powerpc/mm/iommu: allow large IOMMU page size only for hugetlb backing

THP pages can get split during different code paths.  An incremented
reference count does imply we will not split the compound page.  But the
pmd entry can be converted to level 4 pte entries.  Keep the code
simpler by allowing large IOMMU page size only if the guest ram is
backed by hugetlb pages.

Link: http://lkml.kernel.org/r/20190114095438.32470-6-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 85b4e9f..e7a9c4f 100644 (file)
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -98,8 +98,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
        struct mm_iommu_table_group_mem_t *mem;
        long i, ret, locked_entries = 0;
        unsigned int pageshift;
-       unsigned long flags;
-       unsigned long cur_ua;
 
        mutex_lock(&mem_list_mutex);
 
@@ -167,22 +165,14 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
        for (i = 0; i < entries; ++i) {
                struct page *page = mem->hpages[i];
 
-               cur_ua = ua + (i << PAGE_SHIFT);
-               if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
-                       pte_t *pte;
+               /*
+                * Allow to use larger than 64k IOMMU pages. Only do that
+                * if we are backed by hugetlb.
+                */
+               if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
                        struct page *head = compound_head(page);
-                       unsigned int compshift = compound_order(head);
-                       unsigned int pteshift;
-
-                       local_irq_save(flags); /* disables as well */
-                       pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
-
-                       /* Double check it is still the same pinned page */
-                       if (pte && pte_page(*pte) == head &&
-                           pteshift == compshift + PAGE_SHIFT)
-                               pageshift = max_t(unsigned int, pteshift,
-                                               PAGE_SHIFT);
-                       local_irq_restore(flags);
+
+                       pageshift = compound_order(head) + PAGE_SHIFT;
                }
                mem->pageshift = min(mem->pageshift, pageshift);
                /*