changed, 10 insertions(+) diff --git a/config/common_base b/config/common_base index 8ec3591..1c54777 100644 --- a/config/common_base +++ b/config/c

[dpdk-dev] [PATCH v9 03/22] net/dpaa2: add debug log support

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/Makefile | 5 + drivers/net/dpaa2/dpaa2_ethdev.c | 9 +++-- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/dpaa2/Makefile b/drivers/net/dpaa2/Makefile index 4f5dbf7..3e3c8d1 100644 --- a/drivers/net/dpa

[dpdk-dev] [PATCH v9 02/22] doc: add DPAA2 NIC details

2017-03-17 Thread Hemant Agrawal
This patch adds the NXP dpaa2 architecture and pmd details in the Network interfaces section. Signed-off-by: Hemant Agrawal Acked-by: John McNamara --- MAINTAINERS| 1 + doc/guides/nics/dpaa2.rst | 614 + doc/guides/nics

[dpdk-dev] [PATCH v9 01/22] net/dpaa2: introducing NXP DPAA2 PMD driver

2017-03-17 Thread Hemant Agrawal
add support for fsl-mc bus based dpaa2 pmd driver. Signed-off-by: Hemant Agrawal --- MAINTAINERS | 2 + config/common_base | 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 5 + drivers/net/Makefile| 2 +-

[dpdk-dev] [PATCH v9 00/22] NXP DPAA2 PMD

2017-03-17 Thread Hemant Agrawal
(This patches has been split from DPAA2 PMD v8 series [2] as per comments received on ML [3].) The patch series adds NXP’s QorIQ-Layerscape DPAA2 Architecture based network SoC PMD. This version of the driver supports NXP LS208xA, LS204xA and LS108x families Network SoCs. DPAA2, or Data Path Acc

[dpdk-dev] [PATCH v1] mempool/dpaa2: add DPAA2 hardware offloaded mempool

2017-03-17 Thread Hemant Agrawal
DPAA2 Hardware Mempool handlers allow enqueue/dequeue from NXP's QBMAN hardware block. CONFIG_RTE_MBUF_DEFAULT_MEMPOOL_OPS is set to 'dpaa2', if the pool is enabled. This memory pool currently supports packet mbuf type blocks only. Signed-off-by: Hemant Agrawal --- MAINTAINERS

[dpdk-dev] [PATCH v1] NXP DPAA2 External Mempool Driver

2017-03-17 Thread Hemant Agrawal
(This patches has been split from DPAA2 PMD v8 series [1] as per comments received on ML [2].) This patch implements the HW mempool offload driver for packets buffers using the FSLMC provided DPBP object. The new pool is being configured using compile time option and pool name as "dpaa2". Depend

[dpdk-dev] [PATCH v1 22/22] bus/fslmc: frame queue based dq storage alloc

2017-03-17 Thread Hemant Agrawal
This patch adds generic functions for allowing dq storage for the frame queues. As the frame queues are common resource for different drivers this is helpful. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c| 32 + drivers/bus/fslmc/porta

[dpdk-dev] [PATCH v1 20/22] bus/fslmc: add physical-virtual address translation helpers

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 66 + 1 file changed, 66 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index f37ca0f..ec71314 100644 --- a/drivers/bus/fslmc

[dpdk-dev] [PATCH v1 21/22] bus/fslmc: add support for DMA mapping for ARM SMMU

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 96 + drivers/bus/fslmc/fslmc_vfio.h | 1 + drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 + 3 files changed, 98 insertions(+) diff --git a/drivers/bus/fslmc/fslmc_vfio.c

[dpdk-dev] [PATCH v1 19/22] bus/fslmc: add packet FLE definitions

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 53 + 1 file changed, 53 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 53524f9..f37ca0f 100644 --- a/drivers/bus/fslmc

[dpdk-dev] [PATCH v1 18/22] bus/fslmc: define VLAN header length

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 4 1 file changed, 4 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 2c1a861..53524f9 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h +++ b/dr

[dpdk-dev] [PATCH v1 17/22] bus/fslmc: introduce true and false macros

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 6 ++ 1 file changed, 6 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 84e2101..2c1a861 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h +++ b/

