search for: mlx5_core

...> > > > From: Leon Romanovsky <leonro at nvidia.com> > > > > Remove exposed driver version as it was done in other drivers, so module > > version will work correctly by displaying the kernel version for which it is > > compiled. > > > > And move mlx5_core module name to general include, so auxiliary drivers > > will be able to use it as a basis for a name in their device ID tables. > > > > Signed-off-by: Leon Romanovsky <leonro at nvidia.com> > > --- > > drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2...

...klisted, so that it doesn't load at boot time? We have Infiniband adapters which are not completely supported by CentOS and we want to silence the error messages for the time being. I tried with the files /etc/modprobe.d/blacklist /etc/modprobe.d/blacklist.conf and with entries mlx5_core mlx5_ib blacklist mlx5_core blacklist mlx5_ib install mlx5_core /dev/null install mlx5_ib /dev/null all found on different websites. None of these entries helps. mlx5_core and mlx5_ib are still loaded and the system is flooded with error messages. Cheers frank

...tion. v0: https://lore.kernel.org/lkml/20201026111849.1035786-1-leon at kernel.org/ -------------------------------------------------------------- Hi, This patch set converts mlx5 driver to use auxiliary bus [1]. In this series, we are connecting three subsystems (VDPA, netdev and RDMA) through mlx5_core PCI driver. That driver is responsible to create proper devices based on supported firmware. First four patches are preparitions and fixes that were spotted during code development, rest is the conversion itself. Thanks [1] https://lore.kernel.org/lkml/20201023003338.1285642-1-david.m.ertman at...

...rig/drivers/vdpa/Kconfig >>>> +++ linux-next-20200917/drivers/vdpa/Kconfig >>>> @@ -31,7 +31,7 @@ config IFCVF >>>> >>>> config MLX5_VDPA >>>> bool "MLX5 VDPA support library for ConnectX devices" >>>> - depends on MLX5_CORE >>>> + depends on VHOST_IOTLB && MLX5_CORE >>>> default n >>> >>> While we are here, can anyone who apply this patch delete the "default n" line? >>> It is by default "n". > > I can do that > >>> &g...

...rig/drivers/vdpa/Kconfig >>>> +++ linux-next-20200917/drivers/vdpa/Kconfig >>>> @@ -31,7 +31,7 @@ config IFCVF >>>> >>>> config MLX5_VDPA >>>> bool "MLX5 VDPA support library for ConnectX devices" >>>> - depends on MLX5_CORE >>>> + depends on VHOST_IOTLB && MLX5_CORE >>>> default n >>> >>> While we are here, can anyone who apply this patch delete the "default n" line? >>> It is by default "n". > > I can do that > >>> &g...

...> I know it's in our plans but I see your point. Let me know if you > > > prefer me to send the patch that fixes the 'depends' thing or defer it > > > to a later time. > > > > Not sure what's the depends thing. > > > > Use "select MLX5_CORE" > instead of "depends on MLX5_CORE" > > Wasn't this agreed upon? Hmm I don't know. I recall a similar discussion around VHOST_IOTLB. That's different ... I see [linux]$ git grep MLX5_CORE|grep depends drivers/infiniband/hw/mlx5/Kconfig: depends on NETDEV...

...NTUPLE CloudF DCB VxLAN NVGRE PTP ... kernel: [ 250.279739] Compat-mlnx-ofed backport release: f8de107 kernel: [ 250.280006] Backport based on mlnx_ofed/mlnx-ofa_kernel-4.0.git f8de107 kernel: [ 250.280261] compat.git: mlnx_ofed/mlnx-ofa_kernel-4.0.git kernel: [ 250.287865] mlx5_core 0000:3b:00.0: firmware version: 14.23.1020 kernel: [ 250.293492] tun: Universal TUN/TAP device driver, 1.6 kernel: [ 250.293731] tun: (C) 1999-2004 Max Krasnyansky <maxk at qualcomm.com> kernel: [ 250.360407] nbd: registered device at major 43 kernel: [ 250.367659] nf_conn...

...We have Infiniband adapters which are not > completely supported by CentOS and we want to silence the error messages > for the time being. > > I tried with the files > > ? /etc/modprobe.d/blacklist > ? /etc/modprobe.d/blacklist.conf > > and with entries > > ? mlx5_core > ? mlx5_ib > > ? blacklist mlx5_core > ? blacklist mlx5_ib > > ? install mlx5_core /dev/null > ? install mlx5_ib /dev/null > > all found on different websites. > > None of these entries helps.? mlx5_core and mlx5_ib are still loaded and > the system is...

...ers/vdpa/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- linux-next-20200917.orig/drivers/vdpa/Kconfig +++ linux-next-20200917/drivers/vdpa/Kconfig @@ -31,7 +31,7 @@ config IFCVF config MLX5_VDPA bool "MLX5 VDPA support library for ConnectX devices" - depends on MLX5_CORE + depends on VHOST && MLX5_CORE default n help Support library for Mellanox VDPA drivers. Provides code that is

...t; > > see. Or > > > am I missing something? > > > > and why do we care whether irqs are freed on shutdown? > > > Had to ask around a bit to find out the answer: there can be issues with kexec > IRQ allocation on some platforms. It is documented here [0] for mlx5_core. > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/mellanox/mlx5/core/main.c#n2129 > > Thanks, > Dragos It's quite weird. * Some platforms requiring freeing the IRQ's in the shutdown * flow. If they aren't freed they...

...t; > > am I missing something? > > > > > > and why do we care whether irqs are freed on shutdown? > > > > > Had to ask around a bit to find out the answer: there can be issues with kexec > > IRQ allocation on some platforms. It is documented here [0] for mlx5_core. > > > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/mellanox/mlx5/core/main.c#n2129 > > > > Thanks, > > Dragos > > It's quite weird. > * Some platforms requiring freeing the IRQ's in the shutdo...

...> > > > > > > and why do we care whether irqs are freed on shutdown? > > > > > > > Had to ask around a bit to find out the answer: there can be issues with > > > kexec > > > IRQ allocation on some platforms. It is documented here [0] for mlx5_core. > > > > > > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/mellanox/mlx5/core/main.c#n2129 > > > > > > Thanks, > > > Dragos > > > > It's quite weird. > > ???????? * Some platforms re...

...ers/vdpa/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- linux-next-20200917.orig/drivers/vdpa/Kconfig +++ linux-next-20200917/drivers/vdpa/Kconfig @@ -31,7 +31,7 @@ config IFCVF config MLX5_VDPA bool "MLX5 VDPA support library for ConnectX devices" - depends on MLX5_CORE + depends on VHOST_IOTLB && MLX5_CORE default n help Support library for Mellanox VDPA drivers. Provides code that is

...; > > > --- linux-next-20200917.orig/drivers/vdpa/Kconfig > > +++ linux-next-20200917/drivers/vdpa/Kconfig > > @@ -31,7 +31,7 @@ config IFCVF > > > > config MLX5_VDPA > > bool "MLX5 VDPA support library for ConnectX devices" > > - depends on MLX5_CORE > > + depends on VHOST_IOTLB && MLX5_CORE > > default n > > While we are here, can anyone who apply this patch delete the "default n" line? > It is by default "n". > > Thanks Hmm other drivers select VHOST_IOTLB, why not do the same? &gt...

...dpa/Kconfig > > > >>>> @@ -31,7 +31,7 @@ config IFCVF > > > >>>> > > > >>>> config MLX5_VDPA > > > >>>> bool "MLX5 VDPA support library for ConnectX devices" > > > >>>> - depends on MLX5_CORE > > > >>>> + depends on VHOST_IOTLB && MLX5_CORE > > > >>>> default n > > > >>> > > > >>> While we are here, can anyone who apply this patch delete the "default n" line? > > > >>> It...

...config > > > > +++ linux-next-20200917/drivers/vdpa/Kconfig > > > > @@ -31,7 +31,7 @@ config IFCVF > > > > > > > > config MLX5_VDPA > > > > bool "MLX5 VDPA support library for ConnectX devices" > > > > - depends on MLX5_CORE > > > > + depends on VHOST_IOTLB && MLX5_CORE > > > > default n > > > > > > While we are here, can anyone who apply this patch delete the "default n" line? > > > It is by default "n". > > I can do that > &g...

On 11/15/2017 10:35 AM, Frank Thommen wrote: > > I tried with the files > ? /etc/modprobe.d/blacklist > ? /etc/modprobe.d/blacklist.conf > and with entries > ? blacklist mlx5_core > ? blacklist mlx5_ib The "blacklist" entries prevent a module being loaded by its alias (typically a PCI ID), but not from being loaded if something explicitly loads it by module name.? Most likely, those modules are included in your initrd. I'd suggest using the entries des...

On 11/15/2017 07:50 PM, Gordon Messmer wrote: > On 11/15/2017 10:35 AM, Frank Thommen wrote: >> >> I tried with the files >> /etc/modprobe.d/blacklist >> /etc/modprobe.d/blacklist.conf >> and with entries >> blacklist mlx5_core >> blacklist mlx5_ib > > The "blacklist" entries prevent a module being loaded by its alias > (typically a PCI ID), but not from being loaded if something explicitly > loads it by module name. Most likely, those modules are included in > your initrd. > > I...

...down. At least that's what I > > see. Or > > am I missing something? > > and why do we care whether irqs are freed on shutdown? > Had to ask around a bit to find out the answer: there can be issues with kexec IRQ allocation on some platforms. It is documented here [0] for mlx5_core. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/mellanox/mlx5/core/main.c#n2129 Thanks, Dragos

Otherwise the virtqueue object to instate could point to invalid address that was unmapped from the MTT: mlx5_core 0000:41:04.2: mlx5_cmd_out_err:782:(pid 8321): CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status bad parameter(0x3), syndrome (0x5fa1c), err(-22) Fixes: cae15c2ed8e6 ("vdpa/mlx5: Implement susupend virtqueue callback") Cc: Eli Cohen <elic at nvidia.com> Signed-off-by: Si-...