Previously, vfio_pci_zap_bars() (and the wrapper vfio_pci_zap_and_down_write_memory_lock()) calls were paired with calls of vfio_pci_dma_buf_move().
This commit replaces them a unified new function, vfio_pci_zap_revoke_bars() containing both the vfio_pci_dma_buf_move() and the unmap_mapping_range(), making it harder for callers to omit one. It adds a wrapper, vfio_pci_lock_zap_revoke_bars(), which takes the write memory_lock before zapping, and adds a new vfio_pci_unrevoke_bars() for the re-enable path.
However, as of "vfio/pci: Convert BAR mmap() to use a DMABUF" the unmap_mapping_range() to zap is entirely redundant for plain vfio-pci, since the DMABUFs used for BAR mappings already zap PTEs when the vfio_pci_dma_buf_move() occurs.
One exception remains as a FIXME: in nvgrace-gpu, some BAR VMAs conditionally use custom vm_ops, which have not moved to be backed by DMABUFs. If these BARs are mmap()ed, the vdev enables the existing behaviour of unmap_mapping_range() for the device fd address space.
Signed-off-by: Matt Evans mattev@meta.com --- drivers/vfio/pci/nvgrace-gpu/main.c | 5 +++ drivers/vfio/pci/vfio_pci_config.c | 30 ++++++-------- drivers/vfio/pci/vfio_pci_core.c | 62 +++++++++++++++++++---------- drivers/vfio/pci/vfio_pci_priv.h | 3 +- include/linux/vfio_pci_core.h | 1 + 5 files changed, 62 insertions(+), 39 deletions(-)
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index c1df437754f9..5304d15b9a2b 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -358,6 +358,8 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, struct nvgrace_gpu_pci_core_device *nvdev = container_of(core_vdev, struct nvgrace_gpu_pci_core_device, core_device.vdev); + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); struct mem_region *memregion; u64 req_len, pgoff, end; unsigned int index; @@ -368,6 +370,9 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, if (!memregion) return vfio_pci_core_mmap(core_vdev, vma);
+ /* Non-DMABUF BAR mappings need an extra zap */ + vdev->bar_needs_zap = true; + /* * Request to mmap the BAR. Map to the CPU accessible memory on the * GPU using the memory information gathered from the system ACPI diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index a10ed733f0e3..8bfab0da481c 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -590,12 +590,10 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos, virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY); new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
- if (!new_mem) { - vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_dma_buf_move(vdev, true); - } else { + if (!new_mem) + vfio_pci_lock_zap_revoke_bars(vdev); + else down_write(&vdev->memory_lock); - }
/* * If the user is writing mem/io enable (new_mem/io) and we @@ -631,7 +629,7 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos, *virt_cmd |= cpu_to_le16(new_cmd & mask);
if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); }
@@ -712,16 +710,14 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm) static void vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t state) { - if (state >= PCI_D3hot) { - vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_dma_buf_move(vdev, true); - } else { + if (state >= PCI_D3hot) + vfio_pci_lock_zap_revoke_bars(vdev); + else down_write(&vdev->memory_lock); - }
vfio_pci_set_power_state(vdev, state); if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); }
@@ -908,11 +904,10 @@ static int vfio_exp_config_write(struct vfio_pci_core_device *vdev, int pos, &cap);
if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) { - vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_dma_buf_move(vdev, true); + vfio_pci_lock_zap_revoke_bars(vdev); pci_try_reset_function(vdev->pdev); if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); } } @@ -993,11 +988,10 @@ static int vfio_af_config_write(struct vfio_pci_core_device *vdev, int pos, &cap);
if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) { - vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_dma_buf_move(vdev, true); + vfio_pci_lock_zap_revoke_bars(vdev); pci_try_reset_function(vdev->pdev); if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); } } diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index c00a61d61250..464b63585bef 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -319,8 +319,7 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, * The vdev power related flags are protected with 'memory_lock' * semaphore. */ - vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_dma_buf_move(vdev, true); + vfio_pci_lock_zap_revoke_bars(vdev);