[dpdk-dev] [PATCH v1 16/22] bus/fslmc: define hardware annotation area size

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 10 ++ 1 file changed, 10 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h b/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h index 649d292..84e2101 100644 --- a/drivers/bus/fslmc/portal/dpaa2_hw_pvt.h

[dpdk-dev] [PATCH v1 15/22] bus/fslmc: define queues for DPAA2 devices

2017-03-17 Thread Hemant Agrawal
Before DPAA2 devices can communicate using hardware queues, this patch adds queue definitions in the FSLMC bus which the DPAA2 devices would instantitate. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 20 1 file changed, 20 insertions(+) diff -

[dpdk-dev] [PATCH v1 14/22] bus/fslmc: affine dpio to crypto threads

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c| 45 + drivers/bus/fslmc/portal/dpaa2_hw_dpio.h| 3 ++ drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 + 3 files changed, 49 insertions(+) diff --git a/drivers/bus/fslmc/portal/dpaa2

[dpdk-dev] [PATCH v1 13/22] bus/fslmc: introduce support for hardware mempool object

2017-03-17 Thread Hemant Agrawal
Each mempool instance is represented by a DPBP object from the FSL-MC bus. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/fslmc_vfio.c | 9 +- drivers/bus/fslmc/fslmc_vfio.h | 2 + drivers/bus/fslmc/portal/dp

[dpdk-dev] [PATCH v1 12/22] bus/fslmc: dpio portal driver

2017-03-17 Thread Hemant Agrawal
The portal driver is bound to DPIO objects discovered on the fsl-mc bus and provides services that: - allow other drivers, such as the Ethernet driver, to enqueue and dequeue frames for their respective objects A system will typically allocate 1 DPIO object per CPU to allow queuing operations to

[dpdk-dev] [PATCH v1 11/22] bus/fslmc: add debug log support

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_logs.h | 76 ++ 1 file changed, 76 insertions(+) create mode 100644 drivers/bus/fslmc/fslmc_logs.h diff --git a/drivers/bus/fslmc/fslmc_logs.h b/drivers/bus/fslmc/fslmc_logs.h new file mode 100644

[dpdk-dev] [PATCH v1 09/22] bus/fslmc: add vfio support

2017-03-17 Thread Hemant Agrawal
Add support for using VFIO for dpaa2 based fsl-mc bus. There are some differences in the way vfio used for fsl-mc bus from the eal vfio. - The scanning of bus for individual objects on the basis of the DPRC container. - The use and mapping of MC portal for object access With the evolution of

[dpdk-dev] [PATCH v1 10/22] bus/fslmc: scan for net and sec device

2017-03-17 Thread Hemant Agrawal
This patch will add support in fslmc vfio process to scan and parse the dpni and dpseci object for net and crypto devices. It will add the scanned devices to the fslmc bus. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 63 +- 1 file ch

[dpdk-dev] [PATCH v1 08/22] eal/vfio: adding vfio utility functions in map file

2017-03-17 Thread Hemant Agrawal
adding extra vfio utility functions to map file. They will be used by other vfio supported buses like fslmc bus for NXP DPAA2 devices Signed-off-by: Hemant Agrawal --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 3 +++ lib/librte_eal/linuxapp/eal/rte_eal_version.map | 3 +++ 2 files change

[dpdk-dev] [PATCH v1 07/22] bus/fslmc: add mc dpbp object support

2017-03-17 Thread Hemant Agrawal
DPBP object represent a hw based buffer pool instance in the DPAA2 hardware. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/mc/dpbp.c | 261 drivers/bus/fslmc/mc/

[dpdk-dev] [PATCH v1 06/22] bus/fslmc: add mc dpio object support

2017-03-17 Thread Hemant Agrawal
This patch adds the DPIO object support in MC driver. DPIO - Data Path Input Output represent the processing context to access the QBMAN HW for packet I/O. Signed-off-by: Alex Marginean Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/Makefile | 1 + drivers/bus/fslmc/mc/

[dpdk-dev] [PATCH v1 05/22] bus/fslmc: introduce MC object functions

2017-03-17 Thread Hemant Agrawal
This patch intoduces the DPAA2 MC(Management complex Driver). This is a minimal set of low level functions to send and receive commands to the fsl-mc. It includes support for basic management commands and commands to manipulate MC objects. This is common to be used by various DPAA2 PMDs. e.g.net,

