On Fri, Nov 06, 2020 at 07:35:37PM +, Mark Brown wrote:
> On Thu, Nov 05, 2020 at 08:37:14PM +, Parav Pandit wrote:
>
> > > > This example describes the mlx5 PCI subfunction use case.
> > > > I didn't follow your question about 'explicit example'.
> > > > What part is missing to identify i
On Sun, Sep 20, 2020 at 11:47 AM Greg Kroah-Hartman
wrote:
>
> On Sat, Sep 19, 2020 at 04:22:35PM -0300, Jason Gunthorpe wrote:
> > On Sat, Sep 19, 2020 at 07:27:30PM +0200, Greg Kroah-Hartman wrote:
> > > > It's probably heresy, but why do I need to integrate into the RDMA
> > > > subsystem ?
>
On Sat, Sep 19, 2020 at 11:30 AM Greg Kroah-Hartman
wrote:
>
> On Sat, Sep 19, 2020 at 11:20:03AM +0300, Leon Romanovsky wrote:
> > On Sat, Sep 19, 2020 at 08:40:20AM +0200, Greg Kroah-Hartman wrote:
> > > On Fri, Sep 18, 2020 at 03:19:05PM +0300, Leon Romanovsky wrote:
> > > > > So we do have an
On Fri, Sep 18, 2020 at 6:07 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 05:45:21PM +0300, Oded Gabbay wrote:
>
> > Any access by the device's engines to the host memory is done via our
> > device's MMU. Our MMU supports multiple ASIDs - Address Spac
On Fri, Sep 18, 2020 at 5:19 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 05:12:04PM +0300, Oded Gabbay wrote:
> > On Fri, Sep 18, 2020 at 4:59 PM Jason Gunthorpe wrote:
> > >
> > > On Fri, Sep 18, 2020 at 04:49:25PM +0300, Oded Gabbay wrote:
> >
On Fri, Sep 18, 2020 at 4:59 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 04:49:25PM +0300, Oded Gabbay wrote:
> > On Fri, Sep 18, 2020 at 4:26 PM Jason Gunthorpe wrote:
> > >
> > > On Fri, Sep 18, 2020 at 04:02:24PM +0300, Oded Gabbay wrote:
> > &
On Fri, Sep 18, 2020 at 4:26 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 04:02:24PM +0300, Oded Gabbay wrote:
>
> > The problem with MR is that the API doesn't let us return a new VA. It
> > forces us to use the original VA that the Host OS allocated.
>
On Fri, Sep 18, 2020 at 3:50 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 03:34:54PM +0300, Oded Gabbay wrote:
> > > > Another example is that the submission of WQ is done through our QMAN
> > > > mechanism and is NOT mapped to userspace (due to the rest
On Fri, Sep 18, 2020 at 3:16 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 02:59:28PM +0300, Oded Gabbay wrote:
> > On Fri, Sep 18, 2020 at 2:56 PM Jason Gunthorpe wrote:
> > >
> > > On Fri, Sep 18, 2020 at 02:36:10PM +0300, Gal Pressman wrote:
>
On Fri, Sep 18, 2020 at 3:19 PM Leon Romanovsky wrote:
>
> On Fri, Sep 18, 2020 at 03:07:19PM +0300, Oded Gabbay wrote:
> > On Fri, Sep 18, 2020 at 3:03 PM Leon Romanovsky wrote:
> > >
> > > On Fri, Sep 18, 2020 at 02:56:09PM +0300, Oded Gabbay wrote:
> > >
On Fri, Sep 18, 2020 at 2:36 PM Gal Pressman wrote:
>
> On 17/09/2020 20:18, Jason Gunthorpe wrote:
> > On Tue, Sep 15, 2020 at 11:46:58PM +0300, Oded Gabbay wrote:
> >> infrastructure for communication between multiple accelerators. Same
> >> as Nvidia uses NV
On Fri, Sep 18, 2020 at 3:03 PM Leon Romanovsky wrote:
>
> On Fri, Sep 18, 2020 at 02:56:09PM +0300, Oded Gabbay wrote:
> > On Fri, Sep 18, 2020 at 2:52 PM Leon Romanovsky wrote:
> > >
> > > On Fri, Sep 18, 2020 at 02:36:10PM +0300, Gal Pressman wrote:
>
On Fri, Sep 18, 2020 at 3:00 PM Jason Gunthorpe wrote:
>
>
> On Tue, Sep 15, 2020 at 08:10:08PM +0300, Oded Gabbay wrote:
> > Hello,
> >
> > This is the second version of the patch-set to upstream the GAUDI NIC code
> > into the habanalabs driver.
