Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "All various fixes:

   - Typo breaking the veventq uAPI for 32 bit userspace

   - Several Sashiko found errors in the veventq and fault fd paths

   - Fix incorrect use of dmabuf locks, and possible races with iommufd
     destroy and dmabuf revoke

   - Sashiko errors found in the uAPI validation for IOMMU_HWPT_INVALIDATE"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd:
  iommu: Avoid copying the user array twice in the full-array copy helper
  iommufd/selftest: Add invalidation entry_num and entry_len boundary tests
  iommufd: Set upper bounds on cache invalidation entry_num and entry_len
  iommufd: Clarify IOAS_MAP_FILE dma-buf support
  iommufd: Destroy the pages content after detaching from dmabuf
  iommufd: Take dma_resv lock before dma_buf_unpin() in release path
  iommufd/selftest: Cover invalid read counts on vEVENTQ FD
  iommufd: Avoid partial fault group delivery in iommufd_fault_fops_read()
  iommufd: Break the loop on failure in iommufd_fault_fops_read()
  iommufd: Reject invalid read count in iommufd_fault_fops_read()
  iommufd: Propagate allocation failure in iommufd_veventq_deliver_fetch()
  iommufd: Reject invalid read count in iommufd_veventq_fops_read()
  iommufd: Rewind header length in done if iommufd_veventq_fops_read() fails
  iommufd/selftest: Add boundary tests for veventq_depth
  iommufd: Set veventq_depth upper bound
  iommufd: Move vevent memory allocation outside spinlock
  iommufd: Fix data_len byte-count vs element-count mismatch
  iommufd: Use sizeof(*hdr) instead of sizeof(hdr) in veventq read

drivers/iommu/iommufd/driver.c

@@ -149,15 +149,18 @@ int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 		goto out_unlock_veventqs;
 	}
 
-	spin_lock(&veventq->common.lock);
-	if (veventq->num_events == veventq->depth) {
+	/* Pre-allocate to avoid GFP_ATOMIC; use GFP_NOWAIT to avoid sleeping */
+	vevent = kzalloc_flex(*vevent, event_data, data_len, GFP_NOWAIT);
+	if (!vevent) {
+		spin_lock(&veventq->common.lock);
 		vevent = &veventq->lost_events_header;
+		rc = -ENOMEM;
 		goto out_set_header;
 	}
 
-	vevent = kzalloc_flex(*vevent, event_data, data_len, GFP_ATOMIC);
-	if (!vevent) {
-		rc = -ENOMEM;
+	spin_lock(&veventq->common.lock);
+	if (veventq->num_events == veventq->depth) {
+		kfree(vevent);
 		vevent = &veventq->lost_events_header;
 		goto out_set_header;
 	}

drivers/iommu/iommufd/eventq.c

@@ -139,9 +139,14 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
 
 	mutex_lock(&fault->mutex);
 	while ((group = iommufd_fault_deliver_fetch(fault))) {
+		size_t group_done = done;
+
 		if (done >= count ||
 		    group->fault_count * fault_size > count - done) {
 			iommufd_fault_deliver_restore(fault, group);
+			/* Read count doesn't fit the first fault group */
+			if (done == 0)
+				rc = -EINVAL;
 			break;
 		}
 
@@ -157,14 +162,17 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
 			iommufd_compose_fault_message(&iopf->fault,
 						      &data, idev,
 						      group->cookie);
-			if (copy_to_user(buf + done, &data, fault_size)) {
+			if (copy_to_user(buf + group_done, &data, fault_size)) {
 				xa_erase(&fault->response, group->cookie);
 				iommufd_fault_deliver_restore(fault, group);
 				rc = -EFAULT;
 				break;
 			}
-			done += fault_size;
+			group_done += fault_size;
 		}
+		if (rc)
+			break;
+		done = group_done;
 	}
 	mutex_unlock(&fault->mutex);
 
