1 files changed, 73 insertions, 381 deletions

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index c237b810b03f..5e92b61ad574 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -173,371 +173,6 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
  */
 #define USER_LIMIT	((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
 
-/*
- * Xen leaves the responsibility for maintaining p2m mappings to the
- * guests themselves, but it must also access and update the p2m array
- * during suspend/resume when all the pages are reallocated.
- *
- * The p2m table is logically a flat array, but we implement it as a
- * three-level tree to allow the address space to be sparse.
- *
- *                               Xen
- *                                |
- *     p2m_top              p2m_top_mfn
- *       /  \                   /   \
- * p2m_mid p2m_mid	p2m_mid_mfn p2m_mid_mfn
- *    / \      / \         /           /
- *  p2m p2m p2m p2m p2m p2m p2m ...
- *
- * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
- *
- * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
- * maximum representable pseudo-physical address space is:
- *  P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
- *
- * 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. 
- */
-
-unsigned long xen_max_p2m_pfn __read_mostly;
-
-#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
-#define P2M_MID_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long *))
-#define P2M_TOP_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long **))
-
-#define MAX_P2M_PFN		(P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
-
-/* Placeholders for holes in the address space */
-static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
-
-static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
-
-RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-
-static inline unsigned p2m_top_index(unsigned long pfn)
-{
-	BUG_ON(pfn >= MAX_P2M_PFN);
-	return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
-}
-
-static inline unsigned p2m_mid_index(unsigned long pfn)
-{
-	return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
-}
-
-static inline unsigned p2m_index(unsigned long pfn)
-{
-	return pfn % P2M_PER_PAGE;
-}
-
-static void p2m_top_init(unsigned long ***top)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-		top[i] = p2m_mid_missing;
-}
-
-static void p2m_top_mfn_init(unsigned long *top)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-		top[i] = virt_to_mfn(p2m_mid_missing_mfn);
-}
-
-static void p2m_top_mfn_p_init(unsigned long **top)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
-		top[i] = p2m_mid_missing_mfn;
-}
-
-static void p2m_mid_init(unsigned long **mid)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_MID_PER_PAGE; i++)
-		mid[i] = p2m_missing;
-}
-
-static void p2m_mid_mfn_init(unsigned long *mid)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_MID_PER_PAGE; i++)
-		mid[i] = virt_to_mfn(p2m_missing);
-}
-
-static void p2m_init(unsigned long *p2m)
-{
-	unsigned i;
-
-	for (i = 0; i < P2M_MID_PER_PAGE; i++)
-		p2m[i] = INVALID_P2M_ENTRY;
-}
-
-/*
- * Build the parallel p2m_top_mfn and p2m_mid_mfn structures
- *
- * This is called both at boot time, and after resuming from suspend:
- * - At boot time we're called very early, and must use extend_brk()
- *   to allocate memory.
- *
- * - After resume we're called from within stop_machine, but the mfn
- *   tree should alreay be completely allocated.
- */
-void xen_build_mfn_list_list(void)
-{
-	unsigned long pfn;
-
-	/* Pre-initialize p2m_top_mfn to be completely missing */
-	if (p2m_top_mfn == NULL) {
-		p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		p2m_mid_mfn_init(p2m_mid_missing_mfn);
-
-		p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		p2m_top_mfn_p_init(p2m_top_mfn_p);
-
-		p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		p2m_top_mfn_init(p2m_top_mfn);
-	} else {
-		/* Reinitialise, mfn's all change after migration */
-		p2m_mid_mfn_init(p2m_mid_missing_mfn);
-	}
-
-	for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
-		unsigned topidx = p2m_top_index(pfn);
-		unsigned mididx = p2m_mid_index(pfn);
-		unsigned long **mid;
-		unsigned long *mid_mfn_p;
-
-		mid = p2m_top[topidx];
-		mid_mfn_p = p2m_top_mfn_p[topidx];
-
-		/* Don't bother allocating any mfn mid levels if
-		 * they're just missing, just update the stored mfn,
-		 * since all could have changed over a migrate.
-		 */
-		if (mid == p2m_mid_missing) {
-			BUG_ON(mididx);
-			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
-			p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
-			pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
-			continue;
-		}
-
-		if (mid_mfn_p == p2m_mid_missing_mfn) {
-			/*
-			 * XXX boot-time only!  We should never find
-			 * missing parts of the mfn tree after
