Merge branch 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
x86: Detect whether we should use Xen SWIOTLB.
pci-swiotlb-xen: Add glue code to setup dma_ops utilizing xen_swiotlb_* functions.
swiotlb-xen: SWIOTLB library for Xen PV guest with PCI passthrough.
xen/mmu: inhibit vmap aliases rather than trying to clear them out
vmap: add flag to allow lazy unmap to be disabled at runtime
xen: Add xen_create_contiguous_region
xen: Rename the balloon lock
xen: Allow unprivileged Xen domains to create iomap pages
xen: use _PAGE_IOMAP in ioremap to do machine mappings

Fix up trivial conflicts (adding both xen swiotlb and xen pci platform
driver setup close to each other) in drivers/xen/{Kconfig,Makefile} and
include/xen/xen-ops.h

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

···
  */
 static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 {
-	extern unsigned long max_mapnr;
 	unsigned long pfn = mfn_to_pfn(mfn);
-	if ((pfn < max_mapnr)
-	    && !xen_feature(XENFEAT_auto_translated_physmap)
-	    && (get_phys_to_machine(pfn) != mfn))
-		return max_mapnr; /* force !pfn_valid() */
-	/* XXX fixme; not true with sparsemem */
+	if (get_phys_to_machine(pfn) != mfn)
+		return -1; /* force !pfn_valid() */
 	return pfn;
 }
 

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

···
+#ifndef _ASM_X86_SWIOTLB_XEN_H
+#define _ASM_X86_SWIOTLB_XEN_H
+
+#ifdef CONFIG_SWIOTLB_XEN
+extern int xen_swiotlb;
+extern int __init pci_xen_swiotlb_detect(void);
+extern void __init pci_xen_swiotlb_init(void);
+#else
+#define xen_swiotlb (0)
+static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
+static inline void __init pci_xen_swiotlb_init(void) { }
+#endif
+
+#endif /* _ASM_X86_SWIOTLB_XEN_H */

arch/x86/kernel/pci-dma.c

···
 #include <asm/calgary.h>
 #include <asm/amd_iommu.h>
 #include <asm/x86_init.h>
+#include <asm/xen/swiotlb-xen.h>
 
 static int forbid_dac __read_mostly;
 
···
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 
-	if (pci_swiotlb_detect())
+	if (pci_xen_swiotlb_detect() || pci_swiotlb_detect())
 		goto out;
 
 	gart_iommu_hole_init();
···
 	/* needs to be called after gart_iommu_hole_init */
 	amd_iommu_detect();
 out:
+	pci_xen_swiotlb_init();
+
 	pci_swiotlb_init();
 }
 
···
 #endif
 	x86_init.iommu.iommu_init();
 
-	if (swiotlb) {
+	if (swiotlb || xen_swiotlb) {
 		printk(KERN_INFO "PCI-DMA: "
 		       "Using software bounce buffering for IO (SWIOTLB)\n");
 		swiotlb_print_info();

arch/x86/xen/Makefile

···
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
+obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o

arch/x86/xen/enlighten.c

···
 
 	pgd = (pgd_t *)xen_start_info->pt_base;
 
+	if (!xen_initial_domain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
+	__supported_pte_mask |= _PAGE_IOMAP;
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];

arch/x86/xen/mmu.c

···
 #include <linux/highmem.h>
 #include <linux/debugfs.h>
 #include <linux/bug.h>
+#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
 
···
 #include <asm/mmu_context.h>
 #include <asm/setup.h>
 #include <asm/paravirt.h>
+#include <asm/e820.h>
 #include <asm/linkage.h>
+#include <asm/page.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 
+#include <xen/xen.h>
 #include <xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/hvm/hvm_op.h>
 #include <xen/interface/version.h>
+#include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
 
 #include "multicalls.h"
···
 #include "debugfs.h"
 
 #define MMU_UPDATE_HISTO	30
+
+/*
+ * Protects atomic reservation decrease/increase against concurrent increases.
+ * Also protects non-atomic updates of current_pages and driver_pages, and
+ * balloon lists.
+ */
+DEFINE_SPINLOCK(xen_reservation_lock);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 
···
 	return PagePinned(page);
 }
 
