'__sync' builtins are deprecated, enable '__atomic' builtins for
generic atomic operations.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Tested-by: Phil Yang
---
lib/librte_eal/common/include/generic/rte_atomic.h | 80 ++
1 file changed, 80 inserti
'__sync' builtins are deprecated, use '__atomic' builtins instead for
packet_ordering.
Fixes: 850f373 ("examples/packet_ordering: new sample app")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Ruifeng Wang
---
examples/packet_ordering/main.c | 27
Keep only single config option RTE_USE_C11_MEM_MODEL for C11 memory
model, so all modules can leverage C11 atomic extension by enable this
option.
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Acked-by: Jerin Jacob
---
config/arm/meson.build
the values
being synced before updating fifo_write and fifo_read.
Fixes: 3fc5ca2 ("kni: initial import")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Reviewed-by: Ola Liljedahl
Reviewed-by: Jerin Jacob
---
lib/librte_kni/rte_kni_f
Adding memory barrier to make sure the values being synced
before updating fifo_write in kni_fifo_put and fifo_read in
kni_fifo_get.
Fixes: 3fc5ca2 ("kni: initial import")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
---
kernel/linux/kni/
Syncing the values by adding c11 atomic memory barriers to make sure
the values being synced before updating fifo_write and fifo_read.
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Reviewed-by: Ola Liljedahl
---
.../linuxapp/eal/include/exec-env
iled
Fix by allocate the devices port to the first available socket or the
socket configured in port-numa-config.
Fixes: 487f9a5 ("app/testpmd: fix NUMA structures initialization")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
app/test-pmd/testpmd.c | 29 +
Once the lcore list setting excluded the socket which physic device
attached, it will cause failure. Meanwhile, it will disable Testpmd
cross NUMA scenario.
Fixes: dbfb8ec ("app/testpmd: optimize mbuf pool allocation")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
app/test-pmd
Once the lcore list setting excluded the socket which physic device
attached, it will cause failure. Meanwhile, it will disable Testpmd
cross NUMA scenario.
Fixes: dbfb8ec ("app/testpmd: optimize mbuf pool allocation")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
app/test-pmd
ggested-by: Yigit Ferruh
Signed-off-by: Phil Yang
---
app/test-pmd/parameters.c | 14 ++
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index 4a4debb..38b4197 100644
--- a/app/test-pmd/parameters.c
+++ b/ap
Need to release the port and the ring resources after test. Otherwise,
it will cause failure to allocate memory when reentry the test.
Fixes: ea764af ("app/test: add performance test for ring driver")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
test/test/test_pmd_ring_
Need to release the port and the ring resources after test. Otherwise,
it will cause failure to allocate memory when reentry the test.
Fixes: 4ea3801 ("app/test: fix ring unit test")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
test/test/test_pmd_ri
Need to release the port and the ring resources after test. Otherwise,
it will cause failure to allocate memory when reentry the test.
Fixes: 4ea3801 ("app/test: fix ring unit test")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
test/test/test_pmd_ri
Since the tested null device has no capacity of HW CRC offload,
disable it for the link bonding rssconf test by default. Otherwise,
it will cause test unexpected failure.
Fixes: b219c8c("test: enable HW CRC strip by default")
Signed-off-by: Phil Yang
---
test/test/test_link_bonding
Since the tested virtual device has no capacity of HW CRC offload,
disable it for the link bonding test by default. Otherwise, it will
cause test unexpected failure.
Fixes: b219c8c("test: enable HW CRC strip by default")
Signed-off-by: Phil Yang
---
test/test/test_link_bond
Add DEV_RX_OFFLOAD_CRC_STRIP to virtual drivers since they don't
use CRC at all, when an application requires this offload virtual
PMDs should not return error.
Fixes: b219c8c("test: enable HW CRC strip by default")
Signed-off-by: Phil Yang
---
test/test/virtual_pmd.c | 1 +
1
Hi Ferruh,
Thanks for you patch.
> -Original Message-
> From: Ferruh Yigit
> Sent: Monday, July 2, 2018 6:00 PM
> To: dev-boun...@dpdk.org; dev@dpdk.org
> Cc: nd ; Phil Yang
> Subject: Re: [dpdk-dev] [PATCH 1/2] test/link_bonding: disable HW CRC strip by
> defaul
on by socket id")
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index ee48db2..a56af2b 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -47
TRLEN];
char buf[SOCKET_MEM_STRLEN];> /* to avoid copying string onto itself */
Thanks,
Phil Yang
> -Original Message-
> From: Thomas Monjalon
> Sent: Thursday, April 26, 2018 1:07 AM
> To: Phil Yang
> Cc: dev@dpdk.org; nd ; anatoly.bura...@intel.com; Herbert
>
on by socket id")
Signed-off-by: Phil Yang
Acked-by: Gavin Hu
---
app/test-pmd/testpmd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index ee48db2..a56af2b 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd
to make sure
the values being synced before updating fifo_write and fifo_read.
Fixes: 3fc5ca2 ("kni: initial import")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
---
.../linuxapp/eal/include/exec-env/rte_kni_common.h | 5
lib/librte_kni/rte_
Keep only single config option RTE_USE_C11_MEM_MODEL for C11 memory
model, so all modules can leverage C11 atomic extension by enable this
option.
Fixes: 39368eb ("ring: introduce C11 memory model barrier option")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by
Adding memory barrier to make sure the values being synced
before updating fifo_write in kni_fifo_put and fifo_read in
kni_fifo_get.
Fixes: 3fc5ca2 ("kni: initial import")
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
---
kernel/linux/kni/
Enable native/cross compiling for Cortex-A55 and Cortex-A76 on meson.
Signed-off-by: Phil Yang
Reviewed-by: Ola Liljedahl
Reviewed-by: Gavin Hu
---
config/arm/arm64_armv8_linuxapp_gcc | 2 ++
config/arm/meson.build | 2 ++
2 files changed, 4 insertions(+)
diff --git a/config/arm
1. test_memzone_basic: No need to free a NULL memzone. It will cause test
termination.
2. test_memzone_free: Out of mz[RTE_MAX_MEMZONE] memory bound while
reserving memzone for mz. It will flush variable i. Fix by extend to
mz[RTE_MAX_MEMZONE + 1].
Signed-off-by: Phil Yang
---
test/test
No need to free a NULL memzone. It will cause test
termination.
Signed-off-by: Phil Yang
---
test/test/test_memzone.c | 4
1 file changed, 4 deletions(-)
diff --git a/test/test/test_memzone.c b/test/test/test_memzone.c
index 6e80977..9c20172 100644
--- a/test/test/test_memzone.c
+++ b
an the maximum
test memzone_reserve flags
1GB Huge pages available
Fail memzone free
Test Failed
Phil Yang (2):
test/memzone: Fix test_memzone_basic issue
test/memzone: Fix test_memzone_free issue
test/test/test_memzone.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
--
2.7.4
When reserving memzone for mz[], it will out of mz[RTE_MAX_MEMZONE] memory
bound after the counter reached to RTE_MAX_MEMZONE. It will flush the counter's
memory and lead to mz[] memory cannot be freed.
Fixd by extend to mz[RTE_MAX_MEMZONE + 1].
Signed-off-by: Phil Yang
---
test
No need to free a NULL memzone. It will cause test
termination.
Signed-off-by: Phil Yang
---
test/test/test_memzone.c | 4
1 file changed, 4 deletions(-)
diff --git a/test/test/test_memzone.c b/test/test/test_memzone.c
index 6e80977..9c20172 100644
--- a/test/test/test_memzone.c
+++ b
When reserving memzone for mz[], it will out of mz[RTE_MAX_MEMZONE] memory
bound after the counter reached to RTE_MAX_MEMZONE. It will flush the
counter's memory and lead to mz[] memory cannot be freed.
Fixd by extend to mz[RTE_MAX_MEMZONE + 1].
