[dpdk-dev] [PATCH v2 19/19] vhost: make buf vector for scatter Rx local

From: Ilya Maximets Array of buf_vector's is just an array for temporary storing information about available descriptors. It used only locally in virtio_dev_merge_rx() and there is no reason for that array to be shared. Fix that by allocating local buf_vec inside

[dpdk-dev] [PATCH v2 18/19] vhost: per device virtio net header len

Virtio net header length is set per device, but not per queue. So, there is no reason to store it in vhost_virtqueue struct, instead, we should store it in virtio_net struct, to make one copy only. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost-net.h | 2 +-

[dpdk-dev] [PATCH v2 17/19] vhost: reserve few more space for future extension

"virtio_net_device_ops" is the only left open struct that an application can access, therefore, it's the only place that might introduce potential ABI break in future for extension. So, do some reservation for it. 5 should be pretty enough, considering that we have barely touched it for a long

[dpdk-dev] [PATCH v2 16/19] vhost: remove virtio-net.h

It barely has anything useful there, just 2 functions prototype. Here move them to vhost-net.h, and delete it. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost-net.h | 3 ++ lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 1 - lib/librte_vhost/vhost_rxtx.c

[dpdk-dev] [PATCH v2 15/19] vhost: remove unnecessary fields

The "reserved" field in virtio_net and vhost_virtqueue struct is not necessary any more. We now expose virtio_net device with a number "vid". This patch also removes the "priv" field: all fields are priviate now: application can't access it now. The only way that we could still access it is to

[dpdk-dev] [PATCH v2 14/19] vhost: hide internal structs/macros/functions

We are now safe to move all those internal structs/macros/functions to vhost-net.h, to hide them from external access. This patch also breaks long lines and removes some redundant comments. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/rte_virtio_net.h| 139

[dpdk-dev] [PATCH v2 13/19] vhost: export vid as the only interface to applications

With all the previous prepare works, we are just one step away from the final ABI refactoring. That is, to change current API to let them stick to vid instead of the old virtio_net dev. Signed-off-by: Yuanhan Liu --- v2: update release note --- doc/guides/rel_notes/release_16_07.rst|

[dpdk-dev] [PATCH v2 12/19] vhost: remove dependency on priv field

This change could let us avoid the dependency of "virtio_net" struct, to prepare for the ABI refactoring. Signed-off-by: Yuanhan Liu --- drivers/net/vhost/rte_eth_vhost.c | 13 +++-- examples/vhost/main.c | 18 -- 2 files changed, 23 insertions(+), 8

[dpdk-dev] [PATCH v2 11/19] vhost: introduce new API to export queue free entries

The new API rte_vhost_avail_entries() is actually a rename of rte_vring_available_entries(), with the "vring" to "vhost" name change to keep the consistency of other vhost exported APIs. This change could let us avoid the dependency of "virtio_net" struct, to prepare for the ABI refactoring.

[dpdk-dev] [PATCH v2 10/19] vhost: introduce new API to export ifname

Introduce a new API rte_vhost_get_ifname() to export the ifname to application. Signed-off-by: Yuanhan Liu --- drivers/net/vhost/rte_eth_vhost.c | 12 lib/librte_vhost/rte_vhost_version.map | 1 + lib/librte_vhost/rte_virtio_net.h | 17 +

[dpdk-dev] [PATCH v2 09/19] vhost: introduce new API to export number of queues

Introduce a new API rte_vhost_get_queue_num() to export the number of queues. Signed-off-by: Yuanhan Liu --- drivers/net/vhost/rte_eth_vhost.c | 2 +- lib/librte_vhost/rte_vhost_version.map | 1 + lib/librte_vhost/rte_virtio_net.h | 11 +++ lib/librte_vhost/virtio-net.c

[dpdk-dev] [PATCH v2 08/19] vhost: introduce new API to export numa node

Introduce a new API rte_vhost_get_numa_node() to get the numa node from which the virtio_net struct is allocated. Signed-off-by: Yuanhan Liu --- drivers/net/vhost/rte_eth_vhost.c | 13 - lib/librte_vhost/rte_vhost_version.map | 7 +++ lib/librte_vhost/rte_virtio_net.h

