From: Rizwan Ansari
Patch fixes below build error:
/home/mv/work/thunder/santosh/dpdk/santosh/dpdk/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c:
In function ?pci_vfio_set_iommu_type?:
/home/mv/work/thunder/santosh/dpdk/santosh/dpdk/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c:243:2:
error: ?for? loop
From: Anatoly Burakov
This commit is adding a generic mechanism to support multiple IOMMU
types. For now, it's only type 1 (x86 IOMMU) and no-IOMMU (a special
VFIO mode that doesn't use IOMMU at all), but it's easily extended
by adding necessary definitions into eal_pci_init.h and a DMA
mapping f
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 +-
config/defconfig_arm64-armv8a-linuxapp-gcc |6 +-
2 files changed, 10 insertions(+), 2
Flag required for vfio case, It helps to update vfio_dev_fd for each
virtio net interface.
Signed-off-by: Santosh Shukla
---
drivers/net/virtio/virtio_ethdev.c |4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev.c
inde
- adding pci_dev member in struct virtio_hw{} to track
vfio_dev_fd per virtio interface, required for ioport
rd/wr operation.
- Masked default VIRTIO_READ/WRITE for vfio case.
Signed-off-by: Santosh Shukla
Signed-off-by: Rizwan Ansari
Signed-off-by: Rakesh Krishnamurhty
---
drivers/net/virtio
For vfio case - Use pread/pwrite api to access virtio
ioport space.
Signed-off-by: Santosh Shukla
Signed-off-by: Rizwan Ansari
Signed-off-by: Rakesh Krishnamurthy
---
drivers/net/virtio/virtio_vfio.h | 146 ++
1 file changed, 146 insertions(+)
create mode
Introducing below api for pci bar space rd/wr. Currently used for
pci iobar rd/wr.
Api's are:
- rte_eal_pci_read_bar
- rte_eal_pci_write_bar
virtio when used for vfio-mode then virtio driver will use these api
to do rd/wr operation on ioport pci bar.
Signed-off-by: Santosh Shukla
---
lib/librt
make sure sys/io.h used only for x86 archs. This fixes build error
arm64/arm case.
Signed-off-by: Santosh Shukla
---
drivers/net/virtio/virtio_pci.h |2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h
index 47f722a..8b5b031 1
vfio_pci_mmap() try to map all pci bars. ioport region ar not mapped in
vfio/kernel so ignore mmaping for ioport.
Signed-off-by: Santosh Shukla
---
lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 20
1 file changed, 20 insertions(+)
diff --git a/lib/librte_eal/linuxapp/eal/e
iopl() syscall not supported in linux-arm/arm64 so always return 0 value.
Signed-off-by: Santosh Shukla
Acked-by: Jan Viktorin
---
lib/librte_eal/linuxapp/eal/eal.c |3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/librte_eal/linuxapp/eal/eal.c
b/lib/librte_eal/linuxapp/eal/eal.c
i
i686 target config example:
config/defconfig_i686-native-linuxapp-gcc says "Vectorized PMD is not supported
on 32-bit".
So setting RTE_VIRTIO_INC_VECTOR to 'n'.
Signed-off-by: Santosh Shukla
---
config/defconfig_i686-native-linuxapp-gcc |1 +
config/defconfig_i686-native-linuxapp-icc |1
virtio_recv_pkts_vec and other virtio vector friend apis are written for sse/avx
instructions. For arm64 in particular, virtio vector implementation does not
exist(todo).
So virtio pmd driver wont build for targets like i686, arm64. By making
RTE_VIRTIO_INC_VECTOR=n, Driver can build for non-sse/
This v3 patch uses vfio-noiommu-way to access virtio-net pci interface.
Tested for arm64 thunderX platform. Patch builds for
x86/i386/arm/armv8/thunderX.
The patchset has below dependancy:
- Kernel should be patched with Alex vfio-noiommu patch, available at linuz-next
[1].
- Anatoly's dpdk patch
On 1/7/16, 12:19 PM, "dev on behalf of Stephen Hemminger" wrote:
>On Thu, 7 Jan 2016 22:03:03 +0530
>Santosh Shukla wrote:
>
>>
>> +int rte_eal_pci_read_bar(const struct rte_pci_device *device __rte_unused,
>> + void *buf __rte_unused,
>> + size_t len _
Hi Santosh,
> Patch fixes below build error:
> /home/mv/work/thunder/santosh/dpdk/santosh/dpdk/lib/librte_eal/linuxa
> pp/eal/eal_pci_vfio.c:
> In function ?pci_vfio_set_iommu_type?:
> /home/mv/work/thunder/santosh/dpdk/santosh/dpdk/lib/librte_eal/linuxa
> pp/eal/eal_pci_vfio.c:243:2:
> error: ?fo
On 01/03/2016 07:56 PM, Huawei Xie wrote:
> v2 changes:
> change LOG level from ERR to INFO
>
> virtio PMD could use IO port to configure the virtio device without
> using uio driver.
