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

Pull KVM updates from Paolo Bonzini:
 "ARM:

   - More progress on the protected VM front, now with the full fixed
     feature set as well as the limitation of some hypercalls after
     initialisation.

   - Cleanup of the RAZ/WI sysreg handling, which was pointlessly
     complicated

   - Fixes for the vgic placement in the IPA space, together with a
     bunch of selftests

   - More memcg accounting of the memory allocated on behalf of a guest

   - Timer and vgic selftests

   - Workarounds for the Apple M1 broken vgic implementation

   - KConfig cleanups

   - New kvmarm.mode=none option, for those who really dislike us

  RISC-V:

   - New KVM port.

  x86:

   - New API to control TSC offset from userspace

   - TSC scaling for nested hypervisors on SVM

   - Switch masterclock protection from raw_spin_lock to seqcount

   - Clean up function prototypes in the page fault code and avoid
     repeated memslot lookups

   - Convey the exit reason to userspace on emulation failure

   - Configure time between NX page recovery iterations

   - Expose Predictive Store Forwarding Disable CPUID leaf

   - Allocate page tracking data structures lazily (if the i915 KVM-GT
     functionality is not compiled in)

   - Cleanups, fixes and optimizations for the shadow MMU code

  s390:

   - SIGP Fixes

   - initial preparations for lazy destroy of secure VMs

   - storage key improvements/fixes

   - Log the guest CPNC

  Starting from this release, KVM-PPC patches will come from Michael
  Ellerman's PPC tree"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  RISC-V: KVM: fix boolreturn.cocci warnings
  RISC-V: KVM: remove unneeded semicolon
  RISC-V: KVM: Fix GPA passed to __kvm_riscv_hfence_gvma_xyz() functions
  RISC-V: KVM: Factor-out FP virtualization into separate sources
  KVM: s390: add debug statement for diag 318 CPNC data
  KVM: s390: pv: properly handle page flags for protected guests
  KVM: s390: Fix handle_sske page fault handling
  KVM: x86: SGX must obey the KVM_INTERNAL_ERROR_EMULATION protocol
  KVM: x86: On emulation failure, convey the exit reason, etc. to userspace
  KVM: x86: Get exit_reason as part of kvm_x86_ops.get_exit_info
  KVM: x86: Clarify the kvm_run.emulation_failure structure layout
  KVM: s390: Add a routine for setting userspace CPU state
  KVM: s390: Simplify SIGP Set Arch handling
  KVM: s390: pv: avoid stalls when making pages secure
  KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm
  KVM: s390: pv: avoid double free of sida page
  KVM: s390: pv: add macros for UVC CC values
  s390/mm: optimize reset_guest_reference_bit()
  s390/mm: optimize set_guest_storage_key()
  s390/mm: no need for pte_alloc_map_lock() if we know the pmd is present
  ...

2 files changed, 151 insertions, 0 deletions

diff --git a/tools/arch/x86/include/asm/pvclock-abi.h b/tools/arch/x86/include/asm/pvclock-abi.h
new file mode 100644
index 000000000000..1436226efe3e
--- /dev/null
+++ b/tools/arch/x86/include/asm/pvclock-abi.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_PVCLOCK_ABI_H
+#define _ASM_X86_PVCLOCK_ABI_H
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time.  There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done.  Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+	u32   version;
+	u32   pad0;
+	u64   tsc_timestamp;
+	u64   system_time;
+	u32   tsc_to_system_mul;
+	s8    tsc_shift;
+	u8    flags;
+	u8    pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+	u32   version;
+	u32   sec;
+	u32   nsec;
+} __attribute__((__packed__));
+
+#define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
+#define PVCLOCK_GUEST_STOPPED	(1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
+#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/tools/arch/x86/include/asm/pvclock.h b/tools/arch/x86/include/asm/pvclock.h
new file mode 100644
index 000000000000..2628f9a6330b
--- /dev/null
+++ b/tools/arch/x86/include/asm/pvclock.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_PVCLOCK_H
+#define _ASM_X86_PVCLOCK_H
+
+#include <asm/barrier.h>
+#include <asm/pvclock-abi.h>
+
+/* 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);
+void pvclock_set_flags(u8 flags);
+unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
+void pvclock_resume(void);
+
+void pvclock_touch_watchdogs(void);
+
+static __always_inline
+unsigned pvclock_read_begin(const struct pvclock_vcpu_time_info *src)
+{
+	unsigned version = src->version & ~1;
+	/* Make sure that the version is read before the data. */
+	rmb();
+	return version;
+}
+
+static __always_inline
+bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src,
+			unsigned version)
+{
+	/* Make sure that the version is re-read after the data. */
+	rmb();
+	return version != src->version;
+}
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#else
+	unsigned long tmp;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif defined(__x86_64__)
+	__asm__ (
+		"mulq %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		: [lo]"=a"(product),
+		  [hi]"=d"(tmp)
+		: "0"(delta),
+		  [mul_frac]"rm"((u64)mul_frac));
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
+static __always_inline
+u64 __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u64 tsc)
+{
+	u64 delta = tsc - src->tsc_timestamp;
+	u64 offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+					     src->tsc_shift);
+	return src->system_time + offset;
+}
+
+struct pvclock_vsyscall_time_info {
+	struct pvclock_vcpu_time_info pvti;
+} __attribute__((__aligned__(64)));
+
+#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 */