|
|
|
|
|
|
|
|
|
|
xen-devel
Re: [Xen-devel] [PATCH] Re-enable MSI support
On 10/12/2008 15:24, "Jiang, Yunhong" <yunhong.jiang@xxxxxxxxx> wrote:
>> Except, since it is used as a read_lock most of the time it does not
>> actually protect things in the way a spinlock would do.
>
> Ahh, yes, I didn't realize this. So how do you think changing it to spinlock,
> since it is not performance ciritical. Or do you know how much benifit for
> read_lock?
A spinlock is actually faster unless the read sections are frequently
contended, in which case the lost parallelism counteracts the faster lock.
-- Keir
> Also, as for the reference to pci_dev, do you have plan to add such support?
> For example, I'm not sure if we can return fail for pci_remove_device if there
> is still reference to it? Will dom0 support such failure?
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
<Prev in Thread] |
Current Thread |
[Next in Thread>
|
- [Xen-devel] [PATCH] Re-enable MSI support, Jiang, Yunhong
- Re: [Xen-devel] [PATCH] Re-enable MSI support, Espen Skoglund
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Tian, Kevin
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Jiang, Yunhong
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Espen Skoglund
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Jiang, Yunhong
- Re: [Xen-devel] [PATCH] Re-enable MSI support,
Keir Fraser <=
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Espen Skoglund
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Espen Skoglund
- Re: [Xen-devel] [PATCH] Re-enable MSI support, Keir Fraser
- RE: [Xen-devel] [PATCH] Re-enable MSI support, Jiang, Yunhong
|
|
|
|
|