Re: [PATCH v6 11/16] remoteproc: Properly deal with the resource table when attached

[Arnaud POULIQUEN]

On 2/24/21 12:35 AM, Mathieu Poirier wrote:
> If it is possible to detach the remote processor, keep an untouched
> copy of the resource table.  That way we can start from the same
> resource table without having to worry about original values or what
> elements the startup code has changed when re-attaching to the remote
> processor.
> 
> Signed-off-by: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
> ---
> New for V6:
> - Double free of the cached table has been fixed.
> - rproc_reset_loaded_rsc_table() has seen a complete re-write.
> - rproc_stop() now calls rproc_reset_loaded_rsc_table() rather than
>   dealing with the cached.  This allows to properly shutdown a
>   remote processor that was attached to.
> ---
> 
>  drivers/remoteproc/remoteproc_core.c | 86 +++++++++++++++++++++++++++-
>  include/linux/remoteproc.h           |  3 +
>  2 files changed, 88 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
> index fc01b29290a6..3a4692cc5220 100644
> --- a/drivers/remoteproc/remoteproc_core.c
> +++ b/drivers/remoteproc/remoteproc_core.c
> @@ -1556,6 +1556,21 @@ static int rproc_set_loaded_rsc_table(struct rproc *rproc)
>  		return ret;
>  	}
>  
> +	/*
> +	 * If it is possible to detach the remote processor, keep an untouched
> +	 * copy of the resource table.  That way we can start fresh again when
> +	 * the remote processor is re-attached, that is:
> +	 *
> +	 *      DETACHED -> ATTACHED -> DETACHED -> ATTACHED
> +	 *
> +	 * Free'd in rproc_reset_loaded_rsc_table().
> +	 */
> +	if (rproc->ops->detach) {
> +		rproc->clean_table = kmemdup(table_ptr, table_sz, GFP_KERNEL);
> +		if (!rproc->clean_table)
> +			return -ENOMEM;
> +	}
> +
>  	rproc->cached_table = NULL;
>  	rproc->table_ptr = table_ptr;
>  	rproc->table_sz = table_sz;
> @@ -1563,6 +1578,65 @@ static int rproc_set_loaded_rsc_table(struct rproc *rproc)
>  	return 0;
>  }
>  
> +static int rproc_reset_loaded_rsc_table(struct rproc *rproc)

I spent some time to review this function that handles both the resource table
for both the stop and detach. To make it easier to read, I would divide it into
two functions.
I added a proposal at the end of this mail.

Regards,
Arnaud

> +{
> +	struct resource_table *table_ptr;
> +
> +	/*
> +	 * The cached table is already set if the remote processor was started
> +	 * by the remoteproc core.
> +	 */
> +	if (rproc->state == RPROC_RUNNING) {
> +		rproc->table_ptr = rproc->cached_table;
> +		return 0;
> +	}
> +
> +	/* A resource table was never retrieved, nothing to do here */
> +	if (!rproc->table_ptr)
> +		return 0;
> +
> +	/*
> +	 * If we made it to this point a cached_table _must_ have been
> +	 * allocated in rproc_set_loaded_rsc_table().  If one isn't present
> +	 * something went really wrong and we must complain.
> +	 */
> +	if (WARN_ON(!rproc->clean_table))
> +		return -EINVAL;
> +
> +	/* Remember where the external entity installed the resource table */
> +	table_ptr = rproc->table_ptr;
> +
> +	/*
> +	 * Make a copy of the resource table currently used by the remote
> +	 * processor.  Free'd in rproc_detach() or rproc_shutdown().
> +	 */
> +	rproc->cached_table = kmemdup(rproc->table_ptr,
> +				      rproc->table_sz, GFP_KERNEL);
> +	if (!rproc->cached_table)
> +		return -ENOMEM;
> +
> +	/*
> +	 * Use a copy of the resource table for the remainder of the
> +	 * shutdown process.
> +	 */
> +	rproc->table_ptr = rproc->cached_table;
> +
> +	/*
> +	 * Reset the memory area where the firmware loaded the resource table
> +	 * to its original value.  That way when we re-attach the remote
> +	 * processor the resource table is clean and ready to be used again.
> +	 */
> +	memcpy(table_ptr, rproc->clean_table, rproc->table_sz);
> +
> +	/*
> +	 * The clean resource table is no longer needed.  Allocated in
> +	 * rproc_set_loaded_rsc_table().
> +	 */
> +	kfree(rproc->clean_table);
> +
> +	return 0;
> +}
> +
>  /*
>   * Attach to remote processor - similar to rproc_fw_boot() but without
>   * the steps that deal with the firmware image.
> @@ -1688,7 +1762,11 @@ static int rproc_stop(struct rproc *rproc, bool crashed)
>  	rproc_stop_subdevices(rproc, crashed);
>  
>  	/* the installed resource table is no longer accessible */
> -	rproc->table_ptr = rproc->cached_table;
> +	ret = rproc_reset_loaded_rsc_table(rproc);
> +	if (ret) {
> +		dev_err(dev, "can't reset resource table: %d\n", ret);
> +		return ret;
> +	}
>  
>  	/* power off the remote processor */
>  	ret = rproc->ops->stop(rproc);
> @@ -1721,6 +1799,9 @@ static int __rproc_detach(struct rproc *rproc)
>  	/* Stop any subdevices for the remote processor */
>  	rproc_stop_subdevices(rproc, false);
>  
> +	/* the installed resource table is no longer accessible */
> +	ret = rproc_reset_loaded_rsc_table(rproc);
> +
>  	/* Tell the remote processor the core isn't available anymore */
>  	ret = rproc->ops->detach(rproc);
>  	if (ret) {
> @@ -1997,6 +2078,9 @@ int rproc_detach(struct rproc *rproc)
>  
>  	rproc_disable_iommu(rproc);
>  
> +	/* Free the copy of the resource table */
> +	kfree(rproc->cached_table);
> +	rproc->cached_table = NULL;
>  	rproc->table_ptr = NULL;
>  out:
>  	mutex_unlock(&rproc->lock);
> diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
> index e1c843c19cc6..e5f52a12a650 100644
> --- a/include/linux/remoteproc.h
> +++ b/include/linux/remoteproc.h
> @@ -514,6 +514,8 @@ struct rproc_dump_segment {
>   * @recovery_disabled: flag that state if recovery was disabled
>   * @max_notifyid: largest allocated notify id.
>   * @table_ptr: pointer to the resource table in effect
> + * @clean_table: copy of the resource table without modifications.  Used
> + *		 when a remote processor is attached or detached from the core
>   * @cached_table: copy of the resource table
>   * @table_sz: size of @cached_table
>   * @has_iommu: flag to indicate if remote processor is behind an MMU
> @@ -550,6 +552,7 @@ struct rproc {
>  	bool recovery_disabled;
>  	int max_notifyid;
>  	struct resource_table *table_ptr;
> +	struct resource_table *clean_table;
>  	struct resource_table *cached_table;
>  	size_t table_sz;
>  	bool has_iommu;
> 


---
 drivers/remoteproc/remoteproc_core.c | 101 ++++++++++++++++++++++++++-
 include/linux/remoteproc.h           |   3 +
 2 files changed, 103 insertions(+), 1 deletion(-)

diff --git a/drivers/remoteproc/remoteproc_core.c
b/drivers/remoteproc/remoteproc_core.c
index fc01b29290a6..cc24c360eb8b 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1556,6 +1556,21 @@ static int rproc_set_loaded_rsc_table(struct rproc *rproc)
 		return ret;
 	}

+	/*
+	 * If it is possible to detach the remote processor, keep an untouched
+	 * copy of the resource table.  That way we can start fresh again when
+	 * the remote processor is re-attached, that is:
+	 *
+	 *      DETACHED -> ATTACHED -> DETACHED -> ATTACHED
+	 *
+	 * Free'd in rproc_reset_loaded_rsc_table().
+	 */
+	if (rproc->ops->detach) {
+		rproc->clean_table = kmemdup(table_ptr, table_sz, GFP_KERNEL);
+		if (!rproc->clean_table)
+			return -ENOMEM;
+	}
+
 	rproc->cached_table = NULL;
 	rproc->table_ptr = table_ptr;
 	rproc->table_sz = table_sz;
@@ -1563,6 +1578,79 @@ static int rproc_set_loaded_rsc_table(struct rproc *rproc)
 	return 0;
 }

+static int rproc_set_to_cached_rsc_table(struct rproc *rproc)
+{
+	/* A resource table was never retrieved, nothing to do here */
+	if (!rproc->table_ptr)
+		return 0;
+
+	/*
+	 * The cached table is already set if the remote processor was started
+	 * by the remoteproc core.
+	 */
+	if (!rproc->cached_table) {
+		rproc->table_ptr = rproc->cached_table;
+		return 0;
+	}
+
+	/*
+	 * Make a copy of the resource table currently used by the remote
+	 * processor.  Free'd in rproc_detach() or rproc_shutdown().
+	 */
+	rproc->cached_table = kmemdup(rproc->table_ptr,
+				      rproc->table_sz, GFP_KERNEL);
+	if (!rproc->cached_table)
+		return -ENOMEM;
+
+	/*
+	 * Use a copy of the resource table for the remainder of the
+	 * shutdown process.
+	 */
+	rproc->table_ptr = rproc->cached_table;
+
+	return 0;
+}
+
+static int rproc_reset_loaded_rsc_table(struct rproc *rproc)
+{
+	struct resource_table *table_ptr;
+	int ret;
+
+	/* A resource table was never retrieved, nothing to do here */
+	if (!rproc->table_ptr)
+		return 0;
+
+	/*
+	 * If we made it to this point a cached_table _mst_ have been
+	 * allocated in rproc_set_loaded_rsc_table().  If one isn't present
+	 * something went really wrong and we must complain.
+	 */
+	if (WARN_ON(!rproc->clean_table))
+		return -EINVAL;
+
+	/* Remember where the external entity installed the resource table */
+	table_ptr = rproc->table_ptr;
+
+	ret = rproc_set_to_cached_rsc_table(rproc);
+	if (ret)
+		return ret;
+
+	/*
+	 * Reset the memory area where the firmware loaded the resource table
+	 * to its original value.  That way when we re-attach the remote
+	 * processor the resource table is clean and ready to be used again.
+	 */
+	memcpy(table_ptr, rproc->clean_table, rproc->table_sz);
+
+	/*
+	 * The clean resource table is no longer needed.  Allocated in
+	 * rproc_set_loaded_rsc_table().
+	 */
+	kfree(rproc->clean_table);
+
+	return 0;
+}
+
 /*
  * Attach to remote processor - similar to rproc_fw_boot() but without
  * the steps that deal with the firmware image.
@@ -1688,7 +1776,11 @@ static int rproc_stop(struct rproc *rproc, bool crashed)
 	rproc_stop_subdevices(rproc, crashed);

 	/* the installed resource table is no longer accessible */
-	rproc->table_ptr = rproc->cached_table;
+	ret = rproc_set_to_cached_rsc_table(rproc);
+	if (ret) {
+		dev_err(dev, "can't reset resource table: %d\n", ret);
+		return ret;
+	}

 	/* power off the remote processor */
 	ret = rproc->ops->stop(rproc);
@@ -1721,6 +1813,9 @@ static int __rproc_detach(struct rproc *rproc)
 	/* Stop any subdevices for the remote processor */
 	rproc_stop_subdevices(rproc, false);

+	/* The installed resource table need to be reset and no longer accessible */
+	ret = rproc_reset_loaded_rsc_table(rproc);
+
 	/* Tell the remote processor the core isn't available anymore */
 	ret = rproc->ops->detach(rproc);
 	if (ret) {
@@ -1941,6 +2036,7 @@ void rproc_shutdown(struct rproc *rproc)

 	/* Free the copy of the resource table */
 	kfree(rproc->cached_table);
+	kfree(rproc->clean_table);
 	rproc->cached_table = NULL;
 	rproc->table_ptr = NULL;
 out:
@@ -1997,6 +2093,9 @@ int rproc_detach(struct rproc *rproc)

 	rproc_disable_iommu(rproc);

+	/* Free the copy of the resource table */
+	kfree(rproc->cached_table);
+	rproc->cached_table = NULL;
 	rproc->table_ptr = NULL;
 out:
 	mutex_unlock(&rproc->lock);
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index e1c843c19cc6..e5f52a12a650 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -514,6 +514,8 @@ struct rproc_dump_segment {
  * @recovery_disabled: flag that state if recovery was disabled
  * @max_notifyid: largest allocated notify id.
  * @table_ptr: pointer to the resource table in effect
+ * @clean_table: copy of the resource table without modifications.  Used
+ *		 when a remote processor is attached or detached from the core
  * @cached_table: copy of the resource table
  * @table_sz: size of @cached_table
  * @has_iommu: flag to indicate if remote processor is behind an MMU
@@ -550,6 +552,7 @@ struct rproc {
 	bool recovery_disabled;
 	int max_notifyid;
 	struct resource_table *table_ptr;
+	struct resource_table *clean_table;
 	struct resource_table *cached_table;
 	size_t table_sz;
 	bool has_iommu;
--