[dpdk-dev] [PATCH 0/3] fix build issues with librte_sched, test_red on non x86 platform

2015-08-18 Thread Jerin Jacob
This patch set enable librte_sched, app/test/test_sched and app/test/test_red to build on non x86 platform Jerin Jacob (3): sched: remove unused inclusion of tmmintrin.h app/test: test_sched: fix needless build dependency on CONFIG_RTE_ARCH_X86_64 app/test: enable test_red to build

[dpdk-dev] [PATCH 1/3] sched: remove unused inclusion of tmmintrin.h

2015-08-18 Thread Jerin Jacob
SSSE3 intrinsics not used in rte_bitmap.h Signed-off-by: Jerin Jacob --- lib/librte_sched/rte_bitmap.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/lib/librte_sched/rte_bitmap.h b/lib/librte_sched/rte_bitmap.h index 216a344..3d911e4 100644 --- a/lib/librte_sched/rte_bitmap.h +++ b/lib

[dpdk-dev] [PATCH 2/3] app/test: test_sched: fix needless build dependency on CONFIG_RTE_ARCH_X86_64

2015-08-18 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- app/test/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/test/Makefile b/app/test/Makefile index e7f148f..43429b9 100644 --- a/app/test/Makefile +++ b/app/test/Makefile @@ -115,7 +115,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_CMDLINE

[dpdk-dev] [PATCH 3/3] app/test: enable test_red to build on non x86 platform

2015-08-18 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- app/test/test_red.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/app/test/test_red.c b/app/test/test_red.c index 262df72..813c508 100644 --- a/app/test/test_red.c +++ b/app/test/test_red.c @@ -146,6 +146,7 @@ static void rdtsc_prof_init(struct rdtsc_prof

[dpdk-dev] [PATCH 3/3] app/test: enable test_red to build on non x86 platform

2015-08-27 Thread Jerin Jacob
On Tue, Aug 25, 2015 at 02:03:13PM +0200, Thomas Monjalon wrote: > 2015-08-18 18:10, Jerin Jacob: > > --- a/app/test/test_red.c > > +++ b/app/test/test_red.c > > +#if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686) || > > defined(RTE_ARCH_X86_X32) > > #if

[dpdk-dev] [PATCH v2 0/3] fix build issues with librte_sched, test_red on non x86 platform

2015-08-30 Thread Jerin Jacob
This patch set enable librte_sched, app/test/test_sched and app/test/test_red to build on non x86 platform v1..v2 use memory barrier version rte_rdtsc() for multi arch support as suggested by Thomas Monjalon Jerin Jacob (3): sched: remove unused inclusion of tmmintrin.h app/test: test_sched

[dpdk-dev] [PATCH 1/3] sched: remove unused inclusion of tmmintrin.h

2015-08-30 Thread Jerin Jacob
SSSE3 intrinsics not used in rte_bitmap.h Signed-off-by: Jerin Jacob --- lib/librte_sched/rte_bitmap.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/lib/librte_sched/rte_bitmap.h b/lib/librte_sched/rte_bitmap.h index 216a344..3d911e4 100644 --- a/lib/librte_sched/rte_bitmap.h +++ b/lib

[dpdk-dev] [PATCH 2/3] app/test: test_sched: fix needless build dependency on CONFIG_RTE_ARCH_X86_64

2015-08-30 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- app/test/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/test/Makefile b/app/test/Makefile index e7f148f..43429b9 100644 --- a/app/test/Makefile +++ b/app/test/Makefile @@ -115,7 +115,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_CMDLINE

[dpdk-dev] [PATCH 3/3] app/test: use memory barrier version of rte_rdtsc() eal api for multi arch support

2015-08-30 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- app/test/test_red.c | 11 +-- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/app/test/test_red.c b/app/test/test_red.c index 262df72..37841b3 100644 --- a/app/test/test_red.c +++ b/app/test/test_red.c @@ -146,16 +146,7 @@ static void

[dpdk-dev] [PATCH 2/4] eal/acl: enable acl for armv7-a

2015-12-01 Thread Jerin Jacob
On Tue, Dec 01, 2015 at 01:41:14PM -0500, Jianbo Liu wrote: > Implement vqtbl1q_u8 intrinsic function, which is not support in armv7-a. > > Signed-off-by: Jianbo Liu > --- > config/defconfig_arm-armv7a-linuxapp-gcc | 1 - > lib/librte_acl/Makefile | 2 +- >

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-01 Thread Jerin Jacob
On Tue, Dec 01, 2015 at 01:41:15PM -0500, Jianbo Liu wrote: > Adds ARM NEON support for lpm. > And enables table/pipeline libraries which depend on lpm. I already sent the patch on the same yesterday. We can converge the patches after the discussion. Please check "[dpdk-dev] [PATCH 0/3] add lpm

[dpdk-dev] [PATCH 4/4] maintainers: claim resposibility for ARMv7 and ARMv8

2015-12-01 Thread Jerin Jacob
; @@ -124,10 +124,12 @@ F: doc/guides/sample_app_ug/multi_process.rst > > ARM v7 > M: Jan Viktorin > +M: Jianbo Liu > F: lib/librte_eal/common/include/arch/arm/ > > ARM v8 > M: Jerin Jacob > +M: Jianbo Liu +1 > F: lib/librte_eal/comm