[dpdk-dev] [PATCH v2 07/19] vhost: move vhost device ctx to cuse

vhost cuse is now the last reference of the vhost_device_ctx struct; move it there, and do a rename to "vhost_cuse_device_ctx", to make it clear that it's "cuse only". Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost-net.h | 8

[dpdk-dev] [PATCH v2 06/19] vhost: get device by vid only

get_device() just needs vid, so pass vid as the parameter only. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/vhost-net.h | 30 ++-- lib/librte_vhost/vhost_cuse/vhost-net-cdev.c | 64 - lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 18

[dpdk-dev] [PATCH v2 05/19] vhost: rename device fh to vid

I failed to figure out what does "fh" mean here for a long while. The only guess I could have had is "file handle". So, you get the point that it's not well named. I then figured it out that "fh" is derived from the fuse lib, and my above guess is right. However, device_fh represents a virtio net

[dpdk-dev] [PATCH v2 04/19] examples/vhost: make a copy of virtio device id

Make a copy of virtio device id (device_fh) from the virtio_net struct, so that we could have less dependency on the virtio_net struct. Signed-off-by: Yuanhan Liu --- examples/vhost/main.c | 59 --- examples/vhost/main.h | 1 + 2 files changed,

[dpdk-dev] [PATCH v2 03/19] vhost: declare device fh as int

Firstly, "int" would be big enough: we don't need 64 bit to represent a virtio-net device id. Secondly, this could let us avoid the ugly "%" PRIu64 ".." stuff. And since ctx.fh is derived from device_fh, declare it as int, too. Signed-off-by: Yuanhan Liu --- examples/vhost/main.c

[dpdk-dev] [PATCH v2 02/19] vhost: set/reset dev flags internally

It does not make sense to ask the application to set/unset the flag VIRTIO_DEV_RUNNING (that used internal only) at new_device()/ destroy_device() callback. Instead, it should be set after new_device() succeeds and reset before destroy_device() is invoked inside vhost lib. This patch fixes it.

[dpdk-dev] [PATCH v2 01/19] vhost: declare backend with int type

It's an fd; so define it as "int", which could also save the unncessary (int) case. Signed-off-by: Yuanhan Liu --- lib/librte_vhost/rte_virtio_net.h | 2 +- lib/librte_vhost/virtio-net.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git

[dpdk-dev] [PATCH v2 00/19] vhost ABI/API refactoring

v2: - exported ifname as well to fix a vhost-pmd issue reported by Rich - separated the big patch that introduces several new APIs into some small patches. - updated release note - updated version.map NOTE: I created a branch at dpdk.org [0] for more conveinient testing:

[dpdk-dev] [PATCH v4 6/8] virtio-user: add new virtual pci driver for virtio

On Fri, May 13, 2016 at 09:54:33AM +0800, Tan, Jianfeng wrote: > > So, I'd suggest something like following: > > if (is_vdev(..)) { > > > The blocker issue of your suggestion is that we have no such condition. > > Previously, I use dev_type, but as David's comment said:

[dpdk-dev] [RFC] mbuf: new flag when vlan is stripped

Hi Olivier, > ... > This is a draft patch that implements what was previously discussed, except > the packet_type, which does not exist for vlan today (and I think it is not > mandatory for now, let's do it in another patch). > > After doing this patch, it appeared that ixgbe was the only driver

[dpdk-dev] mbuff rearm_data aligmenet issue on non x86

On Thu, May 12, 2016 at 01:14:34PM +, Ananyev, Konstantin wrote: > > > > On Thu, May 12, 2016 at 10:07:09AM +, Ananyev, Konstantin wrote: > > > Hi Jerrin, > > > > > > > > > > > Hi All, > > > > > > > > I would like align mbuff rearm_data field to 8 byte aligned so that > > > > write to

[dpdk-dev] [PATCH v4 6/8] virtio-user: add new virtual pci driver for virtio

On Thu, May 12, 2016 at 03:08:05PM +0800, Tan, Jianfeng wrote: > (2) It's more aligned to previous logic to hide the detail to differentiate > modern/legacy device. Why is there a need to support legacy interfaces at all? It's a container so if it's in use one can be reasonably sure you have a

[dpdk-dev] [RFC PATCH v2 1/3] rte: change xstats to use integer keys

2016-05-09 13:59, David Harton: > > } > > > > - > > Not sure how the community feels about white-space only changes. > Just mentioning in case some folks get excited about it. One here and a few > below. It's a trivial cleanup. No problem I think.