Signed-off-by: Phil Yang
---
test
an the maximum
test memzone_reserve flags
1GB Huge pages available
Fail memzone free
Test Failed
Phil Yang (2):
test/memzone: Fix test_memzone_basic issue
test/memzone: Fix test_memzone_free issue
test/test/test_memzone.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
--
2.7.4
Hi Anatoly,
Thanks for your comments. Updated. Please review the version 2.
Thanks,
Phil Yang
> -Original Message-
> From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
> Sent: Saturday, January 13, 2018 1:44 AM
> To: Phil Yang ; dev@dpdk.org
> Cc: nd ; Jianbo Liu
While running testpmd in container with stats-period option, it can't
quit normally after received SIGINT.
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index e0
While running testpmd in container with stats-period option, it can't
quit normally after received SIGINT.
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index e0
While running testpmd in container with stats-period option, it can't
quit normally after received SIGINT.
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index e0
In container, the process cannot be terminated by SIGINT/SIGTERM when
execute with 'stats-period' option.
Fixed by adding a flag to exit stats period loop after received SIGINT/SIGTERM.
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 13 -
1 file changed, 12 insert
In container, the process cannot be terminated by SIGINT/SIGTERM when
execute with 'stats-period' option.
Fixed by adding a flag to exit stats period loop after received either
SIGINT or SIGTERM.
Signed-off-by: Phil Yang
---
app/test-pmd/testpmd.c | 13 -
1 file c
eal/linuxapp/eal/eal.c:957
#12 0xaab1e004 in main (argc=5, argv=0xfb58) at
test.c:86
...
Phil Yang (1):
test/memzone: fix incorrect result judging criteria
test/test/test_memzone.c | 141 +--
1 file changed, 74 insertions(+), 67 deletions(-)
--
2.7.4
remained at the end.
Fixes: 71330483a193 ("test/memzone: fix memory leak")
Signed-off-by: Phil Yang
---
test/test/test_memzone.c | 141 +--
1 file changed, 74 insertions(+), 67 deletions(-)
diff --git a/test/test/test_memzone.c b
on in the header file.
>
> Fixes: 134975073af3 ("lib: remove unnecessary pointer cast")
>
> Signed-off-by: Pavan Nikhilesh
Acked-by: Phil Yang
> ---
>
> This was already fixed in a previous patch by Olivier commit id
> f82f705b635d31a63446a16bc4526dbebf29
about the memzone used in memzone autotest. It is rough but it
seems more reliable. 😊
Thanks,
Phil Yang
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Anatoly Burakov
> Sent: Saturday, January 27, 2018 1:41 AM
> To: dev@dpdk.org
> Cc: radoslaw.
That is OK for me. Thanks for your comments.
Thanks,
Phil Yang
> -Original Message-
> From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
> Sent: Wednesday, January 31, 2018 6:05 PM
> To: Phil Yang ; dev@dpdk.org
> Cc: radoslaw.bierna...@linaro.org; sta...@dpdk.org
Since RTE_MAX_NUMA_NODES is configurable, the existing socket number
could greater than RTE_MAX_NUMA_NODES. Optimize test case to cover this
situation.(i.e RTE_MAX_NUMA_NODES=1)
Fixes: 45f1b6e8680a ('app: add new tests on eal flags')
Signed-off-by: Phil Yang
---
test/test/test_eal_f
- Ro Pkts tx failed: 0
- Pkts transmitted w/o reorder:0
- Pkts tx failed w/o reorder: 0
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
doc/guides/sample_app_ug/packet_ordering.rst | 4 ++-
examples/packet_ordering/main
C11_MEM_MODEL is enabled.
Phil Yang (3):
packet_ordering: add statistics for each worker thread
test/distributor: replace sync builtins with atomic builtins
test/ring_perf: replace sync builtins with atomic builtins
app/test/test_distributor.c | 18 +-
app/test
f_autotest with this patch ***
Cache line switch test ===
Time for 33554432 iterations = 1251715496 ticks
Ticks per iteration = 37
Less ticks needed for the cache line switch test. It got 17% of
performance improvement.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Ruifeng Wan
ing
operations performance.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Joyce Kong
Reviewed-by: Dharmik Thakkar
---
app/test/test_ring_perf.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/app/test/test_ring_perf.c b/app/test/test_ring_per
Honnappa Nagarahalli
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
doc/guides/sample_app_ug/packet_ordering.rst | 4 ++-
examples/packet_ordering/main.c | 50 +---
2 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/doc/guides/sample_app_ug/packet
f_autotest with this patch ***
Cache line switch test ===
Time for 33554432 iterations = 1251715496 ticks
Ticks per iteration = 37
Less ticks needed for the cache line switch test. It got 17% of
performance improvement.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Ruifeng Wan
. Reimplement test_ring_perf with atomic one-way barrier, if
C11_MEM_MODEL is enabled.
v1:
Reimplement packet_ordering with __atomic one-way barrier.
Phil Yang (3):
packet_ordering: add statistics for each worker thread
test/distributor: replace sync builtins with atomic builtins
test/ring_perf
ing
operations performance.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Joyce Kong
Reviewed-by: Dharmik Thakkar
---
app/test/test_ring_perf.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/app/test/test_ring_perf.c b/app/test/test_ring_per
Honnappa Nagarahalli
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
doc/guides/sample_app_ug/packet_ordering.rst | 4 ++-
examples/packet_ordering/main.c | 50 +---
2 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/doc/guides/sample_app_ug/packet
. Reimplement test_distributor with atomic one-way barrier, if
C11_MEM_MODEL is enabled.
3. Reimplement test_ring_perf with atomic one-way barrier, if
C11_MEM_MODEL is enabled.
v1:
Reimplement packet_ordering with __atomic one-way barrier.
Phil Yang (3):
packet_ordering: add statistics for each worker
ing
operations performance.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Joyce Kong
Reviewed-by: Dharmik Thakkar
---
app/test/test_ring_perf.c | 12 ++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/app/test/test_ring_perf.c b/app/test/test_ring_per
f_autotest with this patch ***
Cache line switch test ===
Time for 33554432 iterations = 1251715496 ticks
Ticks per iteration = 37
Less ticks needed for the cache line switch test. It got 17% of
performance improvement.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Ruifeng Wan
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Friday, June 19, 2020 2:26 AM
> To: Carrillo, Erik G ; Phil Yang
> ; dev@dpdk.org
> Cc: d...@linux.vnet.ibm.com; Ruifeng Wang ;
> Dharmik Thakkar ; nd ;
> sta...@dpdk.org; Honnappa Nagarahalli ;
> nd
> -Original Message-
> From: Jerin Jacob
> Sent: Wednesday, July 1, 2020 7:22 PM
> To: Phil Yang
> Cc: Honnappa Nagarahalli ; Carrillo, Erik G
> ; dev@dpdk.org; d...@linux.vnet.ibm.com;
> Ruifeng Wang ; Dharmik Thakkar
> ; nd ; sta...@dpdk.org
> Subject
c11 atomics with RELAXED ordering to prevent confliction.
Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
Cc: erik.g.carri...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carril
There is no thread will access these impl_opaque data after timer
canceled. When new timer armed, it got refilled. So the cleanup
process is unnecessary.
Signed-off-by: Phil Yang
---
lib/librte_eventdev/rte_event_timer_adapter.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/lib
threads. Then the atomic CAS operation is needed.
Use the c11 atomic CAS instead of the generic rte_atomic operations
to avoid the unnecessary barrier on aarch64.
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
v2:
1. Make the code comments more accurate. (Erik)
2
synchronize the opaque data between timer arm and cancel threads.
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
v2:
1. Removed implementation-specific opaque data cleanup code.
2. Replaced thread fence with atomic ACQURE/RELEASE ordering on state access.
lib
Hi Jerin,
Your insight would be much appreciated.
