From 41311242221e3482b20bfed10fa4d9db98d87016 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 28 Apr 2020 17:02:24 -0600 Subject: [PATCH 1/6] vfio/type1: Support faulting PFNMAP vmas With conversion to follow_pfn(), DMA mapping a PFNMAP range depends on the range being faulted into the vma. Add support to manually provide that, in the same way as done on KVM with hva_to_pfn_remapped(). Reviewed-by: Peter Xu Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 36 ++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index cc1d64765ce7..4a4cb7cd86b2 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -317,6 +317,32 @@ 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) { @@ -339,12 +365,16 @@ 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; } done: up_read(&mm->mmap_sem); From 11c4cd07ba111a09f49625f9e4c851d83daf0a22 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 28 Apr 2020 13:12:20 -0600 Subject: [PATCH 2/6] vfio-pci: Fault mmaps to enable vma tracking Rather than calling remap_pfn_range() when a region is mmap'd, setup a vm_ops handler to support dynamic faulting of the range on access. This allows us to manage a list of vmas actively mapping the area that we can later use to invalidate those mappings. The open callback invalidates the vma range so that all tracking is inserted in the fault handler and removed in the close handler. Reviewed-by: Peter Xu Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 76 ++++++++++++++++++++++++++++- drivers/vfio/pci/vfio_pci_private.h | 7 +++ 2 files changed, 81 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 6c6b37b5c04e..66a545a01f8f 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1299,6 +1299,70 @@ 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); } +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; + + mutex_lock(&vdev->vma_lock); + list_add(&mmap_vma->vma_next, &vdev->vma_list); + mutex_unlock(&vdev->vma_lock); + + 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; + + if (vfio_pci_add_vma(vdev, vma)) + return VM_FAULT_OOM; + + if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, vma->vm_page_prot)) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} + +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 +1421,14 @@ 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 +1678,8 @@ 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); ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 36ec69081ecd..9b25f9f6ce1d 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 +137,8 @@ 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; }; #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) From abafbc551fddede3e0a08dee1dcde08fc0eb8476 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 22 Apr 2020 13:48:11 -0600 Subject: [PATCH 3/6] vfio-pci: Invalidate mmaps and block MMIO access on disabled memory Accessing the disabled memory space of a PCI device would typically result in a master abort response on conventional PCI, or an unsupported request on PCI express. The user would generally see these as a -1 response for the read return data and the write would be silently discarded, possibly with an uncorrected, non-fatal AER error triggered on the host. Some systems however take it upon themselves to bring down the entire system when they see something that might indicate a loss of data, such as this discarded write to a disabled memory space. To avoid this, we want to try to block the user from accessing memory spaces while they're disabled. We start with a semaphore around the memory enable bit, where writers modify the memory enable state and must be serialized, while readers make use of the memory region and can access in parallel. Writers include both direct manipulation via the command register, as well as any reset path where the internal mechanics of the reset may both explicitly and implicitly disable memory access, and manipulation of the MSI-X configuration, where the MSI-X vector table resides in MMIO space of the device. Readers include the read and write file ops to access the vfio device fd offsets as well as memory mapped access. In the latter case, we make use of our new vma list support to zap, or invalidate, those memory mappings in order to force them to be faulted back in on access. Our semaphore usage will stall user access to MMIO spaces across internal operations like reset, but the user might experience new behavior when trying to access the MMIO space while disabled