-			 * runtime.  extend_brk() will BUG if we call
-			 * it too late.
-			 */
-			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_mfn_init(mid_mfn_p);
-
-			p2m_top_mfn_p[topidx] = mid_mfn_p;
-		}
-
-		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
-		mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
-	}
-}
-
-void xen_setup_mfn_list_list(void)
-{
-	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
-
-	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
-		virt_to_mfn(p2m_top_mfn);
-	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
-}
-
-/* Set up p2m_top to point to the domain-builder provided p2m pages */
-void __init xen_build_dynamic_phys_to_machine(void)
-{
-	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
-	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
-	unsigned long pfn;
-
-	xen_max_p2m_pfn = max_pfn;
-
-	p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	p2m_init(p2m_missing);
-
-	p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	p2m_mid_init(p2m_mid_missing);
-
-	p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	p2m_top_init(p2m_top);
-
-	/*
-	 * The domain builder gives us a pre-constructed p2m array in
-	 * mfn_list for all the pages initially given to us, so we just
-	 * need to graft that into our tree structure.
-	 */
-	for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
-		unsigned topidx = p2m_top_index(pfn);
-		unsigned mididx = p2m_mid_index(pfn);
-
-		if (p2m_top[topidx] == p2m_mid_missing) {
-			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_init(mid);
-
-			p2m_top[topidx] = mid;
-		}
-
-		p2m_top[topidx][mididx] = &mfn_list[pfn];
-	}
-}
-
-unsigned long get_phys_to_machine(unsigned long pfn)
-{
-	unsigned topidx, mididx, idx;
-
-	if (unlikely(pfn >= MAX_P2M_PFN))
-		return INVALID_P2M_ENTRY;
-
-	topidx = p2m_top_index(pfn);
-	mididx = p2m_mid_index(pfn);
-	idx = p2m_index(pfn);
-
-	return p2m_top[topidx][mididx][idx];
-}
-EXPORT_SYMBOL_GPL(get_phys_to_machine);
-
-static void *alloc_p2m_page(void)
-{
-	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
-}
-
-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
- * the new pages are installed with cmpxchg; if we lose the race then
- * simply free the page we allocated and use the one that's there.
- */
-static bool alloc_p2m(unsigned long pfn)
-{
-	unsigned topidx, mididx;
-	unsigned long ***top_p, **mid;
-	unsigned long *top_mfn_p, *mid_mfn;
-
-	topidx = p2m_top_index(pfn);
-	mididx = p2m_mid_index(pfn);
-
-	top_p = &p2m_top[topidx];
-	mid = *top_p;
-
-	if (mid == p2m_mid_missing) {
-		/* Mid level is missing, allocate a new one */
-		mid = alloc_p2m_page();
-		if (!mid)
-			return false;
-
-		p2m_mid_init(mid);
-
-		if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
-			free_p2m_page(mid);
-	}
-
-	top_mfn_p = &p2m_top_mfn[topidx];
-	mid_mfn = p2m_top_mfn_p[topidx];
-
-	BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
-
-	if (mid_mfn == p2m_mid_missing_mfn) {
-		/* Separately check the mid mfn level */
-		unsigned long missing_mfn;
-		unsigned long mid_mfn_mfn;
-
-		mid_mfn = alloc_p2m_page();
-		if (!mid_mfn)
-			return false;
-
-		p2m_mid_mfn_init(mid_mfn);
-
-		missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
-		mid_mfn_mfn = virt_to_mfn(mid_mfn);
-		if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
-			free_p2m_page(mid_mfn);
-		else
-			p2m_top_mfn_p[topidx] = mid_mfn;
-	}
-
-	if (p2m_top[topidx][mididx] == p2m_missing) {
-		/* p2m leaf page is missing */
-		unsigned long *p2m;
-
-		p2m = alloc_p2m_page();
-		if (!p2m)
-			return false;
-
-		p2m_init(p2m);
-
-		if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
-			free_p2m_page(p2m);
-		else
-			mid_mfn[mididx] = virt_to_mfn(p2m);
-	}
-
-	return true;
-}
-
-/* Try to install p2m mapping; fail if intermediate bits missing */
-bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	unsigned topidx, mididx, idx;
-
-	if (unlikely(pfn >= MAX_P2M_PFN)) {
-		BUG_ON(mfn != INVALID_P2M_ENTRY);
-		return true;
-	}
-
-	topidx = p2m_top_index(pfn);
-	mididx = p2m_mid_index(pfn);
-	idx = p2m_index(pfn);
-
-	if (p2m_top[topidx][mididx] == p2m_missing)
-		return mfn == INVALID_P2M_ENTRY;
-
-	p2m_top[topidx][mididx][idx] = mfn;
-
-	return true;
-}
-
-bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
-		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-		return true;
-	}
-
-	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
-		if (!alloc_p2m(pfn))
-			return false;
-
-		if (!__set_phys_to_machine(pfn, mfn))
-			return false;
-	}
-
-	return true;
-}
-
 unsigned long arbitrary_virt_to_mfn(void *vaddr)
 {
 	xmaddr_t maddr = arbitrary_virt_to_machine(vaddr);
@@ -566,6 +201,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 	offset = address & ~PAGE_MASK;
 	return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset);
 }
+EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
 
 void make_lowmem_page_readonly(void *vaddr)
 {
@@ -2034,6 +1670,20 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 	set_page_prot(pmd, PAGE_KERNEL_RO);
 }
 
+void __init xen_setup_machphys_mapping(void)
+{
+	struct xen_machphys_mapping mapping;
+	unsigned long machine_to_phys_nr_ents;
+
+	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
+		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
+		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+	} else {
+		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+	}
+	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+}
+
 #ifdef CONFIG_X86_64
 static void convert_pfn_mfn(void *v)
 {
@@ -2119,44 +1769,83 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	return pgd;
 }
 #else	/* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
+
+static __init void xen_write_cr3_init(unsigned long cr3)
+{
+	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
+
+	BUG_ON(read_cr3() != __pa(initial_page_table));
+	BUG_ON(cr3 != __pa(swapper_pg_dir));
+
+	/*
+	 * We are switching to swapper_pg_dir for the first time (from
+	 * initial_page_table) and therefore need to mark that page
+	 * read-only and then pin it.
+	 *
+	 * Xen disallows sharing of kernel PMDs for PAE
+	 * guests. Therefore we must copy the kernel PMD from
+	 * initial_page_table into a new kernel PMD to be used in
+	 * swapper_pg_dir.
+	 */
+	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);
+	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
+	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
+
+	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+	xen_write_cr3(cr3);
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
+
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	set_page_prot(initial_page_table, PAGE_KERNEL);
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
+
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
+}
 
 __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
-	level2_kernel_pgt = extend_brk(sizeof(pmd_t *) * PTRS_PER_PMD, PAGE_SIZE);
+	initial_kernel_pmd =
+		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
 	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
 				  xen_start_info->nr_pt_frames * PAGE_SIZE +
 				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-	memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
 
-	xen_map_identity_early(level2_kernel_pgt, max_pfn);
+	xen_map_identity_early(initial_kernel_pmd, max_pfn);
 
-	memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
-	set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
-			__pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+	memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+	initial_page_table[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
 
-	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
-	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
+	set_page_prot(initial_page_table, PAGE_KERNEL_RO);
 	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
 
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-	xen_write_cr3(__pa(swapper_pg_dir));
-
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	xen_write_cr3(__pa(initial_page_table));
 
 	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
 
-	return swapper_pg_dir;
+	return initial_page_table;
 }
 #endif	/* CONFIG_X86_64 */
 
@@ -2290,7 +1979,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.write_cr2 = xen_write_cr2,
 
 	.read_cr3 = xen_read_cr3,
+#ifdef CONFIG_X86_32
+	.write_cr3 = xen_write_cr3_init,
+#else
 	.write_cr3 = xen_write_cr3,
+#endif
 
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
@@ -2358,8 +2051,6 @@ void __init xen_init_mmu_ops(void)
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;
 
-	vmap_lazy_unmap = false;
-
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
 
@@ -2627,7 +2318,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 
 	prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
 
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
+				(VM_PFNMAP | VM_RESERVED | VM_IO)));
 
 	rmd.mfn = mfn;
 	rmd.prot = prot;