xen: Add __GFP_DMA flag when xen_swiotlb_init gets free pages on ARM

Make sure that xen_swiotlb_init allocates buffers that are DMA capable
when at least one memblock is available below 4G. Otherwise we assume
that all devices on the SoC can cope with >4G addresses. We do this on
ARM and ARM64, where dom0 is mapped 1:1, so pfn == mfn in this case.

No functional changes on x86.

From: Chen Baozi <baozich@gmail.com>

Signed-off-by: Chen Baozi <baozich@gmail.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Tested-by: Chen Baozi <baozich@gmail.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

arch/arm/include/asm/xen/page.h

@@ -110,5 +110,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 bool xen_arch_need_swiotlb(struct device *dev,
 			   unsigned long pfn,
 			   unsigned long mfn);
+unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */

arch/arm/xen/mm.c

@@ -4,6 +4,7 @@
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
+#include <linux/memblock.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -21,6 +22,20 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
+unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+{
+	struct memblock_region *reg;
+	gfp_t flags = __GFP_NOWARN;
+
+	for_each_memblock(memory, reg) {
+		if (reg->base < (phys_addr_t)0xffffffff) {
+			flags |= __GFP_DMA;
+			break;
+		}
+	}
+	return __get_free_pages(flags, order);
+}
+
 enum dma_cache_op {
        DMA_UNMAP,
        DMA_MAP,

arch/x86/include/asm/xen/page.h

@@ -269,4 +269,9 @@ static inline bool xen_arch_need_swiotlb(struct device *dev,
 	return false;
 }
 
+static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+{
+	return __get_free_pages(__GFP_NOWARN, order);
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */

drivers/xen/swiotlb-xen.c

@@ -235,7 +235,7 @@ retry:
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 		while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-			xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
+			xen_io_tlb_start = (void *)xen_get_swiotlb_free_pages(order);
 			if (xen_io_tlb_start)
 				break;
 			order--;