5 files changed, 140 insertions, 93 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f17b29210ac..ffb101e4573 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1537,7 +1537,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	if (!xen_pvh_domain())
 		pv_cpu_ops = xen_cpu_ops;
 
-	x86_init.resources.memory_setup = xen_memory_setup;
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
+	else
+		x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index c9858358858..ebfa9b2c871 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -36,99 +36,133 @@
 
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <xen/xen.h>
 
 #include <asm/pgtable.h>
 
-static int map_pte_fn(pte_t *pte, struct page *pmd_page,
-		      unsigned long addr, void *data)
+static struct gnttab_vm_area {
+	struct vm_struct *area;
+	pte_t **ptes;
+} gnttab_shared_vm_area, gnttab_status_vm_area;
+
+int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   void **__shared)
 {
-	unsigned long **frames = (unsigned long **)data;
+	void *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
-	return 0;
-}
+	if (shared == NULL)
+		*__shared = shared = gnttab_shared_vm_area.area->addr;
 
-/*
- * This function is used to map shared frames to store grant status. It is
- * different from map_pte_fn above, the frames type here is uint64_t.
- */
-static int map_pte_fn_status(pte_t *pte, struct page *pmd_page,
-			     unsigned long addr, void *data)
-{
-	uint64_t **frames = (uint64_t **)data;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
 	return 0;
 }
 
-static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
-			unsigned long addr, void *data)
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
 {
+	grant_status_t *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
+
+	if (shared == NULL)
+		*__shared = shared = gnttab_status_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, __pte(0));
 	return 0;
 }
 
-int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   void **__shared)
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
-	int rc;
-	void *shared = *__shared;
+	pte_t **ptes;
+	unsigned long addr;
+	unsigned long i;
 
-	if (shared == NULL) {
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
-	}
+	if (shared == gnttab_status_vm_area.area->addr)
+		ptes = gnttab_status_vm_area.ptes;
+	else
+		ptes = gnttab_shared_vm_area.ptes;
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn, &frames);
-	return rc;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, ptes[i], __pte(0));
+		addr += PAGE_SIZE;
+	}
 }
 
-int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   grant_status_t **__shared)
+static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 {
-	int rc;
-	grant_status_t *shared = *__shared;
+	area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL);
+	if (area->ptes == NULL)
+		return -ENOMEM;
 
-	if (shared == NULL) {
-		/* No need to pass in PTE as we are going to do it
-		 * in apply_to_page_range anyhow. */
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
+	area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes);
+	if (area->area == NULL) {
+		kfree(area->ptes);
+		return -ENOMEM;
 	}
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn_status, &frames);
-	return rc;
+	return 0;
 }
 
-void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
+static void arch_gnttab_vfree(struct gnttab_vm_area *area)
+{
+	free_vm_area(area->area);
+	kfree(area->ptes);
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
 {
-	apply_to_page_range(&init_mm, (unsigned long)shared,
-			    PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
+	int ret;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Always allocate the space for the status frames in case
+	 * we're migrated to a host with V2 support.
+	 */
+	ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+  err:
+	arch_gnttab_vfree(&gnttab_shared_vm_area);
+	return -ENOMEM;
 }
+
 #ifdef CONFIG_XEN_PVH
 #include <xen/balloon.h>
 #include <xen/events.h>
-#include <xen/xen.h>
 #include <linux/slab.h>
 static int __init xlated_setup_gnttab_pages(void)
 {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6f6e15d2846..e8a1201c329 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1494,7 +1494,7 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		page->private = (unsigned long)user_pgd;
 
 		if (user_pgd != NULL) {
-			user_pgd[pgd_index(VSYSCALL_START)] =
+			user_pgd[pgd_index(VSYSCALL_ADDR)] =
 				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
 			ret = 0;
 		}
@@ -2062,8 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
 # endif
 #else
-	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
-	case VVAR_PAGE:
+	case VSYSCALL_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
@@ -2104,8 +2103,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
-	    idx == VVAR_PAGE) {
+	if (idx == VSYSCALL_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 210426a26cc..2e555163c2f 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -27,7 +27,6 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
-#include "mmu.h"
 #include "xen-ops.h"
 #include "vdso.h"
 
@@ -82,9 +81,6 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 
 	memblock_reserve(start, size);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
 	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
@@ -107,7 +103,6 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 		.domid        = DOMID_SELF
 	};
 	unsigned long len = 0;
-	int xlated_phys = xen_feature(XENFEAT_auto_translated_physmap);
 	unsigned long pfn;
 	int ret;
 
@@ -121,7 +116,7 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 				continue;
 			frame = mfn;
 		} else {
-			if (!xlated_phys && mfn != INVALID_P2M_ENTRY)
+			if (mfn != INVALID_P2M_ENTRY)
 				continue;
 			frame = pfn;
 		}
@@ -159,13 +154,6 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 static unsigned long __init xen_release_chunk(unsigned long start,
 					      unsigned long end)
 {
-	/*
-	 * Xen already ballooned out the E820 non RAM regions for us
-	 * and set them up properly in EPT.
-	 */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return end - start;
-
 	return xen_do_chunk(start, end, true);
 }
 
@@ -234,13 +222,7 @@ static void __init xen_set_identity_and_release_chunk(
 	 * (except for the ISA region which must be 1:1 mapped) to
 	 * release the refcounts (in Xen) on the original frames.
 	 */
-
-	/*
-	 * PVH E820 matches the hypervisor's P2M which means we need to
-	 * account for the proper values of *release and *identity.
-	 */
-	for (pfn = start_pfn; !xen_feature(XENFEAT_auto_translated_physmap) &&
-	     pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
 		pte_t pte = __pte_ma(0);
 
 		if (pfn < PFN_UP(ISA_END_ADDRESS))
@@ -518,6 +500,35 @@ char * __init xen_memory_setup(void)
 }
 
 /*
+ * Machine specific memory setup for auto-translated guests.
+ */
+char * __init xen_auto_xlated_memory_setup(void)
+{
+	static struct e820entry map[E820MAX] __initdata;
+
+	struct xen_memory_map memmap;
+	int i;
+	int rc;
+
+	memmap.nr_entries = E820MAX;
+	set_xen_guest_handle(memmap.buffer, map);
+
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc < 0)
+		panic("No memory map (%d)\n", rc);
+
+	sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries);
+
+	for (i = 0; i < memmap.nr_entries; i++)
+		e820_add_region(map[i].addr, map[i].size, map[i].type);
+
+	memblock_reserve(__pa(xen_start_info->mfn_list),
+			 xen_start_info->pt_base - xen_start_info->mfn_list);
+
+	return "Xen";
+}
+
+/*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
  * can have un-truncated segments, so wrapping around is allowed.
@@ -525,10 +536,17 @@ char * __init xen_memory_setup(void)
 static void __init fiddle_vdso(void)
 {
 #ifdef CONFIG_X86_32
+	/*
+	 * This could be called before selected_vdso32 is initialized, so
+	 * just fiddle with both possible images.  vdso_image_32_syscall
+	 * can't be selected, since it only exists on 64-bit systems.
+	 */
 	u32 *mask;
-	mask = VDSO32_SYMBOL(&vdso32_int80_start, NOTE_MASK);
+	mask = vdso_image_32_int80.data +
+		vdso_image_32_int80.sym_VDSO32_NOTE_MASK;
 	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
-	mask = VDSO32_SYMBOL(&vdso32_sysenter_start, NOTE_MASK);
+	mask = vdso_image_32_sysenter.data +
+		vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK;
 	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
 #endif
 }
@@ -583,13 +601,7 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-void xen_enable_nmi(void)
-{
-#ifdef CONFIG_X86_64
-	if (register_callback(CALLBACKTYPE_nmi, (char *)nmi))
-		BUG();
-#endif
-}
+
 void __init xen_pvmmu_arch_setup(void)
 {
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -604,7 +616,6 @@ void __init xen_pvmmu_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-	xen_enable_nmi();
 }
 
 /* This function is not called for HVM domains */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c834d4b231f..97d87659f77 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -36,6 +36,7 @@ void xen_mm_unpin_all(void);
 void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);
+char * xen_auto_xlated_memory_setup(void);
 void __init xen_arch_setup(void);
 void xen_enable_sysenter(void);
 void xen_enable_syscall(void);