Message ID | 1610717170-31279-13-git-send-email-juraj.linkes@pantheon.tech (mailing list archive) |
---|---|
State | Superseded, archived |
Delegated to: | Thomas Monjalon |
Headers | show |
Series | Arm build options rework | expand |
Context | Check | Description |
---|---|---|
ci/iol-testing | fail | Testing issues |
ci/iol-abi-testing | success | Testing PASS |
ci/iol-mellanox-Performance | success | Performance Testing PASS |
ci/Intel-compilation | success | Compilation OK |
ci/iol-mellanox-Functional | success | Functional Testing PASS |
ci/iol-intel-Performance | success | Performance Testing PASS |
ci/iol-intel-Functional | success | Functional Testing PASS |
ci/iol-broadcom-Functional | success | Functional Testing PASS |
ci/checkpatch | success | coding style OK |
15/01/2021 14:26, Juraj Linkeš: > Fix the implementer and part number of DPAA and ARMADA SoCs. > The current values of 16 cores and 1 NUMA node don't cover all SoCs from > the Arm implementer, e.g. Taishan 2280 has 64 cores and 4 NUMA nodes. > Increase these to 64 and 4 to widen the coverage. > Add configuration to SoC options where smaller values are needed. > > Fixes: 6ec78c2463ac ("build: add meson support for dpaaX platforms") > Cc: hemant.agrawal@nxp.com > Fixes: dd1cd845c102 ("config: add Marvell ARMADA based on armv8-a") > Cc: lironh@marvell.com > Fixes: d97108a33231 ("config: change defaults of armv8") > Cc: yskoh@mellanox.com > > Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech> > Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> We are missing acks for Broacom, Marvell, Nvidia and NXP SoC values. Repeating clearly: we NEED REVIEW TODAY from all of you!
Reviewed-by: Liron Himi <lironh@marvell.com> -----Original Message----- From: Thomas Monjalon <thomas@monjalon.net> Sent: Monday, 18 January 2021 15:45 To: Juraj Linkeš <juraj.linkes@pantheon.tech> Cc: bruce.richardson@intel.com; Ruifeng.Wang@arm.com; Honnappa.Nagarahalli@arm.com; Phil.Yang@arm.com; vcchunga@amazon.com; Dharmik.Thakkar@arm.com; jerinjacobk@gmail.com; hemant.agrawal@nxp.com; ajit.khaparde@broadcom.com; ferruh.yigit@intel.com; aboyer@pensando.io; dev@dpdk.org; Liron Himi <lironh@marvell.com>; rasland@nvidia.com; viacheslavo@nvidia.com Subject: [EXT] Re: [dpdk-dev] [PATCH v15 12/12] config: fix Arm implementer and its SoCs External Email ---------------------------------------------------------------------- 15/01/2021 14:26, Juraj Linkeš: > Fix the implementer and part number of DPAA and ARMADA SoCs. > The current values of 16 cores and 1 NUMA node don't cover all SoCs > from the Arm implementer, e.g. Taishan 2280 has 64 cores and 4 NUMA nodes. > Increase these to 64 and 4 to widen the coverage. > Add configuration to SoC options where smaller values are needed. > > Fixes: 6ec78c2463ac ("build: add meson support for dpaaX platforms") > Cc: hemant.agrawal@nxp.com > Fixes: dd1cd845c102 ("config: add Marvell ARMADA based on armv8-a") > Cc: lironh@marvell.com > Fixes: d97108a33231 ("config: change defaults of armv8") > Cc: yskoh@mellanox.com > > Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech> > Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> We are missing acks for Broacom, Marvell, Nvidia and NXP SoC values. Repeating clearly: we NEED REVIEW TODAY from all of you!
