Merge tag 'stable/for-linus-3.7-x86-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull Xen update from Konrad Rzeszutek Wilk:
 "Features:
   - When hotplugging PCI devices in a PV guest we can allocate
     Xen-SWIOTLB later.
   - Cleanup Xen SWIOTLB.
   - Support pages out grants from HVM domains in the backends.
   - Support wild cards in xen-pciback.hide=(BDF) arguments.
   - Update grant status updates with upstream hypervisor.
   - Boot PV guests with more than 128GB.
   - Cleanup Xen MMU code/add comments.
   - Obtain XENVERS using a preferred method.
   - Lay out generic changes to support Xen ARM.
   - Allow privcmd ioctl for HVM (used to do only PV).
   - Do v2 of mmap_batch for privcmd ioctls.
   - If hypervisor saves the LED keyboard light - we will now instruct
     the kernel about its state.
  Fixes:
   - More fixes to Xen PCI backend for various calls/FLR/etc.
   - With more than 4GB in a 64-bit PV guest disable native SWIOTLB.
   - Fix up smatch warnings.
   - Fix up various return values in privmcmd and mm."

* tag 'stable/for-linus-3.7-x86-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: (48 commits)
  xen/pciback: Restore the PCI config space after an FLR.
  xen-pciback: properly clean up after calling pcistub_device_find()
  xen/vga: add the xen EFI video mode support
  xen/x86: retrieve keyboard shift status flags from hypervisor.
  xen/gndev: Xen backend support for paged out grant targets V4.
  xen-pciback: support wild cards in slot specifications
  xen/swiotlb: Fix compile warnings when using plain integer instead of NULL pointer.
  xen/swiotlb: Remove functions not needed anymore.
  xen/pcifront: Use Xen-SWIOTLB when initting if required.
  xen/swiotlb: For early initialization, return zero on success.
  xen/swiotlb: Use the swiotlb_late_init_with_tbl to init Xen-SWIOTLB late when PV PCI is used.
  xen/swiotlb: Move the error strings to its own function.
  xen/swiotlb: Move the nr_tbl determination in its own function.
  xen/arm: compile and run xenbus
  xen: resynchronise grant table status codes with upstream
  xen/privcmd: return -EFAULT on error
  xen/privcmd: Fix mmap batch ioctl error status copy back.
  xen/privcmd: add PRIVCMD_MMAPBATCH_V2 ioctl
  xen/mm: return more precise error from xen_remap_domain_range()
  xen/mmu: If the revector fails, don't attempt to revector anything else.
  ...

10 files changed, 378 insertions, 59 deletions

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index ec57bd3818a4..7005ced5d1ad 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -6,8 +6,9 @@
 
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
+#include "xen-ops.h"
 
-unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
+static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 {
 	struct physdev_apic apic_op;
 	int ret;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1fbe75a95f15..2d932c351f91 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -80,6 +80,8 @@
 #include "smp.h"
 #include "multicalls.h"
 
+#include <xen/events.h>
+
 EXPORT_SYMBOL_GPL(hypercall_page);
 
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
@@ -1288,7 +1290,6 @@ asmlinkage void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	int rc;
-	pgd_t *pgd;
 
 	if (!xen_start_info)
 		return;
@@ -1380,8 +1381,6 @@ asmlinkage void __init xen_start_kernel(void)
 	acpi_numa = -1;
 #endif
 
-	pgd = (pgd_t *)xen_start_info->pt_base;
-
 	/* 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];
@@ -1390,7 +1389,7 @@ asmlinkage void __init xen_start_kernel(void)
 	early_boot_irqs_disabled = true;
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
-	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
 
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
@@ -1441,11 +1440,19 @@ asmlinkage void __init xen_start_kernel(void)
 		const struct dom0_vga_console_info *info =
 			(void *)((char *)xen_start_info +
 				 xen_start_info->console.dom0.info_off);
+		struct xen_platform_op op = {
+			.cmd = XENPF_firmware_info,
+			.interface_version = XENPF_INTERFACE_VERSION,
+			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
+		};
 
 		xen_init_vga(info, xen_start_info->console.dom0.info_size);
 		xen_start_info->console.domU.mfn = 0;
 		xen_start_info->console.domU.evtchn = 0;
 
+		if (HYPERVISOR_dom0_op(&op) == 0)
+			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
+
 		xen_init_apic();
 
 		/* Make sure ACS will be enabled */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 7a769b7526cb..5a16824cc2b3 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -84,6 +84,7 @@
  */
 DEFINE_SPINLOCK(xen_reservation_lock);
 
+#ifdef CONFIG_X86_32
 /*
  * Identity map, in addition to plain kernel map.  This needs to be
  * large enough to allocate page table pages to allocate the rest.
@@ -91,7 +92,7 @@ DEFINE_SPINLOCK(xen_reservation_lock);
  */
 #define LEVEL1_IDENT_ENTRIES	(PTRS_PER_PTE * 4)
 static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-
+#endif
 #ifdef CONFIG_X86_64
 /* l3 pud for userspace vsyscall mapping */
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
@@ -1176,13 +1177,6 @@ static void xen_exit_mmap(struct mm_struct *mm)
 
 static void xen_post_allocator_init(void);
 
-static void __init xen_pagetable_init(void)
-{
-	paging_init();
-	xen_setup_shared_info();
-	xen_post_allocator_init();
-}
-
 static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
 {
 	/* reserve the range used */
@@ -1197,6 +1191,87 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
 	}
 }
 
+#ifdef CONFIG_X86_64
+static void __init xen_cleanhighmap(unsigned long vaddr,
+				    unsigned long vaddr_end)
+{
+	unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+	pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
+
+	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
+	 * We include the PMD passed in on _both_ boundaries. */
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+			pmd++, vaddr += PMD_SIZE) {
+		if (pmd_none(*pmd))
+			continue;
+		if (vaddr < (unsigned long) _text || vaddr > kernel_end)
+			set_pmd(pmd, __pmd(0));
+	}
+	/* In case we did something silly, we should crash in this function
+	 * instead of somewhere later and be confusing. */
+	xen_mc_flush();
+}
+#endif
+static void __init xen_pagetable_init(void)
+{
+#ifdef CONFIG_X86_64
+	unsigned long size;
+	unsigned long addr;
+#endif
+	paging_init();
+	xen_setup_shared_info();
+#ifdef CONFIG_X86_64
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		unsigned long new_mfn_list;
+
+		size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+		/* On 32-bit, we get zero so this never gets executed. */
+		new_mfn_list = xen_revector_p2m_tree();
+		if (new_mfn_list && new_mfn_list != xen_start_info->mfn_list) {
+			/* using __ka address and sticking INVALID_P2M_ENTRY! */
+			memset((void *)xen_start_info->mfn_list, 0xff, size);
+
+			/* We should be in __ka space. */
+			BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
+			addr = xen_start_info->mfn_list;
+			/* We roundup to the PMD, which means that if anybody at this stage is
+			 * using the __ka address of xen_start_info or xen_start_info->shared_info
+			 * they are in going to crash. Fortunatly we have already revectored
+			 * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+			size = roundup(size, PMD_SIZE);
+			xen_cleanhighmap(addr, addr + size);
+
+			size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+			memblock_free(__pa(xen_start_info->mfn_list), size);
+			/* And revector! Bye bye old array */
+			xen_start_info->mfn_list = new_mfn_list;
+		} else
+			goto skip;
+	}
+	/* At this stage, cleanup_highmap has already cleaned __ka space
+	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
+	 * the ramdisk). We continue on, erasing PMD entries that point to page
+	 * tables - do note that they are accessible at this stage via __va.
+	 * For good measure we also round up to the PMD - which means that if
+	 * anybody is using __ka address to the initial boot-stack - and try
+	 * to use it - they are going to crash. The xen_start_info has been
+	 * taken care of already in xen_setup_kernel_pagetable. */
+	addr = xen_start_info->pt_base;
+	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+
+	xen_cleanhighmap(addr, addr + size);
+	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
+#ifdef DEBUG
+	/* This is superflous and is not neccessary, but you know what
+	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
+	 * anything at this stage. */
+	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
+#endif
+skip:
+#endif
+	xen_post_allocator_init();
+}
 static void xen_write_cr2(unsigned long cr2)
 {
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
@@ -1652,7 +1727,7 @@ static void set_page_prot(void *addr, pgprot_t prot)
 	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
 		BUG();
 }
-
+#ifdef CONFIG_X86_32
 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
 	unsigned pmdidx, pteidx;
@@ -1703,7 +1778,7 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 
 	set_page_prot(pmd, PAGE_KERNEL_RO);
 }
-
+#endif
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
@@ -1731,7 +1806,20 @@ static void convert_pfn_mfn(void *v)
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		pte[i] = xen_make_pte(pte[i].pte);
 }
-
+static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
+				 unsigned long addr)
+{
+	if (*pt_base == PFN_DOWN(__pa(addr))) {
+		set_page_prot((void *)addr, PAGE_KERNEL);
+		clear_page((void *)addr);
+		(*pt_base)++;
+	}
+	if (*pt_end == PFN_DOWN(__pa(addr))) {
+		set_page_prot((void *)addr, PAGE_KERNEL);
+		clear_page((void *)addr);
+		(*pt_end)--;
+	}
+}
 /*
  * Set up the initial kernel pagetable.
  *
@@ -1743,11 +1831,13 @@ static void convert_pfn_mfn(void *v)
  * of the physical mapping once some sort of allocator has been set
  * up.
  */
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
-					 unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
 	pud_t *l3;
 	pmd_t *l2;
+	unsigned long addr[3];
+	unsigned long pt_base, pt_end;
+	unsigned i;
 
 	/* max_pfn_mapped is the last pfn mapped in the initial memory
 	 * mappings. Considering that on Xen after the kernel mappings we
@@ -1755,32 +1845,53 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	 * set max_pfn_mapped to the last real pfn mapped. */
 	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
 
+	pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
+	pt_end = pt_base + xen_start_info->nr_pt_frames;
+
 	/* Zap identity mapping */
 	init_level4_pgt[0] = __pgd(0);
 
 	/* Pre-constructed entries are in pfn, so convert to mfn */
+	/* L4[272] -> level3_ident_pgt
+	 * L4[511] -> level3_kernel_pgt */
 	convert_pfn_mfn(init_level4_pgt);
+
+	/* L3_i[0] -> level2_ident_pgt */
 	convert_pfn_mfn(level3_ident_pgt);
+	/* L3_k[510] -> level2_kernel_pgt
+	 * L3_i[511] -> level2_fixmap_pgt */
 	convert_pfn_mfn(level3_kernel_pgt);
 
+	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
 	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
 
-	memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-	memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
+	addr[0] = (unsigned long)pgd;
+	addr[1] = (unsigned long)l3;
+	addr[2] = (unsigned long)l2;
+	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
+	 * Both L4[272][0] and L4[511][511] have entries that point to the same
+	 * L2 (PMD) tables. Meaning that if you modify it in __va space
+	 * it will be also modified in the __ka space! (But if you just
+	 * modify the PMD table to point to other PTE's or none, then you
+	 * are OK - which is what cleanup_highmap does) */
+	copy_page(level2_ident_pgt, l2);
+	/* Graft it onto L4[511][511] */
+	copy_page(level2_kernel_pgt, l2);
+
+	/* Get [511][510] and graft that in level2_fixmap_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
 	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
-	memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
-	/* Set up identity map */
-	xen_map_identity_early(level2_ident_pgt, max_pfn);
+	copy_page(level2_fixmap_pgt, l2);
+	/* Note that we don't do anything with level1_fixmap_pgt which
+	 * we don't need. */
 
 	/* Make pagetable pieces RO */
 	set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+	set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
 
@@ -1791,22 +1902,28 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	/* Unpin Xen-provided one */
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-	/* Switch over */
-	pgd = init_level4_pgt;
-
 	/*
 	 * At this stage there can be no user pgd, and no page
 	 * structure to attach it to, so make sure we just set kernel
 	 * pgd.
 	 */
 	xen_mc_batch();
-	__xen_write_cr3(true, __pa(pgd));
+	__xen_write_cr3(true, __pa(init_level4_pgt));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	memblock_reserve(__pa(xen_start_info->pt_base),
-			 xen_start_info->nr_pt_frames * PAGE_SIZE);
+	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
+	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
+	 * the initial domain. For guests using the toolstack, they are in:
+	 * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
+	 * rip out the [L4] (pgd), but for guests we shave off three pages.
+	 */
+	for (i = 0; i < ARRAY_SIZE(addr); i++)
+		check_pt_base(&pt_base, &pt_end, addr[i]);
 
-	return pgd;
+	/* Our (by three pages) smaller Xen pagetable that we are using */
+	memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+	/* Revector the xen_start_info */
+	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
 }
 #else	/* !CONFIG_X86_64 */
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
@@ -1831,8 +1948,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	 */
 	swapper_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-	memcpy(swapper_kernel_pmd, initial_kernel_pmd,
-	       sizeof(pmd_t) * PTRS_PER_PMD);
+	copy_page(swapper_kernel_pmd, initial_kernel_pmd);
 	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
 		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
 	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
@@ -1849,8 +1965,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
-					 unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
@@ -1862,11 +1977,11 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+	copy_page(initial_kernel_pmd, kernel_pmd);
 
 	xen_map_identity_early(initial_kernel_pmd, max_pfn);
 
-	memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+	copy_page(initial_page_table, pgd);
 	initial_page_table[KERNEL_PGD_BOUNDARY] =
 		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
 
@@ -1882,8 +1997,6 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	memblock_reserve(__pa(xen_start_info->pt_base),
 			 xen_start_info->nr_pt_frames * PAGE_SIZE);
-
-	return initial_page_table;
 }
 #endif	/* CONFIG_X86_64 */
 
@@ -2333,6 +2446,9 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	unsigned long range;
 	int err = 0;
 
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -EINVAL;
+
 	prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
 
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
@@ -2351,8 +2467,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 		if (err)
 			goto out;
 
-		err = -EFAULT;
-		if (HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid) < 0)
+		err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid);
+		if (err < 0)
 			goto out;
 
 		nr -= batch;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 72213da605f5..95fb2aa5927e 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -22,7 +22,7 @@
  *
  * P2M_PER_PAGE depends on the architecture, as a mfn is always
  * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
- * 512 and 1024 entries respectively. 
+ * 512 and 1024 entries respectively.
  *
  * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
  *
@@ -139,11 +139,11 @@
  *      /    | ~0, ~0, ....  |
  *     |     \---------------/
  *     |
- *     p2m_missing             p2m_missing
- * /------------------\     /------------\
- * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
- * | [p2m_mid_missing]+---->| ..., ~0    |
- * \------------------/     \------------/
+ *   p2m_mid_missing           p2m_missing
+ * /-----------------\     /------------\
+ * | [p2m_missing]   +---->| ~0, ~0, ~0 |
+ * | [p2m_missing]   +---->| ..., ~0    |
+ * \-----------------/     \------------/
  *
  * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
  */
@@ -396,7 +396,85 @@ void __init xen_build_dynamic_phys_to_machine(void)
 
 	m2p_override_init();
 }
+#ifdef CONFIG_X86_64
+#include <linux/bootmem.h>
+unsigned long __init xen_revector_p2m_tree(void)
+{
+	unsigned long va_start;
+	unsigned long va_end;
+	unsigned long pfn;
+	unsigned long pfn_free = 0;
+	unsigned long *mfn_list = NULL;
+	unsigned long size;
+
+	va_start = xen_start_info->mfn_list;
+	/*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
+	 * so make sure it is rounded up to that */
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+	va_end = va_start + size;
+
+	/* If we were revectored already, don't do it again. */
+	if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
+		return 0;
+
+	mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
+	if (!mfn_list) {
+		pr_warn("Could not allocate space for a new P2M tree!\n");
+		return xen_start_info->mfn_list;
+	}
+	/* Fill it out with INVALID_P2M_ENTRY value */
+	memset(mfn_list, 0xFF, size);
+
+	for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
+		unsigned topidx = p2m_top_index(pfn);
+		unsigned mididx;
+		unsigned long *mid_p;
+
+		if (!p2m_top[topidx])
+			continue;
+
+		if (p2m_top[topidx] == p2m_mid_missing)
+			continue;
+
+		mididx = p2m_mid_index(pfn);
+		mid_p = p2m_top[topidx][mididx];
+		if (!mid_p)
+			continue;
+		if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
+			continue;
+
+		if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
+			continue;
+
+		/* The old va. Rebase it on mfn_list */
+		if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
+			unsigned long *new;
+
+			if (pfn_free  > (size / sizeof(unsigned long))) {
+				WARN(1, "Only allocated for %ld pages, but we want %ld!\n",
+				     size / sizeof(unsigned long), pfn_free);
+				return 0;
+			}
+			new = &mfn_list[pfn_free];
+
+			copy_page(new, mid_p);
+			p2m_top[topidx][mididx] = &mfn_list[pfn_free];
+			p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]);
+
+			pfn_free += P2M_PER_PAGE;
 
+		}
+		/* This should be the leafs allocated for identity from _brk. */
+	}
+	return (unsigned long)mfn_list;
+
+}
+#else
+unsigned long __init xen_revector_p2m_tree(void)
+{
+	return 0;
+}
+#endif
 unsigned long get_phys_to_machine(unsigned long pfn)
 {
 	unsigned topidx, mididx, idx;
@@ -430,7 +508,7 @@ static void free_p2m_page(void *p)
 	free_page((unsigned long)p);
 }
 
-/* 
+/*
  * Fully allocate the p2m structure for a given pfn.  We need to check
  * that both the top and mid levels are allocated, and make sure the
  * parallel mfn tree is kept in sync.  We may race with other cpus, so
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 967633ad98c4..969570491c39 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -8,6 +8,14 @@
 #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>
+
 int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
@@ -34,34 +42,64 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 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) &&
-	    (xen_pv_domain()))
+	if ((xen_initial_domain() || swiotlb || 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. */
-	if (xen_pv_domain())
-		swiotlb = 0;
+	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;
 }
 
 void __init pci_xen_swiotlb_init(void)
 {
 	if (xen_swiotlb) {
-		xen_swiotlb_init(1);
+		xen_swiotlb_init(1, true /* early */);
 		dma_ops = &xen_swiotlb_dma_ops;
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
 }
+
+int pci_xen_swiotlb_init_late(void)
+{
+	int rc;
+
+	if (xen_swiotlb)
+		return 0;
+
+	rc = xen_swiotlb_init(1, false /* late */);
+	if (rc)
+		return rc;
+
+	dma_ops = &xen_swiotlb_dma_ops;
+	/* Make sure ACS will be enabled */
+	pci_request_acs();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+
 IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
-		  0,
+		  NULL,
 		  pci_xen_swiotlb_init,
-		  0);
+		  NULL);
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index ffcf2615640b..0a7852483ffe 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 
 #include <xen/platform_pci.h>
+#include "xen-ops.h"
 
 #define XEN_PLATFORM_ERR_MAGIC -1
 #define XEN_PLATFORM_ERR_PROTOCOL -2
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index e2d62d697b5d..8971a26d21ab 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -432,6 +432,24 @@ char * __init xen_memory_setup(void)
 	 *  - mfn_list
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
+	 * We tried to make the the memblock_reserve more selective so
+	 * that it would be clear what region is reserved. Sadly we ran
+	 * in the problem wherein on a 64-bit hypervisor with a 32-bit
+	 * initial domain, the pt_base has the cr3 value which is not
+	 * neccessarily where the pagetable starts! As Jan put it: "
+	 * Actually, the adjustment turns out to be correct: The page
+	 * tables for a 32-on-64 dom0 get allocated in the order "first L1",
+	 * "first L2", "first L3", so the offset to the page table base is
+	 * indeed 2. When reading xen/include/public/xen.h's comment
+	 * very strictly, this is not a violation (since there nothing is said
+	 * that the first thing in the page table space is pointed to by
+	 * pt_base; I admit that this seems to be implied though, namely
+	 * do I think that it is implied that the page table space is the
+	 * range [pt_base, pt_base + nt_pt_frames), whereas that
+	 * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
+	 * which - without a priori knowledge - the kernel would have
+	 * difficulty to figure out)." - so lets just fall back to the
+	 * easy way and reserve the whole region.
 	 */
 	memblock_reserve(__pa(xen_start_info->mfn_list),
 			 xen_start_info->pt_base - xen_start_info->mfn_list);
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index 1cd7f4d11e29..6722e3733f02 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -35,6 +35,7 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
 			info->u.text_mode_3.font_height;
 		break;
 
