Merge tag 'dma-mapping-5.19-2022-05-25' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - don't over-decrypt memory (Robin Murphy)

 - takes min align mask into account for the swiotlb max mapping size
   (Tianyu Lan)

 - use GFP_ATOMIC in dma-debug (Mikulas Patocka)

 - fix DMA_ATTR_NO_KERNEL_MAPPING on xen/arm (me)

 - don't fail on highmem CMA pages in dma_direct_alloc_pages (me)

 - cleanup swiotlb initialization and share more code with swiotlb-xen
   (me, Stefano Stabellini)

* tag 'dma-mapping-5.19-2022-05-25' of git://git.infradead.org/users/hch/dma-mapping: (23 commits)
  dma-direct: don't over-decrypt memory
  swiotlb: max mapping size takes min align mask into account
  swiotlb: use the right nslabs-derived sizes in swiotlb_init_late
  swiotlb: use the right nslabs value in swiotlb_init_remap
  swiotlb: don't panic when the swiotlb buffer can't be allocated
  dma-debug: change allocation mode from GFP_NOWAIT to GFP_ATIOMIC
  dma-direct: don't fail on highmem CMA pages in dma_direct_alloc_pages
  swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm
  x86: remove cruft from <asm/dma-mapping.h>
  swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl
  swiotlb: merge swiotlb-xen initialization into swiotlb
  swiotlb: provide swiotlb_init variants that remap the buffer
  swiotlb: pass a gfp_mask argument to swiotlb_init_late
  swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction
  swiotlb: make the swiotlb_init interface more useful
  x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
  x86: remove the IOMMU table infrastructure
  MIPS/octeon: use swiotlb_init instead of open coding it
  arm/xen: don't check for xen_initial_domain() in xen_create_contiguous_region
  swiotlb: rename swiotlb_late_init_with_default_size
  ...

Author: torvalds

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

@@ -271,11 +271,7 @@ static void __init free_highpages(void)
 void __init mem_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > arm_dma_pfn_limit)
-		swiotlb_init(1);
-	else
-		swiotlb_force = SWIOTLB_NO_FORCE;
+	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);

arch/arm/mm/init.c

@@ -23,22 +23,20 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
-unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+static gfp_t xen_swiotlb_gfp(void)
 {
 	phys_addr_t base;
-	gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
 	u64 i;
 
 	for_each_mem_range(i, &base, NULL) {
 		if (base < (phys_addr_t)0xffffffff) {
 			if (IS_ENABLED(CONFIG_ZONE_DMA32))
-				flags |= __GFP_DMA32;
-			else
-				flags |= __GFP_DMA;
-			break;
+				return __GFP_DMA32;
+			return __GFP_DMA;
 		}
 	}
-	return __get_free_pages(flags, order);
+
+	return GFP_KERNEL;
 }
 
 static bool hypercall_cflush = false;
@@ -118,23 +116,6 @@ bool xen_arch_need_swiotlb(struct device *dev,
 		!dev_is_dma_coherent(dev));
 }
 
-int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
-				 unsigned int address_bits,
-				 dma_addr_t *dma_handle)
-{
-	if (!xen_initial_domain())
-		return -EINVAL;
-
-	/* we assume that dom0 is mapped 1:1 for now */
-	*dma_handle = pstart;
-	return 0;
-}
-
-void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
-{
-	return;
-}
-
 static int __init xen_mm_init(void)
 {
 	struct gnttab_cache_flush cflush;
@@ -143,10 +124,13 @@ static int __init xen_mm_init(void)
 	if (!xen_swiotlb_detect())
 		return 0;
 
-	rc = xen_swiotlb_init();
 	/* we can work with the default swiotlb */
-	if (rc < 0 && rc != -EEXIST)
-		return rc;
+	if (!io_tlb_default_mem.nslabs) {
+		rc = swiotlb_init_late(swiotlb_size_or_default(),
+				       xen_swiotlb_gfp(), NULL);
+		if (rc < 0)
+			return rc;
+	}
 
 	cflush.op = 0;
 	cflush.a.dev_bus_addr = 0;

arch/arm/xen/mm.c

@@ -451,11 +451,7 @@ void __init bootmem_init(void)
  */
 void __init mem_init(void)
 {
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
-		swiotlb_init(1);
-	else if (!xen_swiotlb_detect())
-		swiotlb_force = SWIOTLB_NO_FORCE;
+	swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE);
 
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();

arch/arm64/include/asm/xen/page-coherent.h

@@ -437,9 +437,7 @@ mem_init (void)
 		if (iommu_detected)
 			break;
 #endif
-#ifdef CONFIG_SWIOTLB
-		swiotlb_init(1);
-#endif
+		swiotlb_init(true, SWIOTLB_VERBOSE);
 	} while (0);
 
 #ifdef CONFIG_FLATMEM

arch/arm64/mm/init.c

@@ -186,15 +186,12 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
-char *octeon_swiotlb;
-
 void __init plat_swiotlb_setup(void)
 {
 	phys_addr_t start, end;
 	phys_addr_t max_addr;
 	phys_addr_t addr_size;
 	size_t swiotlbsize;
-	unsigned long swiotlb_nslabs;
 	u64 i;
 
 	max_addr = 0;
@@ -236,15 +233,7 @@ void __init plat_swiotlb_setup(void)
 	if (OCTEON_IS_OCTEON2() && max_addr >= 0x100000000ul)
 		swiotlbsize = 64 * (1<<20);
 #endif
-	swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
-	swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
-	swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
-
-	octeon_swiotlb = memblock_alloc_low(swiotlbsize, PAGE_SIZE);
-	if (!octeon_swiotlb)
-		panic("%s: Failed to allocate %zu bytes align=%lx\n",
-		      __func__, swiotlbsize, PAGE_SIZE);
 
-	if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
-		panic("Cannot allocate SWIOTLB buffer");
+	swiotlb_adjust_size(swiotlbsize);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }

arch/ia64/include/asm/iommu_table.h

@@ -24,5 +24,5 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 
 void __init plat_swiotlb_setup(void)
 {
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }

arch/ia64/mm/init.c

@@ -664,7 +664,7 @@ static int __init octeon_pci_setup(void)
 
 		/* BAR1 movable regions contiguous to cover the swiotlb */
 		octeon_bar1_pci_phys =
-			virt_to_phys(octeon_swiotlb) & ~((1ull << 22) - 1);
+			io_tlb_default_mem.start & ~((1ull << 22) - 1);
 
 		for (index = 0; index < 32; index++) {
 			union cvmx_pci_bar1_indexx bar1_index;