Merge tag 'for-linus-4.3-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from David Vrabel:
 "Xen features and fixes for 4.3:

   - Convert xen-blkfront to the multiqueue API
   - [arm] Support binding event channels to different VCPUs.
   - [x86] Support > 512 GiB in a PV guests (off by default as such a
     guest cannot be migrated with the current toolstack).
   - [x86] PMU support for PV dom0 (limited support for using perf with
     Xen and other guests)"

* tag 'for-linus-4.3-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (33 commits)
  xen: switch extra memory accounting to use pfns
  xen: limit memory to architectural maximum
  xen: avoid another early crash of memory limited dom0
  xen: avoid early crash of memory limited dom0
  arm/xen: Remove helpers which are PV specific
  xen/x86: Don't try to set PCE bit in CR4
  xen/PMU: PMU emulation code
  xen/PMU: Intercept PMU-related MSR and APIC accesses
  xen/PMU: Describe vendor-specific PMU registers
  xen/PMU: Initialization code for Xen PMU
  xen/PMU: Sysfs interface for setting Xen PMU mode
  xen: xensyms support
  xen: remove no longer needed p2m.h
  xen: allow more than 512 GB of RAM for 64 bit pv-domains
  xen: move p2m list if conflicting with e820 map
  xen: add explicit memblock_reserve() calls for special pages
  mm: provide early_memremap_ro to establish read-only mapping
  xen: check for initrd conflicting with e820 map
  xen: check pre-allocated page tables for conflict with memory map
  xen: check for kernel memory conflicting with memory layout
  ...

15 files changed, 1435 insertions, 215 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 484145368a24..c7b15f3e2cf3 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -7,6 +7,7 @@ config XEN
 	depends on PARAVIRT
 	select PARAVIRT_CLOCK
 	select XEN_HAVE_PVMMU
+	select XEN_HAVE_VPMU
 	depends on X86_64 || (X86_32 && X86_PAE)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
@@ -23,14 +24,18 @@ config XEN_PVHVM
 	def_bool y
 	depends on XEN && PCI && X86_LOCAL_APIC
 
-config XEN_MAX_DOMAIN_MEMORY
-       int
-       default 500 if X86_64
-       default 64 if X86_32
-       depends on XEN
-       help
-         This only affects the sizing of some bss arrays, the unused
-         portions of which are freed.
+config XEN_512GB
+	bool "Limit Xen pv-domain memory to 512GB"
+	depends on XEN && X86_64
+	default y
+	help
+	  Limit paravirtualized user domains to 512GB of RAM.
+
+	  The Xen tools and crash dump analysis tools might not support
+	  pv-domains with more than 512 GB of RAM. This option controls the
+	  default setting of the kernel to use only up to 512 GB or more.
+	  It is always possible to change the default via specifying the
+	  boot parameter "xen_512gb_limit".
 
 config XEN_SAVE_RESTORE
        bool
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 4b6e29ac0968..e47e52787d32 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,7 +13,7 @@ CFLAGS_mmu.o			:= $(nostackp)
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o apic.o
+			p2m.o apic.o pmu.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 70e060ad879a..acda713ab5be 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -7,6 +7,7 @@
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
 #include "xen-ops.h"
+#include "pmu.h"
 #include "smp.h"
 
 static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
@@ -72,6 +73,11 @@ static u32 xen_apic_read(u32 reg)
 
 static void xen_apic_write(u32 reg, u32 val)
 {
+	if (reg == APIC_LVTPC) {
+		(void)pmu_apic_update(reg);
+		return;
+	}
+
 	/* Warn to see if there's any stray references */
 	WARN(1,"register: %x, value: %x\n", reg, val);
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d9cfa452da9d..30d12afe52ed 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -84,6 +84,7 @@
 #include "mmu.h"
 #include "smp.h"
 #include "multicalls.h"
+#include "pmu.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
 
@@ -1010,8 +1011,7 @@ static void xen_write_cr0(unsigned long cr0)
 
 static void xen_write_cr4(unsigned long cr4)
 {
-	cr4 &= ~X86_CR4_PGE;
-	cr4 &= ~X86_CR4_PSE;
+	cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE);
 
 	native_write_cr4(cr4);
 }
@@ -1030,6 +1030,9 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 {
 	u64 val;
 
+	if (pmu_msr_read(msr, &val, err))
+		return val;
+
 	val = native_read_msr_safe(msr, err);
 	switch (msr) {
 	case MSR_IA32_APICBASE:
@@ -1076,7 +1079,8 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		   Xen console noise. */
 
 	default:
-		ret = native_write_msr_safe(msr, low, high);
+		if (!pmu_msr_write(msr, low, high, &ret))
+			ret = native_write_msr_safe(msr, low, high);
 	}
 
 	return ret;
@@ -1215,7 +1219,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_msr = xen_read_msr_safe,
 	.write_msr = xen_write_msr_safe,
 
-	.read_pmc = native_read_pmc,
+	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
 #ifdef CONFIG_X86_64
@@ -1264,6 +1268,10 @@ static const struct pv_apic_ops xen_apic_ops __initconst = {
 static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		xen_pmu_finish(cpu);
 
 	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
@@ -1607,7 +1615,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	early_boot_irqs_disabled = true;
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
-	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
+	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
+				   xen_start_info->nr_pages);
+	xen_reserve_special_pages();
 
 	/*
 	 * Modify the cache mode translation tables to match Xen's PAT
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dd151b2045b0..2c50b445884e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -116,6 +116,7 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
 DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 
+static phys_addr_t xen_pt_base, xen_pt_size __initdata;
 
 /*
  * Just beyond the highest usermode address.  STACK_TOP_MAX has a
@@ -1093,6 +1094,16 @@ static void xen_exit_mmap(struct mm_struct *mm)
 
 static void xen_post_allocator_init(void);
 
+static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct mmuext_op op;
+
+	op.cmd = cmd;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+		BUG();
+}
+
 #ifdef CONFIG_X86_64
 static void __init xen_cleanhighmap(unsigned long vaddr,
 				    unsigned long vaddr_end)
@@ -1114,6 +1125,83 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
 	xen_mc_flush();
 }
 
+/*
+ * Make a page range writeable and free it.
+ */
+static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
+{
+	void *vaddr = __va(paddr);
+	void *vaddr_end = vaddr + size;
+
+	for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
+		make_lowmem_page_readwrite(vaddr);
+
+	memblock_free(paddr, size);
+}
+
+static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
+{
+	unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK;
+
+	if (unpin)
+		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa));
+	ClearPagePinned(virt_to_page(__va(pa)));
+	xen_free_ro_pages(pa, PAGE_SIZE);
+}
+
+/*
+ * Since it is well isolated we can (and since it is perhaps large we should)
+ * also free the page tables mapping the initial P->M table.
+ */
+static void __init xen_cleanmfnmap(unsigned long vaddr)
+{
+	unsigned long va = vaddr & PMD_MASK;
+	unsigned long pa;
+	pgd_t *pgd = pgd_offset_k(va);
+	pud_t *pud_page = pud_offset(pgd, 0);
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned int i;
+	bool unpin;
+
+	unpin = (vaddr == 2 * PGDIR_SIZE);
+	set_pgd(pgd, __pgd(0));
+	do {
+		pud = pud_page + pud_index(va);
+		if (pud_none(*pud)) {
+			va += PUD_SIZE;
+		} else if (pud_large(*pud)) {
+			pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
+			xen_free_ro_pages(pa, PUD_SIZE);
+			va += PUD_SIZE;
+		} else {
+			pmd = pmd_offset(pud, va);
+			if (pmd_large(*pmd)) {
+				pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
+				xen_free_ro_pages(pa, PMD_SIZE);
+			} else if (!pmd_none(*pmd)) {
+				pte = pte_offset_kernel(pmd, va);
+				set_pmd(pmd, __pmd(0));
+				for (i = 0; i < PTRS_PER_PTE; ++i) {
+					if (pte_none(pte[i]))
+						break;
+					pa = pte_pfn(pte[i]) << PAGE_SHIFT;
+					xen_free_ro_pages(pa, PAGE_SIZE);
+				}
+				xen_cleanmfnmap_free_pgtbl(pte, unpin);
+			}
+			va += PMD_SIZE;
+			if (pmd_index(va))
+				continue;
+			set_pud(pud, __pud(0));
+			xen_cleanmfnmap_free_pgtbl(pmd, unpin);
+		}
+
+	} while (pud_index(va) || pmd_index(va));
+	xen_cleanmfnmap_free_pgtbl(pud_page, unpin);
+}
+
 static void __init xen_pagetable_p2m_free(void)
 {
 	unsigned long size;
@@ -1128,18 +1216,31 @@ static void __init xen_pagetable_p2m_free(void)
 	/* using __ka address and sticking INVALID_P2M_ENTRY! */
 	memset((void *)xen_start_info->mfn_list, 0xff, size);
 
