habanalabs: increase timeout if working with simulator

Where there is a spike in the CPU consumption, it may cause
random failures in the C/I since the KMD timeout for CPU
and/or QMAN0 jobs expires and it stops communicating to the simulator.
This commit fixes it by increasing timeout on polling functions
if working with simulator.

Signed-off-by: Dalit Ben Zoor <dbenzoor@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This commit is contained in:
Dalit Ben Zoor 2019-04-30 17:18:51 +03:00 committed by Oded Gabbay
parent f0539fb0fb
commit b1b537713e
2 changed files with 13 additions and 2 deletions

View file

@ -1147,7 +1147,13 @@ int hl_poll_timeout_memory(struct hl_device *hdev, u64 addr,
* either by the direct access of the device or by another core
*/
u32 *paddr = (u32 *) (uintptr_t) addr;
ktime_t timeout = ktime_add_us(ktime_get(), timeout_us);
ktime_t timeout;
/* timeout should be longer when working with simulator */
if (!hdev->pdev)
timeout_us *= 10;
timeout = ktime_add_us(ktime_get(), timeout_us);
might_sleep();

View file

@ -1042,7 +1042,12 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
#define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \
({ \
ktime_t __timeout = ktime_add_us(ktime_get(), 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)); \
might_sleep_if(sleep_us); \
for (;;) { \
(val) = RREG32(addr); \