The current flow to detect admin completion is:
while (command_not_completed) {
if (timeout)
error
check_for_completion()
sleep()
}
So in case the sleep took more than the timeout
(in case the thread/workqueue was not scheduled due to higher priority
task or prolonged VMexit), the driver can detect a stall even if
the completion is present.
The fix changes the order of this function to first check for
completion and only after that check if the timeout expired.
Fixes: 1738cd3ed342 ("Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx,
struct ena_com_admin_queue *admin_queue)
{
static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx,
struct ena_com_admin_queue *admin_queue)
{
- unsigned long flags;
- u32 start_time;
+ unsigned long flags, timeout;
- start_time = ((u32)jiffies_to_usecs(jiffies));
+ timeout = jiffies + ADMIN_CMD_TIMEOUT_US;
+
+ while (1) {
+ spin_lock_irqsave(&admin_queue->q_lock, flags);
+ ena_com_handle_admin_completion(admin_queue);
+ spin_unlock_irqrestore(&admin_queue->q_lock, flags);
- while (comp_ctx->status == ENA_CMD_SUBMITTED) {
- if ((((u32)jiffies_to_usecs(jiffies)) - start_time) >
- ADMIN_CMD_TIMEOUT_US) {
+ if (comp_ctx->status != ENA_CMD_SUBMITTED)
+ break;
+
+ if (time_is_before_jiffies(timeout)) {
pr_err("Wait for completion (polling) timeout\n");
/* ENA didn't have any completion */
spin_lock_irqsave(&admin_queue->q_lock, flags);
pr_err("Wait for completion (polling) timeout\n");
/* ENA didn't have any completion */
spin_lock_irqsave(&admin_queue->q_lock, flags);
- spin_lock_irqsave(&admin_queue->q_lock, flags);
- ena_com_handle_admin_completion(admin_queue);
- spin_unlock_irqrestore(&admin_queue->q_lock, flags);
-