xen: switch to linear virtual mapped sparse p2m list

At start of the day the Xen hypervisor presents a contiguous mfn list
to a pv-domain. In order to support sparse memory this mfn list is
accessed via a three level p2m tree built early in the boot process.
Whenever the system needs the mfn associated with a pfn this tree is
used to find the mfn.

Instead of using a software walked tree for accessing a specific mfn
list entry this patch is creating a virtual address area for the
entire possible mfn list including memory holes. The holes are
covered by mapping a pre-defined  page consisting only of "invalid
mfn" entries. Access to a mfn entry is possible by just using the
virtual base address of the mfn list and the pfn as index into that
list. This speeds up the (hot) path of determining the mfn of a
pfn.

Kernel build on a Dell Latitude E6440 (2 cores, HT) in 64 bit Dom0
showed following improvements:

Elapsed time: 32:50 ->  32:35
System:       18:07 ->  17:47
User:        104:00 -> 103:30

Tested with following configurations:
- 64 bit dom0, 8GB RAM
- 64 bit dom0, 128 GB RAM, PCI-area above 4 GB
- 32 bit domU, 512 MB, 8 GB, 43 GB (more wouldn't work even without
                                    the patch)
- 32 bit domU, ballooning up and down
- 32 bit domU, save and restore
- 32 bit domU with PCI passthrough
- 64 bit domU, 8 GB, 2049 MB, 5000 MB
- 64 bit domU, ballooning up and down
- 64 bit domU, save and restore
- 64 bit domU with PCI passthrough
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

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

@@ -65,13 +65,25 @@ extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
  *   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().
- * - get_phys_to_machine() is to be called by __pfn_to_mfn() only to allow
- *   for future optimizations.
+ *   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)
 {
-	return get_phys_to_machine(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)

arch/x86/xen/mmu.c

@@ -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
@@ -1214,14 +1208,26 @@ 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();
-#else
-	xen_revector_p2m_tree();
+	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_pagetable_p2m_setup();
+
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
 

arch/x86/xen/xen-ops.h

@@ -49,7 +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);