> >
>
On Fri, Sep 18, 2020 at 2:56 PM Jason Gunthorpe wrote:
>
> On Fri, Sep 18, 2020 at 02:36:10PM +0300, Gal Pressman wrote:
> > On 17/09/2020 20:18, Jason Gunthorpe wrote:
> > > On Tue, Sep 15, 2020 at 11:46:58PM +0300, Oded Gabbay wrote:
> > >> infrastructure f
On Fri, Sep 18, 2020 at 2:52 PM Leon Romanovsky wrote:
>
> On Fri, Sep 18, 2020 at 02:36:10PM +0300, Gal Pressman wrote:
> > On 17/09/2020 20:18, Jason Gunthorpe wrote:
> > > On Tue, Sep 15, 2020 at 11:46:58PM +0300, Oded Gabbay wrote:
> > >> infrastructure f
On Wed, Sep 16, 2020 at 11:21 AM Greg Kroah-Hartman
wrote:
>
> On Wed, Sep 16, 2020 at 11:02:39AM +0300, Oded Gabbay wrote:
> > On Wed, Sep 16, 2020 at 10:41 AM Greg Kroah-Hartman
> > wrote:
> > >
> > > On Wed, Sep 16, 2020 at 09:36:23AM +0300, Oded Gabbay wr
On Wed, Sep 16, 2020 at 10:41 AM Greg Kroah-Hartman
wrote:
>
> On Wed, Sep 16, 2020 at 09:36:23AM +0300, Oded Gabbay wrote:
> > On Wed, Sep 16, 2020 at 9:25 AM Greg Kroah-Hartman
> > wrote:
> > >
> > > On Tue, Sep 15, 2020 at 11:49:12PM +0300, Oded Gabbay wr
On Wed, Sep 16, 2020 at 9:25 AM Greg Kroah-Hartman
wrote:
>
> On Tue, Sep 15, 2020 at 11:49:12PM +0300, Oded Gabbay wrote:
> > On Tue, Sep 15, 2020 at 11:42 PM David Miller wrote:
> > >
> > > From: Oded Gabbay
> > > Date: Tue, 15 Sep 2020 20:10:08 +0300
&
On Wed, Sep 16, 2020 at 1:34 AM David Miller wrote:
>
> From: Oded Gabbay
> Date: Wed, 16 Sep 2020 00:20:12 +0300
>
> > I completely understand but you didn't answer my question. How come
> > there are drivers which create netdev objects, and specifically sgi-xp
>
On Mon, Sep 14, 2020 at 7:50 PM Jakub Kicinski wrote:
>
> On Mon, 14 Sep 2020 13:48:14 + Omer Shpigelman wrote:
> > On Thu, Sep 10, 2020 at 11:31 PM Jakub Kicinski wrote:
> > > On Thu, 10 Sep 2020 23:17:59 +0300 Oded Gabbay wrote:
> > > > > Doesn
On Wed, Sep 16, 2020 at 12:37 AM Andrew Lunn wrote:
>
> > I completely understand but you didn't answer my question. How come
> > there are drivers which create netdev objects, and specifically sgi-xp
> > in misc (but I also saw it in usb drivers) that live outside
> > drivers/net ? Why doesn't yo
On Wed, Sep 16, 2020 at 12:04 AM Jakub Kicinski wrote:
>
> On Tue, 15 Sep 2020 23:46:58 +0300 Oded Gabbay wrote:
> > On Tue, Sep 15, 2020 at 11:35 PM Jakub Kicinski wrote:
> > > On Tue, 15 Sep 2020 20:10:08 +0300 Oded Gabbay wrote:
> > > > Hello,
> > > &
On Tue, Sep 15, 2020 at 11:42 PM David Miller wrote:
>
> From: Oded Gabbay
> Date: Tue, 15 Sep 2020 20:10:08 +0300
>
> > This is the second version of the patch-set to upstream the GAUDI NIC code
> > into the habanalabs driver.
> >
> > The only modification fr
On Tue, Sep 15, 2020 at 11:35 PM Jakub Kicinski wrote:
>
> On Tue, 15 Sep 2020 20:10:08 +0300 Oded Gabbay wrote:
> > Hello,
> >
> > This is the second version of the patch-set to upstream the GAUDI NIC code
> > into the habanalabs driver.
> >
> > The o
From: Omer Shpigelman
The user needs this information when working in a distributed environment
with master/slave configuration. All the slaves get their MAC addresses
from the driver and send them to the master.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded
Hello,
This is the second version of the patch-set to upstream the GAUDI NIC code
into the habanalabs driver.
The only modification from v2 is in the ethtool patch (patch 12). Details
are in that patch's commit message.
Link to v2 cover letter:
https://lkml.org/lkml/2020/9/12/201
Thanks,
Oded
Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/device.c | 6 +-
drivers/misc/habanalabs/common/habanalabs.h | 3 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 20 +-
drivers/misc/habanalabs/gaudi/gaudi.c | 1 +
drivers/misc/habanalabs/gaudi/gaudiP.h
HW. The user should provide the
device virtual address of the WQ.
- Unset WQ: reset the WQ configuration in the HW.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/common/habanalabs_ioctl.c | 10 +-
drivers/misc/habanalabs
ed opcodes are:
- Create a QP
- Set requester context
- Set responder context
- Destroy a QP
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/habanalabs.h | 3 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 98
From: Omer Shpigelman
Add new structures and messages that the driver use to interact with the
firmware to receive information and events (errors) about GAUDI's NIC.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/include/c
on QMAN errors from the firmware.
However, the nic_ports_mask is still initialized to 0. That means this code
won't initialize the QMANs just yet. That will be in a later patch.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/haban
the beginning of the
reset flow.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/context.c |1 +
drivers/misc/habanalabs/common/firmware_if.c | 44 +
drivers/misc/habanalabs/common/habanalabs.h | 13 +-
.../misc
From: Omer Shpigelman
Finally, enable the NIC engines. Initialize the NIC ports mask variable
with full mask so all ports will be initialized.
Call the NIC init/fini from the common code.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc
).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/gaudi.c | 13
drivers/misc/habanalabs/gaudi/gaudiP.h| 1 +
drivers/misc/habanalabs/gaudi/gaudi_nic.c | 95 +++
3 files changed, 109
nters strings.
- get_sset_count: get counters number.
- get_ethtool_stats: get counters values.
- get_module_info: get EEPROM type and length.
- get_module_eeprom: get EEPROM (supported in raw mode only).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Chang
elman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/Makefile| 2 +-
drivers/misc/habanalabs/gaudi/gaudi_nic.c | 3 +
.../misc/habanalabs/gaudi/gaudi_nic_dcbnl.c | 108 ++
3 files changed, 112 insertions(+), 1 deletion(-)
create
quality improvement) and not for setting the
transmission parameters. As a result, the Auto-negotiation is currently
supported only between Gaudi cards.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/Makefile|2
On Mon, Sep 14, 2020 at 11:07 PM Jakub Kicinski wrote:
>
> On Mon, 14 Sep 2020 03:24:13 +0200 Andrew Lunn wrote:
> > > +static void gaudi_nic_get_internal_stats(struct net_device *netdev, u64
> > > *data)
> > > +{
> > > + struct gaudi_nic_device **ptr = netdev_priv(netdev);
> > > + struct gau
On Mon, Sep 14, 2020 at 4:37 AM Andrew Lunn wrote:
>
> > +static int gaudi_nic_get_module_eeprom(struct net_device *netdev,
> > + struct ethtool_eeprom *ee, u8 *data)
> > +{
> > + struct gaudi_nic_device **ptr = netdev_priv(netdev);
> > + struct gaudi_ni
On Mon, Sep 14, 2020 at 4:39 AM Florian Fainelli wrote:
>
>
>
> On 9/12/2020 7:41 AM, Oded Gabbay wrote:
> > From: Omer Shpigelman
> >
> > The driver supports ethtool callbacks and provides statistics using the
> > device's profiling infrastructure (cores
On Sat, Sep 12, 2020 at 6:07 PM Randy Dunlap wrote:
>
> Hi,
>
> On 9/12/20 7:41 AM, Oded Gabbay wrote:
> > +#define HL_IOCTL_NIC _IOWR('H', 0x07, struct hl_nic_args)
>
>
> ioctl numbers ('H') should be documented in
> Documentation/userspace-api/i
on QMAN errors from the firmware.