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 02:54:52PM +0800, Jianbo Liu wrote: > On 2 December 2015 at 00:41, Jerin Jacob > wrote: > > On Tue, Dec 01, 2015 at 01:41:15PM -0500, Jianbo Liu wrote: > >> Adds ARM NEON support for lpm. > >> And enables table/pipeline libraries which de

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 05:49:41PM +0800, Jianbo Liu wrote: > On 2 December 2015 at 16:03, Jerin Jacob > wrote: > > On Wed, Dec 02, 2015 at 02:54:52PM +0800, Jianbo Liu wrote: > >> On 2 December 2015 at 00:41, Jerin Jacob >> caviumnetworks.com> wrote: > >&g

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 10:33:44AM +, Ananyev, Konstantin wrote: > Hi everyone, > > > -Original Message- > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jianbo Liu > > Sent: Wednesday, December 02, 2015 9:50 AM > > To: Jerin Jacob > >

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 09:13:51PM +0800, Jianbo Liu wrote: > On 2 December 2015 at 18:39, Jerin Jacob > wrote: > > On Wed, Dec 02, 2015 at 05:49:41PM +0800, Jianbo Liu wrote: > >> On 2 December 2015 at 16:03, Jerin Jacob >> caviumnetworks.com> wrote: > >&g

[dpdk-dev] [PATCH 0/3] add lpm support for NEON

2015-12-02 Thread Jerin Jacob
. > > On Mon, 30 Nov 2015 22:54:10 +0530 > Jerin Jacob wrote: > > > - Introduce new rte_vect_* abstractions in eal > > - This patch set has the changes required for optimised pm library usage in > > arm64 perspective > > - Tested on Juno and Thunder boards &

[dpdk-dev] [PATCH 1/3] eal: introduce rte_vect_* abstractions

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 02:43:34PM +0100, Jan Viktorin wrote: > On Mon, 30 Nov 2015 22:54:11 +0530 > Jerin Jacob wrote: > > > introduce rte_vect_* abstractions to remove SSE/AVX specific > > code in the common code(i.e the test applications) > > > > The patc

[dpdk-dev] [PATCH 2/3] lpm: add support for NEON

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 02:43:40PM +0100, Jan Viktorin wrote: > On Mon, 30 Nov 2015 22:54:12 +0530 > Jerin Jacob wrote: > > > enabled CONFIG_RTE_LIBRTE_LPM, CONFIG_RTE_LIBRTE_TABLE, > > CONFIG_RTE_LIBRTE_PIPELINE libraries for arm64. > > > > TABLE, PIPELINE l

[dpdk-dev] [PATCH 3/3] maintainers: claim responsibility for arm64 specific files of hash and lpm

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 02:43:52PM +0100, Jan Viktorin wrote: > On Mon, 30 Nov 2015 22:54:13 +0530 > Jerin Jacob wrote: > > > Signed-off-by: Jerin Jacob > > --- > > MAINTAINERS | 3 +++ > > 1 file changed, 3 insertions(+) > > > > diff --git

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 05:40:13PM +0100, Thomas Monjalon wrote: > 2015-12-02 20:04, Jerin Jacob: > > On Wed, Dec 02, 2015 at 09:13:51PM +0800, Jianbo Liu wrote: > > > On 2 December 2015 at 18:39, Jerin Jacob > > caviumnetworks.com> wrote: > > > > AND

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-02 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 05:57:10PM +0100, Thomas Monjalon wrote: > 2015-12-02 22:23, Jerin Jacob: > > On Wed, Dec 02, 2015 at 05:40:13PM +0100, Thomas Monjalon wrote: > > > 2015-12-02 20:04, Jerin Jacob: > > > > On Wed, Dec 02, 2015 at 09:13:51PM +0800, Jianbo Liu

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-03 Thread Jerin Jacob
On Wed, Dec 02, 2015 at 05:57:10PM +0100, Thomas Monjalon wrote: > 2015-12-02 22:23, Jerin Jacob: > > On Wed, Dec 02, 2015 at 05:40:13PM +0100, Thomas Monjalon wrote: > > > 2015-12-02 20:04, Jerin Jacob: > > > > On Wed, Dec 02, 2015 at 09:13:51PM +0800, Jianbo Liu

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-03 Thread Jerin Jacob
On Thu, Dec 03, 2015 at 11:02:07AM +, Ananyev, Konstantin wrote: Hi Konstantin, > Hi Jerin, > > > -Original Message- > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jerin Jacob > > Sent: Thursday, December 03, 2015 9:34 AM > > To: Thomas Mo

[dpdk-dev] [PATCH 3/4] eal/arm: Enable lpm/table/pipeline libs

2015-12-03 Thread Jerin Jacob
On Thu, Dec 03, 2015 at 12:42:13PM +, Ananyev, Konstantin wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Thursday, December 03, 2015 12:17 PM > > To: Ananyev, Konstantin > > Cc: Thomas

[dpdk-dev] [PATCH v2 2/3] eal/acl: enable acl for armv7-a

2015-12-03 Thread Jerin Jacob
On Thu, Dec 03, 2015 at 11:02:55PM +0800, Jianbo Liu wrote: > Implement vqtbl1q_u8 intrinsic function, which is not support in armv7-a. > > Signed-off-by: Jianbo Liu Acked-by: Jerin Jacob > --- > config/defconfig_arm-armv7a-linuxapp-gcc | 1 - > lib/l

