diff options
Diffstat (limited to 'drivers/vfio/pci')
| -rw-r--r-- | drivers/vfio/pci/Kconfig | 6 | ||||
| -rw-r--r-- | drivers/vfio/pci/Makefile | 1 | ||||
| -rw-r--r-- | drivers/vfio/pci/trace.h | 102 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci.c | 202 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_nvlink2.c | 482 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_private.h | 26 |
6 files changed, 793 insertions, 26 deletions
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 42dc1d3d71cf..d0f8e4f5a039 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -38,3 +38,9 @@ config VFIO_PCI_IGD and LPC bridge config space. To enable Intel IGD assignment through vfio-pci, say Y. + +config VFIO_PCI_NVLINK2 + def_bool y + depends on VFIO_PCI && PPC_POWERNV + help + VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 76d8ec058edd..9662c063a6b1 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,5 +1,6 @@ vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o +vfio-pci-$(CONFIG_VFIO_PCI_NVLINK2) += vfio_pci_nvlink2.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/trace.h b/drivers/vfio/pci/trace.h new file mode 100644 index 000000000000..228ccdb8d1c8 --- /dev/null +++ b/drivers/vfio/pci/trace.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * VFIO PCI mmap/mmap_fault tracepoints + * + * Copyright (C) 2018 IBM Corp. All rights reserved. + * Author: Alexey Kardashevskiy <aik@ozlabs.ru> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vfio_pci + +#if !defined(_TRACE_VFIO_PCI_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VFIO_PCI_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(vfio_pci_nvgpu_mmap_fault, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + vm_fault_t ret), + TP_ARGS(pdev, hpa, ua, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->ret) +); + +TRACE_EVENT(vfio_pci_nvgpu_mmap, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + unsigned long size, int ret), + TP_ARGS(pdev, hpa, ua, size, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(unsigned long, size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->size = size; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx size=%lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->size, __entry->ret) +); + +TRACE_EVENT(vfio_pci_npu2_mmap, + TP_PROTO(struct pci_dev *pdev, unsigned long hpa, unsigned long ua, + unsigned long size, int ret), + TP_ARGS(pdev, hpa, ua, size, ret), + + TP_STRUCT__entry( + __field(const char *, name) + __field(unsigned long, hpa) + __field(unsigned long, ua) + __field(unsigned long, size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->name = dev_name(&pdev->dev), + __entry->hpa = hpa; + __entry->ua = ua; + __entry->size = size; + __entry->ret = ret; + ), + + TP_printk("%s: %lx -> %lx size=%lx ret=%d", __entry->name, __entry->hpa, + __entry->ua, __entry->size, __entry->ret) +); + +#endif /* _TRACE_VFIO_PCI_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 50cdedfca9fe..ff60bd1ea587 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -56,8 +56,6 @@ module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(disable_idle_d3, "Disable using the PCI D3 low power state for idle, unused devices"); -static DEFINE_MUTEX(driver_lock); - static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -289,14 +287,37 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) if (ret) { dev_warn(&vdev->pdev->dev, "Failed to setup Intel IGD regions\n"); - vfio_pci_disable(vdev); - return ret; + goto disable_exit; + } + } + + if (pdev->vendor == PCI_VENDOR_ID_NVIDIA && + IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) { + ret = vfio_pci_nvdia_v100_nvlink2_init(vdev); + if (ret && ret != -ENODEV) { + dev_warn(&vdev->pdev->dev, + "Failed to setup NVIDIA NV2 RAM region\n"); + goto disable_exit; + } + } + + if (pdev->vendor == PCI_VENDOR_ID_IBM && + IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) { + ret = vfio_pci_ibm_npu2_init(vdev); + if (ret && ret != -ENODEV) { + dev_warn(&vdev->pdev->dev, + "Failed to setup NVIDIA NV2 ATSD region\n"); + goto disable_exit; } } vfio_pci_probe_mmaps(vdev); return 0; + +disable_exit: + vfio_pci_disable(vdev); + return ret; } static void vfio_pci_disable(struct vfio_pci_device *vdev) @@ -393,14 +414,14 @@ static void vfio_pci_release(void *device_data) { struct vfio_pci_device *vdev = device_data; - mutex_lock(&driver_lock); + mutex_lock(&vdev->reflck->lock); if (!(--vdev->refcnt)) { vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); } - mutex_unlock(&driver_lock); + mutex_unlock(&vdev->reflck->lock); module_put(THIS_MODULE); } @@ -413,7 +434,7 @@ static int vfio_pci_open(void *device_data) if (!try_module_get(THIS_MODULE)) return -ENODEV; - mutex_lock(&driver_lock); + mutex_lock(&vdev->reflck->lock); if (!vdev->refcnt) { ret = vfio_pci_enable(vdev); @@ -424,7 +445,7 @@ static int vfio_pci_open(void *device_data) } vdev->refcnt++; error: - mutex_unlock(&driver_lock); + mutex_unlock(&vdev->reflck->lock); if (ret) module_put(THIS_MODULE); return ret; @@ -750,6 +771,12 @@ static long vfio_pci_ioctl(void *device_data, if (ret) return ret; + if (vdev->region[i].ops->add_capability) { + ret = vdev->region[i].ops->add_capability(vdev, + &vdev->region[i], &caps); + if (ret) + return ret; + } } } @@ -1117,6 +1144,15 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) return -EINVAL; if ((vma->vm_flags & VM_SHARED) == 0) return -EINVAL; + if (index >= VFIO_PCI_NUM_REGIONS) { + int regnum = index - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_region *region = vdev->region + regnum; + + if (region && region->ops && region->ops->mmap && + (region->flags & VFIO_REGION_INFO_FLAG_MMAP)) + return region->ops->mmap(vdev, region, vma); + return -EINVAL; + } if (index >= VFIO_PCI_ROM_REGION_INDEX) return -EINVAL; if (!vdev->bar_mmap_supported[index]) @@ -1187,6 +1223,9 @@ static const struct vfio_device_ops vfio_pci_ops = { .request = vfio_pci_request, }; +static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev); +static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck); + static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct vfio_pci_device *vdev; @@ -1233,6 +1272,14 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } + ret = vfio_pci_reflck_attach(vdev); + if (ret) { + vfio_del_group_dev(&pdev->dev); + vfio_iommu_group_put(group, &pdev->dev); + kfree(vdev); + return ret; + } + if (vfio_pci_is_vga(pdev)) { vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode); vga_set_legacy_decoding(pdev, @@ -1264,6 +1311,8 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; + vfio_pci_reflck_put(vdev->reflck); + vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); kfree(vdev->region); mutex_destroy(&vdev->ioeventfds_lock); @@ -1320,16 +1369,97 @@ static struct pci_driver vfio_pci_driver = { .err_handler = &vfio_err_handlers, }; +static DEFINE_MUTEX(reflck_lock); + +static struct vfio_pci_reflck *vfio_pci_reflck_alloc(void) +{ + struct vfio_pci_reflck *reflck; + + reflck = kzalloc(sizeof(*reflck), GFP_KERNEL); + if (!reflck) + return ERR_PTR(-ENOMEM); + + kref_init(&reflck->kref); + mutex_init(&reflck->lock); + + return reflck; +} + +static void vfio_pci_reflck_get(struct vfio_pci_reflck *reflck) +{ + kref_get(&reflck->kref); +} + +static int vfio_pci_reflck_find(struct pci_dev *pdev, void *data) +{ + struct vfio_pci_reflck **preflck = data; + struct vfio_device *device; + struct vfio_pci_device *vdev; + + device = vfio_device_get_from_dev(&pdev->dev); + if (!device) + return 0; + + if (pci_dev_driver(pdev) != &vfio_pci_driver) { + vfio_device_put(device); + return 0; + } + + vdev = vfio_device_data(device); + + if (vdev->reflck) { + vfio_pci_reflck_get(vdev->reflck); + *preflck = vdev->reflck; + vfio_device_put(device); + return 1; + } + + vfio_device_put(device); + return 0; +} + +static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev) +{ + bool slot = !pci_probe_reset_slot(vdev->pdev->slot); + + mutex_lock(&reflck_lock); + + if (pci_is_root_bus(vdev->pdev->bus) || + vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_reflck_find, + &vdev->reflck, slot) <= 0) + vdev->reflck = vfio_pci_reflck_alloc(); + + mutex_unlock(&reflck_lock); + + return PTR_ERR_OR_ZERO(vdev->reflck); +} + +static void vfio_pci_reflck_release(struct kref *kref) +{ + struct vfio_pci_reflck *reflck = container_of(kref, + struct vfio_pci_reflck, + kref); + + kfree(reflck); + mutex_unlock(&reflck_lock); +} + +static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck) +{ + kref_put_mutex(&reflck->kref, vfio_pci_reflck_release, &reflck_lock); +} + struct vfio_devices { struct vfio_device **devices; int cur_index; int max_index; }; -static int vfio_pci_get_devs(struct pci_dev *pdev, void *data) +static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data) { struct vfio_devices *devs = data; struct vfio_device *device; + struct vfio_pci_device *vdev; if (devs->cur_index == devs->max_index) return -ENOSPC; @@ -1343,16 +1473,28 @@ static int vfio_pci_get_devs(struct pci_dev *pdev, void *data) return -EBUSY; } + vdev = vfio_device_data(device); + + /* Fault if the device is not unused */ + if (vdev->refcnt) { + vfio_device_put(device); + return -EBUSY; + } + devs->devices[devs->cur_index++] = device; return 0; } /* - * Attempt to do a bus/slot reset if there are devices affected by a reset for - * this device that are needs_reset and all of the affected devices are unused - * (!refcnt). Callers are required to hold driver_lock when calling this to - * prevent device opens and concurrent bus reset attempts. We prevent device - * unbinds by acquiring and holding a reference to the vfio_device. + * If a bus or slot reset is available for the provided device and: + * - All of the devices affected by that bus or slot reset are unused + * (!refcnt) + * - At least one of the affected devices is marked dirty via + * needs_reset (such as by lack of FLR support) + * Then attempt to perform that bus or slot reset. Callers are required + * to hold vdev->reflck->lock, protecting the bus/slot reset group from + * concurrent opens. A vfio_device reference is acquired for each device + * to prevent unbinds during the reset operation. * * NB: vfio-core considers a group to be viable even if some devices are * bound to drivers like pci-stub or pcieport. Here we require all devices @@ -1363,7 +1505,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) { struct vfio_devices devs = { .cur_index = 0 }; int i = 0, ret = -EINVAL; - bool needs_reset = false, slot = false; + bool slot = false; struct vfio_pci_device *tmp; if (!pci_probe_reset_slot(vdev->pdev->slot)) @@ -1381,28 +1523,36 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) return; if (vfio_pci_for_each_slot_or_bus(vdev->pdev, - vfio_pci_get_devs, &devs, slot)) + vfio_pci_get_unused_devs, + &devs, slot)) goto put_devs; + /* Does at least one need a reset? */ for (i = 0; i < devs.cur_index; i++) { tmp = vfio_device_data(devs.devices[i]); - if (tmp->needs_reset) - needs_reset = true; - if (tmp->refcnt) - goto put_devs; + if (tmp->needs_reset) { + ret = pci_reset_bus(vdev->pdev); + break; + } } - if (needs_reset) - ret = pci_reset_bus(vdev->pdev); - put_devs: for (i = 0; i < devs.cur_index; i++) { tmp = vfio_device_data(devs.devices[i]); - if (!ret) + + /* + * If reset was successful, affected devices no longer need + * a reset and we should return all the collateral devices + * to low power. If not successful, we either didn't reset + * the bus or timed out