Merge branch 'stable/128gb.v5.1' into stable/for-linus-3.7

* stable/128gb.v5.1:
  xen/mmu: If the revector fails, don't attempt to revector anything else.
  xen/p2m: When revectoring deal with holes in the P2M array.
  xen/mmu: Release just the MFN list, not MFN list and part of pagetables.
  xen/mmu: Remove from __ka space PMD entries for pagetables.
  xen/mmu: Copy and revector the P2M tree.
  xen/p2m: Add logic to revector a P2M tree to use __va leafs.
  xen/mmu: Recycle the Xen provided L4, L3, and L2 pages
  xen/mmu: For 64-bit do not call xen_map_identity_early
  xen/mmu: use copy_page instead of memcpy.
  xen/mmu: Provide comments describing the _ka and _va aliasing issue
  xen/mmu: The xen_setup_kernel_pagetable doesn't need to return anything.
  Revert "xen/x86: Workaround 64-bit hypervisor and 32-bit initial domain." and "xen/x86: Use memblock_reserve for sensitive areas."
  xen/x86: Workaround 64-bit hypervisor and 32-bit initial domain.
  xen/x86: Use memblock_reserve for sensitive areas.
  xen/p2m: Fix the comment describing the P2M tree.

Conflicts:
	arch/x86/xen/mmu.c

The pagetable_init is the old xen_pagetable_setup_done and xen_pagetable_setup_start
rolled in one.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

arch/x86/xen/enlighten.c

@@ -1290,7 +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;
@@ -1382,8 +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];
@@ -1392,7 +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();

arch/x86/xen/p2m.c

@@ -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;

arch/x86/xen/setup.c

@@ -431,6 +431,24 @@ 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);

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);