From c435c54639aa5513ab877c8b014dd83d4ce6b40e Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:14 -0400 Subject: vfio/pci: introduce CONFIG_VFIO_PCI_ZDEV_KVM The current contents of vfio-pci-zdev are today only useful in a KVM environment; let's tie everything currently under vfio-pci-zdev to this Kconfig statement and require KVM in this case, reducing complexity (e.g. symbol lookups). Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-11-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- include/linux/vfio_pci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 23c176d4b073..63af2897939c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -206,7 +206,7 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) } #endif -#ifdef CONFIG_S390 +#ifdef CONFIG_VFIO_PCI_ZDEV_KVM extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps); #else -- cgit v1.2.3 From 3c5a1b6f0a18520a0edd0600fef6f1a8553b8fdc Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:19 -0400 Subject: KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding These routines will be wired into a kvm ioctl in order to respond to requests to enable / disable a device for Adapter Event Notifications / Adapter Interuption Forwarding. Reviewed-by: Christian Borntraeger Acked-by: Niklas Schnelle Signed-off-by: Matthew Rosato Link: https://lore.kernel.org/r/20220606203325.110625-16-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 247 +++++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 1 + arch/s390/pci/pci_insn.c | 1 + include/linux/sched/user.h | 3 +- 4 files changed, 251 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index d566551d3018..b232c8cbaa81 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "pci.h" struct zpci_aift *aift; @@ -152,6 +153,252 @@ unlock: return rc; } +/* Modify PCI: Register floating adapter interruption forwarding */ +static int kvm_zpci_set_airq(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT); + struct zpci_fib fib = {}; + u8 status; + + fib.fmt0.isc = zdev->kzdev->fib.fmt0.isc; + fib.fmt0.sum = 1; /* enable summary notifications */ + fib.fmt0.noi = airq_iv_end(zdev->aibv); + fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector); + fib.fmt0.aibvo = 0; + fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib.fmt0.aisbo = zdev->aisb & 63; + fib.gd = zdev->gisa; + + return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; +} + +/* Modify PCI: Unregister floating adapter interruption forwarding */ +static int kvm_zpci_clear_airq(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT); + struct zpci_fib fib = {}; + u8 cc, status; + + fib.gd = zdev->gisa; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc == 3 || (cc == 1 && status == 24)) + /* Function already gone or IRQs already deregistered. */ + cc = 0; + + return cc ? -EIO : 0; +} + +static inline void unaccount_mem(unsigned long nr_pages) +{ + struct user_struct *user = get_uid(current_user()); + + if (user) + atomic_long_sub(nr_pages, &user->locked_vm); + if (current->mm) + atomic64_sub(nr_pages, ¤t->mm->pinned_vm); +} + +static inline int account_mem(unsigned long nr_pages) +{ + struct user_struct *user = get_uid(current_user()); + unsigned long page_limit, cur_pages, new_pages; + + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + do { + cur_pages = atomic_long_read(&user->locked_vm); + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return -ENOMEM; + } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, + new_pages) != cur_pages); + + atomic64_add(nr_pages, ¤t->mm->pinned_vm); + + return 0; +} + +static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, + bool assist) +{ + struct page *pages[1], *aibv_page, *aisb_page = NULL; + unsigned int msi_vecs, idx; + struct zpci_gaite *gaite; + unsigned long hva, bit; + struct kvm *kvm; + phys_addr_t gaddr; + int rc = 0, gisc, npages, pcount = 0; + + /* + * Interrupt forwarding is only applicable if the device is already + * enabled for interpretation + */ + if (zdev->gisa == 0) + return -EINVAL; + + kvm = zdev->kzdev->kvm; + msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi); + + /* Get the associated forwarding ISC - if invalid, return the error */ + gisc = kvm_s390_gisc_register(kvm, fib->fmt0.isc); + if (gisc < 0) + return gisc; + + /* Replace AIBV address */ + idx = srcu_read_lock(&kvm->srcu); + hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv)); + npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages); + srcu_read_unlock(&kvm->srcu, idx); + if (npages < 1) { + rc = -EIO; + goto out; + } + aibv_page = pages[0]; + pcount++; + gaddr = page_to_phys(aibv_page) + (fib->fmt0.aibv & ~PAGE_MASK); + fib->fmt0.aibv = gaddr; + + /* Pin the guest AISB if one was specified */ + if (fib->fmt0.sum == 1) { + idx = srcu_read_lock(&kvm->srcu); + hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb)); + npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, + pages); + srcu_read_unlock(&kvm->srcu, idx); + if (npages < 1) { + rc = -EIO; + goto unpin1; + } + aisb_page = pages[0]; + pcount++; + } + + /* Account for pinned pages, roll back on failure */ + if (account_mem(pcount)) + goto unpin2; + + /* AISB must be allocated before we can fill in GAITE */ + mutex_lock(&aift->aift_lock); + bit = airq_iv_alloc_bit(aift->sbv); + if (bit == -1UL) + goto unlock; + zdev->aisb = bit; /* store the summary bit number */ + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | + AIRQ_IV_BITLOCK | + AIRQ_IV_GUESTVEC, + phys_to_virt(fib->fmt0.aibv)); + + spin_lock_irq(&aift->gait_lock); + gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * + sizeof(struct zpci_gaite)); + + /* If assist not requested, host will get all alerts */ + if (assist) + gaite->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa); + else + gaite->gisa = 0; + + gaite->gisc = fib->fmt0.isc; + gaite->count++; + gaite->aisbo = fib->fmt0.aisbo; + gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb & + ~PAGE_MASK)); + aift->kzdev[zdev->aisb] = zdev->kzdev; + spin_unlock_irq(&aift->gait_lock); + + /* Update guest FIB for re-issue */ + fib->fmt0.aisbo = zdev->aisb & 63; + fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib->fmt0.isc = gisc; + + /* Save some guest fib values in the host for later use */ + zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc; + zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv; + mutex_unlock(&aift->aift_lock); + + /* Issue the clp to setup the irq now */ + rc = kvm_zpci_set_airq(zdev); + return rc; + +unlock: + mutex_unlock(&aift->aift_lock); +unpin2: + if (fib->fmt0.sum == 1) + unpin_user_page(aisb_page); +unpin1: + unpin_user_page(aibv_page); +out: + return rc; +} + +static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) +{ + struct kvm_zdev *kzdev = zdev->kzdev; + struct zpci_gaite *gaite; + struct page *vpage = NULL, *spage = NULL; + int rc, pcount = 0; + u8 isc; + + if (zdev->gisa == 0) + return -EINVAL; + + mutex_lock(&aift->aift_lock); + + /* + * If the clear fails due to an error, leave now unless we know this + * device is about to go away (force) -- In that case clear the GAITE + * regardless. + */ + rc = kvm_zpci_clear_airq(zdev); + if (rc && !force) + goto out; + + if (zdev->kzdev->fib.fmt0.aibv == 0) + goto out; + spin_lock_irq(&aift->gait_lock); + gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * + sizeof(struct zpci_gaite)); + isc = gaite->gisc; + gaite->count--; + if (gaite->count == 0) { + /* Release guest AIBV and AISB */ + vpage = phys_to_page(kzdev->fib.fmt0.aibv); + if (gaite->aisb != 0) + spage = phys_to_page(gaite->aisb); + /* Clear the GAIT entry */ + gaite->aisb = 0; + gaite->gisc = 0; + gaite->aisbo = 0; + gaite->gisa = 0; + aift->kzdev[zdev->aisb] = 0; + /* Clear zdev info */ + airq_iv_free_bit(aift->sbv, zdev->aisb); + airq_iv_release(zdev->aibv); + zdev->aisb = 0; + zdev->aibv = NULL; + } + spin_unlock_irq(&aift->gait_lock); + kvm_s390_gisc_unregister(kzdev->kvm, isc); + kzdev->fib.fmt0.isc = 0; + kzdev->fib.fmt0.aibv = 0; + + if (vpage) { + unpin_user_page(vpage); + pcount++; + } + if (spage) { + unpin_user_page(spage); + pcount++; + } + if (pcount > 0) + unaccount_mem(pcount); +out: + mutex_unlock(&aift->aift_lock); + + return rc; +} + static int kvm_s390_pci_dev_open(struct zpci_dev *zdev) { struct kvm_zdev *kzdev; diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 9f7828d97605..9d091033fc02 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -20,6 +20,7 @@ struct kvm_zdev { struct zpci_dev *zdev; struct kvm *kvm; + struct zpci_fib fib; }; struct zpci_gaite { diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 5798178aec9d..56480be48244 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -92,6 +92,7 @@ u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status) return cc; } +EXPORT_SYMBOL_GPL(zpci_mod_fc); /* Refresh PCI Translations */ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 00ed419dd464..f054d0360a75 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -24,7 +24,8 @@ struct user_struct { kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ - defined(CONFIG_NET) || defined(CONFIG_IO_URING) + defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ + defined(CONFIG_VFIO_PCI_ZDEV_KVM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE -- cgit v1.2.3 From 8061d1c31f1a018281bc9877ecce44bfc779e21d Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:21 -0400 Subject: vfio-pci/zdev: add open/close device hooks During vfio-pci open_device, pass the KVM associated with the vfio group (if one exists). This is needed in order to pass a special indicator (GISA) to firmware to allow zPCI interpretation facilities to be used for only the specific KVM associated with the vfio-pci device. During vfio-pci close_device, unregister the notifier. Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20220606203325.110625-18-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_core.c | 10 +++++++++- drivers/vfio/pci/vfio_pci_zdev.c | 24 ++++++++++++++++++++++++ include/linux/vfio_pci_core.h | 10 ++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index a0d69ddaf90d..b1e5cfbadf38 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -316,10 +316,14 @@ 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; @@ -340,6 +344,8 @@ 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; @@ -418,6 +424,8 @@ 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..686f2e75e392 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -136,3 +137,26 @@ 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); +} diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 63af2897939c..d5d9e17f0156 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -209,12 +209,22 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) #ifdef CONFIG_VFIO_PCI_ZDEV_KVM extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps); +int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev); +void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev); #else static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, struct vfio_info_cap *caps) { return -ENODEV; } + +static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) +{ + return 0; +} + +static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) +{} #endif /* Will be exported for vfio pci drivers usage */ -- cgit v1.2.3 From faf3bfcb895037ae2a8b89d1048090c9e1291cae Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:22 -0400 Subject: vfio-pci/zdev: add function handle to clp base capability The function handle is a system-wide unique identifier for a zPCI device. With zPCI instruction interpretation, the host will no longer be executing the zPCI instructions on behalf of the guest. As a result, the guest needs to use the real function handle in order for firmware to associate the instruction with the proper PCI function. Let's provide that handle to the guest. Reviewed-by: Christian Borntraeger Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-19-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 5 +++-- include/uapi/linux/vfio_zdev.h | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 686f2e75e392..4f28cdd7ecd1 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -24,14 +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)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index b4309397b6b2..78c022af3d29 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base { __u16 fmb_length; /* Measurement Block Length (in bytes) */ __u8 pft; /* PCI Function Type */ __u8 gid; /* PCI function group ID */ + /* End of version 1 */ + __u32 fh; /* PCI function handle */ + /* End of version 2 */ }; /** -- cgit v1.2.3 From ba6090ff8ae01b41288be87ed9f6bed3d8cf5961 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:23 -0400 Subject: vfio-pci/zdev: different maxstbl for interpreted devices When doing load/store interpretation, the maximum store block length is determined by the underlying firmware, not the host kernel API. Reflect that in the associated Query PCI Function Group clp capability and let userspace decide which is appropriate to present to the guest. Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-20-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 6 ++++-- include/uapi/linux/vfio_zdev.h | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 4f28cdd7ecd1..e163aa9f6144 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -45,14 +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)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index 78c022af3d29..77f2aff1f27e 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -50,6 +50,10 @@ struct vfio_device_info_cap_zpci_group { __u16 noi; /* Maximum number of MSIs */ __u16 maxstbl; /* Maximum Store Block Length */ __u8 version; /* Supported PCI Version */ + /* End of version 1 */ + __u8 reserved; + __u16 imaxstbl; /* Maximum Interpreted Store Block Length */ + /* End of version 2 */ }; /** -- cgit v1.2.3 From db1c875e0539518e3d5fe9876ef50975cf4476bb Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:24 -0400 Subject: KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices The KVM_S390_ZPCI_OP ioctl provides a mechanism for managing hardware-assisted virtualization features for s390x zPCI passthrough. Add the first 2 operations, which can be used to enable/disable the specified device for Adapter Event Notification interpretation. Signed-off-by: Matthew Rosato Acked-by: Pierre Morel Reviewed-by: Thomas Huth Link: https://lore.kernel.org/r/20220606203325.110625-21-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/api.rst | 47 +++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 16 ++++++++ arch/s390/kvm/pci.c | 85 ++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 2 + include/uapi/linux/kvm.h | 31 +++++++++++++++ 5 files changed, 181 insertions(+) (limited to 'include') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 11e00a46c610..d58354e9af8f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5802,6 +5802,53 @@ of CPUID leaf 0xD on the host. This ioctl injects an event channel interrupt directly to the guest vCPU. +4.137 KVM_S390_ZPCI_OP +-------------------- + +:Capability: KVM_CAP_S390_ZPCI_OP +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_zpci_op (in) +: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_AEN */ + 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_aen; + __u64 reserved[8]; + } u; + }; + +The type of operation is specified in the "op" field. +KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event +notification interpretation, which will allow firmware delivery of adapter +events directly to the vm, with KVM providing a backup delivery mechanism; +KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of +adapter event notifications. + +The target zPCI function must also be specified via the "fh" field. For the +KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware +delivery must be provided via the "reg_aen" struct. + +The "pad" and "reserved" fields may be used for future extensions and should be +set to 0s by userspace. + 5. The kvm_run structure ======================== diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4758bb731199..f214e0fc62ed 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -618,6 +618,9 @@ 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: + r = kvm_s390_pci_interp_allowed(); + break; default: r = 0; } @@ -2629,6 +2632,19 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_S390_ZPCI_OP: { + struct kvm_s390_zpci_op args; + + r = -EINVAL; + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + break; + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + r = kvm_s390_pci_zpci_op(kvm, &args); + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 24211741deb0..4946fb7757d6 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -585,6 +585,91 @@ void kvm_s390_pci_clear_list(struct kvm *kvm) spin_unlock(&kvm->arch.kzdev_list_lock); } +static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh) +{ + struct zpci_dev *zdev = NULL; + struct kvm_zdev *kzdev; + + spin_lock(&kvm->arch.kzdev_list_lock); + list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) { + if (kzdev->zdev->fh == fh) { + zdev = kzdev->zdev; + break; + } + } + spin_unlock(&kvm->arch.kzdev_list_lock); + + return zdev; +} + +static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev, + struct kvm_s390_zpci_op *args) +{ + struct zpci_fib fib = {}; + bool hostflag; + + fib.fmt0.aibv = args->u.reg_aen.ibv; + fib.fmt0.isc = args->u.reg_aen.isc; + fib.fmt0.noi = args->u.reg_aen.noi; + if (args->u.reg_aen.sb != 0) { + fib.fmt0.aisb = args->u.reg_aen.sb; + fib.fmt0.aisbo = args->u.reg_aen.sbo; + fib.fmt0.sum = 1; + } else { + fib.fmt0.aisb = 0; + fib.fmt0.aisbo = 0; + fib.fmt0.sum = 0; + } + + hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST); + return kvm_s390_pci_aif_enable(zdev, &fib, hostflag); +} + +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; + + zdev = get_zdev_from_kvm_by_fh(kvm, args->fh); + if (!zdev) + return -ENODEV; + + mutex_lock(&zdev->kzdev_lock); + mutex_lock(&kvm->lock); + + kzdev = zdev->kzdev; + if (!kzdev) { + r = -ENODEV; + goto out; + } + if (kzdev->kvm != kvm) { + r = -EPERM; + goto out; + } + + switch (args->op) { + case KVM_S390_ZPCIOP_REG_AEN: + /* Fail on unknown flags */ + if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) { + r = -EINVAL; + break; + } + r = kvm_s390_pci_zpci_reg_aen(zdev, args); + break; + case KVM_S390_ZPCIOP_DEREG_AEN: + r = kvm_s390_pci_aif_disable(zdev, false); + break; + default: + r = -EINVAL; + } + +out: + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + return r; +} + 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 fb2b91b76e0c..0351382e990f 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -59,6 +59,8 @@ 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_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args); + int kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..2f302e2287d1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1157,6 +1157,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_ZPCI_OP 221 #ifdef KVM_CAP_IRQ_ROUTING @@ -2118,4 +2119,34 @@ 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, 0xd1, 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_AEN */ + 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_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3