@@ -264,8 +272,10 @@ iommufd_veventq_deliver_fetch(struct iommufd_veventq *veventq)
 		/* Make a copy of the lost_events_header for copy_to_user */
 		if (next == &veventq->lost_events_header) {
 			vevent = kzalloc_obj(*vevent, GFP_ATOMIC);
-			if (!vevent)
+			if (!vevent) {
+				vevent = ERR_PTR(-ENOMEM);
 				goto out_unlock;
+			}
 		}
 		list_del(&next->node);
 		if (vevent)
@@ -310,8 +320,17 @@ static ssize_t iommufd_veventq_fops_read(struct file *filep, char __user *buf,
 
 	if (*ppos)
 		return -ESPIPE;
+	/* Minimum read count is a vEVENT header */
+	if (count < sizeof(*hdr))
+		return -EINVAL;
 
 	while ((cur = iommufd_veventq_deliver_fetch(veventq))) {
+		if (IS_ERR(cur)) {
+			if (done == 0)
+				rc = PTR_ERR(cur);
+			break;
+		}
+
 		/* Validate the remaining bytes against the header size */
 		if (done >= count || sizeof(*hdr) > count - done) {
 			iommufd_veventq_deliver_restore(veventq, cur);
@@ -321,8 +340,11 @@ static ssize_t iommufd_veventq_fops_read(struct file *filep, char __user *buf,
 
 		/* If being a normal vEVENT, validate against the full size */
 		if (!vevent_for_lost_events_header(cur) &&
-		    sizeof(hdr) + cur->data_len > count - done) {
+		    sizeof(*hdr) + cur->data_len > count - done) {
 			iommufd_veventq_deliver_restore(veventq, cur);
+			/* Read count doesn't fit a single normal vEVENT */
+			if (done == 0)
+				rc = -EINVAL;
 			break;
 		}
 
@@ -336,6 +358,7 @@ static ssize_t iommufd_veventq_fops_read(struct file *filep, char __user *buf,
 		if (cur->data_len &&
 		    copy_to_user(buf + done, cur->event_data, cur->data_len)) {
 			iommufd_veventq_deliver_restore(veventq, cur);
+			done -= sizeof(*hdr);
 			rc = -EFAULT;
 			break;
 		}
@@ -473,6 +496,9 @@ int iommufd_fault_iopf_handler(struct iopf_group *group)
 static const struct file_operations iommufd_veventq_fops =
 	INIT_EVENTQ_FOPS(iommufd_veventq_fops_read, NULL);
 
+/* An arbitrary upper bound for veventq_depth that fits all existing HWs */
+#define VEVENTQ_MAX_DEPTH (1U << 19)
+
 int iommufd_veventq_alloc(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_veventq_alloc *cmd = ucmd->cmd;
@@ -484,7 +510,7 @@ int iommufd_veventq_alloc(struct iommufd_ucmd *ucmd)
 	if (cmd->flags || cmd->__reserved ||
 	    cmd->type == IOMMU_VEVENTQ_TYPE_DEFAULT)
 		return -EOPNOTSUPP;
-	if (!cmd->veventq_depth)
+	if (!cmd->veventq_depth || cmd->veventq_depth > VEVENTQ_MAX_DEPTH)
 		return -EINVAL;
 
 	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);

drivers/iommu/iommufd/hw_pagetable.c

@@ -489,6 +489,9 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	return rc;
 }
 
+/* An arbitrary entry_num cap, far above any realistic invalidation batch */
+#define IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX (1U << 19)
+
 int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
@@ -507,7 +510,13 @@ int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
 		goto out;
 	}
 
-	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+	/*
+	 * Bound entry_num and entry_len so a single call cannot pin the CPU;
+	 * entry_len also caps the copy_struct_from_user() trailing-zero scan.
+	 */
+	if (cmd->entry_num &&
+	    (!cmd->data_uptr || !cmd->entry_len || cmd->entry_len > PAGE_SIZE ||
+	     cmd->entry_num > IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX)) {
 		rc = -EINVAL;
 		goto out;
 	}

drivers/iommu/iommufd/iommufd_private.h

@@ -602,7 +602,7 @@ struct iommufd_vevent {
 	struct iommufd_vevent_header header;
 	struct list_head node; /* for iommufd_eventq::deliver */
 	ssize_t data_len;
-	u64 event_data[] __counted_by(data_len);
+	u8 event_data[] __counted_by(data_len);
 };
 
 #define vevent_for_lost_events_header(vevent) \

drivers/iommu/iommufd/pages.c

@@ -1656,20 +1656,22 @@ void iopt_release_pages(struct kref *kref)
 	WARN_ON(!RB_EMPTY_ROOT(&pages->domains_itree.rb_root));
 	WARN_ON(pages->npinned);
 	WARN_ON(!xa_empty(&pages->pinned_pfns));
-	mmdrop(pages->source_mm);
-	mutex_destroy(&pages->mutex);
-	put_task_struct(pages->source_task);
-	free_uid(pages->source_user);
 	if (iopt_is_dmabuf(pages) && pages->dmabuf.attach) {
 		struct dma_buf *dmabuf = pages->dmabuf.attach->dmabuf;
 
