New: kernel BUG at drivers/pci/intel-iommu.c:1656 while registering memory for InfiniBand

https://bugzilla.kernel.org/show_bug.cgi?id=37402

Summary: kernel BUG at drivers/pci/intel-iommu.c:1656 while
registering memory for InfiniBand
Product: Drivers
Version: 2.5
Kernel Version: 2.6.38.6-26.rc1.fc15.x86_64
Platform: All
OS/Version: Linux
Tree: Fedora
Status: NEW
Severity: normal
Priority: P1
Component: Infiniband/RDMA
AssignedTo: drivers_infiniband-rdma-ztI5WcYan/[email protected]
ReportedBy: [email protected]
Regression: No

Created an attachment (id=61782)
--> (https://bugzilla.kernel.org/attachment.cgi?id=61782)
Crash dump

Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Hi intel-iommu guys,

It seems that the user is getting this BUG when doing something that essentially does
dma_map_sg() for 1GB of memory. AFAICT, the mlx4 driver is correctly doing

	pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
	pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));

during init, but the BUG being hit here is:

	BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);

Any suggestions on what might be going wrong here?

Thanks,
Roland

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html