if (vdev->pm_runtime_engaged) { up_write(&vdev->memory_lock); @@ -406,7 +405,7 @@ static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) down_write(&vdev->memory_lock); __vfio_pci_runtime_pm_exit(vdev); if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); }
@@ -1229,7 +1228,7 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, if (!vdev->reset_works) return -EINVAL;
- vfio_pci_zap_and_down_write_memory_lock(vdev); + vfio_pci_lock_zap_revoke_bars(vdev);
/* * This function can be invoked while the power state is non-D0. If @@ -1242,10 +1241,9 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, */ vfio_pci_set_power_state(vdev, PCI_D0);
- vfio_pci_dma_buf_move(vdev, true); ret = pci_try_reset_function(vdev->pdev); if (__vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock);
return ret; @@ -1613,20 +1611,44 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu } EXPORT_SYMBOL_GPL(vfio_pci_core_write);
-static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev) +static void vfio_pci_zap_revoke_bars(struct vfio_pci_core_device *vdev) { - struct vfio_device *core_vdev = &vdev->vdev; - loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); - loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); - loff_t len = end - start; + lockdep_assert_held_write(&vdev->memory_lock); + vfio_pci_dma_buf_move(vdev, true);
- unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true); + /* + * All VFIO PCI BARs are backed by DMABUFs, with the current + * exception of the nvgrace-gpu device which uses its own + * vm_ops for a subset of BARs. For this, BAR mappings are + * still made in the vdev's address_space, and a zap is + * required. The tracking is crude, and will (harmlessly) + * continue to zap if the special BAR is unmapped, but that + * behaviour isn't the common case. + * + * FIXME: This can go away if the special nvgrace-gpu mapping + * is converted to use DMABUF. + */ + if (vdev->bar_needs_zap) { + struct vfio_device *core_vdev = &vdev->vdev; + loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); + loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); + loff_t len = end - start; + + unmap_mapping_range(core_vdev->inode->i_mapping, + start, len, true); + } }
-void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) +void vfio_pci_lock_zap_revoke_bars(struct vfio_pci_core_device *vdev) { down_write(&vdev->memory_lock); - vfio_pci_zap_bars(vdev); + vfio_pci_zap_revoke_bars(vdev); +} + +void vfio_pci_unrevoke_bars(struct vfio_pci_core_device *vdev) +{ + lockdep_assert_held_write(&vdev->memory_lock); + vfio_pci_dma_buf_move(vdev, false); }
u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) @@ -2480,9 +2502,10 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, }
/* - * Take the memory write lock for each device and zap BAR - * mappings to prevent the user accessing the device while in - * reset. Locking multiple devices is prone to deadlock, + * Take the memory write lock for each device and + * zap/revoke BAR mappings to prevent the user (or + * peers) accessing the device while in reset. + * Locking multiple devices is prone to deadlock, * runaway and unwind if we hit contention. */ if (!down_write_trylock(&vdev->memory_lock)) { @@ -2490,8 +2513,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, break; }
- vfio_pci_dma_buf_move(vdev, true); - vfio_pci_zap_bars(vdev); + vfio_pci_zap_revoke_bars(vdev); }
if (!list_entry_is_head(vdev, @@ -2521,7 +2543,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, list_for_each_entry_from_reverse(vdev, &dev_set->device_list, vdev.dev_set_list) { if (vdev->vdev.open_count && __vfio_pci_memory_enabled(vdev)) - vfio_pci_dma_buf_move(vdev, false); + vfio_pci_unrevoke_bars(vdev); up_write(&vdev->memory_lock); }
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h index 868a54ba482c..a8edbee6ce56 100644 --- a/drivers/vfio/pci/vfio_pci_priv.h +++ b/drivers/vfio/pci/vfio_pci_priv.h @@ -82,7 +82,8 @@ void vfio_config_free(struct vfio_pci_core_device *vdev); int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t state);
-void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev); +void vfio_pci_lock_zap_revoke_bars(struct vfio_pci_core_device *vdev); +void vfio_pci_unrevoke_bars(struct vfio_pci_core_device *vdev); u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, u16 cmd); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 2ea4e773c121..c1cd67741125 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -127,6 +127,7 @@ struct vfio_pci_core_device { bool needs_pm_restore:1; bool pm_intx_masked:1; bool pm_runtime_engaged:1; + bool bar_needs_zap:1; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr;