Re: [PATCH net-next v3 05/18] net/smc: reserve CHID range for SMC-D virtual device

[Wen Gu <guwen@linux.alibaba.com>]

On 2023/9/22 07:32, Wenjia Zhang wrote:
> 
> 
> On 21.09.23 15:19, Wen Gu wrote:
>> This patch reserve CHID range from 0xFF00 to 0xFFFF for SMC-D virtual
>> device and introduces helpers to identify them.
>>
>> Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
>> ---
>>   net/smc/smc_ism.h | 15 +++++++++++++++
>>   1 file changed, 15 insertions(+)
>>
>> diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
>> index 14d2e77..2ecc8de 100644
>> --- a/net/smc/smc_ism.h
>> +++ b/net/smc/smc_ism.h
>> @@ -15,6 +15,9 @@
>>   #include "smc.h"
>> +#define SMC_VIRT_ISM_CHID_MAX        0xFFFF
>> +#define SMC_VIRT_ISM_CHID_MIN        0xFF00
>> +
>>   struct smcd_dev_list {    /* List of SMCD devices */
>>       struct list_head list;
>>       struct mutex mutex;    /* Protects list of devices */
>> @@ -57,4 +60,16 @@ static inline int smc_ism_write(struct smcd_dev *smcd, u64 dmb_tok,
>>       return rc < 0 ? rc : 0;
>>   }
>> +static inline bool __smc_ism_is_virtdev(u16 chid)
>> +{
>> +    return (chid >= SMC_VIRT_ISM_CHID_MIN && chid <= SMC_VIRT_ISM_CHID_MAX);
>> +}
>> +
>> +static inline bool smc_ism_is_virtdev(struct smcd_dev *smcd)
>> +{
>> +    u16 chid = smcd->ops->get_chid(smcd);
>> +
>> +    return __smc_ism_is_virtdev(chid);
>> +}
>> +
> I'm wondering if barrier is needed here.

I think this helper doesn't involve memory race or multi-threaded/multi-processor
cases that needs enforcing ordering and synchronization of memory operations.

So IMHO barrier is no very necessary here.

Thank you.

>>   #endif