提交 2c47e351 编写于 作者: S Shannon Nelson 提交者: Jeff Kirsher

i40e: catch NVM write semaphore timeout and retry

In some circumstances, a multi-write transaction takes longer than the
default 3 minute timeout on the write semaphore.  If the write failed with
an EBUSY status, this is likely the problem, so here we try to reacquire
the semaphore then retry the write.  We only do one retry, then give up.

Change-ID: I1c8be60688acc2f39573839579baf601207c4a36
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
上级 33c62b34
master alk-4.19.24 alk-4.19.30 alk-4.19.34 alk-4.19.36 alk-4.19.43 alk-4.19.48 alk-4.19.57 ck-4.19.67 ck-4.19.81 ck-4.19.91 github/fork/deepanshu1422/fix-typo-in-comment github/fork/haosdent/fix-typo linux-next v4.19.91 v4.19.90 v4.19.89 v4.19.88 v4.19.87 v4.19.86 v4.19.85 v4.19.84 v4.19.83 v4.19.82 v4.19.81 v4.19.80 v4.19.79 v4.19.78 v4.19.77 v4.19.76 v4.19.75 v4.19.74 v4.19.73 v4.19.72 v4.19.71 v4.19.70 v4.19.69 v4.19.68 v4.19.67 v4.19.66 v4.19.65 v4.19.64 v4.19.63 v4.19.62 v4.19.61 v4.19.60 v4.19.59 v4.19.58 v4.19.57 v4.19.56 v4.19.55 v4.19.54 v4.19.53 v4.19.52 v4.19.51 v4.19.50 v4.19.49 v4.19.48 v4.19.47 v4.19.46 v4.19.45 v4.19.44 v4.19.43 v4.19.42 v4.19.41 v4.19.40 v4.19.39 v4.19.38 v4.19.37 v4.19.36 v4.19.35 v4.19.34 v4.19.33 v4.19.32 v4.19.31 v4.19.30 v4.19.29 v4.19.28 v4.19.27 v4.19.26 v4.19.25 v4.19.24 v4.19.23 v4.19.22 v4.19.21 v4.19.20 v4.19.19 v4.19.18 v4.19.17 v4.19.16 v4.19.15 v4.19.14 v4.19.13 v4.19.12 v4.19.11 v4.19.10 v4.19.9 v4.19.8 v4.19.7 v4.19.6 v4.19.5 v4.19.4 v4.19.3 v4.19.2 v4.19.1 v4.19 v4.19-rc8 v4.19-rc7 v4.19-rc6 v4.19-rc5 v4.19-rc4 v4.19-rc3 v4.19-rc2 v4.19-rc1 ck-release-21 ck-release-20 ck-release-19.2 ck-release-19.1 ck-release-19 ck-release-18 ck-release-17.2 ck-release-17.1 ck-release-17 ck-release-16 ck-release-15.1 ck-release-15 ck-release-14 ck-release-13.2 ck-release-13 ck-release-12 ck-release-11 ck-release-10 ck-release-9 ck-release-7 alk-release-15 alk-release-14 alk-release-13.2 alk-release-13 alk-release-12 alk-release-11 alk-release-10 alk-release-9 alk-release-7
无相关合并请求
......@@ -679,9 +679,11 @@ static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw,
{
i40e_status status;
enum i40e_nvmupd_cmd upd_cmd;
bool retry_attempt = false;
upd_cmd = i40e_nvmupd_validate_command(hw, cmd, errno);
retry:
switch (upd_cmd) {
case I40E_NVMUPD_WRITE_CON:
status = i40e_nvmupd_nvm_write(hw, cmd, bytes, errno);
......@@ -725,6 +727,39 @@ static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw,
*errno = -ESRCH;
break;
}
/* In some circumstances, a multi-write transaction takes longer
* than the default 3 minute timeout on the write semaphore. If
* the write failed with an EBUSY status, this is likely the problem,
* so here we try to reacquire the semaphore then retry the write.
* We only do one retry, then give up.
*/
if (status && (hw->aq.asq_last_status == I40E_AQ_RC_EBUSY) &&
!retry_attempt) {
i40e_status old_status = status;
u32 old_asq_status = hw->aq.asq_last_status;
u32 gtime;
gtime = rd32(hw, I40E_GLVFGEN_TIMER);
if (gtime >= hw->nvm.hw_semaphore_timeout) {
i40e_debug(hw, I40E_DEBUG_ALL,
"NVMUPD: write semaphore expired (%d >= %lld), retrying\n",
gtime, hw->nvm.hw_semaphore_timeout);
i40e_release_nvm(hw);
status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE);
if (status) {
i40e_debug(hw, I40E_DEBUG_ALL,
"NVMUPD: write semaphore reacquire failed aq_err = %d\n",
hw->aq.asq_last_status);
status = old_status;
hw->aq.asq_last_status = old_asq_status;
} else {
retry_attempt = true;
goto retry;
}
}
}
return status;
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部