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
  ...

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

-/* SPDX-License-Identifier: GPL-2.0 */
-#include <xen/arm/page-coherent.h>

arch/arm/mm/init.c

@@ -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/xen/mm.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/arm64/include/asm/xen/page-coherent.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#include <xen/arm/page-coherent.h>

arch/arm64/mm/init.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/ia64/include/asm/iommu_table.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_IA64_IOMMU_TABLE_H
-#define _ASM_IA64_IOMMU_TABLE_H
-
-#define IOMMU_INIT_POST(_detect)
-
-#endif /* _ASM_IA64_IOMMU_TABLE_H */

arch/ia64/mm/init.c

@@ -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/mips/cavium-octeon/dma-octeon.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/mips/loongson64/dma.c

@@ -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/mips/pci/pci-octeon.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;

arch/mips/sibyte/common/dma.c

@@ -10,5 +10,5 @@
 
 void __init plat_swiotlb_setup(void)
 {
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }

arch/powerpc/include/asm/svm.h

@@ -15,8 +15,6 @@ static inline bool is_secure_guest(void)
 	return mfmsr() & MSR_S;
 }
 
-void __init svm_swiotlb_init(void);
-
 void dtl_cache_ctor(void *addr);
 #define get_dtl_cache_ctor()	(is_secure_guest() ? dtl_cache_ctor : NULL)
 
@@ -27,8 +25,6 @@ static inline bool is_secure_guest(void)
 	return false;
 }
 
-static inline void svm_swiotlb_init(void) {}
-
 #define get_dtl_cache_ctor() NULL
 
 #endif /* CONFIG_PPC_SVM */

arch/powerpc/include/asm/swiotlb.h

@@ -9,6 +9,7 @@
 #include <linux/swiotlb.h>
 
 extern unsigned int ppc_swiotlb_enable;
+extern unsigned int ppc_swiotlb_flags;
 
 #ifdef CONFIG_SWIOTLB
 void swiotlb_detect_4g(void);

arch/powerpc/kernel/dma-swiotlb.c

@@ -10,6 +10,7 @@
 #include <asm/swiotlb.h>
 
 unsigned int ppc_swiotlb_enable;
+unsigned int ppc_swiotlb_flags;
 
 void __init swiotlb_detect_4g(void)
 {

arch/powerpc/mm/mem.c

@@ -17,6 +17,7 @@
 #include <linux/suspend.h>
 #include <linux/dma-direct.h>
 
+#include <asm/swiotlb.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/kasan.h>
@@ -248,10 +249,7 @@ void __init mem_init(void)
 	 * back to to-down.
 	 */
 	memblock_set_bottom_up(true);
-	if (is_secure_guest())
-		svm_swiotlb_init();
-	else
-		swiotlb_init(0);
+	swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
 #endif
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);

arch/powerpc/platforms/pseries/setup.c

@@ -849,9 +849,6 @@ static void __init pSeries_setup_arch(void)
 	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
-
-	if (swiotlb_force == SWIOTLB_FORCE)
-		ppc_swiotlb_enable = 1;
 }
 
 static void pseries_panic(char *str)

arch/powerpc/platforms/pseries/svm.c

@@ -28,7 +28,7 @@ static int __init init_svm(void)
 	 * need to use the SWIOTLB buffer for DMA even if dma_capable() says
 	 * otherwise.
 	 */
-	swiotlb_force = SWIOTLB_FORCE;
+	ppc_swiotlb_flags |= SWIOTLB_ANY | SWIOTLB_FORCE;
 
 	/* Share the SWIOTLB buffer with the host. */
 	swiotlb_update_mem_attributes();
@@ -37,30 +37,6 @@ static int __init init_svm(void)
 }
 machine_early_initcall(pseries, init_svm);
 
-/*
- * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it
- * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have
- * any addressing limitation, we don't need to allocate it in low addresses.
- */
-void __init svm_swiotlb_init(void)
-{
-	unsigned char *vstart;
-	unsigned long bytes, io_tlb_nslabs;
-
-	io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT);
-	io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-
-	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
-	vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
-	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
-		return;
-
-
-	memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	panic("SVM: Cannot allocate SWIOTLB buffer");
-}
-
 int set_memory_encrypted(unsigned long addr, int numpages)
 {
 	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))

arch/riscv/mm/init.c

@@ -120,13 +120,7 @@ void __init mem_init(void)
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
-#ifdef CONFIG_SWIOTLB
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(dma32_phys_limit))
-		swiotlb_init(1);
-	else
-		swiotlb_force = SWIOTLB_NO_FORCE;
-#endif
+	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
 	memblock_free_all();
 
 	print_vm_layout();

arch/s390/mm/init.c

@@ -185,8 +185,7 @@ static void pv_init(void)
 		return;
 
 	/* make sure bounce buffers are shared */
-	swiotlb_force = SWIOTLB_FORCE;
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
 	swiotlb_update_mem_attributes();
 }
 

arch/x86/include/asm/dma-mapping.h

@@ -2,18 +2,6 @@
 #ifndef _ASM_X86_DMA_MAPPING_H
 #define _ASM_X86_DMA_MAPPING_H
 
-/*
- * IOMMU interface. See Documentation/core-api/dma-api-howto.rst and
- * Documentation/core-api/dma-api.rst for documentation.
- */
-
-#include <linux/scatterlist.h>
-#include <asm/io.h>
-#include <asm/swiotlb.h>
-
-extern int iommu_merge;
-extern int panic_on_overflow;
-
 extern const struct dma_map_ops *dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)

arch/x86/include/asm/gart.h

@@ -38,7 +38,7 @@ extern int gart_iommu_aperture_disabled;
 extern void early_gart_iommu_check(void);
 extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
-extern int gart_iommu_hole_init(void);
+void gart_iommu_hole_init(void);
 
 #else
 #define gart_iommu_aperture            0
@@ -51,9 +51,8 @@ static inline void early_gart_iommu_check(void)
 static inline void gart_parse_options(char *options)
 {
 }
-static inline int gart_iommu_hole_init(void)
+static inline void gart_iommu_hole_init(void)
 {
-	return -ENODEV;
 }
 #endif
 

arch/x86/include/asm/iommu.h

@@ -8,6 +8,14 @@
 
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int iommu_merge;
+extern int panic_on_overflow;
+
+#ifdef CONFIG_SWIOTLB
+extern bool x86_swiotlb_enable;
+#else
+#define x86_swiotlb_enable false
+#endif
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)

arch/x86/include/asm/iommu_table.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IOMMU_TABLE_H
-#define _ASM_X86_IOMMU_TABLE_H
-
-#include <asm/swiotlb.h>
-
-/*
- * History lesson:
- * The execution chain of IOMMUs in 2.6.36 looks as so:
- *
- *            [xen-swiotlb]
- *                 |
- *         +----[swiotlb *]--+
- *        /         |         \
- *       /          |          \
- *    [GART]     [Calgary]  [Intel VT-d]
- *     /
- *    /
- * [AMD-Vi]
- *
- * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
- * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
- * Also it would surreptitiously initialize set the swiotlb=1 if there were
- * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
- * flag would be turned off by all IOMMUs except the Calgary one.
- *
- * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
- * to be built by defining who we depend on.
- *
- * And all that needs to be done is to use one of the macros in the IOMMU
- * and the pci-dma.c will take care of the rest.
- */
-
-struct iommu_table_entry {
-	initcall_t	detect;
-	initcall_t	depend;
-	void		(*early_init)(void); /* No memory allocate available. */
-	void		(*late_init)(void); /* Yes, can allocate memory. */
-#define IOMMU_FINISH_IF_DETECTED (1<<0)
-#define IOMMU_DETECTED		 (1<<1)
-	int		flags;
-};
-/*
- * Macro fills out an entry in the .iommu_table that is equivalent
- * to the fields that 'struct iommu_table_entry' has. The entries
- * that are put in the .iommu_table section are not put in any order
- * hence during boot-time we will have to resort them based on
- * dependency. */
-
-
-#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
-	static const struct iommu_table_entry				\
-		__iommu_entry_##_detect __used				\
-	__attribute__ ((unused, __section__(".iommu_table"),		\
-			aligned((sizeof(void *)))))	\
-	= {_detect, _depend, _early_init, _late_init,			\
-	   _finish ? IOMMU_FINISH_IF_DETECTED : 0}
-/*
- * The simplest IOMMU definition. Provide the detection routine
- * and it will be run after the SWIOTLB and the other IOMMUs
- * that utilize this macro. If the IOMMU is detected (ie, the
- * detect routine returns a positive value), the other IOMMUs
- * are also checked. You can use IOMMU_INIT_POST_FINISH if you prefer
- * to stop detecting the other IOMMUs after yours has been detected.
- */
-#define IOMMU_INIT_POST(_detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 0)
-
-#define IOMMU_INIT_POST_FINISH(detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 1)
-
-/*
- * A more sophisticated version of IOMMU_INIT. This variant requires:
- *  a). A detection routine function.
- *  b). The name of the detection routine we depend on to get called
- *      before us.
- *  c). The init routine which gets called if the detection routine
- *      returns a positive value from the pci_iommu_alloc. This means
- *      no presence of a memory allocator.
- *  d). Similar to the 'init', except that this gets called from pci_iommu_init
- *      where we do have a memory allocator.
- *
- * The standard IOMMU_INIT differs from the IOMMU_INIT_FINISH variant
- * in that the former will continue detecting other IOMMUs in the call
- * list after the detection routine returns a positive number, while the
- * latter will stop the execution chain upon first successful detection.
- * Both variants will still call the 'init' and 'late_init' functions if
- * they are set.
- */
-#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)		\
-	__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
-
-#define IOMMU_INIT(_detect, _depend, _init, _late_init)			\
-	__IOMMU_INIT(_detect, _depend, _init, _late_init, 0)
-
-void sort_iommu_table(struct iommu_table_entry *start,
-		      struct iommu_table_entry *finish);
-
-void check_iommu_entries(struct iommu_table_entry *start,
-			 struct iommu_table_entry *finish);
-
-#endif /* _ASM_X86_IOMMU_TABLE_H */

arch/x86/include/asm/swiotlb.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_SWIOTLB_H
-#define _ASM_X86_SWIOTLB_H
-
-#include <linux/swiotlb.h>
-
-#ifdef CONFIG_SWIOTLB
-extern int swiotlb;
-extern int __init pci_swiotlb_detect_override(void);
-extern int __init pci_swiotlb_detect_4gb(void);
-extern void __init pci_swiotlb_init(void);
-extern void __init pci_swiotlb_late_init(void);
-#else
-#define swiotlb 0
-static inline int pci_swiotlb_detect_override(void)
-{
-	return 0;
-}
-static inline int pci_swiotlb_detect_4gb(void)
-{
-	return 0;
-}
-static inline void pci_swiotlb_init(void)
-{
-}
-static inline void pci_swiotlb_late_init(void)
-{
-}
-#endif
-#endif /* _ASM_X86_SWIOTLB_H */

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

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
-#define _ASM_X86_XEN_PAGE_COHERENT_H
-
-#include <asm/page.h>
-#include <linux/dma-mapping.h>
-
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags,
-		unsigned long attrs)
-{
-	void *vstart = (void*)__get_free_pages(flags, get_order(size));
-	*dma_handle = virt_to_phys(vstart);
-	return vstart;
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle,
-		unsigned long attrs)
-{
-	free_pages((unsigned long) cpu_addr, get_order(size));
-}
-
-#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */

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

@@ -357,9 +357,4 @@ 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 */

arch/x86/include/asm/xen/swiotlb-xen.h

@@ -3,11 +3,15 @@
 #define _ASM_X86_SWIOTLB_XEN_H
 
 #ifdef CONFIG_SWIOTLB_XEN
-extern int __init pci_xen_swiotlb_detect(void);
 extern int pci_xen_swiotlb_init_late(void);
 #else
-#define pci_xen_swiotlb_detect NULL
 static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
 #endif
 
+int xen_swiotlb_fixup(void *buf, unsigned long nslabs);
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				unsigned int address_bits,
+				dma_addr_t *dma_handle);
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
+
 #endif /* _ASM_X86_SWIOTLB_XEN_H */

arch/x86/kernel/Makefile

@@ -66,7 +66,6 @@ obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o hw_breakpoint.o
 obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
-obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 obj-y			+= irqflags.o
 obj-y			+= static_call.o
@@ -132,7 +131,6 @@ obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
 obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
-obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 obj-$(CONFIG_OF)			+= devicetree.o
 obj-$(CONFIG_UPROBES)			+= uprobes.o
 

arch/x86/kernel/amd_gart_64.c

@@ -38,11 +38,9 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/set_memory.h>
-#include <asm/swiotlb.h>
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size;	/* size of remapping area bytes */
@@ -808,7 +806,7 @@ int __init gart_iommu_init(void)
 	flush_gart();
 	dma_ops = &gart_dma_ops;
 	x86_platform.iommu_shutdown = gart_iommu_shutdown;
-	swiotlb = 0;
+	x86_swiotlb_enable = false;
 
 	return 0;
 }
@@ -842,4 +840,3 @@ void __init gart_parse_options(char *p)
 		}
 	}
 }
-IOMMU_INIT_POST(gart_iommu_hole_init);

arch/x86/kernel/aperture_64.c

@@ -392,7 +392,7 @@ void __init early_gart_iommu_check(void)
 
 static int __initdata printed_gart_size_msg;
 
-int __init gart_iommu_hole_init(void)
+void __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -401,11 +401,11 @@ int __init gart_iommu_hole_init(void)
 	int i, node;
 
 	if (!amd_gart_present())
-		return -ENODEV;
+		return;
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return -ENODEV;
+		return;
 
 	pr_info("Checking aperture...\n");
 
@@ -491,10 +491,8 @@ int __init gart_iommu_hole_init(void)
 			 * and fixed up the northbridge
 			 */
 			exclude_from_core(last_aper_base, last_aper_order);
-
-			return 1;
 		}
-		return 0;
+		return;
 	}
 
 	if (!fallback_aper_force) {
@@ -527,7 +525,7 @@ int __init gart_iommu_hole_init(void)
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return 0;
+		return;
 	}
 
