powerps/pseries/dma: Add support for 2M IOMMU page size

The upcoming PAPR spec adds a 2M page size, bit 23 right after 16G page
size in the "ibm,query-pe-dma-window" call.

This adds support for the new page size. Since the new page size is out
of sorted order, this changes the loop to not assume that shift[] is
sorted.

This has now been tested and is known to work on a pre-release version
of phyp.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Leonardo Bras <leobras.c@gmail.com>
Reviewed-by: Frederic Barrat <fbarrat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211006044735.1114669-1-aik@ozlabs.ru

arch/powerpc/platforms/pseries/iommu.c

@@ -1159,14 +1159,15 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
 /* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */
 static int iommu_get_page_shift(u32 query_page_size)
 {
-	/* Supported IO page-sizes according to LoPAR */
+	/* Supported IO page-sizes according to LoPAR, note that 2M is out of order */
 	const int shift[] = {
 		__builtin_ctzll(SZ_4K),   __builtin_ctzll(SZ_64K), __builtin_ctzll(SZ_16M),
 		__builtin_ctzll(SZ_32M),  __builtin_ctzll(SZ_64M), __builtin_ctzll(SZ_128M),
-		__builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G)
+		__builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G), __builtin_ctzll(SZ_2M)
 	};
 
 	int i = ARRAY_SIZE(shift) - 1;
+	int ret = 0;
 
 	/*
 	 * On LoPAR, ibm,query-pe-dma-window outputs "IO Page Sizes" using a bit field:
@@ -1176,11 +1177,10 @@ static int iommu_get_page_shift(u32 query_page_size)
 	 */
 	for (; i >= 0 ; i--) {
 		if (query_page_size & (1 << i))
-			return shift[i];
+			ret = max(ret, shift[i]);
 	}
 
-	/* No valid page size found. */
-	return 0;
+	return ret;
 }
 
 static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr,