Re: [PATCH] rds_rdma: don't assume infiniband device is PCI

[Thadeu Lima de Souza Cascardo]

On Fri, Jan 06, 2012 at 01:57:50PM -0200, Thadeu Lima de Souza Cascardo wrote:
> On Thu, Jan 05, 2012 at 03:05:24PM -0200, Thadeu Lima de Souza Cascardo wrote:
> > > ----- Original Message -----
> > > From: cascardo@xxxxxxxxxxxxxxxxxx
> > > To: venkat.x.venkatsubra@xxxxxxxxxx
> > > Cc: davem@xxxxxxxxxxxxx, netdev@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, cascardo@xxxxxxxxxxxxxxxxxx, dledford@xxxxxxxxxx, Jes.Sorensen@xxxxxxxxxx, rds-devel@xxxxxxxxxxxxxx
> > > Sent: Wednesday, January 4, 2012 4:03:42 PM GMT -06:00 US/Canada Central
> > > Subject: [PATCH] rds_rdma: don't assume infiniband device is PCI
> > > 
> > > RDS code assumes that the struct ib_device dma_device member, which is a
> > > pointer, points to a struct device embedded in a struct pci_dev.
> > > 
> > > This is not the case for ehca, for example, which is a OF driver, and
> > > makes dma_device point to a struct device embedded in a struct
> > > platform_device.
> > > 
> > > This will make the system crash when rds_rdma is loaded in a system
> > > with ehca, since it will try to access the bus member of a non-existent
> > > struct pci_dev.
> > > 
> > > The only reason rds_rdma uses the struct pci_dev is to get the NUMA node
> > > the device is attached to. Using dev_to_node for that is much better,
> > > since it won't assume which bus the infiniband is attached to.
> > > 
> > > Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@xxxxxxxxxxxxxxxxxx>
> > > Cc: dledford@xxxxxxxxxx
> > > Cc: Jes.Sorensen@xxxxxxxxxx
> > > Cc: Venkat Venkatsubra <venkat.x.venkatsubra@xxxxxxxxxx>
> > > Cc: rds-devel@xxxxxxxxxxxxxx
> > > ---
> > >  net/rds/ib.h |    3 +--
> > >  1 files changed, 1 insertions(+), 2 deletions(-)
> > > 
> > > diff --git a/net/rds/ib.h b/net/rds/ib.h
> > > index edfaaaf..8d2b3d5 100644
> > > --- a/net/rds/ib.h
> > > +++ b/net/rds/ib.h
> > > @@ -186,8 +186,7 @@ struct rds_ib_device {
> > >  	struct work_struct	free_work;
> > >  };
> > >  
> > > -#define pcidev_to_node(pcidev) pcibus_to_node(pcidev->bus)
> > > -#define ibdev_to_node(ibdev) pcidev_to_node(to_pci_dev(ibdev->dma_device))
> > > +#define ibdev_to_node(ibdev) dev_to_node(ibdev->dma_device)
> > >  #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev)
> > >  
> > >  /* bits for i_ack_flags */
> > > -- 
> > > 1.7.4.4
> > > 
> > 
> > On Thu, Jan 05, 2012 at 08:56:34AM -0800, Venkat Venkatsubra wrote:
> > > Hi Cascardo,
> > > 
> > > Your changes look good to me.
> > > But our latest code doesn't use this rdsibdev_to_node macro anywhere.
> > > Checking with the people in my group who know the history of the NUMA feature.
> > > Trying to find out if the call to kzalloc_node() can be replaced by kzalloc().
> > > In which case this macro can be removed.
> > > 
> > > I will keep you posted.
> > > 
> > > Venkat
> > > 
> > 
> > Hi, Venkat.
> > 
> > Do you have any public tree where we can track the last changes in RDS?
> > Note that I have changed ibsdev_to_node, which rdsibdev_to_node makes
> > use of. Anyway, replacing kzalloc_node with kzalloc has crossed my mind,
> > but since I was not sure if this would affect latency of RDS in any use
> > cases, I kept that and used a better function to get the node from the
> > device. And we have dev_to_node since 2.6.20, so it should not be a
> > problem to use it.
> > 
> > If possible, keep everyone copied and avoid top posting.
> > 
> > Regards.
> > Cascardo.
> 
> Just to make it clean, ibdev_to_node is used in Linus' tree and
> next/master as of today and this patch fixes a real oops. I should have
> probably added the stack trace in the log message. For completion, here
> it is, running 3.2.0-rc7-00039-g89307ba:
> 
> NET: Registered protocol family 21
> Registered RDS/iwarp transport
> Unable to handle kernel paging request for data at address 0x00000088
> Faulting instruction address: 0xc0000000000336d0
> cpu 0x6: Vector: 300 (Data Access) at [c0000000ddd837e0]
>     pc: c0000000000336d0: .pcibus_to_node+0x0/0x10
>     lr: d000000004590de0: .rds_ib_add_one+0x100/0x360 [rds_rdma]
>     sp: c0000000ddd83a60
>    msr: 8000000000009032
>    dar: 88
>  dsisr: 40000000
>   current = 0xc0000000ee6c0000
>   paca    = 0xc000000006c32d00
>     pid   = 8574, comm = modprobe
> enter ? for help
> [link register   ] d000000004590de0 .rds_ib_add_one+0x100/0x360
> [rds_rdma]
> [c0000000ddd83a60] d000000004590d88 .rds_ib_add_one+0xa8/0x360
> [rds_rdma] (unreliable)
> [c0000000ddd83b10] d000000003195240 .ib_register_client+0xc0/0x120
> [ib_core]
> [c0000000ddd83bb0] d00000000459074c .rds_ib_init+0x2c/0xf0 [rds_rdma]
> [c0000000ddd83c30] d000000004590144 .rds_rdma_init+0xe4/0x180 [rds_rdma]
> [c0000000ddd83cd0] c00000000000aa54 .do_one_initcall+0x64/0x1e0
> [c0000000ddd83d90] c0000000000d359c .SyS_init_module+0xcc/0x220
> [c0000000ddd83e30] c0000000000097e4 syscall_exit+0x0/0x40
> --- Exception: c00 (System Call) at 00000fff7dc3d3d8
> SP (fffe87eeeb0) is in userspace
> 
> Regards.
> Cascardo.
> 

David,

The References was broken by Venkat email, so patchwork is not catching
up the new messages in the thread. At least, that's what I expect it
uses. So, I am sending this message with a fixed References. Sorry for
that.

Regards.
Cascardo.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/