Merge tag 'for-linus-4.15-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "Xen features and fixes for v4.15-rc1

  Apart from several small fixes it contains the following features:

   - a series by Joao Martins to add vdso support of the pv clock
     interface

   - a series by Juergen Gross to add support for Xen pv guests to be
     able to run on 5 level paging hosts

   - a series by Stefano Stabellini adding the Xen pvcalls frontend
     driver using a paravirtualized socket interface"

* tag 'for-linus-4.15-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (34 commits)
  xen/pvcalls: fix potential endless loop in pvcalls-front.c
  xen/pvcalls: Add MODULE_LICENSE()
  MAINTAINERS: xen, kvm: track pvclock-abi.h changes
  x86/xen/time: setup vcpu 0 time info page
  x86/xen/time: set pvclock flags on xen_time_init()
  x86/pvclock: add setter for pvclock_pvti_cpu0_va
  ptp_kvm: probe for kvm guest availability
  xen/privcmd: remove unused variable pageidx
  xen: select grant interface version
  xen: update arch/x86/include/asm/xen/cpuid.h
  xen: add grant interface version dependent constants to gnttab_ops
  xen: limit grant v2 interface to the v1 functionality
  xen: re-introduce support for grant v2 interface
  xen: support priv-mapping in an HVM tools domain
  xen/pvcalls: remove redundant check for irq >= 0
  xen/pvcalls: fix unsigned less than zero error check
  xen/time: Return -ENODEV from xen_get_wallclock()
  xen/pvcalls-front: mark expected switch fall-through
  xen: xenbus_probe_frontend: mark expected switch fall-throughs
  xen/time: do not decrease steal time after live migration on xen
  ...

MAINTAINERS

@@ -7650,6 +7650,7 @@ S:	Supported
 F:	arch/x86/kvm/
 F:	arch/x86/include/uapi/asm/kvm*
 F:	arch/x86/include/asm/kvm*
+F:	arch/x86/include/asm/pvclock-abi.h
 F:	arch/x86/kernel/kvm.c
 F:	arch/x86/kernel/kvmclock.c
 
@@ -14838,6 +14839,7 @@ F:	arch/x86/xen/
 F:	drivers/*/xen-*front.c
 F:	drivers/xen/
 F:	arch/x86/include/asm/xen/
+F:	arch/x86/include/asm/pvclock-abi.h
 F:	include/xen/
 F:	include/uapi/xen/
 F:	Documentation/ABI/stable/sysfs-hypervisor-xen

arch/arm/xen/grant-table.c

@@ -45,7 +45,14 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 	return;
 }
 
-int arch_gnttab_init(unsigned long nr_shared)
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
+{
+	return -ENOSYS;
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
 {
 	return 0;
 }

arch/x86/entry/vdso/vma.c

@@ -112,7 +112,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
-			pvclock_pvti_cpu0_va();
+			pvclock_get_pvti_cpu0_va();
 		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
 			ret = vm_insert_pfn_prot(
 				vma,

arch/x86/include/asm/pvclock.h

@@ -5,15 +5,6 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
-#ifdef CONFIG_KVM_GUEST
-extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
-#else
-static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
-{
-	return NULL;
-}
-#endif
-
 /* some helper functions for xen and kvm pv clock sources */
 u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
@@ -102,4 +93,14 @@ struct pvclock_vsyscall_time_info {
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti);
+struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _ASM_X86_PVCLOCK_H */

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

@@ -73,22 +73,44 @@
 #define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0
 #define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD  (1u<<0)
 
+/*
+ * Leaf 4 (0x40000x03)
+ * Sub-leaf 0: EAX: bit 0: emulated tsc
+ *                  bit 1: host tsc is known to be reliable
+ *                  bit 2: RDTSCP instruction available
+ *             EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate,
+ *                            2=no emulation, 3=no emulation + TSC_AUX support
+ *             ECX: guest tsc frequency in kHz
+ *             EDX: guest tsc incarnation (migration count)
+ * Sub-leaf 1: EAX: tsc offset low part
+ *             EBX: tsc offset high part
+ *             ECX: multiplicator for tsc->ns conversion
+ *             EDX: shift amount for tsc->ns conversion
+ * Sub-leaf 2: EAX: host tsc frequency in kHz
+ */
+
 /*
  * Leaf 5 (0x40000x04)
  * HVM-specific features
- * EAX: Features
- * EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
+ * Sub-leaf 0: EAX: Features
+ * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
  */
-
-/* Virtualized APIC registers */
-#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
-/* Virtualized x2APIC accesses */
-#define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1)
+#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
+#define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1) /* Virtualized x2APIC accesses */
 /* Memory mapped from other domains has valid IOMMU entries */
 #define XEN_HVM_CPUID_IOMMU_MAPPINGS   (1u << 2)
-/* vcpu id is present in EBX */
-#define XEN_HVM_CPUID_VCPU_ID_PRESENT  (1u << 3)
+#define XEN_HVM_CPUID_VCPU_ID_PRESENT  (1u << 3) /* vcpu id is present in EBX */
+
+/*
+ * Leaf 6 (0x40000x05)
+ * PV-specific parameters
+ * Sub-leaf 0: EAX: max available sub-leaf
+ * Sub-leaf 0: EBX: bits 0-7: max machine address width
+ */
+
+/* Max. address width in bits taking memory hotplug into account. */
+#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0)
 
-#define XEN_CPUID_MAX_NUM_LEAVES 4
+#define XEN_CPUID_MAX_NUM_LEAVES 5
 
 #endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */

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

@@ -27,6 +27,15 @@ typedef struct xpaddr {
 	phys_addr_t paddr;
 } xpaddr_t;
 
+#ifdef CONFIG_X86_64
+#define XEN_PHYSICAL_MASK	__sme_clr((1UL << 52) - 1)
+#else
+#define XEN_PHYSICAL_MASK	__PHYSICAL_MASK
+#endif
+
+#define XEN_PTE_MFN_MASK	((pteval_t)(((signed long)PAGE_MASK) & \
+					    XEN_PHYSICAL_MASK))
+
 #define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
 #define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
 
@@ -278,7 +287,7 @@ static inline unsigned long bfn_to_local_pfn(unsigned long mfn)
 
 static inline unsigned long pte_mfn(pte_t pte)
 {
-	return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pte.pte & XEN_PTE_MFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)

arch/x86/kernel/kvmclock.c

@@ -48,12 +48,6 @@ early_param("no-kvmclock", parse_no_kvmclock);
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock *wall_clock;
 
-struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
-{
-	return hv_clock;
-}
-EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va);
-
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
@@ -377,6 +371,7 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 		return 1;
 	}
 
+	pvclock_set_pvti_cpu0_va(hv_clock);
 	put_cpu();
 
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;

arch/x86/kernel/pvclock.c

@@ -25,8 +25,10 @@
 
 #include <asm/fixmap.h>
 #include <asm/pvclock.h>
+#include <asm/vgtod.h>
 
 static u8 valid_flags __read_mostly = 0;
+static struct pvclock_vsyscall_time_info *pvti_cpu0_va __read_mostly;
 
 void pvclock_set_flags(u8 flags)
 {
@@ -144,3 +146,15 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
+
+void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti)
+{
+	WARN_ON(vclock_was_used(VCLOCK_PVCLOCK));
+	pvti_cpu0_va = pvti;
+}
+
+struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
+{
+	return pvti_cpu0_va;
+}
+EXPORT_SYMBOL_GPL(pvclock_get_pvti_cpu0_va);

arch/x86/xen/grant-table.c

@@ -49,7 +49,7 @@
 static struct gnttab_vm_area {
 	struct vm_struct *area;
 	pte_t **ptes;
-} gnttab_shared_vm_area;
+} gnttab_shared_vm_area, gnttab_status_vm_area;
 
 int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
@@ -73,16 +73,43 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 	return 0;
 }
 
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
+{
+	grant_status_t *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
+
+	if (shared == NULL)
+		*__shared = shared = gnttab_status_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
 void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
+	pte_t **ptes;
 	unsigned long addr;
 	unsigned long i;
 
+	if (shared == gnttab_status_vm_area.area->addr)
+		ptes = gnttab_status_vm_area.ptes;
+	else
+		ptes = gnttab_shared_vm_area.ptes;
+
 	addr = (unsigned long)shared;
 
 	for (i = 0; i < nr_gframes; i++) {
-		set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
-			   __pte(0));
+		set_pte_at(&init_mm, addr, ptes[i], __pte(0));
 		addr += PAGE_SIZE;
 	}
 }
@@ -102,12 +129,35 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 	return 0;
 }
 
-int arch_gnttab_init(unsigned long nr_shared)
+static void arch_gnttab_vfree(struct gnttab_vm_area *area)
 {
+	free_vm_area(area->area);
+	kfree(area->ptes);
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	int ret;
+
 	if (!xen_pv_domain())
 		return 0;
 
-	return arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Always allocate the space for the status frames in case
+	 * we're migrated to a host with V2 support.
+	 */
+	ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+err:
+	arch_gnttab_vfree(&gnttab_shared_vm_area);
+	return -ENOMEM;
 }
 