>-----Original Message----- >From: dev <dev-bounces@dpdk.org> On Behalf Of Juraj Linkeš >Sent: Friday, January 15, 2021 6:56 PM >To: bruce.richardson@intel.com; Ruifeng.Wang@arm.com; >Honnappa.Nagarahalli@arm.com; Phil.Yang@arm.com; >vcchunga@amazon.com; Dharmik.Thakkar@arm.com; >jerinjacobk@gmail.com; hemant.agrawal@nxp.com; >ajit.khaparde@broadcom.com; ferruh.yigit@intel.com; >aboyer@pensando.io >Cc: dev@dpdk.org; Juraj Linkeš <juraj.linkes@pantheon.tech>; Liron >Himi <lironh@marvell.com>; yskoh@mellanox.com >Subject: [EXT] [dpdk-dev] [PATCH v15 12/12] config: fix Arm >implementer and its SoCs > >External Email > >---------------------------------------------------------------------- >Fix the implementer and part number of DPAA and ARMADA SoCs. >The current values of 16 cores and 1 NUMA node don't cover all SoCs >from >the Arm implementer, e.g. Taishan 2280 has 64 cores and 4 NUMA >nodes. >Increase these to 64 and 4 to widen the coverage. >Add configuration to SoC options where smaller values are needed. > >Fixes: 6ec78c2463ac ("build: add meson support for dpaaX platforms") >Cc: hemant.agrawal@nxp.com >Fixes: dd1cd845c102 ("config: add Marvell ARMADA based on armv8-a") >Cc: lironh@marvell.com >Fixes: d97108a33231 ("config: change defaults of armv8") >Cc: yskoh@mellanox.com > >Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech> >Reviewed-by: Honnappa Nagarahalli ><honnappa.nagarahalli@arm.com> Acked-by: Pavan Nikhilesh <pbhagavatula@marvell.com> >--- > config/arm/meson.build | 60 +++++++++++++++++++---------------------- >- > 1 file changed, 27 insertions(+), 33 deletions(-) > >diff --git a/config/arm/meson.build b/config/arm/meson.build >index eb91e80ff..f6cd7a5e0 100644 >--- a/config/arm/meson.build >+++ b/config/arm/meson.build >@@ -60,7 +60,8 @@ part_number_config_arm = { > ['RTE_MACHINE', '"neoverse-n1"'], > ['RTE_ARM_FEATURE_ATOMICS', true], > ['RTE_MAX_MEM_MB', 1048576], >- ['RTE_MAX_LCORE', 80] >+ ['RTE_MAX_LCORE', 80], >+ ['RTE_MAX_NUMA_NODES', 1] > ] > }, > '0xd49': { >@@ -68,7 +69,8 @@ part_number_config_arm = { > 'flags': [ > ['RTE_MACHINE', '"neoverse-n2"'], > ['RTE_ARM_FEATURE_ATOMICS', true], >- ['RTE_MAX_LCORE', 64] >+ ['RTE_MAX_LCORE', 64], >+ ['RTE_MAX_NUMA_NODES', 1] > ] > } > } >@@ -78,8 +80,8 @@ implementer_arm = { > ['RTE_MACHINE', '"armv8a"'], > ['RTE_USE_C11_MEM_MODEL', true], > ['RTE_CACHE_LINE_SIZE', 64], >- ['RTE_MAX_LCORE', 16], >- ['RTE_MAX_NUMA_NODES', 1] >+ ['RTE_MAX_LCORE', 64], >+ ['RTE_MAX_NUMA_NODES', 4] > ], > 'part_number_config': part_number_config_arm > } >@@ -147,38 +149,12 @@ implementer_ampere = { > } > } > >-implementer_marvell = { >- 'description': 'Marvell ARMADA', >- 'flags': [ >- ['RTE_MACHINE', '"armv8a"'], >- ['RTE_CACHE_LINE_SIZE', 64], >- ['RTE_MAX_LCORE', 16], >- ['RTE_MAX_NUMA_NODES', 1] >- ], >- 'part_number_config': part_number_config_arm >-} >- >-implementer_dpaa = { >- 'description': 'NXP DPAA', >- 'flags': [ >- ['RTE_MACHINE', '"dpaa"'], >- ['RTE_LIBRTE_DPAA2_USE_PHYS_IOVA', false], >- ['RTE_USE_C11_MEM_MODEL', true], >- ['RTE_CACHE_LINE_SIZE', 64], >- ['RTE_MAX_LCORE', 16], >- ['RTE_MAX_NUMA_NODES', 1] >- ], >- 'part_number_config': part_number_config_arm >-} >- > ## Arm implementers (ID from MIDR in Arm Architecture Reference >Manual) > implementers = { > 'generic': implementer_generic, > '0x41': implementer_arm, > '0x43': implementer_cavium, >- '0x50': implementer_ampere, >- '0x56': implementer_marvell, >- 'dpaa': implementer_dpaa >+ '0x50': implementer_ampere > } > > # soc specific aarch64 flags have the highest priority >@@ -191,8 +167,12 @@ soc_generic = { > > soc_armada = { > 'description': 'Marvell ARMADA', >- 'implementer': '0x56', >+ 'implementer': '0x41', > 'part_number': '0xd08', >+ 'flags': [ >+ ['RTE_MAX_LCORE', 16], >+ ['RTE_MAX_NUMA_NODES', 1] >+ ], > 'numa': false, > 'disabled_drivers': ['bus/dpaa', 'bus/fslmc', 'common/dpaax'] > } >@@ -201,13 +181,23 @@ soc_bluefield = { > 'description': 'NVIDIA BlueField', > 'implementer': '0x41', > 'part_number': '0xd08', >+ 'flags': [ >+ ['RTE_MAX_LCORE', 16], >+ ['RTE_MAX_NUMA_NODES', 1] >+ ], > 'numa': false > } > > soc_dpaa = { > 'description': 'NXP DPAA', >- 'implementer': 'dpaa', >+ 'implementer': '0x41', > 'part_number': '0xd08', >+ 'flags': [ >+ ['RTE_MACHINE', '"dpaa"'], >+ ['RTE_LIBRTE_DPAA2_USE_PHYS_IOVA', false], >+ ['RTE_MAX_LCORE', 16], >+ ['RTE_MAX_NUMA_NODES', 1] >+ ], > 'numa': false > } > >@@ -251,6 +241,10 @@ soc_octeontx2 = { > soc_stingray = { > 'description': 'Broadcom Stingray', > 'implementer': '0x41', >+ 'flags': [ >+ ['RTE_MAX_LCORE', 16], >+ ['RTE_MAX_NUMA_NODES', 1] >+ ], > 'part_number': '0xd08', > 'numa': false > } >-- >2.20.1
Resend the letter due to SMTP issues. > Fix the implementer and part number of DPAA and ARMADA SoCs. > The current values of 16 cores and 1 NUMA node don't cover all SoCs > from the Arm implementer, e.g. Taishan 2280 has 64 cores and 4 NUMA nodes. > Increase these to 64 and 4 to widen the coverage. > Add configuration to SoC options where smaller values are needed. > > Fixes: 6ec78c2463ac ("build: add meson support for dpaaX platforms") > Cc: hemant.agrawal@nxp.com > Fixes: dd1cd845c102 ("config: add Marvell ARMADA based on armv8-a") > Cc: lironh@marvell.com > Fixes: d97108a33231 ("config: change defaults of armv8") > Cc: yskoh@mellanox.com > > Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech> > Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> It seems nVidia Bluefield configuration is preserved, in this part: Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
diff --git a/config/arm/meson.build b/config/arm/meson.build index eb91e80ff..f6cd7a5e0 100644 --- a/config/arm/meson.build +++ b/config/arm/meson.build @@ -60,7 +60,8 @@ part_number_config_arm = { ['RTE_MACHINE', '"neoverse-n1"'], ['RTE_ARM_FEATURE_ATOMICS', true], ['RTE_MAX_MEM_MB', 1048576], - ['RTE_MAX_LCORE', 80] + ['RTE_MAX_LCORE', 80], + ['RTE_MAX_NUMA_NODES', 1] ] }, '0xd49': { @@ -68,7 +69,8 @@ part_number_config_arm = { 'flags': [ ['RTE_MACHINE', '"neoverse-n2"'], ['RTE_ARM_FEATURE_ATOMICS', true], - ['RTE_MAX_LCORE', 64] + ['RTE_MAX_LCORE', 64], + ['RTE_MAX_NUMA_NODES', 1] ] } } @@ -78,8 +80,8 @@ implementer_arm = { ['RTE_MACHINE', '"armv8a"'], ['RTE_USE_C11_MEM_MODEL', true], ['RTE_CACHE_LINE_SIZE', 64], - ['RTE_MAX_LCORE', 16], - ['RTE_MAX_NUMA_NODES', 1] + ['RTE_MAX_LCORE', 64], + ['RTE_MAX_NUMA_NODES', 4] ], 'part_number_config': part_number_config_arm } @@ -147,38 +149,12 @@ implementer_ampere = { } } -implementer_marvell = { - 'description': 'Marvell ARMADA', - 'flags': [ - ['RTE_MACHINE', '"armv8a"'], - ['RTE_CACHE_LINE_SIZE', 64], - ['RTE_MAX_LCORE', 16], - ['RTE_MAX_NUMA_NODES', 1] - ], - 'part_number_config': part_number_config_arm -} - -implementer_dpaa = { - 'description': 'NXP DPAA', - 'flags': [ - ['RTE_MACHINE', '"dpaa"'], - ['RTE_LIBRTE_DPAA2_USE_PHYS_IOVA', false], - ['RTE_USE_C11_MEM_MODEL', true], - ['RTE_CACHE_LINE_SIZE', 64], - ['RTE_MAX_LCORE', 16], - ['RTE_MAX_NUMA_NODES', 1] - ], - 'part_number_config': part_number_config_arm -} - ## Arm implementers (ID from MIDR in Arm Architecture Reference Manual) implementers = { 'generic': implementer_generic, '0x41': implementer_arm, '0x43': implementer_cavium, - '0x50': implementer_ampere, - '0x56': implementer_marvell, - 'dpaa': implementer_dpaa + '0x50': implementer_ampere } # soc specific aarch64 flags have the highest priority @@ -191,8 +167,12 @@ soc_generic = { soc_armada = { 'description': 'Marvell ARMADA', - 'implementer': '0x56', + 'implementer': '0x41', 'part_number': '0xd08', + 'flags': [ + ['RTE_MAX_LCORE', 16], + ['RTE_MAX_NUMA_NODES', 1] + ], 'numa': false, 'disabled_drivers': ['bus/dpaa', 'bus/fslmc', 'common/dpaax'] } @@ -201,13 +181,23 @@ soc_bluefield = { 'description': 'NVIDIA BlueField', 'implementer': '0x41', 'part_number': '0xd08', + 'flags': [ + ['RTE_MAX_LCORE', 16], + ['RTE_MAX_NUMA_NODES', 1] + ], 'numa': false } soc_dpaa = { 'description': 'NXP DPAA', - 'implementer': 'dpaa', + 'implementer': '0x41', 'part_number': '0xd08', + 'flags': [ + ['RTE_MACHINE', '"dpaa"'], + ['RTE_LIBRTE_DPAA2_USE_PHYS_IOVA', false], + ['RTE_MAX_LCORE', 16], + ['RTE_MAX_NUMA_NODES', 1] + ], 'numa': false } @@ -251,6 +241,10 @@ soc_octeontx2 = { soc_stingray = { 'description': 'Broadcom Stingray', 'implementer': '0x41', + 'flags': [ + ['RTE_MAX_LCORE', 16], + ['RTE_MAX_NUMA_NODES', 1] + ], 'part_number': '0xd08', 'numa': false }