[PATCH v4 28/32] KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices

From: Matthew Rosato
Date: Mon Mar 14 2022 - 15:50:56 EST

Next message: Matthew Rosato: "[PATCH v4 29/32] vfio-pci/zdev: add DTSM to clp group capability"
Previous message: Nathan Chancellor: "[PATCH 2/2] x86/Kconfig: Do not allow CONFIG_X86_X32_ABI=y with llvm-objcopy"
In reply to: Matthew Rosato: "[PATCH v4 27/32] KVM: s390: intercept the rpcit instruction"
Next in thread: Matthew Rosato: "[PATCH v4 29/32] vfio-pci/zdev: add DTSM to clp group capability"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

The KVM_S390_ZPCI_OP ioctl provides a series of operations that
can be invoked to manage hardware-assisted virtualization features
for s390x PCI passthrough.

Signed-off-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
---
Documentation/virt/kvm/api.rst | 60 ++++++++++++++++++++++++++
arch/s390/kvm/kvm-s390.c | 26 ++++++++++++
arch/s390/kvm/pci.c | 77 ++++++++++++++++++++++++++++++++++
arch/s390/kvm/pci.h | 3 +-
include/uapi/linux/kvm.h | 43 +++++++++++++++++++
5 files changed, 208 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9f3172376ec3..c642ff891cf2 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5574,6 +5574,66 @@ enabled with ``arch_prctl()``, but this may change in the future.
The offsets of the state save areas in struct kvm_xsave follow the contents
of CPUID leaf 0xD on the host.

+4.134 KVM_S390_ZPCI_OP
+--------------------
+
+:Capability: KVM_CAP_S390_ZPCI_OP
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_zpci_op (in, out)
+:Returns: 0 on success, <0 on error
+
+Used to manage hardware-assisted virtualization features for zPCI devices.
+
+Parameters are specified via the following structure::
+
+ struct kvm_s390_zpci_op {
+ /* in */
+ __u32 fh; /* target device */
+ __u8 op; /* operation to perform */
+ __u8 pad[3];
+ union {
+ /* for KVM_S390_ZPCIOP_REG_INT */
+ struct {
+ __u64 ibv; /* Guest addr of interrupt bit vector */
+ __u64 sb; /* Guest addr of summary bit */
+ __u32 flags;
+ __u32 noi; /* Number of interrupts */
+ __u8 isc; /* Guest interrupt subclass */
+ __u8 sbo; /* Offset of guest summary bit vector */
+ __u16 pad;
+ } reg_int;
+ /* for KVM_S390_ZPCIOP_REG_IOAT */
+ struct {
+ __u64 iota; /* I/O Translation settings */
+ } reg_ioat;
+ __u8 reserved[64];
+ } u;
+ /* out */
+ __u32 newfh; /* updated device handle */
+ };
+
+The type of operation is specified in the "op" field.
+KVM_S390_ZPCIOP_INIT is used to assocaite a zPCI function with this vm.
+Conversely, KVM_S390_ZPCIOP_END is used to terminate that association.
+KVM_S390_ZPCIOP_START_INTERP is used to enable interpretive execution
+for the specified zPCI function for this VM; KVM_S390_ZPCIOP_STOP_INTERP
+is used to subsequently disable interpretive execution.
+KVM_S390_ZPCIOP_REG_INT is used to register the VM for adapter interruption
+forwarding, which will allow firmware delivery of interrupts directly to
+the vm, with KVM providing a backup delivery mechanism;
+KVM_S390_ZPCIOP_DEREG_INT is used to subsequently disable interrupt forwarding.
+KVM_S390_ZPCIOP_REG_IOAT is used to enable KVM-managed IOMMU ops to begin
+synchronizing guest and host DMA tables; KVM_S390_ZPCIOP_DEREG_IOAT is used
+to subsequently disable IOMMU mapping.
+
+The target zPCI function must also be specified via the "fh" field. For the
+KVM_S390_ZPCIOP_REG_INT operation, additional information to establish the
+interrupt forwarding must be provided via the "reg_int" struct. For the
+KVM_S390_ZPCIOP_REG_IOAT operation, guest table format and location must be
+specified via the "reg_ioat" struct.
+
+The "reserved" field is meant for future extensions.

