Merge v7.1.4linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 44 insertions, 20 deletions

diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
index 8b0ca7a09064..8a2f1b0cce3f 100644
--- a/drivers/vfio/debugfs.c
+++ b/drivers/vfio/debugfs.c
@@ -97,6 +97,7 @@ void vfio_device_debugfs_init(struct vfio_device *vdev)
 void vfio_device_debugfs_exit(struct vfio_device *vdev)
 {
 	debugfs_remove_recursive(vdev->debug_root);
+	vdev->debug_root = NULL;
 }
 
 void vfio_debugfs_create_root(void)
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index deed0f132f39..c86d8b243a52 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -158,26 +158,29 @@ struct mlx5_vhca_qp {
 struct mlx5_vhca_page_tracker {
 	u32 id;
 	u32 pdn;
-	u8 is_err:1;
-	u8 object_changed:1;
+	/* Flags modified at runtime - dedicated storage unit */
+	u8 is_err;
+	u8 object_changed;
+	int status;
 	struct mlx5_uars_page *uar;
 	struct mlx5_vhca_cq cq;
 	struct mlx5_vhca_qp *host_qp;
 	struct mlx5_vhca_qp *fw_qp;
 	struct mlx5_nb nb;
-	int status;
 };
 
 struct mlx5vf_pci_core_device {
 	struct vfio_pci_core_device core_device;
 	int vf_id;
 	u16 vhca_id;
+	/* Flags only modified on setup/release - bitfield ok */
 	u8 migrate_cap:1;
-	u8 deferred_reset:1;
-	u8 mdev_detach:1;
-	u8 log_active:1;
 	u8 chunk_mode:1;
 	u8 mig_state_cap:1;
+	/* Flags modified at runtime - dedicated storage unit */
+	u8 mdev_detach;
+	u8 log_active;
+	u8 deferred_reset;
 	struct completion tracker_comp;
 	/* protect migration state */
 	struct mutex state_mutex;
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 050e7542952e..beb1674c6945 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -271,8 +271,11 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat
 	int ret;
 
 	/* Prevent changing power state for PFs with VFs enabled */
-	if (pci_num_vf(pdev) && state > PCI_D0)
-		return -EBUSY;
+	if (state > PCI_D0) {
+		lockdep_assert_held_write(&vdev->memory_lock);
+		if (vdev->sriov_active)
+			return -EBUSY;
+	}
 
 	if (vdev->needs_pm_restore) {
 		if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) {
@@ -535,7 +538,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
 	u16 cmd;
 	u8 msix_pos;
 
-	if (!disable_idle_d3) {
+	if (!vdev->disable_idle_d3) {
 		ret = pm_runtime_resume_and_get(&pdev->dev);
 		if (ret < 0)
 			return ret;
@@ -614,7 +617,7 @@ out_free_state:
 out_disable_device:
 	pci_disable_device(pdev);
 out_power:
-	if (!disable_idle_d3)
+	if (!vdev->disable_idle_d3)
 		pm_runtime_put(&pdev->dev);
 	return ret;
 }
@@ -750,7 +753,7 @@ out:
 	vfio_pci_dev_set_try_reset(vdev->vdev.dev_set);
 
 	/* Put the pm-runtime usage counter acquired during enable */
-	if (!disable_idle_d3)
+	if (!vdev->disable_idle_d3)
 		pm_runtime_put(&pdev->dev);
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_disable);
@@ -2142,6 +2145,8 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev)
 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);
 
+	vdev->disable_idle_d3 = disable_idle_d3;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_init_dev);
@@ -2237,7 +2242,7 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 
 	dev->driver->pm = &vfio_pci_core_pm_ops;
 	pm_runtime_allow(dev);
-	if (!disable_idle_d3)
+	if (!vdev->disable_idle_d3)
 		pm_runtime_put(dev);
 
 	ret = vfio_register_group_dev(&vdev->vdev);
@@ -2246,10 +2251,11 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 	return 0;
 
 out_power:
-	if (!disable_idle_d3)
+	if (!vdev->disable_idle_d3)
 		pm_runtime_get_noresume(dev);
 
 	pm_runtime_forbid(dev);
+	vfio_pci_vga_uninit(vdev);
 out_vf:
 	vfio_pci_vf_uninit(vdev);
 	return ret;
@@ -2265,7 +2271,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev)
 	vfio_pci_vf_uninit(vdev);
 	vfio_pci_vga_uninit(vdev);
 
-	if (!disable_idle_d3)
+	if (!vdev->disable_idle_d3)
 		pm_runtime_get_noresume(&vdev->pdev->dev);
 
 	pm_runtime_forbid(&vdev->pdev->dev);
@@ -2327,8 +2333,9 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
 
 		down_write(&vdev->memory_lock);
 		vfio_pci_set_power_state(vdev, PCI_D0);
-		ret = pci_enable_sriov(pdev, nr_virtfn);
+		vdev->sriov_active = true;
 		up_write(&vdev->memory_lock);
+		ret = pci_enable_sriov(pdev, nr_virtfn);
 		if (ret) {
 			pm_runtime_put(&pdev->dev);
 			goto out_del;
@@ -2342,6 +2349,13 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
 	}
 
 out_del:
+	/*
+	 * Avoid taking the memory_lock intentionally. A race with a power
+	 * state transition would at most result in an -EBUSY, leaving the
+	 * device in PCI_D0.
+	 */
+	vdev->sriov_active = false;
+
 	mutex_lock(&vfio_pci_sriov_pfs_mutex);
 	list_del_init(&vdev->sriov_pfs_item);
 out_unlock:
@@ -2589,7 +2603,7 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
 	 * state. Increment the usage count for all the devices in the dev_set
 	 * before reset and decrement the same after reset.
 	 */
-	if (!disable_idle_d3 && vfio_pci_dev_set_pm_runtime_get(dev_set))
+	if (vfio_pci_dev_set_pm_runtime_get(dev_set))
 		return;
 
 	if (!pci_reset_bus(pdev))
@@ -2599,8 +2613,7 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
 		if (reset_done)
 			cur->needs_reset = false;
 
-		if (!disable_idle_d3)
-			pm_runtime_put(&cur->pdev->dev);
+		pm_runtime_put(&cur->pdev->dev);
 	}
 }
 
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 6222376ab6ab..ed538aebb0b8 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -407,6 +407,13 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 	vfio_device_group_unregister(device);
 
 	/*
+	 * Remove debugfs before device_del(), which releases devres.  Some
+	 * debugfs entries are created with debugfs_create_devm_seqfile() and
+	 * therefore rely on devres-managed inode private data.
+	 */
+	vfio_device_debugfs_exit(device);
+
+	/*
 	 * Balances vfio_device_add() in register path, also prevents
 	 * new device opened by userspace in the cdev path.
 	 */
@@ -435,7 +442,6 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
-	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -858,7 +864,8 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 	 * logical state, as per the above comment.
 	 */
 	*next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm];
-	while ((state_flags_table[*next_fsm] & device->migration_flags) !=
+	while (*next_fsm != VFIO_DEVICE_STATE_ERROR &&
+	       (state_flags_table[*next_fsm] & device->migration_flags) !=
 			state_flags_table[*next_fsm])
 		*next_fsm = vfio_from_fsm_table[*next_fsm][new_fsm];