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 | 77 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_intrs.c | 18 | ||||
| -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_iommu_type1.c | 110 |
7 files changed, 554 insertions, 54 deletions
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index 7570c7602ab4..f32c582611eb 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 02206162eaa9..a72fd5309b09 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -27,6 +27,7 @@ #include <linux/vfio.h> #include <linux/vgaarb.h> #include <linux/nospec.h> +#include <linux/sched/mm.h> #include "vfio_pci_private.h" @@ -177,6 +178,7 @@ 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 @@ -472,6 +474,19 @@ static void vfio_pci_release(void *device_data) if (!(--vdev->refcnt)) { 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); @@ -688,6 +703,12 @@ 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) { @@ -761,7 +782,7 @@ 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; @@ -781,10 +802,7 @@ 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; @@ -792,8 +810,8 @@ 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: @@ -936,8 +954,16 @@ 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; @@ -1017,8 +1043,9 @@ 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); @@ -1070,9 +1097,9 @@ 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; @@ -1085,8 +1112,9 @@ 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); @@ -1105,13 +1133,63 @@ 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_sem, 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; @@ -1192,6 +1270,202 @@ 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_sem 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_sem => vma_lock + * ordering, which requires using vma_lock to walk vma_list to + * acquire an mm, then dropping vma_lock to get the mmap_sem and + * reacquiring vma_lock. This logic is derived from similar + * requirements in uverbs_user_mmap_disassociate(). + * + * mmap_sem 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_sem 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_sem 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 (!down_read_trylock(&mm->mmap_sem)) { + mmput(mm); + return 0; + } + } else { + down_read(&mm->mmap_sem); + } + if (mmget_still_valid(mm)) { + if (try) { + if (!mutex_trylock(&vdev->vma_lock)) { + up_read(&mm->mmap_sem); + 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); + } + up_read(&mm->mmap_sem); + 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; @@ -1250,8 +1524,14 @@ 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) @@ -1327,6 +1607,9 @@ 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) { @@ -1516,12 +1799,6 @@ 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; @@ -1552,6 +1829,39 @@ 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 f0891bd8444c..bf32997c557f 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->no_command_memory || (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) @@ -504,8 +518,8 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos, count = vfio_default_config_read(vdev, pos, count, perm, offset, val); - /* Mask in virtual memory enable for SR-IOV devices */ - if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) { + /* Mask in virtual memory enable */ + if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) { u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); u32 tmp_val = le32_to_cpu(*val); @@ -554,13 +568,18 @@ 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 @@ -568,17 +587,22 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, * shows it disabled (phys_mem/io, then the device has * undergone some kind of backdoor reset and needs to be * restored before we allow it to enable the bars. - * SR-IOV devices will trigger this, but we catch them later + * SR-IOV devices will trigger this - for mem enable let's + * catch this now and for io enable it will be caught later */ - if ((new_mem && virt_mem && !phys_mem) || + if ((new_mem && virt_mem && !phys_mem && + !pdev->no_command_memory) || (new_io && virt_io && !phys_io) || vfio_need_bar_restore(vdev)) vfio_bar_restore(vdev); } 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 @@ -589,6 +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 */ @@ -826,8 +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); + } } /* @@ -905,8 +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; @@ -1460,7 +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); @@ -1698,6 +1735,17 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ } + if (pdev->no_command_memory) { + /* + * VFs and devices that set pdev->no_command_memory do not + * 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) vconfig[PCI_INTERRUPT_PIN] = 0; @@ -1726,8 +1774,11 @@ 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..869dce5f134d 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); @@ -341,11 +352,13 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, vdev->ctx[vector].producer.token = trigger; vdev->ctx[vector].producer.irq = irq; ret = irq_bypass_register_producer(&vdev->ctx[vector].producer); - if (unlikely(ret)) + if (unlikely(ret)) { dev_info(&pdev->dev, "irq bypass producer (token %p) registration fails: %d\n", vdev->ctx[vector].producer.token, ret); + vdev->ctx[vector].producer.token = NULL; + } vdev->ctx[vector].trigger = trigger; return 0; @@ -376,6 +389,7 @@ 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 +398,9 @@ 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_private.h b/drivers/vfio/pci/vfio_pci_private.h index ee6ee91718a4..987b4d311fde 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -84,6 +84,11 @@ struct vfio_pci_reflck { struct mutex lock; }; +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_RESOURCE_END + 1]; @@ -122,6 +127,9 @@ struct vfio_pci_device { struct list_head dummy_resources_list; struct mutex ioeventfds_lock; struct list_head ioeventfds_list; + 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) @@ -164,6 +172,13 @@ 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 0120d8324a40..83f81d24df78 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_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6cc47af1f06d..3b31e83a9215 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -335,6 +335,32 @@ static int put_pfn(unsigned long pfn, int prot) return 0; } +static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, + unsigned long vaddr, unsigned long *pfn, + bool write_fault) +{ + int ret; + + ret = follow_pfn(vma, vaddr, pfn); + if (ret) { + bool unlocked = false; + + ret = fixup_user_fault(NULL, mm, vaddr, + FAULT_FLAG_REMOTE | + (write_fault ? FAULT_FLAG_WRITE : 0), + &unlocked); + if (unlocked) + return -EAGAIN; + + if (ret) + return ret; + + ret = follow_pfn(vma, vaddr, pfn); + } + + return ret; +} + static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, int prot, unsigned long *pfn) { @@ -377,12 +403,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, vaddr = untagged_addr(vaddr); +retry: vma = find_vma_intersection(mm, vaddr, vaddr + 1); if (vma && vma->vm_flags & VM_PFNMAP) { - if (!follow_pfn(vma, vaddr, pfn) && - is_invalid_reserved_pfn(*pfn)) - ret = 0; + ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE); + if (ret == -EAGAIN) + goto retry; + + if (!ret && !is_invalid_reserved_pfn(*pfn)) + ret = -EFAULT; } up_read(&mm->mmap_sem); @@ -601,7 +631,8 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]); if (ret) { - vfio_unpin_page_external(dma, iova, do_accounting); + if (put_pfn(phys_pfn[i], dma->prot) && do_accounting) + vfio_lock_acct(dma, -1, true); goto pin_unwind; } } @@ -1187,13 +1218,16 @@ static int vfio_bus_type(struct device *dev, void *data) static int vfio_iommu_replay(struct vfio_iommu *iommu, struct vfio_domain *domain) { - struct vfio_domain *d; + struct vfio_domain *d = NULL; struct rb_node *n; unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; int ret; /* Arbitrarily pick the first domain in the list for lookups */ - d = list_first_entry(&iommu->domain_list, struct vfio_domain, next); + if (!list_empty(&iommu->domain_list)) + d = list_first_entry(&iommu->domain_list, + struct vfio_domain, next); + n = rb_first(&iommu->dma_list); for (; n; n = rb_next(n)) { @@ -1211,6 +1245,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, phys_addr_t p; dma_addr_t i; + if (WARN_ON(!d)) { /* mapped w/o a domain?! */ + ret = -EINVAL; + goto unwind; + } + phys = iommu_iova_to_phys(d->domain, iova); if (WARN_ON(!phys)) { @@ -1240,7 +1279,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, if (npage <= 0) { WARN_ON(!npage); ret = (int)npage; - return ret; + goto unwind; } phys = pfn << PAGE_SHIFT; @@ -1249,14 +1288,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, ret = iommu_map(domain->domain, iova, phys, size, dma->prot | domain->prot); - if (ret) - return ret; + if (ret) { + if (!dma->iommu_mapped) + vfio_unpin_pages_remote(dma, iova, + phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, + true); + goto unwind; + } iova += size; } + } + + /* All dmas are now mapped, defer to second tree walk for unwind */ + for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma->iommu_mapped = true; } + return 0; + +unwind: + for (; n; n = rb_prev(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma_addr_t iova; + + if (dma->iommu_mapped) { + iommu_unmap(domain->domain, dma->iova, dma->size); + continue; + } + + iova = dma->iova; + while (iova < dma->iova + dma->size) { + phys_addr_t phys, p; + size_t size; + dma_addr_t i; + + phys = iommu_iova_to_phys(domain->domain, iova); + if (!phys) { + iova += PAGE_SIZE; + continue; + } + + size = PAGE_SIZE; + p = phys + size; + i = iova + size; + while (i < dma->iova + dma->size && + p == iommu_iova_to_phys(domain->domain, i)) { + size += PAGE_SIZE; + p += PAGE_SIZE; + i += PAGE_SIZE; + } + + iommu_unmap(domain->domain, iova, size); + vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, true); + } + } + + return ret; } /* |