[PATCH kernel v2 2/2] powerpc/mm_iommu: Allow pinning large regions

Alexey Kardashevskiy aik at ozlabs.ru
Wed Apr 3 15:12:33 AEDT 2019


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 <aik at ozlabs.ru>
---
 arch/powerpc/mm/mmu_context_iommu.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 9d9be850f8c2..8330f135294f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -98,6 +98,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	struct mm_iommu_table_group_mem_t *mem, *mem2;
 	long i, ret, locked_entries = 0, pinned = 0;
 	unsigned int pageshift;
+	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
 		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
@@ -134,11 +135,26 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+			sizeof(struct vm_area_struct *);
+	chunk = min(chunk, entries);
+	for (entry = 0; entry < entries; entry += chunk) {
+		unsigned long n = min(entries - entry, chunk);
+
+		ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+				FOLL_WRITE, mem->hpages + entry, NULL);
+		if (ret == n) {
+			pinned += n;
+			continue;
+		}
+		if (ret > 0)
+			pinned += ret;
+		break;
+	}
 	up_read(&mm->mmap_sem);
-	pinned = ret > 0 ? ret : 0;
-	if (ret != entries) {
-		ret = -EFAULT;
+	if (pinned != entries) {
+		if (!ret)
+			ret = -EFAULT;
 		goto free_exit;
 	}
 
-- 
2.17.1



More information about the Linuxppc-dev mailing list