From 9251ba89d446b5e108b2e43bd9e01e0871077e9f Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:20 -0400 Subject: [PATCH] KVM: s390: pci: add routines to start/stop interpretive execution These routines will be invoked at the time an s390x vfio-pci device is associated with a KVM (or when the association is removed), allowing the zPCI device to enable or disable load/store intepretation mode; this requires the host zPCI device to inform firmware of the unique token (GISA designation) that is associated with the owning KVM. Signed-off-by: Matthew Rosato Acked-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-17-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger (backported from commit 09340b2fca007509c3cbc34fdc97961e0abfc589) Signed-off-by: Matthew Rosato --- arch/s390/include/asm/kvm_host.h | 18 ++++ arch/s390/include/asm/pci.h | 1 + arch/s390/kvm/kvm-s390.c | 15 +++ arch/s390/kvm/pci.c | 162 +++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 5 + arch/s390/pci/pci.c | 4 + 6 files changed, 205 insertions(+) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 38982c1de413..543997217694 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -965,6 +966,8 @@ struct kvm_arch{ DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); struct kvm_s390_gisa_interrupt gisa_int; struct kvm_s390_pv pv; + struct list_head kzdev_list; + spinlock_t kzdev_list_lock; }; #define KVM_HVA_ERR_BAD (-1UL) @@ -1017,4 +1020,19 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu); +#define __KVM_HAVE_ARCH_VM_FREE +void kvm_arch_free_vm(struct kvm *kvm); + +#ifdef CONFIG_VFIO_PCI_ZDEV_KVM +int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm); +void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev); +#else +static inline int kvm_s390_pci_register_kvm(struct zpci_dev *dev, + struct kvm *kvm) +{ + return -EPERM; +} +static inline void kvm_s390_pci_unregister_kvm(struct zpci_dev *dev) {} +#endif + #endif diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index b57c38ac1dff..d49b5e94398e 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -194,6 +194,7 @@ struct zpci_dev { /* IOMMU and passthrough */ struct s390_domain *s390_domain; /* s390 IOMMU domain data */ struct kvm_zdev *kzdev; + struct mutex kzdev_lock; }; static inline bool zdev_enabled(struct zpci_dev *zdev) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0a21ddecc251..44470ad04988 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2829,6 +2829,14 @@ static void sca_dispose(struct kvm *kvm) kvm->arch.sca = NULL; } +void kvm_arch_free_vm(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_clear_list(kvm); + + __kvm_arch_free_vm(kvm); +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { gfp_t alloc_flags = GFP_KERNEL_ACCOUNT; @@ -2911,6 +2919,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_s390_crypto_init(kvm); + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { + mutex_lock(&kvm->lock); + kvm_s390_pci_init_list(kvm); + kvm_s390_vcpu_pci_enable_interp(kvm); + mutex_unlock(&kvm->lock); + } + mutex_init(&kvm->arch.float_int.ais_lock); spin_lock_init(&kvm->arch.float_int.lock); for (i = 0; i < FIRQ_LIST_COUNT; i++) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index b232c8cbaa81..24211741deb0 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -12,7 +12,9 @@ #include #include #include +#include #include "pci.h" +#include "kvm-s390.h" struct zpci_aift *aift; @@ -423,6 +425,166 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev) kfree(kzdev); } + +/* + * Register device with the specified KVM. If interpetation facilities are + * available, enable them and let userspace indicate whether or not they will + * be used (specify SHM bit to disable). + */ +int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm) +{ + int rc; + + if (!zdev) + return -EINVAL; + + mutex_lock(&zdev->kzdev_lock); + + if (zdev->kzdev || zdev->gisa != 0 || !kvm) { + mutex_unlock(&zdev->kzdev_lock); + return -EINVAL; + } + + kvm_get_kvm(kvm); + + mutex_lock(&kvm->lock); + + rc = kvm_s390_pci_dev_open(zdev); + if (rc) + goto err; + + /* + * If interpretation facilities aren't available, add the device to + * the kzdev list but don't enable for interpretation. + */ + if (!kvm_s390_pci_interp_allowed()) + goto out; + + /* + * If this is the first request to use an interpreted device, make the + * necessary vcpu changes + */ + if (!kvm->arch.use_zpci_interp) + kvm_s390_vcpu_pci_enable_interp(kvm); + + if (zdev_enabled(zdev)) { + rc = zpci_disable_device(zdev); + if (rc) + goto err; + } + + /* + * Store information about the identity of the kvm guest allowed to + * access this device via interpretation to be used by host CLP + */ + zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa); + + rc = zpci_enable_device(zdev); + if (rc) + goto clear_gisa; + + /* Re-register the IOMMU that was already created */ + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table)); + if (rc) + goto clear_gisa; + +out: + zdev->kzdev->kvm = kvm; + + spin_lock(&kvm->arch.kzdev_list_lock); + list_add_tail(&zdev->kzdev->entry, &kvm->arch.kzdev_list); + spin_unlock(&kvm->arch.kzdev_list_lock); + + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + return 0; + +clear_gisa: + zdev->gisa = 0; +err: + if (zdev->kzdev) + kvm_s390_pci_dev_release(zdev); + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + kvm_put_kvm(kvm); + return rc; +} +EXPORT_SYMBOL_GPL(kvm_s390_pci_register_kvm); + +void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev) +{ + struct kvm *kvm; + + if (!zdev) + return; + + mutex_lock(&zdev->kzdev_lock); + + if (WARN_ON(!zdev->kzdev)) { + mutex_unlock(&zdev->kzdev_lock); + return; + } + + kvm = zdev->kzdev->kvm; + mutex_lock(&kvm->lock); + + /* + * A 0 gisa means interpretation was never enabled, just remove the + * device from the list. + */ + if (zdev->gisa == 0) + goto out; + + /* Forwarding must be turned off before interpretation */ + if (zdev->kzdev->fib.fmt0.aibv != 0) + kvm_s390_pci_aif_disable(zdev, true); + + /* Remove the host CLP guest designation */ + zdev->gisa = 0; + + if (zdev_enabled(zdev)) { + if (zpci_disable_device(zdev)) + goto out; + } + + if (zpci_enable_device(zdev)) + goto out; + + /* Re-register the IOMMU that was already created */ + zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table)); + +out: + spin_lock(&kvm->arch.kzdev_list_lock); + list_del(&zdev->kzdev->entry); + spin_unlock(&kvm->arch.kzdev_list_lock); + kvm_s390_pci_dev_release(zdev); + + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + + kvm_put_kvm(kvm); +} +EXPORT_SYMBOL_GPL(kvm_s390_pci_unregister_kvm); + +void kvm_s390_pci_init_list(struct kvm *kvm) +{ + spin_lock_init(&kvm->arch.kzdev_list_lock); + INIT_LIST_HEAD(&kvm->arch.kzdev_list); +} + +void kvm_s390_pci_clear_list(struct kvm *kvm) +{ + /* + * This list should already be empty, either via vfio device closures + * or kvm fd cleanup. + */ + spin_lock(&kvm->arch.kzdev_list_lock); + WARN_ON_ONCE(!list_empty(&kvm->arch.kzdev_list)); + spin_unlock(&kvm->arch.kzdev_list_lock); +} + int kvm_s390_pci_init(void) { aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 9d091033fc02..fb2b91b76e0c 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -21,6 +22,7 @@ struct kvm_zdev { struct zpci_dev *zdev; struct kvm *kvm; struct zpci_fib fib; + struct list_head entry; }; struct zpci_gaite { @@ -54,6 +56,9 @@ static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift, int kvm_s390_pci_aen_init(u8 nisc); void kvm_s390_pci_aen_exit(void); +void kvm_s390_pci_init_list(struct kvm *kvm); +void kvm_s390_pci_clear_list(struct kvm *kvm); + int kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 877f03c9291a..b0f8f10efc16 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -132,6 +132,7 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status); return cc; } +EXPORT_SYMBOL_GPL(zpci_register_ioat); /* Modify PCI: Unregister I/O address translation parameters */ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) @@ -712,6 +713,7 @@ int zpci_enable_device(struct zpci_dev *zdev) zpci_update_fh(zdev, fh); return rc; } +EXPORT_SYMBOL_GPL(zpci_enable_device); int zpci_disable_device(struct zpci_dev *zdev) { @@ -735,6 +737,7 @@ int zpci_disable_device(struct zpci_dev *zdev) } return rc; } +EXPORT_SYMBOL_GPL(zpci_disable_device); /** * zpci_hot_reset_device - perform a reset of the given zPCI function @@ -828,6 +831,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) kref_init(&zdev->kref); mutex_init(&zdev->lock); + mutex_init(&zdev->kzdev_lock); rc = zpci_init_iommu(zdev); if (rc) -- 2.40.1