Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

3 files changed, 220 insertions, 0 deletions

diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index bdce33291161..384f661a6496 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -90,4 +90,16 @@ config PTP_1588_CLOCK_PCH
 	  To compile this driver as a module, choose M here: the module
 	  will be called ptp_pch.
 
+config PTP_1588_CLOCK_KVM
+	tristate "KVM virtual PTP clock"
+	depends on PTP_1588_CLOCK
+	depends on KVM_GUEST && X86
+	default y
+	help
+	  This driver adds support for using kvm infrastructure as a PTP
+	  clock. This clock is only useful if you are using KVM guests.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called ptp_kvm.
+
 endmenu
diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile
index 8b58597298de..530736161a8b 100644
--- a/drivers/ptp/Makefile
+++ b/drivers/ptp/Makefile
@@ -6,3 +6,4 @@ ptp-y					:= ptp_clock.o ptp_chardev.o ptp_sysfs.o
 obj-$(CONFIG_PTP_1588_CLOCK)		+= ptp.o
 obj-$(CONFIG_PTP_1588_CLOCK_IXP46X)	+= ptp_ixp46x.o
 obj-$(CONFIG_PTP_1588_CLOCK_PCH)	+= ptp_pch.o
+obj-$(CONFIG_PTP_1588_CLOCK_KVM)	+= ptp_kvm.o
diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c
new file mode 100644
index 000000000000..09b4df74291e
--- /dev/null
+++ b/drivers/ptp/ptp_kvm.c
@@ -0,0 +1,207 @@
+/*
+ * Virtual PTP 1588 clock for use with KVM guests
+ *
+ * Copyright (C) 2017 Red Hat Inc.
+ *
+ *  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/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <uapi/linux/kvm_para.h>
+#include <asm/kvm_para.h>
+#include <asm/pvclock.h>
+#include <asm/kvmclock.h>
+#include <uapi/asm/kvm_para.h>
+
+#include <linux/ptp_clock_kernel.h>
+
+struct kvm_ptp_clock {
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info caps;
+};
+
+DEFINE_SPINLOCK(kvm_ptp_lock);
+
+static struct pvclock_vsyscall_time_info *hv_clock;
+
+static struct kvm_clock_pairing clock_pair;
+static phys_addr_t clock_pair_gpa;
+
+static int ptp_kvm_get_time_fn(ktime_t *device_time,
+			       struct system_counterval_t *system_counter,
+			       void *ctx)
+{
+	unsigned long ret;
+	struct timespec64 tspec;
+	unsigned version;
+	int cpu;
+	struct pvclock_vcpu_time_info *src;
+
+	spin_lock(&kvm_ptp_lock);
+
+	preempt_disable_notrace();
+	cpu = smp_processor_id();
+	src = &hv_clock[cpu].pvti;
+
+	do {
+		/*
+		 * We are using a TSC value read in the hosts
+		 * kvm_hc_clock_pairing handling.
+		 * So any changes to tsc_to_system_mul
+		 * and tsc_shift or any other pvclock
+		 * data invalidate that measurement.
+		 */
+		version = pvclock_read_begin(src);
+
+		ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING,
+				     clock_pair_gpa,
+				     KVM_CLOCK_PAIRING_WALLCLOCK);
+		if (ret != 0) {
+			pr_err_ratelimited("clock pairing hypercall ret %lu\n", ret);
+			spin_unlock(&kvm_ptp_lock);
+			preempt_enable_notrace();
+			return -EOPNOTSUPP;
+		}
+
+		tspec.tv_sec = clock_pair.sec;
+		tspec.tv_nsec = clock_pair.nsec;
+		ret = __pvclock_read_cycles(src, clock_pair.tsc);
+	} while (pvclock_read_retry(src, version));
+
+	preempt_enable_notrace();
+
+	system_counter->cycles = ret;
+	system_counter->cs = &kvm_clock;
+
+	*device_time = timespec64_to_ktime(tspec);
+
+	spin_unlock(&kvm_ptp_lock);
+
+	return 0;
+}
+
+static int ptp_kvm_getcrosststamp(struct ptp_clock_info *ptp,
+				  struct system_device_crosststamp *xtstamp)
+{
+	return get_device_system_crosststamp(ptp_kvm_get_time_fn, NULL,
+					     NULL, xtstamp);
+}
+
+/*
+ * PTP clock operations
+ */
+
+static int ptp_kvm_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_kvm_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_kvm_settime(struct ptp_clock_info *ptp,
+			   const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_kvm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	unsigned long ret;
+	struct timespec64 tspec;
+
+	spin_lock(&kvm_ptp_lock);
+
+	ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING,
+			     clock_pair_gpa,
+			     KVM_CLOCK_PAIRING_WALLCLOCK);
+	if (ret != 0) {
+		pr_err_ratelimited("clock offset hypercall ret %lu\n", ret);
+		spin_unlock(&kvm_ptp_lock);
+		return -EOPNOTSUPP;
+	}
+
+	tspec.tv_sec = clock_pair.sec;
+	tspec.tv_nsec = clock_pair.nsec;
+	spin_unlock(&kvm_ptp_lock);
+
+	memcpy(ts, &tspec, sizeof(struct timespec64));
+
+	return 0;
+}
+
+static int ptp_kvm_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info ptp_kvm_caps = {
+	.owner		= THIS_MODULE,
+	.name		= "KVM virtual PTP",
+	.max_adj	= 0,
+	.n_ext_ts	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.adjfreq	= ptp_kvm_adjfreq,
+	.adjtime	= ptp_kvm_adjtime,
+	.gettime64	= ptp_kvm_gettime,
+	.settime64	= ptp_kvm_settime,
+	.enable		= ptp_kvm_enable,
+	.getcrosststamp = ptp_kvm_getcrosststamp,
+};
+
+/* module operations */
+
+static struct kvm_ptp_clock kvm_ptp_clock;
+
+static void __exit ptp_kvm_exit(void)
+{
+	ptp_clock_unregister(kvm_ptp_clock.ptp_clock);
+}
+
+static int __init ptp_kvm_init(void)
+{
+	long ret;
+
+	clock_pair_gpa = slow_virt_to_phys(&clock_pair);
+	hv_clock = pvclock_pvti_cpu0_va();
+
+	if (!hv_clock)
+		return -ENODEV;
+
+	ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa,
+			KVM_CLOCK_PAIRING_WALLCLOCK);
+	if (ret == -KVM_ENOSYS || ret == -KVM_EOPNOTSUPP)
+		return -ENODEV;
+
+	kvm_ptp_clock.caps = ptp_kvm_caps;
+
+	kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL);
+
+	if (IS_ERR(kvm_ptp_clock.ptp_clock))
+		return PTR_ERR(kvm_ptp_clock.ptp_clock);
+
+	return 0;
+}
+
+module_init(ptp_kvm_init);
+module_exit(ptp_kvm_exit);
+
+MODULE_AUTHOR("Marcelo Tosatti <mtosatti@redhat.com>");
+MODULE_DESCRIPTION("PTP clock using KVMCLOCK");
+MODULE_LICENSE("GPL");