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

Pull kvm updates from Paolo Bonzini:
 "Quite a large pull request due to a selftest API overhaul and some
  patches that had come in too late for 5.19.

  ARM:

   - Unwinder implementations for both nVHE modes (classic and
     protected), complete with an overflow stack

   - Rework of the sysreg access from userspace, with a complete rewrite
     of the vgic-v3 view to allign with the rest of the infrastructure

   - Disagregation of the vcpu flags in separate sets to better track
     their use model.

   - A fix for the GICv2-on-v3 selftest

   - A small set of cosmetic fixes

  RISC-V:

   - Track ISA extensions used by Guest using bitmap

   - Added system instruction emulation framework

   - Added CSR emulation framework

   - Added gfp_custom flag in struct kvm_mmu_memory_cache

   - Added G-stage ioremap() and iounmap() functions

   - Added support for Svpbmt inside Guest

  s390:

   - add an interface to provide a hypervisor dump for secure guests

   - improve selftests to use TAP interface

   - enable interpretive execution of zPCI instructions (for PCI
     passthrough)

   - First part of deferred teardown

   - CPU Topology

   - PV attestation

   - Minor fixes

  x86:

   - Permit guests to ignore single-bit ECC errors

   - Intel IPI virtualization

   - Allow getting/setting pending triple fault with
     KVM_GET/SET_VCPU_EVENTS

   - PEBS virtualization

   - Simplify PMU emulation by just using PERF_TYPE_RAW events

   - More accurate event reinjection on SVM (avoid retrying
     instructions)

   - Allow getting/setting the state of the speaker port data bit

   - Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
     are inconsistent

   - "Notify" VM exit (detect microarchitectural hangs) for Intel

   - Use try_cmpxchg64 instead of cmpxchg64

   - Ignore benign host accesses to PMU MSRs when PMU is disabled

   - Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

   - Allow NX huge page mitigation to be disabled on a per-vm basis

   - Port eager page splitting to shadow MMU as well

   - Enable CMCI capability by default and handle injected UCNA errors

   - Expose pid of vcpu threads in debugfs

   - x2AVIC support for AMD

   - cleanup PIO emulation

   - Fixes for LLDT/LTR emulation

   - Don't require refcounted "struct page" to create huge SPTEs

   - Miscellaneous cleanups:
      - MCE MSR emulation
      - Use separate namespaces for guest PTEs and shadow PTEs bitmasks
      - PIO emulation
      - Reorganize rmap API, mostly around rmap destruction
      - Do not workaround very old KVM bugs for L0 that runs with nesting enabled
      - new selftests API for CPUID

  Generic:

   - Fix races in gfn->pfn cache refresh; do not pin pages tracked by
     the cache

   - new selftests API using struct kvm_vcpu instead of a (vm, id)
     tuple"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
  selftests: kvm: set rax before vmcall
  selftests: KVM: Add exponent check for boolean stats
  selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
  selftests: KVM: Check stat name before other fields
  KVM: x86/mmu: remove unused variable
  RISC-V: KVM: Add support for Svpbmt inside Guest/VM
  RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
  RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
  KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
  RISC-V: KVM: Add extensible CSR emulation framework
  RISC-V: KVM: Add extensible system instruction emulation framework
  RISC-V: KVM: Factor-out instruction emulation into separate sources
  RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
  RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
  RISC-V: KVM: Fix variable spelling mistake
  RISC-V: KVM: Improve ISA extension by using a bitmap
  KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
  KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
  KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
  KVM: x86: Do not block APIC write for non ICR registers
  ...

4 files changed, 52 insertions, 6 deletions

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 4da1914425e1..f9d0c908e738 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -44,6 +44,17 @@ config VFIO_PCI_IGD
 	  To enable Intel IGD assignment through vfio-pci, say Y.
 endif
 
+config VFIO_PCI_ZDEV_KVM
+	bool "VFIO PCI extensions for s390x KVM passthrough"
+	depends on S390 && KVM
+	default y
+	help
+	  Support s390x-specific extensions to enable support for enhancements
+	  to KVM passthrough capabilities, such as interpretive execution of
+	  zPCI instructions.
+
+	  To enable s390x KVM vfio-pci extensions, say Y.
+
 source "drivers/vfio/pci/mlx5/Kconfig"
 
 source "drivers/vfio/pci/hisilicon/Kconfig"
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 7052ebd893e0..24c524224da5 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
-vfio-pci-core-$(CONFIG_S390) += vfio_pci_zdev.o
+vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o
 obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
 
 vfio-pci-y := vfio_pci.o
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 756d049bd9cf..0d8d4cdfb2f0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -317,10 +317,14 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
 		pci_write_config_word(pdev, PCI_COMMAND, cmd);
 	}
 
-	ret = vfio_config_init(vdev);
+	ret = vfio_pci_zdev_open_device(vdev);
 	if (ret)
 		goto out_free_state;
 
+	ret = vfio_config_init(vdev);
+	if (ret)
+		goto out_free_zdev;
+
 	msix_pos = pdev->msix_cap;
 	if (msix_pos) {
 		u16 flags;
@@ -341,6 +345,8 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
 
 	return 0;
 
+out_free_zdev:
+	vfio_pci_zdev_close_device(vdev);
 out_free_state:
 	kfree(vdev->pci_saved_state);
 	vdev->pci_saved_state = NULL;
@@ -419,6 +425,8 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 
 	vdev->needs_reset = true;
 
+	vfio_pci_zdev_close_device(vdev);
+
 	/*
 	 * If we have saved state, restore it.  If we can reset the device,
 	 * even better.  Resetting with current state seems better than
diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
index ea4c0d2b0663..e163aa9f6144 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -11,6 +11,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/vfio_zdev.h>
+#include <linux/kvm_host.h>
 #include <asm/pci_clp.h>
 #include <asm/pci_io.h>
 
@@ -23,14 +24,15 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_base cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE,
-		.header.version = 1,
+		.header.version = 2,
 		.start_dma = zdev->start_dma,
 		.end_dma = zdev->end_dma,
 		.pchid = zdev->pchid,
 		.vfn = zdev->vfn,
 		.fmb_length = zdev->fmb_length,
 		.pft = zdev->pft,
-		.gid = zdev->pfgid
+		.gid = zdev->pfgid,
+		.fh = zdev->fh
 	};
 
 	return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@@ -43,14 +45,16 @@ static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_group cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP,
-		.header.version = 1,
+		.header.version = 2,
 		.dasm = zdev->dma_mask,
 		.msi_addr = zdev->msi_addr,
 		.flags = VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH,
 		.mui = zdev->fmb_update,
 		.noi = zdev->max_msi,
 		.maxstbl = ZPCI_MAX_WRITE_SIZE,
-		.version = zdev->version
+		.version = zdev->version,
+		.reserved = 0,
+		.imaxstbl = zdev->maxstbl
 	};
 
 	return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@@ -136,3 +140,26 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 
 	return ret;
 }
+
+int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
+{
+	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+
+	if (!zdev)
+		return -ENODEV;
+
+	if (!vdev->vdev.kvm)
+		return 0;
+
+	return kvm_s390_pci_register_kvm(zdev, vdev->vdev.kvm);
+}
+
+void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
+{
+	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+
+	if (!zdev || !vdev->vdev.kvm)
+		return;
+
+	kvm_s390_pci_unregister_kvm(zdev);
+}