-	/* We should be in __ka space. */
-	BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
 	addr = xen_start_info->mfn_list;
-	/* We roundup to the PMD, which means that if anybody at this stage is
-	 * using the __ka address of xen_start_info or xen_start_info->shared_info
-	 * they are in going to crash. Fortunatly we have already revectored
-	 * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+	/*
+	 * We could be in __ka space.
+	 * We roundup to the PMD, which means that if anybody at this stage is
+	 * using the __ka address of xen_start_info or
+	 * xen_start_info->shared_info they are in going to crash. Fortunatly
+	 * we have already revectored in xen_setup_kernel_pagetable and in
+	 * xen_setup_shared_info.
+	 */
 	size = roundup(size, PMD_SIZE);
-	xen_cleanhighmap(addr, addr + size);
 
-	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
-	memblock_free(__pa(xen_start_info->mfn_list), size);
+	if (addr >= __START_KERNEL_map) {
+		xen_cleanhighmap(addr, addr + size);
+		size = PAGE_ALIGN(xen_start_info->nr_pages *
+				  sizeof(unsigned long));
+		memblock_free(__pa(addr), size);
+	} else {
+		xen_cleanmfnmap(addr);
+	}
+}
+
+static void __init xen_pagetable_cleanhighmap(void)
+{
+	unsigned long size;
+	unsigned long addr;
 
 	/* 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
@@ -1172,6 +1273,8 @@ static void __init xen_pagetable_p2m_setup(void)
 
 #ifdef CONFIG_X86_64
 	xen_pagetable_p2m_free();
+
+	xen_pagetable_cleanhighmap();
 #endif
 	/* And revector! Bye bye old array */
 	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
@@ -1461,6 +1564,24 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 #else /* CONFIG_X86_64 */
 static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 {
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_writable_page_tables) ||
+	    xen_feature(XENFEAT_auto_translated_physmap) ||
+	    xen_start_info->mfn_list >= __START_KERNEL_map)
+		return pte;
+
+	/*
+	 * Pages belonging to the initial p2m list mapped outside the default
+	 * address range must be mapped read-only. This region contains the
+	 * page tables for mapping the p2m list, too, and page tables MUST be
+	 * mapped read-only.
+	 */
+	pfn = pte_pfn(pte);
+	if (pfn >= xen_start_info->first_p2m_pfn &&
+	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+		pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
+
 	return pte;
 }
 #endif /* CONFIG_X86_64 */
@@ -1489,15 +1610,6 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 	native_set_pte(ptep, pte);
 }
 
-static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
-	struct mmuext_op op;
-	op.cmd = cmd;
-	op.arg1.mfn = pfn_to_mfn(pfn);
-	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-		BUG();
-}
-
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
@@ -1815,7 +1927,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	 * mappings. Considering that on Xen after the kernel mappings we
 	 * have the mappings of some pages that don't exist in pfn space, we
 	 * set max_pfn_mapped to the last real pfn mapped. */
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+	if (xen_start_info->mfn_list < __START_KERNEL_map)
+		max_pfn_mapped = xen_start_info->first_p2m_pfn;
+	else
+		max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
 
 	pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
 	pt_end = pt_base + xen_start_info->nr_pt_frames;
@@ -1855,6 +1970,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
+	/* Copy the initial P->M table mappings if necessary. */
+	i = pgd_index(xen_start_info->mfn_list);
+	if (i && i < pgd_index(__START_KERNEL_map))
+		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
+
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1894,10 +2014,192 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		check_pt_base(&pt_base, &pt_end, addr[i]);
 
 	/* Our (by three pages) smaller Xen pagetable that we are using */
-	memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+	xen_pt_base = PFN_PHYS(pt_base);
+	xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
+	memblock_reserve(xen_pt_base, xen_pt_size);
+
 	/* Revector the xen_start_info */
 	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
 }
+
+/*
+ * Read a value from a physical address.
+ */
+static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
+{
+	unsigned long *vaddr;
+	unsigned long val;
+
+	vaddr = early_memremap_ro(addr, sizeof(val));
+	val = *vaddr;
+	early_memunmap(vaddr, sizeof(val));
+	return val;
+}
+
+/*
+ * Translate a virtual address to a physical one without relying on mapped
+ * page tables.
+ */
+static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
+{
+	phys_addr_t pa;
+	pgd_t pgd;
+	pud_t pud;
+	pmd_t pmd;
+	pte_t pte;
+
+	pa = read_cr3();
+	pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) *
+						       sizeof(pgd)));
+	if (!pgd_present(pgd))
+		return 0;
+
+	pa = pgd_val(pgd) & PTE_PFN_MASK;
+	pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) *
+						       sizeof(pud)));
+	if (!pud_present(pud))
+		return 0;
+	pa = pud_pfn(pud) << PAGE_SHIFT;
+	if (pud_large(pud))
+		return pa + (vaddr & ~PUD_MASK);
+
+	pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
+						       sizeof(pmd)));
+	if (!pmd_present(pmd))
+		return 0;
+	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	if (pmd_large(pmd))
+		return pa + (vaddr & ~PMD_MASK);
+
+	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
+						       sizeof(pte)));
+	if (!pte_present(pte))
+		return 0;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+
+	return pa | (vaddr & ~PAGE_MASK);
+}
+
+/*
+ * Find a new area for the hypervisor supplied p2m list and relocate the p2m to
+ * this area.
+ */
+void __init xen_relocate_p2m(void)
+{
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
+	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
+	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
+	pte_t *pt;
+	pmd_t *pmd;
+	pud_t *pud;
+	pgd_t *pgd;
+	unsigned long *new_p2m;
+
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
+	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
+	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
+	n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	n_frames = n_pte + n_pt + n_pmd + n_pud;
+
+	new_area = xen_find_free_area(PFN_PHYS(n_frames));
+	if (!new_area) {
+		xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
+		BUG();
+	}
+
+	/*
+	 * Setup the page tables for addressing the new p2m list.
+	 * We have asked the hypervisor to map the p2m list at the user address
+	 * PUD_SIZE. It may have done so, or it may have used a kernel space
+	 * address depending on the Xen version.
+	 * To avoid any possible virtual address collision, just use
+	 * 2 * PUD_SIZE for the new area.
+	 */
+	pud_phys = new_area;
+	pmd_phys = pud_phys + PFN_PHYS(n_pud);
+	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
+	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
+
+	pgd = __va(read_cr3());
+	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
+	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+		pud = early_memremap(pud_phys, PAGE_SIZE);
+		clear_page(pud);
+		for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+		     idx_pmd++) {
+			pmd = early_memremap(pmd_phys, PAGE_SIZE);
+			clear_page(pmd);
+			for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+			     idx_pt++) {
+				pt = early_memremap(pt_phys, PAGE_SIZE);
+				clear_page(pt);
+				for (idx_pte = 0;
+				     idx_pte < min(n_pte, PTRS_PER_PTE);
+				     idx_pte++) {
+					set_pte(pt + idx_pte,
+						pfn_pte(p2m_pfn, PAGE_KERNEL));
+					p2m_pfn++;
+				}
+				n_pte -= PTRS_PER_PTE;
+				early_memunmap(pt, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pt_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+						  PFN_DOWN(pt_phys));
+				set_pmd(pmd + idx_pt,
+					__pmd(_PAGE_TABLE | pt_phys));
+				pt_phys += PAGE_SIZE;
+			}
+			n_pt -= PTRS_PER_PMD;
+			early_memunmap(pmd, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pmd_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+					  PFN_DOWN(pmd_phys));
+			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+			pmd_phys += PAGE_SIZE;
+		}
+		n_pmd -= PTRS_PER_PUD;
+		early_memunmap(pud, PAGE_SIZE);
+		make_lowmem_page_readonly(__va(pud_phys));
+		pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+		set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+		pud_phys += PAGE_SIZE;
+	}
+
+	/* Now copy the old p2m info to the new area. */
+	memcpy(new_p2m, xen_p2m_addr, size);
+	xen_p2m_addr = new_p2m;
+
+	/* Release the old p2m list and set new list info. */
+	p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
+	BUG_ON(!p2m_pfn);
+	p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
+
+	if (xen_start_info->mfn_list < __START_KERNEL_map) {
+		pfn = xen_start_info->first_p2m_pfn;
+		pfn_end = xen_start_info->first_p2m_pfn +
+			  xen_start_info->nr_p2m_frames;
+		set_pgd(pgd + 1, __pgd(0));
+	} else {
+		pfn = p2m_pfn;
+		pfn_end = p2m_pfn_end;
+	}
+
+	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
+	while (pfn < pfn_end) {
+		if (pfn == p2m_pfn) {
+			pfn = p2m_pfn_end;
+			continue;
+		}
+		make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+		pfn++;
+	}
+
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+	xen_start_info->first_p2m_pfn =  PFN_DOWN(new_area);
+	xen_start_info->nr_p2m_frames = n_frames;
+}
+
 #else	/* !CONFIG_X86_64 */
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
 static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
@@ -1938,18 +2240,41 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
+/*
+ * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
+ * not the first page table in the page table pool.
+ * Iterate through the initial page tables to find the real page table base.
+ */
+static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+{
+	phys_addr_t pt_base, paddr;
+	unsigned pmdidx;
+
+	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
+
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
+		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
+			paddr = m2p(pmd[pmdidx].pmd);
+			pt_base = min(pt_base, paddr);
+		}
+
+	return pt_base;
+}
+
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
+	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+
+	xen_pt_base = xen_find_pt_base(kernel_pmd);
+	xen_pt_size = xen_start_info->nr_pt_frames * 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);
+	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
 
-	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	copy_page(initial_kernel_pmd, kernel_pmd);
 
 	xen_map_identity_early(initial_kernel_pmd, max_pfn);
@@ -1968,11 +2293,33 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 			  PFN_DOWN(__pa(initial_page_table)));
 	xen_write_cr3(__pa(initial_page_table));
 
-	memblock_reserve(__pa(xen_start_info->pt_base),
-			 xen_start_info->nr_pt_frames * PAGE_SIZE);
+	memblock_reserve(xen_pt_base, xen_pt_size);
 }
 #endif	/* CONFIG_X86_64 */
 
+void __init xen_reserve_special_pages(void)
+{
+	phys_addr_t paddr;
+
+	memblock_reserve(__pa(xen_start_info), PAGE_SIZE);
+	if (xen_start_info->store_mfn) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+	if (!xen_initial_domain()) {
+		paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn));
+		memblock_reserve(paddr, PAGE_SIZE);
+	}
+}
+
+void __init xen_pt_check_e820(void)
+{
+	if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
+		xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
+		BUG();
+	}
+}
+
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
 
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b7f18e200aa..bfc08b13044b 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -79,10 +79,14 @@
 #include <xen/balloon.h>
 #include <xen/grant_table.h>
 
-#include "p2m.h"
 #include "multicalls.h"
 #include "xen-ops.h"
 