+static bool xen_iomap_pte(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_IOMAP;
+}
+
+static void xen_set_iomap_pte(pte_t *ptep, pte_t pteval)
+{
+	struct multicall_space mcs;
+	struct mmu_update *u;
+
+	mcs = xen_mc_entry(sizeof(*u));
+	u = mcs.args;
+
+	/* ptep might be kmapped when using 32-bit HIGHPTE */
+	u->ptr = arbitrary_virt_to_machine(ptep).maddr;
+	u->val = pte_val_ma(pteval);
+
+	MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_IO);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
 static void xen_extend_mmu_update(const struct mmu_update *update)
 {
 	struct multicall_space mcs;
···
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval)
 {
+	if (xen_iomap_pte(pteval)) {
+		xen_set_iomap_pte(ptep, pteval);
+		goto out;
+	}
+
 	ADD_STATS(set_pte_at, 1);
 //	ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
 	ADD_STATS(set_pte_at_current, mm == current->mm);
···
 	return val;
 }
 
+static pteval_t iomap_pte(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & PTE_FLAGS_MASK;
+
+		/* We assume the pte frame number is a MFN, so
+		   just use it as-is. */
+		val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
 pteval_t xen_pte_val(pte_t pte)
 {
+	if (xen_initial_domain() && (pte.pte & _PAGE_IOMAP))
+		return pte.pte;
+
 	return pte_mfn_to_pfn(pte.pte);
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
···
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	pte = pte_pfn_to_mfn(pte);
+	phys_addr_t addr = (pte & PTE_PFN_MASK);
+
+	/*
+	 * Unprivileged domains are allowed to do IOMAPpings for
+	 * PCI passthrough, but not map ISA space.  The ISA
+	 * mappings are just dummy local mappings to keep other
+	 * parts of the kernel happy.
+	 */
+	if (unlikely(pte & _PAGE_IOMAP) &&
+	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+		pte = iomap_pte(pte);
+	} else {
+		pte &= ~_PAGE_IOMAP;
+		pte = pte_pfn_to_mfn(pte);
+	}
+
 	return native_make_pte(pte);
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
···
 
 void xen_set_pte(pte_t *ptep, pte_t pte)
 {
+	if (xen_iomap_pte(pte)) {
+		xen_set_iomap_pte(ptep, pte);
+		return;
+	}
+
 	ADD_STATS(pte_update, 1);
 //	ADD_STATS(pte_update_pinned, xen_page_pinned(ptep));
 	ADD_STATS(pte_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
···
 #ifdef CONFIG_X86_PAE
 void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
+	if (xen_iomap_pte(pte)) {
+		xen_set_iomap_pte(ptep, pte);
+		return;
+	}
+
 	set_64bit((u64 *)ptep, native_pte_val(pte));
 }
 
···
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
-	vm_unmap_aliases();
-
 	xen_mc_batch();
 
 	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
···
 	if (PagePinned(virt_to_page(mm->pgd))) {
 		SetPagePinned(page);
 
-		vm_unmap_aliases();
 		if (!PageHighMem(page)) {
 			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
···
 		pte = pfn_pte(phys, prot);
 		break;
 
-	default:
+	case FIX_PARAVIRT_BOOTMAP:
+		/* This is an MFN, but it isn't an IO mapping from the
+		   IO domain */
 		pte = mfn_pte(phys, prot);
+		break;
+
+	default:
+		/* By default, set_fixmap is used for hardware mappings */
+		pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP));
 		break;
 	}
 