[dpdk-dev] [PATCH v2 09/11] eal/pci: replace SYSFS_PCI_DEVICES with pci_get_sysfs_path()

2016-05-12 17:46, Jan Viktorin: > On Thu, 12 May 2016 17:41:22 +0200 > Thomas Monjalon wrote: > > 2016-05-10 20:13, Jan Viktorin: > > > + orig = pci_get_sysfs_path(); > > > + ret = setenv("SYSFS_PCI_DEVICES", "My Documents", 1); > > > > Oh no! > > Not sure about your reaction... MS

[dpdk-dev] [PATCH v2 06/11] app/test: use linked list to store PCI drivers

2016-05-12 17:53, Jan Viktorin: > On Thu, 12 May 2016 17:31:28 +0200 > Thomas Monjalon wrote: > > > 2016-05-10 20:13, Jan Viktorin: > > > The test unregisters all real drivers before starting into an array. This > > > inflexiable as we can use a linked list for this purpose. > > > > I don't

[dpdk-dev] [PATCH v2 06/11] app/test: use linked list to store PCI drivers

On Thu, 12 May 2016 17:31:28 +0200 Thomas Monjalon wrote: > 2016-05-10 20:13, Jan Viktorin: > > The test unregisters all real drivers before starting into an array. This > > inflexiable as we can use a linked list for this purpose. > > I don't understand this. Maybe some words are missing.

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On 12 May 2016 at 16:57, Santosh Shukla wrote: > On Thu, May 12, 2016 at 01:54:13PM +0800, Jianbo Liu wrote: >> On 12 May 2016 at 13:06, Santosh Shukla >> wrote: >> > On Thu, May 12, 2016 at 11:42:26AM +0800, Jianbo Liu wrote: >> >> On 12 May 2016 at 11:17, Santosh Shukla >> >> wrote: >> >> >

[dpdk-dev] mbuff rearm_data aligmenet issue on non x86

On Thu, May 12, 2016 at 10:07:09AM +, Ananyev, Konstantin wrote: > Hi Jerrin, > > > > > Hi All, > > > > I would like align mbuff rearm_data field to 8 byte aligned so that > > write to mbuf->rearm_data with uint64_t* will be naturally aligned. > > I am not sure about IA but some other

[dpdk-dev] [PATCH v2 09/11] eal/pci: replace SYSFS_PCI_DEVICES with pci_get_sysfs_path()

On Thu, 12 May 2016 17:41:22 +0200 Thomas Monjalon wrote: > 2016-05-10 20:13, Jan Viktorin: > > The SYSFS_PCI_DEVICES is a constant that makes the PCI testing difficult as > > it points to an absolute path. We remove using this constant and introducing > > a function pci_get_sysfs_path that

[dpdk-dev] [PATCH v2 09/11] eal/pci: replace SYSFS_PCI_DEVICES with pci_get_sysfs_path()

2016-05-10 20:13, Jan Viktorin: > The SYSFS_PCI_DEVICES is a constant that makes the PCI testing difficult as > it points to an absolute path. We remove using this constant and introducing > a function pci_get_sysfs_path that gives the same value. However, the user can > pass a SYSFS_PCI_DEVICES

[dpdk-dev] [PATCH v2 09/11] eal/pci: replace SYSFS_PCI_DEVICES with pci_get_sysfs_path()

2016-05-10 20:13, Jan Viktorin: > The SYSFS_PCI_DEVICES is a constant that makes the PCI testing difficult as > it points to an absolute path. We remove using this constant and introducing > a function pci_get_sysfs_path that gives the same value. However, the user can > pass a SYSFS_PCI_DEVICES

[dpdk-dev] [dpdk-dev, 2/3] eth_dev: add support for device dma mask

Hi, Just a note, please, when replying inline, do not prepend ">" before your new text. I could not find your replies. See below... On Thu, 12 May 2016 16:03:14 +0100 Alejandro Lucero wrote: > Hi Jan > > On Thu, May 12, 2016 at 3:52 PM, Jan Viktorin > wrote: > > > Hello Alejandro, > > > >

[dpdk-dev] [PATCH v2 08/11] app/test: convert current pci_test into a single test case

2016-05-10 20:13, Jan Viktorin: > The current test_pci is just a single test case that tests the blacklisting > of devices. Rename it to test_pci_blacklist and call it from the test_pci. The functions are also moved. It is confusing. Maybe this patch can be squashed with the previous one.

