[PATCH v3 3/8] firmware: smccc: lfa: Add timeout and trigger watchdog

[Andre Przywara]

From: Vedashree Vidwans <vvidwans at nvidia.com>

Enhance PRIME/ACTIVATION functions to touch watchdog and implement
timeout mechanism. This update ensures that any potential hangs are
detected promptly and that the LFA process is allocated sufficient
execution time before the watchdog timer expires. These changes improve
overall system reliability by reducing the risk of undetected process
stalls and unexpected watchdog resets.

Signed-off-by: Vedashree Vidwans <vvidwans at nvidia.com>
Signed-off-by: Andre Przywara <andre.przywara at arm.com>
---
 drivers/firmware/smccc/lfa_fw.c | 43 ++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/smccc/lfa_fw.c b/drivers/firmware/smccc/lfa_fw.c
index b333b1e28c0d..357e41f95206 100644
--- a/drivers/firmware/smccc/lfa_fw.c
+++ b/drivers/firmware/smccc/lfa_fw.c
@@ -6,11 +6,14 @@
 #include <linux/arm-smccc.h>
 #include <linux/arm-smccc-bus.h>
 #include <linux/array_size.h>
+#include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kobject.h>
+#include <linux/ktime.h>
 #include <linux/list.h>
 #include <linux/module.h>
+#include <linux/nmi.h>
 #include <linux/psci.h>
 #include <linux/stop_machine.h>
 #include <linux/string.h>
@@ -27,6 +30,11 @@
 #define LFA_PRIME_CALL_AGAIN		BIT(0)
 #define LFA_ACTIVATE_CALL_AGAIN		BIT(0)
 
+#define LFA_PRIME_BUDGET_MS		30000		/* 30s cap */
+#define LFA_PRIME_DELAY_MS		10		/* 10ms between polls */
+#define LFA_ACTIVATE_BUDGET_MS		10000		/* 10s cap */
+#define LFA_ACTIVATE_DELAY_MS		10		/* 10ms between polls */
+
 /* LFA return values */
 #define LFA_SUCCESS			0
 #define LFA_NOT_SUPPORTED		1
@@ -276,6 +284,7 @@ static int call_lfa_activate(void *data)
 	struct fw_image *image = data;
 	struct arm_smccc_1_2_regs reg = { 0 }, res;
 
+	touch_nmi_watchdog();
 	reg.a0 = ARM_SMCCC_LFA_ACTIVATE;
 	reg.a1 = image->fw_seq_id;
 	/*
@@ -299,6 +308,7 @@ static int call_lfa_activate(void *data)
 
 static int activate_fw_image(struct fw_image *image)
 {
+	ktime_t end = ktime_add_ms(ktime_get(), LFA_ACTIVATE_BUDGET_MS);
 	int ret;
 
 retry:
@@ -314,8 +324,14 @@ static int activate_fw_image(struct fw_image *image)
 	}
 
 	/* SMC returned with call_again flag set, or with LFA_BUSY */
-	if (ret == -LFA_CALL_AGAIN || ret == -LFA_BUSY)
-		goto retry;
+	if (ret == -LFA_CALL_AGAIN || ret == -LFA_BUSY) {
+		if (ktime_before(ktime_get(), end)) {
+			msleep_interruptible(LFA_ACTIVATE_DELAY_MS);
+			goto retry;
+		}
+
+		ret = -LFA_TIMED_OUT;
+	}
 
 	lfa_cancel(image);
 
@@ -328,6 +344,7 @@ static int activate_fw_image(struct fw_image *image)
 static int prime_fw_image(struct fw_image *image)
 {
 	struct arm_smccc_1_2_regs reg = { 0 }, res;
+	ktime_t end = ktime_add_ms(ktime_get(), LFA_PRIME_BUDGET_MS);
 
 	if (image->may_reset_cpu) {
 		pr_err("CPU reset not supported by kernel driver\n");
@@ -335,6 +352,8 @@ static int prime_fw_image(struct fw_image *image)
 		return -EINVAL;
 	}
 
+	touch_nmi_watchdog();
+
 	reg.a0 = ARM_SMCCC_LFA_PRIME;
 retry:
 	/*
@@ -353,8 +372,24 @@ static int prime_fw_image(struct fw_image *image)
 		return res.a0;
 	}
 
-	if (res.a1 & LFA_PRIME_CALL_AGAIN)
-		goto retry;
+	if (res.a1 & LFA_PRIME_CALL_AGAIN) {
+		int ret;
+
+		/* SMC returned with call_again flag set */
+		if (ktime_before(ktime_get(), end)) {
+			msleep_interruptible(LFA_PRIME_DELAY_MS);
+			goto retry;
+		}
+
+		pr_err("LFA_PRIME for image %s timed out",
+		       get_image_name(image));
+
+		ret = lfa_cancel(image);
+		if (ret != 0)
+			return ret;
+
+		return -ETIMEDOUT;
+	}
 
 	return 0;
 }
-- 
2.43.0