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

7 files changed, 372 insertions, 13 deletions

diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 018a0a40079..bf5f7d32bd0 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -112,13 +112,9 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine)
  */
 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;
 }
 
diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
new file mode 100644
index 00000000000..1be1ab7d6a4
--- /dev/null
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -0,0 +1,14 @@
+#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 */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 4b7e3d8b01d..9f07cfcbd3a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -13,6 +13,7 @@
 #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;
 
@@ -132,7 +133,7 @@ void __init pci_iommu_alloc(void)
 	/* 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();
@@ -144,6 +145,8 @@ void __init pci_iommu_alloc(void)
 	/* needs to be called after gart_iommu_hole_init */
 	amd_iommu_detect();
 out:
+	pci_xen_swiotlb_init();
+
 	pci_swiotlb_init();
 }
 
@@ -296,7 +299,7 @@ static int __init pci_iommu_init(void)
 #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();
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 93095468598..77938515891 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
+obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d4ff5e83621..7d46c844141 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1172,6 +1172,10 @@ asmlinkage void __init xen_start_kernel(void)
 
 	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];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 413b19b3d0f..42086ac406a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,6 +42,7 @@
 #include <linux/highmem.h>
 #include <linux/debugfs.h>
 #include <linux/bug.h>
+#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
 
@@ -51,15 +52,19 @@
 #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"
@@ -68,6 +73,13 @@
 
 #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
 
 static struct {
@@ -378,6 +390,28 @@ static bool xen_page_pinned(void *ptr)
 	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;
@@ -454,6 +488,11 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 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);
@@ -524,8 +563,25 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 	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);
@@ -538,7 +594,22 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_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);
@@ -594,6 +665,11 @@ void xen_set_pud(pud_t *ptr, pud_t val)
 
 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);
@@ -610,6 +686,11 @@ void xen_set_pte(pte_t *ptep, pte_t pte)
 #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));
 }
 
@@ -936,8 +1017,6 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    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)) {
@@ -1501,7 +1580,6 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l
 	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)
@@ -1812,9 +1890,16 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 		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;
 	}
 
 	__native_set_fixmap(idx, pte);
@@ -1940,7 +2025,205 @@ void __init xen_init_mmu_ops(void)
 	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)
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
new file mode 100644
index 00000000000..a013ec9d0c5
--- /dev/null
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -0,0 +1,58 @@
+/* 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;
+	}
+}