Merge branch 'devel/for-linus-3.19' into stable/for-linus-3.19

arch/x86/include/asm/pgtable_types.h

@@ -396,6 +396,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
+extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags);

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

@@ -41,10 +41,12 @@ typedef struct xpaddr {
 
 extern unsigned long *machine_to_phys_mapping;
 extern unsigned long  machine_to_phys_nr;
+extern unsigned long *xen_p2m_addr;
+extern unsigned long  xen_p2m_size;
+extern unsigned long  xen_max_p2m_pfn;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 					     unsigned long pfn_e);
@@ -52,17 +54,52 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
 				   struct page **pages, unsigned int count);
-extern int m2p_add_override(unsigned long mfn, struct page *page,
-			    struct gnttab_map_grant_ref *kmap_op);
 extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 				     struct gnttab_map_grant_ref *kmap_ops,
 				     struct page **pages, unsigned int count);
-extern int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
-			       unsigned long mfn);
-extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
+/*
+ * Helper functions to write or read unsigned long values to/from
+ * memory, when the access may fault.
+ */
+static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
+{
+	return __put_user(val, (unsigned long __user *)addr);
+}
+
+static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val)
+{
+	return __get_user(*val, (unsigned long __user *)addr);
+}
+
+/*
+ * When to use pfn_to_mfn(), __pfn_to_mfn() or get_phys_to_machine():
+ * - pfn_to_mfn() returns either INVALID_P2M_ENTRY or the mfn. No indicator
+ *   bits (identity or foreign) are set.
+ * - __pfn_to_mfn() returns the found entry of the p2m table. A possibly set
+ *   identity or foreign indicator will be still set. __pfn_to_mfn() is
+ *   encapsulating get_phys_to_machine() which is called in special cases only.
+ * - get_phys_to_machine() is to be called by __pfn_to_mfn() only in special
+ *   cases needing an extended handling.
+ */
+static inline unsigned long __pfn_to_mfn(unsigned long pfn)
+{
+	unsigned long mfn;
+
+	if (pfn < xen_p2m_size)
+		mfn = xen_p2m_addr[pfn];
+	else if (unlikely(pfn < xen_max_p2m_pfn))
+		return get_phys_to_machine(pfn);
+	else
+		return IDENTITY_FRAME(pfn);
+
+	if (unlikely(mfn == INVALID_P2M_ENTRY))
+		return get_phys_to_machine(pfn);
+
+	return mfn;
+}
+
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
 	unsigned long mfn;
@@ -70,7 +107,7 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn)
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return pfn;
 
-	mfn = get_phys_to_machine(pfn);
+	mfn = __pfn_to_mfn(pfn);
 
 	if (mfn != INVALID_P2M_ENTRY)
 		mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
@@ -83,7 +120,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 1;
 
-	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
+	return __pfn_to_mfn(pfn) != INVALID_P2M_ENTRY;
 }
 
 static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
@@ -102,7 +139,7 @@ static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+	ret = xen_safe_read_ulong(&machine_to_phys_mapping[mfn], &pfn);
 	if (ret < 0)
 		return ~0;
 
@@ -117,7 +154,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 		return mfn;
 
 	pfn = mfn_to_pfn_no_overrides(mfn);
-	if (get_phys_to_machine(pfn) != mfn) {
+	if (__pfn_to_mfn(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -133,8 +170,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 	 * entry doesn't map back to the mfn and m2p_override doesn't have a
 	 * valid entry for it.
 	 */
-	if (pfn == ~0 &&
-			get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+	if (pfn == ~0 && __pfn_to_mfn(mfn) == IDENTITY_FRAME(mfn))
 		pfn = mfn;
 
 	return pfn;
@@ -180,7 +216,7 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 		return mfn;
 
 	pfn = mfn_to_pfn(mfn);
-	if (get_phys_to_machine(pfn) != mfn)
+	if (__pfn_to_mfn(pfn) != mfn)
 		return -1; /* force !pfn_valid() */
 	return pfn;
 }

arch/x86/mm/pageattr.c

@@ -383,6 +383,26 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
         return lookup_address(address, level);
 }
 
+/*
+ * Lookup the PMD entry for a virtual address. Return a pointer to the entry
+ * or NULL if not present.
+ */
+pmd_t *lookup_pmd_address(unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(address);
+	if (pgd_none(*pgd))
+		return NULL;
+
+	pud = pud_offset(pgd, address);
+	if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
+		return NULL;
+
+	return pmd_offset(pud, address);
+}
+
 /*
  * This is necessary because __pa() does not work on some
  * kinds of memory, like vmalloc() or the alloc_remap()

arch/x86/xen/mmu.c

@@ -387,7 +387,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		unsigned long mfn;
 
 		if (!xen_feature(XENFEAT_auto_translated_physmap))
-			mfn = get_phys_to_machine(pfn);
+			mfn = __pfn_to_mfn(pfn);
 		else
 			mfn = pfn;
 		/*
@@ -1158,20 +1158,16 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
 	 * instead of somewhere later and be confusing. */
 	xen_mc_flush();
 }
-static void __init xen_pagetable_p2m_copy(void)
+
+static void __init xen_pagetable_p2m_free(void)
 {
 	unsigned long size;
 	unsigned long addr;
-	unsigned long new_mfn_list;
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
 
 	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
 
-	new_mfn_list = xen_revector_p2m_tree();
 	/* No memory or already called. */
-	if (!new_mfn_list || new_mfn_list == xen_start_info->mfn_list)
+	if ((unsigned long)xen_p2m_addr == xen_start_info->mfn_list)
 		return;
 
 	/* using __ka address and sticking INVALID_P2M_ENTRY! */
@@ -1189,8 +1185,6 @@ static void __init xen_pagetable_p2m_copy(void)
 
 	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;
 
 	/* 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
@@ -1214,17 +1208,35 @@ static void __init xen_pagetable_p2m_copy(void)
 }
 #endif
 
-static void __init xen_pagetable_init(void)
+static void __init xen_pagetable_p2m_setup(void)
 {
-	paging_init();
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return;
+
+	xen_vmalloc_p2m_tree();
+
 #ifdef CONFIG_X86_64
-	xen_pagetable_p2m_copy();
+	xen_pagetable_p2m_free();
 #endif
+	/* And revector! Bye bye old array */
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+}
+
+static void __init xen_pagetable_init(void)
+{
+	paging_init();
+	xen_post_allocator_init();
+
+	xen_pagetable_p2m_setup();
+
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
 
+	/* Remap memory freed due to conflicts with E820 map */
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		xen_remap_memory();
+
 	xen_setup_shared_info();
-	xen_post_allocator_init();
 }
 static void xen_write_cr2(unsigned long cr2)
 {

arch/x86/xen/setup.c

@@ -30,6 +30,7 @@
 #include "xen-ops.h"
 #include "vdso.h"
 #include "p2m.h"
+#include "mmu.h"
 
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
@@ -47,8 +48,19 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 /* Number of pages released from the initial allocation. */
 unsigned long xen_released_pages;
 
-/* Buffer used to remap identity mapped pages */
-unsigned long xen_remap_buf[P2M_PER_PAGE] __initdata;
+/*
+ * Buffer used to remap identity mapped pages. We only need the virtual space.
+ * The physical page behind this address is remapped as needed to different
+ * buffer pages.
+ */
+#define REMAP_SIZE	(P2M_PER_PAGE - 3)
+static struct {
+	unsigned long	next_area_mfn;
+	unsigned long	target_pfn;
+	unsigned long	size;
+	unsigned long	mfns[REMAP_SIZE];
+} xen_remap_buf __initdata __aligned(PAGE_SIZE);
+static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
 
 /* 
  * The maximum amount of extra memory compared to the base size.  The
@@ -64,7 +76,6 @@ unsigned long xen_remap_buf[P2M_PER_PAGE] __initdata;
 
 static void __init xen_add_extra_mem(u64 start, u64 size)
 {
-	unsigned long pfn;
 	int i;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
@@ -84,75 +95,76 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
 
 	memblock_reserve(start, size);
+}
 
-	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);
-
-		if (WARN_ONCE(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
-			continue;
-		WARN_ONCE(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
-			  pfn, mfn);
+static void __init xen_del_extra_mem(u64 start, u64 size)
+{
+	int i;
+	u64 start_r, size_r;
 