5. The kvm_run structure
========================
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 84acaf59a7d3..613101ba29be 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -616,6 +616,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_PROTECTED:
r = is_prot_virt_host();
break;
+ case KVM_CAP_S390_ZPCI_OP:
+ if (IS_ENABLED(CONFIG_S390_KVM_IOMMU) && test_facility(69) &&
+ test_facility(70) && test_facility(71) &&
+ test_facility(72)) {
+ r = 1;
+ } else {
+ r = 0;
+ }
+ break;
default:
r = 0;
}
@@ -2532,6 +2541,23 @@ long kvm_arch_vm_ioctl(struct file *filp,
}
break;
}
+ case KVM_S390_ZPCI_OP: {
+ struct kvm_s390_zpci_op args;
+
+ r = -EINVAL;
+ if (!IS_ENABLED(CONFIG_VFIO_PCI))
+ break;
+ if (copy_from_user(&args, argp, sizeof(args))) {
+ r = -EFAULT;
+ break;
+ }
+ r = kvm_s390_pci_zpci_op(kvm, &args);
+ if (r)
+ break;
+ if (copy_to_user(argp, &args, sizeof(args)))
+ r = -EFAULT;
+ break;
+ }
default:
r = -ENOTTY;
}
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 40d2fadbfbd5..15b581915cd7 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -739,6 +739,83 @@ void kvm_s390_pci_clear_list(struct kvm *kvm)
}
}

+static int kvm_s390_pci_zpci_reg_int(struct zpci_dev *zdev,
+ struct kvm_s390_zpci_op *args)
+{
+ struct zpci_fib fib = {};
+
+ fib.fmt0.aibv = args->u.reg_int.ibv;
+ fib.fmt0.isc = args->u.reg_int.isc;
+ fib.fmt0.noi = args->u.reg_int.noi;
+ if (args->u.reg_int.sb != 0) {
+ fib.fmt0.aisb = args->u.reg_int.sb;
+ fib.fmt0.aisbo = args->u.reg_int.sbo;
+ fib.fmt0.sum = 1;
+ } else {
+ fib.fmt0.aisb = 0;
+ fib.fmt0.aisbo = 0;
+ fib.fmt0.sum = 0;
+ }
+
+ if (args->u.reg_int.flags & KVM_S390_ZPCIOP_REGINT_HOST)
+ return kvm_s390_pci_aif_enable(zdev, &fib, true);
+ else
+ return kvm_s390_pci_aif_enable(zdev, &fib, false);
+}
+
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args)
+{
+ struct kvm_zdev *kzdev;
+ struct zpci_dev *zdev;
+ int r;
+
+ if (args->op == KVM_S390_ZPCIOP_INIT) {
+ zdev = get_zdev_by_fh(args->fh);
+ if (!zdev)
+ return -ENODEV;
+ } else {
+ kzdev = get_kzdev_by_fh(kvm, args->fh);
+ if (!kzdev || !kzdev->zdev)
+ return -ENODEV;
+ zdev = kzdev->zdev;
+ }
+
+ switch (args->op) {
+ case KVM_S390_ZPCIOP_INIT:
+ r = kvm_s390_pci_zpci_start(kvm, zdev);
+ break;
+ case KVM_S390_ZPCIOP_END:
+ r = kvm_s390_pci_zpci_stop(kvm, zdev);
+ break;
+ case KVM_S390_ZPCIOP_START_INTERP:
+ r = kvm_s390_pci_interp_enable(zdev);
+ break;
+ case KVM_S390_ZPCIOP_STOP_INTERP:
+ r = kvm_s390_pci_interp_disable(zdev, false);
+ break;
+ case KVM_S390_ZPCIOP_REG_INT:
+ r = kvm_s390_pci_zpci_reg_int(zdev, args);
+ break;
+ case KVM_S390_ZPCIOP_DEREG_INT:
+ r = kvm_s390_pci_aif_disable(zdev, false);
+ break;
+ case KVM_S390_ZPCIOP_REG_IOAT:
+ r = kvm_s390_pci_ioat_enable(zdev, args->u.reg_ioat.iota);
+ break;
+ case KVM_S390_ZPCIOP_DEREG_IOAT:
+ r = kvm_s390_pci_ioat_disable(zdev);
+ break;
+ default:
+ r = -EINVAL;
+ }
+
+ /* On success, always return the current host function handle */
+ if (r == 0)
+ args->newfh = zdev->fh;
+
+ return r;
+}
+
int kvm_s390_pci_init(void)
{
int rc;
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
index 2cb1b27396c1..c30b0bacca00 100644
--- a/arch/s390/kvm/pci.h
+++ b/arch/s390/kvm/pci.h
@@ -12,6 +12,7 @@

#include <linux/pci.h>
#include <linux/mutex.h>
+#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/airq.h>
#include <asm/kvm_pci.h>
@@ -56,7 +57,7 @@ int kvm_s390_pci_zpci_start(struct kvm *kvm, struct zpci_dev *zdev);
int kvm_s390_pci_zpci_stop(struct kvm *kvm, struct zpci_dev *zdev);
void kvm_s390_pci_init_list(struct kvm *kvm);
void kvm_s390_pci_clear_list(struct kvm *kvm);
-
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args);
int kvm_s390_pci_init(void);

#endif /* __KVM_S390_PCI_H */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 507ee1f2aa96..be8693ccc833 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1135,6 +1135,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
#define KVM_CAP_PPC_AIL_MODE_3 210
+#define KVM_CAP_S390_ZPCI_OP 211

#ifdef KVM_CAP_IRQ_ROUTING

@@ -2049,4 +2050,46 @@ struct kvm_stats_desc {
/* Available with KVM_CAP_XSAVE2 */
#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)

+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd0, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+ /* in */
+ __u32 fh; /* target device */
+ __u8 op; /* operation to perform */
+ __u8 pad[3];
+ union {
+ /* for KVM_S390_ZPCIOP_REG_INT */
+ struct {
+ __u64 ibv; /* Guest addr of interrupt bit vector */
+ __u64 sb; /* Guest addr of summary bit */
+ __u32 flags;
+ __u32 noi; /* Number of interrupts */
+ __u8 isc; /* Guest interrupt subclass */
+ __u8 sbo; /* Offset of guest summary bit vector */
+ __u16 pad;
+ } reg_int;
+ /* for KVM_S390_ZPCIOP_REG_IOAT */
+ struct {
+ __u64 iota; /* I/O Translation settings */
+ } reg_ioat;
+ __u8 reserved[64];
+ } u;
+ /* out */
+ __u32 newfh; /* updated device handle */
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_INIT 0
+#define KVM_S390_ZPCIOP_END 1
+#define KVM_S390_ZPCIOP_START_INTERP 2
+#define KVM_S390_ZPCIOP_STOP_INTERP 3
+#define KVM_S390_ZPCIOP_REG_INT 4
+#define KVM_S390_ZPCIOP_DEREG_INT 5
+#define KVM_S390_ZPCIOP_REG_IOAT 6
+#define KVM_S390_ZPCIOP_DEREG_IOAT 7
+
+/* flags for kvm_s390_zpci_op->u.reg_int.flags */
+#define KVM_S390_ZPCIOP_REGINT_HOST (1 << 0)
+
#endif /* __LINUX_KVM_H */
--
2.27.0

Next message: Matthew Rosato: "[PATCH v4 29/32] vfio-pci/zdev: add DTSM to clp group capability"
Previous message: Nathan Chancellor: "[PATCH 2/2] x86/Kconfig: Do not allow CONFIG_X86_X32_ABI=y with llvm-objcopy"
In reply to: Matthew Rosato: "[PATCH v4 27/32] KVM: s390: intercept the rpcit instruction"
Next in thread: Matthew Rosato: "[PATCH v4 29/32] vfio-pci/zdev: add DTSM to clp group capability"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]