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
  ...

23 files changed, 1679 insertions, 250 deletions

diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h
index 8b1f37bfeeec..71e473d05fcc 100644
--- a/arch/arm/include/asm/xen/events.h
+++ b/arch/arm/include/asm/xen/events.h
@@ -20,4 +20,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 							    atomic64_t,	\
 							    counter), (val))
 
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
 #endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 1bee8ca12494..98b1084f8282 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -54,26 +54,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 
 #define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
 
-static inline xmaddr_t phys_to_machine(xpaddr_t phys)
-{
-	unsigned offset = phys.paddr & ~PAGE_MASK;
-	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
-}
-
-static inline xpaddr_t machine_to_phys(xmaddr_t machine)
-{
-	unsigned offset = machine.maddr & ~PAGE_MASK;
-	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
-}
 /* VIRT <-> MACHINE conversion */
-#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
 #define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
+/* Only used in PV code. But ARM guests are always HVM. */
 static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 {
-	/* TODO: assuming it is mapped in the kernel 1:1 */
-	return virt_to_machine(vaddr);
+	BUG();
 }
 
 /* TODO: this shouldn't be here but it is because the frontend drivers
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 6c09cc440a2b..c50c8d33f874 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -45,13 +45,6 @@ static struct vcpu_info __percpu *xen_vcpu_info;
 unsigned long xen_released_pages;
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
-/* TODO: to be removed */
-__read_mostly int xen_have_vector_callback;
-EXPORT_SYMBOL_GPL(xen_have_vector_callback);
-
-int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
-EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
-
 static __read_mostly unsigned int xen_events_irq;
 
 static __initdata struct device_node *xen_node;
diff --git a/arch/arm64/include/asm/xen/events.h b/arch/arm64/include/asm/xen/events.h
index 86553213c132..4318866d053c 100644
--- a/arch/arm64/include/asm/xen/events.h
+++ b/arch/arm64/include/asm/xen/events.h
@@ -18,4 +18,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
 #endif /* _ASM_ARM64_XEN_EVENTS_H */
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 608a79d5a466..e6911caf5bbf 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -20,4 +20,15 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 /* No need for a barrier -- XCHG is a barrier on x86. */
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
+extern int xen_have_vector_callback;
+
+/*
+ * Events delivered via platform PCI interrupts are always
+ * routed to vcpu 0 and hence cannot be rebound.
+ */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return (!xen_hvm_domain() || xen_have_vector_callback);
+}
+
 #endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index ca08a27b90b3..83aea8055119 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -465,6 +465,12 @@ HYPERVISOR_tmem_op(
 	return _hypercall1(int, tmem_op, op);
 }
 
+static inline int
+HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
+{
+	return _hypercall2(int, xenpmu_op, op, arg);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 3400dbaec3c3..62ca03ef5c65 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -3,12 +3,38 @@
  *
  * Guest OS interface to x86 Xen.
  *
- * Copyright (c) 2004, K A Fraser
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2004-2006, K A Fraser
  */
 
 #ifndef _ASM_X86_XEN_INTERFACE_H
 #define _ASM_X86_XEN_INTERFACE_H
 
+/*
+ * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field
+ * in a struct in memory.
+ * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an
+ * hypercall argument.
+ * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but
+ * they might not be on other architectures.
+ */
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
     typedef struct { type *p; } __guest_handle_ ## name
@@ -88,13 +114,16 @@ DEFINE_GUEST_HANDLE(xen_ulong_t);
  * start of the GDT because some stupid OSes export hard-coded selector values
  * in their ABI. These hard-coded values are always near the start of the GDT,
  * so Xen places itself out of the way, at the far end of the GDT.
+ *
+ * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op
  */
 #define FIRST_RESERVED_GDT_PAGE  14
 #define FIRST_RESERVED_GDT_BYTE  (FIRST_RESERVED_GDT_PAGE * 4096)
 #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
 
