[PATCH 12/17] dmaengine: idxd: hold device commands off while the reset re-creates its interrupts

[Daniel Byrne]

The re-probe after a reset frees the misc interrupt and the MSI-X
vectors and requests them again. A device command whose completion
interrupt arrives in between is never completed, so its owner times
out and fences the device that was just reset, and the rebind in
idxd_reset_done() then fails.

Wait for the running command before the vectors are freed, since its
interrupt still arrives, and then hold IDXD_FLAG_CMD_RUNNING without an
owner until the interrupts are back, so that commands issued meanwhile
wait as they wait for any running command. A halt's recovery may forget
the hold, so it is released only if no newer command owns the state.

Assisted-by: Claude:claude-opus-5-5
Assisted-by: Claude:claude-fable-5-1
Signed-off-by: Daniel Byrne <daniel1.byrne@xxxxxxxxx>
---
 drivers/dma/idxd/device.c | 44 +++++++++++++++++++++++++++++++++++++++
 drivers/dma/idxd/idxd.h   |  2 ++
 drivers/dma/idxd/init.c   | 10 +++++++++
 3 files changed, 56 insertions(+)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index d3b95593a686..222c201669bd 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -724,6 +724,50 @@ void idxd_cmd_reset_state(struct idxd_device *idxd)
 	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
 }
 
+/*
+ * Hold device commands off while the re-probe after a reset frees the
+ * interrupts and requests them again. A command whose completion
+ * interrupt comes while the misc vector is gone is never completed, and
+ * its owner would time out and fence the device that was just reset.
+ * The running command, if any, is waited for first: its owner gives up
+ * within its timeout, and the misc vector still takes its interrupt.
+ * RUNNING is then held without an owner, and new commands wait for it
+ * as for any running command. Returns false, holding nothing, when a
+ * command timed out, since commands then fail fast anyway.
+ */
+bool idxd_cmd_hold(struct idxd_device *idxd, u32 *seq)
+{
+	bool held = false;
+
+	spin_lock_irq(&idxd->cmd_lock);
+	wait_event_lock_irq(idxd->cmd_waitq,
+			    !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags) ||
+			    test_bit(IDXD_FLAG_CMD_TIMEDOUT, &idxd->flags),
+			    idxd->cmd_lock);
+	if (!test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags)) {
+		__set_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags);
+		*seq = ++idxd->cmd_seq;
+		held = true;
+	}
+	spin_unlock_irq(&idxd->cmd_lock);
+	return held;
+}
+
+/*
+ * End a hold taken by idxd_cmd_hold(). A halt's recovery may have
+ * forgotten the hold meanwhile and let another command run, which then
+ * has an owner or a newer sequence number, and its state is left alone.
+ */
+void idxd_cmd_unhold(struct idxd_device *idxd, u32 seq)
+{
+	spin_lock_irq(&idxd->cmd_lock);
+	if (idxd->cmd_seq == seq && !idxd->cmd_done) {
+		__clear_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags);
+		wake_up(&idxd->cmd_waitq);
+	}
+	spin_unlock_irq(&idxd->cmd_lock);
+}
+
 int idxd_device_enable(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index c04a2855aa3f..9d88b0d82fee 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -794,6 +794,8 @@ int idxd_device_disable(struct idxd_device *idxd);
 int idxd_device_reset(struct idxd_device *idxd);
 void idxd_device_clear_state(struct idxd_device *idxd);
 void idxd_cmd_reset_state(struct idxd_device *idxd);
+bool idxd_cmd_hold(struct idxd_device *idxd, u32 *seq);
+void idxd_cmd_unhold(struct idxd_device *idxd, u32 seq);
 int idxd_device_config(struct idxd_device *idxd);
 int idxd_device_drain_pasid(struct idxd_device *idxd, int pasid);
 int idxd_device_load_config(struct idxd_device *idxd);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index a037a6e76362..312b4670b3e8 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -1212,6 +1212,14 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
 	}
 
 	if (!alloc_idxd) {
+		bool held;
+		u32 seq;
+
+		/*
+		 * Commands complete through the misc interrupt, which is
+		 * gone until it is requested again.
+		 */
+		held = idxd_cmd_hold(idxd, &seq);
 		/* Release interrupts in the IDXD device. */
 		idxd_cleanup_interrupts(idxd);
 
@@ -1219,6 +1227,8 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
 		rc = idxd_setup_interrupts(idxd);
 		if (rc)
 			dev_warn(dev, "IDXD interrupts failed to setup\n");
+		if (held)
+			idxd_cmd_unhold(idxd, seq);
 	}
 
 	dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n",
-- 
2.43.0