Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Siddha, Suresh B
On Tue, Apr 03, 2007 at 01:39:43PM -0600, Eric W. Biederman wrote: > "Siddha, Suresh B" <[EMAIL PROTECTED]> writes: > > Further now that we cache the msi message that read_msi_msg should go > away and we should use the cached version from the msi_desc. Ok. Then this patch is a must. > > Don't

Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Eric W. Biederman
"Siddha, Suresh B" <[EMAIL PROTECTED]> writes: > set_msi_irq_affinity() is already doing read_msi_msg(). So the mask operation > before this should atleast get flushed before we modify the irq destination > information. We modify irq reception information in assign_irq_vector, before that. With

Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Siddha, Suresh B
On Tue, Apr 03, 2007 at 01:41:49AM -0600, Eric W. Biederman wrote: > When we mask or unmask a msi-x irqs the writes may be posted because > we are writing to memory mapped region. This means the mask and > unmask don't happen immediately but at some unspecified time in the > future. Which is out

RE: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Williams, Mitch A
Acked-by: Mitch Williams <[EMAIL PROTECTED]> >This is a simplified and actually more comprehensive form of a bug >fix from Mitch Williams <[EMAIL PROTECTED]>. [snip] >Then if people do have a kernel message stating "No irq for vector" we >will know it is yet another novel cause that needs a

[PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Eric W. Biederman
This is a simplified and actually more comprehensive form of a bug fix from Mitch Williams <[EMAIL PROTECTED]>. When we mask or unmask a msi-x irqs the writes may be posted because we are writing to memory mapped region. This means the mask and unmask don't happen immediately but at some

[PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Eric W. Biederman
This is a simplified and actually more comprehensive form of a bug fix from Mitch Williams [EMAIL PROTECTED]. When we mask or unmask a msi-x irqs the writes may be posted because we are writing to memory mapped region. This means the mask and unmask don't happen immediately but at some

RE: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Williams, Mitch A
Acked-by: Mitch Williams [EMAIL PROTECTED] This is a simplified and actually more comprehensive form of a bug fix from Mitch Williams [EMAIL PROTECTED]. [snip] Then if people do have a kernel message stating No irq for vector we will know it is yet another novel cause that needs a complete new

Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Siddha, Suresh B
On Tue, Apr 03, 2007 at 01:41:49AM -0600, Eric W. Biederman wrote: When we mask or unmask a msi-x irqs the writes may be posted because we are writing to memory mapped region. This means the mask and unmask don't happen immediately but at some unspecified time in the future. Which is out of

Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Eric W. Biederman
Siddha, Suresh B [EMAIL PROTECTED] writes: set_msi_irq_affinity() is already doing read_msi_msg(). So the mask operation before this should atleast get flushed before we modify the irq destination information. We modify irq reception information in assign_irq_vector, before that. With my

Re: [PATCH] msi: Immediately mask and unmask msi-x irqs.

2007-04-03 Thread Siddha, Suresh B
On Tue, Apr 03, 2007 at 01:39:43PM -0600, Eric W. Biederman wrote: Siddha, Suresh B [EMAIL PROTECTED] writes: Further now that we cache the msi message that read_msi_msg should go away and we should use the cached version from the msi_desc. Ok. Then this patch is a must. Don't we need the