[PATCH 1/7] drm/gpusvm: fix hmm_pfn_to_map_order() usage

[Matthew Auld]

Handle the case where the hmm range partially covers a huge page (like
2M), otherwise we can potentially end up doing something nasty like
mapping memory which potentially is outside the range, and maybe not
even mapped by the mm. Fix is based on the xe userptr code, which in a
future patch will directly use gpusvm, so needs alignment here.

Reported-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/drm_gpusvm.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 2451c816edd5..48993cef4a74 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -817,6 +817,27 @@ drm_gpusvm_range_alloc(struct drm_gpusvm *gpusvm,
 	return range;
 }
 
+/*
+ * To allow skipping PFNs with the same flags (like when they belong to
+ * the same huge PTE) when looping over the pfn array, take a given a hmm_pfn,
+ * and return the largest order that will fit inside the PTE, but also crucially
+ * accounting for the original hmm range boundaries.
+ */
+static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn,
+						unsigned long hmm_pfn_index,
+						unsigned long npages)
+{
+	unsigned long size;
+
+	size = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+	size -= (hmm_pfn & ~HMM_PFN_FLAGS) & (size - 1);
+	hmm_pfn_index += size;
+	if (hmm_pfn_index > npages)
+		size -= (hmm_pfn_index - npages);
+
+	return fls(size) - 1;
+}
+
 /**
  * drm_gpusvm_check_pages() - Check pages
  * @gpusvm: Pointer to the GPU SVM structure
@@ -875,7 +896,7 @@ static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm,
 			err = -EFAULT;
 			goto err_free;
 		}
-		i += 0x1 << hmm_pfn_to_map_order(pfns[i]);
+		i += 0x1 << drm_gpusvm_hmm_pfn_to_order(pfns[i], i, npages);
 	}
 
 err_free:
@@ -1408,7 +1429,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 	for (i = 0, j = 0; i < npages; ++j) {
 		struct page *page = hmm_pfn_to_page(pfns[i]);
 
-		order = hmm_pfn_to_map_order(pfns[i]);
+		order = drm_gpusvm_hmm_pfn_to_order(pfns[i], i, npages);
 		if (is_device_private_page(page) ||
 		    is_device_coherent_page(page)) {
 			if (zdd != page->zone_device_data && i > 0) {
-- 
2.48.1