IB/hfi1: Fix an Oops on pci device force remove

This patch fixes an Oops on device unbind, when the device is used
by a PSM user process. PSM processes access device resources which
are freed on device removal. Similar protection exists in uverbs
in ib_core for Verbs clients, but PSM doesn't use ib_uverbs hence
a separate protection is required for PSM clients.

Cc: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dean Luick <dean.luick@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/chip.c

@@ -14691,6 +14691,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret)
 		goto bail_free_cntrs;
 
+	init_completion(&dd->user_comp);
+
+	/* The user refcount starts with one to inidicate an active device */
+	atomic_set(&dd->user_refcount, 1);
+
 	goto bail;
 
 bail_free_rcverr:

drivers/infiniband/hw/hfi1/file_ops.c

@@ -172,6 +172,9 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 					       struct hfi1_devdata,
 					       user_cdev);
 
+	if (!atomic_inc_not_zero(&dd->user_refcount))
+		return -ENXIO;
+
 	/* Just take a ref now. Not all opens result in a context assign */
 	kobject_get(&dd->kobj);
 
@@ -183,11 +186,17 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 		fd->rec_cpu_num = -1; /* no cpu affinity by default */
 		fd->mm = current->mm;
 		atomic_inc(&fd->mm->mm_count);
-	}
+		fp->private_data = fd;
+	} else {
+		fp->private_data = NULL;
+
+		if (atomic_dec_and_test(&dd->user_refcount))
+			complete(&dd->user_comp);
 
-	fp->private_data = fd;
+		return -ENOMEM;
+	}
 
-	return fd ? 0 : -ENOMEM;
+	return 0;
 }
 
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -798,6 +807,10 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 done:
 	mmdrop(fdata->mm);
 	kobject_put(&dd->kobj);
+
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
 	kfree(fdata);
 	return 0;
 }

drivers/infiniband/hw/hfi1/hfi.h

@@ -1174,6 +1174,10 @@ struct hfi1_devdata {
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
 	atomic_t aspm_disabled_cnt;
+	/* Keeps track of user space clients */
+	atomic_t user_refcount;
+	/* Used to wait for outstanding user space clients before dev removal */
+	struct completion user_comp;
 
 	struct hfi1_affinity *affinity;
 	struct rhashtable sdma_rht;

drivers/infiniband/hw/hfi1/init.c

@@ -1538,12 +1538,31 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return ret;
 }
 
+static void wait_for_clients(struct hfi1_devdata *dd)
+{
+	/*
+	 * Remove the device init value and complete the device if there is
+	 * no clients or wait for active clients to finish.
+	 */
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
+	wait_for_completion(&dd->user_comp);
+}
+
 static void remove_one(struct pci_dev *pdev)
 {
 	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
 
 	/* close debugfs files before ib unregister */
 	hfi1_dbg_ibdev_exit(&dd->verbs_dev);
+
+	/* remove the /dev hfi1 interface */
+	hfi1_device_remove(dd);
+
+	/* wait for existing user space clients to finish */
+	wait_for_clients(dd);
+
 	/* unregister from IB core */
 	hfi1_unregister_ib_device(dd);
 
@@ -1558,8 +1577,6 @@ static void remove_one(struct pci_dev *pdev)
 	/* wait until all of our (qsfp) queue_work() calls complete */
 	flush_workqueue(ib_wq);
 
-	hfi1_device_remove(dd);
-
 	postinit_cleanup(dd);
 }