+		dma_resv_lock(dmabuf->resv, NULL);
 		dma_buf_unpin(pages->dmabuf.attach);
+		dma_resv_unlock(dmabuf->resv);
 		dma_buf_detach(dmabuf, pages->dmabuf.attach);
 		dma_buf_put(dmabuf);
 		WARN_ON(!list_empty(&pages->dmabuf.tracker));
 	} else if (pages->type == IOPT_ADDRESS_FILE) {
 		fput(pages->file);
 	}
+	mmdrop(pages->source_mm);
+	mutex_destroy(&pages->mutex);
+	put_task_struct(pages->source_task);
+	free_uid(pages->source_user);
 	kfree(pages);
 }
 

include/linux/iommu.h

@@ -575,6 +575,7 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
 				   user_array->entry_num *
 					   user_array->entry_len))
 			return -EFAULT;
+		return 0;
 	}
 
 	/* Copy item by item */

include/uapi/linux/iommufd.h

@@ -224,13 +224,17 @@ struct iommu_ioas_map {
  * @size: sizeof(struct iommu_ioas_map_file)
  * @flags: same as for iommu_ioas_map
  * @ioas_id: same as for iommu_ioas_map
- * @fd: the memfd to map
- * @start: byte offset from start of file to map from
+ * @fd: the memfd or supported dma-buf file to map
+ * @start: byte offset from start of the file to map from
  * @length: same as for iommu_ioas_map
  * @iova: same as for iommu_ioas_map
  *
- * Set an IOVA mapping from a memfd file.  All other arguments and semantics
- * match those of IOMMU_IOAS_MAP.
+ * Set an IOVA mapping from a memfd file. On kernels with dma-buf support,
+ * supported dma-buf files may also be accepted. This is not a generic
+ * dma-buf import path; currently supported dma-bufs include single-range
+ * VFIO PCI dma-bufs exported through VFIO_DEVICE_FEATURE_DMA_BUF, and
+ * other dma-bufs may be rejected. All other arguments and semantics match
+ * those of IOMMU_IOAS_MAP.
  */
 struct iommu_ioas_map_file {
 	__u32 size;

tools/testing/selftests/iommu/iommufd.c

@@ -556,6 +556,21 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 					 1, &num_inv);
 		assert(!num_inv);
 
+		/* Negative test: entry_len is bounded by PAGE_SIZE */
+		num_inv = 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 PAGE_SIZE + 1, &num_inv);
+		assert(!num_inv);
+
+		/* Negative test: entry_num is bounded */
+#define IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX (1U << 19)
+		num_inv = IOMMU_HWPT_INVALIDATE_ENTRY_NUM_MAX + 1;
+		test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs,
+					 IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+					 sizeof(*inv_reqs), &num_inv);
+		assert(!num_inv);
+
 		/* Negative test: invalid flag is passed */
 		num_inv = 1;
 		inv_reqs[0].flags = 0xffffffff;
@@ -2980,22 +2995,54 @@ TEST_F(iommufd_viommu, vdevice_alloc)
 	uint32_t veventq_id;
 	uint32_t veventq_fd;
 	int prev_seq = -1;
+	size_t hdr_size = sizeof(struct iommufd_vevent_header);
+	char vbuf[64];
 
 	if (dev_id) {
 		/* Must allocate vdevice before attaching to a nested hwpt */
 		test_err_mock_domain_replace(ENOENT, self->stdev_id,
 					     self->nested_hwpt_id);
 