[dpdk-dev] [PATCH v2 06/11] app/test: use linked list to store PCI drivers

2016-05-10 20:13, Jan Viktorin: > The test unregisters all real drivers before starting into an array. This > inflexiable as we can use a linked list for this purpose. I don't understand this. Maybe some words are missing. > +/* real drivers (not used for testing) */ What do mean by "not used

[dpdk-dev] [PATCH v1 04/10] app/test: support resources archived by tar

2016-05-12 17:26, Thomas Monjalon: > 2016-05-06 12:48, Jan Viktorin: > > +$(eval $(call resource,test_resource_tar,resource.tar)) > > This tar resource is not provided. Should it be created in the Makefile? Sorry I was looking at v1 while it is implemented in v2.

[dpdk-dev] [PATCH v2 01/11] app/test: introduce resources for tests

On Thu, 12 May 2016 17:19:21 +0200 Thomas Monjalon wrote: > 2016-05-10 20:13, Jan Viktorin: > > +REGISTER_TEST_COMMAND(resource_cmd); > > Should you add this test in group 1 of autotest_data.py? Will do for v3. This way: ... 84

[dpdk-dev] [PATCH v1 04/10] app/test: support resources archived by tar

2016-05-06 12:48, Jan Viktorin: > When needing a more complex resource (a file hierarchy), packing every single > file as a single resource would be very ineffective. For that purpose, it is > possible to pack the files into a tar archive, extract it before test from the > resource and finally

[dpdk-dev] [PATCH v2 01/11] app/test: introduce resources for tests

2016-05-10 20:13, Jan Viktorin: > +REGISTER_TEST_COMMAND(resource_cmd); Should you add this test in group 1 of autotest_data.py?

[dpdk-dev] [dpdk-dev,3/3] nfp: set device dma mask

On Thu, 12 May 2016 16:13:55 +0100 Alejandro Lucero wrote: > On Thu, May 12, 2016 at 4:03 PM, Jan Viktorin > wrote: > > > On Thu, 12 May 2016 15:34:00 +0100 > > "Alejandro.Lucero" wrote: > > > > > - Just hugepages within the supported range will be available. > > > > Again the hyphen is

[dpdk-dev] [PATCH v2 01/11] app/test: introduce resources for tests

2016-05-10 20:13, Jan Viktorin: > +struct resource { > + const char *name; /** Unique name of the resource */ > + const char *begin; /** Start of resource data */ > + const char *end; /** End of resource data */ > + TAILQ_ENTRY(resource) next; > +}; There is no doxygen

[dpdk-dev] [dpdk-dev, 1/3] eal/linux: add function for checking hugepages within device supported address range

On Thu, 12 May 2016 15:33:58 +0100 "Alejandro.Lucero" wrote: > - This is needed for avoiding problems with devices not being able to address >all the physical available memory. WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #14: -

[dpdk-dev] [PATCH v1 02/10] app/test: support resources externally linked

2016-05-09 17:19, Jan Viktorin: > On Fri, 06 May 2016 16:32:53 +0200 > Thomas Monjalon wrote: > > > It looks a lot too much tricky to be integrated without code comments ;) > > Please make a documentation effort. > > > [...] > > Thomas, > > is it OK to include the PCI test enhancements? Or

[dpdk-dev] [dpdk-dev,3/3] nfp: set device dma mask

On Thu, 12 May 2016 15:34:00 +0100 "Alejandro.Lucero" wrote: > - Just hugepages within the supported range will be available. Again the hyphen is redundant here. By the way, this text does not describe the change well. If I understood the whole patch set (I am not quite sure now), the

