From: Hal Rosenstock <hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
To: Ira Weiny <weiny2-i2BcT+NCU+M@public.gmane.org>
Cc: "linux-rdma
(linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org)"
<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Sarat Kakarla
<sarat.kakarla-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Subject: Re: [PATCH] libibmad: Add NodeRecord query API
Date: Wed, 13 Feb 2013 18:16:18 -0500 [thread overview]
Message-ID: <511C1EC2.5000608@dev.mellanox.co.il> (raw)
In-Reply-To: <20130213142147.653df0ca629e3d450f9907a9-i2BcT+NCU+M@public.gmane.org>
On 2/13/2013 5:21 PM, Ira Weiny wrote:
> Due to the fact there is no corresponding patch to the diags I assume this is something you want to support other uses of libibmad?
It's in out of tree apps.
> As this changes the API could you update libibmad.ver as well.
I thought that this is done once right before the new release is cut.
Otherwise, there is the possibility of too many version updates.
-- Hal
> Ira
>
> On Thu, 31 Jan 2013 01:43:42 -0500
> Hal Rosenstock <hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org> wrote:
>
>> Add ib_node_query_via routine similar to ib_path_query_via
>>
>> Signed-off-by: Hal Rosenstock <hal-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
>> ---
>> diff --git a/include/infiniband/mad.h b/include/infiniband/mad.h
>> index 0694dc4..02b2353 100644
>> --- a/include/infiniband/mad.h
>> +++ b/include/infiniband/mad.h
>> @@ -65,6 +65,7 @@ BEGIN_C_DECLS
>> #define IB_PC_DATA_SZ (IB_MAD_SIZE - IB_PC_DATA_OFFS)
>> #define IB_SA_MCM_RECSZ 53
>> #define IB_SA_PR_RECSZ 64
>> +#define IB_SA_NR_RECSZ 108
>> #define IB_SA_GIR_RECSZ 72
>> #define IB_BM_DATA_OFFS 64
>> #define IB_BM_DATA_SZ (IB_MAD_SIZE - IB_BM_DATA_OFFS)
>> @@ -1519,6 +1542,9 @@ MAD_EXPORT int ib_path_query_via(const struct ibmad_port *srcport,
>> ibmad_gid_t srcgid, ibmad_gid_t destgid,
>> ib_portid_t * sm_id, void *buf);
>> /* returns lid */
>> +MAD_EXPORT int ib_node_query_via(const struct ibmad_port *srcport,
>> + uint64_t guid, ib_portid_t * sm_id,
>> + void *buf);
>>
>> /* resolve.c */
>> MAD_EXPORT int ib_resolve_smlid(ib_portid_t * sm_id, int timeout) DEPRECATED;
>> diff --git a/src/libibmad.map b/src/libibmad.map
>> index a4d4418..3f92885 100644
>> --- a/src/libibmad.map
>> +++ b/src/libibmad.map
>> @@ -148,5 +148,6 @@ IBMAD_1.3 {
>> cc_config_status_via;
>> smp_mkey_get;
>> smp_mkey_set;
>> + ib_node_query_via;
>> local: *;
>> };
>> diff --git a/src/sa.c b/src/sa.c
>> index a9a93cc..352ed9f 100644
>> --- a/src/sa.c
>> +++ b/src/sa.c
>> @@ -145,3 +145,47 @@ int ib_path_query(ibmad_gid_t srcgid, ibmad_gid_t destgid, ib_portid_t * sm_id,
>> {
>> return ib_path_query_via(ibmp, srcgid, destgid, sm_id, buf);
>> }
>> +
>> +/* NodeRecord */
>> +#define IB_NR_COMPMASK_LID (1ull<<0)
>> +#define IB_NR_COMPMASK_RESERVED1 (1ull<<1)
>> +#define IB_NR_COMPMASK_BASEVERSION (1ull<<2)
>> +#define IB_NR_COMPMASK_CLASSVERSION (1ull<<3)
>> +#define IB_NR_COMPMASK_NODETYPE (1ull<<4)
>> +#define IB_NR_COMPMASK_NUMPORTS (1ull<<5)
>> +#define IB_NR_COMPMASK_SYSIMAGEGUID (1ull<<6)
>> +#define IB_NR_COMPMASK_NODEGUID (1ull<<7)
>> +#define IB_NR_COMPMASK_PORTGUID (1ull<<8)
>> +#define IB_NR_COMPMASK_PARTCAP (1ull<<9)
>> +#define IB_NR_COMPMASK_DEVID (1ull<<10)
>> +#define IB_NR_COMPMASK_REV (1ull<<11)
>> +#define IB_NR_COMPMASK_PORTNUM (1ull<<12)
>> +#define IB_NR_COMPMASK_VENDID (1ull<<13)
>> +#define IB_NR_COMPMASK_NODEDESC (1ull<<14)
>> +
>> +#define IB_NR_DEF_MASK IB_NR_COMPMASK_PORTGUID
>> +
>> +int ib_node_query_via(const struct ibmad_port *srcport, uint64_t guid,
>> + ib_portid_t * sm_id, void *buf)
>> +{
>> + ib_sa_call_t sa = { 0 };
>> + uint8_t *p;
>> +
>> + memset(&sa, 0, sizeof sa);
>> + sa.method = IB_MAD_METHOD_GET;
>> + sa.attrid = IB_SA_ATTR_NODERECORD;
>> + sa.mask = IB_NR_DEF_MASK;
>> + sa.trid = mad_trid();
>> +
>> + memset(buf, 0, IB_SA_NR_RECSZ);
>> +
>> + mad_encode_field(buf, IB_SA_NR_PORT_GUID_F, &guid);
>> +
>> + p = sa_rpc_call(srcport, buf, sm_id, &sa, 0);
>> + if (!p) {
>> + IBWARN("sa call node_query failed");
>> + return -1;
>> + }
>> +
>> + return 0;
>> +}
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2013-02-13 23:16 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-31 6:43 [PATCH] libibmad: Add NodeRecord query API Hal Rosenstock
[not found] ` <510A129E.4000600-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2013-02-13 22:21 ` Ira Weiny
[not found] ` <20130213142147.653df0ca629e3d450f9907a9-i2BcT+NCU+M@public.gmane.org>
2013-02-13 23:16 ` Hal Rosenstock [this message]
[not found] ` <511C1EC2.5000608-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2013-02-13 23:21 ` Ira Weiny
[not found] ` <20130213152117.a7e9828bcf6069b1604d2f36-i2BcT+NCU+M@public.gmane.org>
2013-02-14 0:33 ` Hal Rosenstock
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=511C1EC2.5000608@dev.mellanox.co.il \
--to=hal-ldsdmyg8hgv8yrgs2mwiifqbs+8scbdb@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=sarat.kakarla-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org \
--cc=weiny2-i2BcT+NCU+M@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.