 #ifdef CONFIG_XEN_PVH

arch/x86/xen/mmu.c

@@ -172,6 +172,9 @@ int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
 			       pgprot_t prot, unsigned domid,
 			       struct page **pages)
 {
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -EOPNOTSUPP;
+
 	return do_remap_gfn(vma, addr, &gfn, nr, NULL, prot, domid, pages);
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range);
@@ -182,6 +185,10 @@ int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       int *err_ptr, pgprot_t prot,
 			       unsigned domid, struct page **pages)
 {
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
+						 prot, domid, pages);
+
 	/* We BUG_ON because it's a programmer error to pass a NULL err_ptr,
 	 * and the consequences later is quite hard to detect what the actual
 	 * cause of "wrong memory was mapped in".
@@ -193,9 +200,12 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array);
 
 /* Returns: 0 success */
 int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
-			       int numpgs, struct page **pages)
+			       int nr, struct page **pages)
 {
-	if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return xen_xlate_unmap_gfn_range(vma, nr, pages);
+
+	if (!pages)
 		return 0;
 
 	return -EINVAL;

arch/x86/xen/mmu_pv.c

@@ -315,7 +315,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
 	if (val & _PAGE_PRESENT) {
-		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long mfn = (val & XEN_PTE_MFN_MASK) >> PAGE_SHIFT;
 		unsigned long pfn = mfn_to_pfn(mfn);
 
 		pteval_t flags = val & PTE_FLAGS_MASK;
@@ -1721,7 +1721,7 @@ static unsigned long __init m2p(phys_addr_t maddr)
 {
 	phys_addr_t paddr;
 
-	maddr &= PTE_PFN_MASK;
+	maddr &= XEN_PTE_MFN_MASK;
 	paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
 
 	return paddr;

arch/x86/xen/suspend.c

@@ -17,6 +17,8 @@
 
 void xen_arch_pre_suspend(void)
 {
+	xen_save_time_memory_area();
+
 	if (xen_pv_domain())
 		xen_pv_pre_suspend();
 }
@@ -27,6 +29,8 @@ void xen_arch_post_suspend(int cancelled)
 		xen_pv_post_suspend(cancelled);
 	else
 		xen_hvm_post_suspend(cancelled);
+
+	xen_restore_time_memory_area();
 }
 
 static void xen_vcpu_notify_restore(void *data)

arch/x86/xen/time.c

@@ -75,7 +75,7 @@ static void xen_get_wallclock(struct timespec *now)
 
 static int xen_set_wallclock(const struct timespec *now)
 {
-	return -1;
+	return -ENODEV;
 }
 
 static int xen_pvclock_gtod_notify(struct notifier_block *nb,
@@ -371,8 +371,95 @@ static const struct pv_time_ops xen_time_ops __initconst = {
 	.steal_clock = xen_steal_clock,
 };
 
+static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
+
+void xen_save_time_memory_area(void)
+{
+	struct vcpu_register_time_memory_area t;
+	int ret;
+
+	if (!xen_clock)
+		return;
+
+	t.addr.v = NULL;
+
+	ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
+	if (ret != 0)
+		pr_notice("Cannot save secondary vcpu_time_info (err %d)",
+			  ret);
+	else
+		clear_page(xen_clock);
+}
+
+void xen_restore_time_memory_area(void)
+{
+	struct vcpu_register_time_memory_area t;
+	int ret;
+
+	if (!xen_clock)
+		return;
+
+	t.addr.v = &xen_clock->pvti;
+
+	ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
+
+	/*
+	 * We don't disable VCLOCK_PVCLOCK entirely if it fails to register the
+	 * secondary time info with Xen or if we migrated to a host without the
+	 * necessary flags. On both of these cases what happens is either
+	 * process seeing a zeroed out pvti or seeing no PVCLOCK_TSC_STABLE_BIT
+	 * bit set. Userspace checks the latter and if 0, it discards the data
+	 * in pvti and fallbacks to a system call for a reliable timestamp.
+	 */
+	if (ret != 0)
+		pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
+			  ret);
+}
+
+static void xen_setup_vsyscall_time_info(void)
+{
+	struct vcpu_register_time_memory_area t;
+	struct pvclock_vsyscall_time_info *ti;
+	int ret;
+
+	ti = (struct pvclock_vsyscall_time_info *)get_zeroed_page(GFP_KERNEL);
+	if (!ti)
+		return;
+
+	t.addr.v = &ti->pvti;
+
+	ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
+	if (ret) {
+		pr_notice("xen: VCLOCK_PVCLOCK not supported (err %d)\n", ret);
+		free_page((unsigned long)ti);
+		return;
+	}
+
+	/*
+	 * If primary time info had this bit set, secondary should too since
+	 * it's the same data on both just different memory regions. But we
+	 * still check it in case hypervisor is buggy.
+	 */
+	if (!(ti->pvti.flags & PVCLOCK_TSC_STABLE_BIT)) {
+		t.addr.v = NULL;
+		ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area,
+					 0, &t);
+		if (!ret)
+			free_page((unsigned long)ti);
+
+		pr_notice("xen: VCLOCK_PVCLOCK not supported (tsc unstable)\n");
+		return;
+	}
+
+	xen_clock = ti;
+	pvclock_set_pvti_cpu0_va(xen_clock);
+
+	xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK;
+}
+
 static void __init xen_time_init(void)
 {
+	struct pvclock_vcpu_time_info *pvti;
 	int cpu = smp_processor_id();
 	struct timespec tp;
 
@@ -396,6 +483,16 @@ static void __init xen_time_init(void)
 
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
+	/*
+	 * We check ahead on the primary time info if this
+	 * bit is supported hence speeding up Xen clocksource.
+	 */
+	pvti = &__this_cpu_read(xen_vcpu)->time;
+	if (pvti->flags & PVCLOCK_TSC_STABLE_BIT) {
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+		xen_setup_vsyscall_time_info();
+	}
+
 	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();

arch/x86/xen/xen-ops.h

@@ -70,6 +70,8 @@ void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
 u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
+void xen_save_time_memory_area(void);
+void xen_restore_time_memory_area(void);
 void __init xen_init_time_ops(void);
 void __init xen_hvm_init_time_ops(void);
 

drivers/ptp/ptp_kvm.c

@@ -178,8 +178,11 @@ static int __init ptp_kvm_init(void)
 {
 	long ret;
 
+	if (!kvm_para_available())
+		return -ENODEV;
+
 	clock_pair_gpa = slow_virt_to_phys(&clock_pair);
-	hv_clock = pvclock_pvti_cpu0_va();
+	hv_clock = pvclock_get_pvti_cpu0_va();
 
 	if (!hv_clock)
 		return -ENODEV;

drivers/xen/Kconfig

@@ -196,6 +196,17 @@ config XEN_PCIDEV_BACKEND
 
 	  If in doubt, say m.
 
+config XEN_PVCALLS_FRONTEND
+	tristate "XEN PV Calls frontend driver"
+	depends on INET && XEN
+	default n
+	select XEN_XENBUS_FRONTEND
+	help
+	  Experimental frontend for the Xen PV Calls protocol
+	  (https://xenbits.xen.org/docs/unstable/misc/pvcalls.html). It
+	  sends a small set of POSIX calls to the backend, which
+	  implements them.
+
 config XEN_PVCALLS_BACKEND
 	bool "XEN PV Calls backend driver"
 	depends on INET && XEN && XEN_BACKEND

drivers/xen/Makefile

@@ -37,6 +37,7 @@ obj-$(CONFIG_XEN_EFI)			+= efi.o
 obj-$(CONFIG_XEN_SCSI_BACKEND)		+= xen-scsiback.o
 obj-$(CONFIG_XEN_AUTO_XLATE)		+= xlate_mmu.o
 obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
+obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o

drivers/xen/grant-table.c

@@ -33,6 +33,7 @@
 
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
+#include <linux/bootmem.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
@@ -43,6 +44,7 @@
 #include <linux/hardirq.h>
 #include <linux/workqueue.h>
 #include <linux/ratelimit.h>
+#include <linux/moduleparam.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -52,6 +54,9 @@
 #include <xen/hvc-console.h>
 #include <xen/swiotlb-xen.h>
 #include <xen/balloon.h>
+#ifdef CONFIG_X86
+#include <asm/xen/cpuid.h>
+#endif
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -68,14 +73,25 @@ static int gnttab_free_count;
 static grant_ref_t gnttab_free_head;
 static DEFINE_SPINLOCK(gnttab_list_lock);
 struct grant_frames xen_auto_xlat_grant_frames;
+static unsigned int xen_gnttab_version;
+module_param_named(version, xen_gnttab_version, uint, 0);
 
 static union {
 	struct grant_entry_v1 *v1;
+	union grant_entry_v2 *v2;
 	void *addr;
 } gnttab_shared;
 
 /*This is a structure of function pointers for grant table*/
 struct gnttab_ops {
+	/*
+	 * Version of the grant interface.
+	 */
+	unsigned int version;
+	/*
+	 * Grant refs per grant frame.
+	 */
+	unsigned int grefs_per_grant_frame;
 	/*
 	 * Mapping a list of frames for storing grant entries. Frames parameter
 	 * is used to store grant table address when grant table being setup,
@@ -130,14 +146,15 @@ struct unmap_refs_callback_data {
 
 static const struct gnttab_ops *gnttab_interface;
 
-static int grant_table_version;
-static int grefs_per_grant_frame;
+/* This reflects status of grant entries, so act as a global value. */
+static grant_status_t *grstatus;
 
 static struct gnttab_free_callback *gnttab_free_callback_list;
 
 static int gnttab_expand(unsigned int req_entries);
 
 #define RPP (PAGE_SIZE / sizeof(grant_ref_t))
+#define SPP (PAGE_SIZE / sizeof(grant_status_t))
 
 static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
 {
@@ -210,7 +227,7 @@ static void put_free_entry(grant_ref_t ref)
 }
 
 /*
- * Following applies to gnttab_update_entry_v1.
+ * Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
  * Introducing a valid entry into the grant table:
  *  1. Write ent->domid.
  *  2. Write ent->frame:
@@ -229,6 +246,15 @@ static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid,
 	gnttab_shared.v1[ref].flags = flags;
 }
 
+static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid,
+				   unsigned long frame, unsigned int flags)
+{
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	gnttab_shared.v2[ref].full_page.frame = frame;
+	wmb();	/* Hypervisor concurrent accesses. */
+	gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags;
+}
+
 /*
  * Public grant-issuing interface functions
  */
@@ -260,6 +286,11 @@ static int gnttab_query_foreign_access_v1(grant_ref_t ref)
 	return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing);
 }
 
+static int gnttab_query_foreign_access_v2(grant_ref_t ref)
+{
+	return grstatus[ref] & (GTF_reading|GTF_writing);
+}
+
 int gnttab_query_foreign_access(grant_ref_t ref)
 {
 	return gnttab_interface->query_foreign_access(ref);
@@ -282,6 +313,29 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
 	return 1;
 }
 
+static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
+{
+	gnttab_shared.v2[ref].hdr.flags = 0;
+	mb();	/* Concurrent access by hypervisor. */
+	if (grstatus[ref] & (GTF_reading|GTF_writing)) {
+		return 0;
+	} else {
+		/*
+		 * The read of grstatus needs to have acquire semantics.
+		 *  On x86, reads already have that, and we just need to
+		 * protect against compiler reorderings.
+		 * On other architectures we may need a full barrier.
+		 */
+#ifdef CONFIG_X86
+		barrier();
+#else
+		mb();
+#endif
+	}
+
+	return 1;
+}
+
 static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
 {
 	return gnttab_interface->end_foreign_access_ref(ref, readonly);
@@ -442,6 +496,37 @@ static unsigned long gnttab_end_foreign_transfer_ref_v1(grant_ref_t ref)
 	return frame;
 }
 
+static unsigned long gnttab_end_foreign_transfer_ref_v2(grant_ref_t ref)
+{
+	unsigned long frame;
+	u16           flags;
+	u16          *pflags;
+
+	pflags = &gnttab_shared.v2[ref].hdr.flags;
+
+	/*
+	 * If a transfer is not even yet started, try to reclaim the grant
+	 * reference and return failure (== 0).
+	 */
+	while (!((flags = *pflags) & GTF_transfer_committed)) {
+		if (sync_cmpxchg(pflags, flags, 0) == flags)
+			return 0;
+		cpu_relax();
+	}
+
+	/* If a transfer is in progress then wait until it is completed. */
+	while (!(flags & GTF_transfer_completed)) {
+		flags = *pflags;
+		cpu_relax();
+	}
+
+	rmb();  /* Read the frame number /after/ reading completion status. */
+	frame = gnttab_shared.v2[ref].full_page.frame;
+	BUG_ON(frame == 0);
+
+	return frame;
+}
+
 unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref)
 {
 	return gnttab_interface->end_foreign_transfer_ref(ref);
@@ -563,19 +648,26 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
 }
 EXPORT_SYMBOL_GPL(gnttab_cancel_free_callback);
 
+static unsigned int gnttab_frames(unsigned int frames, unsigned int align)
+{
+	return (frames * gnttab_interface->grefs_per_grant_frame + align - 1) /
+	       align;
+}
+
 static int grow_gnttab_list(unsigned int more_frames)
 {
 	unsigned int new_nr_grant_frames, extra_entries, i;
 	unsigned int nr_glist_frames, new_nr_glist_frames;
+	unsigned int grefs_per_frame;
 
-	BUG_ON(grefs_per_grant_frame == 0);
+	BUG_ON(gnttab_interface == NULL);
+	grefs_per_frame = gnttab_interface->grefs_per_grant_frame;
 
 	new_nr_grant_frames = nr_grant_frames + more_frames;
-	extra_entries       = more_frames * grefs_per_grant_frame;
+	extra_entries = more_frames * grefs_per_frame;
 
-	nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
-	new_nr_glist_frames =
-		(new_nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
+	nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
+	new_nr_glist_frames = gnttab_frames(new_nr_grant_frames, RPP);
 	for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
 		if (!gnttab_list[i])
@@ -583,12 +675,12 @@ static int grow_gnttab_list(unsigned int more_frames)
 	}
 
 
-	for (i = grefs_per_grant_frame * nr_grant_frames;
-	     i < grefs_per_grant_frame * new_nr_grant_frames - 1; i++)
+	for (i = grefs_per_frame * nr_grant_frames;
+	     i < grefs_per_frame * new_nr_grant_frames - 1; i++)
 		gnttab_entry(i) = i + 1;
 
 	gnttab_entry(i) = gnttab_free_head;
-	gnttab_free_head = grefs_per_grant_frame * nr_grant_frames;
+	gnttab_free_head = grefs_per_frame * nr_grant_frames;
 	gnttab_free_count += extra_entries;
 
 	nr_grant_frames = new_nr_grant_frames;
@@ -938,6 +1030,12 @@ int gnttab_unmap_refs_sync(struct gntab_unmap_queue_data *item)
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs_sync);
 
+static unsigned int nr_status_frames(unsigned int nr_grant_frames)
+{
+	BUG_ON(gnttab_interface == NULL);
+	return gnttab_frames(nr_grant_frames, SPP);
+}
+
 static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
 {
 	int rc;
@@ -955,6 +1053,55 @@ static void gnttab_unmap_frames_v1(void)
 	arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
 }
 
+static int gnttab_map_frames_v2(xen_pfn_t *frames, unsigned int nr_gframes)
+{
+	uint64_t *sframes;
+	unsigned int nr_sframes;
+	struct gnttab_get_status_frames getframes;
+	int rc;
+
+	nr_sframes = nr_status_frames(nr_gframes);
+
+	/* No need for kzalloc as it is initialized in following hypercall
+	 * GNTTABOP_get_status_frames.
+	 */
+	sframes = kmalloc_array(nr_sframes, sizeof(uint64_t), GFP_ATOMIC);
+	if (!sframes)
+		return -ENOMEM;
+
+	getframes.dom        = DOMID_SELF;
+	getframes.nr_frames  = nr_sframes;
+	set_xen_guest_handle(getframes.frame_list, sframes);
+
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames,
+				       &getframes, 1);
+	if (rc == -ENOSYS) {
+		kfree(sframes);
+		return -ENOSYS;
+	}
+
+	BUG_ON(rc || getframes.status);
+
+	rc = arch_gnttab_map_status(sframes, nr_sframes,
+				    nr_status_frames(gnttab_max_grant_frames()),
+				    &grstatus);
+	BUG_ON(rc);
+	kfree(sframes);
+
+	rc = arch_gnttab_map_shared(frames, nr_gframes,
+				    gnttab_max_grant_frames(),
+				    &gnttab_shared.addr);
+	BUG_ON(rc);
+
+	return 0;
+}
+
+static void gnttab_unmap_frames_v2(void)
+{
+	arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
+	arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames));
+}
+
 static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 {
 	struct gnttab_setup_table setup;
@@ -1014,6 +1161,9 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 }
 
 static const struct gnttab_ops gnttab_v1_ops = {
+	.version			= 1,
+	.grefs_per_grant_frame		= XEN_PAGE_SIZE /
+					  sizeof(struct grant_entry_v1),
 	.map_frames			= gnttab_map_frames_v1,
 	.unmap_frames			= gnttab_unmap_frames_v1,
 	.update_entry			= gnttab_update_entry_v1,
@@ -1022,14 +1172,56 @@ static const struct gnttab_ops gnttab_v1_ops = {
 	.query_foreign_access		= gnttab_query_foreign_access_v1,
 };
 
