diff options
| author | Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> | 2015-10-09 08:32:21 +0530 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2015-10-12 15:30:09 +1100 |
| commit | 891121e6c02c6242487aa4ea1d5c75b7ecdc45ee (patch) | |
| tree | 118c5b4df68fe004438e4a1a629b04fbeed9b417 /arch/powerpc/kernel | |
| parent | ec2640b114d535ba7d895b6ee353791d542f2407 (diff) | |
powerpc/mm: Differentiate between hugetlb and THP during page walk
We need to properly identify whether a hugepage is an explicit or
a transparent hugepage in follow_huge_addr(). We used to depend
on hugepage shift argument to do that. But in some case that can
result in wrong results. For ex:
On finding a transparent hugepage we set hugepage shift to PMD_SHIFT.
But we can end up clearing the thp pte, via pmdp_huge_get_and_clear.
We do prevent reusing the pfn page via the usage of
kick_all_cpus_sync(). But that happens after we updated the pte to 0.
Hence in follow_huge_addr() we can find hugepage shift set, but transparent
huge page check fail for a thp pte.
NOTE: We fixed a variant of this race against thp split in commit
691e95fd7396905a38d98919e9c150dbc3ea21a3
("powerpc/mm/thp: Make page table walk safe against thp split/collapse")
Without this patch, we may hit the BUG_ON(flags & FOLL_GET) in
follow_page_mask occasionally.
In the long term, we may want to switch ppc64 64k page size config to
enable CONFIG_ARCH_WANT_GENERAL_HUGETLB
Reported-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/kernel')
| -rw-r--r-- | arch/powerpc/kernel/eeh.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/kernel/io-workarounds.c | 2 |
2 files changed, 3 insertions, 2 deletions
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e968533e3e05..00ba5de12256 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -351,7 +351,8 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) * worried about _PAGE_SPLITTING/collapse. Also we will not hit * page table free, because of init_mm. */ - ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift); + ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token, + NULL, &hugepage_shift); if (!ptep) return token; WARN_ON(hugepage_shift); diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index 63d9cc4d7366..5f8613ceb97f 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -76,7 +76,7 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) * a page table free due to init_mm */ ptep = __find_linux_pte_or_hugepte(init_mm.pgd, vaddr, - &hugepage_shift); + NULL, &hugepage_shift); if (ptep == NULL) paddr = 0; else { |