[dpdk-dev] [PATCH v1 01/10] app/test: introduce resources for tests

On Thu, 12 May 2016 16:58:31 +0200 Thomas Monjalon wrote: > 2016-05-06 18:20, Jan Viktorin: > > On Fri, 06 May 2016 16:01:08 +0200 > > Thomas Monjalon wrote: > > > 2016-05-06 12:48, Jan Viktorin: > > > > +static struct resource linkres_ ##_n = { \ > > > > + .name = RTE_STR(_n),

[dpdk-dev] [PATCH v1 01/10] app/test: introduce resources for tests

2016-05-06 18:20, Jan Viktorin: > On Fri, 06 May 2016 16:01:08 +0200 > Thomas Monjalon wrote: > > 2016-05-06 12:48, Jan Viktorin: > > > +static struct resource linkres_ ##_n = { \ > > > + .name = RTE_STR(_n), \ > > > + .beg = _b, \ > > > + .end = _e, \ > > >

[dpdk-dev] [dpdk-dev, 2/3] eth_dev: add support for device dma mask

Hello Alejandro, On Thu, 12 May 2016 15:33:59 +0100 "Alejandro.Lucero" wrote: > - New dma_mask field in rte_eth_dev_data. > - If PMD sets device dma_mask, call to check hugepages within I think that one of the purposes of DPDK is to support DMA transfers in userspace. In other words, I can

[dpdk-dev] [dpdk-dev,3/3] nfp: set device dma mask

On Thu, May 12, 2016 at 4:03 PM, Jan Viktorin wrote: > On Thu, 12 May 2016 15:34:00 +0100 > "Alejandro.Lucero" wrote: > > > - Just hugepages within the supported range will be available. > > Again the hyphen is redundant here. > > By the way, this text does not describe the change well. If I

[dpdk-dev] [PATCH] i40e: fix flexible payload selection

When setting up flexible payload selection rules, it is allowed that setting value to 63 to disable the rule (NONUSE_FLX_PIT_DEST_OFF). However, MK_FLX_PIT macro is always adding an offset value 50 (I40E_FLX_OFFSET_IN_FIELD_VECTOR), it will be set to "63 + 50" and when setting

[dpdk-dev] [dpdk-dev, 2/3] eth_dev: add support for device dma mask

Hi Jan On Thu, May 12, 2016 at 3:52 PM, Jan Viktorin wrote: > Hello Alejandro, > > On Thu, 12 May 2016 15:33:59 +0100 > "Alejandro.Lucero" wrote: > > > - New dma_mask field in rte_eth_dev_data. > > - If PMD sets device dma_mask, call to check hugepages within > > I think that one of the

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Thu, May 12, 2016 at 05:52:54PM +0800, Jianbo Liu wrote: > On 12 May 2016 at 16:57, Santosh Shukla > wrote: > > On Thu, May 12, 2016 at 01:54:13PM +0800, Jianbo Liu wrote: > >> On 12 May 2016 at 13:06, Santosh Shukla > >> wrote: > >> > On Thu, May 12, 2016 at 11:42:26AM +0800, Jianbo Liu

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

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jerin Jacob > Sent: Saturday, May 7, 2016 4:16 PM > To: dev at dpdk.org > Cc: thomas.monjalon at 6wind.com; Richardson, Bruce > ; Jerin Jacob > ; Maciej Czekaj > ; Kamil Rytarowski > ; Zyta Szpak > ; Slawomir

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

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jerin Jacob > Sent: Saturday, May 7, 2016 4:16 PM > To: dev at dpdk.org > Cc: thomas.monjalon at 6wind.com; Richardson, Bruce > ; Jerin Jacob > ; Maciej Czekaj > ; Kamil Rytarowski > ; Zyta Szpak > ; Slawomir

[dpdk-dev] [PATCH 3/3] nfp: set device dma mask

- Just hugepages within the supported range will be available. Signed-off-by: Alejandro Lucero --- drivers/net/nfp/nfp_net.c | 11 +++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c index ea5a2a3..e0e444a 100644 ---

[dpdk-dev] [PATCH 2/3] eth_dev: add support for device dma mask

- New dma_mask field in rte_eth_dev_data. - If PMD sets device dma_mask, call to check hugepages within supported range. Signed-off-by: Alejandro Lucero --- lib/librte_ether/rte_ethdev.c | 7 +++ lib/librte_ether/rte_ethdev.h | 1 + 2 files changed, 8 insertions(+) diff --git

[dpdk-dev] [PATCH 1/3] eal/linux: add function for checking hugepages within device supported address range

- This is needed for avoiding problems with devices not being able to address all the physical available memory. Signed-off-by: Alejandro Lucero --- lib/librte_eal/common/include/rte_memory.h | 6 ++ lib/librte_eal/linuxapp/eal/eal_memory.c | 27 +++ 2 files

[dpdk-dev] [PATCH 0/3] add support for devices with addressing limitations

A kernel driver uses a dma mask specifying the memory address range supported by the device for DMA operations. With DPDK there is no possibility for doing the same thing so it could lead to problems with those devices not being able to use all the available physical memory. This patchset adds

[dpdk-dev] [PATCH] i40e: fix link management

Previously, there was a known issue "On Intel? 40G Ethernet Controller stopping the port does not really down the port link." There were two reasons why the port is always kept up. 1. Old version Firmware would cause issue when call "Set PHY config command" on 40G NIC. 2. Because linux kernel i40e

[dpdk-dev] [PATCH v4 6/8] virtio-user: add new virtual pci driver for virtio

Hi yuanhan, On 5/12/2016 10:12 AM, Yuanhan Liu wrote: > On Fri, Apr 29, 2016 at 01:18:34AM +, Jianfeng Tan wrote: >> +static void >> +vdev_read_dev_config(struct virtio_hw *hw, uint64_t offset, >> + void *dst, int length) >> +{ >> +int i; >> +struct virtio_user_hw

[dpdk-dev] [PATCH] rte mempool: division or modulo by zero

Fix issue reported by Coverity. Coverity ID 13243: Division or modulo by zero In function call rte_mempool_xmem_size, division by expression total_size which may be zero has undefined behavior. Fixes: 148f963fb532 ("xen: core library changes") Signed-off-by: Slawomir Mrozowicz ---

[dpdk-dev] mbuff rearm_data aligmenet issue on non x86

Hi All, I would like align mbuff rearm_data field to 8 byte aligned so that write to mbuf->rearm_data with uint64_t* will be naturally aligned. I am not sure about IA but some other architecture/implementation has overhead in non-naturally aligned stores. Proposed patch is something like this

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Thu, May 12, 2016 at 01:54:13PM +0800, Jianbo Liu wrote: > On 12 May 2016 at 13:06, Santosh Shukla > wrote: > > On Thu, May 12, 2016 at 11:42:26AM +0800, Jianbo Liu wrote: > >> On 12 May 2016 at 11:17, Santosh Shukla > >> wrote: > >> > On Thu, May 12, 2016 at 10:01:05AM +0800, Jianbo Liu

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On 12 May 2016 at 13:06, Santosh Shukla wrote: > On Thu, May 12, 2016 at 11:42:26AM +0800, Jianbo Liu wrote: >> On 12 May 2016 at 11:17, Santosh Shukla >> wrote: >> > On Thu, May 12, 2016 at 10:01:05AM +0800, Jianbo Liu wrote: >> >> On 12 May 2016 at 02:25, Stephen Hemminger > >>

[dpdk-dev] mbuff rearm_data aligmenet issue on non x86

> > On Thu, May 12, 2016 at 10:07:09AM +, Ananyev, Konstantin wrote: > > Hi Jerrin, > > > > > > > > Hi All, > > > > > > I would like align mbuff rearm_data field to 8 byte aligned so that > > > write to mbuf->rearm_data with uint64_t* will be naturally aligned. > > > I am not sure about IA

[dpdk-dev] virtio pmd failed in pci probing

I add a debug log line in dpdk-16.04/lib/librte_ether/rte_ethdev.c rte_eth_driver_register void rte_eth_driver_register(struct eth_driver *eth_drv) { eth_drv->pci_drv.devinit = rte_eth_dev_init; eth_drv->pci_drv.devuninit = rte_eth_dev_uninit;

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On 12 May 2016 at 11:17, Santosh Shukla wrote: > On Thu, May 12, 2016 at 10:01:05AM +0800, Jianbo Liu wrote: >> On 12 May 2016 at 02:25, Stephen Hemminger >> wrote: >> > On Wed, 11 May 2016 22:32:16 +0530 >> > Jerin Jacob wrote: >> > >> >> On Wed, May 11, 2016 at 08:22:59AM -0700, Stephen

