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
  ...

13 files changed, 249 insertions, 38 deletions

diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c
index e43791829ace..91cf08ba1e95 100644
--- a/arch/arm/xen/grant-table.c
+++ b/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;
 }
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index d63053142b16..5b8b556dbb12 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/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,
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 3e4ed8fb5f91..a7471dcd2205 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/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 */
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 3bdd10d71223..a9630104f1c4 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -74,21 +74,43 @@
 #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__ */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c6b84245e5ab..123e669bf363 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/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)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 77b492c2d658..8b26c9e01cc4 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/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;
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 5c3f6d6a5078..761f6af6efa5 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/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);
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 809b6c812654..92ccc718152d 100644
--- a/arch/x86/xen/grant-table.c
+++ b/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
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3e15345abfe7..d33e7dbe3129 100644
--- a/arch/x86/xen/mmu.c
+++ b/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;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2ccdaba31a07..fc048ec686e7 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/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;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 92bf5ecb6baf..d9f96cc5d743 100644
--- a/arch/x86/xen/suspend.c
+++ b/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)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 80c2a4bdf230..29163c43ebbd 100644
--- a/arch/x86/xen/time.c
+++ b/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();
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index f377e1820c6c..75011b80660f 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/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);