[PATCH v4 09/10] drivers: qcom: rpmh: add support for batch RPMH request

[Lina Iyer]

Platform drivers need make a lot of resource state requests at the same
time, say, at the start or end of an usecase. It can be quite
inefficient to send each request separately. Instead they can give the
RPMH library a batch of requests to be sent and wait on the whole
transaction to be complete.

rpmh_write_batch() is a blocking call that can be used to send multiple
RPMH command sets. Each RPMH command set is set asynchronously and the
API blocks until all the command sets are complete and receive their
tx_done callbacks.

Signed-off-by: Lina Iyer <ilina@xxxxxxxxxxxxxx>
---

Changes in v4:
	- reorganize rpmh_write_batch()
	- introduce wait_count here, instead of patch#4
---
 drivers/soc/qcom/rpmh.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++-
 include/soc/qcom/rpmh.h |   8 +++
 2 files changed, 162 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index 3a96e5f58302..daadbb3f0494 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -23,6 +23,7 @@
 
 #define RPMH_MAX_MBOXES			2
 #define RPMH_TIMEOUT_MS			10000
+#define RPMH_MAX_REQ_IN_BATCH		10
 
 #define DEFINE_RPMH_MSG_ONSTACK(rc, s, q, name)		\
 	struct rpmh_request name = {			\
@@ -36,6 +37,7 @@
 		.completion = q,			\
 		.rc = rc,				\
 		.free = NULL,				\
+		.wait_count = NULL,			\
 	}
 
 /**
@@ -61,6 +63,7 @@ struct cache_req {
  * @completion: triggered when request is done
  * @err: err return from the controller
  * @free: the request object to be freed at tx_done
+ * @wait_count: count of waiters for this completion
  */
 struct rpmh_request {
 	struct tcs_request msg;
@@ -69,6 +72,7 @@ struct rpmh_request {
 	struct rpmh_client *rc;
 	int err;
 	struct rpmh_request *free;
+	atomic_t *wait_count;
 };
 
 /**
@@ -78,12 +82,14 @@ struct rpmh_request {
  * @cache: the list of cached requests
  * @lock: synchronize access to the controller data
  * @dirty: was the cache updated since flush
+ * @batch_cache: Cache sleep and wake requests sent as batch
  */
 struct rpmh_ctrlr {
 	struct rsc_drv *drv;
 	struct list_head cache;
 	spinlock_t lock;
 	bool dirty;
+	const struct rpmh_request *batch_cache[2 * RPMH_MAX_REQ_IN_BATCH];
 };
 
 /**
@@ -105,6 +111,7 @@ void rpmh_tx_done(const struct tcs_request *msg, int r)
 	struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request,
 						    msg);
 	struct completion *compl = rpm_msg->completion;
+	atomic_t *wc = rpm_msg->wait_count;
 
 	rpm_msg->err = r;
 
@@ -116,8 +123,13 @@ void rpmh_tx_done(const struct tcs_request *msg, int r)
 	kfree(rpm_msg->free);
 
 	/* Signal the blocking thread we are done */
-	if (compl)
-		complete(compl);
+	if (!compl)
+		return;
+
+	if (wc && !atomic_dec_and_test(wc))
+		return;
+
+	complete(compl);
 }
 EXPORT_SYMBOL(rpmh_tx_done);
 
@@ -339,6 +351,139 @@ int rpmh_write(struct rpmh_client *rc, enum rpmh_state state,
 }
 EXPORT_SYMBOL(rpmh_write);
 
+static int cache_batch(struct rpmh_client *rc,
+		       struct rpmh_request **rpm_msg, int count)
+{
+	struct rpmh_ctrlr *rpm = rc->ctrlr;
+	unsigned long flags;
+	int ret = 0;
+	int index = 0;
+	int i;
+
+	spin_lock_irqsave(&rpm->lock, flags);
+	while (rpm->batch_cache[index])
+		index++;
+	if (index + count >=  2 * RPMH_MAX_REQ_IN_BATCH) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	for (i = 0; i < count; i++)
+		rpm->batch_cache[index + i] = rpm_msg[i];
+fail:
+	spin_unlock_irqrestore(&rpm->lock, flags);
+
+	return ret;
+}
+
+static int flush_batch(struct rpmh_client *rc)
+{
+	struct rpmh_ctrlr *rpm = rc->ctrlr;
+	const struct rpmh_request *rpm_msg;
+	unsigned long flags;
+	int ret = 0;
+	int i;
+
+	/* Send Sleep/Wake requests to the controller, expect no response */
+	spin_lock_irqsave(&rpm->lock, flags);
+	for (i = 0; rpm->batch_cache[i]; i++) {
+		rpm_msg = rpm->batch_cache[i];
+		ret = rpmh_rsc_write_ctrl_data(rc->ctrlr->drv, &rpm_msg->msg);
+		if (ret)
+			break;
+	}
+	spin_unlock_irqrestore(&rpm->lock, flags);
+
+	return ret;
+}
+
+static void invalidate_batch(struct rpmh_client *rc)
+{
+	struct rpmh_ctrlr *rpm = rc->ctrlr;
+	unsigned long flags;
+	int index = 0;
+	int i;
+
+	spin_lock_irqsave(&rpm->lock, flags);
+	while (rpm->batch_cache[index])
+		index++;
+	for (i = 0; i < index; i++) {
+		kfree(rpm->batch_cache[i]->free);
+		rpm->batch_cache[i] = NULL;
+	}
+	spin_unlock_irqrestore(&rpm->lock, flags);
+}
+
+/**
+ * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
+ * batch to finish.
+ *
+ * @rc: The RPMh handle got from rpmh_get_client
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The array of count of elements in each batch, 0 terminated.
+ *
+ * Write a request to the mailbox controller without caching. If the request
+ * state is ACTIVE, then the requests are treated as completion request
+ * and sent to the controller immediately. The function waits until all the
+ * commands are complete. If the request was to SLEEP or WAKE_ONLY, then the
+ * request is sent as fire-n-forget and no ack is expected.
+ *
+ * May sleep. Do not call from atomic contexts for ACTIVE_ONLY requests.
+ */
+int rpmh_write_batch(struct rpmh_client *rc, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n)
+{
+	struct rpmh_request *rpm_msg[RPMH_MAX_REQ_IN_BATCH] = { NULL };
+	DECLARE_COMPLETION_ONSTACK(compl);
+	atomic_t wait_count = ATOMIC_INIT(0);
+	int count = 0;
+	int ret, i;
+
+	if (IS_ERR_OR_NULL(rc) || !cmd || !n)
+		return -EINVAL;
+
+	while (n[count++] > 0)
+		;
+	count--;
+	if (!count || count > RPMH_MAX_REQ_IN_BATCH)
+		return -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		rpm_msg[i] = __get_rpmh_msg_async(rc, state, cmd, n[i]);
+		if (IS_ERR_OR_NULL(rpm_msg[i])) {
+			ret = PTR_ERR(rpm_msg[i]);
+			for (; i >= 0; i--)
+				kfree(rpm_msg[i]->free);
+			return ret;
+		}
+		cmd += n[i];
+	}
+
+	if (state != RPMH_ACTIVE_ONLY_STATE)
+		return cache_batch(rc, rpm_msg, count);
+
+	atomic_set(&wait_count, count);
+
+	for (i = 0; i < count; i++) {
+		rpm_msg[i]->completion = &compl;
+		rpm_msg[i]->wait_count = &wait_count;
+		ret = rpmh_rsc_send_data(rc->ctrlr->drv, &rpm_msg[i]->msg);
+		if (ret) {
+			int j;
+
+			pr_err("Error(%d) sending RPMH message addr=%#x\n",
+			       ret, rpm_msg[i]->msg.cmds[0].addr);
+			for (j = i; j < count; j++)
+				rpmh_tx_done(&rpm_msg[j]->msg, ret);
+			break;
+		}
+	}
+
+	return wait_for_tx_done(rc, &compl, cmd[0].addr, cmd[0].data);
+}
+EXPORT_SYMBOL(rpmh_write_batch);
+
 static int is_req_valid(struct cache_req *req)
 {
 	return (req->sleep_val != UINT_MAX &&
@@ -386,6 +531,11 @@ int rpmh_flush(struct rpmh_client *rc)
 		return 0;
 	}
 
+	/* First flush the cached batch requests */
+	ret = flush_batch(rc);
+	if (ret)
+		return ret;
+
 	/*
 	 * Nobody else should be calling this function other than system PM,,
 	 * hence we can run without locks.
@@ -427,6 +577,8 @@ int rpmh_invalidate(struct rpmh_client *rc)
 	if (IS_ERR_OR_NULL(rc))
 		return -EINVAL;
 
+	invalidate_batch(rc);
+
 	rpm->dirty = true;
 
 	do {
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
index 9e6de09e43f0..a5d5c57a4329 100644
--- a/include/soc/qcom/rpmh.h
+++ b/include/soc/qcom/rpmh.h
@@ -18,6 +18,9 @@ int rpmh_write(struct rpmh_client *rc, enum rpmh_state state,
 int rpmh_write_async(struct rpmh_client *rc, enum rpmh_state state,
 		     const struct tcs_cmd *cmd, u32 n);
 
+int rpmh_write_batch(struct rpmh_client *rc, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n);
+
 struct rpmh_client *rpmh_get_client(struct platform_device *pdev);
 
 int rpmh_flush(struct rpmh_client *rc);
@@ -40,6 +43,11 @@ static inline int rpmh_write_async(struct rpmh_client *rc,
 				   const struct tcs_cmd *cmd, u32 n)
 { return -ENODEV; }
 
+static inline int rpmh_write_batch(struct rpmh_client *rc,
+				   enum rpmh_state state,
+				   const struct tcs_cmd *cmd, u32 *n)
+{ return -ENODEV; }
+
 static inline int rpmh_flush(struct rpmh_client *rc)
 { return -ENODEV; }
 
-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project