 	/*
@@ -561,6 +559,4 @@ int __init gart_iommu_hole_init(void)
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
-
-	return 1;
 }

arch/x86/kernel/cpu/mshyperv.c

@@ -337,14 +337,6 @@ static void __init ms_hyperv_init_platform(void)
 			swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary;
 #endif
 		}
-
-#ifdef CONFIG_SWIOTLB
-		/*
-		 * Enable swiotlb force mode in Isolation VM to
-		 * use swiotlb bounce buffer for dma transaction.
-		 */
-		swiotlb_force = SWIOTLB_FORCE;
-#endif
 		/* Isolation VMs are unenlightened SEV-based VMs, thus this check: */
 		if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
 			if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE)

arch/x86/kernel/pci-dma.c

@@ -7,13 +7,16 @@
 #include <linux/memblock.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/amd-iommu.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
+
+#include <xen/xen.h>
+#include <xen/swiotlb-xen.h>
 
 static bool disable_dac_quirk __read_mostly;
 
@@ -34,24 +37,90 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+#ifdef CONFIG_SWIOTLB
+bool x86_swiotlb_enable;
+static unsigned int x86_swiotlb_flags;
+
+static void __init pci_swiotlb_detect(void)
+{
+	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
+		x86_swiotlb_enable = true;
+
+	/*
+	 * Set swiotlb to 1 so that bounce buffers are allocated and used for
+	 * devices that can't support DMA to encrypted memory.
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		x86_swiotlb_enable = true;
+
+	/*
+	 * Guest with guest memory encryption currently perform all DMA through
+	 * bounce buffers as the hypervisor can't access arbitrary VM memory
+	 * that is not explicitly shared with it.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
+		x86_swiotlb_enable = true;
+		x86_swiotlb_flags |= SWIOTLB_FORCE;
+	}
+}
+#else
+static inline void __init pci_swiotlb_detect(void)
+{
+}
+#define x86_swiotlb_flags 0
+#endif /* CONFIG_SWIOTLB */
+
+#ifdef CONFIG_SWIOTLB_XEN
+static void __init pci_xen_swiotlb_init(void)
+{
+	if (!xen_initial_domain() && !x86_swiotlb_enable)
+		return;
+	x86_swiotlb_enable = true;
+	x86_swiotlb_flags |= SWIOTLB_ANY;
+	swiotlb_init_remap(true, x86_swiotlb_flags, xen_swiotlb_fixup);
+	dma_ops = &xen_swiotlb_dma_ops;
+	if (IS_ENABLED(CONFIG_PCI))
+		pci_request_acs();
+}
+
+int pci_xen_swiotlb_init_late(void)
+{
+	if (dma_ops == &xen_swiotlb_dma_ops)
+		return 0;
+
+	/* we can work with the default swiotlb */
+	if (!io_tlb_default_mem.nslabs) {
+		int rc = swiotlb_init_late(swiotlb_size_or_default(),
+					   GFP_KERNEL, xen_swiotlb_fixup);
+		if (rc < 0)
+			return rc;
+	}
+
+	/* XXX: this switches the dma ops under live devices! */
+	dma_ops = &xen_swiotlb_dma_ops;
+	if (IS_ENABLED(CONFIG_PCI))
+		pci_request_acs();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+#else
+static inline void __init pci_xen_swiotlb_init(void)
+{
+}
+#endif /* CONFIG_SWIOTLB_XEN */
 
 void __init pci_iommu_alloc(void)
 {
-	struct iommu_table_entry *p;
-
-	sort_iommu_table(__iommu_table, __iommu_table_end);
-	check_iommu_entries(__iommu_table, __iommu_table_end);
-
-	for (p = __iommu_table; p < __iommu_table_end; p++) {
-		if (p && p->detect && p->detect() > 0) {
-			p->flags |= IOMMU_DETECTED;
-			if (p->early_init)
-				p->early_init();
-			if (p->flags & IOMMU_FINISH_IF_DETECTED)
-				break;
-		}
+	if (xen_pv_domain()) {
+		pci_xen_swiotlb_init();
+		return;
 	}
+	pci_swiotlb_detect();
+	gart_iommu_hole_init();
+	amd_iommu_detect();
+	detect_intel_iommu();
+	swiotlb_init(x86_swiotlb_enable, x86_swiotlb_flags);
 }
 
 /*
@@ -102,7 +171,7 @@ static __init int iommu_setup(char *p)
 		}
 #ifdef CONFIG_SWIOTLB
 		if (!strncmp(p, "soft", 4))
-			swiotlb = 1;
+			x86_swiotlb_enable = true;
 #endif
 		if (!strncmp(p, "pt", 2))
 			iommu_set_default_passthrough(true);
@@ -121,14 +190,17 @@ early_param("iommu", iommu_setup);
 
 static int __init pci_iommu_init(void)
 {
-	struct iommu_table_entry *p;
-
 	x86_init.iommu.iommu_init();
 
-	for (p = __iommu_table; p < __iommu_table_end; p++) {
-		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
-			p->late_init();
+#ifdef CONFIG_SWIOTLB
+	/* An IOMMU turned us off. */
+	if (x86_swiotlb_enable) {
+		pr_info("PCI-DMA: Using software bounce buffering for IO (SWIOTLB)\n");
+		swiotlb_print_info();
+	} else {
+		swiotlb_exit();
 	}
+#endif
 
 	return 0;
 }

arch/x86/kernel/pci-iommu_table.c

-// SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
-#include <asm/iommu_table.h>
-#include <linux/string.h>
-#include <linux/kallsyms.h>
-
-static struct iommu_table_entry * __init
-find_dependents_of(struct iommu_table_entry *start,
-		   struct iommu_table_entry *finish,
-		   struct iommu_table_entry *q)
-{
-	struct iommu_table_entry *p;
-
-	if (!q)
-		return NULL;
-
-	for (p = start; p < finish; p++)
-		if (p->detect == q->depend)
-			return p;
-
-	return NULL;
-}
-
-
-void __init sort_iommu_table(struct iommu_table_entry *start,
-			     struct iommu_table_entry *finish) {
-
-	struct iommu_table_entry *p, *q, tmp;
-
-	for (p = start; p < finish; p++) {
-again:
-		q = find_dependents_of(start, finish, p);
-		/* We are bit sneaky here. We use the memory address to figure
-		 * out if the node we depend on is past our point, if so, swap.
-		 */
-		if (q > p) {
-			tmp = *p;
-			memmove(p, q, sizeof(*p));
-			*q = tmp;
-			goto again;
-		}
-	}
-
-}
-
-#ifdef DEBUG
-void __init check_iommu_entries(struct iommu_table_entry *start,
-				struct iommu_table_entry *finish)
-{
-	struct iommu_table_entry *p, *q, *x;
-
-	/* Simple cyclic dependency checker. */
-	for (p = start; p < finish; p++) {
-		q = find_dependents_of(start, finish, p);
-		x = find_dependents_of(start, finish, q);
-		if (p == x) {
-			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
-			       p->detect, q->detect);
-			/* Heavy handed way..*/
-			x->depend = NULL;
-		}
-	}
-
-	for (p = start; p < finish; p++) {
-		q = find_dependents_of(p, finish, p);
-		if (q && q > p) {
-			printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
-			       p->detect, q->detect);
-		}
-	}
-}
-#else
-void __init check_iommu_entries(struct iommu_table_entry *start,
-				       struct iommu_table_entry *finish)
-{
-}
-#endif