waiting for it, so let's not touch + * the power state. + */ + if (!ret) { tmp->needs_reset = false; - if (!tmp->refcnt && !disable_idle_d3) - pci_set_power_state(tmp->pdev, PCI_D3hot); + if (tmp != vdev && !disable_idle_d3) + pci_set_power_state(tmp->pdev, PCI_D3hot); + } vfio_device_put(devs.devices[i]); } diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c new file mode 100644 index 000000000000..054a2cf9dd8e --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_nvlink2.c @@ -0,0 +1,482 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * VFIO PCI NVIDIA Whitherspoon GPU support a.k.a. NVLink2. + * + * Copyright (C) 2018 IBM Corp. All rights reserved. + * Author: Alexey Kardashevskiy <aik@ozlabs.ru> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Register an on-GPU RAM region for cacheable access. + * + * Derived from original vfio_pci_igd.c: + * Copyright (C) 2016 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson <alex.williamson@redhat.com> + */ + +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/sched/mm.h> +#include <linux/mmu_context.h> +#include <asm/kvm_ppc.h> +#include "vfio_pci_private.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" + +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_nvgpu_mmap_fault); +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_nvgpu_mmap); +EXPORT_TRACEPOINT_SYMBOL_GPL(vfio_pci_npu2_mmap); + +struct vfio_pci_nvgpu_data { + unsigned long gpu_hpa; /* GPU RAM physical address */ + unsigned long gpu_tgt; /* TGT address of corresponding GPU RAM */ + unsigned long useraddr; /* GPU RAM userspace address */ + unsigned long size; /* Size of the GPU RAM window (usually 128GB) */ + struct mm_struct *mm; + struct mm_iommu_table_group_mem_t *mem; /* Pre-registered RAM descr. */ + struct pci_dev *gpdev; + struct notifier_block group_notifier; +}; + +static size_t vfio_pci_nvgpu_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_nvgpu_data *data = vdev->region[i].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + loff_t posaligned = pos & PAGE_MASK, posoff = pos & ~PAGE_MASK; + size_t sizealigned; + void __iomem *ptr; + + if (pos >= vdev->region[i].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[i].size - pos)); + + /* + * We map only a bit of GPU RAM for a short time instead of mapping it + * for the guest lifetime as: + * + * 1) we do not know GPU RAM size, only aperture which is 4-8 times + * bigger than actual RAM size (16/32GB RAM vs. 128GB aperture); + * 2) mapping GPU RAM allows CPU to prefetch and if this happens + * before NVLink bridge is reset (which fences GPU RAM), + * hardware management interrupts (HMI) might happen, this + * will freeze NVLink bridge. + * + * This is not fast path anyway. + */ + sizealigned = _ALIGN_UP(posoff + count, PAGE_SIZE); + ptr = ioremap_cache(data->gpu_hpa + posaligned, sizealigned); + if (!ptr) + return -EFAULT; + + if (iswrite) { + if (copy_from_user(ptr + posoff, buf, count)) + count = -EFAULT; + else + *ppos += count; + } else { + if (copy_to_user(buf, ptr + posoff, count)) + count = -EFAULT; + else + *ppos += count; + } + + iounmap(ptr); + + return count; +} + +static void vfio_pci_nvgpu_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_nvgpu_data *data = region->data; + long ret; + + /* If there were any mappings at all... */ + if (data->mm) { + ret = mm_iommu_put(data->mm, data->mem); + WARN_ON(ret); + + mmdrop(data->mm); + } + + vfio_unregister_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &data->group_notifier); + + pnv_npu2_unmap_lpar_dev(data->gpdev); + + kfree(data); +} + +static vm_fault_t vfio_pci_nvgpu_mmap_fault(struct vm_fault *vmf) +{ + vm_fault_t ret; + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_region *region = vma->vm_private_data; + struct vfio_pci_nvgpu_data *data = region->data; + unsigned long vmf_off = (vmf->address - vma->vm_start) >> PAGE_SHIFT; + unsigned long nv2pg = data->gpu_hpa >> PAGE_SHIFT; + unsigned long vm_pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + unsigned long pfn = nv2pg + vm_pgoff + vmf_off; + + ret = vmf_insert_pfn(vma, vmf->address, pfn); + trace_vfio_pci_nvgpu_mmap_fault(data->gpdev, pfn << PAGE_SHIFT, + vmf->address, ret); + + return ret; +} + +static const struct vm_operations_struct vfio_pci_nvgpu_mmap_vmops = { + .fault = vfio_pci_nvgpu_mmap_fault, +}; + +static int vfio_pci_nvgpu_mmap(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vm_area_struct *vma) +{ + int ret; + struct vfio_pci_nvgpu_data *data = region->data; + + if (data->useraddr) + return -EPERM; + + if (vma->vm_end - vma->vm_start > data->size) + return -EINVAL; + + vma->vm_private_data = region; + vma->vm_flags |= VM_PFNMAP; + vma->vm_ops = &vfio_pci_nvgpu_mmap_vmops; + + /* + * Calling mm_iommu_newdev() here once as the region is not + * registered yet and therefore right initialization will happen now. + * Other places will use mm_iommu_find() which returns + * registered @mem and does not go gup(). + */ + data->useraddr = vma->vm_start; + data->mm = current->mm; + + atomic_inc(&data->mm->mm_count); + ret = (int) mm_iommu_newdev(data->mm, data->useraddr, + (vma->vm_end - vma->vm_start) >> PAGE_SHIFT, + data->gpu_hpa, &data->mem); + + trace_vfio_pci_nvgpu_mmap(vdev->pdev, data->gpu_hpa, data->useraddr, + vma->vm_end - vma->vm_start, ret); + + return ret; +} + +static int vfio_pci_nvgpu_add_capability(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vfio_info_cap *caps) +{ + struct vfio_pci_nvgpu_data *data = region->data; + struct vfio_region_info_cap_nvlink2_ssatgt cap = { 0 }; + + cap.header.id = VFIO_REGION_INFO_CAP_NVLINK2_SSATGT; + cap.header.version = 1; + cap.tgt = data->gpu_tgt; + + return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); +} + +static const struct vfio_pci_regops vfio_pci_nvgpu_regops = { + .rw = vfio_pci_nvgpu_rw, + .release = vfio_pci_nvgpu_release, + .mmap = vfio_pci_nvgpu_mmap, + .add_capability = vfio_pci_nvgpu_add_capability, +}; + +static int vfio_pci_nvgpu_group_notifier(struct notifier_block *nb, + unsigned long action, void *opaque) +{ + struct kvm *kvm = opaque; + struct vfio_pci_nvgpu_data *data = container_of(nb, + struct vfio_pci_nvgpu_data, + group_notifier); + + if (action == VFIO_GROUP_NOTIFY_SET_KVM && kvm && + pnv_npu2_map_lpar_dev(data->gpdev, + kvm->arch.lpid, MSR_DR | MSR_PR)) + return NOTIFY_BAD; + + return NOTIFY_OK; +} + +int vfio_pci_nvdia_v100_nvlink2_init(struct vfio_pci_device *vdev) +{ + int ret; + u64 reg[2]; + u64 tgt = 0; + struct device_node *npu_node, *mem_node; + struct pci_dev *npu_dev; + struct vfio_pci_nvgpu_data *data; + uint32_t mem_phandle = 0; + unsigned long events = VFIO_GROUP_NOTIFY_SET_KVM; + + /* + * PCI config space does not tell us about NVLink presense but + * platform does, use this. + */ + npu_dev = pnv_pci_get_npu_dev(vdev->pdev, 0); + if (!npu_dev) + return -ENODEV; + + npu_node = pci_device_to_OF_node(npu_dev); + if (!npu_node) + return -EINVAL; + + if (of_property_read_u32(npu_node, "memory-region", &mem_phandle)) + return -EINVAL; + + mem_node = of_find_node_by_phandle(mem_phandle); + if (!mem_node) + return -EINVAL; + + if (of_property_read_variable_u64_array(mem_node, "reg", reg, + ARRAY_SIZE(reg), ARRAY_SIZE(reg)) != + ARRAY_SIZE(reg)) + return -EINVAL; + + if (of_property_read_u64(npu_node, "ibm,device-tgt-addr", &tgt)) { + dev_warn(&vdev->pdev->dev, "No ibm,device-tgt-addr found\n"); + return -EFAULT; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->gpu_hpa = reg[0]; + data->gpu_tgt = tgt; + data->size = reg[1]; + + dev_dbg(&vdev->pdev->dev, "%lx..%lx\n", data->gpu_hpa, + data->gpu_hpa + data->size - 1); + + data->gpdev = vdev->pdev; + data->group_notifier.notifier_call = vfio_pci_nvgpu_group_notifier; + + ret = vfio_register_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &events, &data->group_notifier); + if (ret) + goto free_exit; + + /* + * We have just set KVM, we do not need the listener anymore. + * Also, keeping it registered means that if more than one GPU is + * assigned, we will get several similar notifiers notifying about + * the same device again which does not help with anything. + */ + vfio_unregister_notifier(&data->gpdev->dev, VFIO_GROUP_NOTIFY, + &data->group_notifier); + + ret = vfio_pci_register_dev_region(vdev, + PCI_VENDOR_ID_NVIDIA | VFIO_REGION_TYPE_PCI_VENDOR_TYPE, + VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM, + &vfio_pci_nvgpu_regops, + data->size, + VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE | + VFIO_REGION_INFO_FLAG_MMAP, + data); + if (ret) + goto free_exit; + + return 0; +free_exit: + kfree(data); + + return ret; +} + +/* + * IBM NPU2 bridge + */ +struct vfio_pci_npu2_data { + void *base; /* ATSD register virtual address, for emulated access */ + unsigned long mmio_atsd; /* ATSD physical address */ + unsigned long gpu_tgt; /* TGT address of corresponding GPU RAM */ + unsigned int link_speed; /* The link speed from DT's ibm,nvlink-speed */ +}; + +static size_t vfio_pci_npu2_rw(struct vfio_pci_device *vdev, + char __user *buf, size_t count, loff_t *ppos, bool iswrite) +{ + unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS; + struct vfio_pci_npu2_data *data = vdev->region[i].data; + loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK; + + if (pos >= vdev->region[i].size) + return -EINVAL; + + count = min(count, (size_t)(vdev->region[i].size - pos)); + + if (iswrite) { + if (copy_from_user(data->base + pos, buf, count)) + return -EFAULT; + } else { + if (copy_to_user(buf, data->base + pos, count)) + return -EFAULT; + } + *ppos += count; + + return count; +} + +static int vfio_pci_npu2_mmap(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vm_area_struct *vma) +{ + int ret; + struct vfio_pci_npu2_data *data = region->data; + unsigned long req_len = vma->vm_end - vma->vm_start; + + if (req_len != PAGE_SIZE) + return -EINVAL; + + vma->vm_flags |= VM_PFNMAP; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + ret = remap_pfn_range(vma, vma->vm_start, data->mmio_atsd >> PAGE_SHIFT, + req_len, vma->vm_page_prot); + trace_vfio_pci_npu2_mmap(vdev->pdev, data->mmio_atsd, vma->vm_start, + vma->vm_end - vma->vm_start, ret); + + return ret; +} + +static void vfio_pci_npu2_release(struct vfio_pci_device *vdev, + struct vfio_pci_region *region) +{ + struct vfio_pci_npu2_data *data = region->data; + + memunmap(data->base); + kfree(data); +} + +static int vfio_pci_npu2_add_capability(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, struct vfio_info_cap *caps) +{ + struct vfio_pci_npu2_data *data = region->data; + struct vfio_region_info_cap_nvlink2_ssatgt captgt = { 0 }; + struct vfio_region_info_cap_nvlink2_lnkspd capspd = { 0 }; + int ret; + + captgt.header.id = VFIO_REGION_INFO_CAP_NVLINK2_SSATGT; + captgt.header.version = 1; + captgt.tgt = data->gpu_tgt; + + capspd.header.id = VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD; + capspd.header.version = 1; + capspd.link_speed = data->link_speed; + + ret = vfio_info_add_capability(caps, &captgt.header, sizeof(captgt)); + if (ret) + return ret; + + return vfio_info_add_capability(caps, &capspd.header, sizeof(capspd)); +} + +static const struct vfio_pci_regops vfio_pci_npu2_regops = { + .rw = vfio_pci_npu2_rw, + .mmap = vfio_pci_npu2_mmap, + .release = vfio_pci_npu2_release, + .add_capability = vfio_pci_npu2_add_capability, +}; + +int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev) +{ + int ret; + struct vfio_pci_npu2_data *data; + struct device_node *nvlink_dn; + u32 nvlink_index = 0; + struct pci_dev *npdev = vdev->pdev; + struct device_node *npu_node = pci_device_to_OF_node(npdev); + struct pci_controller *hose = pci_bus_to_host(npdev->bus); + u64 mmio_atsd = 0; + u64 tgt = 0; + u32 link_speed = 0xff; + + /* + * PCI config space does not tell us about NVLink presense but + * platform does, use this. + */ + if (!pnv_pci_get_gpu_dev(vdev->pdev)) + return -ENODEV; + + /* + * NPU2 normally has 8 ATSD registers (for concurrency) and 6 links + * so we can allocate one register per link, using nvlink index as + * a key. + * There is always at least one ATSD register so as long as at least + * NVLink bridge #0 is passed to the guest, ATSD will be available. + */ + nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); + if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", + &nvlink_index))) + return -ENODEV; + + if (of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", nvlink_index, + &mmio_atsd)) { + dev_warn(&vdev->pdev->dev, "No available ATSD found\n"); + mmio_atsd = 0; + } + + if (of_property_read_u64(npu_node, "ibm,device-tgt-addr", &tgt)) { + dev_warn(&vdev->pdev->dev, "No ibm,device-tgt-addr found\n"); + return -EFAULT; + } + + if (of_property_read_u32(npu_node, "ibm,nvlink-speed", &link_speed)) { + dev_warn(&vdev->pdev->dev, "No ibm,nvlink-speed found\n"); + return -EFAULT; + } + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->mmio_atsd = mmio_atsd; + data->gpu_tgt = tgt; + data->link_speed = link_speed; + if (data->mmio_atsd) { + data->base = memremap(data->mmio_atsd, SZ_64K, MEMREMAP_WT); + if (!data->base) { + ret = -ENOMEM; + goto free_exit; + } + } + + /* + * We want to expose the capability even if this specific NVLink + * did not get its own ATSD register because capabilities + * belong to VFIO regions and normally there will be ATSD register + * assigned to the NVLink bridge. + */ + ret = vfio_pci_register_dev_region(vdev, + PCI_VENDOR_ID_IBM | + VFIO_REGION_TYPE_PCI_VENDOR_TYPE, + VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD, + &vfio_pci_npu2_regops, + data->mmio_atsd ? PAGE_SIZE : 0, + VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE | + VFIO_REGION_INFO_FLAG_MMAP, + data); + if (ret) + goto free_exit; + + return 0; + +free_exit: + kfree(data); + + return ret; +} diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index cde3b5d3441a..8c0009f00818 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -59,6 +59,12 @@ struct vfio_pci_regops { size_t count, loff_t *ppos, bool iswrite); void (*release)(struct vfio_pci_device *vdev, struct vfio_pci_region *region); + int (*mmap)(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, + struct vm_area_struct *vma); + int (*add_capability)(struct vfio_pci_device *vdev, + struct vfio_pci_region *region, + struct vfio_info_cap *caps); }; struct vfio_pci_region { @@ -76,6 +82,11 @@ struct vfio_pci_dummy_resource { struct list_head res_next; }; +struct vfio_pci_reflck { + struct kref kref; + struct mutex lock; +}; + struct vfio_pci_device { struct pci_dev *pdev; void __iomem *barmap[PCI_STD_RESOURCE_END + 1]; @@ -104,6 +115,7 @@ struct vfio_pci_device { bool needs_reset; bool nointx; struct pci_saved_state *pci_saved_state; + struct vfio_pci_reflck *reflck; int refcnt; int ioeventfds_nr; struct eventfd_ctx *err_trigger; @@ -157,4 +169,18 @@ static inline int vfio_pci_igd_init(struct vfio_pci_device *vdev) return -ENODEV; } #endif +#ifdef CONFIG_VFIO_PCI_NVLINK2 +extern int vfio_pci_nvdia_v100_nvlink2_init(struct vfio_pci_device *vdev); +extern int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev); +#else +static inline int vfio_pci_nvdia_v100_nvlink2_init(struct vfio_pci_device *vdev) +{ + return -ENODEV; +} + +static inline int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev) +{ + return -ENODEV; +} +#endif #endif /* VFIO_PCI_PRIVATE_H */ |