cxl: Fix possible idr warning when contexts are released

An idr warning is reported when a context is release after the capi card
is unbound from the cxl driver via sysfs. Below are the steps to
reproduce:

1. Create multiple afu contexts in an user-space application using libcxl.
2. Unbind capi card from cxl using command of form
   echo <capi-card-pci-addr> > /sys/bus/pci/drivers/cxl-pci/unbind
3. Exit/kill the application owning afu contexts.

After above steps a warning message is usually seen in the kernel logs
of the form "idr_remove called for id=<context-id> which is not
allocated."

This is caused by the function cxl_release_afu which destroys the
contexts_idr table. So when a context is release no entry for context pe
is found in the contexts_idr table and idr code prints this warning.

This patch fixes this issue by increasing & decreasing the ref-count on
the afu device when a context is initialized or when its freed
respectively. This prevents the afu from being released until all the
afu contexts have been released. The patch introduces two new functions
namely cxl_afu_get/put that manage the ref-count on the afu device.

Also the patch removes code inside cxl_dev_context_init that increases ref
on the afu device as its guaranteed to be alive during this function.

Reported-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 32 insertions, 12 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 103baf0e0c5b..a6543aefa299 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -25,7 +25,6 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 
 	afu = cxl_pci_to_afu(dev);
 
-	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx)) {
 		rc = PTR_ERR(ctx);
@@ -61,7 +60,6 @@ err_mapping:
 err_ctx:
 	kfree(ctx);
 err_dev:
-	put_device(&afu->dev);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
@@ -87,8 +85,6 @@ int cxl_release_context(struct cxl_context *ctx)
 	if (ctx->status >= STARTED)
 		return -EBUSY;
 
-	put_device(&ctx->afu->dev);
-
 	cxl_context_free(ctx);
 
 	return 0;
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 2faa1270d085..6dde7a9d6a7e 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -97,6 +97,12 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	ctx->pe = i;
 	ctx->elem = &ctx->afu->spa[i];
 	ctx->pe_inserted = false;
+
+	/*
+	 * take a ref on the afu so that it stays alive at-least till
+	 * this context is reclaimed inside reclaim_ctx.
+	 */
+	cxl_afu_get(afu);
 	return 0;
 }
 
@@ -278,6 +284,9 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	if (ctx->irq_bitmap)
 		kfree(ctx->irq_bitmap);
 
+	/* Drop ref to the afu device taken during cxl_context_init */
+	cxl_afu_put(ctx->afu);
+
 	kfree(ctx);
 }
 
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 0cfb9c129f27..25ae57fa79b0 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -403,6 +403,18 @@ struct cxl_afu {
 	bool enabled;
 };
 
+/* AFU refcount management */
+static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu)
+{
+
+	return (get_device(&afu->dev) == NULL) ? NULL : afu;
+}
+
+static inline void  cxl_afu_put(struct cxl_afu *afu)
+{
+	put_device(&afu->dev);
+}
+
 
 struct cxl_irq_name {
 	struct list_head list;
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 7ccd2998be92..5cc14599837d 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -67,7 +67,13 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 		spin_unlock(&adapter->afu_list_lock);
 		goto err_put_adapter;
 	}
-	get_device(&afu->dev);
+
+	/*
+	 * taking a ref to the afu so that it doesn't go away
+	 * for rest of the function. This ref is released before
+	 * we return.
+	 */
+	cxl_afu_get(afu);
 	spin_unlock(&adapter->afu_list_lock);
 
 	if (!afu->current_mode)
@@ -90,13 +96,12 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 	file->private_data = ctx;
 	cxl_ctx_get();
 
-	/* Our ref on the AFU will now hold the adapter */
-	put_device(&adapter->dev);
-
-	return 0;
+	/* indicate success */
+	rc = 0;
 
 err_put_afu:
-	put_device(&afu->dev);
+	/* release the ref taken earlier */
+	cxl_afu_put(afu);
 err_put_adapter:
 	put_device(&adapter->dev);
 	return rc;
@@ -131,8 +136,6 @@ int afu_release(struct inode *inode, struct file *file)
 		mutex_unlock(&ctx->mapping_lock);
 	}
 
-	put_device(&ctx->afu->dev);
-
 	/*
 	 * At this this point all bottom halfs have finished and we should be
 	 * getting no more IRQs from the hardware for this context.  Once it's