arch/x86/kernel/pci-swiotlb.c

-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/pci.h>
-#include <linux/cache.h>
-#include <linux/init.h>
-#include <linux/swiotlb.h>
-#include <linux/memblock.h>
-#include <linux/dma-direct.h>
-#include <linux/cc_platform.h>
-
-#include <asm/iommu.h>
-#include <asm/swiotlb.h>
-#include <asm/dma.h>
-#include <asm/xen/swiotlb-xen.h>
-#include <asm/iommu_table.h>
-
-int swiotlb __read_mostly;
-
-/*
- * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
- *
- * This returns non-zero if we are forced to use swiotlb (by the boot
- * option).
- */
-int __init pci_swiotlb_detect_override(void)
-{
-	if (swiotlb_force == SWIOTLB_FORCE)
-		swiotlb = 1;
-
-	return swiotlb;
-}
-IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
-		  pci_xen_swiotlb_detect,
-		  pci_swiotlb_init,
-		  pci_swiotlb_late_init);
-
-/*
- * If 4GB or more detected (and iommu=off not set) or if SME is active
- * then set swiotlb to 1 and return 1.
- */
-int __init pci_swiotlb_detect_4gb(void)
-{
-	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
-		swiotlb = 1;
-
-	/*
-	 * Set swiotlb to 1 so that bounce buffers are allocated and used for
-	 * devices that can't support DMA to encrypted memory.
-	 */
-	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
-		swiotlb = 1;
-
-	return swiotlb;
-}
-IOMMU_INIT(pci_swiotlb_detect_4gb,
-	   pci_swiotlb_detect_override,
-	   pci_swiotlb_init,
-	   pci_swiotlb_late_init);
-
-void __init pci_swiotlb_init(void)
-{
-	if (swiotlb)
-		swiotlb_init(0);
-}
-
-void __init pci_swiotlb_late_init(void)
-{
-	/* An IOMMU turned us off. */
-	if (!swiotlb)
-		swiotlb_exit();
-	else {
-		printk(KERN_INFO "PCI-DMA: "
-		       "Using software bounce buffering for IO (SWIOTLB)\n");
-		swiotlb_print_info();
-	}
-}

arch/x86/kernel/tboot.c

@@ -24,7 +24,6 @@
 #include <asm/processor.h>
 #include <asm/bootparam.h>
 #include <asm/pgalloc.h>
-#include <asm/swiotlb.h>
 #include <asm/fixmap.h>
 #include <asm/proto.h>
 #include <asm/setup.h>

arch/x86/kernel/vmlinux.lds.S

@@ -315,18 +315,6 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 
-	/*
-	 * struct iommu_table_entry entries are injected in this section.
-	 * It is an array of IOMMUs which during run time gets sorted depending
-	 * on its dependency order. After rootfs_initcall is complete
-	 * this section can be safely removed.
-	 */
-	.iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
-		__iommu_table = .;
-		*(.iommu_table)
-		__iommu_table_end = .;
-	}
-
 	. = ALIGN(8);
 	.apicdrivers : AT(ADDR(.apicdrivers) - LOAD_OFFSET) {
 		__apicdrivers = .;

arch/x86/mm/mem_encrypt_amd.c

@@ -495,9 +495,6 @@ void __init sme_early_init(void)
 	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
 		protection_map[i] = pgprot_encrypted(protection_map[i]);
 
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		swiotlb_force = SWIOTLB_FORCE;
-
 	x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare;
 	x86_platform.guest.enc_status_change_finish  = amd_enc_status_change_finish;
 	x86_platform.guest.enc_tlb_flush_required    = amd_enc_tlb_flush_required;

arch/x86/pci/sta2x11-fixup.c

@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
 		int size = STA2X11_SWIOTLB_SIZE;
 		/* First instance: register your own swiotlb area */
 		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_late_init_with_default_size(size))
+		if (swiotlb_init_late(size, GFP_DMA, NULL))
 			dev_emerg(&pdev->dev, "init swiotlb failed\n");
 	}
 	list_add(&instance->list, &sta2x11_instance_list);

arch/x86/xen/Makefile

@@ -47,6 +47,4 @@ obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
 obj-$(CONFIG_XEN_PV_DOM0)	+= vga.o
 
-obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
-
 obj-$(CONFIG_XEN_EFI)		+= efi.o

arch/x86/xen/mmu_pv.c

@@ -80,6 +80,7 @@
 #include <xen/interface/version.h>
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
+#include <xen/swiotlb-xen.h>
 
 #include "multicalls.h"
 #include "mmu.h"

arch/x86/xen/pci-swiotlb-xen.c

-// SPDX-License-Identifier: GPL-2.0
-
-/* Glue code to lib/swiotlb-xen.c */
-
-#include <linux/dma-map-ops.h>
-#include <linux/pci.h>
-#include <xen/swiotlb-xen.h>
-
-#include <asm/xen/hypervisor.h>
-#include <xen/xen.h>
-#include <asm/iommu_table.h>
-
-
-#include <asm/xen/swiotlb-xen.h>
-#ifdef CONFIG_X86_64
-#include <asm/iommu.h>
-#include <asm/dma.h>
-#endif
-#include <linux/export.h>
-
-static int xen_swiotlb __read_mostly;
-
-/*
- * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary
- *
- * This returns non-zero if we are forced to use xen_swiotlb (by the boot
- * option).
- */
-int __init pci_xen_swiotlb_detect(void)
-{
-
-	if (!xen_pv_domain())
-		return 0;
-
-	/* If running as PV guest, either iommu=soft, or swiotlb=force will
-	 * activate this IOMMU. If running as PV privileged, activate it
-	 * irregardless.
-	 */
-	if (xen_initial_domain() || swiotlb || swiotlb_force == SWIOTLB_FORCE)
-		xen_swiotlb = 1;
-
-	/* If we are running under Xen, we MUST disable the native SWIOTLB.
-	 * Don't worry about swiotlb_force flag activating the native, as
-	 * the 'swiotlb' flag is the only one turning it on. */
-	swiotlb = 0;
-
-#ifdef CONFIG_X86_64
-	/* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
-	 * (so no iommu=X command line over-writes).
-	 * Considering that PV guests do not want the *native SWIOTLB* but
-	 * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
-	 */
-	if (max_pfn > MAX_DMA32_PFN)
-		no_iommu = 1;
-#endif
-	return xen_swiotlb;
-}
-
-static void __init pci_xen_swiotlb_init(void)
-{
-	if (xen_swiotlb) {
-		xen_swiotlb_init_early();
-		dma_ops = &xen_swiotlb_dma_ops;
-
-#ifdef CONFIG_PCI
-		/* Make sure ACS will be enabled */
-		pci_request_acs();
-#endif
-	}
-}
-
-int pci_xen_swiotlb_init_late(void)
-{
-	int rc;
-
-	if (xen_swiotlb)
-		return 0;
-
-	rc = xen_swiotlb_init();
-	if (rc)
-		return rc;
-
-	dma_ops = &xen_swiotlb_dma_ops;
-#ifdef CONFIG_PCI
-	/* Make sure ACS will be enabled */
-	pci_request_acs();
-#endif
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
-
-IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
-		  NULL,
-		  pci_xen_swiotlb_init,
-		  NULL);

drivers/iommu/amd/init.c

@@ -27,7 +27,6 @@
 #include <asm/apic.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/set_memory.h>
@@ -3257,11 +3256,6 @@ __setup("ivrs_ioapic",		parse_ivrs_ioapic);
 __setup("ivrs_hpet",		parse_ivrs_hpet);
 __setup("ivrs_acpihid",		parse_ivrs_acpihid);
 
-IOMMU_INIT_FINISH(amd_iommu_detect,
-		  gart_iommu_hole_init,
-		  NULL,
-		  NULL);
-
 bool amd_iommu_v2_supported(void)
 {
 	return amd_iommu_v2_present;

drivers/iommu/amd/iommu.c

@@ -1840,7 +1840,10 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 
 static void __init amd_iommu_init_dma_ops(void)
 {
-	swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
+	if (iommu_default_passthrough() || sme_me_mask)
+		x86_swiotlb_enable = true;
+	else
+		x86_swiotlb_enable = false;
 }
 
 int __init amd_iommu_init_api(void)

drivers/iommu/intel/dmar.c

@@ -30,7 +30,6 @@
 #include <linux/numa.h>
 #include <linux/limits.h>
 #include <asm/irq_remapping.h>
-#include <asm/iommu_table.h>
 #include <trace/events/intel_iommu.h>
 
 #include "../irq_remapping.h"
@@ -912,7 +911,7 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 	return 0;
 }
 
-int __init detect_intel_iommu(void)
+void __init detect_intel_iommu(void)
 {
 	int ret;
 	struct dmar_res_callback validate_drhd_cb = {
@@ -945,8 +944,6 @@ int __init detect_intel_iommu(void)
 		dmar_tbl = NULL;
 	}
 	up_write(&dmar_global_lock);
-
-	return ret ? ret : 1;
 }
 
 static void unmap_iommu(struct intel_iommu *iommu)
@@ -2164,7 +2161,6 @@ static int __init dmar_free_unused_resources(void)
 }
 
 late_initcall(dmar_free_unused_resources);
-IOMMU_INIT_POST(detect_intel_iommu);
 
 /*
  * DMAR Hotplug Support

drivers/xen/swiotlb-xen.c

@@ -36,7 +36,6 @@
 #include <xen/hvc-console.h>
 
 #include <asm/dma-mapping.h>
-#include <asm/xen/page-coherent.h>
 
 #include <trace/events/swiotlb.h>
 #define MAX_DMA_BITS 32
@@ -104,7 +103,8 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
-static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
+#ifdef CONFIG_X86
+int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 {
 	int rc;
 	unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
@@ -130,223 +130,59 @@ static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 	return 0;
 }
 
-enum xen_swiotlb_err {
-	XEN_SWIOTLB_UNKNOWN = 0,
-	XEN_SWIOTLB_ENOMEM,
-	XEN_SWIOTLB_EFIXUP
-};
-
-static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
-{
-	switch (err) {
-	case XEN_SWIOTLB_ENOMEM:
-		return "Cannot allocate Xen-SWIOTLB buffer\n";
-	case XEN_SWIOTLB_EFIXUP:
-		return "Failed to get contiguous memory for DMA from Xen!\n"\
-		    "You either: don't have the permissions, do not have"\
-		    " enough free memory under 4GB, or the hypervisor memory"\
-		    " is too fragmented!";
-	default:
-		break;
-	}
-	return "";
-}
-
-int xen_swiotlb_init(void)
-{
-	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
-	unsigned long bytes = swiotlb_size_or_default();
-	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
-	unsigned int order, repeat = 3;
-	int rc = -ENOMEM;
-	char *start;
-
-	if (io_tlb_default_mem.nslabs) {
-		pr_warn("swiotlb buffer already initialized\n");
-		return -EEXIST;
-	}
-
-retry:
-	m_ret = XEN_SWIOTLB_ENOMEM;
-	order = get_order(bytes);
-
-	/*
-	 * Get IO TLB memory from any location.
-	 */
-#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) {
-		start = (void *)xen_get_swiotlb_free_pages(order);
-		if (start)
-			break;
-		order--;
-	}
-	if (!start)
-		goto exit;
-	if (order != get_order(bytes)) {
-		pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
-			(PAGE_SIZE << order) >> 20);
-		nslabs = SLABS_PER_PAGE << order;
-		bytes = nslabs << IO_TLB_SHIFT;
-	}
-
-	/*
-	 * And replace that memory with pages under 4GB.
-	 */
-	rc = xen_swiotlb_fixup(start, nslabs);
-	if (rc) {
-		free_pages((unsigned long)start, order);
-		m_ret = XEN_SWIOTLB_EFIXUP;
-		goto error;
-	}
-	rc = swiotlb_late_init_with_tbl(start, nslabs);
-	if (rc)
-		return rc;
-	swiotlb_set_max_segment(PAGE_SIZE);
-	return 0;
-error:
-	if (nslabs > 1024 && repeat--) {
-		/* Min is 2MB */
-		nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
-		bytes = nslabs << IO_TLB_SHIFT;
-		pr_info("Lowering to %luMB\n", bytes >> 20);
-		goto retry;
-	}
-exit:
-	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
-	return rc;
-}
-
-#ifdef CONFIG_X86
-void __init xen_swiotlb_init_early(void)
-{
-	unsigned long bytes = swiotlb_size_or_default();
-	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
-	unsigned int repeat = 3;
-	char *start;
-	int rc;
-
-retry:
-	/*
-	 * Get IO TLB memory from any location.
-	 */
-	start = memblock_alloc(PAGE_ALIGN(bytes),
-			       IO_TLB_SEGSIZE << IO_TLB_SHIFT);
-	if (!start)
-		panic("%s: Failed to allocate %lu bytes\n",
-		      __func__, PAGE_ALIGN(bytes));
-
-	/*
-	 * And replace that memory with pages under 4GB.
-	 */
-	rc = xen_swiotlb_fixup(start, nslabs);
-	if (rc) {
-		memblock_free(start, PAGE_ALIGN(bytes));
-		if (nslabs > 1024 && repeat--) {
-			/* Min is 2MB */
-			nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
-			bytes = nslabs << IO_TLB_SHIFT;
-			pr_info("Lowering to %luMB\n", bytes >> 20);
-			goto retry;
-		}
-		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
-	}
-
-	if (swiotlb_init_with_tbl(start, nslabs, true))
-		panic("Cannot allocate SWIOTLB buffer");
-	swiotlb_set_max_segment(PAGE_SIZE);
-}
-#endif /* CONFIG_X86 */
-
 static void *
-xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flags,
-			   unsigned long attrs)
+xen_swiotlb_alloc_coherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
 {
-	void *ret;
+	u64 dma_mask = dev->coherent_dma_mask;
 	int order = get_order(size);
-	u64 dma_mask = DMA_BIT_MASK(32);
 	phys_addr_t phys;
-	dma_addr_t dev_addr;
-
-	/*
-	* Ignore region specifiers - the kernel's ideas of
-	* pseudo-phys memory layout has nothing to do with the
-	* machine physical layout.  We can't allocate highmem
-	* because we can't return a pointer to it.
-	*/
-	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
+	void *ret;
 
-	/* Convert the size to actually allocated. */
+	/* Align the allocation to the Xen page size */
 	size = 1UL << (order + XEN_PAGE_SHIFT);
 
-	/* On ARM this function returns an ioremap'ped virtual address for
-	 * which virt_to_phys doesn't return the corresponding physical
-	 * address. In fact on ARM virt_to_phys only works for kernel direct
-	 * mapped RAM memory. Also see comment below.
-	 */
-	ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
-
+	ret = (void *)__get_free_pages(flags, get_order(size));
 	if (!ret)
 		return ret;
-
-	if (hwdev && hwdev->coherent_dma_mask)
-		dma_mask = hwdev->coherent_dma_mask;
-
-	/* At this point dma_handle is the dma address, next we are
-	 * going to set it to the machine address.
-	 * Do not use virt_to_phys(ret) because on ARM it doesn't correspond
-	 * to *dma_handle. */
-	phys = dma_to_phys(hwdev, *dma_handle);
-	dev_addr = xen_phys_to_dma(hwdev, phys);
-	if (((dev_addr + size - 1 <= dma_mask)) &&
-	    !range_straddles_page_boundary(phys, size))
-		*dma_handle = dev_addr;
-	else {
-		if (xen_create_contiguous_region(phys, order,
-						 fls64(dma_mask), dma_handle) != 0) {
-			xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
-			return NULL;
-		}
-		*dma_handle = phys_to_dma(hwdev, *dma_handle);
+	phys = virt_to_phys(ret);
+
+	*dma_handle = xen_phys_to_dma(dev, phys);
+	if (*dma_handle + size - 1 > dma_mask ||
+	    range_straddles_page_boundary(phys, size)) {
+		if (xen_create_contiguous_region(phys, order, fls64(dma_mask),
+				dma_handle) != 0)
+			goto out_free_pages;
 		SetPageXenRemapped(virt_to_page(ret));
 	}
+
 	memset(ret, 0, size);
 	return ret;
+
+out_free_pages:
+	free_pages((unsigned long)ret, get_order(size));
+	return NULL;
 }
 
 static void
-xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-			  dma_addr_t dev_addr, unsigned long attrs)
+xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
 {
+	phys_addr_t phys = virt_to_phys(vaddr);
 	int order = get_order(size);
-	phys_addr_t phys;
-	u64 dma_mask = DMA_BIT_MASK(32);
-	struct page *page;
-
-	if (hwdev && hwdev->coherent_dma_mask)
-		dma_mask = hwdev->coherent_dma_mask;
-
-	/* do not use virt_to_phys because on ARM it doesn't return you the
-	 * physical address */
-	phys = xen_dma_to_phys(hwdev, dev_addr);
 
 	/* Convert the size to actually allocated. */
 	size = 1UL << (order + XEN_PAGE_SHIFT);
 
-	if (is_vmalloc_addr(vaddr))
-		page = vmalloc_to_page(vaddr);
-	else
-		page = virt_to_page(vaddr);
+	if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) ||
+	    WARN_ON_ONCE(range_straddles_page_boundary(phys, size)))
+	    	return;
 
-	if (!WARN_ON((dev_addr + size - 1 > dma_mask) ||
-		     range_straddles_page_boundary(phys, size)) &&
-	    TestClearPageXenRemapped(page))
+	if (TestClearPageXenRemapped(virt_to_page(vaddr)))
 		xen_destroy_contiguous_region(phys, order);
-
-	xen_free_coherent_pages(hwdev, size, vaddr, phys_to_dma(hwdev, phys),
-				attrs);
+	free_pages((unsigned long)vaddr, get_order(size));
 }
+#endif /* CONFIG_X86 */
 
 /*
  * Map a single buffer of the indicated size for DMA in streaming mode.  The
@@ -378,7 +214,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+	trace_swiotlb_bounced(dev, dev_addr, size);
 
 	map = swiotlb_tbl_map_single(dev, phys, size, size, 0, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
@@ -549,8 +385,13 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 }
 
 const struct dma_map_ops xen_swiotlb_dma_ops = {
+#ifdef CONFIG_X86
 	.alloc = xen_swiotlb_alloc_coherent,
 	.free = xen_swiotlb_free_coherent,
+#else
+	.alloc = dma_direct_alloc,
+	.free = dma_direct_free,
+#endif
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,

include/linux/dmar.h

@@ -121,7 +121,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 				 u16 segment, struct dmar_dev_scope *devices,
 				 int count);
 /* Intel IOMMU detection */
-extern int detect_intel_iommu(void);
+void detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 extern int dmar_device_add(acpi_handle handle);
 extern int dmar_device_remove(acpi_handle handle);
@@ -197,6 +197,10 @@ static inline bool dmar_platform_optin(void)
 	return false;
 }
 
+static inline void detect_intel_iommu(void)
+{
+}
+
 #endif /* CONFIG_DMAR_TABLE */
 
 struct irte {

include/linux/swiotlb.h

@@ -13,11 +13,9 @@ struct device;
 struct page;
 struct scatterlist;
 
-enum swiotlb_force {
-	SWIOTLB_NORMAL,		/* Default - depending on HW DMA mask etc. */
-	SWIOTLB_FORCE,		/* swiotlb=force */
-	SWIOTLB_NO_FORCE,	/* swiotlb=noforce */
-};
+#define SWIOTLB_VERBOSE	(1 << 0) /* verbose initialization */
+#define SWIOTLB_FORCE	(1 << 1) /* force bounce buffering */
+#define SWIOTLB_ANY	(1 << 2) /* allow any memory for the buffer */
 
 /*
  * Maximum allowable number of contiguous slabs to map,
@@ -36,11 +34,11 @@ enum swiotlb_force {
 /* default to 64MB */
 #define IO_TLB_DEFAULT_SIZE (64UL<<20)
 
-extern void swiotlb_init(int verbose);
-int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 unsigned long swiotlb_size_or_default(void);
-extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-extern int swiotlb_late_init_with_default_size(size_t default_size);
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+	int (*remap)(void *tlb, unsigned long nslabs));
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+	int (*remap)(void *tlb, unsigned long nslabs));
 extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
@@ -126,13 +124,16 @@ static inline bool is_swiotlb_force_bounce(struct device *dev)
 	return mem && mem->force_bounce;
 }
 
+void swiotlb_init(bool addressing_limited, unsigned int flags);
 void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
 bool is_swiotlb_active(struct device *dev);
 void __init swiotlb_adjust_size(unsigned long size);
 #else
-#define swiotlb_force SWIOTLB_NO_FORCE
+static inline void swiotlb_init(bool addressing_limited, unsigned int flags)
+{
+}
 static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
 {
 	return false;
@@ -164,7 +165,6 @@ static inline void swiotlb_adjust_size(unsigned long size)
 #endif /* CONFIG_SWIOTLB */
 
 extern void swiotlb_print_info(void);
-extern void swiotlb_set_max_segment(unsigned int);
 
 #ifdef CONFIG_DMA_RESTRICTED_POOL
 struct page *swiotlb_alloc(struct device *dev, size_t size);

include/trace/events/swiotlb.h

@@ -8,20 +8,15 @@
 #include <linux/tracepoint.h>
 
 TRACE_EVENT(swiotlb_bounced,
-
-	TP_PROTO(struct device *dev,
-		 dma_addr_t dev_addr,
-		 size_t size,
-		 enum swiotlb_force swiotlb_force),
-
-	TP_ARGS(dev, dev_addr, size, swiotlb_force),
+	TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+	TP_ARGS(dev, dev_addr, size),
 
 	TP_STRUCT__entry(
-		__string(	dev_name,	dev_name(dev)		)
-		__field(	u64,	dma_mask			)
-		__field(	dma_addr_t,	dev_addr		)
-		__field(	size_t,	size				)
-		__field(	enum swiotlb_force,	swiotlb_force	)
+		__string(dev_name, dev_name(dev))
+		__field(u64, dma_mask)
+		__field(dma_addr_t, dev_addr)
+		__field(size_t, size)
+		__field(bool, force)
 	),
 
 	TP_fast_assign(
@@ -29,19 +24,15 @@ TRACE_EVENT(swiotlb_bounced,
 		__entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0);
 		__entry->dev_addr = dev_addr;
 		__entry->size = size;
-		__entry->swiotlb_force = swiotlb_force;
+		__entry->force = is_swiotlb_force_bounce(dev);
 	),
 
-	TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx "
-		"size=%zu %s",
+	TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx size=%zu %s",
 		__get_str(dev_name),
 		__entry->dma_mask,
 		(unsigned long long)__entry->dev_addr,
 		__entry->size,
-		__print_symbolic(__entry->swiotlb_force,
-			{ SWIOTLB_NORMAL,	"NORMAL" },
-			{ SWIOTLB_FORCE,	"FORCE" },
-			{ SWIOTLB_NO_FORCE,	"NO_FORCE" }))
+		__entry->force ? "FORCE" : "NORMAL")
 );
 
 #endif /*  _TRACE_SWIOTLB_H */

include/xen/arm/page-coherent.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_ARM_PAGE_COHERENT_H
-#define _XEN_ARM_PAGE_COHERENT_H
-
-#include <linux/dma-mapping.h>
-#include <asm/page.h>
-
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
-{
-	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
-}
-
-#endif /* _XEN_ARM_PAGE_COHERENT_H */

include/xen/arm/page.h

@@ -115,6 +115,5 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 bool xen_arch_need_swiotlb(struct device *dev,
 			   phys_addr_t phys,
 			   dma_addr_t dev_addr);
-unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */

include/xen/swiotlb-xen.h

@@ -10,8 +10,6 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
 void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
 			     size_t size, enum dma_data_direction dir);
 
-int xen_swiotlb_init(void);
-void __init xen_swiotlb_init_early(void);
 extern const struct dma_map_ops xen_swiotlb_dma_ops;
 
 #endif /* __LINUX_SWIOTLB_XEN_H */

include/xen/xen-ops.h

@@ -42,13 +42,6 @@ int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
 
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
-				unsigned int address_bits,
-				dma_addr_t *dma_handle);
-void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
-#endif
-
 #if defined(CONFIG_XEN_PV)
 int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
 		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,

kernel/dma/debug.c

@@ -448,7 +448,7 @@ void debug_dma_dump_mappings(struct device *dev)
  * other hand, consumes a single dma_debug_entry, but inserts 'nents'
  * entries into the tree.
  */
-static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
+static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC);
 static DEFINE_SPINLOCK(radix_lock);
 #define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
 #define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)

kernel/dma/direct.c

@@ -79,7 +79,7 @@ static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size)
 {
 	if (!force_dma_unencrypted(dev))
 		return 0;
-	return set_memory_decrypted((unsigned long)vaddr, 1 << get_order(size));
+	return set_memory_decrypted((unsigned long)vaddr, PFN_UP(size));
 }
 
 static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
@@ -88,7 +88,7 @@ static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
 
 	if (!force_dma_unencrypted(dev))
 		return 0;
-	ret = set_memory_encrypted((unsigned long)vaddr, 1 << get_order(size));
+	ret = set_memory_encrypted((unsigned long)vaddr, PFN_UP(size));
 	if (ret)
 		pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n");
 	return ret;
@@ -115,7 +115,7 @@ static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size)
 }
 
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		gfp_t gfp)
+		gfp_t gfp, bool allow_highmem)
 {
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
@@ -129,9 +129,12 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
-	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		dma_free_contiguous(dev, page, size);
-		page = NULL;
+	if (page) {
+		if (!dma_coherent_ok(dev, page_to_phys(page), size) ||
+		    (!allow_highmem && PageHighMem(page))) {
+			dma_free_contiguous(dev, page, size);
+			page = NULL;
+		}
 	}
 again:
 	if (!page)
@@ -189,7 +192,7 @@ static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size,
 {
 	struct page *page;
 
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
 	if (!page)
 		return NULL;
 
@@ -262,7 +265,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	/* we always manually zero the memory once we are done */
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
 	if (!page)
 		return NULL;
 
@@ -370,19 +373,9 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
-	page = __dma_direct_alloc_pages(dev, size, gfp);
+	page = __dma_direct_alloc_pages(dev, size, gfp, false);
 	if (!page)
 		return NULL;
-	if (PageHighMem(page)) {
-		/*
-		 * Depending on the cma= arguments and per-arch setup
-		 * dma_alloc_contiguous could return highmem pages.
-		 * Without remapping there is no way to return them here,
-		 * so log an error and fail.
-		 */
-		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		goto out_free_pages;
-	}
 
 	ret = page_address(page);
 	if (dma_set_decrypted(dev, ret, size))

kernel/dma/direct.h

@@ -91,7 +91,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 		return swiotlb_map(dev, phys, size, dir, attrs);
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
+		if (is_swiotlb_active(dev))
 			return swiotlb_map(dev, phys, size, dir, attrs);
 
 		dev_WARN_ONCE(dev, 1,

kernel/dma/swiotlb.c

@@ -62,18 +62,13 @@
 
 #define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 
-enum swiotlb_force swiotlb_force;
+static bool swiotlb_force_bounce;
+static bool swiotlb_force_disable;
 
 struct io_tlb_mem io_tlb_default_mem;
 
 phys_addr_t swiotlb_unencrypted_base;
 
-/*
- * Max segment that we can provide which (if pages are contingous) will
- * not be bounced (unless SWIOTLB_FORCE is set).
- */
-static unsigned int max_segment;
-
 static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
 
 static int __init
@@ -87,9 +82,9 @@ setup_io_tlb_npages(char *str)
 	if (*str == ',')
 		++str;
 	if (!strcmp(str, "force"))
-		swiotlb_force = SWIOTLB_FORCE;
+		swiotlb_force_bounce = true;
 	else if (!strcmp(str, "noforce"))
-		swiotlb_force = SWIOTLB_NO_FORCE;
+		swiotlb_force_disable = true;
 
 	return 0;
 }
@@ -97,18 +92,12 @@ early_param("swiotlb", setup_io_tlb_npages);
 
 unsigned int swiotlb_max_segment(void)
 {
-	return io_tlb_default_mem.nslabs ? max_segment : 0;
+	if (!io_tlb_default_mem.nslabs)
+		return 0;
+	return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE);
 }
 EXPORT_SYMBOL_GPL(swiotlb_max_segment);
 
-void swiotlb_set_max_segment(unsigned int val)
-{
-	if (swiotlb_force == SWIOTLB_FORCE)
-		max_segment = 1;
-	else
-		max_segment = rounddown(val, PAGE_SIZE);
-}
-
 unsigned long swiotlb_size_or_default(void)
 {
 	return default_nslabs << IO_TLB_SHIFT;
@@ -214,7 +203,7 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	mem->index = 0;
 	mem->late_alloc = late_alloc;
 
-	if (swiotlb_force == SWIOTLB_FORCE)
+	if (swiotlb_force_bounce)
 		mem->force_bounce = true;
 
 	spin_lock_init(&mem->lock);
@@ -236,17 +225,49 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	return;
 }
 
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+		int (*remap)(void *tlb, unsigned long nslabs))
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
+	unsigned long nslabs = default_nslabs;
 	size_t alloc_size;
+	size_t bytes;
+	void *tlb;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return 0;
+	if (!addressing_limit && !swiotlb_force_bounce)
+		return;
+	if (swiotlb_force_disable)
+		return;
 
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
+	/*
+	 * By default allocate the bounce buffer memory from low memory, but
+	 * allow to pick a location everywhere for hypervisors with guest
+	 * memory encryption.
+	 */
+retry:
+	bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT);
+	if (flags & SWIOTLB_ANY)
+		tlb = memblock_alloc(bytes, PAGE_SIZE);
+	else
+		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+	if (!tlb) {
+		pr_warn("%s: failed to allocate tlb structure\n", __func__);
+		return;
+	}
+
+	if (remap && remap(tlb, nslabs) < 0) {
+		memblock_free(tlb, PAGE_ALIGN(bytes));
+
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs < IO_TLB_MIN_SLABS)
+			panic("%s: Failed to remap %zu bytes\n",
+			      __func__, bytes);
+		goto retry;
+	}
 
 	alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
 	mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
@@ -255,38 +276,15 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		      __func__, alloc_size, PAGE_SIZE);
 
 	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
+	mem->force_bounce = flags & SWIOTLB_FORCE;
 
-	if (verbose)
+	if (flags & SWIOTLB_VERBOSE)
 		swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
-	return 0;
 }
 
-/*
- * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the DMA API.
- */
-void  __init
-swiotlb_init(int verbose)
+void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 {
-	size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
-	void *tlb;
-
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return;
-
-	/* Get IO TLB memory from the low pages */
-	tlb = memblock_alloc_low(bytes, PAGE_SIZE);
-	if (!tlb)
-		goto fail;
-	if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose))
-		goto fail_free_mem;
-	return;
-
-fail_free_mem:
-	memblock_free(tlb, bytes);
-fail:
-	pr_warn("Cannot allocate buffer");
+	return swiotlb_init_remap(addressing_limit, flags, NULL);
 }
 
 /*
@@ -294,72 +292,65 @@ swiotlb_init(int verbose)
  * initialize the swiotlb later using the slab allocator if needed.
  * This should be just like above, but with some error catching.
  */
-int
-swiotlb_late_init_with_default_size(size_t default_size)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+		int (*remap)(void *tlb, unsigned long nslabs))
 {
-	unsigned long nslabs =
-		ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
-	unsigned long bytes;
+	struct io_tlb_mem *mem = &io_tlb_default_mem;
+	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned char *vstart = NULL;
 	unsigned int order;
+	bool retried = false;
 	int rc = 0;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (swiotlb_force_disable)
 		return 0;
 
-	/*
-	 * Get IO TLB memory from the low pages
-	 */
+retry:
 	order = get_order(nslabs << IO_TLB_SHIFT);
 	nslabs = SLABS_PER_PAGE << order;
-	bytes = nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+		vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
 						  order);
 		if (vstart)
 			break;
 		order--;
+		nslabs = SLABS_PER_PAGE << order;
+		retried = true;
 	}
 
 	if (!vstart)
 		return -ENOMEM;
 
-	if (order != get_order(bytes)) {
-		pr_warn("only able to allocate %ld MB\n",
-			(PAGE_SIZE << order) >> 20);
-		nslabs = SLABS_PER_PAGE << order;
-	}
-	rc = swiotlb_late_init_with_tbl(vstart, nslabs);
-	if (rc)
+	if (remap)
+		rc = remap(vstart, nslabs);
+	if (rc) {
 		free_pages((unsigned long)vstart, order);
 
-	return rc;
-}
-
-int
-swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
-{
-	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	unsigned long bytes = nslabs << IO_TLB_SHIFT;
-
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
-		return 0;
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs < IO_TLB_MIN_SLABS)
+			return rc;
+		retried = true;
+		goto retry;
+	}
 
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
+	if (retried) {
+		pr_warn("only able to allocate %ld MB\n",
+			(PAGE_SIZE << order) >> 20);
+	}
 
 	mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 		get_order(array_size(sizeof(*mem->slots), nslabs)));
-	if (!mem->slots)
+	if (!mem->slots) {
+		free_pages((unsigned long)vstart, order);
 		return -ENOMEM;
+	}
 
-	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
-	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
+	set_memory_decrypted((unsigned long)vstart,
+			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
+	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, true);
 
 	swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
@@ -369,6 +360,9 @@ void __init swiotlb_exit(void)
 	unsigned long tbl_vaddr;
 	size_t tbl_size, slots_size;
 
+	if (swiotlb_force_bounce)
+		return;
+
 	if (!mem->nslabs)
 		return;
 
@@ -717,8 +711,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	phys_addr_t swiotlb_addr;
 	dma_addr_t dma_addr;
 
-	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
-			      swiotlb_force);
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
 			attrs);
@@ -743,7 +736,18 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 
 size_t swiotlb_max_mapping_size(struct device *dev)
 {
-	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
+	int min_align_mask = dma_get_min_align_mask(dev);
+	int min_align = 0;
+
+	/*
+	 * swiotlb_find_slots() skips slots according to
+	 * min align mask. This affects max mapping size.
+	 * Take it into acount here.
+	 */
+	if (min_align_mask)
+		min_align = roundup(min_align_mask, IO_TLB_SIZE);
+
+	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
 }
 
 bool is_swiotlb_active(struct device *dev)