+#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)
+
 #define PMDS_PER_MID_PAGE	(P2M_MID_PER_PAGE / PTRS_PER_PTE)
 
 unsigned long *xen_p2m_addr __read_mostly;
@@ -199,7 +203,8 @@ void __ref xen_build_mfn_list_list(void)
 	unsigned int level, topidx, mididx;
 	unsigned long *mid_mfn_p;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	if (xen_feature(XENFEAT_auto_translated_physmap) ||
+	    xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
 		return;
 
 	/* Pre-initialize p2m_top_mfn to be completely missing */
@@ -260,9 +265,16 @@ 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);
+	if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS)
+		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = ~0UL;
+	else
+		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;
+	HYPERVISOR_shared_info->arch.p2m_generation = 0;
+	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
+	HYPERVISOR_shared_info->arch.p2m_cr3 =
+		xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
 }
 
 /* Set up p2m_top to point to the domain-builder provided p2m pages */
@@ -478,8 +490,12 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
 
 		ptechk = lookup_address(vaddr, &level);
 		if (ptechk == pte_pg) {
+			HYPERVISOR_shared_info->arch.p2m_generation++;
+			wmb(); /* Tools are synchronizing via p2m_generation. */
 			set_pmd(pmdp,
 				__pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
+			wmb(); /* Tools are synchronizing via p2m_generation. */
+			HYPERVISOR_shared_info->arch.p2m_generation++;
 			pte_newpg[i] = NULL;
 		}
 
@@ -505,7 +521,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
  */
 static bool alloc_p2m(unsigned long pfn)
 {
-	unsigned topidx, mididx;
+	unsigned topidx;
 	unsigned long *top_mfn_p, *mid_mfn;
 	pte_t *ptep, *pte_pg;
 	unsigned int level;
@@ -513,9 +529,6 @@ static bool alloc_p2m(unsigned long pfn)
 	unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
 	unsigned long p2m_pfn;
 
-	topidx = p2m_top_index(pfn);
-	mididx = p2m_mid_index(pfn);
-
 	ptep = lookup_address(addr, &level);
 	BUG_ON(!ptep || level != PG_LEVEL_4K);
 	pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
@@ -527,7 +540,8 @@ static bool alloc_p2m(unsigned long pfn)
 			return false;
 	}
 
-	if (p2m_top_mfn) {
+	if (p2m_top_mfn && pfn < MAX_P2M_PFN) {
+		topidx = p2m_top_index(pfn);
 		top_mfn_p = &p2m_top_mfn[topidx];
 		mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]);
 
@@ -577,10 +591,14 @@ static bool alloc_p2m(unsigned long pfn)
 		spin_lock_irqsave(&p2m_update_lock, flags);
 
 		if (pte_pfn(*ptep) == p2m_pfn) {
+			HYPERVISOR_shared_info->arch.p2m_generation++;
+			wmb(); /* Tools are synchronizing via p2m_generation. */
 			set_pte(ptep,
 				pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL));
+			wmb(); /* Tools are synchronizing via p2m_generation. */
+			HYPERVISOR_shared_info->arch.p2m_generation++;
 			if (mid_mfn)
-				mid_mfn[mididx] = virt_to_mfn(p2m);
+				mid_mfn[p2m_mid_index(pfn)] = virt_to_mfn(p2m);
 			p2m = NULL;
 		}
 
@@ -630,6 +648,11 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 		return true;
 	}
 
+	/*
+	 * The interface requires atomic updates on p2m elements.
+	 * xen_safe_write_ulong() is using __put_user which does an atomic
+	 * store via asm().
+	 */
 	if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
 		return true;
 
diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h
deleted file mode 100644
index ad8aee24ab72..000000000000
--- a/arch/x86/xen/p2m.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _XEN_P2M_H
-#define _XEN_P2M_H
-
-#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)
-
-#define MAX_REMAP_RANGES    10
-
-extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
-                                      unsigned long pfn_e);
-
-#endif  /* _XEN_P2M_H */
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index a8261716d58d..9586ff32810c 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -68,7 +68,7 @@ static int check_platform_magic(void)
 	return 0;
 }
 