-static void gnttab_request_version(void)
+static const struct gnttab_ops gnttab_v2_ops = {
+	.version			= 2,
+	.grefs_per_grant_frame		= XEN_PAGE_SIZE /
+					  sizeof(union grant_entry_v2),
+	.map_frames			= gnttab_map_frames_v2,
+	.unmap_frames			= gnttab_unmap_frames_v2,
+	.update_entry			= gnttab_update_entry_v2,
+	.end_foreign_access_ref		= gnttab_end_foreign_access_ref_v2,
+	.end_foreign_transfer_ref	= gnttab_end_foreign_transfer_ref_v2,
+	.query_foreign_access		= gnttab_query_foreign_access_v2,
+};
+
+static bool gnttab_need_v2(void)
 {
-	/* Only version 1 is used, which will always be available. */
-	grant_table_version = 1;
-	grefs_per_grant_frame = XEN_PAGE_SIZE / sizeof(struct grant_entry_v1);
-	gnttab_interface = &gnttab_v1_ops;
+#ifdef CONFIG_X86
+	uint32_t base, width;
+
+	if (xen_pv_domain()) {
+		base = xen_cpuid_base();
+		if (cpuid_eax(base) < 5)
+			return false;	/* Information not available, use V1. */
+		width = cpuid_ebx(base + 5) &
+			XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK;
+		return width > 32 + PAGE_SHIFT;
+	}
+#endif
+	return !!(max_possible_pfn >> 32);
+}
 
-	pr_info("Grant tables using version %d layout\n", grant_table_version);
+static void gnttab_request_version(void)
+{
+	long rc;
+	struct gnttab_set_version gsv;
+
+	if (gnttab_need_v2())
+		gsv.version = 2;
+	else
+		gsv.version = 1;
+
+	/* Boot parameter overrides automatic selection. */
+	if (xen_gnttab_version >= 1 && xen_gnttab_version <= 2)
+		gsv.version = xen_gnttab_version;
+
+	rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
+	if (rc == 0 && gsv.version == 2)
+		gnttab_interface = &gnttab_v2_ops;
+	else
+		gnttab_interface = &gnttab_v1_ops;
+	pr_info("Grant tables using version %d layout\n",
+		gnttab_interface->version);
 }
 
 static int gnttab_setup(void)
@@ -1069,10 +1261,10 @@ static int gnttab_expand(unsigned int req_entries)
 	int rc;
 	unsigned int cur, extra;
 
-	BUG_ON(grefs_per_grant_frame == 0);
+	BUG_ON(gnttab_interface == NULL);
 	cur = nr_grant_frames;
-	extra = ((req_entries + (grefs_per_grant_frame-1)) /
-		 grefs_per_grant_frame);
+	extra = ((req_entries + gnttab_interface->grefs_per_grant_frame - 1) /
+		 gnttab_interface->grefs_per_grant_frame);
 	if (cur + extra > gnttab_max_grant_frames()) {
 		pr_warn_ratelimited("xen/grant-table: max_grant_frames reached"
 				    " cur=%u extra=%u limit=%u"
@@ -1104,16 +1296,16 @@ int gnttab_init(void)
 	/* Determine the maximum number of frames required for the
 	 * grant reference free list on the current hypervisor.
 	 */
-	BUG_ON(grefs_per_grant_frame == 0);
+	BUG_ON(gnttab_interface == NULL);
 	max_nr_glist_frames = (max_nr_grant_frames *
-			       grefs_per_grant_frame / RPP);
+			       gnttab_interface->grefs_per_grant_frame / RPP);
 
 	gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
 			      GFP_KERNEL);
 	if (gnttab_list == NULL)
 		return -ENOMEM;
 
-	nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
+	nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
 	for (i = 0; i < nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
 		if (gnttab_list[i] == NULL) {
@@ -1122,7 +1314,8 @@ int gnttab_init(void)
 		}
 	}
 
-	ret = arch_gnttab_init(max_nr_grant_frames);
+	ret = arch_gnttab_init(max_nr_grant_frames,
+			       nr_status_frames(max_nr_grant_frames));
 	if (ret < 0)
 		goto ini_nomem;
 
@@ -1131,7 +1324,8 @@ int gnttab_init(void)
 		goto ini_nomem;
 	}
 
-	nr_init_grefs = nr_grant_frames * grefs_per_grant_frame;
+	nr_init_grefs = nr_grant_frames *
+			gnttab_interface->grefs_per_grant_frame;
 
 	for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
 		gnttab_entry(i) = i + 1;

drivers/xen/manage.c

@@ -72,18 +72,15 @@ static int xen_suspend(void *data)
 	}
 
 	gnttab_suspend();
+	xen_manage_runstate_time(-1);
 	xen_arch_pre_suspend();
 
-	/*
-	 * This hypercall returns 1 if suspend was cancelled
-	 * or the domain was merely checkpointed, and 0 if it
-	 * is resuming in a new domain.
-	 */
 	si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
                                            ? virt_to_gfn(xen_start_info)
                                            : 0);
 
 	xen_arch_post_suspend(si->cancelled);
+	xen_manage_runstate_time(si->cancelled ? 1 : 0);
 	gnttab_resume();
 
 	if (!si->cancelled) {

drivers/xen/privcmd.c

@@ -191,13 +191,10 @@ static int traverse_pages_block(unsigned nelem, size_t size,
 				void *state)
 {
 	void *pagedata;
-	unsigned pageidx;
 	int ret = 0;
 
 	BUG_ON(size > PAGE_SIZE);
 
-	pageidx = PAGE_SIZE;
-
 	while (nelem) {
 		int nr = (PAGE_SIZE/size);
 		struct page *page;

drivers/xen/pvcalls-back.c

@@ -1238,3 +1238,7 @@ static void __exit pvcalls_back_fin(void)
 }
 
 module_exit(pvcalls_back_fin);
+
+MODULE_DESCRIPTION("Xen PV Calls backend driver");
+MODULE_AUTHOR("Stefano Stabellini <sstabellini@kernel.org>");
+MODULE_LICENSE("GPL");

drivers/xen/pvcalls-front.c

+/*
+ * (c) 2017 Stefano Stabellini <stefano@aporeto.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+
+#include <net/sock.h>
+
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pvcalls.h>
+
+#include "pvcalls-front.h"
+
+#define PVCALLS_INVALID_ID UINT_MAX
+#define PVCALLS_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
+#define PVCALLS_NR_RSP_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
+#define PVCALLS_FRONT_MAX_SPIN 5000
+
+struct pvcalls_bedata {
+	struct xen_pvcalls_front_ring ring;
+	grant_ref_t ref;
+	int irq;
+
+	struct list_head socket_mappings;
+	spinlock_t socket_lock;
+
+	wait_queue_head_t inflight_req;
+	struct xen_pvcalls_response rsp[PVCALLS_NR_RSP_PER_RING];
+};
+/* Only one front/back connection supported. */
+static struct xenbus_device *pvcalls_front_dev;
+static atomic_t pvcalls_refcount;
+
+/* first increment refcount, then proceed */
+#define pvcalls_enter() {               \
+	atomic_inc(&pvcalls_refcount);      \
+}
+
+/* first complete other operations, then decrement refcount */
+#define pvcalls_exit() {                \
+	atomic_dec(&pvcalls_refcount);      \
+}
+
+struct sock_mapping {
+	bool active_socket;
+	struct list_head list;
+	struct socket *sock;
+	union {
+		struct {
+			int irq;
+			grant_ref_t ref;
+			struct pvcalls_data_intf *ring;
+			struct pvcalls_data data;
+			struct mutex in_mutex;
+			struct mutex out_mutex;
+
+			wait_queue_head_t inflight_conn_req;
+		} active;
+		struct {
+		/* Socket status */
+#define PVCALLS_STATUS_UNINITALIZED  0
+#define PVCALLS_STATUS_BIND          1
+#define PVCALLS_STATUS_LISTEN        2
+			uint8_t status;
+		/*
+		 * Internal state-machine flags.
+		 * Only one accept operation can be inflight for a socket.
+		 * Only one poll operation can be inflight for a given socket.
+		 */
+#define PVCALLS_FLAG_ACCEPT_INFLIGHT 0
+#define PVCALLS_FLAG_POLL_INFLIGHT   1
+#define PVCALLS_FLAG_POLL_RET        2
+			uint8_t flags;
+			uint32_t inflight_req_id;
+			struct sock_mapping *accept_map;
+			wait_queue_head_t inflight_accept_req;
+		} passive;
+	};
+};
+
+static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
+{
+	*req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
+	if (RING_FULL(&bedata->ring) ||
+	    bedata->rsp[*req_id].req_id != PVCALLS_INVALID_ID)
+		return -EAGAIN;
+	return 0;
+}
+
+static bool pvcalls_front_write_todo(struct sock_mapping *map)
+{
+	struct pvcalls_data_intf *intf = map->active.ring;
+	RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+	int32_t error;
+
+	error = intf->out_error;
+	if (error == -ENOTCONN)
+		return false;
+	if (error != 0)
+		return true;
+
+	cons = intf->out_cons;
+	prod = intf->out_prod;
+	return !!(size - pvcalls_queued(prod, cons, size));
+}
+
+static bool pvcalls_front_read_todo(struct sock_mapping *map)
+{
+	struct pvcalls_data_intf *intf = map->active.ring;
+	RING_IDX cons, prod;
+	int32_t error;
+
+	cons = intf->in_cons;
+	prod = intf->in_prod;
+	error = intf->in_error;
+	return (error != 0 ||
+		pvcalls_queued(prod, cons,
+			       XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER)) != 0);
+}
+
+static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
+{
+	struct xenbus_device *dev = dev_id;
+	struct pvcalls_bedata *bedata;
+	struct xen_pvcalls_response *rsp;
+	uint8_t *src, *dst;
+	int req_id = 0, more = 0, done = 0;
+
+	if (dev == NULL)
+		return IRQ_HANDLED;
+
+	pvcalls_enter();
+	bedata = dev_get_drvdata(&dev->dev);
+	if (bedata == NULL) {
+		pvcalls_exit();
+		return IRQ_HANDLED;
+	}
+
+again:
+	while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) {
+		rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons);
+
+		req_id = rsp->req_id;
+		if (rsp->cmd == PVCALLS_POLL) {
+			struct sock_mapping *map = (struct sock_mapping *)(uintptr_t)
+						   rsp->u.poll.id;
+
+			clear_bit(PVCALLS_FLAG_POLL_INFLIGHT,
+				  (void *)&map->passive.flags);
+			/*
+			 * clear INFLIGHT, then set RET. It pairs with
+			 * the checks at the beginning of
+			 * pvcalls_front_poll_passive.
+			 */
+			smp_wmb();
+			set_bit(PVCALLS_FLAG_POLL_RET,
+				(void *)&map->passive.flags);
+		} else {
+			dst = (uint8_t *)&bedata->rsp[req_id] +
+			      sizeof(rsp->req_id);
+			src = (uint8_t *)rsp + sizeof(rsp->req_id);
+			memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id));
+			/*
+			 * First copy the rest of the data, then req_id. It is
+			 * paired with the barrier when accessing bedata->rsp.
+			 */
+			smp_wmb();
+			bedata->rsp[req_id].req_id = req_id;
+		}
+
+		done = 1;
+		bedata->ring.rsp_cons++;
+	}
+
+	RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more);
+	if (more)
+		goto again;
+	if (done)
+		wake_up(&bedata->inflight_req);
+	pvcalls_exit();
+	return IRQ_HANDLED;
+}
+
+static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
+				   struct sock_mapping *map)
+{
+	int i;
+
+	unbind_from_irqhandler(map->active.irq, map);
+
+	spin_lock(&bedata->socket_lock);
+	if (!list_empty(&map->list))
+		list_del_init(&map->list);
+	spin_unlock(&bedata->socket_lock);
+
+	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
+		gnttab_end_foreign_access(map->active.ring->ref[i], 0, 0);
+	gnttab_end_foreign_access(map->active.ref, 0, 0);
+	free_page((unsigned long)map->active.ring);
+
+	kfree(map);
+}
+
+static irqreturn_t pvcalls_front_conn_handler(int irq, void *sock_map)
+{
+	struct sock_mapping *map = sock_map;
+
+	if (map == NULL)
+		return IRQ_HANDLED;
+
+	wake_up_interruptible(&map->active.inflight_conn_req);
+
+	return IRQ_HANDLED;
+}
+
+int pvcalls_front_socket(struct socket *sock)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map = NULL;
+	struct xen_pvcalls_request *req;
+	int notify, req_id, ret;
+
+	/*
+	 * PVCalls only supports domain AF_INET,
+	 * type SOCK_STREAM and protocol 0 sockets for now.
+	 *
+	 * Check socket type here, AF_INET and protocol checks are done
+	 * by the caller.
+	 */
+	if (sock->type != SOCK_STREAM)
+		return -EOPNOTSUPP;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -EACCES;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (map == NULL) {
+		pvcalls_exit();
+		return -ENOMEM;
+	}
+
+	spin_lock(&bedata->socket_lock);
+
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		kfree(map);
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+
+	/*
+	 * sock->sk->sk_send_head is not used for ip sockets: reuse the
+	 * field to store a pointer to the struct sock_mapping
+	 * corresponding to the socket. This way, we can easily get the
+	 * struct sock_mapping from the struct socket.
+	 */
+	sock->sk->sk_send_head = (void *)map;
+	list_add_tail(&map->list, &bedata->socket_mappings);
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_SOCKET;
+	req->u.socket.id = (uintptr_t) map;
+	req->u.socket.domain = AF_INET;
+	req->u.socket.type = SOCK_STREAM;
+	req->u.socket.protocol = IPPROTO_IP;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+
+	/* read req_id, then the content */
+	smp_rmb();
+	ret = bedata->rsp[req_id].ret;
+	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+
+	pvcalls_exit();
+	return ret;
+}
+
+static int create_active(struct sock_mapping *map, int *evtchn)
+{
+	void *bytes;
+	int ret = -ENOMEM, irq = -1, i;
+
+	*evtchn = -1;
+	init_waitqueue_head(&map->active.inflight_conn_req);
+
+	map->active.ring = (struct pvcalls_data_intf *)
+		__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	if (map->active.ring == NULL)
+		goto out_error;
+	map->active.ring->ring_order = PVCALLS_RING_ORDER;
+	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					PVCALLS_RING_ORDER);
+	if (bytes == NULL)
+		goto out_error;
+	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
+		map->active.ring->ref[i] = gnttab_grant_foreign_access(
+			pvcalls_front_dev->otherend_id,
+			pfn_to_gfn(virt_to_pfn(bytes) + i), 0);
+
+	map->active.ref = gnttab_grant_foreign_access(
+		pvcalls_front_dev->otherend_id,
+		pfn_to_gfn(virt_to_pfn((void *)map->active.ring)), 0);
+
+	map->active.data.in = bytes;
+	map->active.data.out = bytes +
+		XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+
+	ret = xenbus_alloc_evtchn(pvcalls_front_dev, evtchn);
+	if (ret)
+		goto out_error;
+	irq = bind_evtchn_to_irqhandler(*evtchn, pvcalls_front_conn_handler,
+					0, "pvcalls-frontend", map);
+	if (irq < 0) {
+		ret = irq;
+		goto out_error;
+	}
+
+	map->active.irq = irq;
+	map->active_socket = true;
+	mutex_init(&map->active.in_mutex);
+	mutex_init(&map->active.out_mutex);
+
+	return 0;
+
+out_error:
+	if (*evtchn >= 0)
+		xenbus_free_evtchn(pvcalls_front_dev, *evtchn);
+	kfree(map->active.data.in);
+	kfree(map->active.ring);
+	return ret;
+}
+
+int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
+				int addr_len, int flags)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map = NULL;
+	struct xen_pvcalls_request *req;
+	int notify, req_id, ret, evtchn;
+
+	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
+		return -EOPNOTSUPP;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *)sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	ret = create_active(map, &evtchn);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_CONNECT;
+	req->u.connect.id = (uintptr_t)map;
+	req->u.connect.len = addr_len;
+	req->u.connect.flags = flags;
+	req->u.connect.ref = map->active.ref;
+	req->u.connect.evtchn = evtchn;
+	memcpy(req->u.connect.addr, addr, sizeof(*addr));
+
+	map->sock = sock;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+
+	/* read req_id, then the content */
+	smp_rmb();
+	ret = bedata->rsp[req_id].ret;
+	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+	pvcalls_exit();
+	return ret;
+}
+
+static int __write_ring(struct pvcalls_data_intf *intf,
+			struct pvcalls_data *data,
+			struct iov_iter *msg_iter,
+			int len)
+{
+	RING_IDX cons, prod, size, masked_prod, masked_cons;
+	RING_IDX array_size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+	int32_t error;
+
+	error = intf->out_error;
+	if (error < 0)
+		return error;
+	cons = intf->out_cons;
+	prod = intf->out_prod;
+	/* read indexes before continuing */
+	virt_mb();
+
+	size = pvcalls_queued(prod, cons, array_size);
+	if (size >= array_size)
+		return -EINVAL;
+	if (len > array_size - size)
+		len = array_size - size;
+
+	masked_prod = pvcalls_mask(prod, array_size);
+	masked_cons = pvcalls_mask(cons, array_size);
+
+	if (masked_prod < masked_cons) {
+		len = copy_from_iter(data->out + masked_prod, len, msg_iter);
+	} else {
+		if (len > array_size - masked_prod) {
+			int ret = copy_from_iter(data->out + masked_prod,
+				       array_size - masked_prod, msg_iter);
+			if (ret != array_size - masked_prod) {
+				len = ret;
+				goto out;
+			}
+			len = ret + copy_from_iter(data->out, len - ret, msg_iter);
+		} else {
+			len = copy_from_iter(data->out + masked_prod, len, msg_iter);
+		}
+	}
+out:
+	/* write to ring before updating pointer */
+	virt_wmb();
+	intf->out_prod += len;
+
+	return len;
+}
+
+int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
+			  size_t len)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	int sent, tot_sent = 0;
+	int count = 0, flags;
+
+	flags = msg->msg_flags;
+	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
+		return -EOPNOTSUPP;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	mutex_lock(&map->active.out_mutex);
+	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
+		mutex_unlock(&map->active.out_mutex);
+		pvcalls_exit();
+		return -EAGAIN;
+	}
+	if (len > INT_MAX)
+		len = INT_MAX;
+
+again:
+	count++;
+	sent = __write_ring(map->active.ring,
+			    &map->active.data, &msg->msg_iter,
+			    len);
+	if (sent > 0) {
+		len -= sent;
+		tot_sent += sent;
+		notify_remote_via_irq(map->active.irq);
+	}
+	if (sent >= 0 && len > 0 && count < PVCALLS_FRONT_MAX_SPIN)
+		goto again;
+	if (sent < 0)
+		tot_sent = sent;
+
+	mutex_unlock(&map->active.out_mutex);
+	pvcalls_exit();
+	return tot_sent;
+}
+
+static int __read_ring(struct pvcalls_data_intf *intf,
+		       struct pvcalls_data *data,
+		       struct iov_iter *msg_iter,
+		       size_t len, int flags)
+{
+	RING_IDX cons, prod, size, masked_prod, masked_cons;
+	RING_IDX array_size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+	int32_t error;
+
+	cons = intf->in_cons;
+	prod = intf->in_prod;
+	error = intf->in_error;
+	/* get pointers before reading from the ring */
+	virt_rmb();
+	if (error < 0)
+		return error;
+
+	size = pvcalls_queued(prod, cons, array_size);
+	masked_prod = pvcalls_mask(prod, array_size);
+	masked_cons = pvcalls_mask(cons, array_size);
+
+	if (size == 0)
+		return 0;
+
+	if (len > size)
+		len = size;
+
+	if (masked_prod > masked_cons) {
+		len = copy_to_iter(data->in + masked_cons, len, msg_iter);
+	} else {
+		if (len > (array_size - masked_cons)) {
+			int ret = copy_to_iter(data->in + masked_cons,
+				     array_size - masked_cons, msg_iter);
+			if (ret != array_size - masked_cons) {
+				len = ret;
+				goto out;
+			}
+			len = ret + copy_to_iter(data->in, len - ret, msg_iter);
+		} else {
+			len = copy_to_iter(data->in + masked_cons, len, msg_iter);
+		}
+	}
+out:
+	/* read data from the ring before increasing the index */
+	virt_mb();
+	if (!(flags & MSG_PEEK))
+		intf->in_cons += len;
+
+	return len;
+}
+
+int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		     int flags)
+{
+	struct pvcalls_bedata *bedata;
+	int ret;
+	struct sock_mapping *map;
+
+	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
+		return -EOPNOTSUPP;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	mutex_lock(&map->active.in_mutex);
+	if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER))
+		len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
+
+	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
+		wait_event_interruptible(map->active.inflight_conn_req,
+					 pvcalls_front_read_todo(map));
+	}
+	ret = __read_ring(map->active.ring, &map->active.data,
+			  &msg->msg_iter, len, flags);
+
+	if (ret > 0)
+		notify_remote_via_irq(map->active.irq);
+	if (ret == 0)
+		ret = (flags & MSG_DONTWAIT) ? -EAGAIN : 0;
+	if (ret == -ENOTCONN)
+		ret = 0;
+
+	mutex_unlock(&map->active.in_mutex);
+	pvcalls_exit();
+	return ret;
+}
+
+int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map = NULL;
+	struct xen_pvcalls_request *req;
+	int notify, req_id, ret;
+
+	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
+		return -EOPNOTSUPP;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (map == NULL) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	map->sock = sock;
+	req->cmd = PVCALLS_BIND;
+	req->u.bind.id = (uintptr_t)map;
+	memcpy(req->u.bind.addr, addr, sizeof(*addr));
+	req->u.bind.len = addr_len;
+
+	init_waitqueue_head(&map->passive.inflight_accept_req);
+
+	map->active_socket = false;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+
+	/* read req_id, then the content */
+	smp_rmb();
+	ret = bedata->rsp[req_id].ret;
+	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+
+	map->passive.status = PVCALLS_STATUS_BIND;
+	pvcalls_exit();
+	return 0;
+}
+
+int pvcalls_front_listen(struct socket *sock, int backlog)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	struct xen_pvcalls_request *req;
+	int notify, req_id, ret;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	if (map->passive.status != PVCALLS_STATUS_BIND) {
+		pvcalls_exit();
+		return -EOPNOTSUPP;
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_LISTEN;
+	req->u.listen.id = (uintptr_t) map;
+	req->u.listen.backlog = backlog;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+
+	/* read req_id, then the content */
+	smp_rmb();
+	ret = bedata->rsp[req_id].ret;
+	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+
+	map->passive.status = PVCALLS_STATUS_LISTEN;
+	pvcalls_exit();
+	return ret;
+}
+
+int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	struct sock_mapping *map2 = NULL;
+	struct xen_pvcalls_request *req;
+	int notify, req_id, ret, evtchn, nonblock;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -ENOTCONN;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return -ENOTSOCK;
+	}
+
+	if (map->passive.status != PVCALLS_STATUS_LISTEN) {
+		pvcalls_exit();
+		return -EINVAL;
+	}
+
+	nonblock = flags & SOCK_NONBLOCK;
+	/*
+	 * Backend only supports 1 inflight accept request, will return
+	 * errors for the others
+	 */
+	if (test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			     (void *)&map->passive.flags)) {
+		req_id = READ_ONCE(map->passive.inflight_req_id);
+		if (req_id != PVCALLS_INVALID_ID &&
+		    READ_ONCE(bedata->rsp[req_id].req_id) == req_id) {
+			map2 = map->passive.accept_map;
+			goto received;
+		}
+		if (nonblock) {
+			pvcalls_exit();
+			return -EAGAIN;
+		}
+		if (wait_event_interruptible(map->passive.inflight_accept_req,
+			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+					  (void *)&map->passive.flags))) {
+			pvcalls_exit();
+			return -EINTR;
+		}
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	map2 = kzalloc(sizeof(*map2), GFP_KERNEL);
+	if (map2 == NULL) {
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return -ENOMEM;
+	}
+	ret = create_active(map2, &evtchn);
+	if (ret < 0) {
+		kfree(map2);
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	list_add_tail(&map2->list, &bedata->socket_mappings);
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_ACCEPT;
+	req->u.accept.id = (uintptr_t) map;
+	req->u.accept.ref = map2->active.ref;
+	req->u.accept.id_new = (uintptr_t) map2;
+	req->u.accept.evtchn = evtchn;
+	map->passive.accept_map = map2;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+	/* We could check if we have received a response before returning. */
+	if (nonblock) {
+		WRITE_ONCE(map->passive.inflight_req_id, req_id);
+		pvcalls_exit();
+		return -EAGAIN;
+	}
+
+	if (wait_event_interruptible(bedata->inflight_req,
+		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
+		pvcalls_exit();
+		return -EINTR;
+	}
+	/* read req_id, then the content */
+	smp_rmb();
+
+received:
+	map2->sock = newsock;
+	newsock->sk = kzalloc(sizeof(*newsock->sk), GFP_KERNEL);
+	if (!newsock->sk) {
+		bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+		map->passive.inflight_req_id = PVCALLS_INVALID_ID;
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
+		pvcalls_front_free_map(bedata, map2);
+		pvcalls_exit();
+		return -ENOMEM;
+	}
+	newsock->sk->sk_send_head = (void *)map2;
+
+	ret = bedata->rsp[req_id].ret;
+	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
+	map->passive.inflight_req_id = PVCALLS_INVALID_ID;
+
+	clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags);
+	wake_up(&map->passive.inflight_accept_req);
+
+	pvcalls_exit();
+	return ret;
+}
+
+static unsigned int pvcalls_front_poll_passive(struct file *file,
+					       struct pvcalls_bedata *bedata,
+					       struct sock_mapping *map,
+					       poll_table *wait)
+{
+	int notify, req_id, ret;
+	struct xen_pvcalls_request *req;
+
+	if (test_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+		     (void *)&map->passive.flags)) {
+		uint32_t req_id = READ_ONCE(map->passive.inflight_req_id);
+
+		if (req_id != PVCALLS_INVALID_ID &&
+		    READ_ONCE(bedata->rsp[req_id].req_id) == req_id)
+			return POLLIN | POLLRDNORM;
+
+		poll_wait(file, &map->passive.inflight_accept_req, wait);
+		return 0;
+	}
+
+	if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET,
+			       (void *)&map->passive.flags))
+		return POLLIN | POLLRDNORM;
+
+	/*
+	 * First check RET, then INFLIGHT. No barriers necessary to
+	 * ensure execution ordering because of the conditional
+	 * instructions creating control dependencies.
+	 */
+
+	if (test_and_set_bit(PVCALLS_FLAG_POLL_INFLIGHT,
+			     (void *)&map->passive.flags)) {
+		poll_wait(file, &bedata->inflight_req, wait);
+		return 0;
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		return ret;
+	}
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_POLL;
+	req->u.poll.id = (uintptr_t) map;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	poll_wait(file, &bedata->inflight_req, wait);
+	return 0;
+}
+
+static unsigned int pvcalls_front_poll_active(struct file *file,
+					      struct pvcalls_bedata *bedata,
+					      struct sock_mapping *map,
+					      poll_table *wait)
+{
+	unsigned int mask = 0;
+	int32_t in_error, out_error;
+	struct pvcalls_data_intf *intf = map->active.ring;
+
+	out_error = intf->out_error;
+	in_error = intf->in_error;
+
+	poll_wait(file, &map->active.inflight_conn_req, wait);
+	if (pvcalls_front_write_todo(map))
+		mask |= POLLOUT | POLLWRNORM;
+	if (pvcalls_front_read_todo(map))
+		mask |= POLLIN | POLLRDNORM;
+	if (in_error != 0 || out_error != 0)
+		mask |= POLLERR;
+
+	return mask;
+}
+
+unsigned int pvcalls_front_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	int ret;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return POLLNVAL;
+	}
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (!map) {
+		pvcalls_exit();
+		return POLLNVAL;
+	}
+	if (map->active_socket)
+		ret = pvcalls_front_poll_active(file, bedata, map, wait);
+	else
+		ret = pvcalls_front_poll_passive(file, bedata, map, wait);
+	pvcalls_exit();
+	return ret;
+}
+
+int pvcalls_front_release(struct socket *sock)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map;
+	int req_id, notify, ret;
+	struct xen_pvcalls_request *req;
+
+	if (sock->sk == NULL)
+		return 0;
+
+	pvcalls_enter();
+	if (!pvcalls_front_dev) {
+		pvcalls_exit();
+		return -EIO;
+	}
+
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+
+	map = (struct sock_mapping *) sock->sk->sk_send_head;
+	if (map == NULL) {
+		pvcalls_exit();
+		return 0;
+	}
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
+	if (ret < 0) {
+		spin_unlock(&bedata->socket_lock);
+		pvcalls_exit();
+		return ret;
+	}
+	sock->sk->sk_send_head = NULL;
+
+	req = RING_GET_REQUEST(&bedata->ring, req_id);
+	req->req_id = req_id;
+	req->cmd = PVCALLS_RELEASE;
+	req->u.release.id = (uintptr_t)map;
+
+	bedata->ring.req_prod_pvt++;
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
+	spin_unlock(&bedata->socket_lock);
+	if (notify)
+		notify_remote_via_irq(bedata->irq);
+
+	wait_event(bedata->inflight_req,
+		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
+
+	if (map->active_socket) {
+		/*
+		 * Set in_error and wake up inflight_conn_req to force
+		 * recvmsg waiters to exit.
+		 */
+		map->active.ring->in_error = -EBADF;
+		wake_up_interruptible(&map->active.inflight_conn_req);
+
+		/*
+		 * We need to make sure that sendmsg/recvmsg on this socket have
+		 * not started before we've cleared sk_send_head here. The
+		 * easiest (though not optimal) way to guarantee this is to see
+		 * that no pvcall (other than us) is in progress.
+		 */
+		while (atomic_read(&pvcalls_refcount) > 1)
+			cpu_relax();
+
+		pvcalls_front_free_map(bedata, map);
+	} else {
+		spin_lock(&bedata->socket_lock);
+		list_del(&map->list);
+		spin_unlock(&bedata->socket_lock);
+		if (READ_ONCE(map->passive.inflight_req_id) !=
+		    PVCALLS_INVALID_ID) {
+			pvcalls_front_free_map(bedata,
+					       map->passive.accept_map);
+		}
+		kfree(map);
+	}
+	WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);
+
+	pvcalls_exit();
+	return 0;
+}
+
+static const struct xenbus_device_id pvcalls_front_ids[] = {
+	{ "pvcalls" },
+	{ "" }
+};
+
+static int pvcalls_front_remove(struct xenbus_device *dev)
+{
+	struct pvcalls_bedata *bedata;
+	struct sock_mapping *map = NULL, *n;
+
+	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
+	dev_set_drvdata(&dev->dev, NULL);
+	pvcalls_front_dev = NULL;
+	if (bedata->irq >= 0)
+		unbind_from_irqhandler(bedata->irq, dev);
+
+	list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
+		map->sock->sk->sk_send_head = NULL;
+		if (map->active_socket) {
+			map->active.ring->in_error = -EBADF;
+			wake_up_interruptible(&map->active.inflight_conn_req);
+		}
+	}
+
+	smp_mb();
+	while (atomic_read(&pvcalls_refcount) > 0)
+		cpu_relax();
+	list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
+		if (map->active_socket) {
+			/* No need to lock, refcount is 0 */
+			pvcalls_front_free_map(bedata, map);
+		} else {
+			list_del(&map->list);
+			kfree(map);
+		}
+	}
+	if (bedata->ref >= 0)
+		gnttab_end_foreign_access(bedata->ref, 0, 0);
+	kfree(bedata->ring.sring);
+	kfree(bedata);
+	xenbus_switch_state(dev, XenbusStateClosed);
+	return 0;
+}
+
+static int pvcalls_front_probe(struct xenbus_device *dev,
+			  const struct xenbus_device_id *id)
+{
+	int ret = -ENOMEM, evtchn, i;
+	unsigned int max_page_order, function_calls, len;
+	char *versions;
+	grant_ref_t gref_head = 0;
+	struct xenbus_transaction xbt;
+	struct pvcalls_bedata *bedata = NULL;
+	struct xen_pvcalls_sring *sring;
+
+	if (pvcalls_front_dev != NULL) {
+		dev_err(&dev->dev, "only one PV Calls connection supported\n");
+		return -EINVAL;
+	}
+
+	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
+	if (!len)
+		return -EINVAL;
+	if (strcmp(versions, "1")) {
+		kfree(versions);
+		return -EINVAL;
+	}
+	kfree(versions);
+	max_page_order = xenbus_read_unsigned(dev->otherend,
+					      "max-page-order", 0);
+	if (max_page_order < PVCALLS_RING_ORDER)
+		return -ENODEV;
+	function_calls = xenbus_read_unsigned(dev->otherend,
+					      "function-calls", 0);
+	/* See XENBUS_FUNCTIONS_CALLS in pvcalls.h */
+	if (function_calls != 1)
+		return -ENODEV;
+	pr_info("%s max-page-order is %u\n", __func__, max_page_order);
+
+	bedata = kzalloc(sizeof(struct pvcalls_bedata), GFP_KERNEL);
+	if (!bedata)
+		return -ENOMEM;
+
+	dev_set_drvdata(&dev->dev, bedata);
+	pvcalls_front_dev = dev;
+	init_waitqueue_head(&bedata->inflight_req);
+	INIT_LIST_HEAD(&bedata->socket_mappings);
+	spin_lock_init(&bedata->socket_lock);
+	bedata->irq = -1;
+	bedata->ref = -1;
+
+	for (i = 0; i < PVCALLS_NR_RSP_PER_RING; i++)
+		bedata->rsp[i].req_id = PVCALLS_INVALID_ID;
+
+	sring = (struct xen_pvcalls_sring *) __get_free_page(GFP_KERNEL |
+							     __GFP_ZERO);
+	if (!sring)
+		goto error;
+	SHARED_RING_INIT(sring);
+	FRONT_RING_INIT(&bedata->ring, sring, XEN_PAGE_SIZE);
+
+	ret = xenbus_alloc_evtchn(dev, &evtchn);
+	if (ret)
+		goto error;
+
+	bedata->irq = bind_evtchn_to_irqhandler(evtchn,
+						pvcalls_front_event_handler,
+						0, "pvcalls-frontend", dev);
+	if (bedata->irq < 0) {
+		ret = bedata->irq;
+		goto error;
+	}
+
+	ret = gnttab_alloc_grant_references(1, &gref_head);
+	if (ret < 0)
+		goto error;
+	ret = gnttab_claim_grant_reference(&gref_head);
+	if (ret < 0)
+		goto error;
+	bedata->ref = ret;
+	gnttab_grant_foreign_access_ref(bedata->ref, dev->otherend_id,
+					virt_to_gfn((void *)sring), 0);
+
+ again:
+	ret = xenbus_transaction_start(&xbt);
+	if (ret) {
+		xenbus_dev_fatal(dev, ret, "starting transaction");
+		goto error;
+	}
+	ret = xenbus_printf(xbt, dev->nodename, "version", "%u", 1);
+	if (ret)
+		goto error_xenbus;
+	ret = xenbus_printf(xbt, dev->nodename, "ring-ref", "%d", bedata->ref);
+	if (ret)
+		goto error_xenbus;
+	ret = xenbus_printf(xbt, dev->nodename, "port", "%u",
+			    evtchn);
+	if (ret)
+		goto error_xenbus;
+	ret = xenbus_transaction_end(xbt, 0);
+	if (ret) {
+		if (ret == -EAGAIN)
+			goto again;
+		xenbus_dev_fatal(dev, ret, "completing transaction");
+		goto error;
+	}
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+ error_xenbus:
+	xenbus_transaction_end(xbt, 1);
+	xenbus_dev_fatal(dev, ret, "writing xenstore");
+ error:
+	pvcalls_front_remove(dev);
+	return ret;
+}
+
+static void pvcalls_front_changed(struct xenbus_device *dev,
+			    enum xenbus_state backend_state)
+{
+	switch (backend_state) {
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
+	case XenbusStateInitialising:
+	case XenbusStateInitialised:
+	case XenbusStateUnknown:
+		break;
+
+	case XenbusStateInitWait:
+		break;
+
+	case XenbusStateConnected:
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's CLOSING state */
+		/* fall through */
+	case XenbusStateClosing:
+		xenbus_frontend_closed(dev);
+		break;
+	}
+}
+
+static struct xenbus_driver pvcalls_front_driver = {
+	.ids = pvcalls_front_ids,
+	.probe = pvcalls_front_probe,
+	.remove = pvcalls_front_remove,
+	.otherend_changed = pvcalls_front_changed,
+};
+
+static int __init pvcalls_frontend_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	pr_info("Initialising Xen pvcalls frontend driver\n");
+
+	return xenbus_register_frontend(&pvcalls_front_driver);
+}
+
+module_init(pvcalls_frontend_init);
+
+MODULE_DESCRIPTION("Xen PV Calls frontend driver");
+MODULE_AUTHOR("Stefano Stabellini <sstabellini@kernel.org>");
+MODULE_LICENSE("GPL");

drivers/xen/pvcalls-front.h

+#ifndef __PVCALLS_FRONT_H__
+#define __PVCALLS_FRONT_H__
+
+#include <linux/net.h>
+
+int pvcalls_front_socket(struct socket *sock);
+int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
+			  int addr_len, int flags);
+int pvcalls_front_bind(struct socket *sock,
+		       struct sockaddr *addr,
+		       int addr_len);
+int pvcalls_front_listen(struct socket *sock, int backlog);
+int pvcalls_front_accept(struct socket *sock,
+			 struct socket *newsock,
+			 int flags);
+int pvcalls_front_sendmsg(struct socket *sock,
+			  struct msghdr *msg,
+			  size_t len);
+int pvcalls_front_recvmsg(struct socket *sock,
+			  struct msghdr *msg,
+			  size_t len,
+			  int flags);
+unsigned int pvcalls_front_poll(struct file *file,
+				struct socket *sock,
+				poll_table *wait);
+int pvcalls_front_release(struct socket *sock);
+
+#endif

drivers/xen/time.c

@@ -6,6 +6,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 
 #include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
@@ -20,6 +21,8 @@
 /* runstate info updated by Xen */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
 
+static DEFINE_PER_CPU(u64[4], old_runstate_time);
+
 /* return an consistent snapshot of 64-bit time/counter value */
 static u64 get64(const u64 *p)
 {
@@ -48,8 +51,8 @@ static u64 get64(const u64 *p)
 	return ret;
 }
 
-static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
-					  unsigned int cpu)
+static void xen_get_runstate_snapshot_cpu_delta(
+			      struct vcpu_runstate_info *res, unsigned int cpu)
 {
 	u64 state_time;
 	struct vcpu_runstate_info *state;
@@ -67,6 +70,71 @@ static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
 		 (state_time & XEN_RUNSTATE_UPDATE));
 }
 
+static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
+					  unsigned int cpu)
+{
+	int i;
+
+	xen_get_runstate_snapshot_cpu_delta(res, cpu);
+
+	for (i = 0; i < 4; i++)
+		res->time[i] += per_cpu(old_runstate_time, cpu)[i];
+}
+
+void xen_manage_runstate_time(int action)
+{
+	static struct vcpu_runstate_info *runstate_delta;
+	struct vcpu_runstate_info state;
+	int cpu, i;
+
+	switch (action) {
+	case -1: /* backup runstate time before suspend */
+		if (unlikely(runstate_delta))
+			pr_warn_once("%s: memory leak as runstate_delta is not NULL\n",
+					__func__);
+
+		runstate_delta = kmalloc_array(num_possible_cpus(),
+					sizeof(*runstate_delta),
+					GFP_ATOMIC);
+		if (unlikely(!runstate_delta)) {
+			pr_warn("%s: failed to allocate runstate_delta\n",
+					__func__);
+			return;
+		}
+
+		for_each_possible_cpu(cpu) {
+			xen_get_runstate_snapshot_cpu_delta(&state, cpu);
+			memcpy(runstate_delta[cpu].time, state.time,
+					sizeof(runstate_delta[cpu].time));
+		}
+
+		break;
+
+	case 0: /* backup runstate time after resume */
+		if (unlikely(!runstate_delta)) {
+			pr_warn("%s: cannot accumulate runstate time as runstate_delta is NULL\n",
+					__func__);
+			return;
+		}
+
+		for_each_possible_cpu(cpu) {
+			for (i = 0; i < 4; i++)
+				per_cpu(old_runstate_time, cpu)[i] +=
+					runstate_delta[cpu].time[i];
+		}
+
+		break;
+
+	default: /* do not accumulate runstate time for checkpointing */
+		break;
+	}
+
+	if (action != -1 && runstate_delta) {
+		kfree(runstate_delta);
+		runstate_delta = NULL;
+	}
+}
+
 /*
  * Runstate accounting
  */

drivers/xen/xenbus/xenbus_probe_frontend.c

@@ -379,10 +379,12 @@ static void xenbus_reset_frontend(char *fe, char *be, int be_state)
 	case XenbusStateConnected:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing);
 		xenbus_reset_wait_for_backend(be, XenbusStateClosing);
+		/* fall through */
 
 	case XenbusStateClosing:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed);
 		xenbus_reset_wait_for_backend(be, XenbusStateClosed);
+		/* fall through */
 
 	case XenbusStateClosed:
 		xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising);

include/xen/grant_table.h

@@ -174,10 +174,13 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr,
 	unmap->dev_bus_addr = 0;
 }
 
-int arch_gnttab_init(unsigned long nr_shared);
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status);
 int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
 			   void **__shared);
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared);
 void arch_gnttab_unmap(void *shared, unsigned long nr_gframes);
 
 struct grant_frames {

include/xen/interface/vcpu.h

@@ -178,4 +178,46 @@ DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_vcpu_info);
 
 /* Send an NMI to the specified VCPU. @extra_arg == NULL. */
 #define VCPUOP_send_nmi             11
+
+/*
+ * Get the physical ID information for a pinned vcpu's underlying physical
+ * processor.  The physical ID informmation is architecture-specific.
+ * On x86: id[31:0]=apic_id, id[63:32]=acpi_id.
+ * This command returns -EINVAL if it is not a valid operation for this VCPU.
+ */
+#define VCPUOP_get_physid           12 /* arg == vcpu_get_physid_t */
+struct vcpu_get_physid {
+	uint64_t phys_id;
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_get_physid);
+#define xen_vcpu_physid_to_x86_apicid(physid) ((uint32_t)(physid))
+#define xen_vcpu_physid_to_x86_acpiid(physid) ((uint32_t)((physid) >> 32))
+
+/*
+ * Register a memory location to get a secondary copy of the vcpu time
+ * parameters.  The master copy still exists as part of the vcpu shared
+ * memory area, and this secondary copy is updated whenever the master copy
+ * is updated (and using the same versioning scheme for synchronisation).
+ *
+ * The intent is that this copy may be mapped (RO) into userspace so
+ * that usermode can compute system time using the time info and the
+ * tsc.  Usermode will see an array of vcpu_time_info structures, one
+ * for each vcpu, and choose the right one by an existing mechanism
+ * which allows it to get the current vcpu number (such as via a
+ * segment limit).  It can then apply the normal algorithm to compute
+ * system time from the tsc.
+ *
+ * @extra_arg == pointer to vcpu_register_time_info_memory_area structure.
+ */
+#define VCPUOP_register_vcpu_time_memory_area   13
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_time_info);
+struct vcpu_register_time_memory_area {
+	union {
+		GUEST_HANDLE(vcpu_time_info) h;
+		struct pvclock_vcpu_time_info *v;
+		uint64_t p;
+	} addr;
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_time_memory_area);
+
 #endif /* __XEN_PUBLIC_VCPU_H__ */

include/xen/xen-ops.h

@@ -33,6 +33,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb);
 bool xen_vcpu_stolen(int vcpu);
 void xen_setup_runstate_info(int cpu);
 void xen_time_setup_guest(void);
+void xen_manage_runstate_time(int action);
 void xen_get_runstate_snapshot(struct vcpu_runstate_info *res);
 u64 xen_steal_clock(int cpu);
 
@@ -104,6 +105,8 @@ int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
 			       struct page **pages);
 int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 			       int numpgs, struct page **pages);
+
+#ifdef CONFIG_XEN_AUTO_XLATE
 int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
 			      unsigned long addr,
 			      xen_pfn_t *gfn, int nr,
@@ -112,6 +115,28 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
 			      struct page **pages);
 int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
 			      int nr, struct page **pages);
+#else
+/*
+ * These two functions are called from arch/x86/xen/mmu.c and so stubs
+ * are needed for a configuration not specifying CONFIG_XEN_AUTO_XLATE.
+ */
+static inline int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
+					    unsigned long addr,
+					    xen_pfn_t *gfn, int nr,
+					    int *err_ptr, pgprot_t prot,
+					    unsigned int domid,
+					    struct page **pages)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
+					    int nr, struct page **pages)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr,
 				  unsigned long nr_grant_frames);