soc: qcom: rpmh: Remove serialization of TCS commands

Requests sent to RPMH can be sent as fire-n-forget or response required,
with the latter ensuring the command has been completed by the hardware
accelerator. Commands in a request with tcs_cmd::wait set, would ensure
that those select commands are sent as response required, even though
the actual TCS request may be fire-n-forget.

Also, commands with .wait flag were also guaranteed to be complete
before the following command in the TCS is sent. This means that the
next command of the same request blocked until the current request is
completed. This could mean waiting for a voltage to settle or series of
NOCs be configured before the next command is sent. But drivers using
this feature have never cared about the serialization aspect. By not
enforcing the serialization we can allow the hardware to run in parallel
improving the performance.

Let's clarify the usage of this member in the tcs_cmd structure to mean
only completion and not serialization. This should also improve the
performance of bus requests where changes could happen in parallel.
Also, CPU resume from deep idle may see benefits from certain wake
requests.

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Maulik Shah <mkshah@codeaurora.org>
Link: https://lore.kernel.org/r/1610008770-13891-1-git-send-email-mkshah@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>

1 files changed, 9 insertions, 13 deletions

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 0b082ec894a1..a84ab0d6a9d4 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -231,10 +231,9 @@ static void tcs_invalidate(struct rsc_drv *drv, int type)
 	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS))
 		return;
 
-	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
+	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++)
 		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0);
-		write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, m, 0);
-	}
+
 	bitmap_zero(tcs->slots, MAX_TCS_SLOTS);
 }
 
@@ -443,7 +442,6 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 skip:
 		/* Reclaim the TCS */
 		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
-		write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, i, 0);
 		writel_relaxed(BIT(i), drv->tcs_base + RSC_DRV_IRQ_CLEAR);
 		spin_lock(&drv->lock);
 		clear_bit(i, drv->tcs_in_use);
@@ -476,23 +474,23 @@ skip:
 static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 			       const struct tcs_request *msg)
 {
-	u32 msgid, cmd_msgid;
+	u32 msgid;
+	u32 cmd_msgid = CMD_MSGID_LEN | CMD_MSGID_WRITE;
 	u32 cmd_enable = 0;
-	u32 cmd_complete;
 	struct tcs_cmd *cmd;
 	int i, j;
 
-	cmd_msgid = CMD_MSGID_LEN;
+	/* Convert all commands to RR when the request has wait_for_compl set */
 	cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0;
-	cmd_msgid |= CMD_MSGID_WRITE;
-
-	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id);
 
 	for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) {
 		cmd = &msg->cmds[i];
 		cmd_enable |= BIT(j);
-		cmd_complete |= cmd->wait << j;
 		msgid = cmd_msgid;
+		/*
+		 * Additionally, if the cmd->wait is set, make the command
+		 * response reqd even if the overall request was fire-n-forget.
+		 */
 		msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0;
 
 		write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid);
@@ -501,7 +499,6 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 		trace_rpmh_send_msg(drv, tcs_id, j, msgid, cmd);
 	}
 
-	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
 	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id);
 	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
 }
@@ -652,7 +649,6 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
 		 * cleaned from rpmh_flush() by invoking rpmh_rsc_invalidate()
 		 */
 		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
-		write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
 		enable_tcs_irq(drv, tcs_id, true);
 	}
 	spin_unlock_irqrestore(&drv->lock, flags);