Messages in this thread | | | Subject | Re: [HMM 12/15] mm/migrate: new memory migration helper for use with device memory v4 | From | Evgeny Baskakov <> | Date | Fri, 30 Jun 2017 16:19:25 -0700 |
| |
On 6/26/17 5:07 PM, Evgeny Baskakov wrote:
> Hi Jerome, > > The documentation shown above doesn't tell what the alloc_and_copy callback should do for source pages that have not been allocated yet. Instead, it unconditionally suggests checking if the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flags are set. > > Based on my testing and looking in the source code, I see that for such pages the respective 'src' PFN entries are always set to 0 without any flags. > > The sample driver specifically handles that by checking if there's no page in the 'src' entry, and ignores any flags in such case: > > struct page *spage = migrate_pfn_to_page(*src_pfns); > ... > if (spage && !(*src_pfns & MIGRATE_PFN_MIGRATE)) > continue; > > if (spage && (*src_pfns & MIGRATE_PFN_DEVICE)) { > > I would like to suggest reflecting that in the documentation. Or, which would be more logical, migrate_vma could keep the zero in the PFN entries for not allocated pages, but set the MIGRATE_PFN_MIGRATE flag anyway. > > Thanks! > > Evgeny Baskakov > NVIDIA >
Hi Jerome,
It seems that the kernel can pass 0 in src_pfns for pages that it cannot migrate (i.e. the kernel knows that they cannot migrate prior to calling alloc_and_copy).
So, a zero in src_pfns can mean either "the page is not allocated yet" or "the page cannot migrate".
Can migrate_vma set the MIGRATE_PFN_MIGRATE flag for not allocated pages? On the driver side it is difficult to differentiate between the cases.
Thanks!
Evgeny Baskakov NVIDIA
| |