>
> There are two issues with previous implementation:
> 1) virtio PMD will take over each virtio device blindly
with only one hugepage or already sorted hugepage addresses, the sort
function called memcpy with same src and dst pointer. Debugging with
valgrind will issue a warning about overlapping area. This patch changes
the sort method to qsort to avoid this behavior. The separate sort
function is no longe
with only one hugepage or already sorted hugepage addresses, the sort
function called memcpy with same src and dst pointer. Debugging with
valgrind will issue a warning about overlapping area. This patch changes
the sort method to qsort to avoid this behavior. The separate sort
function is no longe
Hi Sergio,
On 07.01.2016 11:38, Sergio Gonzalez Monroy wrote:
>> Forgot to mention that there is a checkpatch warning:
>> WARNING:LONG_LINE: line over 90 characters
>> #113: FILE: lib/librte_eal/linuxapp/eal/eal_memory.c:1167:
>> + qsort(&tmp_hp[hp_offset], hpi->num_pages[0],
>> size
Hi Ralf,
It seems like the title update you did for v3 is missing in this patch.
On 07/01/2016 13:59, Ralf Hoffmann wrote:
> with only one hugepage or already sorted hugepage addresses, the sort
> function called memcpy with same src and dst pointer. Debugging with
> valgrind will issue a warning
On Thu, Jan 07, 2016 at 10:24:19AM +, Ananyev, Konstantin wrote:
>
>
> > -Original Message-
> > From: Adrien Mazarguil [mailto:adrien.mazarguil at 6wind.com]
> > Sent: Wednesday, January 06, 2016 5:23 PM
> > To: Ananyev, Konstantin
> > Cc: N?lio Laranjeiro; Tan, Jianfeng; dev at dpdk.
On Mon, Jan 04, 2016 at 05:56:49PM +, Xie, Huawei wrote:
> On 1/5/2016 1:24 AM, Stephen Hemminger wrote:
> > On Mon, 4 Jan 2016 01:56:13 +0800
> > Huawei Xie wrote:
> >
> >> + if (pci_dev->kdrv != RTE_KDRV_NONE) {
> >> + PMD_INIT_LOG(INFO,
> >> + "kernel driver is m
On Tue, Jan 05, 2016 at 09:07:42AM +0800, Jianfeng Tan wrote:
> Fix the issue that virtio device cannot be started after stopped.
>
> The field, hw->started, should be changed by virtio_dev_start/stop instead
> of virtio_dev_close.
>
> Signed-off-by: Jianfeng Tan
Acked-by: Yuanhan Liu
BTW, if
On Thu, 7 Jan 2016 18:26:30 +
"Wiles, Keith" wrote:
> On 1/7/16, 12:19 PM, "dev on behalf of Stephen Hemminger" dpdk.org on behalf of stephen at networkplumber.org> wrote:
>
> >On Thu, 7 Jan 2016 22:03:03 +0530
> >Santosh Shukla wrote:
> >
> >>
> >> +int rte_eal_pci_read_bar(const struc
On 07/01/2016 09:51, Sergio Gonzalez Monroy wrote:
> On 07/01/2016 09:33, Sergio Gonzalez Monroy wrote:
>> On 05/01/2016 09:37, Ralf Hoffmann wrote:
>>> with only one hugepage or already sorted hugepage addresses, the sort
>>> function called memcpy with same src and dst pointer. Debugging with
>>>
On Tue, Jan 05, 2016 at 02:14:09PM -0800, Rich Lane wrote:
> The common vhost code only supported a single mmap per device. vhost-user
> worked around this by saving the address/length/fd of each mmap after the end
> of the rte_virtio_memory struct. This only works if the vhost-user code frees
> de
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarguil at 6wind.com]
> Sent: Wednesday, January 06, 2016 5:23 PM
> To: Ananyev, Konstantin
> Cc: N?lio Laranjeiro; Tan, Jianfeng; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 01/12] ethdev: add API to query what/if packet
Thanks Jasvinder for your quick response.
-Original Message-
From: Singh, Jasvinder [mailto:jasvinder.si...@intel.com]
Sent: Thursday, January 07, 2016 3:44 PM
To: Ravulakollu Udaya Kumar (WT01 - Product Engineering Service)
Cc: dev at dpdk.org
Subject: RE: [dpdk-dev] Traffic scheduling in
On Thu, 7 Jan 2016 22:03:06 +0530
Santosh Shukla wrote:
> +#ifdef RTE_EAL_VFIO
> + .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_DETACHABLE,
> +#else
> .drv_flags = RTE_PCI_DRV_DETACHABLE,
> +#endif
Since VFIO is determined at runtime not compile time, the flags
On Thu, 7 Jan 2016 22:03:03 +0530
Santosh Shukla wrote:
>
> +int rte_eal_pci_read_bar(const struct rte_pci_device *device __rte_unused,
> + void *buf __rte_unused,
> + size_t len __rte_unused,
> + off_t offset __rte_unused,
> +
This looks like the right thing to do. Minor nits.
> diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> index 74f91ba..4077eb6 100644
> --- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> +++ b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> @@ -7
Hi Uday,
> -Original Message-
> From: ravulakollu.kumar at wipro.com [mailto:ravulakollu.kumar at wipro.com]
> Sent: Thursday, January 7, 2016 6:29 AM
> To: Singh, Jasvinder
> Cc: dev at dpdk.org
> Subject: RE: [dpdk-dev] Traffic scheduling in DPDK
>
> Hi Jasvinder,
>
> Below is my syst
On Thu, 7 Jan 2016 22:03:00 +0530
Santosh Shukla wrote:
> #else
> +#if defined(RTE_ARCH_ARM) || defined(RTE_ARCH_ARM64)
> + return 0; /* iopl syscall not supported for ARM/ARM64 */
> +#endif
> return -1;
> #endif
Minor net why not:
#elif defined(RTE_ARCH_ARM) || defined(RTE_ARCH_AR
On 07/01/2016 09:33, Sergio Gonzalez Monroy wrote:
> On 05/01/2016 09:37, Ralf Hoffmann wrote:
>> with only one hugepage or already sorted hugepage addresses, the sort
>> function called memcpy with same src and dst pointer. Debugging with
>> valgrind will issue a warning about overlapping area. Th
Hi Jianfeng,
> -Original Message-
> From: Tan, Jianfeng
> Sent: Thursday, January 07, 2016 1:20 AM
> To: Ananyev, Konstantin; dev at dpdk.org
> Cc: Zhang, Helin
> Subject: Re: [PATCH 12/12] examples/l3fwd: add option to parse ptype
>
>
> Hi Konstantin,
>
> On 1/6/2016 12:49 AM, Ananyev,
So is there no resolution to this issue ?
-Original Message-
From: Tan, Jianfeng [mailto:jianfeng@intel.com]
Sent: Thursday, January 07, 2016 2:18 PM
To: Dey, Souvik ; dev at dpdk.org
Subject: RE: tx_burst errors seen with virtual pmds
Hi Souvik,
> -Original Message-
> From
On 05/01/2016 09:37, Ralf Hoffmann wrote:
> with only one hugepage or already sorted hugepage addresses, the sort
> function called memcpy with same src and dst pointer. Debugging with
> valgrind will issue a warning about overlapping area. This patch
> changes the sort method to qsort to avoid thi
Hi Konstantin,
On 1/6/2016 12:49 AM, Ananyev, Konstantin wrote:
> Hi Jianfeng,
>
+static int
+check_packet_type_ok(int portid)
+{
+ int i;
+ int ret;
+ uint32_t ptypes[RTE_PTYPE_L3_MAX_NUM];
+ int ptype_l3_ipv4 = 0, ptype_l3_ipv6 = 0;
+
+ ret = rt
Hi Souvik,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Dey, Souvik
> Sent: Thursday, January 7, 2016 2:15 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] tx_burst errors seen with virtual pmds
>
> Hi All,
> While trying call load with vir
On 1/7/2016 10:27 AM, Yuanhan Liu wrote:
> On Tue, Jan 05, 2016 at 02:14:09PM -0800, Rich Lane wrote:
>> The common vhost code only supported a single mmap per device. vhost-user
>> worked around this by saving the address/length/fd of each mmap after the end
>> of the rte_virtio_memory struct. Thi
Hi Jasvinder,
Below is my system configuration
Hugepages:
--
[root at qos_sched]# grep -i huge /proc/meminfo
AnonHugePages: 4096 kB
HugePages_Total:8000
HugePages_Free: 7488
HugePages_Rsvd:0
HugePages_Surp:0
Hugepagesize: 2048 kB
NUMA Nodes:
---
Hi All,
While trying call load with virtio_pmd/vmxnet3_pmd , I am
seeing that at around 100Mbps, we are having tx_burst errors. We are currently
using DPDK 2.1 and send 1 packet at a time. When we try the same with ixgbe_vf
we are not seeing similar drops. Is there any issues wi
42 matches
Mail list logo