+	case XEN_VGATYPE_EFI_LFB:
 	case XEN_VGATYPE_VESA_LFB:
 		if (size < offsetof(struct dom0_vga_console_info,
 				    u.vesa_lfb.gbl_caps))
@@ -54,6 +55,12 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
 		screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
 		screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
 		screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+
+		if (info->video_type == XEN_VGATYPE_EFI_LFB) {
+			screen_info->orig_video_isVGA = VIDEO_TYPE_EFI;
+			break;
+		}
+
 		if (size >= offsetof(struct dom0_vga_console_info,
 				     u.vesa_lfb.gbl_caps)
 		    + sizeof(info->u.vesa_lfb.gbl_caps))
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index aaa7291c9259..7faed5869e5b 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -28,9 +28,61 @@ ENTRY(startup_xen)
 	__FINIT
 
 .pushsection .text
-	.align PAGE_SIZE
+	.balign PAGE_SIZE
 ENTRY(hypercall_page)
-	.skip PAGE_SIZE
+#define NEXT_HYPERCALL(x) \
+	ENTRY(xen_hypercall_##x) \
+	.skip 32
+
+NEXT_HYPERCALL(set_trap_table)
+NEXT_HYPERCALL(mmu_update)
+NEXT_HYPERCALL(set_gdt)
+NEXT_HYPERCALL(stack_switch)
+NEXT_HYPERCALL(set_callbacks)
+NEXT_HYPERCALL(fpu_taskswitch)
+NEXT_HYPERCALL(sched_op_compat)
+NEXT_HYPERCALL(platform_op)
+NEXT_HYPERCALL(set_debugreg)
+NEXT_HYPERCALL(get_debugreg)
+NEXT_HYPERCALL(update_descriptor)
+NEXT_HYPERCALL(ni)
+NEXT_HYPERCALL(memory_op)
+NEXT_HYPERCALL(multicall)
+NEXT_HYPERCALL(update_va_mapping)
+NEXT_HYPERCALL(set_timer_op)
+NEXT_HYPERCALL(event_channel_op_compat)
+NEXT_HYPERCALL(xen_version)
+NEXT_HYPERCALL(console_io)
+NEXT_HYPERCALL(physdev_op_compat)
+NEXT_HYPERCALL(grant_table_op)
+NEXT_HYPERCALL(vm_assist)
+NEXT_HYPERCALL(update_va_mapping_otherdomain)
+NEXT_HYPERCALL(iret)
+NEXT_HYPERCALL(vcpu_op)
+NEXT_HYPERCALL(set_segment_base)
+NEXT_HYPERCALL(mmuext_op)
+NEXT_HYPERCALL(xsm_op)
+NEXT_HYPERCALL(nmi_op)
+NEXT_HYPERCALL(sched_op)
+NEXT_HYPERCALL(callback_op)
+NEXT_HYPERCALL(xenoprof_op)
+NEXT_HYPERCALL(event_channel_op)
+NEXT_HYPERCALL(physdev_op)
+NEXT_HYPERCALL(hvm_op)
+NEXT_HYPERCALL(sysctl)
+NEXT_HYPERCALL(domctl)
+NEXT_HYPERCALL(kexec_op)
+NEXT_HYPERCALL(tmem_op) /* 38 */
+ENTRY(xen_hypercall_rsvr)
+	.skip 320
+NEXT_HYPERCALL(mca) /* 48 */
+NEXT_HYPERCALL(arch_1)
+NEXT_HYPERCALL(arch_2)
+NEXT_HYPERCALL(arch_3)
+NEXT_HYPERCALL(arch_4)
+NEXT_HYPERCALL(arch_5)
+NEXT_HYPERCALL(arch_6)
+	.balign PAGE_SIZE
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 202d4c150154..bb5a8105ea86 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -27,7 +27,7 @@ void xen_setup_mfn_list_list(void);
 void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
-pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
+void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_reserve_top(void);
 extern unsigned long xen_max_p2m_pfn;
 
@@ -45,6 +45,7 @@ void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
+unsigned long __init xen_revector_p2m_tree(void);
 
 void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);