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/kvm | |
| 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/kvm')
| -rw-r--r-- | arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_rm_mmu.c | 8 | ||||
| -rw-r--r-- | arch/powerpc/kvm/e500_mmu_host.c | 2 |
3 files changed, 7 insertions, 5 deletions
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 1f9c0a17f445..3fc2ba784a71 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -543,7 +543,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ local_irq_save(flags); ptep = find_linux_pte_or_hugepte(current->mm->pgd, - hva, NULL); + hva, NULL, NULL); if (ptep) { pte = kvmppc_read_update_linux_pte(ptep, 1); if (pte_write(pte)) diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index c1df9bb1e413..0bce4fffcb2e 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -32,7 +32,7 @@ static void *real_vmalloc_addr(void *x) * So don't worry about THP collapse/split. Called * Only in realmode, hence won't need irq_save/restore. */ - p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL); + p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL, NULL); if (!p || !pte_present(*p)) return NULL; addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK); @@ -221,10 +221,12 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, * retry via mmu_notifier_retry. */ if (realmode) - ptep = __find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift); + ptep = __find_linux_pte_or_hugepte(pgdir, hva, NULL, + &hpage_shift); else { local_irq_save(irq_flags); - ptep = find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift); + ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, + &hpage_shift); } if (ptep) { pte_t pte; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 4d33e199edcc..805fee9beefa 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -476,7 +476,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL); + ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, NULL); if (ptep) { pte_t pte = READ_ONCE(*ptep); |