-		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		start_r = xen_extra_mem[i].start;
+		size_r = xen_extra_mem[i].size;
+
+		/* Start of region. */
+		if (start_r == start) {
+			BUG_ON(size > size_r);
+			xen_extra_mem[i].start += size;
+			xen_extra_mem[i].size -= size;
+			break;
+		}
+		/* End of region. */
+		if (start_r + size_r == start + size) {
+			BUG_ON(size > size_r);
+			xen_extra_mem[i].size -= size;
+			break;
+		}
+		/* Mid of region. */
+		if (start > start_r && start < start_r + size_r) {
+			BUG_ON(start + size > start_r + size_r);
+			xen_extra_mem[i].size = start - start_r;
+			/* Calling memblock_reserve() again is okay. */
+			xen_add_extra_mem(start + size, start_r + size_r -
+					  (start + size));
+			break;
+		}
 	}
+	memblock_free(start, size);
 }
 
-static unsigned long __init xen_do_chunk(unsigned long start,
-					 unsigned long end, bool release)
+/*
+ * Called during boot before the p2m list can take entries beyond the
+ * hypervisor supplied p2m list. Entries in extra mem are to be regarded as
+ * invalid.
+ */
+unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
 {
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = 0,
-		.domid        = DOMID_SELF
-	};
-	unsigned long len = 0;
-	unsigned long pfn;
-	int ret;
+	int i;
+	unsigned long addr = PFN_PHYS(pfn);
 
-	for (pfn = start; pfn < end; pfn++) {
-		unsigned long frame;
-		unsigned long mfn = pfn_to_mfn(pfn);
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		if (addr >= xen_extra_mem[i].start &&
+		    addr < xen_extra_mem[i].start + xen_extra_mem[i].size)
+			return INVALID_P2M_ENTRY;
+	}
 
-		if (release) {
-			/* Make sure pfn exists to start with */
-			if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
-				continue;
-			frame = mfn;
-		} else {
-			if (mfn != INVALID_P2M_ENTRY)
-				continue;
-			frame = pfn;
-		}
-		set_xen_guest_handle(reservation.extent_start, &frame);
-		reservation.nr_extents = 1;
+	return IDENTITY_FRAME(pfn);
+}
 
-		ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
-					   &reservation);
-		WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
-		     release ? "release" : "populate", pfn, ret);
+/*
+ * Mark all pfns of extra mem as invalid in p2m list.
+ */
+void __init xen_inv_extra_mem(void)
+{
+	unsigned long pfn, pfn_s, pfn_e;
+	int i;
 
-		if (ret == 1) {
-			if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
-				if (release)
-					break;
-				set_xen_guest_handle(reservation.extent_start, &frame);
-				reservation.nr_extents = 1;
-				ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
-							   &reservation);
-				break;
-			}
-			len++;
-		} else
-			break;
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		pfn_s = PFN_DOWN(xen_extra_mem[i].start);
+		pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
+		for (pfn = pfn_s; pfn < pfn_e; pfn++)
+			set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 	}
-	if (len)
-		printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
-		       release ? "Freeing" : "Populating",
-		       start, end, len,
-		       release ? "freed" : "added");
-
-	return len;
 }
 
 /*
@@ -198,26 +210,62 @@ static unsigned long __init xen_find_pfn_range(
 	return done;
 }
 
+static int __init xen_free_mfn(unsigned long mfn)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = 0,
+		.domid        = DOMID_SELF
+	};
+
+	set_xen_guest_handle(reservation.extent_start, &mfn);
+	reservation.nr_extents = 1;
+
+	return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+
 /*
- * This releases a chunk of memory and then does the identity map. It's used as
+ * This releases a chunk of memory and then does the identity map. It's used
  * as a fallback if the remapping fails.
  */
 static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 	unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity,
 	unsigned long *released)
 {
+	unsigned long len = 0;
+	unsigned long pfn, end;
+	int ret;
+
 	WARN_ON(start_pfn > end_pfn);
 
+	end = min(end_pfn, nr_pages);
+	for (pfn = start_pfn; pfn < end; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
+
+		/* Make sure pfn exists to start with */
+		if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+			continue;
+
+		ret = xen_free_mfn(mfn);
+		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
+
+		if (ret == 1) {
+			if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
+				break;
+			len++;
+		} else
+			break;
+	}
+
 	/* Need to release pages first */
-	*released += xen_do_chunk(start_pfn, min(end_pfn, nr_pages), true);
+	*released += len;
 	*identity += set_phys_range_identity(start_pfn, end_pfn);
 }
 
 /*
- * Helper function to update both the p2m and m2p tables.
+ * Helper function to update the p2m and m2p tables and kernel mapping.
  */
-static unsigned long __init xen_update_mem_tables(unsigned long pfn,
-						  unsigned long mfn)
+static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
 {
 	struct mmu_update update = {
 		.ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
@@ -225,161 +273,88 @@ static unsigned long __init xen_update_mem_tables(unsigned long pfn,
 	};
 
 	/* Update p2m */
-	if (!early_set_phys_to_machine(pfn, mfn)) {
+	if (!set_phys_to_machine(pfn, mfn)) {
 		WARN(1, "Failed to set p2m mapping for pfn=%ld mfn=%ld\n",
 		     pfn, mfn);
-		return false;
+		BUG();
 	}
 
 	/* Update m2p */
 	if (HYPERVISOR_mmu_update(&update, 1, NULL, DOMID_SELF) < 0) {
 		WARN(1, "Failed to set m2p mapping for mfn=%ld pfn=%ld\n",
 		     mfn, pfn);
-		return false;
+		BUG();
 	}
 
-	return true;
+	/* Update kernel mapping, but not for highmem. */
+	if ((pfn << PAGE_SHIFT) >= __pa(high_memory))
+		return;
+
+	if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
+					 mfn_pte(mfn, PAGE_KERNEL), 0)) {
+		WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n",
+		      mfn, pfn);
+		BUG();
+	}
 }
 
 /*
  * This function updates the p2m and m2p tables with an identity map from
- * start_pfn to start_pfn+size and remaps the underlying RAM of the original
- * allocation at remap_pfn. It must do so carefully in P2M_PER_PAGE sized blocks
- * to not exhaust the reserved brk space. Doing it in properly aligned blocks
- * ensures we only allocate the minimum required leaf pages in the p2m table. It
- * copies the existing mfns from the p2m table under the 1:1 map, overwrites
- * them with the identity map and then updates the p2m and m2p tables with the
- * remapped memory.
+ * start_pfn to start_pfn+size and prepares remapping the underlying RAM of the
+ * original allocation at remap_pfn. The information needed for remapping is
+ * saved in the memory itself to avoid the need for allocating buffers. The
+ * complete remap information is contained in a list of MFNs each containing
+ * up to REMAP_SIZE MFNs and the start target PFN for doing the remap.
+ * This enables us to preserve the original mfn sequence while doing the
+ * remapping at a time when the memory management is capable of allocating
+ * virtual and physical memory in arbitrary amounts, see 'xen_remap_memory' and
+ * its callers.
  */
-static unsigned long __init xen_do_set_identity_and_remap_chunk(
+static void __init xen_do_set_identity_and_remap_chunk(
         unsigned long start_pfn, unsigned long size, unsigned long remap_pfn)
 {
+	unsigned long buf = (unsigned long)&xen_remap_buf;
+	unsigned long mfn_save, mfn;
 	unsigned long ident_pfn_iter, remap_pfn_iter;
-	unsigned long ident_start_pfn_align, remap_start_pfn_align;
-	unsigned long ident_end_pfn_align, remap_end_pfn_align;
-	unsigned long ident_boundary_pfn, remap_boundary_pfn;
-	unsigned long ident_cnt = 0;
-	unsigned long remap_cnt = 0;
+	unsigned long ident_end_pfn = start_pfn + size;
 	unsigned long left = size;
-	unsigned long mod;
-	int i;
+	unsigned long ident_cnt = 0;
+	unsigned int i, chunk;
 
 	WARN_ON(size == 0);
 
 	BUG_ON(xen_feature(XENFEAT_auto_translated_physmap));
 
-	/*
-	 * Determine the proper alignment to remap memory in P2M_PER_PAGE sized
-	 * blocks. We need to keep track of both the existing pfn mapping and
-	 * the new pfn remapping.
-	 */
-	mod = start_pfn % P2M_PER_PAGE;
-	ident_start_pfn_align =
-		mod ? (start_pfn - mod + P2M_PER_PAGE) : start_pfn;
-	mod = remap_pfn % P2M_PER_PAGE;
-	remap_start_pfn_align =
-		mod ? (remap_pfn - mod + P2M_PER_PAGE) : remap_pfn;
-	mod = (start_pfn + size) % P2M_PER_PAGE;
-	ident_end_pfn_align = start_pfn + size - mod;
-	mod = (remap_pfn + size) % P2M_PER_PAGE;
-	remap_end_pfn_align = remap_pfn + size - mod;
-
-	/* Iterate over each p2m leaf node in each range */
-	for (ident_pfn_iter = ident_start_pfn_align, remap_pfn_iter = remap_start_pfn_align;
-	     ident_pfn_iter < ident_end_pfn_align && remap_pfn_iter < remap_end_pfn_align;
-	     ident_pfn_iter += P2M_PER_PAGE, remap_pfn_iter += P2M_PER_PAGE) {
-		/* Check we aren't past the end */
-		BUG_ON(ident_pfn_iter + P2M_PER_PAGE > start_pfn + size);
-		BUG_ON(remap_pfn_iter + P2M_PER_PAGE > remap_pfn + size);
-
-		/* Save p2m mappings */
-		for (i = 0; i < P2M_PER_PAGE; i++)
-			xen_remap_buf[i] = pfn_to_mfn(ident_pfn_iter + i);
-
-		/* Set identity map which will free a p2m leaf */
-		ident_cnt += set_phys_range_identity(ident_pfn_iter,
-			ident_pfn_iter + P2M_PER_PAGE);
+	mfn_save = virt_to_mfn(buf);
 
-#ifdef DEBUG
-		/* Helps verify a p2m leaf has been freed */
-		for (i = 0; i < P2M_PER_PAGE; i++) {
-			unsigned int pfn = ident_pfn_iter + i;
-			BUG_ON(pfn_to_mfn(pfn) != pfn);
-		}
-#endif
-		/* Now remap memory */
-		for (i = 0; i < P2M_PER_PAGE; i++) {
-			unsigned long mfn = xen_remap_buf[i];
-
-			/* This will use the p2m leaf freed above */
-			if (!xen_update_mem_tables(remap_pfn_iter + i, mfn)) {
-				WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n",
-					remap_pfn_iter + i, mfn);
-				return 0;
-			}
-
-			remap_cnt++;
-		}
-
-		left -= P2M_PER_PAGE;
-	}
-
-	/* Max boundary space possible */
-	BUG_ON(left > (P2M_PER_PAGE - 1) * 2);
+	for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn;
+	     ident_pfn_iter < ident_end_pfn;
+	     ident_pfn_iter += REMAP_SIZE, remap_pfn_iter += REMAP_SIZE) {
+		chunk = (left < REMAP_SIZE) ? left : REMAP_SIZE;
 
-	/* Now handle the boundary conditions */
-	ident_boundary_pfn = start_pfn;
-	remap_boundary_pfn = remap_pfn;
-	for (i = 0; i < left; i++) {
-		unsigned long mfn;
+		/* Map first pfn to xen_remap_buf */
+		mfn = pfn_to_mfn(ident_pfn_iter);
+		set_pte_mfn(buf, mfn, PAGE_KERNEL);
 
-		/* These two checks move from the start to end boundaries */
-		if (ident_boundary_pfn == ident_start_pfn_align)
-			ident_boundary_pfn = ident_pfn_iter;
-		if (remap_boundary_pfn == remap_start_pfn_align)
-			remap_boundary_pfn = remap_pfn_iter;
+		/* Save mapping information in page */
+		xen_remap_buf.next_area_mfn = xen_remap_mfn;
+		xen_remap_buf.target_pfn = remap_pfn_iter;
+		xen_remap_buf.size = chunk;
+		for (i = 0; i < chunk; i++)
+			xen_remap_buf.mfns[i] = pfn_to_mfn(ident_pfn_iter + i);
 
-		/* Check we aren't past the end */
-		BUG_ON(ident_boundary_pfn >= start_pfn + size);
-		BUG_ON(remap_boundary_pfn >= remap_pfn + size);
-
-		mfn = pfn_to_mfn(ident_boundary_pfn);
-
-		if (!xen_update_mem_tables(remap_boundary_pfn, mfn)) {
-			WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n",
-				remap_pfn_iter + i, mfn);
-			return 0;
-		}
-		remap_cnt++;
+		/* Put remap buf into list. */
+		xen_remap_mfn = mfn;
 
-		ident_boundary_pfn++;
-		remap_boundary_pfn++;
-	}
+		/* Set identity map */
+		ident_cnt += set_phys_range_identity(ident_pfn_iter,
+			ident_pfn_iter + chunk);
 
-	/* Finish up the identity map */
-	if (ident_start_pfn_align >= ident_end_pfn_align) {
-		/*
-                 * In this case we have an identity range which does not span an
-                 * aligned block so everything needs to be identity mapped here.
-                 * If we didn't check this we might remap too many pages since
-                 * the align boundaries are not meaningful in this case.
-	         */
-		ident_cnt += set_phys_range_identity(start_pfn,
-			start_pfn + size);
-	} else {
-		/* Remapped above so check each end of the chunk */
-		if (start_pfn < ident_start_pfn_align)
-			ident_cnt += set_phys_range_identity(start_pfn,
-				ident_start_pfn_align);
-		if (start_pfn + size > ident_pfn_iter)
-			ident_cnt += set_phys_range_identity(ident_pfn_iter,
-				start_pfn + size);
+		left -= chunk;
 	}
 
-	BUG_ON(ident_cnt != size);
-	BUG_ON(remap_cnt != size);
-
-	return size;
+	/* Restore old xen_remap_buf mapping */
+	set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
 }
 
 /*
@@ -396,8 +371,7 @@ static unsigned long __init xen_do_set_identity_and_remap_chunk(
 static unsigned long __init xen_set_identity_and_remap_chunk(
         const struct e820entry *list, size_t map_size, unsigned long start_pfn,
 	unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
-	unsigned long *identity, unsigned long *remapped,
-	unsigned long *released)
+	unsigned long *identity, unsigned long *released)
 {
 	unsigned long pfn;
 	unsigned long i = 0;
@@ -431,19 +405,12 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		if (size > remap_range_size)
 			size = remap_range_size;
 
-		if (!xen_do_set_identity_and_remap_chunk(cur_pfn, size, remap_pfn)) {
-			WARN(1, "Failed to remap 1:1 memory cur_pfn=%ld size=%ld remap_pfn=%ld\n",
-				cur_pfn, size, remap_pfn);
-			xen_set_identity_and_release_chunk(cur_pfn,
-				cur_pfn + left, nr_pages, identity, released);
-			break;
-		}
+		xen_do_set_identity_and_remap_chunk(cur_pfn, size, remap_pfn);
 
 		/* Update variables to reflect new mappings. */
 		i += size;
 		remap_pfn += size;
 		*identity += size;
-		*remapped += size;
 	}
 
 	/*
@@ -458,13 +425,12 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 	return remap_pfn;
 }
 
-static unsigned long __init xen_set_identity_and_remap(
+static void __init xen_set_identity_and_remap(
 	const struct e820entry *list, size_t map_size, unsigned long nr_pages,
 	unsigned long *released)
 {
 	phys_addr_t start = 0;
 	unsigned long identity = 0;
-	unsigned long remapped = 0;
 	unsigned long last_pfn = nr_pages;
 	const struct e820entry *entry;
 	unsigned long num_released = 0;
@@ -494,8 +460,7 @@ static unsigned long __init xen_set_identity_and_remap(
 				last_pfn = xen_set_identity_and_remap_chunk(
 						list, map_size, start_pfn,
 						end_pfn, nr_pages, last_pfn,
-						&identity, &remapped,
-						&num_released);
+						&identity, &num_released);
 			start = end;
 		}
 	}
@@ -503,12 +468,63 @@ static unsigned long __init xen_set_identity_and_remap(
 	*released = num_released;
 
