Re: pci_enable_msi() for everyone?

[David S. Miller]

From: Jeff Garzik <jgarzik@xxxxxxxxx>
Date: Mon, 06 Jun 2005 19:53:55 -0400

> A technology (MSI) allows one to more efficiently call interrupt 
> handlers, with fewer bus reads...  and you want to add a test to each 
> interrupt handler -- a test which adds several bus reads to the hot path 
> of every MSI driver?

I think he's saying something different.

He is saying this test goes in the spot where you select
which interrupt handler to register, in place of the current
logic which call pci_enable_msi() and checks the return value.

MSI unaware drivers are OK because they can only assume
looser semantics (shared interrupts possible, no DMA ordering
guarentees wrt. interrupt delivery etc.) in their interrupt
handlers.

So I guess what Greg is proposing is not a bad idea afterall.
-
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/