[dpdk-dev] releases scheduling

Hi everybody, The deadlines for the next releases are available on the website: http://dpdk.org/dev/roadmap#dates Release 16.07 Proposal deadline: May 8 Integration deadline: June 16 Release: July 18 Release 16.11 Proposal deadline: August 28 Integration deadline:

[dpdk-dev] [RFC] mbuf: remove unused rx error flags

Hi, On 05/12/2016 03:32 AM, John Daley (johndale) wrote: >> This patch removes the unused flags from rte_mbuf, and their use in >> the drivers. The enic driver is modified to drop bad packets, but >> i40e and fm10k are kept as they are today and should be fixed to >> drop bad packets. > > Perhaps

[dpdk-dev] [PATCH] eal: fix log level/type retrieving on a standard pthread

Hi Ferruh, On 05/11/2016 06:39 PM, Ferruh Yigit wrote: > On 5/9/2016 5:13 PM, Olivier Matz wrote: >> --- a/lib/librte_eal/common/eal_common_log.c >> +++ b/lib/librte_eal/common/eal_common_log.c >> @@ -98,9 +98,10 @@ static int history_enabled = 1; >> struct log_cur_msg { >> uint32_t

[dpdk-dev] [PATCH] lpm: unchecked return value

Hi, I handle Coverity defect ID 13201. It is about unchecked return value from rte_lpm6_delete() instances in rte_lpm6_add() function. Next I found this thread and I see that both defects (ID 13205 and ID 13201) may be resolved all together. > >> Fix issue reported by Coverity. > >> > >>

[dpdk-dev] [PATCH v2] eal/linuxapp: fix resource leak

Fix issue reported by Coverity. Coverity ID 97920 munmap structure of hugepage leaked_storage: Variable hugepage going out of scope leaks the storage it points to. The system resource will not be reclaimed and reused, reducing the future availability of the resource. In rte_eal_hugepage_init:

[dpdk-dev] DPDK Community Call - 16.04 Retrospective - Wednesday May 11th

Meeting Minutes for Community Call - May 11th 2014 Topic: DPDK 16.04 Retrospective Facilitators: Mike Glynn (Intel), John McNamara (Intel) Attendees: Christian Ehrhardt, Hemant Agrawal, Jan Viktorin, Mauricio Vasquez, Mike Holmes, Stephen Hemminger, Thomas Monjalon, Naoyuki Mori, Tom Gall,

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Thu, May 12, 2016 at 11:42:26AM +0800, Jianbo Liu wrote: > On 12 May 2016 at 11:17, Santosh Shukla > wrote: > > On Thu, May 12, 2016 at 10:01:05AM +0800, Jianbo Liu wrote: > >> On 12 May 2016 at 02:25, Stephen Hemminger > >> wrote: > >> > On Wed, 11 May 2016 22:32:16 +0530 > >> > Jerin Jacob

[dpdk-dev] mbuff rearm_data aligmenet issue on non x86

Hi Jerrin, > > Hi All, > > I would like align mbuff rearm_data field to 8 byte aligned so that > write to mbuf->rearm_data with uint64_t* will be naturally aligned. > I am not sure about IA but some other architecture/implementation has overhead > in non-naturally aligned stores. > > Proposed

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On 12 May 2016 at 02:25, Stephen Hemminger wrote: > On Wed, 11 May 2016 22:32:16 +0530 > Jerin Jacob wrote: > >> On Wed, May 11, 2016 at 08:22:59AM -0700, Stephen Hemminger wrote: >> > On Wed, 11 May 2016 19:17:58 +0530 >> > Hemant Agrawal wrote: >> > >> > > IGB_UIO not supported for arm64

[dpdk-dev] [PATCH v3] examples/qos_meter: fix unchecked return value

> -Original Message- > From: Dumitrescu, Cristian > Sent: Thursday, May 12, 2016 10:41 AM > To: Mrozowicz, SlawomirX > Cc: dev at dpdk.org; Singh, Jasvinder > Subject: RE: [PATCH v3] examples/qos_meter: fix unchecked return value > > > > > -Original Message- > > From:

[dpdk-dev] Updates to large patchsets

2016-05-11 14:22, Stephen Hurd: > When submitting an update to a single patch in a large patchset, what's the > preferred method? Do I send a single "[PATCH v2 01/40]" email with the > modified patch or do I send the entire series of 40 patches again? Good question :) It's generally easier to

[dpdk-dev] [PATCH v3] examples/qos_meter: fix unchecked return value

> -Original Message- > From: Mrozowicz, SlawomirX > Sent: Thursday, May 12, 2016 8:06 AM > To: Dumitrescu, Cristian > Cc: dev at dpdk.org; Singh, Jasvinder > Subject: RE: [PATCH v3] examples/qos_meter: fix unchecked return value > > > > >-Original Message- > >From:

[dpdk-dev] [PATCH v4 6/8] virtio-user: add new virtual pci driver for virtio

On Thu, May 12, 2016 at 03:08:05PM +0800, Tan, Jianfeng wrote: > >>+static int > >>+vdev_setup_queue(struct virtio_hw *hw __rte_unused, struct virtqueue *vq) > >>+{ > >>+ /* Changed to use virtual addr */ > >>+ vq->vq_ring_mem = (phys_addr_t)vq->mz->addr; > >>+ if (vq->virtio_net_hdr_mz) { >

[dpdk-dev] virtio pmd failed in pci probing

Hi I am testing mTCP https://github.com/eunyoung14/mtcp with dpdk-16.04 on KVM guest and it appears the virtio pmd fail to load, detail info below: # ./tools/dpdk_nic_bind.py --status Network devices using DPDK-compatible driver :00:07.0

[dpdk-dev] [PATCH] eal/linuxapp: fix resource leak

Hi, On 11/05/2016 17:01, Daniel Mrzyglod wrote: > Fix issue reported by Coverity. > Coverity ID 97920 > > munmap structure of hugepage > > leaked_storage: Variable hugepage going out of scope leaks the storage > it points to. > > The system resource will not be reclaimed and reused, reducing the

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Thu, May 12, 2016 at 10:01:05AM +0800, Jianbo Liu wrote: > On 12 May 2016 at 02:25, Stephen Hemminger > wrote: > > On Wed, 11 May 2016 22:32:16 +0530 > > Jerin Jacob wrote: > > > >> On Wed, May 11, 2016 at 08:22:59AM -0700, Stephen Hemminger wrote: > >> > On Wed, 11 May 2016 19:17:58 +0530 >

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Wed, May 11, 2016 at 11:25:59AM -0700, Stephen Hemminger wrote: > On Wed, 11 May 2016 22:32:16 +0530 > Jerin Jacob wrote: > > > On Wed, May 11, 2016 at 08:22:59AM -0700, Stephen Hemminger wrote: > > > On Wed, 11 May 2016 19:17:58 +0530 > > > Hemant Agrawal wrote: > > > > > > > IGB_UIO not

[dpdk-dev] [PATCH v3] examples/qos_meter: fix unchecked return value

>-Original Message- >From: Dumitrescu, Cristian >Sent: Wednesday, May 11, 2016 7:57 PM >To: Mrozowicz, SlawomirX >Cc: dev at dpdk.org; Singh, Jasvinder >Subject: RE: [PATCH v3] examples/qos_meter: fix unchecked return value > > > >> -Original Message- >> From: Mrozowicz,

[dpdk-dev] [RFC] mbuf: remove unused rx error flags

Hi, > -Original Message- > From: Olivier Matz [mailto:olivier.matz at 6wind.com] > Sent: Tuesday, May 10, 2016 1:40 AM > To: dev at dpdk.org > Cc: konstantin.ananyev at intel.com; John Daley (johndale) > ; helin.zhang at intel.com; arnon at qwilt.com; > rolette at infinite.io > Subject:

[dpdk-dev] [PATCH v4] eal: make hugetlb initialization more robust

This patch adds an option, --huge-trybest, to use a recover mechanism to the case that there are not so many hugepages (declared in sysfs), which can be used. It relys on a mem access to fault-in hugepages, and if fails with SIGBUS, recover to previously saved stack environment with siglongjmp().