[PATCH] habanalabs: cap simulator timeout

[PATCH] habanalabs: cap simulator timeout

[Oded Gabbay]

In the driver timeout functions, we give the simulator a factor of 10
in the timeout. This was necessary when the requested timeout is small
but if it was a few seconds, this can result in a very large timeout which
is unnecessary.

This patch caps the maximum timeout of the simulator to 10 seconds, which
is our largest timeout in the code. That is more then enough for anything
the simulator is doing.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/habanalabs.h | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 10da9940ee0d..57183ae9b95d 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -36,6 +36,8 @@
 
 #define HL_PCI_ELBI_TIMEOUT_MSEC	10 /* 10ms */
 
+#define HL_SIM_MAX_TIMEOUT_US		10000000 /* 10s */
+
 #define HL_MAX_QUEUES			128
 
 #define HL_MAX_JOBS_PER_CS		64
@@ -1036,14 +1038,18 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 	WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | \
 			(val) << REG_FIELD_SHIFT(reg, field))
 
+/* Timeout should be longer when working with simulator but cap the
+ * increased timeout to some maximum
+ */
 #define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \
 ({ \
 	ktime_t __timeout; \
-	/* timeout should be longer when working with simulator */ \
 	if (hdev->pdev) \
 		__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	else \
-		__timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
 		(val) = RREG32(addr); \
@@ -1067,11 +1073,12 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 #define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us) \
 ({ \
 	ktime_t __timeout; \
-	/* timeout should be longer when working with simulator */ \
 	if (hdev->pdev) \
 		__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	else \
-		__timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
 		/* Verify we read updates done by other cores or by device */ \
@@ -1093,11 +1100,12 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 					timeout_us) \
 ({ \
 	ktime_t __timeout; \
-	/* timeout should be longer when working with simulator */ \
 	if (hdev->pdev) \
 		__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	else \
-		__timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
 		(val) = readl(addr); \
-- 
2.17.1

RE: [PATCH] habanalabs: cap simulator timeout

[Omer Shpigelman]

From: Oded Gabbay <oded.gabbay@gmail.com>
Sent: Thursday, 18 July 2019 11:48

> In the driver timeout functions, we give the simulator a factor of 10 in the
> timeout. This was necessary when the requested timeout is small but if it
> was a few seconds, this can result in a very large timeout which is
> unnecessary.
> 
> This patch caps the maximum timeout of the simulator to 10 seconds, which
> is our largest timeout in the code. That is more then enough for anything the
> simulator is doing.
> 
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>