[dpdk-dev] [PATCH v1 04/22] bus/fslmc: add QBMAN driver to bus

2017-03-17 Thread Hemant Agrawal
QBMAN, is a hardware block which interfaces with the other accelerating hardware blocks (For e.g., WRIOP) on NXP's DPAA2 SoC for queue, buffer and packet scheduling. This patch introduces a userspace driver for interfacing with the QBMAN hw block. The qbman-portal component provides APIs to do th

[dpdk-dev] [PATCH v1 03/22] bus/fslmc: introducing fsl-mc bus driver

2017-03-17 Thread Hemant Agrawal
The fslmc bus driver is a rte_bus driver which scans the fsl-mc bus for NXP DPAA2 SoCs. Signed-off-by: Hemant Agrawal --- MAINTAINERS | 4 + config/common_base | 5 + config/defconfig_arm64-dpaa2-linuxapp-gcc | 8 +- drivers/Makefi

[dpdk-dev] [PATCH v1 02/22] mk: handle intra drivers dependencies for shared build

2017-03-17 Thread Hemant Agrawal
From: Shreyansh Jain Suggested-by: Ferruh Yigit Signed-off-by: Shreyansh Jain --- mk/rte.lib.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mk/rte.lib.mk b/mk/rte.lib.mk index 5b72475..9486204 100644 --- a/mk/rte.lib.mk +++ b/mk/rte.lib.mk @@ -87,7 +87,7 @@ endif # T

[dpdk-dev] [PATCH v1 01/22] mk/dpaa2: add the crc support to the machine type

2017-03-17 Thread Hemant Agrawal
Signed-off-by: Hemant Agrawal Acked-by: Jerin Jacob --- mk/machine/dpaa2/rte.vars.mk | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/mk/machine/dpaa2/rte.vars.mk b/mk/machine/dpaa2/rte.vars.mk index 8541633..e4735c2 100644 --- a/mk/machine/dpaa2/rte.vars.mk +++ b/mk/mach

[dpdk-dev] [PATCH v1 00/22] NXP DPAA2 FSLMC Bus driver

2017-03-17 Thread Hemant Agrawal
(This patches has been split from DPAA2 PMD v8 series [1] as per comments received on ML [2].) The patchset introduces NXP’s QorIQ-Layerscape DPAA2 Architecture based fsl-mc bus driver. This version of the driver supports NXP LS208xA, LS204xA and LS108x family of Network SoCs. This driver is base

Re: [dpdk-dev] [PATCH v4 04/17] eventdev: add APIs for extended stats

2017-03-17 Thread Jerin Jacob
On Fri, Mar 10, 2017 at 07:43:19PM +, Harry van Haaren wrote: > From: Bruce Richardson > > Add in APIs for extended stats so that eventdev implementations can report > out information on their internal state. The APIs are based on, but not > identical to, the equivalent ethdev functions. > >

[dpdk-dev] next technical board meeting, 2017-03-20

2017-03-17 Thread Ananyev, Konstantin
Hello everyone, A meeting of the DPDK technical board will occur next Monday, March 20th 2017 at 3pm UTC. The meeting takes place on the #dpdk-board channel on IRC. This meeting is public, so anybody can join, see below for the agenda. Konstantin 1. AVP PMD Patches: http://dpdk.org/dev/patchwork/

Re: [dpdk-dev] [PATCH] vfio: add hotplug support

2017-03-17 Thread Eelco Chaudron
On 16/03/17 11:51, Alejandro Lucero wrote: Current device hotplug is just when using UIO. This patch adds same functionality with VFIO. It has been validated through tests using IOMMU and also with VFIO and no-iommu mode. Signed-off-by: Alejandro Lucero --- lib/librte_eal/common/eal_common_p

Re: [dpdk-dev] [PATCH v2 00/13] introduce fail-safe PMD

2017-03-17 Thread Gaëtan Rivet
On Thu, Mar 16, 2017 at 04:50:43PM -0400, Neil Horman wrote: On Wed, Mar 15, 2017 at 03:25:37PM +0100, Gaëtan Rivet wrote: On Wed, Mar 15, 2017 at 12:15:56PM +0100, Thomas Monjalon wrote: > 2017-03-15 03:28, Bruce Richardson: > > On Tue, Mar 14, 2017 at 03:49:47PM +0100, Gaëtan Rivet wrote: > >

  1   2   >