 	pr_info("Set %ld page(s) to 1-1 mapping\n", identity);
-	pr_info("Remapped %ld page(s), last_pfn=%ld\n", remapped,
-		last_pfn);
 	pr_info("Released %ld page(s)\n", num_released);
+}
+
+/*
+ * Remap the memory prepared in xen_do_set_identity_and_remap_chunk().
+ * The remap information (which mfn remap to which pfn) is contained in the
+ * to be remapped memory itself in a linked list anchored at xen_remap_mfn.
+ * This scheme allows to remap the different chunks in arbitrary order while
+ * the resulting mapping will be independant from the order.
+ */
+void __init xen_remap_memory(void)
+{
+	unsigned long buf = (unsigned long)&xen_remap_buf;
+	unsigned long mfn_save, mfn, pfn;
+	unsigned long remapped = 0;
+	unsigned int i;
+	unsigned long pfn_s = ~0UL;
+	unsigned long len = 0;
+
+	mfn_save = virt_to_mfn(buf);
+
+	while (xen_remap_mfn != INVALID_P2M_ENTRY) {
+		/* Map the remap information */
+		set_pte_mfn(buf, xen_remap_mfn, PAGE_KERNEL);
 
-	return last_pfn;
+		BUG_ON(xen_remap_mfn != xen_remap_buf.mfns[0]);
+
+		pfn = xen_remap_buf.target_pfn;
+		for (i = 0; i < xen_remap_buf.size; i++) {
+			mfn = xen_remap_buf.mfns[i];
+			xen_update_mem_tables(pfn, mfn);
+			remapped++;
+			pfn++;
+		}
+		if (pfn_s == ~0UL || pfn == pfn_s) {
+			pfn_s = xen_remap_buf.target_pfn;
+			len += xen_remap_buf.size;
+		} else if (pfn_s + len == xen_remap_buf.target_pfn) {
+			len += xen_remap_buf.size;
+		} else {
+			xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+			pfn_s = xen_remap_buf.target_pfn;
+			len = xen_remap_buf.size;
+		}
+
+		mfn = xen_remap_mfn;
+		xen_remap_mfn = xen_remap_buf.next_area_mfn;
+	}
+
+	if (pfn_s != ~0UL && len)
+		xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+
+	set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
+
+	pr_info("Remapped %ld page(s)\n", remapped);
 }
+
 static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages = MAX_DOMAIN_PAGES;
@@ -569,7 +585,6 @@ char * __init xen_memory_setup(void)
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
-	unsigned long last_pfn = 0;
 	unsigned long extra_pages = 0;
 	int i;
 	int op;
@@ -616,17 +631,14 @@ char * __init xen_memory_setup(void)
 		extra_pages += max_pages - max_pfn;
 
 	/*
-	 * Set identity map on non-RAM pages and remap the underlying RAM.
+	 * Set identity map on non-RAM pages and prepare remapping the
+	 * underlying RAM.
 	 */
-	last_pfn = xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
-					      &xen_released_pages);
+	xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
+				   &xen_released_pages);
 
 	extra_pages += xen_released_pages;
 
-	if (last_pfn > max_pfn) {
-		max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
-		mem_end = PFN_PHYS(max_pfn);
-	}
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
 	 * factor the base size.  On non-highmem systems, the base
@@ -653,6 +665,7 @@ char * __init xen_memory_setup(void)
 				size = min(size, (u64)extra_pages * PAGE_SIZE);
 				extra_pages -= size / PAGE_SIZE;
 				xen_add_extra_mem(addr, size);
+				xen_max_p2m_pfn = PFN_DOWN(addr + size);
 			} else
 				type = E820_UNUSABLE;
 		}

arch/x86/xen/xen-ops.h

@@ -29,12 +29,14 @@ void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_reserve_top(void);
-extern unsigned long xen_max_p2m_pfn;
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
 void xen_set_pat(u64);
 
+unsigned long __ref xen_chk_extra_mem(unsigned long pfn);
+void __init xen_inv_extra_mem(void);
+void __init xen_remap_memory(void);
 char * __init xen_memory_setup(void);
 char * xen_auto_xlated_memory_setup(void);
 void __init xen_arch_setup(void);
@@ -47,7 +49,7 @@ 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 __init xen_vmalloc_p2m_tree(void);
 
 void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);