From mboxrd@z Thu Jan  1 00:00:00 1970
From: maxg@mellanox.com (Max Gurtovoy)
Date: Thu, 7 Jun 2018 16:02:23 +0300
Subject: [PATCH 08/17] nvme: limit integrity segments to be <= data
 segments
In-Reply-To: <19c8562a-8478-196c-c9f5-385d2076448e@grimberg.me>
References: <1527436222-15494-1-git-send-email-maxg@mellanox.com>
 <1527436222-15494-9-git-send-email-maxg@mellanox.com>
 <19c8562a-8478-196c-c9f5-385d2076448e@grimberg.me>
Message-ID: <f7bf4e84-f403-7576-299f-63b0c4aa6f1b@mellanox.com>



On 5/31/2018 1:09 AM, Sagi Grimberg wrote:
> 
>> There is no reason for setting max_integrity_segments to be greater than
>> max_segments.
>>
>> Signed-off-by: Max Gurtovoy <maxg at mellanox.com>
>> ---
>> ? drivers/nvme/host/core.c | 4 ++++
>> ? 1 file changed, 4 insertions(+)
>>
>> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
>> index 197208a..e81e898 100644
>> --- a/drivers/nvme/host/core.c
>> +++ b/drivers/nvme/host/core.c
>> @@ -1795,6 +1795,10 @@ static void nvme_set_queue_limits(struct 
>> nvme_ctrl *ctrl,
>> ????????? u32 max_segments =
>> ????????????? (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
>> +??????? if (ctrl->max_integrity_segments)
>> +??????????? ctrl->max_integrity_segments = 
>> min(ctrl->max_integrity_segments,
>> +?????????????????????????????? max_segments);
>> +
> 
> What is this protecting against?

This is for good practice, I don't think the block layer will/can send 
us more integrity_segments than data_segments. but seems weird to have 
more max_integrity_segments than max_data_segments, isn't it ?