+		/* Test depth lower and upper bounds (mirrors kernel cap) */
+#define VEVENTQ_MAX_DEPTH (1U << 19)
+		test_err_veventq_alloc(EINVAL, viommu_id,
+				       IOMMU_VEVENTQ_TYPE_SELFTEST, 0, NULL,
+				       NULL);
+		test_err_veventq_alloc(EINVAL, viommu_id,
+				       IOMMU_VEVENTQ_TYPE_SELFTEST,
+				       VEVENTQ_MAX_DEPTH + 1, NULL, NULL);
+		test_cmd_veventq_alloc(viommu_id, IOMMU_VEVENTQ_TYPE_SELFTEST,
+				       VEVENTQ_MAX_DEPTH, &veventq_id,
+				       &veventq_fd);
+		close(veventq_fd);
+		test_ioctl_destroy(veventq_id);
+
 		/* Allocate a vEVENTQ with veventq_depth=2 */
 		test_cmd_veventq_alloc(viommu_id, IOMMU_VEVENTQ_TYPE_SELFTEST,
-				       &veventq_id, &veventq_fd);
+				       2, &veventq_id, &veventq_fd);
 		test_err_veventq_alloc(EEXIST, viommu_id,
-				       IOMMU_VEVENTQ_TYPE_SELFTEST, NULL, NULL);
+				       IOMMU_VEVENTQ_TYPE_SELFTEST, 2, NULL,
+				       NULL);
+
+		/* Invalid read counts on an empty vEVENTQ */
+		ASSERT_EQ(-1, read(veventq_fd, vbuf, 0));
+		ASSERT_EQ(EINVAL, errno);
+		ASSERT_EQ(-1, read(veventq_fd, vbuf, hdr_size - 1));
+		ASSERT_EQ(EINVAL, errno);
+
 		/* Set vdev_id to 0x99, unset it, and set to 0x88 */
 		test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id);
 		test_cmd_mock_domain_replace(self->stdev_id,
 					     self->nested_hwpt_id);
 		test_cmd_trigger_vevents(dev_id, 1);
+
+		/* Invalid read counts on a non-empty vEVENTQ */
+		ASSERT_EQ(-1, read(veventq_fd, vbuf, 0));
+		ASSERT_EQ(EINVAL, errno);
+		/* header fits but the event's payload doesn't */
+		ASSERT_EQ(-1, read(veventq_fd, vbuf, hdr_size));
+		ASSERT_EQ(EINVAL, errno);
+
 		test_cmd_read_vevents(veventq_fd, 1, 0x99, &prev_seq);
 		test_err_vdevice_alloc(EEXIST, viommu_id, dev_id, 0x99,
 				       &vdev_id);

tools/testing/selftests/iommu/iommufd_fail_nth.c

@@ -712,7 +712,7 @@ TEST_FAIL_NTH(basic_fail_nth, device)
 		return -1;
 
 	if (_test_cmd_veventq_alloc(self->fd, viommu_id,
-				    IOMMU_VEVENTQ_TYPE_SELFTEST, &veventq_id,
+				    IOMMU_VEVENTQ_TYPE_SELFTEST, 2, &veventq_id,
 				    &veventq_fd))
 		return -1;
 	close(veventq_fd);

tools/testing/selftests/iommu/iommufd_utils.h

@@ -1060,12 +1060,13 @@ static int _test_cmd_hw_queue_alloc(int fd, __u32 viommu_id, __u32 type,
 					      base_addr, len, out_qid))
 
 static int _test_cmd_veventq_alloc(int fd, __u32 viommu_id, __u32 type,
-				   __u32 *veventq_id, __u32 *veventq_fd)
+				   __u32 depth, __u32 *veventq_id,
+				   __u32 *veventq_fd)
 {
 	struct iommu_veventq_alloc cmd = {
 		.size = sizeof(cmd),
 		.type = type,
-		.veventq_depth = 2,
+		.veventq_depth = depth,
 		.viommu_id = viommu_id,
 	};
 	int ret;
@@ -1080,13 +1081,13 @@ static int _test_cmd_veventq_alloc(int fd, __u32 viommu_id, __u32 type,
 	return 0;
 }
 
-#define test_cmd_veventq_alloc(viommu_id, type, veventq_id, veventq_fd) \
-	ASSERT_EQ(0, _test_cmd_veventq_alloc(self->fd, viommu_id, type, \
+#define test_cmd_veventq_alloc(viommu_id, type, depth, veventq_id, veventq_fd) \
+	ASSERT_EQ(0, _test_cmd_veventq_alloc(self->fd, viommu_id, type, depth, \
 					     veventq_id, veventq_fd))
-#define test_err_veventq_alloc(_errno, viommu_id, type, veventq_id,     \
-			       veventq_fd)                              \
-	EXPECT_ERRNO(_errno,                                            \
-		     _test_cmd_veventq_alloc(self->fd, viommu_id, type, \
+#define test_err_veventq_alloc(_errno, viommu_id, type, depth, veventq_id,     \
+			       veventq_fd)                                     \
+	EXPECT_ERRNO(_errno,                                                   \
+		     _test_cmd_veventq_alloc(self->fd, viommu_id, type, depth, \
 					     veventq_id, veventq_fd))
 
 static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents)