Thanks, looks OK for me.
Reviewed-by: Radoslaw Biernacki
adoslaw.bierna...@linaro.com>
On 26 January 2018 at 18:40, Anatoly Burakov
wrote:
> Currently, memzone autotest expects there to be no memzones
> present by the time the test is run. Some hardware drivers
> will allocate memzones for int
Looks OK.
Following note is aside from the patch.
Might be beneficial (in some rare cases) to add bailout recovery with
goto's in test_memzone_basic()
Just in case one of the rte_memzone_reserve() we should not make return -1,
but instead a goto to below section where we call rte_memzone_free().
T
On Fri, Jan 26, 2018 at 03:19:00PM +0100, Adrien Mazarguil wrote:
...
> +static int
> +mlx4_glue_init(void)
> +{
> + char file[] = "/tmp/" MLX4_DRIVER_NAME "_XX";
> + int fd = mkstemp(file);
...
> + while (off != mlx4_glue_lib_size) {
> + ssize_t ret;
> +
> +
Friday, January 26, 2018 10:36 AM, Thomas Monjalon:
> 26/01/2018 09:06, Lu, Wenzhuo:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > 26/01/2018 08:30, Lu, Wenzhuo:
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > > > 25/01/2018 02:11, Lu, Wenzhuo:
> > > > > Why these of
This commit moves the rte_service_finalize() function
to be in the component header, and marks it as @internal.
The function is only called internally by rte_eal_finalize().
Signed-off-by: Harry van Haaren
---
Cc: tho...@monjalon.net
Cc: vipin.vargh...@intel.com
---
lib/librte_eal/common/inclu
This commit adds a new function rte_eal_finalize().
The function serves as a hook to allow DPDK to release
internal resources (e.g.: hugepage allocations).
This function allows DPDK to become more like an ordinary
library, where the library context itself can be initialized
and finalized by the ap
This patch adds a call to the newly introduced finalize()
function just before quitting the pdump app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause
This patch adds a call to the newly introduced finalize()
function just before quitting the app.
Adding this function call before quitting from a secondary processes
is important, as otherwise it will leak hugepage memory. For a secondary
process that is run multiple times, this could cause hugepa
This patch set includes some bug fixes and minor enhancements for QEDE PMD.
It also includes NIC guide updates for BNX2X and QEDE PMDs.
Please apply.
Thanks!
-Rasesh
Harish Patil (4):
net/qede/base: fix VF LRO tunnel params configuration
net/qede: initialize VF tunnel as enabled on start
n
From: Harish Patil
Add missing LRO tunnel configuration parameters for VF over sriov channel.
Fixes: ec94dbc57362 ("qede: add base driver")
Cc: sta...@dpdk.org
Signed-off-by: Harish Patil
---
drivers/net/qede/base/ecore_vf.c |6 ++
drivers/net/qede/base/ecore_vfpf_if.h |2 ++
From: Harish Patil
By default, the PF driver enables tunnel offload for its child VF.
So mark tunnel offloads as enabled in the VF driver to reflect the
actual state.
Fixes: 52d94b57e1c7 ("net/qede: add slowpath support for VXLAN tunneling")
Fixes: d378cefab84e ("net/qede: add support for GENEVE
From: Harish Patil
- Add a check to verify tunnel IP header checksum is valid and mark MBUF
flag as appropriate.
- Bit of refactoring so that inner frame handling for tunneled packets can
be made common as regular (non-tunneled) packets.
- make qede_tunn_exist() as inline.
- remove RTE_PTYPE_L2_E
Add support to clear the per queue statistics thereby clearing xstats
counters.
Fixes: 7634c5f91569 ("net/qede: add queue statistics")
Cc: sta...@dpdk.org
Signed-off-by: Rasesh Mody
---
drivers/net/qede/qede_ethdev.c | 58
1 file changed, 58 insertions(
This patch fixes issues related to MTU set and max_rx_pkt_len usage.
- Adjust MTU during device configuration when jumbo is enabled
- In qede_set_mtu():
Return not supported for VF as currently we do not support it.
Cache new mtu value in mtu_new for proper update.
Add check for RXQ a
From: Harish Patil
- Fix incorrect header size. In the tunnel case, the outer L2/L3 lengths
should be included to calculate tunnel header_size.
- In TSO case, skip manipulating TX BD1 and TX BD2 data buffer fields
since those fields are already updated with header and payload lengths
respectively
With dynamic logging, we no longer need DEBUG INFO config option.
Signed-off-by: Rasesh Mody
---
config/common_base |1 -
doc/guides/nics/qede.rst | 10 +-
drivers/net/qede/qede_ethdev.c |8
drivers/net/qede/qede_logs.h |4
4 files changed,
Signed-off-by: Rasesh Mody
---
doc/guides/nics/qede.rst | 16 +---
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/doc/guides/nics/qede.rst b/doc/guides/nics/qede.rst
index 43b0f3f..0ca5084 100644
--- a/doc/guides/nics/qede.rst
+++ b/doc/guides/nics/qede.rst
@@ -35,14
Signed-off-by: Rasesh Mody
---
doc/guides/nics/bnx2x.rst |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/nics/bnx2x.rst b/doc/guides/nics/bnx2x.rst
index b1fec8a..31f146a 100644
--- a/doc/guides/nics/bnx2x.rst
+++ b/doc/guides/nics/bnx2x.rst
@@ -84,7 +84,7 @@ Pre
Signed-off-by: Rasesh Mody
---
drivers/net/qede/qede_ethdev.h |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/qede/qede_ethdev.h b/drivers/net/qede/qede_ethdev.h
index cb95973..c7bb415 100644
--- a/drivers/net/qede/qede_ethdev.h
+++ b/drivers/net/qede/qede_ethde
From: Shahed Shaikh
Test the return value of ecore_ptt_acquire for NULL.
Fixes: d378cefab84e ("net/qede: add support for GENEVE tunneling offload")
Coverity issue: 257049
Signed-off-by: Shahed Shaikh
---
drivers/net/qede/qede_ethdev.c | 11 ++-
1 file changed, 10 insertions(+), 1 de
26/01/2018 06:04, Pavan Nikhilesh:
> In some use cases of integer division, denominator remains constant and
> numerator varies. It is possible to optimize division for such specific
> scenarios.
>
> The librte_sched uses rte_reciprocal to optimize division so, moving it to
> eal/common would allo
Friday, January 26, 2018 6:44 PM, Adrien Mazarguil:
> Hi Ophir,
>
> On Tue, Jan 23, 2018 at 11:32:47PM +, Ophir Munk wrote:
> > The number of mlx4 present ports is calculated as follows:
> > conf.ports.present |= (UINT64_C(1) << device_attr.phys_port_cnt) - 1;
> >
> > That is - all ones seque
25/01/2018 22:02, Yongseok Koh:
> This patchset is to introduce coherent I/O memory barriers, which could be
> more
> efficient for coherent memory between I/O device and CPU, especially for
> ARMv8.
>
> v4:
> * rename barriers to "coherent I/O memory barrier".
> * Make groups for various barrie
23 matches
Mail list logo
