[PATCH kernel] powerpc/mm_iommu: Allow pinning large regions

[Alexey Kardashevskiy]

When called with vmas_arg==NULL, get_user_pages_longterm() allocates
an array of nr_pages*8 which can easily get greater that the max order,
for example, registering memory for a 256GB guest does this and fails
in __alloc_pages_nodemask().

This adds a loop over chunks of entries to fit the max order limit.

Fixes: 678e174c4c16 ("powerpc/mm/iommu: allow migration of cma allocated pages 
during mm_iommu_do_alloc", 2019-03-05)
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
 arch/powerpc/mm/mmu_context_iommu.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/mm/mmu_context_iommu.c 
b/arch/powerpc/mm/mmu_context_iommu.c
index 36a826e23d45..e058064b013c 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -131,6 +131,7 @@ long mm_iommu_new(struct mm_struct *mm, unsigned long ua, 
unsigned long entries,
        unsigned int pageshift, mem_pageshift;
        struct page **hpages;
        phys_addr_t *hpas;
+       unsigned long entry, chunk, pinned;
 
        mutex_lock(&mem_list_mutex);
        if (mm_iommu_find(mm, ua, entries)) {
@@ -152,13 +153,29 @@ long mm_iommu_new(struct mm_struct *mm, unsigned long ua, 
unsigned long entries,
        }
 
        down_read(&mm->mmap_sem);
-       ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, hpages, NULL);
+       chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+               sizeof(struct vm_area_struct *);
+       chunk = min(chunk, entries);
+       for (entry = 0, pinned = 0; entry < entries; entry += chunk) {
+               unsigned long n = min(entries - entry, chunk);
+
+               ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+                               FOLL_WRITE, hpages + entry, NULL);
+               if (ret == n) {
+                       pinned += n;
+                       continue;
+               }
+               if (ret >= 0)
+                       pinned += ret;
+               break;
+       }
        up_read(&mm->mmap_sem);
-       if (ret != entries) {
+       if (pinned != entries) {
                /* free the reference taken */
-               for (i = 0; i < ret; i++)
+               for (i = 0; i < pinned; i++)
                        put_page(hpages[i]);
-               ret = -EFAULT;
+               if (!ret)
+                       ret = -EFAULT;
                goto cleanup_exit;
        }
 
-- 
2.17.1