via the PCI command register. Access via read or write while disabled will return -EIO and access via memory maps will result in a SIGBUS. This is expected to be compatible with known use cases and potentially provides better error handling capabilities than present in the hardware, while avoiding the more readily accessible and severe platform error responses that might otherwise occur. Fixes: CVE-2020-12888 Reviewed-by: Peter Xu Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 291 ++++++++++++++++++++++++---- drivers/vfio/pci/vfio_pci_config.c | 36 +++- drivers/vfio/pci/vfio_pci_intrs.c | 14 ++ drivers/vfio/pci/vfio_pci_private.h | 8 + drivers/vfio/pci/vfio_pci_rdwr.c | 24 ++- 5 files changed, 330 insertions(+), 43 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 66a545a01f8f..aabba6439a5b 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -26,6 +26,7 @@ #include #include #include +#include #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 @@ -736,6 +738,12 @@ 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 +817,7 @@ 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 +837,7 @@ 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 +845,8 @@ 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 +989,16 @@ 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 +1078,9 @@ 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 +1132,9 @@ 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 +1147,9 @@ 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 +1168,63 @@ 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; @@ -1299,8 +1364,126 @@ 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); } -static int vfio_pci_add_vma(struct vfio_pci_device *vdev, - struct vm_area_struct *vma) +/* 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; @@ -1309,10 +1492,7 @@ static int vfio_pci_add_vma(struct vfio_pci_device *vdev, return -ENOMEM; mmap_vma->vma = vma; - - mutex_lock(&vdev->vma_lock); list_add(&mmap_vma->vma_next, &vdev->vma_list); - mutex_unlock(&vdev->vma_lock); return 0; } @@ -1346,15 +1526,32 @@ 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; - if (vfio_pci_add_vma(vdev, vma)) - return VM_FAULT_OOM; + 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)) - return VM_FAULT_SIGBUS; + ret = VM_FAULT_SIGBUS; - return VM_FAULT_NOPAGE; +up_out: + up_read(&vdev->memory_lock); + return ret; } static const struct vm_operations_struct vfio_pci_mmap_ops = { @@ -1680,6 +1877,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) 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) @@ -1933,12 +2131,6 @@ 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; @@ -1969,6 +2161,39 @@ 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..3dcddbd572e6 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -395,6 +395,14 @@ 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) +{ + u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); + + return 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 +564,18 @@ 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 +592,11 @@ 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 +607,8 @@ 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 +846,11 @@ 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 +928,11 @@ 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; 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_private.h b/drivers/vfio/pci/vfio_pci_private.h index 9b25f9f6ce1d..86a02aff8735 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -139,6 +139,7 @@ struct vfio_pci_device { 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) @@ -181,6 +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; } From bc138db1b96264b9c1779cf18d5a3b186aa90066 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 8 Apr 2020 11:45:28 -0600 Subject: [PATCH 4/6] vfio-pci: Mask cap zero The PCI Code and ID Assignment Specification changed capability ID 0 from reserved to a NULL capability in the v1.1 revision. The NULL capability is defined to include only the 16-bit capability header, ie. only the ID and next pointer. Unfortunately vfio-pci creates a map of config space, where ID 0 is used to reserve the standard type 0 header. Finding an actual capability with this ID therefore results in a bogus range marked in that map and conflicts with subsequent capabilities. As this seems to be a dummy capability anyway and we already support dropping capabilities, let's hide this one rather than delving into the potentially subtle dependencies within our map. Seen on an NVIDIA Tesla T4. Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 90c0b80f8acf..8fc27393bf7a 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1462,7 +1462,12 @@ 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); From 3e63b94b6274324ff2e7d8615df31586de827c4e Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sun, 10 May 2020 12:16:56 -0400 Subject: [PATCH 5/6] vfio/pci: fix memory leaks in alloc_perm_bits() vfio_pci_disable() calls vfio_config_free() but forgets to call free_perm_bits() resulting in memory leaks, unreferenced object 0xc000000c4db2dee0 (size 16): comm "qemu-kvm", pid 4305, jiffies 4295020272 (age 3463.780s) hex dump (first 16 bytes): 00 00 ff 00 ff ff ff ff ff ff ff ff ff ff 00 00 ................ backtrace: [<00000000a6a4552d>] alloc_perm_bits+0x58/0xe0 [vfio_pci] [<00000000ac990549>] vfio_config_init+0xdf0/0x11b0 [vfio_pci] init_pci_cap_msi_perm at drivers/vfio/pci/vfio_pci_config.c:1125 (inlined by) vfio_msi_cap_len at drivers/vfio/pci/vfio_pci_config.c:1180 (inlined by) vfio_cap_len at drivers/vfio/pci/vfio_pci_config.c:1241 (inlined by) vfio_cap_init at drivers/vfio/pci/vfio_pci_config.c:1468 (inlined by) vfio_config_init at drivers/vfio/pci/vfio_pci_config.c:1707 [<000000006db873a1>] vfio_pci_open+0x234/0x700 [vfio_pci] [<00000000630e1906>] vfio_group_fops_unl_ioctl+0x8e0/0xb84 [vfio] [<000000009e34c54f>] ksys_ioctl+0xd8/0x130 [<000000006577923d>] sys_ioctl+0x28/0x40 [<000000006d7b1cf2>] system_call_exception+0x114/0x1e0 [<0000000008ea7dd5>] system_call_common+0xf0/0x278 unreferenced object 0xc000000c4db2e330 (size 16): comm "qemu-kvm", pid 4305, jiffies 4295020272 (age 3463.780s) hex dump (first 16 bytes): 00 ff ff 00 ff ff ff ff ff ff ff ff ff ff 00 00 ................ backtrace: [<000000004c71914f>] alloc_perm_bits+0x44/0xe0 [vfio_pci] [<00000000ac990549>] vfio_config_init+0xdf0/0x11b0 [vfio_pci] [<000000006db873a1>] vfio_pci_open+0x234/0x700 [vfio_pci] [<00000000630e1906>] vfio_group_fops_unl_ioctl+0x8e0/0xb84 [vfio] [<000000009e34c54f>] ksys_ioctl+0xd8/0x130 [<000000006577923d>] sys_ioctl+0x28/0x40 [<000000006d7b1cf2>] system_call_exception+0x114/0x1e0 [<0000000008ea7dd5>] system_call_common+0xf0/0x278 Fixes: 89e1f7d4c66d ("vfio: Add PCI device driver") Signed-off-by: Qian Cai [aw: rolled in follow-up patch] Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 90c0b80f8acf..43b95f9cdaf7 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1728,8 +1728,11 @@ 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; + } } /* From 1518ac272e789cae8c555d69951b032a275b7602 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Mon, 11 May 2020 00:34:50 -0400 Subject: [PATCH 6/6] vfio/pci: fix memory leaks of eventfd ctx Finished a qemu-kvm (-device vfio-pci,host=0001:01:00.0) triggers a few memory leaks after a while because vfio_pci_set_ctx_trigger_single() calls eventfd_ctx_fdget() without the matching eventfd_ctx_put() later. Fix it by calling eventfd_ctx_put() for those memory in vfio_pci_release() before vfio_device_release(). unreferenced object 0xebff008981cc2b00 (size 128): comm "qemu-kvm", pid 4043, jiffies 4294994816 (age 9796.310s) hex dump (first 32 bytes): 01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........ backtrace: [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4 [<000000005fcec025>] do_eventfd+0x54/0x1ac [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44 [<00000000b819758c>] do_el0_svc+0x128/0x1dc [<00000000b244e810>] el0_sync_handler+0xd0/0x268 [<00000000d495ef94>] el0_sync+0x164/0x180 unreferenced object 0x29ff008981cc4180 (size 128): comm "qemu-kvm", pid 4043, jiffies 4294994818 (age 9796.290s) hex dump (first 32 bytes): 01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........ backtrace: [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4 [<000000005fcec025>] do_eventfd+0x54/0x1ac [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44 [<00000000b819758c>] do_el0_svc+0x128/0x1dc [<00000000b244e810>] el0_sync_handler+0xd0/0x268 [<00000000d495ef94>] el0_sync+0x164/0x180 Signed-off-by: Qian Cai Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 6c6b37b5c04e..080e6608f297 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -519,6 +519,10 @@ 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); + if (vdev->err_trigger) + eventfd_ctx_put(vdev->err_trigger); + if (vdev->req_trigger) + eventfd_ctx_put(vdev->req_trigger); } mutex_unlock(&vdev->reflck->lock);