···
 	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;
+
+	vmap_lazy_unmap = false;
 }
+
+/* Protected by xen_reservation_lock. */
+#define MAX_CONTIG_ORDER 9 /* 2MB */
+static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
+
+#define VOID_PTE (mfn_pte(0, __pgprot(0)))
+static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
+				unsigned long *in_frames,
+				unsigned long *out_frames)
+{
+	int i;
+	struct multicall_space mcs;
+
+	xen_mc_batch();
+	for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) {
+		mcs = __xen_mc_entry(0);
+
+		if (in_frames)
+			in_frames[i] = virt_to_mfn(vaddr);
+
+		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
+		set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+
+		if (out_frames)
+			out_frames[i] = virt_to_pfn(vaddr);
+	}
+	xen_mc_issue(0);
+}
+
+/*
+ * Update the pfn-to-mfn mappings for a virtual address range, either to
+ * point to an array of mfns, or contiguously from a single starting
+ * mfn.
+ */
+static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
+				     unsigned long *mfns,
+				     unsigned long first_mfn)
+{
+	unsigned i, limit;
+	unsigned long mfn;
+
+	xen_mc_batch();
+
+	limit = 1u << order;
+	for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) {
+		struct multicall_space mcs;
+		unsigned flags;
+
+		mcs = __xen_mc_entry(0);
+		if (mfns)
+			mfn = mfns[i];
+		else
+			mfn = first_mfn + i;
+
+		if (i < (limit - 1))
+			flags = 0;
+		else {
+			if (order == 0)
+				flags = UVMF_INVLPG | UVMF_ALL;
+			else
+				flags = UVMF_TLB_FLUSH | UVMF_ALL;
+		}
+
+		MULTI_update_va_mapping(mcs.mc, vaddr,
+				mfn_pte(mfn, PAGE_KERNEL), flags);
+
+		set_phys_to_machine(virt_to_pfn(vaddr), mfn);
+	}
+
+	xen_mc_issue(0);
+}
+
+/*
+ * Perform the hypercall to exchange a region of our pfns to point to
+ * memory with the required contiguous alignment.  Takes the pfns as
+ * input, and populates mfns as output.
+ *
+ * Returns a success code indicating whether the hypervisor was able to
+ * satisfy the request or not.
+ */
+static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
+			       unsigned long *pfns_in,
+			       unsigned long extents_out,
+			       unsigned int order_out,
+			       unsigned long *mfns_out,
+			       unsigned int address_bits)
+{
+	long rc;
+	int success;
+
+	struct xen_memory_exchange exchange = {
+		.in = {
+			.nr_extents   = extents_in,
+			.extent_order = order_in,
+			.extent_start = pfns_in,
+			.domid        = DOMID_SELF
+		},
+		.out = {
+			.nr_extents   = extents_out,
+			.extent_order = order_out,
+			.extent_start = mfns_out,
+			.address_bits = address_bits,
+			.domid        = DOMID_SELF
+		}
+	};
+
+	BUG_ON(extents_in << order_in != extents_out << order_out);
+
+	rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange);
+	success = (exchange.nr_exchanged == extents_in);
+
+	BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0)));
+	BUG_ON(success && (rc != 0));
+
+	return success;
+}
+
+int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+				 unsigned int address_bits)
+{
+	unsigned long *in_frames = discontig_frames, out_frame;
+	unsigned long  flags;
+	int            success;
+
+	/*
+	 * Currently an auto-translated guest will not perform I/O, nor will
+	 * it require PAE page directories below 4GB. Therefore any calls to
+	 * this function are redundant and can be ignored.
+	 */
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
+	if (unlikely(order > MAX_CONTIG_ORDER))
+		return -ENOMEM;
+
+	memset((void *) vstart, 0, PAGE_SIZE << order);
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	/* 1. Zap current PTEs, remembering MFNs. */
+	xen_zap_pfn_range(vstart, order, in_frames, NULL);
+
+	/* 2. Get a new contiguous memory extent. */
+	out_frame = virt_to_pfn(vstart);
+	success = xen_exchange_memory(1UL << order, 0, in_frames,
+				      1, order, &out_frame,
+				      address_bits);
+
+	/* 3. Map the new extent in place of old pages. */
+	if (success)
+		xen_remap_exchanged_ptes(vstart, order, NULL, out_frame);
+	else
+		xen_remap_exchanged_ptes(vstart, order, in_frames, 0);
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+
+	return success ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+
+void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+{
+	unsigned long *out_frames = discontig_frames, in_frame;
+	unsigned long  flags;
+	int success;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	if (unlikely(order > MAX_CONTIG_ORDER))
+		return;
+
+	memset((void *) vstart, 0, PAGE_SIZE << order);
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	/* 1. Find start MFN of contiguous extent. */
+	in_frame = virt_to_mfn(vstart);
+
+	/* 2. Zap current PTEs. */
+	xen_zap_pfn_range(vstart, order, NULL, out_frames);
+
+	/* 3. Do the exchange for non-contiguous MFNs. */
+	success = xen_exchange_memory(1, order, &in_frame, 1UL << order,
+					0, out_frames, 0);
+
+	/* 4. Map new pages in place of old pages. */
+	if (success)
+		xen_remap_exchanged_ptes(vstart, order, out_frames, 0);
+	else
+		xen_remap_exchanged_ptes(vstart, order, NULL, in_frame);
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+}
+EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
 #ifdef CONFIG_XEN_PVHVM
 static void xen_hvm_exit_mmap(struct mm_struct *mm)

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

···
+/* Glue code to lib/swiotlb-xen.c */
+
+#include <linux/dma-mapping.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/xen/hypervisor.h>
+#include <xen/xen.h>
+
+int xen_swiotlb __read_mostly;
+
+static struct dma_map_ops xen_swiotlb_dma_ops = {
+	.mapping_error = xen_swiotlb_dma_mapping_error,
+	.alloc_coherent = xen_swiotlb_alloc_coherent,
+	.free_coherent = xen_swiotlb_free_coherent,
+	.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,
+	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
+	.map_sg = xen_swiotlb_map_sg_attrs,
+	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
+	.map_page = xen_swiotlb_map_page,
+	.unmap_page = xen_swiotlb_unmap_page,
+	.dma_supported = xen_swiotlb_dma_supported,
+};
+
+/*
+ * 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 running as PV guest, either iommu=soft, or swiotlb=force will
+	 * activate this IOMMU. If running as PV privileged, activate it
+	 * irregardlesss.
+	 */
+	if ((xen_initial_domain() || swiotlb || swiotlb_force) &&
+	    (xen_pv_domain()))
+		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. */
+	if (xen_pv_domain())
+		swiotlb = 0;
+
+	return xen_swiotlb;
+}
+
+void __init pci_xen_swiotlb_init(void)
+{
+	if (xen_swiotlb) {
+		xen_swiotlb_init(1);
+		dma_ops = &xen_swiotlb_dma_ops;
+	}
+}

drivers/xen/Kconfig

···
 	  initializing xenbus and grant_table when running in a Xen HVM
 	  domain. As a consequence this driver is required to run any Xen PV
 	  frontend on Xen HVM.
+
+config SWIOTLB_XEN
+	def_bool y
+	depends on SWIOTLB
+
 endmenu

drivers/xen/Makefile

···
 obj-$(CONFIG_XENFS)		+= xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 obj-$(CONFIG_XEN_PLATFORM_PCI)	+= platform-pci.o
+obj-$(CONFIG_SWIOTLB_XEN)	+= swiotlb-xen.o

drivers/xen/balloon.c

···
 
 static int register_balloon(struct sys_device *sysdev);
 
-/*
- * Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and driver_pages, and
- * balloon lists.
- */
-static DEFINE_SPINLOCK(balloon_lock);
-
 static struct balloon_stats balloon_stats;
 
 /* We increase/decrease in batches which fit in a page */
···
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	page = balloon_first_page();
 	for (i = 0; i < nr_pages; i++) {
···
 	balloon_stats.current_pages += rc;
 
  out:
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return rc < 0 ? rc : rc != nr_pages;
 }
···
 	kmap_flush_unused();
 	flush_tlb_all();
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
···
 
 	balloon_stats.current_pages -= nr_pages;
 
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return need_sleep;
 }

drivers/xen/swiotlb-xen.c

···
+/*
+ *  Copyright 2010
+ *  by Konrad Rzeszutek Wilk <[e-mail]>
+ *
+ * This code provides a IOMMU for Xen PV guests with PCI passthrough.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * PV guests under Xen are running in an non-contiguous memory architecture.
+ *
+ * When PCI pass-through is utilized, this necessitates an IOMMU for
+ * translating bus (DMA) to virtual and vice-versa and also providing a
+ * mechanism to have contiguous pages for device drivers operations (say DMA
+ * operations).
+ *
+ * Specifically, under Xen the Linux idea of pages is an illusion. It
+ * assumes that pages start at zero and go up to the available memory. To
+ * help with that, the Linux Xen MMU provides a lookup mechanism to
+ * translate the page frame numbers (PFN) to machine frame numbers (MFN)
+ * and vice-versa. The MFN are the "real" frame numbers. Furthermore
+ * memory is not contiguous. Xen hypervisor stitches memory for guests
+ * from different pools, which means there is no guarantee that PFN==MFN
+ * and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
+ * allocated in descending order (high to low), meaning the guest might
+ * never get any MFN's under the 4GB mark.
+ *
+ */
+
+#include <linux/bootmem.h>
+#include <linux/dma-mapping.h>
+#include <xen/swiotlb-xen.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+
+static char *xen_io_tlb_start, *xen_io_tlb_end;
+static unsigned long xen_io_tlb_nslabs;
+/*
+ * Quick lookup value of the bus address of the IOTLB.
+ */
+
+u64 start_dma_addr;
+
+static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+{
+	return phys_to_machine(XPADDR(paddr)).maddr;;
+}
+
+static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
+{
+	return machine_to_phys(XMADDR(baddr)).paddr;
+}
+
+static dma_addr_t xen_virt_to_bus(void *address)
+{
+	return xen_phys_to_bus(virt_to_phys(address));
+}
+
+static int check_pages_physically_contiguous(unsigned long pfn,
+					     unsigned int offset,
+					     size_t length)
+{
+	unsigned long next_mfn;
+	int i;
+	int nr_pages;
+
+	next_mfn = pfn_to_mfn(pfn);
+	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
+
+	for (i = 1; i < nr_pages; i++) {
+		if (pfn_to_mfn(++pfn) != ++next_mfn)
+			return 0;
+	}
+	return 1;
+}
+
+static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+{
+	unsigned long pfn = PFN_DOWN(p);
+	unsigned int offset = p & ~PAGE_MASK;
+
+	if (offset + size <= PAGE_SIZE)
+		return 0;
+	if (check_pages_physically_contiguous(pfn, offset, size))
+		return 0;
+	return 1;
+}
+
+static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
+{
+	unsigned long mfn = PFN_DOWN(dma_addr);
+	unsigned long pfn = mfn_to_local_pfn(mfn);
+	phys_addr_t paddr;
+
+	/* If the address is outside our domain, it CAN
+	 * have the same virtual address as another address
+	 * in our domain. Therefore _only_ check address within our domain.
+	 */
+	if (pfn_valid(pfn)) {
+		paddr = PFN_PHYS(pfn);
+		return paddr >= virt_to_phys(xen_io_tlb_start) &&
+		       paddr < virt_to_phys(xen_io_tlb_end);
+	}
+	return 0;
+}
+
+static int max_dma_bits = 32;
+
+static int
+xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+{
+	int i, rc;
+	int dma_bits;
+
+	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+
+	i = 0;
+	do {
+		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
+
+		do {
+			rc = xen_create_contiguous_region(
+				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				get_order(slabs << IO_TLB_SHIFT),
+				dma_bits);
+		} while (rc && dma_bits++ < max_dma_bits);
+		if (rc)
+			return rc;
+
+		i += slabs;
+	} while (i < nslabs);
+	return 0;
+}
+
+void __init xen_swiotlb_init(int verbose)
+{
+	unsigned long bytes;
+	int rc;
+
+	xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+	xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+
+	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from any location.
+	 */
+	xen_io_tlb_start = alloc_bootmem(bytes);
+	if (!xen_io_tlb_start)
+		panic("Cannot allocate SWIOTLB buffer");
+
+	xen_io_tlb_end = xen_io_tlb_start + bytes;
+	/*
+	 * And replace that memory with pages under 4GB.
+	 */
+	rc = xen_swiotlb_fixup(xen_io_tlb_start,
+			       bytes,
+			       xen_io_tlb_nslabs);
+	if (rc)
+		goto error;
+
+	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
+	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+
+	return;
+error:
+	panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\
+	      "We either don't have the permission or you do not have enough"\
+	      "free memory under 4GB!\n", rc);
+}
+
+void *
+xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags)
+{
+	void *ret;
+	int order = get_order(size);
+	u64 dma_mask = DMA_BIT_MASK(32);
+	unsigned long vstart;
+
+	/*
+	* 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);
+
+	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
+		return ret;
+
+	vstart = __get_free_pages(flags, order);
+	ret = (void *)vstart;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
+
+	if (ret) {
+		if (xen_create_contiguous_region(vstart, order,
+						 fls64(dma_mask)) != 0) {
+			free_pages(vstart, order);
+			return NULL;
+		}
+		memset(ret, 0, size);
+		*dma_handle = virt_to_machine(ret).maddr;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
+
+void
+xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+			  dma_addr_t dev_addr)
+{
+	int order = get_order(size);
+
+	if (dma_release_from_coherent(hwdev, order, vaddr))
+		return;
+
+	xen_destroy_contiguous_region((unsigned long)vaddr, order);
+	free_pages((unsigned long)vaddr, order);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
+
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode.  The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dev_addr = xen_phys_to_bus(phys);
+	void *map;
+
+	BUG_ON(dir == DMA_NONE);
+	/*
+	 * If the address happens to be in the device's DMA window,
+	 * we can safely return the device addr and not worry about bounce
+	 * buffering it.
+	 */
+	if (dma_capable(dev, dev_addr, size) &&
+	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+		return dev_addr;
+
+	/*
+	 * Oh well, have to allocate and map a bounce buffer.
+	 */
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
+	if (!map)
+		return DMA_ERROR_CODE;
+
+	dev_addr = xen_virt_to_bus(map);
+
+	/*
+	 * Ensure that the address returned is DMA'ble
+	 */
+	if (!dma_capable(dev, dev_addr, size))
+		panic("map_single: bounce buffer is not DMA'ble");
+
+	return dev_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
+
+/*
+ * Unmap a single streaming mode DMA translation.  The dma_addr and size must
+ * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	xen_unmap_single(hwdev, dev_addr, size, dir);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so.  At the next point you give the dma
+ * address back to the card, you must first perform a
+ * xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			enum dma_sync_target target)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
+				       target);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
+
+void
+xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above xen_swiotlb_map_page
+ * interface.  Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length.  They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ *       DMA address/length pairs than there are SG table elements.
+ *       (for example via virtual mapping capabilities)
+ *       The routine returns the number of addr/length pairs actually
+ *       used, at most nents.
+ *
+ * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
+ * same here.
+ */
+int
+xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			 int nelems, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i) {
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
+
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length) ||
+		    range_straddles_page_boundary(paddr, sg->length)) {
+			void *map = swiotlb_tbl_map_single(hwdev,
+							   start_dma_addr,
+							   sg_phys(sg),
+							   sg->length, dir);
+			if (!map) {
+				/* Don't panic here, we expect map_sg users
+				   to do proper error handling. */
+				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+							   attrs);
+				sgl[0].dma_length = 0;
+				return DMA_ERROR_CODE;
+			}
+			sg->dma_address = xen_virt_to_bus(map);
+		} else
+			sg->dma_address = dev_addr;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
+
+int
+xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		   enum dma_data_direction dir)
+{
+	return xen_swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg);
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
+
+void
+xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		     enum dma_data_direction dir)
+{
+	return xen_swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg);
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+		    int nelems, enum dma_data_direction dir,
+		    enum dma_sync_target target)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_swiotlb_sync_single(hwdev, sg->dma_address,
+					sg->dma_length, dir, target);
+}
+
+void
+xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
+
+void
+xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			       int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
+
+int
+xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);

include/linux/vmalloc.h

···
 
 struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 
+extern bool vmap_lazy_unmap;
+
 /* bits in flags of vmalloc's vm_struct below */
 #define VM_IOREMAP	0x00000001	/* ioremap() and friends */
 #define VM_ALLOC	0x00000002	/* vmalloc() */

include/xen/interface/memory.h

···
 #ifndef __XEN_PUBLIC_MEMORY_H__
 #define __XEN_PUBLIC_MEMORY_H__
 
+#include <linux/spinlock.h>
+
 /*
  * Increase or decrease the specified domain's memory reservation. Returns a
  * -ve errcode on failure, or the # extents successfully allocated or freed.
···
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation);
 
+/*
+ * An atomic exchange of memory pages. If return code is zero then
+ * @out.extent_list provides GMFNs of the newly-allocated memory.
+ * Returns zero on complete success, otherwise a negative error code.
+ * On complete success then always @nr_exchanged == @in.nr_extents.
+ * On partial success @nr_exchanged indicates how much work was done.
+ */
+#define XENMEM_exchange             11
+struct xen_memory_exchange {
+    /*
+     * [IN] Details of memory extents to be exchanged (GMFN bases).
+     * Note that @in.address_bits is ignored and unused.
+     */
+    struct xen_memory_reservation in;
+
+    /*
+     * [IN/OUT] Details of new memory extents.
+     * We require that:
+     *  1. @in.domid == @out.domid
+     *  2. @in.nr_extents  << @in.extent_order ==
+     *     @out.nr_extents << @out.extent_order
+     *  3. @in.extent_start and @out.extent_start lists must not overlap
+     *  4. @out.extent_start lists GPFN bases to be populated
+     *  5. @out.extent_start is overwritten with allocated GMFN bases
+     */
+    struct xen_memory_reservation out;
+
+    /*
+     * [OUT] Number of input extents that were successfully exchanged:
+     *  1. The first @nr_exchanged input extents were successfully
+     *     deallocated.
+     *  2. The corresponding first entries in the output extent list correctly
+     *     indicate the GMFNs that were successfully exchanged.
+     *  3. All other input and output extents are untouched.
+     *  4. If not all input exents are exchanged then the return code of this
+     *     command will be non-zero.
+     *  5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER!
+     */
+    unsigned long nr_exchanged;
+};
+
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_exchange);
 /*
  * Returns the maximum machine frame number of mapped RAM in this system.
  * This command always succeeds (it never returns an error code).
···
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list);
 
+
+/*
+ * Prevent the balloon driver from changing the memory reservation
+ * during a driver critical region.
+ */
+extern spinlock_t xen_reservation_lock;
 #endif /* __XEN_PUBLIC_MEMORY_H__ */

include/xen/swiotlb-xen.h

···
+#ifndef __LINUX_SWIOTLB_XEN_H
+#define __LINUX_SWIOTLB_XEN_H
+
+#include <linux/swiotlb.h>
+
+extern void xen_swiotlb_init(int verbose);
+
+extern void
+*xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t flags);
+
+extern void
+xen_swiotlb_free_coherent(struct device *hwdev, size_t size,
+			  void *vaddr, dma_addr_t dma_handle);
+
+extern dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+				       unsigned long offset, size_t size,
+				       enum dma_data_direction dir,
+				       struct dma_attrs *attrs);
+
+extern void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir,
+				   struct dma_attrs *attrs);
+/*
+extern int
+xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+		   enum dma_data_direction dir);
+
+extern void
+xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+		     enum dma_data_direction dir);
+*/
+extern int
+xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			 int nelems, enum dma_data_direction dir,
+			 struct dma_attrs *attrs);
+
+extern void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs);
+
+extern void
+xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				size_t size, enum dma_data_direction dir);
+
+extern void
+xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction dir);
+
+extern void
+xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir);
+
+extern void
+xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			       int nelems, enum dma_data_direction dir);
+
+extern int
+xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
+
+extern int
+xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
+
+#endif /* __LINUX_SWIOTLB_XEN_H */

include/xen/xen-ops.h

···
 
 int xen_setup_shutdown_event(void);
 
+extern unsigned long *xen_contiguous_bitmap;
+int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+				unsigned int address_bits);
+
+void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
+
 #endif /* INCLUDE_XEN_OPS_H */

mm/vmalloc.c

···
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
+bool vmap_lazy_unmap __read_mostly = true;
 
 /*** Page table manipulation functions ***/
 
···
 static unsigned long lazy_max_pages(void)
 {
 	unsigned int log;
+
+	if (!vmap_lazy_unmap)
+		return 0;
 
 	log = fls(num_online_cpus());