Merge patch series "ufs: core: cleanup and threaded irq handler"

Neil Armstrong <neil.armstrong@linaro.org> says:

On systems with a large number request slots and unavailable MCQ,
the current design of the interrupt handler can delay handling of
other subsystems interrupts causing display artifacts, GPU stalls
or system firmware requests timeouts.

Example of errors reported on a loaded system:
 [drm:dpu_encoder_frame_done_timeout:2706] [dpu error]enc32 frame done timeout
 msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] *ERROR* 67.5.20.1: hangcheck detected gpu lockup rb 2!
 msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] *ERROR* 67.5.20.1:     completed fence: 74285
 msm_dpu ae01000.display-controller: [drm:hangcheck_handler [msm]] *ERROR* 67.5.20.1:     submitted fence: 74286
 Error sending AMC RPMH requests (-110)

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250407-topic-ufs-use-threaded-irq-v3-0-08bee980f71e@linaro.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 31 insertions, 11 deletions

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0534390c2a35..b40660ca2fa6 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -643,9 +643,6 @@ static void ufshcd_print_host_state(struct ufs_hba *hba)
 		"last_hibern8_exit_tstamp at %lld us, hibern8_exit_cnt=%d\n",
 		div_u64(hba->ufs_stats.last_hibern8_exit_tstamp, 1000),
 		hba->ufs_stats.hibern8_exit_cnt);
-	dev_err(hba->dev, "last intr at %lld us, last intr status=0x%x\n",
-		div_u64(hba->ufs_stats.last_intr_ts, 1000),
-		hba->ufs_stats.last_intr_status);
 	dev_err(hba->dev, "error handling flags=0x%x, req. abort count=%d\n",
 		hba->eh_flags, hba->req_abort_count);
 	dev_err(hba->dev, "hba->ufs_version=0x%x, Host capabilities=0x%x, caps=0x%x\n",
@@ -6974,7 +6971,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
 }
 
 /**
- * ufshcd_intr - Main interrupt service routine
+ * ufshcd_threaded_intr - Threaded interrupt service routine
  * @irq: irq number
  * @__hba: pointer to adapter instance
  *
@@ -6982,16 +6979,14 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
  *  IRQ_HANDLED - If interrupt is valid
  *  IRQ_NONE    - If invalid interrupt
  */
-static irqreturn_t ufshcd_intr(int irq, void *__hba)
+static irqreturn_t ufshcd_threaded_intr(int irq, void *__hba)
 {
-	u32 intr_status, enabled_intr_status = 0;
+	u32 last_intr_status, intr_status, enabled_intr_status = 0;
 	irqreturn_t retval = IRQ_NONE;
 	struct ufs_hba *hba = __hba;
 	int retries = hba->nutrs;
 
-	intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
-	hba->ufs_stats.last_intr_status = intr_status;
-	hba->ufs_stats.last_intr_ts = local_clock();
+	last_intr_status = intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
 
 	/*
 	 * There could be max of hba->nutrs reqs in flight and in worst case
@@ -7015,7 +7010,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 		dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x (0x%08x, 0x%08x)\n",
 					__func__,
 					intr_status,
-					hba->ufs_stats.last_intr_status,
+					last_intr_status,
 					enabled_intr_status);
 		ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: ");
 	}
@@ -7023,6 +7018,29 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 	return retval;
 }
 
+/**
+ * ufshcd_intr - Main interrupt service routine
+ * @irq: irq number
+ * @__hba: pointer to adapter instance
+ *
+ * Return:
+ *  IRQ_HANDLED     - If interrupt is valid
+ *  IRQ_WAKE_THREAD - If handling is moved to threaded handled
+ *  IRQ_NONE        - If invalid interrupt
+ */
+static irqreturn_t ufshcd_intr(int irq, void *__hba)
+{
+	struct ufs_hba *hba = __hba;
+
+	/* Move interrupt handling to thread when MCQ & ESI are not enabled */
+	if (!hba->mcq_enabled || !hba->mcq_esi_enabled)
+		return IRQ_WAKE_THREAD;
+
+	/* Directly handle interrupts since MCQ ESI handlers does the hard job */
+	return ufshcd_sl_intr(hba, ufshcd_readl(hba, REG_INTERRUPT_STATUS) &
+				   ufshcd_readl(hba, REG_INTERRUPT_ENABLE));
+}
+
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag)
 {
 	int err = 0;
@@ -8722,6 +8740,7 @@ static void ufshcd_config_mcq(struct ufs_hba *hba)
 	u32 intrs;
 
 	ret = ufshcd_mcq_vops_config_esi(hba);
+	hba->mcq_esi_enabled = !ret;
 	dev_info(hba->dev, "ESI %sconfigured\n", ret ? "is not " : "");
 
 	intrs = UFSHCD_ENABLE_MCQ_INTRS;
@@ -10581,7 +10600,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	ufshcd_readl(hba, REG_INTERRUPT_ENABLE);
 
 	/* IRQ registration */
-	err = devm_request_irq(dev, irq, ufshcd_intr, IRQF_SHARED, UFSHCD, hba);
+	err = devm_request_threaded_irq(dev, irq, ufshcd_intr, ufshcd_threaded_intr,
+					IRQF_ONESHOT | IRQF_SHARED, UFSHCD, hba);
 	if (err) {
 		dev_err(hba->dev, "request irq failed\n");
 		goto out_disable;