[PATCH 2/5] HID: intel-thc-hid: intel-ipts: receive reports

[Emfox Zhou <emfox@debian.org>]

Take the port one step further: configure the two DMA engines, one for
the frames the controller sends and one for the frames the host sends,
and register the interrupt that reports them.

Interrupt remapping rejects the MSI requests these ports send: the
requester ID in them is 01:05.0, neither the port's own function nor a
valid DMA alias for it, so only the legacy interrupt pin works once
remapping is on. MSI stays as a fallback for a platform that does not
route that pin. It is shared with other functions on the PCH, so it is
requested with IRQF_SHARED and a foreign interrupt only costs the thread a
few register reads.

Transfer errors are recovered from a work item and not from the threaded
handler: thc_rxdma_reset() takes the bus lock, and a pending
thc_dma_write() holds that lock while it waits for the very completion the
handler has to deliver.

Every frame carries a code and a length in front of the payload. The
receive side decodes that header. Frames are still only logged here,
the next patch hands them to the HID core.

Three details cost time on hardware:

  - The interrupt configuration has to be applied before the DMA
    engines are started: it programs the device interrupt type field to
    the invalid value, and starting the receive engine then replaces that
    field with the type it expects. The other order would leave the
    invalid value in place.

  - The line is masked while the threaded handler runs, and an event
    that arrives in that window leaves nothing behind but its status
    bit. The handler therefore drains the status registers instead of
    trusting a single delivery: a write completion taken for granted
    this way makes the next transfer wait for a completion that never
    comes, and the port stays unusable until it is reset.

  - Bulk transfers have no address phase, so the SPI opcode stays zero.
    The opcodes the HIDSPI path uses make this controller ignore the
    frames altogether.

Signed-off-by: Emfox Zhou <emfox@debian.org>
---
 drivers/hid/intel-thc-hid/intel-ipts/ipts.c   | 193 ++++++++++++++++++
 drivers/hid/intel-thc-hid/intel-ipts/ipts.h   |  15 ++
 .../hid/intel-thc-hid/intel-ipts/pci-ipts.c   |  40 +++-
 3 files changed, 247 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/intel-thc-hid/intel-ipts/ipts.c b/drivers/hid/intel-thc-hid/intel-ipts/ipts.c
index b16dfdc..8529b91 100644
--- a/drivers/hid/intel-thc-hid/intel-ipts/ipts.c
+++ b/drivers/hid/intel-thc-hid/intel-ipts/ipts.c
@@ -5,8 +5,13 @@
  */
 
 #include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/minmax.h>
 #include <linux/regmap.h>
+#include <linux/sizes.h>
 #include <linux/string.h>
+#include <linux/unaligned.h>
+#include <linux/workqueue.h>
 
 #include "intel-thc-hw.h"
 #include "ipts.h"
@@ -20,6 +25,12 @@
 /* Time the controller needs after reset before it answers on the bus. */
 #define THC_IPTS_BOOT_MS		100
 
+/*
+ * The core returns after the first cause it finds, so one interrupt can need
+ * up to four reads: non-DMA, transaction error, overrun, then the data path.
+ */
+#define THC_IPTS_IRQ_CAUSES		4
+
 static int thc_ipts_read_cfg(struct thc_ipts *idev)
 {
 	int ret, try;
@@ -124,6 +135,162 @@ static int thc_ipts_touch_set(struct thc_ipts *idev, bool enable)
 				 &touch);
 }
 
+static void thc_ipts_handle_frame(struct thc_ipts *idev, size_t len)
+{
+	size_t capacity = idev->max_rx - THC_IPTS_RX_HDR_SIZE;
+	u32 code, size;
+
+	if (len < THC_IPTS_RX_HDR_SIZE)
+		return;
+
+	code = get_unaligned_le32(idev->rx_frame);
+	/* The header may claim more than what actually arrived. */
+	size = min_t(u32, get_unaligned_le32(idev->rx_frame + 4),
+		     capacity);
+	size = min_t(u32, size, len - THC_IPTS_RX_HDR_SIZE);
+
+	dev_dbg(idev->dev, "frame code %u, %u bytes\n", code, size);
+}
+
+static void thc_ipts_dma_stop(struct thc_ipts *idev)
+{
+	if (!idev->dma_ready)
+		return;
+
+	idev->dma_ready = false;
+	thc_dma_unconfigure(idev->thc);
+	thc_dma_release(idev->thc);
+}
+
+static int thc_ipts_dma_start(struct thc_ipts *idev)
+{
+	int ret;
+
+	/*
+	 * Allocated once, so each buffer is retried on its own: a resume after a
+	 * failed first start must not end up with a NULL frame buffer.
+	 */
+	if (!idev->rx_frame) {
+		/*
+		 * The core rounds the packet size up to a page when it sets
+		 * up the engines, so the buffer has to be that large.
+		 */
+		idev->rx_frame = devm_kzalloc(idev->dev,
+					      round_up(idev->max_rx, SZ_4K),
+					      GFP_KERNEL);
+		if (!idev->rx_frame)
+			return -ENOMEM;
+	}
+
+	ret = thc_dma_set_max_packet_sizes(idev->thc, 0, idev->max_rx, idev->max_tx, 0);
+	if (ret)
+		return ret;
+
+	ret = thc_dma_allocate(idev->thc);
+	if (ret)
+		return ret;
+
+	ret = thc_dma_configure(idev->thc);
+	if (ret) {
+		thc_dma_release(idev->thc);
+		return ret;
+	}
+
+	idev->dma_ready = true;
+
+	return 0;
+}
+
+irqreturn_t thc_ipts_hardirq(int irq, void *data)
+{
+	struct thc_ipts *idev = data;
+
+	/*
+	 * The pin is shared and this may be another function's interrupt; the
+	 * cause can only be read in the thread, so claim it. Mask first, or a
+	 * level triggered line stays asserted on the way out.
+	 */
+	if (READ_ONCE(idev->stopping) || !READ_ONCE(idev->dma_ready)) {
+		thc_interrupt_enable(idev->thc, false);
+		return IRQ_HANDLED;
+	}
+
+	thc_interrupt_enable(idev->thc, false);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static int thc_ipts_read_frames(struct thc_ipts *idev)
+{
+	for (;;) {
+		int finished = 0;
+		size_t len;
+
+		if (thc_rxdma_read(idev->thc, THC_RXDMA2, idev->rx_frame,
+				   &len, &finished)) {
+			dev_warn_once(idev->dev,
+				      "cannot read a frame from the receive engine\n");
+			return -EIO;
+		}
+
+		thc_ipts_handle_frame(idev, len);
+		if (finished)
+			break;
+	}
+
+	return 0;
+}
+
+/*
+ * Run from a work item: thc_rxdma_reset() takes the bus lock, which
+ * thc_dma_write() holds while it waits for a completion this thread has to
+ * deliver, so resetting inline would stall until the write times out.
+ */
+void thc_ipts_recover(struct work_struct *work)
+{
+	struct thc_ipts *idev = container_of(work, struct thc_ipts, recover_work);
+
+	if (thc_rxdma_reset(idev->thc))
+		dev_err(idev->dev, "cannot reset the receive engine\n");
+}
+
+irqreturn_t thc_ipts_thread(int irq, void *data)
+{
+	struct thc_ipts *idev = data;
+	int pass;
+
+	/*
+	 * The port stays masked until the end of this handler, so a cause that
+	 * arrives in between leaves only its status bit: keep reading until
+	 * the core reports none.
+	 */
+	for (pass = 0; pass < THC_IPTS_IRQ_CAUSES; pass++) {
+		int mask = thc_interrupt_handler(idev->thc);
+
+		/* The core reports this one when no cause is pending. */
+		if (mask == BIT(THC_UNKNOWN_INT))
+			break;
+
+		if (mask & (BIT(THC_FATAL_ERR_INT) | BIT(THC_TXN_ERR_INT))) {
+			dev_err(idev->dev, "transfer error, resetting the receive engine\n");
+			schedule_work(&idev->recover_work);
+			break;
+		}
+
+		/*
+		 * A non-DMA cause needs no action: the core acknowledges it,
+		 * and this port moves report data through the DMA engines.
+		 */
+		if (mask & BIT(THC_RXDMA2_INT) && thc_ipts_read_frames(idev))
+			schedule_work(&idev->recover_work);
+	}
+
+	if (!READ_ONCE(idev->stopping))
+		thc_interrupt_enable(idev->thc, true);
+
+	return IRQ_HANDLED;
+}
+
 /**
  * thc_ipts_port_start - bring one port up
  * @idev: port to start
@@ -133,6 +300,8 @@ int thc_ipts_port_start(struct thc_ipts *idev)
 	u32 ctrl, hz, mode;
 	int ret;
 
+	WRITE_ONCE(idev->stopping, false);
+
 	ret = thc_ipts_quiesce(idev, true);
 	if (ret)
 		return ret;
@@ -203,6 +372,20 @@ int thc_ipts_port_start(struct thc_ipts *idev)
 	ret = thc_ipts_touch_set(idev, true);
 	if (ret)
 		return ret;
+	idev->running = true;
+
+	/*
+	 * thc_interrupt_config() programs the interrupt type field to the
+	 * invalid value; starting RXDMA2 then sets it to the type the engine
+	 * expects, so the configuration has to happen first.
+	 */
+	thc_interrupt_config(idev->thc);
+
+	ret = thc_ipts_dma_start(idev);
+	if (ret)
+		return ret;
+
+	thc_interrupt_enable(idev->thc, true);
 
 	return 0;
 }
@@ -220,6 +403,16 @@ void thc_ipts_port_stop(struct thc_ipts *idev)
 	if (!idev->thc)
 		return;
 
+	/*
+	 * Mask the line, then wait for a handler that may be holding a
+	 * frame for the HID device which is about to go away.
+	 */
+	WRITE_ONCE(idev->stopping, true);
+	thc_interrupt_enable(idev->thc, false);
+	synchronize_irq(idev->irq);
+	cancel_work_sync(&idev->recover_work);
+	thc_ipts_dma_stop(idev);
+
 	if (idev->running)
 		thc_ipts_touch_set(idev, false);
 
diff --git a/drivers/hid/intel-thc-hid/intel-ipts/ipts.h b/drivers/hid/intel-thc-hid/intel-ipts/ipts.h
index b936ac1..3b5002c 100644
--- a/drivers/hid/intel-thc-hid/intel-ipts/ipts.h
+++ b/drivers/hid/intel-thc-hid/intel-ipts/ipts.h
@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/types.h>
+#include <linux/wait.h>
 
 #include "intel-thc-dev.h"
 
@@ -108,24 +109,38 @@ static_assert(offsetof(struct thc_ipts_cfg, vendor) == 0x1c);
  * struct thc_ipts - state of one THC port in IPTS mode
  * @dev: device used for resources and logging
  * @thc: shared THC core context
+ * @irq: interrupt line of the port
  * @cfg: configuration block last read from the controller
  * @vendor: vendor ID the controller reports for its HID device
  * @product: product ID the controller reports for its HID device
  * @max_rx: largest frame the controller may send, in bytes
  * @max_tx: largest frame the driver may send, in bytes
+ * @rx_frame: buffer for one received frame, including its header
+ * @recover_work: resets the receive engine after a transfer error
  * @running: the controller answered and is out of reset
+ * @dma_ready: DMA engines are configured and may be used
+ * @stopping: the port is being torn down, ignore the interrupt
  */
 struct thc_ipts {
 	struct device		*dev;
 	struct thc_device	*thc;
+	int			irq;
 	struct thc_ipts_cfg	cfg;
 	u16			vendor;
 	u16			product;
 	size_t			max_rx;
 	size_t			max_tx;
+	u8			*rx_frame;
+	struct work_struct	recover_work;
 	bool			running;
+	bool			dma_ready;
+	bool			stopping;
 };
 
+irqreturn_t thc_ipts_hardirq(int irq, void *data);
+irqreturn_t thc_ipts_thread(int irq, void *data);
+void thc_ipts_recover(struct work_struct *work);
+
 int thc_ipts_port_start(struct thc_ipts *idev);
 void thc_ipts_port_stop(struct thc_ipts *idev);
 
diff --git a/drivers/hid/intel-thc-hid/intel-ipts/pci-ipts.c b/drivers/hid/intel-thc-hid/intel-ipts/pci-ipts.c
index e45f6ab..7e899df 100644
--- a/drivers/hid/intel-thc-hid/intel-ipts/pci-ipts.c
+++ b/drivers/hid/intel-thc-hid/intel-ipts/pci-ipts.c
@@ -74,10 +74,39 @@ static int thc_ipts_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	if (IS_ERR(idev->thc))
 		return PTR_ERR(idev->thc);
 
+	/*
+	 * Interrupt remapping rejects the MSI requests these ports send, so
+	 * take the legacy pin (shared with other functions on the PCH, hence
+	 * IRQF_SHARED); MSI is only for a platform that routes no pin.
+	 */
+	ret = pci_alloc_irq_vectors(pci, 1, 1, PCI_IRQ_INTX);
+	if (ret < 0) {
+		dev_warn(idev->dev, "no interrupt pin, falling back to MSI\n");
+		ret = pci_alloc_irq_vectors(pci, 1, 1,
+					    PCI_IRQ_MSI | PCI_IRQ_MSIX);
+	}
+	if (ret < 0) {
+		dev_err(idev->dev, "cannot allocate an interrupt vector, error %d\n",
+			ret);
+		return ret;
+	}
+
+	idev->irq = pci_irq_vector(pci, 0);
+
+	ret = devm_request_threaded_irq(idev->dev, idev->irq, thc_ipts_hardirq,
+					thc_ipts_thread,
+					IRQF_ONESHOT | IRQF_SHARED,
+					KBUILD_MODNAME, idev);
+	if (ret) {
+		dev_err(idev->dev, "cannot get the interrupt, error %d\n", ret);
+		goto err_vectors;
+	}
+
 	ret = thc_ipts_port_start(idev);
 	if (ret) {
 		thc_ipts_port_stop(idev);
-		return ret;
+		devm_free_irq(idev->dev, idev->irq, idev);
+		goto err_vectors;
 	}
 
 	dev_info(idev->dev, "controller %04x:%04x rev %u, firmware 0x%08x\n",
@@ -87,6 +116,11 @@ static int thc_ipts_probe(struct pci_dev *pci, const struct pci_device_id *id)
 		 le32_to_cpu(idev->cfg.spi_cfg), idev->max_rx, idev->max_tx);
 
 	return 0;
+
+err_vectors:
+	pci_free_irq_vectors(pci);
+
+	return ret;
 }
 
 static void thc_ipts_remove(struct pci_dev *pci)
@@ -94,6 +128,10 @@ static void thc_ipts_remove(struct pci_dev *pci)
 	struct thc_ipts *idev = pci_get_drvdata(pci);
 
 	thc_ipts_port_stop(idev);
+
+	/* The handler has to go before the vector it is bound to is freed. */
+	devm_free_irq(idev->dev, idev->irq, idev);
+	pci_free_irq_vectors(pci);
 	pci_clear_master(pci);
 }