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
  ...

9 files changed, 99 insertions, 211 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 1a2dc328cb5e..03364dc40d8d 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index ed837383de5c..194d54eed537 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/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);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index af3ba08b684b..7a5630d904b2 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/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 @@ out:
 			 * 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 @@ out:
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return 0;
+		return;
 	}
 
 	/*
@@ -561,6 +559,4 @@ out:
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
-
-	return 1;
 }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4b67094215bb..5b8f2c357160 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/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)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index de234e7a8962..30bbe4abb5d6 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/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;
 }
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
deleted file mode 100644
index 42e92ec62973..000000000000
--- a/arch/x86/kernel/pci-iommu_table.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// 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
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
deleted file mode 100644
index 814ab46a0dad..000000000000
--- a/arch/x86/kernel/pci-swiotlb.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// 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();
-	}
-}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index f9af561c3cd4..0c1154a1c403 100644
--- a/arch/x86/kernel/tboot.c
+++ b/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>
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 7fda7f27e762..f5f6dc2e8007 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/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 = .;