 /*
- * Send an array of these to HYPERVISOR_set_trap_table()
+ * Send an array of these to HYPERVISOR_set_trap_table().
+ * Terminate the array with a sentinel entry, with traps[].address==0.
  * The privilege level specifies which modes may enter a trap via a software
  * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
  * privilege levels as follows:
@@ -118,10 +147,41 @@ struct trap_info {
 DEFINE_GUEST_HANDLE_STRUCT(trap_info);
 
 struct arch_shared_info {
-    unsigned long max_pfn;                  /* max pfn that appears in table */
-    /* Frame containing list of mfns containing list of mfns containing p2m. */
-    unsigned long pfn_to_mfn_frame_list_list;
-    unsigned long nmi_reason;
+	/*
+	 * Number of valid entries in the p2m table(s) anchored at
+	 * pfn_to_mfn_frame_list_list and/or p2m_vaddr.
+	 */
+	unsigned long max_pfn;
+	/*
+	 * Frame containing list of mfns containing list of mfns containing p2m.
+	 * A value of 0 indicates it has not yet been set up, ~0 indicates it
+	 * has been set to invalid e.g. due to the p2m being too large for the
+	 * 3-level p2m tree. In this case the linear mapper p2m list anchored
+	 * at p2m_vaddr is to be used.
+	 */
+	xen_pfn_t pfn_to_mfn_frame_list_list;
+	unsigned long nmi_reason;
+	/*
+	 * Following three fields are valid if p2m_cr3 contains a value
+	 * different from 0.
+	 * p2m_cr3 is the root of the address space where p2m_vaddr is valid.
+	 * p2m_cr3 is in the same format as a cr3 value in the vcpu register
+	 * state and holds the folded machine frame number (via xen_pfn_to_cr3)
+	 * of a L3 or L4 page table.
+	 * p2m_vaddr holds the virtual address of the linear p2m list. All
+	 * entries in the range [0...max_pfn[ are accessible via this pointer.
+	 * p2m_generation will be incremented by the guest before and after each
+	 * change of the mappings of the p2m list. p2m_generation starts at 0
+	 * and a value with the least significant bit set indicates that a
+	 * mapping update is in progress. This allows guest external software
+	 * (e.g. in Dom0) to verify that read mappings are consistent and
+	 * whether they have changed since the last check.
+	 * Modifying a p2m element in the linear p2m list is allowed via an
+	 * atomic write only.
+	 */
+	unsigned long p2m_cr3;		/* cr3 value of the p2m address space */
+	unsigned long p2m_vaddr;	/* virtual address of the p2m list */
+	unsigned long p2m_generation;	/* generation count of p2m mapping */
 };
 #endif	/* !__ASSEMBLY__ */
 