Thanks,
Phil
> -Original Message-
> From: Ruifeng Wang
> Sent: Wednesday, May 27, 2020 4:29 PM
> To: Phil Yang ; dev@dpdk.org
> Cc: tho...@monjalon.net; david.march...@redhat.com;
> jer...@marvell.com; Honnappa Nag
Hi Lijun,
Some comments inline.
> -Original Message-
> From: dev On Behalf Of Lijun Ou
> Sent: Wednesday, July 1, 2020 3:43 PM
> To: wenzhuo...@intel.com; beilei.x...@intel.com;
> bernard.iremon...@intel.com; ferruh.yi...@intel.com
> Cc: dev@dpdk.org; linux...@huawei.com
> Subject: [dpdk
>
> IMPORTANT NOTICE: The contents of this email and any attachments are
> confidential and may also be privileged. If you are not the intended
> recipient,
> please notify the sender immediately and do not disclose the contents to any
> other person, use it for any purpose, or store or copy the
> -Original Message-
> From: David Marchand
> Sent: Friday, July 3, 2020 11:39 PM
> To: Phil Yang
> Cc: dev ; Olivier Matz ; David
> Christensen ; Honnappa Nagarahalli
> ; Ruifeng Wang
> ; nd
> Subject: Re: [dpdk-dev] [PATCH] mbuf: use c11 atomics for refcnt
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, July 6, 2020 6:04 PM
> To: Phil Yang
> Cc: erik.g.carri...@intel.com; dev@dpdk.org; jer...@marvell.com; Honnappa
> Nagarahalli ; d...@linux.vnet.ibm.com;
> Ruifeng Wang ; Dharmik Thakkar
> ; nd ;
> d
llanox.com;
> shah...@mellanox.com; viachesl...@mellanox.com; Honnappa Nagarahalli
> ; Phil Yang ;
> Ruifeng Wang
> Cc: dev@dpdk.org; nd
> Subject: [PATCH v2 1/6] lib/eal: add a common wrapper for restricted
> pointers
>
> The 'restrict' keyword is recognized in C99, while ty
llanox.com;
> shah...@mellanox.com; viachesl...@mellanox.com; Honnappa Nagarahalli
> ; Phil Yang ;
> Ruifeng Wang
> Cc: dev@dpdk.org; nd
> Subject: [PATCH v2 4/6] net/i40e: replace restrict with rte restrict
>
> '__rte_restrict' is a common wrapper for restricted pointe
llanox.com;
> shah...@mellanox.com; viachesl...@mellanox.com; Honnappa Nagarahalli
> ; Phil Yang ;
> Ruifeng Wang
> Cc: dev@dpdk.org; nd
> Subject: [PATCH v2 5/6] examples/performance-thread: replace restrict with
> wrapper
>
> '__rte_restrict' is a common wrapper for
llanox.com;
> shah...@mellanox.com; viachesl...@mellanox.com; Honnappa Nagarahalli
> ; Phil Yang ;
> Ruifeng Wang
> Cc: dev@dpdk.org; nd
> Subject: [PATCH v2 6/6] net/mlx5: replace restrict keyword with rte restrict
>
> The 'restrict' keyword is recognized in C99, which might ha
style.
4. flag __sync_xxx built-ins in new patches.
5. wraps up compiler atomic built-ins
6. move the changes of libraries which make use of c11 atomic APIs out of this
patchset.
v3:
add libatomic dependency for 32-bit clang
v2:
1. fix Clang '-Wincompatible-pointer-types' WARNING.
2. fix ty
__atomic_thread_fence(__ATOMIC_SEQ_CST) is quite expensive
for SMP case. Flag the new code which use __atomic_thread_fence API.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
---
devtools/checkpatches.sh | 40
1 file changed, 40 insertions(+)
diff --git a/devtools
Add deprecating the generic rte_atomic_xx APIs to c11 atomic built-ins
guide and examples.
Signed-off-by: Phil Yang
Signed-off-by: Honnappa Nagarahalli
---
doc/guides/prog_guide/writing_efficient_code.rst | 139 ++-
1 file changed, 138 insertions(+), 1 deletion(-)
diff
Provide a wrapper for __atomic_thread_fence built-in to support
optimized code for __ATOMIC_SEQ_CST memory order for x86 platforms.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Phil Yang
Reviewed-by: Ola Liljedahl
Acked-by: Konstantin Ananyev
---
lib/librte_eal/arm/include/rte_atomic_32
Add the maintainership of C11 atomics code. Different maintainers focus
on different platforms C11 atomics.
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
---
MAINTAINERS | 4
1 file changed, 4 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 27fcd6d..3682d2a 100644
Use C11 atomics with explicit ordering instead of rte_atomic ops which
enforce unnecessary barriers on aarch64.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
---
v2:
Fix ABI issue: revert the rte_mbuf_ext_shared_info struct refcnt field
to refcnt_atomic.
lib/librte_mbuf/rte_mbuf.c
c11 atomics with RELAXED ordering to prevent confliction.
Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
Cc: erik.g.carri...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carril
There is no thread will access these impl_opaque data after timer
canceled. When new timer armed, it got refilled. So the cleanup
process is unnecessary.
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
---
lib/librte_eventdev/rte_event_timer_adapter.c | 2 --
1 file changed, 2 deletions
threads. Then the atomic CAS operation is needed.
Use the C11 atomic CAS instead of the generic rte_atomic operations
to avoid the unnecessary barrier on aarch64.
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carrillo
---
v2:
1. Make the code
.
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carrillo
---
v3:
Fix ABI issue: revert to 'volatile enum rte_event_timer_state type state'.
v2:
1. Removed implementation-specific opaque data cleanup code.
2. Replaced thread
c11 atomics with RELAXED ordering to prevent confliction.
Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
Cc: erik.g.carri...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carril
.
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel Carrillo
---
v4:
1. Fix typo.
2. Cc to stable release. (Honnappa)
v3:
Fix ABI issue: revert to 'volatile enum rte_event_timer_state type state'.
v2:
threads. Then the atomic compare-and-swap
operation is needed.
Use the C11 atomics instead of the generic rte_atomic operations to
avoid the unnecessary barrier on aarch64.
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Erik Gabriel
There is no thread will access these impl_opaque data after timer
canceled. When new timer armed, it got refilled. So the cleanup
process is unnecessary.
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Dharmik Thakkar
---
v4:
Cc to stable release. (Honnappa)
lib/librte_eventdev
> -Original Message-
> From: Jerin Jacob
> Sent: Tuesday, July 7, 2020 10:30 PM
> To: Phil Yang
> Cc: tho...@monjalon.net; Erik Gabriel Carrillo ;
> dpdk-dev ; jer...@marvell.com; Honnappa Nagarahalli
> ; David Christensen
> ; Ruifeng Wang ;
> Dharmik Thak
> -Original Message-
> From: Stephen Hemminger
> Sent: Wednesday, July 8, 2020 1:13 AM
> To: Phil Yang
> Cc: david.march...@redhat.com; dev@dpdk.org; d...@linux.vnet.ibm.com;
> Honnappa Nagarahalli ;
> olivier.m...@6wind.com; Ruifeng Wang ; nd
>
> Subject: Re:
> -Original Message-
> From: dev On Behalf Of Phil Yang
> Sent: Tuesday, July 7, 2020 6:11 PM
> To: david.march...@redhat.com; dev@dpdk.org
> Cc: d...@linux.vnet.ibm.com; Honnappa Nagarahalli
> ; olivier.m...@6wind.com; Ruifeng Wang
> ; nd
> Subject: [dpdk-dev]
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Wednesday, July 8, 2020 1:15 PM
> To: Phil Yang ; dev@dpdk.org
> Cc: d...@linux.vnet.ibm.com; Ruifeng Wang ; nd
> ; shah...@mellanox.com; sta...@dpdk.org; Honnappa
> Nagarahalli ; nd
> Subject: RE:
> -Original Message-
> From: Harman Kalra
> Sent: Wednesday, July 8, 2020 7:41 PM
> To: Phil Yang
> Cc: dev@dpdk.org; d...@linux.vnet.ibm.com; Honnappa Nagarahalli
> ; Ruifeng Wang
> ; nd
> Subject: Re: [dpdk-dev] [PATCH 2/2] eal: use c11 atomics for interrupt st
> -Original Message-
> From: Kinsella, Ray
> Sent: Wednesday, July 8, 2020 11:05 PM
> To: David Marchand ; Phil Yang
> ; Aaron Conole
> Cc: dev ; David Christensen ;
> Honnappa Nagarahalli ; Ruifeng Wang
> ; nd ; Dodji Seketeli
> ; Neil Horman ; Harman
> K
data, so there is no need to set it to invalid
after that.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Harman Kalra
---
v2:
1. Fixed typo.
2. Updated libabigail.abignore to pass ABI check.
3. Merged v1 two patches into one patch.
devtools
If DPDK_ABI_REF_DIR is not set, the default DESTDIR is a relative path.
This will break ninja in the ABI check test.
Fixes: 777014e56d07 ("devtools: add ABI checks")
Signed-off-by: Phil Yang
---
devtools/test-meson-builds.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
di
> -Original Message-
> From: Stefan Puiu
> Sent: Thursday, July 9, 2020 4:02 PM
> To: Phil Yang
> Cc: david.march...@redhat.com; dev@dpdk.org; m...@ashroe.eu;
> acon...@redhat.com; d...@linux.vnet.ibm.com; Honnappa Nagarahalli
> ; Ruifeng Wang
> ; nd ; do...@r
data, so there is no need to set it to invalid
after that.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Harman Kalra
---
v3:
Fixed typo.
v2:
1. Fixed typo.
2. Updated libabigail.abignore to pass ABI check.
3. Merged v1 two patches into one
> -Original Message-
> From: Olivier Matz
> Sent: Wednesday, July 8, 2020 7:43 PM
> To: Phil Yang
> Cc: Stephen Hemminger ;
> david.march...@redhat.com; dev@dpdk.org; d...@linux.vnet.ibm.com;
> Honnappa Nagarahalli ; Ruifeng Wang
> ; nd
> Subject: Re: [dpdk-de
> -Original Message-
> From: Olivier Matz
> Sent: Wednesday, July 8, 2020 7:44 PM
> To: Phil Yang
> Cc: david.march...@redhat.com; dev@dpdk.org; d...@linux.vnet.ibm.com;
> Honnappa Nagarahalli ; Ruifeng Wang
> ; nd
> Subject: Re: [PATCH v2] mbuf: use C11 atomi
Use C11 atomic built-ins with explicit ordering instead of rte_atomic
ops which enforce unnecessary barriers on aarch64.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
---
v3:
1.Fix ABI breakage.
2.Simplify data type cast.
v2:
Fix ABI issue: revert the rte_mbuf_ext_shared_info struct
Hi Oliver,
> -Original Message-
> From: Olivier Matz
> Sent: Thursday, July 9, 2020 7:04 PM
> To: Phil Yang
> Cc: dev@dpdk.org; step...@networkplumber.org;
> david.march...@redhat.com; d...@linux.vnet.ibm.com; Honnappa
> Nagarahalli ; Ruifeng Wang
> ; nd
> S
>
> > >
> > > Hi Phil,
> > >
> > > On Thu, Jul 09, 2020 at 06:10:42PM +0800, Phil Yang wrote:
> > > > Use C11 atomic built-ins with explicit ordering instead of
> > > > rte_atomic ops which enforce unnecessary barriers on aarch64
refcnt_atomic member in structures rte_mbuf and rte_mbuf_ext_shared_info
will be deprecated in 20.11 release.
Signed-off-by: Phil Yang
---
doc/guides/rel_notes/deprecation.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes
1 - 100 of 465 matches
Mail list logo
