Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	net/netfilter/nfnetlink_log.c
	net/netfilter/xt_LOG.c

Rather easy conflict resolution, the 'net' tree had bug fixes to make
sure we checked if a socket is a time-wait one or not and elide the
logging code if so.

Whereas on the 'net-next' side we are calculating the UID and GID from
the creds using different interfaces due to the user namespace changes
from Eric Biederman.

Signed-off-by: David S. Miller <davem@davemloft.net>

18 files changed, 190 insertions, 145 deletions

diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b315a33..33692ea 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -12,8 +12,7 @@
  * Simple spin lock operations.  There are two variants, one clears IRQ's
  * on the local processor, one does not.
  *
- * These are fair FIFO ticket locks, which are currently limited to 256
- * CPUs.
+ * These are fair FIFO ticket locks, which support up to 2^16 CPUs.
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index afb7ff7..ced4534 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -165,7 +165,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
 #endif
 
 #ifdef P6_NOP1
-static const unsigned char  __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
 {
 	P6_NOP1,
 	P6_NOP2,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e..0d3d63a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b426..da02e9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7ad683d..d44f782 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -270,7 +270,7 @@ void fixup_irqs(void)
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
-			affinity = cpu_all_mask;
+			affinity = cpu_online_mask;
 		}
 
 		chip = irq_data_get_irq_chip(data);
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 8a2ce8f..82746f9 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -143,11 +143,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 				  unsigned int *current_size)
 {
 	struct microcode_header_amd *mc_hdr;
-	unsigned int actual_size;
+	unsigned int actual_size, patch_size;
 	u16 equiv_cpu_id;
 
 	/* size of the current patch we're staring at */
-	*current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+	patch_size = *(u32 *)(ucode_ptr + 4);
+	*current_size = patch_size + SECTION_HDR_SIZE;
 
 	equiv_cpu_id = find_equiv_id();
 	if (!equiv_cpu_id)
@@ -174,7 +175,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 	/*
 	 * now that the header looks sane, verify its size
 	 */
-	actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+	actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
 	if (!actual_size)
 		return 0;
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62..9e5bcf1 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97d9a99..a3b57a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg)
 	return address_mask(ctxt, reg);
 }
 
+static void masked_increment(ulong *reg, ulong mask, int inc)
+{
+	assign_masked(reg, *reg + inc, mask);
+}
+
 static inline void
 register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
 {
+	ulong mask;
+
 	if (ctxt->ad_bytes == sizeof(unsigned long))
-		*reg += inc;
+		mask = ~0UL;
 	else
-		*reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt));
+		mask = ad_mask(ctxt);
+	masked_increment(reg, mask, inc);
+}
+
+static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
+{
+	masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc);
 }
 
 static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes)
 {
 	struct segmented_address addr;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes);
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	rsp_increment(ctxt, -bytes);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 
 	return segmented_write(ctxt, addr, data, bytes);
@@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt,
 	int rc;
 	struct segmented_address addr;
 
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 	rc = segmented_read(ctxt, addr, dest, len);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len);
+	rsp_increment(ctxt, len);
 	return rc;
 }
 
@@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
 
 	while (reg >= VCPU_REGS_RAX) {
 		if (reg == VCPU_REGS_RSP) {
-			register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP],
-							ctxt->op_bytes);
+			rsp_increment(ctxt, ctxt->op_bytes);
 			--reg;
 		}
 
@@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val);
+	rsp_increment(ctxt, ctxt->src.val);
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18..9fc9aa7 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 		if (val & 0x10) {
 			u8 edge_irr = s->irr & ~s->elcr;
 			int i;
-			bool found;
+			bool found = false;
 			struct kvm_vcpu *vcpu;
 
 			s->init4 = val & 1;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01ca004..7fbd0d2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4113,16 +4113,21 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 		LIST_HEAD(invalid_list);
 
 		/*
+		 * Never scan more than sc->nr_to_scan VM instances.
+		 * Will not hit this condition practically since we do not try
+		 * to shrink more than one VM and it is very unlikely to see
+		 * !n_used_mmu_pages so many times.
+		 */
+		if (!nr_to_scan--)
+			break;
+		/*
 		 * n_used_mmu_pages is accessed without holding kvm->mmu_lock
 		 * here. We may skip a VM instance errorneosly, but we do not
 		 * want to shrink a VM that only started to populate its MMU
 		 * anyway.
 		 */
-		if (kvm->arch.n_used_mmu_pages > 0) {
-			if (!nr_to_scan--)
-				break;
+		if (!kvm->arch.n_used_mmu_pages)
 			continue;
-		}
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03d..b1eb202 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3619,6 +3619,7 @@ static void seg_setup(int seg)
 
 static int alloc_apic_access_page(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3633,7 +3634,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, 0xfee00);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.apic_access_page = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -3641,6 +3648,7 @@ out:
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3656,8 +3664,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
-			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.ept_identity_pagetable = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -6575,7 +6588,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6598,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 		if (best)
-			best->ecx &= ~bit(X86_FEATURE_INVPCID);
+			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 42bce48..2966c84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
@@ -2000,6 +2000,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_KVM_STEAL_TIME:
 		data = vcpu->arch.st.msr_val;
 		break;
+	case MSR_KVM_PV_EOI_EN:
+		data = vcpu->arch.pv_eoi.msr_val;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:
@@ -5110,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct page *page;
 
 	if (!apic || !apic->vapic_addr)
-		return;
+		return 0;
 
 	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
 
 	vcpu->arch.apic->vapic_page = page;
+	return 0;
 }
 
 static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5427,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
+	r = vapic_enter(vcpu);
+	if (r) {
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		return r;
+	}
 
 	r = 1;
 	while (r > 0) {
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bf4bda6..9642d4a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,7 +31,6 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/syscore_ops.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -1470,130 +1469,38 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-#ifdef CONFIG_XEN_PVHVM
-/*
- * The pfn containing the shared_info is located somewhere in RAM. This
- * will cause trouble if the current kernel is doing a kexec boot into a
- * new kernel. The new kernel (and its startup code) can not know where
- * the pfn is, so it can not reserve the page. The hypervisor will
- * continue to update the pfn, and as a result memory corruption occours
- * in the new kernel.
- *
- * One way to work around this issue is to allocate a page in the
- * xen-platform pci device's BAR memory range. But pci init is done very
- * late and the shared_info page is already in use very early to read
- * the pvclock. So moving the pfn from RAM to MMIO is racy because some
- * code paths on other vcpus could access the pfn during the small
- * window when the old pfn is moved to the new pfn. There is even a
- * small window were the old pfn is not backed by a mfn, and during that
- * time all reads return -1.
- *
- * Because it is not known upfront where the MMIO region is located it
- * can not be used right from the start in xen_hvm_init_shared_info.
- *
- * To minimise trouble the move of the pfn is done shortly before kexec.
- * This does not eliminate the race because all vcpus are still online
- * when the syscore_ops will be called. But hopefully there is no work
- * pending at this point in time. Also the syscore_op is run last which
- * reduces the risk further.
- */
-
-static struct shared_info *xen_hvm_shared_info;
-
-static void xen_hvm_connect_shared_info(unsigned long pfn)
+void __ref xen_hvm_init_shared_info(void)
 {
+	int cpu;
 	struct xen_add_to_physmap xatp;
+	static struct shared_info *shared_info_page = 0;
 
+	if (!shared_info_page)
+		shared_info_page = (struct shared_info *)
+			extend_brk(PAGE_SIZE, PAGE_SIZE);
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = pfn;
+	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 
-}
-static void xen_hvm_set_shared_info(struct shared_info *sip)
-{
-	int cpu;
-
-	HYPERVISOR_shared_info = sip;
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
 
 	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
 	 * page, we use it in the event channel upcall and in some pvclock
 	 * related functions. We don't need the vcpu_info placement
 	 * optimizations because we don't use any pv_mmu or pv_irq op on
 	 * HVM.
-	 * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is
-	 * online but xen_hvm_set_shared_info is run at resume time too and
+	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+	 * online but xen_hvm_init_shared_info is run at resume time too and
 	 * in that case multiple vcpus might be online. */
 	for_each_online_cpu(cpu) {
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 	}
 }
 
-/* Reconnect the shared_info pfn to a mfn */
-void xen_hvm_resume_shared_info(void)
-{
-	xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-}
-
-#ifdef CONFIG_KEXEC
-static struct shared_info *xen_hvm_shared_info_kexec;
-static unsigned long xen_hvm_shared_info_pfn_kexec;
-
-/* Remember a pfn in MMIO space for kexec reboot */
-void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn)
-{
-	xen_hvm_shared_info_kexec = sip;
-	xen_hvm_shared_info_pfn_kexec = pfn;
-}
-
-static void xen_hvm_syscore_shutdown(void)
-{
-	struct xen_memory_reservation reservation = {
-		.domid = DOMID_SELF,
-		.nr_extents = 1,
-	};
-	unsigned long prev_pfn;
-	int rc;
-
-	if (!xen_hvm_shared_info_kexec)
-		return;
-
-	prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT;
-	set_xen_guest_handle(reservation.extent_start, &prev_pfn);
-
-	/* Move pfn to MMIO, disconnects previous pfn from mfn */
-	xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec);
-
-	/* Update pointers, following hypercall is also a memory barrier */
-	xen_hvm_set_shared_info(xen_hvm_shared_info_kexec);
-
-	/* Allocate new mfn for previous pfn */
-	do {
-		rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
-		if (rc == 0)
-			msleep(123);
-	} while (rc == 0);
-
-	/* Make sure the previous pfn is really connected to a (new) mfn */
-	BUG_ON(rc != 1);
-}
-
-static struct syscore_ops xen_hvm_syscore_ops = {
-	.shutdown = xen_hvm_syscore_shutdown,
-};
-#endif
-
-/* Use a pfn in RAM, may move to MMIO before kexec. */
-static void __init xen_hvm_init_shared_info(void)
-{
-	/* Remember pointer for resume */
-	xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-	xen_hvm_set_shared_info(xen_hvm_shared_info);
-}
-
+#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -1644,9 +1551,6 @@ static void __init xen_hvm_guest_init(void)
 	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
-#ifdef CONFIG_KEXEC
-	register_syscore_ops(&xen_hvm_syscore_ops);
-#endif
 
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b65a761..5141d80 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1283,7 +1283,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
 		args->op.arg1.linear_addr = start;
 	}
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b2e91d4..76ba0e9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -196,9 +196,11 @@ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
 
 /* When we populate back during bootup, the amount of pages can vary. The
  * max we have is seen is 395979, but that does not mean it can't be more.
- * But some machines can have 3GB I/O holes even. So lets reserve enough
- * for 4GB of I/O and E820 holes. */
-RESERVE_BRK(p2m_populated, PMD_SIZE * 4);
+ * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
+ * it can re-use Xen provided mfn_list array, so we only need to allocate at
+ * most three P2M top nodes. */
+RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -575,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn)
 	}
 	return true;
 }
+
+/*
+ * Skim over the P2M tree looking at pages that are either filled with
+ * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
+ * replace the P2M leaf with a p2m_missing or p2m_identity.
+ * Stick the old page in the new P2M tree location.
+ */
+bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
+{
+	unsigned topidx;
+	unsigned mididx;
+	unsigned ident_pfns;
+	unsigned inv_pfns;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
+	unsigned idx;
+	unsigned long pfn;
+
+	/* We only look when this entails a P2M middle layer */
+	if (p2m_index(set_pfn))
+		return false;
+
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+		topidx = p2m_top_index(pfn);
+
+		if (!p2m_top[topidx])
+			continue;
+
+		if (p2m_top[topidx] == p2m_mid_missing)
+			continue;
+
+		mididx = p2m_mid_index(pfn);
+		p2m = p2m_top[topidx][mididx];
+		if (!p2m)
+			continue;
+
+		if ((p2m == p2m_missing) || (p2m == p2m_identity))
+			continue;
+
+		if ((unsigned long)p2m == INVALID_P2M_ENTRY)
+			continue;
+
+		ident_pfns = 0;
+		inv_pfns = 0;
+		for (idx = 0; idx < P2M_PER_PAGE; idx++) {
+			/* IDENTITY_PFNs are 1:1 */
+			if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
+				ident_pfns++;
+			else if (p2m[idx] == INVALID_P2M_ENTRY)
+				inv_pfns++;
+			else
+				break;
+		}
+		if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
+			goto found;
+	}
+	return false;
+found:
+	/* Found one, replace old with p2m_identity or p2m_missing */
+	p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
+	/* And the other for save/restore.. */
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	/* NOTE: Even if it is a p2m_identity it should still be point to
+	 * a page filled with INVALID_P2M_ENTRY entries. */
+	mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);
+
+	/* Reset where we want to stick the old page in. */
+	topidx = p2m_top_index(set_pfn);
+	mididx = p2m_mid_index(set_pfn);
+
+	/* This shouldn't happen */
+	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
+		early_alloc_p2m(set_pfn);
+
+	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
+		return false;
+
+	p2m_init(p2m);
+	p2m_top[topidx][mididx] = p2m;
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
 bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
 		if (!early_alloc_p2m(pfn))
 			return false;
 
+		if (early_can_reuse_p2m_middle(pfn, mfn))
+			return __set_phys_to_machine(pfn, mfn);
+
 		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
 			return false;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index ead8557..d11ca11 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	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(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+			continue;
+		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			pfn, mfn);
 
-	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
 }
 
 static unsigned long __init xen_do_chunk(unsigned long start,
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index ae8a00c..45329c8 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
-	xen_hvm_resume_shared_info();
+	xen_hvm_init_shared_info();
 	xen_callback_vector();
 	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 1e4329e..202d4c1 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -41,7 +41,7 @@ void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_resume_shared_info(void);
+void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);