[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v1 3/9] parisc: Convert DMA map_page to map_phys interface
- To: "Jason Gunthorpe" <jgg@xxxxxxxxxx>
- From: "Leon Romanovsky" <leon@xxxxxxxxxx>
- Date: Mon, 06 Oct 2025 07:03:49 +0300
- Cc: "Marek Szyprowski" <m.szyprowski@xxxxxxxxxxx>, "Andreas Larsson" <andreas@xxxxxxxxxxx>, "Borislav Petkov" <bp@xxxxxxxxx>, "Dave Hansen" <dave.hansen@xxxxxxxxxxxxxxx>, "David Miller" <davem@xxxxxxxxxxxxx>, "Geoff Levand" <geoff@xxxxxxxxxxxxx>, "Helge Deller" <deller@xxxxxx>, "Ingo Molnar" <mingo@xxxxxxxxxx>, iommu@xxxxxxxxxxxxxxx, "James E.J. Bottomley" <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>, "Jason Wang" <jasowang@xxxxxxxxxx>, "Juergen Gross" <jgross@xxxxxxxx>, linux-alpha@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, linux-mips@xxxxxxxxxxxxxxx, linux-parisc@xxxxxxxxxxxxxxx, linuxppc-dev@xxxxxxxxxxxxxxxx, "Madhavan Srinivasan" <maddy@xxxxxxxxxxxxx>, "Matt Turner" <mattst88@xxxxxxxxx>, "Michael Ellerman" <mpe@xxxxxxxxxxxxxx>, "Michael S. Tsirkin" <mst@xxxxxxxxxx>, "Richard Henderson" <richard.henderson@xxxxxxxxxx>, sparclinux@xxxxxxxxxxxxxxx, "Stefano Stabellini" <sstabellini@xxxxxxxxxx>, "Thomas Bogendoerfer" <tsbogend@xxxxxxxxxxxxxxxx>, "Thomas Gleixner" <tglx@xxxxxxxxxxxxx>, virtualization@xxxxxxxxxxxxxxx, x86@xxxxxxxxxx, xen-devel@xxxxxxxxxxxxxxxxxxxx, "Magnus Lindholm" <linmag7@xxxxxxxxx>
- Delivery-date: Mon, 06 Oct 2025 04:04:39 +0000
- Feedback-id: i927946fb:Fastmail
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On Mon, Oct 6, 2025, at 02:31, Jason Gunthorpe wrote:
> On Sun, Oct 05, 2025 at 04:22:59PM +0300, Leon Romanovsky wrote:
>> @@ -582,7 +582,7 @@ ccio_io_pdir_entry(__le64 *pdir_ptr, space_t sid,
>> unsigned long vba,
>> ** Grab virtual index [0:11]
>> ** Deposit virt_idx bits into I/O PDIR word
>> */
>> - asm volatile ("lci %%r0(%1), %0" : "=r" (ci) : "r" (vba));
>> + asm volatile ("lci %%r0(%1), %0" : "=r" (ci) : "r" (pba));
>
> Don't know how I missed this, but this is the virtual address for the
> cache invalidate James mentioned
>
> So the optimal is to drop the lpa() and to use phys_to_virt() to get
> vba for this instruction.
The optimal is to keep parisc arch code as I did in v1 and don't change it too
much.
>
> Jason
|
