diff options
Diffstat (limited to 'drivers/vfio')
-rw-r--r-- | drivers/vfio/mdev/mdev_sysfs.c | 2 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci.c | 362 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_config.c | 65 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_intrs.c | 14 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_nvlink2.c | 2 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_private.h | 15 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_rdwr.c | 24 | ||||
-rw-r--r-- | drivers/vfio/vfio.c | 13 | ||||
-rw-r--r-- | drivers/vfio/vfio_iommu_type1.c | 623 |
9 files changed, 1011 insertions, 109 deletions
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index 8ad14e5c02bf..917fd84c1c6f 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -110,7 +110,7 @@ static struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent, "%s-%s", dev_driver_string(parent->dev), group->name); if (ret) { - kfree(type); + kobject_put(&type->kobj); return ERR_PTR(ret); } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 6c6b37b5c04e..de881a6cff35 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -26,6 +26,7 @@ #include <linux/vfio.h> #include <linux/vgaarb.h> #include <linux/nospec.h> +#include <linux/sched/mm.h> #include "vfio_pci_private.h" @@ -184,6 +185,7 @@ no_mmap: static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev); static void vfio_pci_disable(struct vfio_pci_device *vdev); +static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data); /* * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND @@ -519,6 +521,19 @@ static void vfio_pci_release(void *device_data) vfio_pci_vf_token_user_add(vdev, -1); vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); + mutex_lock(&vdev->igate); + if (vdev->err_trigger) { + eventfd_ctx_put(vdev->err_trigger); + vdev->err_trigger = NULL; + } + mutex_unlock(&vdev->igate); + + mutex_lock(&vdev->igate); + if (vdev->req_trigger) { + eventfd_ctx_put(vdev->req_trigger); + vdev->req_trigger = NULL; + } + mutex_unlock(&vdev->igate); } mutex_unlock(&vdev->reflck->lock); @@ -736,6 +751,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev, return 0; } +struct vfio_devices { + struct vfio_device **devices; + int cur_index; + int max_index; +}; + static long vfio_pci_ioctl(void *device_data, unsigned int cmd, unsigned long arg) { @@ -809,7 +830,7 @@ static long vfio_pci_ioctl(void *device_data, { void __iomem *io; size_t size; - u16 orig_cmd; + u16 cmd; info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); info.flags = 0; @@ -829,10 +850,7 @@ static long vfio_pci_ioctl(void *device_data, * Is it really there? Enable memory decode for * implicit access in pci_map_rom(). */ - pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd); - pci_write_config_word(pdev, PCI_COMMAND, - orig_cmd | PCI_COMMAND_MEMORY); - + cmd = vfio_pci_memory_lock_and_enable(vdev); io = pci_map_rom(pdev, &size); if (io) { info.flags = VFIO_REGION_INFO_FLAG_READ; @@ -840,8 +858,8 @@ static long vfio_pci_ioctl(void *device_data, } else { info.size = 0; } + vfio_pci_memory_unlock_and_restore(vdev, cmd); - pci_write_config_word(pdev, PCI_COMMAND, orig_cmd); break; } case VFIO_PCI_VGA_REGION_INDEX: @@ -984,8 +1002,16 @@ static long vfio_pci_ioctl(void *device_data, return ret; } else if (cmd == VFIO_DEVICE_RESET) { - return vdev->reset_works ? - pci_try_reset_function(vdev->pdev) : -EINVAL; + int ret; + + if (!vdev->reset_works) + return -EINVAL; + + vfio_pci_zap_and_down_write_memory_lock(vdev); + ret = pci_try_reset_function(vdev->pdev); + up_write(&vdev->memory_lock); + + return ret; } else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) { struct vfio_pci_hot_reset_info hdr; @@ -1065,8 +1091,9 @@ reset_info_exit: int32_t *group_fds; struct vfio_pci_group_entry *groups; struct vfio_pci_group_info info; + struct vfio_devices devs = { .cur_index = 0 }; bool slot = false; - int i, count = 0, ret = 0; + int i, group_idx, mem_idx = 0, count = 0, ret = 0; minsz = offsetofend(struct vfio_pci_hot_reset, count); @@ -1118,9 +1145,9 @@ reset_info_exit: * user interface and store the group and iommu ID. This * ensures the group is held across the reset. */ - for (i = 0; i < hdr.count; i++) { + for (group_idx = 0; group_idx < hdr.count; group_idx++) { struct vfio_group *group; - struct fd f = fdget(group_fds[i]); + struct fd f = fdget(group_fds[group_idx]); if (!f.file) { ret = -EBADF; break; @@ -1133,8 +1160,9 @@ reset_info_exit: break; } - groups[i].group = group; - groups[i].id = vfio_external_user_iommu_id(group); + groups[group_idx].group = group; + groups[group_idx].id = + vfio_external_user_iommu_id(group); } kfree(group_fds); @@ -1153,13 +1181,63 @@ reset_info_exit: ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_validate_devs, &info, slot); - if (!ret) - /* User has access, do the reset */ - ret = pci_reset_bus(vdev->pdev); + if (ret) + goto hot_reset_release; + + devs.max_index = count; + devs.devices = kcalloc(count, sizeof(struct vfio_device *), + GFP_KERNEL); + if (!devs.devices) { + ret = -ENOMEM; + goto hot_reset_release; + } + + /* + * We need to get memory_lock for each device, but devices + * can share mmap_lock, therefore we need to zap and hold + * the vma_lock for each device, and only then get each + * memory_lock. + */ + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, + vfio_pci_try_zap_and_vma_lock_cb, + &devs, slot); + if (ret) + goto hot_reset_release; + + for (; mem_idx < devs.cur_index; mem_idx++) { + struct vfio_pci_device *tmp; + + tmp = vfio_device_data(devs.devices[mem_idx]); + + ret = down_write_trylock(&tmp->memory_lock); + if (!ret) { + ret = -EBUSY; + goto hot_reset_release; + } + mutex_unlock(&tmp->vma_lock); + } + + /* User has access, do the reset */ + ret = pci_reset_bus(vdev->pdev); hot_reset_release: - for (i--; i >= 0; i--) - vfio_group_put_external_user(groups[i].group); + for (i = 0; i < devs.cur_index; i++) { + struct vfio_device *device; + struct vfio_pci_device *tmp; + + device = devs.devices[i]; + tmp = vfio_device_data(device); + + if (i < mem_idx) + up_write(&tmp->memory_lock); + else + mutex_unlock(&tmp->vma_lock); + vfio_device_put(device); + } + kfree(devs.devices); + + for (group_idx--; group_idx >= 0; group_idx--) + vfio_group_put_external_user(groups[group_idx].group); kfree(groups); return ret; @@ -1299,6 +1377,202 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf, return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true); } +/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ +static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try) +{ + struct vfio_pci_mmap_vma *mmap_vma, *tmp; + + /* + * Lock ordering: + * vma_lock is nested under mmap_lock for vm_ops callback paths. + * The memory_lock semaphore is used by both code paths calling + * into this function to zap vmas and the vm_ops.fault callback + * to protect the memory enable state of the device. + * + * When zapping vmas we need to maintain the mmap_lock => vma_lock + * ordering, which requires using vma_lock to walk vma_list to + * acquire an mm, then dropping vma_lock to get the mmap_lock and + * reacquiring vma_lock. This logic is derived from similar + * requirements in uverbs_user_mmap_disassociate(). + * + * mmap_lock must always be the top-level lock when it is taken. + * Therefore we can only hold the memory_lock write lock when + * vma_list is empty, as we'd need to take mmap_lock to clear + * entries. vma_list can only be guaranteed empty when holding + * vma_lock, thus memory_lock is nested under vma_lock. + * + * This enables the vm_ops.fault callback to acquire vma_lock, + * followed by memory_lock read lock, while already holding + * mmap_lock without risk of deadlock. + */ + while (1) { + struct mm_struct *mm = NULL; + + if (try) { + if (!mutex_trylock(&vdev->vma_lock)) + return 0; + } else { + mutex_lock(&vdev->vma_lock); + } + while (!list_empty(&vdev->vma_list)) { + mmap_vma = list_first_entry(&vdev->vma_list, + struct vfio_pci_mmap_vma, + vma_next); + mm = mmap_vma->vma->vm_mm; + if (mmget_not_zero(mm)) + break; + + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + mm = NULL; + } + if (!mm) + return 1; + mutex_unlock(&vdev->vma_lock); + + if (try) { + if (!mmap_read_trylock(mm)) { + mmput(mm); + return 0; + } + } else { + mmap_read_lock(mm); + } + if (mmget_still_valid(mm)) { + if (try) { + if (!mutex_trylock(&vdev->vma_lock)) { + mmap_read_unlock(mm); + mmput(mm); + return 0; + } + } else { + mutex_lock(&vdev->vma_lock); + } + list_for_each_entry_safe(mmap_vma, tmp, + &vdev->vma_list, vma_next) { + struct vm_area_struct *vma = mmap_vma->vma; + + if (vma->vm_mm != mm) + continue; + + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + + zap_vma_ptes(vma, vma->vm_start, + vma->vm_end - vma->vm_start); + } + mutex_unlock(&vdev->vma_lock); + } + mmap_read_unlock(mm); + mmput(mm); + } +} + +void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev) +{ + vfio_pci_zap_and_vma_lock(vdev, false); + down_write(&vdev->memory_lock); + mutex_unlock(&vdev->vma_lock); +} + +u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev) +{ + u16 cmd; + + down_write(&vdev->memory_lock); + pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd); + if (!(cmd & PCI_COMMAND_MEMORY)) + pci_write_config_word(vdev->pdev, PCI_COMMAND, + cmd | PCI_COMMAND_MEMORY); + + return cmd; +} + +void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd) +{ + pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd); + up_write(&vdev->memory_lock); +} + +/* Caller holds vma_lock */ +static int __vfio_pci_add_vma(struct vfio_pci_device *vdev, + struct vm_area_struct *vma) +{ + struct vfio_pci_mmap_vma *mmap_vma; + + mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL); + if (!mmap_vma) + return -ENOMEM; + + mmap_vma->vma = vma; + list_add(&mmap_vma->vma_next, &vdev->vma_list); + + return 0; +} + +/* + * Zap mmaps on open so that we can fault them in on access and therefore + * our vma_list only tracks mappings accessed since last zap. + */ +static void vfio_pci_mmap_open(struct vm_area_struct *vma) +{ + zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); +} + +static void vfio_pci_mmap_close(struct vm_area_struct *vma) +{ + struct vfio_pci_device *vdev = vma->vm_private_data; + struct vfio_pci_mmap_vma *mmap_vma; + + mutex_lock(&vdev->vma_lock); + list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { + if (mmap_vma->vma == vma) { + list_del(&mmap_vma->vma_next); + kfree(mmap_vma); + break; + } + } + mutex_unlock(&vdev->vma_lock); +} + +static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_device *vdev = vma->vm_private_data; + vm_fault_t ret = VM_FAULT_NOPAGE; + + mutex_lock(&vdev->vma_lock); + down_read(&vdev->memory_lock); + + if (!__vfio_pci_memory_enabled(vdev)) { + ret = VM_FAULT_SIGBUS; + mutex_unlock(&vdev->vma_lock); + goto up_out; + } + + if (__vfio_pci_add_vma(vdev, vma)) { + ret = VM_FAULT_OOM; + mutex_unlock(&vdev->vma_lock); + goto up_out; + } + + mutex_unlock(&vdev->vma_lock); + + if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, vma->vm_page_prot)) + ret = VM_FAULT_SIGBUS; + +up_out: + up_read(&vdev->memory_lock); + return ret; +} + +static const struct vm_operations_struct vfio_pci_mmap_ops = { + .open = vfio_pci_mmap_open, + .close = vfio_pci_mmap_close, + .fault = vfio_pci_mmap_fault, +}; + static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) { struct vfio_pci_device *vdev = device_data; @@ -1357,8 +1631,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; - return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - req_len, vma->vm_page_prot); + /* + * See remap_pfn_range(), called from vfio_pci_fault() but we can't + * change vm_flags within the fault handler. Set them now. + */ + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_ops = &vfio_pci_mmap_ops; + + return 0; } static void vfio_pci_request(void *device_data, unsigned int count) @@ -1608,6 +1888,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) spin_lock_init(&vdev->irqlock); mutex_init(&vdev->ioeventfds_lock); INIT_LIST_HEAD(&vdev->ioeventfds_list); + mutex_init(&vdev->vma_lock); + INIT_LIST_HEAD(&vdev->vma_list); + init_rwsem(&vdev->memory_lock); ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) @@ -1861,12 +2144,6 @@ 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_unused_devs(struct pci_dev *pdev, void *data) { struct vfio_devices *devs = data; @@ -1897,6 +2174,39 @@ static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data) return 0; } +static int vfio_pci_try_zap_and_vma_lock_cb(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; + + device = vfio_device_get_from_dev(&pdev->dev); + if (!device) + return -EINVAL; + + if (pci_dev_driver(pdev) != &vfio_pci_driver) { + vfio_device_put(device); + return -EBUSY; + } + + vdev = vfio_device_data(device); + + /* + * Locking multiple devices is prone to deadlock, runaway and + * unwind if we hit contention. + */ + if (!vfio_pci_zap_and_vma_lock(vdev, true)) { + vfio_device_put(device); + return -EBUSY; + } + + devs->devices[devs->cur_index++] = device; + return 0; +} + /* * 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 diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 90c0b80f8acf..d98843feddce 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -395,6 +395,20 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write) *(__le32 *)(&p->write[off]) = cpu_to_le32(write); } +/* Caller should hold memory_lock semaphore */ +bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); + + /* + * SR-IOV VF memory enable is handled by the MSE bit in the + * PF SR-IOV capability, there's therefore no need to trigger + * faults based on the virtual value. + */ + return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); +} + /* * Restore the *real* BARs after we detect a FLR or backdoor reset. * (backdoor = some device specific technique that we didn't catch) @@ -556,13 +570,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, new_cmd = le32_to_cpu(val); + phys_io = !!(phys_cmd & PCI_COMMAND_IO); + virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO); + new_io = !!(new_cmd & PCI_COMMAND_IO); + phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY); virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY); new_mem = !!(new_cmd & PCI_COMMAND_MEMORY); - phys_io = !!(phys_cmd & PCI_COMMAND_IO); - virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO); - new_io = !!(new_cmd & PCI_COMMAND_IO); + if (!new_mem) + vfio_pci_zap_and_down_write_memory_lock(vdev); + else + down_write(&vdev->memory_lock); /* * If the user is writing mem/io enable (new_mem/io) and we @@ -579,8 +598,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, } count = vfio_default_config_write(vdev, pos, count, perm, offset, val); - if (count < 0) + if (count < 0) { + if (offset == PCI_COMMAND) + up_write(&vdev->memory_lock); return count; + } /* * Save current memory/io enable bits in vconfig to allow for @@ -591,6 +613,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, *virt_cmd &= cpu_to_le16(~mask); *virt_cmd |= cpu_to_le16(new_cmd & mask); + + up_write(&vdev->memory_lock); } /* Emulate INTx disable */ @@ -828,8 +852,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos, pos - offset + PCI_EXP_DEVCAP, &cap); - if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) + if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) { + vfio_pci_zap_and_down_write_memory_lock(vdev); pci_try_reset_function(vdev->pdev); + up_write(&vdev->memory_lock); + } } /* @@ -907,8 +934,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos, pos - offset + PCI_AF_CAP, &cap); - if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) + if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) { + vfio_pci_zap_and_down_write_memory_lock(vdev); pci_try_reset_function(vdev->pdev); + up_write(&vdev->memory_lock); + } } return count; @@ -1462,7 +1492,12 @@ static int vfio_cap_init(struct vfio_pci_device *vdev) if (ret) return ret; - if (cap <= PCI_CAP_ID_MAX) { + /* + * ID 0 is a NULL capability, conflicting with our fake + * PCI_CAP_ID_BASIC. As it has no content, consider it + * hidden for now. + */ + if (cap && cap <= PCI_CAP_ID_MAX) { len = pci_cap_length[cap]; if (len == 0xFF) { /* Variable length */ len = vfio_cap_len(vdev, cap, pos); @@ -1699,6 +1734,15 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN]); vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ + + /* + * VFs do no implement the memory enable bit of the COMMAND + * register therefore we'll not have it set in our initial + * copy of config space after pci_enable_device(). For + * consistency with PFs, set the virtual enable bit here. + */ + *(__le16 *)&vconfig[PCI_COMMAND] |= + cpu_to_le16(PCI_COMMAND_MEMORY); } if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) @@ -1728,8 +1772,11 @@ void vfio_config_free(struct vfio_pci_device *vdev) vdev->vconfig = NULL; kfree(vdev->pci_config_map); vdev->pci_config_map = NULL; - kfree(vdev->msi_perm); - vdev->msi_perm = NULL; + if (vdev->msi_perm) { + free_perm_bits(vdev->msi_perm); + kfree(vdev->msi_perm); + vdev->msi_perm = NULL; + } } /* diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 2056f3f85f59..1d9fb2592945 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -249,6 +249,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) struct pci_dev *pdev = vdev->pdev; unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI; int ret; + u16 cmd; if (!is_irq_none(vdev)) return -EINVAL; @@ -258,13 +259,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) return -ENOMEM; /* return the number of supported vectors if we can't get all: */ + cmd = vfio_pci_memory_lock_and_enable(vdev); ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag); if (ret < nvec) { if (ret > 0) pci_free_irq_vectors(pdev); + vfio_pci_memory_unlock_and_restore(vdev, cmd); kfree(vdev->ctx); return ret; } + vfio_pci_memory_unlock_and_restore(vdev, cmd); vdev->num_ctx = nvec; vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX : @@ -287,6 +291,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, struct pci_dev *pdev = vdev->pdev; struct eventfd_ctx *trigger; int irq, ret; + u16 cmd; if (vector < 0 || vector >= vdev->num_ctx) return -EINVAL; @@ -295,7 +300,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, if (vdev->ctx[vector].trigger) { irq_bypass_unregister_producer(&vdev->ctx[vector].producer); + + cmd = vfio_pci_memory_lock_and_enable(vdev); free_irq(irq, vdev->ctx[vector].trigger); + vfio_pci_memory_unlock_and_restore(vdev, cmd); + kfree(vdev->ctx[vector].name); eventfd_ctx_put(vdev->ctx[vector].trigger); vdev->ctx[vector].trigger = NULL; @@ -323,6 +332,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, * such a reset it would be unsuccessful. To avoid this, restore the * cached value of the message prior to enabling. */ + cmd = vfio_pci_memory_lock_and_enable(vdev); if (msix) { struct msi_msg msg; @@ -332,6 +342,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, ret = request_irq(irq, vfio_msihandler, 0, vdev->ctx[vector].name, trigger); + vfio_pci_memory_unlock_and_restore(vdev, cmd); if (ret) { kfree(vdev->ctx[vector].name); eventfd_ctx_put(trigger); @@ -376,6 +387,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) { struct pci_dev *pdev = vdev->pdev; int i; + u16 cmd; for (i = 0; i < vdev->num_ctx; i++) { vfio_virqfd_disable(&vdev->ctx[i].unmask); @@ -384,7 +396,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix); + cmd = vfio_pci_memory_lock_and_enable(vdev); pci_free_irq_vectors(pdev); + vfio_pci_memory_unlock_and_restore(vdev, cmd); /* * Both disable paths above use pci_intx_for_msi() to clear DisINTx diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c index ed20d73cc27c..65c61710c0e9 100644 --- a/drivers/vfio/pci/vfio_pci_nvlink2.c +++ b/drivers/vfio/pci/vfio_pci_nvlink2.c @@ -67,7 +67,7 @@ static size_t vfio_pci_nvgpu_rw(struct vfio_pci_device *vdev, * * This is not fast path anyway. */ - sizealigned = _ALIGN_UP(posoff + count, PAGE_SIZE); + sizealigned = ALIGN(posoff + count, PAGE_SIZE); ptr = ioremap_cache(data->gpu_hpa + posaligned, sizealigned); if (!ptr) return -EFAULT; diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 36ec69081ecd..86a02aff8735 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -92,6 +92,11 @@ struct vfio_pci_vf_token { int users; }; +struct vfio_pci_mmap_vma { + struct vm_area_struct *vma; + struct list_head vma_next; +}; + struct vfio_pci_device { struct pci_dev *pdev; void __iomem *barmap[PCI_STD_NUM_BARS]; @@ -132,6 +137,9 @@ struct vfio_pci_device { struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; struct notifier_block nb; + struct mutex vma_lock; + struct list_head vma_list; + struct rw_semaphore memory_lock; }; #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) @@ -174,6 +182,13 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev, extern int vfio_pci_set_power_state(struct vfio_pci_device *vdev, pci_power_t state); +extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev); +extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device + *vdev); +extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev); +extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, + u16 cmd); + #ifdef CONFIG_VFIO_PCI_IGD extern int vfio_pci_igd_init(struct vfio_pci_device *vdev); #else diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index a87992892a9f..916b184df3a5 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -162,6 +162,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, size_t x_start = 0, x_end = 0; resource_size_t end; void __iomem *io; + struct resource *res = &vdev->pdev->resource[bar]; ssize_t done; if (pci_resource_start(pdev, bar)) @@ -177,6 +178,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, count = min(count, (size_t)(end - pos)); + if (res->flags & IORESOURCE_MEM) { + down_read(&vdev->memory_lock); + if (!__vfio_pci_memory_enabled(vdev)) { + up_read(&vdev->memory_lock); + return -EIO; + } + } + if (bar == PCI_ROM_RESOURCE) { /* * The ROM can fill less space than the BAR, so we start the @@ -184,13 +193,17 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, * filling large ROM BARs much faster. */ io = pci_map_rom(pdev, &x_start); - if (!io) - return -ENOMEM; + if (!io) { + done = -ENOMEM; + goto out; + } x_end = end; } else { int ret = vfio_pci_setup_barmap(vdev, bar); - if (ret) - return ret; + if (ret) { + done = ret; + goto out; + } io = vdev->barmap[bar]; } @@ -207,6 +220,9 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, if (bar == PCI_ROM_RESOURCE) pci_unmap_rom(pdev, io); +out: + if (res->flags & IORESOURCE_MEM) + up_read(&vdev->memory_lock); return done; } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 765e0e5d83ed..580099afeaff 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -85,6 +85,7 @@ struct vfio_group { atomic_t opened; wait_queue_head_t container_q; bool noiommu; + unsigned int dev_counter; struct kvm *kvm; struct blocking_notifier_head notifier; }; @@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct vfio_group *group, mutex_lock(&group->device_lock); list_add(&device->group_next, &group->device_list); + group->dev_counter++; mutex_unlock(&group->device_lock); return device; @@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref) struct vfio_group *group = device->group; list_del(&device->group_next); + group->dev_counter--; mutex_unlock(&group->device_lock); dev_set_drvdata(device->dev, NULL); @@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, if (!group) return -ENODEV; + if (group->dev_counter > 1) + return -EINVAL; + ret = vfio_group_add_container_user(group); if (ret) goto err_pin_pages; @@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, container = group->container; driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) - ret = driver->ops->pin_pages(container->iommu_data, user_pfn, + ret = driver->ops->pin_pages(container->iommu_data, + group->iommu_group, user_pfn, npage, prot, phys_pfn); else ret = -ENOTTY; @@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group, driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) ret = driver->ops->pin_pages(container->iommu_data, - user_iova_pfn, npage, - prot, phys_pfn); + group->iommu_group, user_iova_pfn, + npage, prot, phys_pfn); else ret = -ENOTTY; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index cc1d64765ce7..5e556ac9102a 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -27,7 +27,7 @@ #include <linux/iommu.h> #include <linux/module.h> #include <linux/mm.h> -#include <linux/mmu_context.h> +#include <linux/kthread.h> #include <linux/rbtree.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> @@ -69,8 +69,11 @@ struct vfio_iommu { struct rb_root dma_list; struct blocking_notifier_head notifier; unsigned int dma_avail; + uint64_t pgsize_bitmap; bool v2; bool nesting; + bool dirty_page_tracking; + bool pinned_page_dirty_scope; }; struct vfio_domain { @@ -91,12 +94,14 @@ struct vfio_dma { bool lock_cap; /* capable(CAP_IPC_LOCK) */ struct task_struct *task; struct rb_root pfn_list; /* Ex-user pinned pfn list */ + unsigned long *bitmap; }; struct vfio_group { struct iommu_group *iommu_group; struct list_head next; bool mdev_group; /* An mdev group */ + bool pinned_page_dirty_scope; }; struct vfio_iova { @@ -112,7 +117,7 @@ struct vfio_pfn { struct rb_node node; dma_addr_t iova; /* Device address */ unsigned long pfn; /* Host pfn */ - atomic_t ref_count; + unsigned int ref_count; }; struct vfio_regions { @@ -125,8 +130,25 @@ struct vfio_regions { #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) \ (!list_empty(&iommu->domain_list)) +#define DIRTY_BITMAP_BYTES(n) (ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE) + +/* + * Input argument of number of bits to bitmap_set() is unsigned integer, which + * further casts to signed integer for unaligned multi-bit operation, + * __bitmap_set(). + * Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte, + * that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page + * system. + */ +#define DIRTY_BITMAP_PAGES_MAX ((u64)INT_MAX) +#define DIRTY_BITMAP_SIZE_MAX DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX) + static int put_pfn(unsigned long pfn, int prot); +static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu, + struct iommu_group *iommu_group); + +static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu); /* * This code handles mapping and unmapping of user data buffers * into DMA'ble space using the IOMMU @@ -175,6 +197,81 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old) rb_erase(&old->node, &iommu->dma_list); } + +static int vfio_dma_bitmap_alloc(struct vfio_dma *dma, size_t pgsize) +{ + uint64_t npages = dma->size / pgsize; + + if (npages > DIRTY_BITMAP_PAGES_MAX) + return -EINVAL; + + /* + * Allocate extra 64 bits that are used to calculate shift required for + * bitmap_shift_left() to manipulate and club unaligned number of pages + * in adjacent vfio_dma ranges. + */ + dma->bitmap = kvzalloc(DIRTY_BITMAP_BYTES(npages) + sizeof(u64), + GFP_KERNEL); + if (!dma->bitmap) + return -ENOMEM; + + return 0; +} + +static void vfio_dma_bitmap_free(struct vfio_dma *dma) +{ + kfree(dma->bitmap); + dma->bitmap = NULL; +} + +static void vfio_dma_populate_bitmap(struct vfio_dma *dma, size_t pgsize) +{ + struct rb_node *p; + unsigned long pgshift = __ffs(pgsize); + + for (p = rb_first(&dma->pfn_list); p; p = rb_next(p)) { + struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node); + + bitmap_set(dma->bitmap, (vpfn->iova - dma->iova) >> pgshift, 1); + } +} + +static int vfio_dma_bitmap_alloc_all(struct vfio_iommu *iommu, size_t pgsize) +{ + struct rb_node *n; + + for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + int ret; + + ret = vfio_dma_bitmap_alloc(dma, pgsize); + if (ret) { + struct rb_node *p; + + for (p = rb_prev(n); p; p = rb_prev(p)) { |