[PATCH 05/15] HMM: handle HMM device page table entry on mirror page table fault and update.

[JÃrÃme Glisse]

When faulting or updating the device page table properly handle the case of
device memory entry.

Signed-off-by: JÃrÃme Glisse <jglisse@xxxxxxxxxx>
---
 mm/hmm.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/mm/hmm.c b/mm/hmm.c
index 08c0160..8b1003a 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -607,6 +607,13 @@ static void hmm_mirror_update_pte(struct hmm_mirror *mirror,
 		goto out;
 	}
 
+	if (hmm_pte_test_valid_dev(hmm_pte)) {
+		*hmm_pte &= event->pte_mask;
+		if (!hmm_pte_test_valid_dev(hmm_pte))
+			hmm_pt_iter_directory_unref(iter);
+		return;
+	}
+
 	if (!hmm_pte_test_valid_dma(hmm_pte))
 		return;
 
@@ -795,6 +802,12 @@ static int hmm_mirror_fault_pmd(pmd_t *pmdp,
 		ptep = pte_offset_map(pmdp, start);
 		hmm_pt_iter_directory_lock(iter);
 		do {
+			if (hmm_pte_test_valid_dev(&hmm_pte[i])) {
+				if (write)
+					hmm_pte_set_write(&hmm_pte[i]);
+				continue;
+			}
+
 			if (!pte_present(*ptep) ||
 			    (write && !pte_write(*ptep))) {
 				ret = -ENOENT;
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/