Merge tag 'stable/for-linus-3.12-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull Xen updates from Konrad Rzeszutek Wilk:
 "A couple of features and a ton of bug-fixes.  There is also some
  maintership changes.  Jeremy is enjoying the full-time work at the
  startup and as much as he would love to help - he can't find the time.
  I have a bunch of other things that I promised to work on - paravirt
  diet, get SWIOTLB working everywhere, etc, but haven't been able to
  find the time.

  As such both David Vrabel and Boris Ostrovsky have graciously
  volunteered to help with the maintership role.  They will keep the lid
  on regressions, bug-fixes, etc.  I will be in the background to help -
  but eventually there will be less of me doing the Xen GIT pulls and
  more of them.  Stefano is still doing the ARM/ARM64 and will continue
  on doing so.

  Features:
   - Xen Trusted Platform Module (TPM) frontend driver - with the
     backend in MiniOS.
   - Scalability improvements in event channel.
   - Two extra Xen co-maintainers (David, Boris) and one going away (Jeremy)

  Bug-fixes:
   - Make the 1:1 mapping work during early bootup on selective regions.
   - Add scratch page to balloon driver to deal with unexpected code
     still holding on stale pages.
   - Allow NMIs on PV guests (64-bit only)
   - Remove unnecessary TLB flush in M2P code.
   - Fixes duplicate callbacks in Xen granttable code.
   - Fixes in PRIVCMD_MMAPBATCH ioctls to allow retries
   - Fix for events being lost due to rescheduling on different VCPUs.
   - More documentation"

* tag 'stable/for-linus-3.12-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (23 commits)
  hvc_xen: Remove unnecessary __GFP_ZERO from kzalloc
  drivers/xen-tpmfront: Fix compile issue with missing option.
  xen/balloon: don't set P2M entry for auto translated guest
  xen/evtchn: double free on error
  Xen: Fix retry calls into PRIVCMD_MMAPBATCH*.
  xen/pvhvm: Initialize xen panic handler for PVHVM guests
  xen/m2p: use GNTTABOP_unmap_and_replace to reinstate the original mapping
  xen: fix ARM build after 6efa20e4
  MAINTAINERS: Remove Jeremy from the Xen subsystem.
  xen/events: document behaviour when scanning the start word for events
  x86/xen: during early setup, only 1:1 map the ISA region
  x86/xen: disable premption when enabling local irqs
  swiotlb-xen: replace dma_length with sg_dma_len() macro
  swiotlb: replace dma_length with sg_dma_len() macro
  xen/balloon: set a mapping for ballooned out pages
  xen/evtchn: improve scalability by using per-user locks
  xen/p2m: avoid unneccesary TLB flush in m2p_remove_override()
  MAINTAINERS: Add in two extra co-maintainers of the Xen tree.
  MAINTAINERS: Update the Xen subsystem's with proper mailing list.
  xen: replace strict_strtoul() with kstrtoul()
  ...

6 files changed, 66 insertions, 32 deletions

diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index ca842f2769e..608a79d5a46 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -7,6 +7,7 @@ enum ipi_vector {
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 	XEN_SPIN_UNLOCK_VECTOR,
 	XEN_IRQ_WORK_VECTOR,
+	XEN_NMI_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2fcaedc0b73..2fc216dfbd9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -427,8 +427,7 @@ static void __init xen_init_cpuid_mask(void)
 
 	if (!xen_initial_domain())
 		cpuid_leaf1_edx_mask &=
-			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
-			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
+			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */
 
 	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
 
@@ -735,8 +734,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		addr = (unsigned long)xen_int3;
 	else if (addr == (unsigned long)stack_segment)
 		addr = (unsigned long)xen_stack_segment;
-	else if (addr == (unsigned long)double_fault ||
-		 addr == (unsigned long)nmi) {
+	else if (addr == (unsigned long)double_fault) {
 		/* Don't need to handle these */
 		return 0;
 #ifdef CONFIG_X86_MCE
@@ -747,7 +745,12 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		 */
 		;
 #endif
-	} else {
+	} else if (addr == (unsigned long)nmi)
+		/*
+		 * Use the native version as well.
+		 */
+		;
+	else {
 		/* Some other trap using IST? */
 		if (WARN_ON(val->ist != 0))
 			return 0;
@@ -1710,6 +1713,8 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_hvm_init_shared_info();
 
+	xen_panic_handler_init();
+
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 	xen_hvm_smp_init();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 01a4dc015ae..0da7f863056 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -47,23 +47,18 @@ static void xen_restore_fl(unsigned long flags)
 	/* convert from IF type flag */
 	flags = !(flags & X86_EFLAGS_IF);
 
-	/* There's a one instruction preempt window here.  We need to
-	   make sure we're don't switch CPUs between getting the vcpu
-	   pointer and updating the mask. */
+	/* See xen_irq_enable() for why preemption must be disabled. */
 	preempt_disable();
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = flags;
-	preempt_enable_no_resched();
-
-	/* Doesn't matter if we get preempted here, because any
-	   pending event will get dealt with anyway. */
 
 	if (flags == 0) {
-		preempt_check_resched();
 		barrier(); /* unmask then check (avoid races) */
 		if (unlikely(vcpu->evtchn_upcall_pending))
 			xen_force_evtchn_callback();
-	}
+		preempt_enable();
+	} else
+		preempt_enable_no_resched();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
 
@@ -82,10 +77,12 @@ static void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
-	/* We don't need to worry about being preempted here, since
-	   either a) interrupts are disabled, so no preemption, or b)
-	   the caller is confused and is trying to re-enable interrupts
-	   on an indeterminate processor. */
+	/*
+	 * We may be preempted as soon as vcpu->evtchn_upcall_mask is
+	 * cleared, so disable preemption to ensure we check for
+	 * events on the VCPU we are still running on.
+	 */
+	preempt_disable();
 
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = 0;
@@ -96,6 +93,8 @@ static void xen_irq_enable(void)
 	barrier(); /* unmask then check (avoid races) */
 	if (unlikely(vcpu->evtchn_upcall_pending))
 		xen_force_evtchn_callback();
+
+	preempt_enable();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa5927..0d4ec35895d 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,6 +161,7 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/balloon.h>
 #include <xen/grant_table.h>
 
 #include "multicalls.h"
@@ -967,7 +968,10 @@ int m2p_remove_override(struct page *page,
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
-			struct gnttab_unmap_grant_ref *unmap_op;
+			struct gnttab_unmap_and_replace *unmap_op;
+			struct page *scratch_page = get_balloon_scratch_page();
+			unsigned long scratch_page_address = (unsigned long)
+				__va(page_to_pfn(scratch_page) << PAGE_SHIFT);
 
 			/*
 			 * It might be that we queued all the m2p grant table
@@ -990,21 +994,25 @@ int m2p_remove_override(struct page *page,
 			}
 
 			mcs = xen_mc_entry(
-					sizeof(struct gnttab_unmap_grant_ref));
+					sizeof(struct gnttab_unmap_and_replace));
 			unmap_op = mcs.args;
 			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->new_addr = scratch_page_address;
 			unmap_op->handle = kmap_op->handle;
-			unmap_op->dev_bus_addr = 0;
 
 			MULTI_grant_table_op(mcs.mc,
-					GNTTABOP_unmap_grant_ref, unmap_op, 1);
+					GNTTABOP_unmap_and_replace, unmap_op, 1);
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 
-			set_pte_at(&init_mm, address, ptep,
-					pfn_pte(pfn, PAGE_KERNEL));
-			__flush_tlb_single(address);
+			mcs = __xen_mc_entry(0);
+			MULTI_update_va_mapping(mcs.mc, scratch_page_address,
+					pfn_pte(page_to_pfn(get_balloon_scratch_page()),
+					PAGE_KERNEL_RO), 0);
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+
 			kmap_op->host_addr = 0;
+			put_balloon_scratch_page();
 		}
 	}
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8f3eea6b80c..09f3059cb00 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -33,6 +33,9 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
+#ifdef CONFIG_X86_64
+extern const char nmi[];
+#endif
 extern void xen_sysenter_target(void);
 extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
@@ -215,13 +218,19 @@ static void __init xen_set_identity_and_release_chunk(
 	unsigned long pfn;
 
 	/*
-	 * If the PFNs are currently mapped, the VA mapping also needs
-	 * to be updated to be 1:1.
+	 * If the PFNs are currently mapped, clear the mappings
+	 * (except for the ISA region which must be 1:1 mapped) to
+	 * release the refcounts (in Xen) on the original frames.
 	 */
-	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+		pte_t pte = __pte_ma(0);
+
+		if (pfn < PFN_UP(ISA_END_ADDRESS))
+			pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+
 		(void)HYPERVISOR_update_va_mapping(
-			(unsigned long)__va(pfn << PAGE_SHIFT),
-			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+			(unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+	}
 
 	if (start_pfn < nr_pages)
 		*released += xen_release_chunk(
@@ -547,7 +556,13 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-
+void __cpuinit xen_enable_nmi(void)
+{
+#ifdef CONFIG_X86_64
+	if (register_callback(CALLBACKTYPE_nmi, nmi))
+		BUG();
+#endif
+}
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
@@ -565,7 +580,7 @@ void __init xen_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-
+	xen_enable_nmi();
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
 		printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 597655bd72b..9235842cd76 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -573,6 +573,12 @@ static inline int xen_map_vector(int vector)
 	case IRQ_WORK_VECTOR:
 		xen_vector = XEN_IRQ_WORK_VECTOR;
 		break;
+#ifdef CONFIG_X86_64
+	case NMI_VECTOR:
+	case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */
+		xen_vector = XEN_NMI_VECTOR;
+		break;
+#endif
 	default:
 		xen_vector = -1;
 		printk(KERN_ERR "xen: vector 0x%x is not implemented\n",