However, the nic_ports_mask is still initialized to 0. That means this code
won't initialize the QMANs just yet. That will be in a later patch.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/haban
the beginning of the
reset flow.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Remove nic_debugfs_reset flag
- Remove kernel parameter of nic_rx_poll
- Fix all instances of reverse Christmas tree
- Remove obsolete TODOs
- Add
From: Omer Shpigelman
Add new structures and messages that the driver use to interact with the
firmware to receive information and events (errors) about GAUDI's NIC.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/include/c
From: Omer Shpigelman
The user needs this information when working in a distributed environment
with master/slave configuration. All the slaves get their MAC addresses
from the driver and send them to the master.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded
HW. The user should provide the
device virtual address of the WQ.
- Unset WQ: reset the WQ configuration in the HW.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse Christmas tree
.../misc
Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse Christmas tree
drivers/misc/habanalabs/common/device.c | 6 +-
drivers/misc/habanalabs/common/habanalabs.h | 3 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 20 +-
drivers/misc/habanalabs/gaudi
nters strings.
- get_sset_count: get counters number.
- get_ethtool_stats: get counters values.
- get_module_info: get EEPROM type and length.
- get_module_eeprom: get EEPROM (supported in raw mode only).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Chang
From: Omer Shpigelman
Finally, enable the NIC engines. Initialize the NIC ports mask variable
with full mask so all ports will be initialized.
Call the NIC init/fini from the common code.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc
).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse Christmas tree
drivers/misc/habanalabs/gaudi/gaudi.c | 13
drivers/misc/habanalabs/gaudi/gaudiP.h| 1 +
drivers/misc/habanalabs/gaudi
elman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse Christmas tree
drivers/misc/habanalabs/gaudi/Makefile| 2 +-
drivers/misc/habanalabs/gaudi/gaudi_nic.c | 3 +
.../misc/habanalabs/gaudi/gaudi_nic_dcbnl.c | 108
ed opcodes are:
- Create a QP
- Set requester context
- Set responder context
- Destroy a QP
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse Christmas tree
- Set QPC REQ burst size to 16. The QPC requester
Hello,
This is the second version of the patch-set to upstream the GAUDI NIC code
into the habanalabs driver.
Modifications were made following reviews of the first version and are
detailed in the commit message of each patch that was changed.
A general note I want to write here is that I remove
quality improvement) and not for setting the
transmission parameters. As a result, the Auto-negotiation is currently
supported only between Gaudi cards.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Fix all instances of reverse
On Fri, Sep 11, 2020 at 12:05 AM Florian Fainelli wrote:
>
>
>
> On 9/10/2020 1:32 PM, Oded Gabbay wrote:
> > On Thu, Sep 10, 2020 at 11:28 PM Jakub Kicinski wrote:
> >>
> >> On Thu, 10 Sep 2020 23:16:22 +0300 Oded Gabbay wrote:
> >>> On Thu
On Thu, Sep 10, 2020 at 11:38 PM Andrew Lunn wrote:
>
> On Thu, Sep 10, 2020 at 11:30:33PM +0300, Oded Gabbay wrote:
> > On Thu, Sep 10, 2020 at 11:25 PM Andrew Lunn wrote:
> > >
> > > > Can you please elaborate on how to do this with a single driver that
> &
On Thu, Sep 10, 2020 at 11:25 PM Andrew Lunn wrote:
>
> > Can you please elaborate on how to do this with a single driver that
> > is already in misc ?
> > As I mentioned in the cover letter, we are not developing a
> > stand-alone NIC. We have a deep-learning accelerator with a NIC
> > interface.
On Thu, Sep 10, 2020 at 11:28 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 23:16:22 +0300 Oded Gabbay wrote:
> > On Thu, Sep 10, 2020 at 11:01 PM Jakub Kicinski wrote:
> > > On Thu, 10 Sep 2020 19:11:11 +0300 Oded Gabbay wrote:
> > > > create mode 100
On Thu, Sep 10, 2020 at 11:31 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 23:17:59 +0300 Oded Gabbay wrote:
> > > Doesn't seem like this one shows any more information than can be
> > > queried with ethtool, right?
> > correct, it just displays it in
On Thu, Sep 10, 2020 at 11:19 PM Andrew Lunn wrote:
>
> > +static int gaudi_nic_get_link_ksettings(struct net_device *netdev,
> > + struct ethtool_link_ksettings *cmd)
> > +{
> > + struct gaudi_nic_device **ptr = netdev_priv(netdev);
> > + struct gaudi_n
On Thu, Sep 10, 2020 at 11:03 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 19:11:16 +0300 Oded Gabbay wrote:
> > +module_param(nic_rx_poll, int, 0444);
> > +MODULE_PARM_DESC(nic_rx_poll,
> > + "Enable NIC Rx polling mode (0 = no, 1 = yes, default no)");
On Thu, Sep 10, 2020 at 11:16 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 23:10:47 +0300 Oded Gabbay wrote:
> > On Thu, Sep 10, 2020 at 11:01 PM Jakub Kicinski wrote:
> > >
> > > On Thu, 10 Sep 2020 19:11:23 +0300 Oded Gabbay wrote:
> > > > From: Om
On Thu, Sep 10, 2020 at 11:01 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 19:11:11 +0300 Oded Gabbay wrote:
> > create mode 100644 drivers/misc/habanalabs/gaudi/gaudi_nic.c
> > create mode 100644 drivers/misc/habanalabs/gaudi/gaudi_nic.h
> > create mode 100644
On Thu, Sep 10, 2020 at 11:01 PM Jakub Kicinski wrote:
>
> On Thu, 10 Sep 2020 19:11:23 +0300 Oded Gabbay wrote:
> > From: Omer Shpigelman
> >
> > Add several debugfs entries to help us debug the NIC engines and ports and
> > also the communication layer of the DL
From: Omer Shpigelman
Add new structures and messages that the driver use to interact with the
firmware to receive information and events (errors) about GAUDI's NIC.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/include/c
HW. The user should provide the
device virtual address of the WQ.
- Unset WQ: reset the WQ configuration in the HW.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/common/habanalabs_ioctl.c | 10 +-
drivers/misc/habanalabs
Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/device.c | 6 +-
drivers/misc/habanalabs/common/habanalabs.h | 3 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 20 +-
drivers/misc/habanalabs/gaudi/gaudi.c | 1 +
drivers/misc/habanalabs/gaudi/gaudiP.h
).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/gaudi.c | 13
drivers/misc/habanalabs/gaudi/gaudiP.h| 1 +
drivers/misc/habanalabs/gaudi/gaudi_nic.c | 93 +++
3 files changed, 107
reconfiguring the link
- nic_pam4_tx_taps: configure PAM4 TX taps
- nic_polarity: configure polarity for NIC port lanes
- nic_check_link: configure whether to check the PCS link periodically
- nic_phy_auto_neg_lpbk: enable PHY auto-negotiation loopback
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
quality improvement) and not for setting the
transmission parameters. As a result, the Auto-negotiation is currently
supported only between Gaudi cards.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/Makefile|2
on QMAN errors from the firmware.
However, the nic_ports_mask is still initialized to 0. That means this code
won't initialize the QMANs just yet. That will be in a later patch.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/haban
elman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/gaudi/Makefile| 2 +-
drivers/misc/habanalabs/gaudi/gaudi_nic.c | 3 +
.../misc/habanalabs/gaudi/gaudi_nic_dcbnl.c | 108 ++
3 files changed, 112 insertions(+), 1 deletion(-)
create
the beginning of the
reset flow.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/context.c |1 +
drivers/misc/habanalabs/common/firmware_if.c | 44 +
drivers/misc/habanalabs/common/habanalabs.h | 13 +-
.../misc
nters strings.
- get_sset_count: get counters number.
- get_ethtool_stats: get counters values.
- get_module_info: get EEPROM type and length.
- get_module_eeprom: get EEPROM (supported in raw mode only).
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
dr
From: Omer Shpigelman
Finally, enable the NIC engines. Initialize the NIC ports mask variable
with full mask so all ports will be initialized.
Call the NIC init/fini from the common code.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc
From: Omer Shpigelman
The user needs this information when working in a distributed environment
with master/slave configuration. All the slaves get their MAC addresses
from the driver and send them to the master.
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded
ed opcodes are:
- Create a QP
- Set requester context
- Set responder context
- Destroy a QP
Signed-off-by: Omer Shpigelman
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/habanalabs.h | 3 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 98
This patch-set adds support for initializing and using the GAUDI NIC ports,
functioning as scale-out interconnect when doing distributed Deep Learning
training. The training can be performed over tens of thousands of GAUDIs
and it is done using the RDMA-over-converged-Ethernet (RoCE) v2 protocol.
78 matches
Mail list logo
