spi: tegra210-quad: Check hardware status on timeout

Under high system load, QSPI interrupts can be delayed or blocked on the
target CPU, causing wait_for_completion_timeout() to report failure even
though the hardware successfully completed the transfer.

When a timeout occurs, check the QSPI_RDY bit in QSPI_TRANS_STATUS to
determine if the hardware actually completed the transfer. If so, manually
invoke the completion handler to process the transfer successfully instead
of failing it.

This distinguishes lost/delayed interrupts from real hardware timeouts,
preventing unnecessary failures of transfers that completed successfully.

Signed-off-by: Vishwaroop A <va@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20251028155703.4151791-4-va@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>

1 files changed, 80 insertions, 20 deletions

diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 69defb4ffe49..cdc3cb7c01f9 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -1048,6 +1048,49 @@ static void tegra_qspi_transfer_end(struct spi_device *spi)
 	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
 }
 
+static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi);
+static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi);
+
+/**
+ * tegra_qspi_handle_timeout - Handle transfer timeout with hardware check
+ * @tqspi: QSPI controller instance
+ *
+ * When a timeout occurs but hardware has completed the transfer (interrupt
+ * was lost or delayed), manually trigger transfer completion processing.
+ * This avoids failing transfers that actually succeeded.
+ *
+ * Returns: 0 if transfer was completed, -ETIMEDOUT if real timeout
+ */
+static int tegra_qspi_handle_timeout(struct tegra_qspi *tqspi)
+{
+	irqreturn_t ret;
+	u32 status;
+
+	/* Check if hardware actually completed the transfer */
+	status = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
+	if (!(status & QSPI_RDY))
+		return -ETIMEDOUT;
+
+	/*
+	 * Hardware completed but interrupt was lost/delayed. Manually
+	 * process the completion by calling the appropriate handler.
+	 */
+	dev_warn_ratelimited(tqspi->dev,
+			     "QSPI interrupt timeout, but transfer complete\n");
+
+	/* Clear the transfer status */
+	status = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
+	tegra_qspi_writel(tqspi, status, QSPI_TRANS_STATUS);
+
+	/* Manually trigger completion handler */
+	if (!tqspi->is_curr_dma_xfer)
+		ret = handle_cpu_based_xfer(tqspi);
+	else
+		ret = handle_dma_based_xfer(tqspi);
+
+	return (ret == IRQ_HANDLED) ? 0 : -EIO;
+}
+
 static u32 tegra_qspi_cmd_config(bool is_ddr, u8 bus_width, u8 len)
 {
 	u32 cmd_config = 0;
@@ -1177,20 +1220,28 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					QSPI_DMA_TIMEOUT);
 
 			if (WARN_ON_ONCE(ret == 0)) {
-				dev_err_ratelimited(tqspi->dev,
-						    "QSPI Transfer failed with timeout\n");
-
-				/* Abort transfer by resetting pio/dma bit */
-				if (tqspi->is_curr_dma_xfer)
-					tegra_qspi_dma_stop(tqspi);
-				else
-					tegra_qspi_pio_stop(tqspi);
-
-				/* Reset controller if timeout happens */
-				tegra_qspi_reset(tqspi);
-
-				ret = -EIO;
-				goto exit;
+				/*
+				 * Check if hardware completed the transfer
+				 * even though interrupt was lost or delayed.
+				 * If so, process the completion and continue.
+				 */
+				ret = tegra_qspi_handle_timeout(tqspi);
+				if (ret < 0) {
+					/* Real timeout - clean up and fail */
+					dev_err(tqspi->dev, "transfer timeout\n");
+
+					/* Abort transfer by resetting pio/dma bit */
+					if (tqspi->is_curr_dma_xfer)
+						tegra_qspi_dma_stop(tqspi);
+					else
+						tegra_qspi_pio_stop(tqspi);
+
+					/* Reset controller if timeout happens */
+					tegra_qspi_reset(tqspi);
+
+					ret = -EIO;
+					goto exit;
+				}
 			}
 
 			if (tqspi->tx_status ||  tqspi->rx_status) {
@@ -1281,14 +1332,23 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
 		ret = wait_for_completion_timeout(&tqspi->xfer_completion,
 						  QSPI_DMA_TIMEOUT);
 		if (WARN_ON(ret == 0)) {
-			dev_err(tqspi->dev, "transfer timeout\n");
+			/*
+			 * Check if hardware completed the transfer even though
+			 * interrupt was lost or delayed. If so, process the
+			 * completion and continue.
+			 */
+			ret = tegra_qspi_handle_timeout(tqspi);
+			if (ret < 0) {
+				/* Real timeout - clean up and fail */
+				dev_err(tqspi->dev, "transfer timeout\n");
 
-			if (tqspi->is_curr_dma_xfer)
-				tegra_qspi_dma_stop(tqspi);
+				if (tqspi->is_curr_dma_xfer)
+					tegra_qspi_dma_stop(tqspi);
 
-			tegra_qspi_handle_error(tqspi);
-			ret = -EIO;
-			goto complete_xfer;
+				tegra_qspi_handle_error(tqspi);
+				ret = -EIO;
+				goto complete_xfer;
+			}
 		}
 
 		if (tqspi->tx_status ||  tqspi->rx_status) {