[dpdk-dev] [PATCH v2 0/3] add lpm support for NEON

2015-12-04 Thread Jerin Jacob
from Jianbo's lpm patches Jerin Jacob (3): lpm: make rte_lpm_lookupx4 API definition architecture agnostic lpm: add support for NEON maintainers: claim responsibility for arm64 specific files of hash and lpm MAINTAINERS| 3 + app/test/test_lpm.c

[dpdk-dev] [PATCH v2 1/3] lpm: make rte_lpm_lookupx4 API definition architecture agnostic

2015-12-04 Thread Jerin Jacob
rte_lpm_lookupx4 implementation for a different architecture. Signed-off-by: Jerin Jacob --- app/test/test_lpm.c | 21 --- app/test/test_xmmt_ops.h | 47 ++ lib/librte_lpm/Makefile | 2 + lib/librte_lpm/rte_lpm.h | 93 +--- lib/librte_lpm

[dpdk-dev] [PATCH v2 2/3] lpm: add support for NEON

2015-12-04 Thread Jerin Jacob
Enabled CONFIG_RTE_LIBRTE_LPM, CONFIG_RTE_LIBRTE_TABLE, CONFIG_RTE_LIBRTE_PIPELINE libraries for arm and arm64 TABLE, PIPELINE libraries were disabled due to LPM library dependency. Signed-off-by: Jerin Jacob Signed-off-by: Jianbo Liu --- app/test/test_xmmt_ops.h | 20

[dpdk-dev] [PATCH v2 3/3] maintainers: claim responsibility for arm64 specific files of hash and lpm

2015-12-04 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 460245b..b8ca465 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -133,6 +133,9 @@ ARM v8 M: Jerin Jacob F: lib/librte_eal/common/include/arch/arm/*_64.h F: lib

[dpdk-dev] [RFC PATCH 0/2] Fix examples/distributor build issue for non x86

2015-12-06 Thread Jerin Jacob
for rte_prefetch_non_temporal() for specific architecures Jerin Jacob (2): eal: introduce rte_prefetch_non_temporal examples/distributor: remove IA specific __mm_prefetch examples/distributor/main.c | 9 + lib/librte_eal/common/include/arch/arm/rte_prefetch_32.h | 5

[dpdk-dev] [PATCH 1/2] eal: introduce rte_prefetch_non_temporal

2015-12-06 Thread Jerin Jacob
non-temporal/transient/stream version of rte_prefetch0() The non-temporal prefetch is intended as a prefetch hint that processor will use the prefetched data only once or short period, unlike the rte_prefetch0() function which imply that prefetched data to use repeatedly. Signed-off-by: Jerin

[dpdk-dev] [PATCH 2/2] examples/distributor: remove IA specific __mm_prefetch

2015-12-06 Thread Jerin Jacob
use rte_prefetch_non_temporal() abstraction instead of _mm_prefetch(x, 0) to in-order to build distributor application for non x86 platforms Signed-off-by: Jerin Jacob --- examples/distributor/main.c | 9 + 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/examples

[dpdk-dev] [PATCH 0/2] fix performance/cache resource issues with 128-byte cache line targets

2015-12-06 Thread Jerin Jacob
degradation for 64-bytes cache line size targets. Jerin Jacob (2): mbuf: fix performance/cache resource issue with 128-byte cache line targets bitmap: optimize for 128-bytes cache line targets app/test/test_mbuf.c | 4 .../linuxapp/eal/include/exec-env

[dpdk-dev] [PATCH 1/2] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-06 Thread Jerin Jacob
No need to split mbuf structure to two cache lines for 128-byte cache line size targets as it can fit on a single 128-byte cache line. Signed-off-by: Jerin Jacob --- app/test/test_mbuf.c | 4 lib/librte_eal/linuxapp/eal/include/exec-env

[dpdk-dev] [PATCH 2/2] bitmap: optimize for 128-bytes cache line targets

2015-12-06 Thread Jerin Jacob
existing rte_bitmap library implementation optimally configured to run on 64-bytes cache line, extending to 128-bytes cache line targets. Signed-off-by: Jerin Jacob --- lib/librte_sched/rte_bitmap.h | 12 +--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/lib

[dpdk-dev] [PATCH v2 1/3] lpm: make rte_lpm_lookupx4 API definition architecture agnostic

2015-12-07 Thread Jerin Jacob
On Mon, Dec 07, 2015 at 02:15:28PM +0800, Jianbo Liu wrote: > On 4 December 2015 at 23:14, Jerin Jacob > wrote: > > -Used architecture agnostic xmm_t to represent 128 bit SIMD variable > > > > -Introduced vect_* API abstraction in app/test to test rte_lpm_lookupx4

[dpdk-dev] [PATCH 0/2] fix performance/cache resource issues with 128-byte cache line targets

2015-12-07 Thread Jerin Jacob
On Sun, Dec 06, 2015 at 05:30:50PM +0100, Thomas Monjalon wrote: > 2015-12-06 21:29, Jerin Jacob: > > This patchset fixes performance/cache resource issues with 128-byte cache > > line targets > > found in mbuf and bitmap DPDK libraries > > > > Currently,

[dpdk-dev] [PATCH] config: cleanup existing RTE_CACHE_LINE_SIZE selection scheme

2015-12-07 Thread Jerin Jacob
-by: Jerin Jacob --- config/common_bsdapp | 5 + config/common_linuxapp| 6 +- config/defconfig_arm64-armv8a-linuxapp-gcc| 2 -- config/defconfig_ppc_64-power8-linuxapp-gcc

[dpdk-dev] [PATCH 0/2] fix performance/cache resource issues with 128-byte cache line targets

2015-12-07 Thread Jerin Jacob
On Mon, Dec 07, 2015 at 03:40:13AM -0800, Thomas Monjalon wrote: > 2015-12-07 12:56, Jerin Jacob: > > On Sun, Dec 06, 2015 at 05:30:50PM +0100, Thomas Monjalon wrote: > > > 2015-12-06 21:29, Jerin Jacob: > > > > This patchset fixes performance/cache resource issue

[dpdk-dev] [PATCH] librte_hash: Fix compile errors on IBM POWER

2015-12-08 Thread Jerin Jacob
On Tue, Dec 08, 2015 at 04:28:52PM +0800, Chao Zhu wrote: > This patch fixes the compile errors caused by lacking of "size_t" definition > in rte_hash.h. > > Signed-off-by: Chao Zhu > --- > lib/librte_hash/rte_hash.h |1 + > 1 files changed, 1 insertions(+), 0 deletions(-) > > diff --git

[dpdk-dev] [PATCH] config: cleanup existing RTE_CACHE_LINE_SIZE selection scheme

2015-12-08 Thread Jerin Jacob
On Mon, Dec 07, 2015 at 03:45:10PM +0100, Thomas Monjalon wrote: > 2015-12-07 19:52, Jerin Jacob: > > by default, all the targets will be configured with the 64-byte cache line > > size, targets which have different cache line size can be overridden > > through target

[dpdk-dev] [PATCH 1/2] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-08 Thread Jerin Jacob
On Mon, Dec 07, 2015 at 03:21:33PM +, Ananyev, Konstantin wrote: Hi Konstantin, > Hi Jerin, > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Sunday, December 06, 2015 3:59 PM > > To: dev at dp

[dpdk-dev] [PATCH 1/2] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-08 Thread Jerin Jacob
On Tue, Dec 08, 2015 at 04:07:46PM +, Ananyev, Konstantin wrote: > > > > Hi Konstantin, > > > > > Hi Jerin, > > > > > > > -Original Message- > > > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > >

[dpdk-dev] [PATCH] librte_hash: Fix compile errors on IBM POWER

2015-12-09 Thread Jerin Jacob
known type name > ?rte_hash_cmp_eq_t? > void rte_hash_set_cmp_func(struct rte_hash *h, rte_hash_cmp_eq_t func); add fixes: Fixes: 95da2f8e9c61 ("hash: customize compare function") with above changes, Acked-by: Jerin Jacob > > Signed-off-by: Chao Zhu > --- > lib/librte

[dpdk-dev] [PATCH 1/2] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-09 Thread Jerin Jacob
On Wed, Dec 09, 2015 at 01:44:44PM +, Ananyev, Konstantin wrote: Hi Konstantin, > > Hi Jerin, > > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Tuesday, December 08, 2015 5:49 PM > > To: Ananyev, Konstantin > > Cc: dev at dpdk.

[dpdk-dev] [PATCH v2 0/4] fix performance/cache resource issues with 128-byte cache line targets

2015-12-10 Thread Jerin Jacob
on these changes by verifying the md5sum of app/test,app/testpmd, app/testacl binaries with or without this patch set Jerin Jacob (4): eal: Introduce new cache macro definitions mbuf: fix performance/cache resource issue with 128-byte cache line targets bitmap: optimize for 128-bytes

[dpdk-dev] [PATCH v2 1/4] eal: Introduce new cache macro definitions

2015-12-10 Thread Jerin Jacob
- RTE_CACHE_MIN_LINE_SIZE(Supported minimum cache line size) - __rte_cache_min_aligned(Force minimum cache line alignment) - RTE_CACHE_LINE_SIZE_LOG2(Express cache line size in terms of log2) Signed-off-by: Jerin Jacob Suggested-by: Konstantin Ananyev --- lib/librte_eal/common/include

[dpdk-dev] [PATCH v2 2/4] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-10 Thread Jerin Jacob
No need to split mbuf structure to two cache lines for 128-byte cache line size targets as it can fit on a single 128-byte cache line. Signed-off-by: Jerin Jacob --- app/test/test_mbuf.c | 2 +- lib/librte_eal/linuxapp/eal/include/exec-env

[dpdk-dev] [PATCH v2 3/4] bitmap: optimize for 128-bytes cache line targets

2015-12-10 Thread Jerin Jacob
existing rte_bitmap library implementation optimally configured to run on 64-bytes cache line, extending to 128-bytes cache line targets. Signed-off-by: Jerin Jacob --- lib/librte_sched/rte_bitmap.h | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/lib/librte_sched

[dpdk-dev] [PATCH v2 4/4] cache/slow-path: reduce cache align requirement for 128-byte cache targets

2015-12-10 Thread Jerin Jacob
slow-path data structures need not be 128-byte cache aligned. Reduce the alignment to 64-byte to save the memory. No behavior change for 64-byte cache aligned systems as minimum cache line size as 64. Signed-off-by: Jerin Jacob --- lib/librte_ether/rte_ethdev.h| 4 ++-- lib/librte_mempool

[dpdk-dev] [PATCH v2 4/4] cache/slow-path: reduce cache align requirement for 128-byte cache targets

2015-12-11 Thread Jerin Jacob
On Fri, Dec 11, 2015 at 12:55:57PM +, Ananyev, Konstantin wrote: > Hi Jerin, > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Thursday, December 10, 2015 4:36 PM > > To: dev at dpdk.org > > Cc: t

[dpdk-dev] [PATCH v3 0/4] fix performance/cache resource issues with 128-byte cache line targets

2015-12-14 Thread Jerin Jacob
on these changes by verifying the md5sum of app/test,app/testpmd, app/testacl binaries with or without this patch set v2..v3 revert the cache alignment of rte_ring_debug_stats, rte_mempool_debug_stats structures For the series, Acked-by: Konstantin Ananyev Jerin Jacob (4): eal: Introduce new

[dpdk-dev] [PATCH v3 1/4] eal: Introduce new cache macro definitions

2015-12-14 Thread Jerin Jacob
- RTE_CACHE_MIN_LINE_SIZE(Supported minimum cache line size) - __rte_cache_min_aligned(Force minimum cache line alignment) - RTE_CACHE_LINE_SIZE_LOG2(Express cache line size in terms of log2) Signed-off-by: Jerin Jacob Suggested-by: Konstantin Ananyev --- lib/librte_eal/common/include

[dpdk-dev] [PATCH v3 2/4] mbuf: fix performance/cache resource issue with 128-byte cache line targets

2015-12-14 Thread Jerin Jacob
No need to split mbuf structure to two cache lines for 128-byte cache line size targets as it can fit on a single 128-byte cache line. Signed-off-by: Jerin Jacob --- app/test/test_mbuf.c | 2 +- lib/librte_eal/linuxapp/eal/include/exec-env

[dpdk-dev] [PATCH v3 3/4] bitmap: optimize for 128-bytes cache line targets

2015-12-14 Thread Jerin Jacob
existing rte_bitmap library implementation optimally configured to run on 64-bytes cache line, extending to 128-bytes cache line targets. Signed-off-by: Jerin Jacob --- lib/librte_sched/rte_bitmap.h | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/lib/librte_sched

[dpdk-dev] [PATCH v3 4/4] cache/slow-path: reduce cache align requirement for 128-byte cache targets

2015-12-14 Thread Jerin Jacob
slow-path data structures need not be 128-byte cache aligned. Reduce the alignment to 64-byte to save the memory. No behavior change for 64-byte cache aligned systems as minimum cache line size as 64. Signed-off-by: Jerin Jacob Acked-by: Konstantin Ananyev --- lib/librte_ether/rte_ethdev.h

[dpdk-dev] [ [PATCH v2] 03/13] rte_io: armv7/v8: Introduce api to emulate x86-style of PCI/ISA ioport access

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 06:30:22PM +0530, Santosh Shukla wrote: > Introducing rte_io.h header file to emulate x86-style of ioport rd/wr api > example {in,out}[bwl] and {in_p,out_p}[bwl]. Api support added for armv7 and > armv8 both. > > Current use-case for this api is for virtio_pci module that

[dpdk-dev] [ [PATCH v2] 04/13] virtio_pci: use rte_io.h for non-x86 arch

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 06:30:23PM +0530, Santosh Shukla wrote: > Use rte_io.h for non-x86 arch. > > Signed-off-by: Santosh Shukla > --- > drivers/net/virtio/virtio_pci.h |4 > 1 file changed, 4 insertions(+) > > diff --git a/drivers/net/virtio/virtio_pci.h

[dpdk-dev] [ [PATCH v2] 06/13] config: armv7/v8: Enable RTE_LIBRTE_VIRTIO_PMD

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 06:30:25PM +0530, Santosh Shukla wrote: > Enable RTE_LIBRTE_VIRTIO_PMD for armv7/v8 and setting RTE_VIRTIO_INC_VEC=n. > Builds successfully for armv7/v8. > > Signed-off-by: Santosh Shukla > --- > config/defconfig_arm-armv7a-linuxapp-gcc |6 +- >

[dpdk-dev] [ [PATCH v2] 07/13] linuxapp: eal: arm: Always return 0 for rte_eal_iopl_init()

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 06:30:26PM +0530, Santosh Shukla wrote: > iopl() syscall not supported in linux-arm/arm64 so always return 0 value. > > Signed-off-by: Santosh Shukla > --- > lib/librte_eal/linuxapp/eal/eal.c |3 +++ > 1 file changed, 3 insertions(+) > > diff --git

[dpdk-dev] [ [PATCH v2] 10/13] include/exec-env: ioport: add rte_virt_ioport header file

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 06:30:29PM +0530, Santosh Shukla wrote: > including virtio_ioport header file has iopci bar page_size, bar_len and > device filename info. > > Signed-off-by: Santosh Shukla > --- > lib/librte_eal/linuxapp/eal/Makefile |2 +- >

[dpdk-dev] [ [PATCH v2] 07/13] linuxapp: eal: arm: Always return 0 for rte_eal_iopl_init()

2015-12-14 Thread Jerin Jacob
On Mon, Dec 14, 2015 at 08:54:08PM +0530, Santosh Shukla wrote: > On Mon, Dec 14, 2015 at 8:07 PM, Jerin Jacob > wrote: > > On Mon, Dec 14, 2015 at 06:30:26PM +0530, Santosh Shukla wrote: > >> iopl() syscall not supported in linux-arm/arm64 so always return 0 value.

[dpdk-dev] [PATCH] eal: map io resources for non x86 architectures

2015-12-18 Thread Jerin Jacob
On Fri, Dec 18, 2015 at 01:30:53PM +0800, Yuanhan Liu wrote: > On Thu, Dec 17, 2015 at 04:52:00PM +0530, Santosh Shukla wrote: > > >> >> IMO, it is worth keeping one special device file who could work across > > >> >> archs like arm/arm64/powerpc and others, who could map iopci bar to > > >> >>

[dpdk-dev] [PATCH v2] cryptodev: fix crash on null dereference

2016-12-03 Thread Jerin Jacob
crypodev->data->name will be null when rte_cryptodev_get_dev_id() invoked without a valid crypto device instance. Fixes: d11b0f30df88 ("cryptodev: introduce API and framework for crypto devices") Signed-off-by: Jerin Jacob <jerin.ja...@caviumnetworks.com> Acked-by: Arek Ku

[dpdk-dev] [PATCH v2 1/2] eal: postpone vdev initialization

2016-12-03 Thread Jerin Jacob
configure/start 2) pcie device 1 configure/start 3) bond device 2 configure/start 3.1) pcie device 0/stop/configure/start 3.2) pcie device 1/stop/configure/start Signed-off-by: Jerin Jacob <jerin.ja...@caviumnetworks.com> --- lib/librte_eal/bsdapp/eal/eal.c | 6 +++--- lib/librte_eal/li

[dpdk-dev] [PATCH v2 0/2] postpone vdev initialization

2016-12-03 Thread Jerin Jacob
v2: - No changes in eal: postpone vdev initialization - Added new patch "eal: rename dev init API for consistency" as suggested by Shreyansh Jain http://dpdk.org/dev/patchwork/patch/17096/ Jerin Jacob (2): eal: postpone vdev initialization eal: rename dev init API for consistency

[dpdk-dev] [PATCH v2 2/2] eal: rename dev init API for consistency

2016-12-03 Thread Jerin Jacob
igned-off-by: Jerin Jacob <jerin.ja...@caviumnetworks.com> --- drivers/net/virtio/virtio_user_ethdev.c | 2 +- lib/librte_eal/bsdapp/eal/eal.c | 4 ++-- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 2 +- lib/librte_eal/common/eal_common_dev.

[dpdk-dev] [PATCH] lib: change rte_ring dequeue to guarantee ordering before tail update

2016-07-23 Thread Jerin Jacob
On Thu, Jul 21, 2016 at 11:26:50PM +0200, Thomas Monjalon wrote: > > > Consumer queue dequeuing must be guaranteed to be done fully before the > > > tail is updated. This is not guaranteed with a read barrier, > > > changed to a write barrier just before tail update which in practice > > >

[dpdk-dev] [PATCH] lib: change rte_ring dequeue to guarantee ordering before tail update

2016-07-23 Thread Jerin Jacob
On Sat, Jul 23, 2016 at 11:02:33AM +0200, Thomas Monjalon wrote: > 2016-07-23 8:05 GMT+02:00 Jerin Jacob : > > On Thu, Jul 21, 2016 at 11:26:50PM +0200, Thomas Monjalon wrote: > >> > > Consumer queue dequeuing must be guaranteed to be done fully before >

[dpdk-dev] [PATCH] lib: change rte_ring dequeue to guarantee ordering before tail update

2016-07-23 Thread Jerin Jacob
On Sat, Jul 23, 2016 at 10:14:51AM +, Ananyev, Konstantin wrote: > Hi lads, > > > On Sat, Jul 23, 2016 at 11:02:33AM +0200, Thomas Monjalon wrote: > > > 2016-07-23 8:05 GMT+02:00 Jerin Jacob : > > > > On Thu, Jul 21, 2016 at 11:26:50PM +0200, Thomas Monjalon w

[dpdk-dev] [PATCH] lib: change rte_ring dequeue to guarantee ordering before tail update

2016-07-23 Thread Jerin Jacob
On Sat, Jul 23, 2016 at 11:15:27AM +, Ananyev, Konstantin wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Saturday, July 23, 2016 11:39 AM > > To: Ananyev, Konstantin > > Cc: Th

[dpdk-dev] [PATCH] lib: change rte_ring dequeue to guarantee ordering before tail update

2016-07-23 Thread Jerin Jacob
On Sat, Jul 23, 2016 at 12:32:01PM +, Ananyev, Konstantin wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Saturday, July 23, 2016 12:49 PM > > To: Ananyev, Konstantin > > Cc: Th

[dpdk-dev] [PATCH] ring: fix sc dequeue performance issue

2016-07-24 Thread Jerin Jacob
to be completed before tail pointer update. Changing to rte_smb_rmb() to enable the required LOAD-STORE barrier. Fixes: ecc7d10e448e ("ring: guarantee dequeue ordering before tail update") Signed-off-by: Jerin Jacob --- lib/librte_ring/rte_ring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletio

[dpdk-dev] usages issue with external mempool

2016-07-27 Thread Jerin Jacob
On Tue, Jul 26, 2016 at 10:11:13AM +, Hemant Agrawal wrote: > Hi, >There was lengthy discussions w.r.t external mempool patches. > However, I am still finding usages issue with the agreed approach. > > The existing API to create packet mempool, "rte_pktmbuf_pool_create" does

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-27 Thread Jerin Jacob
On Wed, Jul 27, 2016 at 01:59:01AM -0700, Thomas Monjalon wrote: > > > Signed-off-by: Tomasz Kulasek > > > --- > > > +* In 16.11 ABI changes are plained: the ``rte_eth_dev`` structure will be > > > + extended with new function pointer ``tx_pkt_prep`` allowing > > > verification > > > + and

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-28 Thread Jerin Jacob
On Wed, Jul 27, 2016 at 05:33:01PM +, Ananyev, Konstantin wrote: > > > > -Original Message- > > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > > Sent: Wednesday, July 27, 2016 6:11 PM > > To: Thomas Monjalon > > Cc: Kulasek, Tom

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-28 Thread Jerin Jacob
On Wed, Jul 27, 2016 at 08:51:09PM +, Ananyev, Konstantin wrote: > > > > > On Wed, Jul 27, 2016 at 05:33:01PM +, Ananyev, Konstantin wrote: > > > > > > > > > > -----Original Message- > > > > From: Jerin Jacob [mailto:jerin.jaco

[dpdk-dev] [PATCH v2] doc: announce ABI change for mbuf structure

2016-07-28 Thread Jerin Jacob
On Wed, Jul 20, 2016 at 09:16:14AM +0200, Olivier Matz wrote: > For 16.11, the mbuf structure will be modified implying ABI breakage. > Some discussions already took place here: > http://www.dpdk.org/dev/patchwork/patch/12878/ > > Signed-off-by: Olivier Matz Acked-by: Jerin Jacob

[dpdk-dev] usages issue with external mempool

2016-07-28 Thread Jerin Jacob
On Thu, Jul 28, 2016 at 10:32:44AM +0200, Olivier MATZ wrote: Hi Olivier, > Hi Hemant, Jerin, > > On 07/27/2016 11:51 AM, Jerin Jacob wrote: > > On Tue, Jul 26, 2016 at 10:11:13AM +, Hemant Agrawal wrote: > > > > > I agree, To me, this is very bad. I ha

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-28 Thread Jerin Jacob
On Thu, Jul 28, 2016 at 10:36:07AM +, Ananyev, Konstantin wrote: > > If it does not cope up then it can skip tx'ing in the actual tx burst > > itself and move the "skipped" tx packets to end of the list in the tx > > burst so that application can take the action on "skipped" packet after > >

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-28 Thread Jerin Jacob
On Thu, Jul 28, 2016 at 01:01:16PM +, Ananyev, Konstantin wrote: > > > > > > > > > > Not according to proposal. It can't be too as application has no > > > > idea what PMD driver does with "prep" what is the implication on a > > > > HW if application does not > > > > > > Why application

[dpdk-dev] [PATCH v2] doc: announce ABI change for rte_eth_dev structure

2016-07-28 Thread Jerin Jacob
On Thu, Jul 28, 2016 at 04:52:45PM +0200, Thomas Monjalon wrote: > 2016-07-28 19:29, Jerin Jacob: > > Above things worries me, I wouldn't have cared if the changes are not comes > > in fastpath and I don't think this sort of issues will never get fixed any > > time >

[dpdk-dev] [PATCH] doc: announce driver name changes

2016-07-29 Thread Jerin Jacob
eful to have consistency in the names. > > Signed-off-by: Pablo de Lara Acked-by: Jerin Jacob > --- > doc/guides/rel_notes/deprecation.rst | 5 + > 1 file changed, 5 insertions(+) > > diff --git a/doc/guides/rel_notes/deprecation.rst > b/doc/guides/rel_notes/depr

[dpdk-dev] [PATCH] mbuf: extend rte_mbuf_prefetch_part* to support more prefetching methods

2016-06-01 Thread Jerin Jacob
On Wed, Jun 01, 2016 at 11:29:47AM +0800, Jianbo Liu wrote: > On 1 June 2016 at 03:28, Olivier MATZ wrote: > > Hi Jianbo, > > > > On 05/31/2016 05:06 AM, Jianbo Liu wrote: > >> Change the inline function to macro with parameters > >> > >> Signed-off-by: Jianbo Liu > >> > >> [...] > >> ---

[dpdk-dev] [PATCH v2] mempool: replace c memcpy code semantics with optimized rte_memcpy

2016-06-01 Thread Jerin Jacob
On Tue, May 31, 2016 at 11:05:30PM +0200, Olivier MATZ wrote: > Hi Jerin, Hi Olivier, > > >>> /* Add elements back into the cache */ > >>> - for (index = 0; index < n; ++index, obj_table++) > >>> - cache_objs[index] = *obj_table; > >>> + rte_memcpy(_objs[0], obj_table, sizeof(void *)

[dpdk-dev] [PATCH v2 02/20] thunderx/nicvf: add pmd skeleton

2016-06-01 Thread Jerin Jacob
On Tue, May 31, 2016 at 09:53:55AM -0700, Stephen Hemminger wrote: > On Sun, 29 May 2016 22:16:46 +0530 > Jerin Jacob wrote: > > > + > > +static struct itimerspec alarm_time = { > > + .it_interval = { > > + .tv_sec = 0, > > + .tv_nsec

[dpdk-dev] [PATCH v5 1/3] mempool: support external handler

2016-06-01 Thread Jerin Jacob
On Wed, Jun 01, 2016 at 11:46:20AM +0100, Hunt, David wrote: > > > On 5/31/2016 10:11 PM, Jerin Jacob wrote: > > On Tue, May 31, 2016 at 10:41:00PM +0200, Olivier MATZ wrote: > > > Hi, > > > > > > On 05/31/2016 06:03 PM, Jerin Jacob wrote: > > &g

[dpdk-dev] [PATCH] mbuf: extend rte_mbuf_prefetch_part* to support more prefetching methods

2016-06-02 Thread Jerin Jacob
On Thu, Jun 02, 2016 at 05:04:13PM +0800, Jianbo Liu wrote: > On 1 June 2016 at 14:00, Jerin Jacob > wrote: > > On Wed, Jun 01, 2016 at 11:29:47AM +0800, Jianbo Liu wrote: > >> On 1 June 2016 at 03:28, Olivier MATZ wrote: > >> > Hi Jianbo, > >> > &g

[dpdk-dev] [PATCH v2] mempool: replace c memcpy code semantics with optimized rte_memcpy

2016-06-02 Thread Jerin Jacob
On Thu, Jun 02, 2016 at 09:36:34AM +0200, Olivier MATZ wrote: > Hi Jerin, > > On 06/01/2016 09:00 AM, Jerin Jacob wrote: > > On Tue, May 31, 2016 at 11:05:30PM +0200, Olivier MATZ wrote: > >> Today, the objects pointers are reversed only in the get(). It m

[dpdk-dev] [PATCH v7 1/5] mempool: support external mempool operations

2016-06-03 Thread Jerin Jacob
On Thu, Jun 02, 2016 at 02:27:19PM +0100, David Hunt wrote: [snip] > /* create the internal ring if not already done */ > if ((mp->flags & MEMPOOL_F_RING_CREATED) == 0) { |> 1) May be RING can be replaced with some other higher abstraction name |> for the internal

[dpdk-dev] [PATCH v2] mempool: replace c memcpy code semantics with optimized rte_memcpy

2016-06-03 Thread Jerin Jacob
On Thu, Jun 02, 2016 at 11:16:16PM +0200, Olivier MATZ wrote: Hi Olivier, > This is probably more a measure of the pure CPU cost of the mempool > function, without considering the memory cache aspect. So, of course, > a real use-case test should be done to confirm or not that it increases > the

[dpdk-dev] [PATCH v7 1/5] mempool: support external mempool operations

2016-06-03 Thread Jerin Jacob
On Fri, Jun 03, 2016 at 11:28:14AM +0100, Hunt, David wrote: > > > > > static inline struct rte_mempool_ops * > > > rte_mempool_ops_get(int ops_index) > > > > > > return _mempool_ops_table.ops[ops_index]; > > |> 2) Considering "get" and "put" are the fast-path callbacks for > > |> pool-manger,

[dpdk-dev] [PATCH v3 00/20] DPDK PMD for ThunderX NIC device

2016-06-07 Thread Jerin Jacob
B+space occurrences in functions -- rebased to c8c33ad7f94c59d1c0676af0cfd61207b3e808db V2->V3 http://dpdk.org/dev/patchwork/patch/13060/ -- Changed polling infrastructure to use rte_eal_alarm* instead of timerfd_create API -- rebased to ca173a909538a2f1082cd0dcb4d778a97dab69c3 Jerin Jacob

[dpdk-dev] [PATCH v3 01/20] thunderx/nicvf/base: add hardware API for ThunderX nicvf inbuilt NIC

2016-06-07 Thread Jerin Jacob
Adds hardware specific API for ThunderX nicvf inbuilt NIC device under drivers/net/thunderx/nicvf/base directory. Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off-by: Zyta Szpak Signed-off-by: Slawomir Rosek Signed-off-by: Radoslaw Biernacki

[dpdk-dev] [PATCH v3 02/20] thunderx/nicvf: add pmd skeleton

2016-06-07 Thread Jerin Jacob
Introduce driver initialization and enable build infrastructure for nicvf pmd driver. By default, It is enabled only for defconfig_arm64-thunderx-* config as it is an inbuilt NIC device. Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off

[dpdk-dev] [PATCH v3 03/20] thunderx/nicvf: add link status and link update support

2016-06-07 Thread Jerin Jacob
Extended the nicvf_interrupt function to respond NIC_MBOX_MSG_BGX_LINK_CHANGE mbox message from PF and update struct rte_eth_link accordingly. Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off-by: Zyta Szpak Signed-off-by: Slawomir Rosek

[dpdk-dev] [PATCH v3 04/20] thunderx/nicvf: add get_reg and get_reg_length support

2016-06-07 Thread Jerin Jacob
Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off-by: Zyta Szpak Signed-off-by: Slawomir Rosek Signed-off-by: Radoslaw Biernacki --- drivers/net/thunderx/nicvf_ethdev.c | 30 ++ 1 file changed, 30 insertions

[dpdk-dev] [PATCH v3 05/20] thunderx/nicvf: add dev_configure support

2016-06-07 Thread Jerin Jacob
Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off-by: Zyta Szpak Signed-off-by: Slawomir Rosek Signed-off-by: Radoslaw Biernacki --- drivers/net/thunderx/nicvf_ethdev.c | 79 + 1 file changed, 79 insertions

[dpdk-dev] [PATCH v3 06/20] thunderx/nicvf: add dev_infos_get support

2016-06-07 Thread Jerin Jacob
Signed-off-by: Jerin Jacob Signed-off-by: Maciej Czekaj Signed-off-by: Kamil Rytarowski Signed-off-by: Zyta Szpak Signed-off-by: Slawomir Rosek Signed-off-by: Radoslaw Biernacki --- drivers/net/thunderx/nicvf_ethdev.c | 47 + drivers/net/thunderx

  1   2   3   4   5   6   >