[IB] 2.6.31-rc9: SW2HW_EQ failed on Dell R610

The problem with the interrupts is not solved in rc9:

[    7.747804] mlx4_core: Mellanox ConnectX core driver v0.01 (May 1,
2007)
[    7.747806] mlx4_core: Initializing 0000:04:00.0
[    7.747839] mlx4_core 0000:04:00.0: PCI INT A -> GSI 38 (level, low) ->
IRQ 38
[    7.747850] mlx4_core 0000:04:00.0: setting latency timer to 64
[    9.759505] mlx4_core 0000:04:00.0: irq 62 for MSI/MSI-X
[    9.759513] mlx4_core 0000:04:00.0: irq 63 for MSI/MSI-X
[    9.759520] mlx4_core 0000:04:00.0: irq 64 for MSI/MSI-X
[    9.759527] mlx4_core 0000:04:00.0: irq 65 for MSI/MSI-X
[    9.759533] mlx4_core 0000:04:00.0: irq 66 for MSI/MSI-X
[    9.759540] mlx4_core 0000:04:00.0: irq 67 for MSI/MSI-X
[    9.759547] mlx4_core 0000:04:00.0: irq 68 for MSI/MSI-X
[    9.759555] mlx4_core 0000:04:00.0: irq 69 for MSI/MSI-X
[    9.759561] mlx4_core 0000:04:00.0: irq 70 for MSI/MSI-X
[    9.759569] mlx4_core 0000:04:00.0: irq 71 for MSI/MSI-X
[    9.759576] mlx4_core 0000:04:00.0: irq 72 for MSI/MSI-X
[    9.759583] mlx4_core 0000:04:00.0: irq 73 for MSI/MSI-X
[    9.759590] mlx4_core 0000:04:00.0: irq 74 for MSI/MSI-X
[    9.759596] mlx4_core 0000:04:00.0: irq 75 for MSI/MSI-X
[    9.759603] mlx4_core 0000:04:00.0: irq 76 for MSI/MSI-X
[    9.759611] mlx4_core 0000:04:00.0: irq 77 for MSI/MSI-X
[    9.759617] mlx4_core 0000:04:00.0: irq 78 for MSI/MSI-X
[    9.759624] mlx4_core 0000:04:00.0: irq 79 for MSI/MSI-X
[    9.759631] mlx4_core 0000:04:00.0: irq 80 for MSI/MSI-X
[    9.759638] mlx4_core 0000:04:00.0: irq 81 for MSI/MSI-X
[    9.759645] mlx4_core 0000:04:00.0: irq 82 for MSI/MSI-X
[    9.759652] mlx4_core 0000:04:00.0: irq 83 for MSI/MSI-X
[    9.759658] mlx4_core 0000:04:00.0: irq 84 for MSI/MSI-X
[    9.759666] mlx4_core 0000:04:00.0: irq 85 for MSI/MSI-X
[    9.759672] mlx4_core 0000:04:00.0: irq 86 for MSI/MSI-X
[    9.759679] mlx4_core 0000:04:00.0: irq 87 for MSI/MSI-X
[    9.759686] mlx4_core 0000:04:00.0: irq 88 for MSI/MSI-X
[    9.759692] mlx4_core 0000:04:00.0: irq 89 for MSI/MSI-X
[    9.759699] mlx4_core 0000:04:00.0: irq 90 for MSI/MSI-X
[    9.759706] mlx4_core 0000:04:00.0: irq 91 for MSI/MSI-X
[    9.759712] mlx4_core 0000:04:00.0: irq 92 for MSI/MSI-X
[    9.759720] mlx4_core 0000:04:00.0: irq 93 for MSI/MSI-X
[    9.759726] mlx4_core 0000:04:00.0: irq 94 for MSI/MSI-X
[   10.044580] mlx4_core 0000:04:00.0: SW2HW_EQ failed (-5)
[   10.058011] mlx4_core 0000:04:00.0: Failed to initialize event queue
table, aborting.
[   10.076589] mlx4_core 0000:04:00.0: PCI INT A disabled
[   10.086805] mlx4_core: probe of 0000:04:00.0 failed with error -5

 > The problem with the interrupts is not solved in rc9:

Yes, by the time we got this all resolved, it was already rc8 and I
though 2.6.31 was right around the corner ... the issue didn't seem
severe enough to stick in so late in the cycle, so I queued the patch
for .32 with a cc to stable to get in 2.6.31.1.

The workaround of limiting possible cpus to 16 should be OK for the time
between 2.6.31 and 2.6.31.1.

 - R.

On Tue, 8 Sep 2009, Roland Dreier wrote:

The workaround of limiting possible cpus to 16 should be OK for the time
between 2.6.31 and 2.6.31.1.

Why not merge it immediately? Dell R610s are fairly standard.

 > > The workaround of limiting possible cpus to 16 should be OK for the time
 > > between 2.6.31 and 2.6.31.1.

 > Why not merge it immediately? Dell R610s are fairly standard.

I think it's too late now post-rc9 ... it's not a regression (I think
the bug has been there since 2.6.29) and I think Linus would prefer to
minimize the # of patches that go in now.

 - R.