@@ -137,13 +197,31 @@ struct arch_shared_info {
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
+ *
+ * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise
+ * for HVM and PVH guests, not all information in this structure is updated:
+ *
+ * - For HVM guests, the structures read include: fpu_ctxt (if
+ * VGCT_I387_VALID is set), flags, user_regs, debugreg[*]
+ *
+ * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to
+ * set cr3. All other fields not used should be set to 0.
  */
 struct vcpu_guest_context {
     /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
     struct { char x[512]; } fpu_ctxt;       /* User-level FPU registers     */
-#define VGCF_I387_VALID (1<<0)
-#define VGCF_HVM_GUEST  (1<<1)
-#define VGCF_IN_KERNEL  (1<<2)
+#define VGCF_I387_VALID                (1<<0)
+#define VGCF_IN_KERNEL                 (1<<2)
+#define _VGCF_i387_valid               0
+#define VGCF_i387_valid                (1<<_VGCF_i387_valid)
+#define _VGCF_in_kernel                2
+#define VGCF_in_kernel                 (1<<_VGCF_in_kernel)
+#define _VGCF_failsafe_disables_events 3
+#define VGCF_failsafe_disables_events  (1<<_VGCF_failsafe_disables_events)
+#define _VGCF_syscall_disables_events  4
+#define VGCF_syscall_disables_events   (1<<_VGCF_syscall_disables_events)
+#define _VGCF_online                   5
+#define VGCF_online                    (1<<_VGCF_online)
     unsigned long flags;                    /* VGCF_* flags                 */
     struct cpu_user_regs user_regs;         /* User-level CPU registers     */
     struct trap_info trap_ctxt[256];        /* Virtual IDT                  */
@@ -172,6 +250,129 @@ struct vcpu_guest_context {
 #endif
 };
 DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
+
+/* AMD PMU registers and structures */
+struct xen_pmu_amd_ctxt {
+	/*
+	 * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd).
+	 * For PV(H) guests these fields are RO.
+	 */
+	uint32_t counters;
+	uint32_t ctrls;
+
+	/* Counter MSRs */
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+	uint64_t regs[];
+#elif defined(__GNUC__)
+	uint64_t regs[0];
+#endif
+};
+
+/* Intel PMU registers and structures */
+struct xen_pmu_cntr_pair {
+	uint64_t counter;
+	uint64_t control;
+};
+
+struct xen_pmu_intel_ctxt {
+	/*
+	 * Offsets to fixed and architectural counter MSRs (relative to
+	 * xen_pmu_arch.c.intel).
+	 * For PV(H) guests these fields are RO.
+	 */
+	uint32_t fixed_counters;
+	uint32_t arch_counters;
+
+	/* PMU registers */
+	uint64_t global_ctrl;
+	uint64_t global_ovf_ctrl;
+	uint64_t global_status;
+	uint64_t fixed_ctrl;
+	uint64_t ds_area;
+	uint64_t pebs_enable;
+	uint64_t debugctl;
+
+	/* Fixed and architectural counter MSRs */
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+	uint64_t regs[];
+#elif defined(__GNUC__)
+	uint64_t regs[0];
+#endif
+};
+
+/* Sampled domain's registers */
+struct xen_pmu_regs {
+	uint64_t ip;
+	uint64_t sp;
+	uint64_t flags;
+	uint16_t cs;
+	uint16_t ss;
+	uint8_t cpl;
+	uint8_t pad[3];
+};
+
+/* PMU flags */
+#define PMU_CACHED	   (1<<0) /* PMU MSRs are cached in the context */
+#define PMU_SAMPLE_USER	   (1<<1) /* Sample is from user or kernel mode */
+#define PMU_SAMPLE_REAL	   (1<<2) /* Sample is from realmode */
+#define PMU_SAMPLE_PV	   (1<<3) /* Sample from a PV guest */
+
+/*
+ * Architecture-specific information describing state of the processor at
+ * the time of PMU interrupt.
+ * Fields of this structure marked as RW for guest should only be written by
+ * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the
+ * hypervisor during PMU interrupt). Hypervisor will read updated data in
+ * XENPMU_flush hypercall and clear PMU_CACHED bit.
+ */
+struct xen_pmu_arch {
+	union {
+		/*
+		 * Processor's registers at the time of interrupt.
+		 * WO for hypervisor, RO for guests.
+		 */
+		struct xen_pmu_regs regs;
+		/*
+		 * Padding for adding new registers to xen_pmu_regs in
+		 * the future
+		 */
+#define XENPMU_REGS_PAD_SZ  64
+		uint8_t pad[XENPMU_REGS_PAD_SZ];
+	} r;
+
+	/* WO for hypervisor, RO for guest */
+	uint64_t pmu_flags;
+
+	/*
+	 * APIC LVTPC register.
+	 * RW for both hypervisor and guest.
+	 * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware
+	 * during XENPMU_flush or XENPMU_lvtpc_set.
+	 */
+	union {
+		uint32_t lapic_lvtpc;
+		uint64_t pad;
+	} l;
+
+	/*
+	 * Vendor-specific PMU registers.
+	 * RW for both hypervisor and guest (see exceptions above).
+	 * Guest's updates to this field are verified and then loaded by the
+	 * hypervisor into hardware during XENPMU_flush
+	 */
+	union {
+		struct xen_pmu_amd_ctxt amd;
+		struct xen_pmu_intel_ctxt intel;
+
+		/*
+		 * Padding for contexts (fixed parts only, does not include
+		 * MSR banks that are specified by offsets)
+		 */
+#define XENPMU_CTXT_PAD_SZ  128
+		uint8_t pad[XENPMU_CTXT_PAD_SZ];
+	} c;
+};
+
 #endif	/* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c44a5d53e464..a3804fbe1f36 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -35,9 +35,7 @@ typedef struct xpaddr {
 #define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
 #define IDENTITY_FRAME(m)	((m) | IDENTITY_FRAME_BIT)
 
-/* Maximum amount of memory we can handle in a domain in pages */
-#define MAX_DOMAIN_PAGES						\
-    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
 
 extern unsigned long *machine_to_phys_mapping;
 extern unsigned long  machine_to_phys_nr;
@@ -48,8 +46,8 @@ 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 __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);
+extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+						    unsigned long pfn_e);
 
 extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
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 initia