-bool xen_has_pv_devices()
+bool xen_has_pv_devices(void)
 {
 	if (!xen_domain())
 		return false;
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
new file mode 100644
index 000000000000..724a08740a04
--- /dev/null
+++ b/arch/x86/xen/pmu.c
@@ -0,0 +1,570 @@
+#include <linux/types.h>
+#include <linux/interrupt.h>
+
+#include <asm/xen/hypercall.h>
+#include <xen/page.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/vcpu.h>
+#include <xen/interface/xenpmu.h>
+
+#include "xen-ops.h"
+#include "pmu.h"
+
+/* x86_pmu.handle_irq definition */
+#include "../kernel/cpu/perf_event.h"
+
+#define XENPMU_IRQ_PROCESSING    1
+struct xenpmu {
+	/* Shared page between hypervisor and domain */
+	struct xen_pmu_data *xenpmu_data;
+
+	uint8_t flags;
+};
+static DEFINE_PER_CPU(struct xenpmu, xenpmu_shared);
+#define get_xenpmu_data()    (this_cpu_ptr(&xenpmu_shared)->xenpmu_data)
+#define get_xenpmu_flags()   (this_cpu_ptr(&xenpmu_shared)->flags)
+
+/* Macro for computing address of a PMU MSR bank */
+#define field_offset(ctxt, field) ((void *)((uintptr_t)ctxt + \
+					    (uintptr_t)ctxt->field))
+
+/* AMD PMU */
+#define F15H_NUM_COUNTERS   6
+#define F10H_NUM_COUNTERS   4
+
+static __read_mostly uint32_t amd_counters_base;
+static __read_mostly uint32_t amd_ctrls_base;
+static __read_mostly int amd_msr_step;
+static __read_mostly int k7_counters_mirrored;
+static __read_mostly int amd_num_counters;
+
+/* Intel PMU */
+#define MSR_TYPE_COUNTER            0
+#define MSR_TYPE_CTRL               1
+#define MSR_TYPE_GLOBAL             2
+#define MSR_TYPE_ARCH_COUNTER       3
+#define MSR_TYPE_ARCH_CTRL          4
+
+/* Number of general pmu registers (CPUID.EAX[0xa].EAX[8..15]) */
+#define PMU_GENERAL_NR_SHIFT        8
+#define PMU_GENERAL_NR_BITS         8
+#define PMU_GENERAL_NR_MASK         (((1 << PMU_GENERAL_NR_BITS) - 1) \
+				     << PMU_GENERAL_NR_SHIFT)
+
+/* Number of fixed pmu registers (CPUID.EDX[0xa].EDX[0..4]) */
+#define PMU_FIXED_NR_SHIFT          0
+#define PMU_FIXED_NR_BITS           5
+#define PMU_FIXED_NR_MASK           (((1 << PMU_FIXED_NR_BITS) - 1) \
+				     << PMU_FIXED_NR_SHIFT)
+
+/* Alias registers (0x4c1) for full-width writes to PMCs */
+#define MSR_PMC_ALIAS_MASK          (~(MSR_IA32_PERFCTR0 ^ MSR_IA32_PMC0))
+
+#define INTEL_PMC_TYPE_SHIFT        30
+
+static __read_mostly int intel_num_arch_counters, intel_num_fixed_counters;
+
+
+static void xen_pmu_arch_init(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+
+		switch (boot_cpu_data.x86) {
+		case 0x15:
+			amd_num_counters = F15H_NUM_COUNTERS;
+			amd_counters_base = MSR_F15H_PERF_CTR;
+			amd_ctrls_base = MSR_F15H_PERF_CTL;
+			amd_msr_step = 2;
+			k7_counters_mirrored = 1;
+			break;
+		case 0x10:
+		case 0x12:
+		case 0x14:
+		case 0x16:
+		default:
+			amd_num_counters = F10H_NUM_COUNTERS;
+			amd_counters_base = MSR_K7_PERFCTR0;
+			amd_ctrls_base = MSR_K7_EVNTSEL0;
+			amd_msr_step = 1;
+			k7_counters_mirrored = 0;