Messages in this thread | | | Date | Thu, 10 Jul 2008 06:03:51 -0700 | From | Andrew Morton <> | Subject | Re: [PATCH 14/34] AMD IOMMU: clue initialization code together |
| |
On Thu, 10 Jul 2008 14:37:47 +0200 Joerg Roedel <joerg.roedel@amd.com> wrote:
> > Is there a reason for using __get_free_pages() in this manner everywhere? > > kmalloc() or kzalloc() are unsuitable? > > Yes. The device table has to be page aligned and has a maximum size of > 2 MB.
OK
> > > + if (amd_iommu_dev_table == NULL) > > > + goto out; > > > + > > > + /* > > > + * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the > > > + * IOMMU see for that device > > > + */ > > > + amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL, > > > + get_order(alias_table_size)); > > Hmm, maybe this table will fit into a kmalloc allocation. Its maximum > size is 128 kb.
Might as well keep it all consistent in that case.
| |