Re: [PATCH V1.1 1/8] opensm: Add guid2mkey cache file support

[Alex Netes <alexne-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>]

Hi Jim,

On 17:25 Tue 03 Jul     , Jim Foraker wrote:
> Adds support for a guid2mkey file, and uses the database
> to select which mkey to use in outgoing SMPs.

One thing that I notice that missing (and I'm not sure how common it's being used,
but still I see it as part of SUSE distro) is sldd.sh script found under
scripts. It distributes guid2lid between STANDBY SMs, so I think guid2mkey file
should be also redistributed between the STANDBY SMs.

> 
> Signed-off-by: Jim Foraker <foraker1-i2BcT+NCU+M@public.gmane.org>
> ---
>  include/opensm/osm_db.h      |    7 +-
>  include/opensm/osm_db_pack.h |  144 ++++++++++++++++++++++++++++++++++++++++++
>  include/opensm/osm_port.h    |   23 ++-----
>  include/opensm/osm_subnet.h  |    2 +
>  opensm/osm_db_files.c        |    1 +
>  opensm/osm_db_pack.c         |   73 +++++++++++++++++++++
>  opensm/osm_lid_mgr.c         |   12 +++-
>  opensm/osm_link_mgr.c        |   14 +++-
>  opensm/osm_opensm.c          |   10 +--
>  opensm/osm_port.c            |   32 ++++++++++
>  opensm/osm_port_info_rcv.c   |    6 +-
>  opensm/osm_req.c             |    1 +
>  opensm/osm_state_mgr.c       |    4 ++
>  opensm/osm_subnet.c          |   77 ++++++++++++++++++++++
>  14 files changed, 377 insertions(+), 29 deletions(-)
> 
> diff --git a/include/opensm/osm_db.h b/include/opensm/osm_db.h
> index 7077347..d05bfa0 100644
> --- a/include/opensm/osm_db.h
> +++ b/include/opensm/osm_db.h
> @@ -43,7 +43,8 @@
>  
>  #include <complib/cl_list.h>
>  #include <complib/cl_spinlock.h>
> -#include <opensm/osm_log.h>
> +
> +struct osm_log;
>  
>  #ifdef __cplusplus
>  #  define BEGIN_C_DECLS extern "C" {
> @@ -118,7 +119,7 @@ typedef struct osm_db_domain {
>  */
>  typedef struct osm_db {
>  	void *p_db_imp;
> -	osm_log_t *p_log;
> +	struct osm_log *p_log;
>  	cl_list_t domains;
>  } osm_db_t;
>  /*
> @@ -185,7 +186,7 @@ void osm_db_destroy(IN osm_db_t * p_db);
>  *
>  * SYNOPSIS
>  */
> -int osm_db_init(IN osm_db_t * p_db, IN osm_log_t * p_log);
> +int osm_db_init(IN osm_db_t * p_db, IN struct osm_log * p_log);
>  /*
>  * PARAMETERS
>  *
> diff --git a/include/opensm/osm_db_pack.h b/include/opensm/osm_db_pack.h
> index 3d24926..25644df 100644
> --- a/include/opensm/osm_db_pack.h
> +++ b/include/opensm/osm_db_pack.h
> @@ -235,5 +235,149 @@ int osm_db_guid2lid_delete(IN osm_db_domain_t * p_g2l, IN uint64_t guid);
>  * osm_db_guid2lid_get, osm_db_guid2lid_set
>  *********/
>  
> +/****f* OpenSM: DB-Pack/osm_db_guid2mkey_init
> +* NAME
> +*	osm_db_guid2mkey_init
> +*
> +* DESCRIPTION
> +*	Initialize a domain for the guid2mkey table
> +*
> +* SYNOPSIS
> +*/
> +static inline osm_db_domain_t *osm_db_guid2mkey_init(IN osm_db_t * p_db)
> +{
> +	return (osm_db_domain_init(p_db, "guid2mkey"));
> +}
> +
> +/*
> +* PARAMETERS
> +*	p_db
> +*		[in] Pointer to the database object to construct
> +*
> +* RETURN VALUES
> +*	The pointer to the new allocated domain object or NULL.
> +*
> +* NOTE: DB domains are destroyed by the osm_db_destroy
> +*
> +* SEE ALSO
> +*	Database, osm_db_init, osm_db_destroy
> +*********/
> +
> +/****f* OpenSM: DB-Pack/osm_db_guid2mkey_guids
> +* NAME
> +*	osm_db_guid2mkey_guids
> +*
> +* DESCRIPTION
> +*	Provides back a list of guid elements.
> +*
> +* SYNOPSIS
> +*/
> +int osm_db_guid2mkey_guids(IN osm_db_domain_t * p_g2m,
> +			  OUT cl_qlist_t * p_guid_list);
> +/*
> +* PARAMETERS
> +*	p_g2l
> +*		[in] Pointer to the guid2mkey domain
> +*
> +*  p_guid_list
> +*     [out] A quick list of guid elements of type osm_db_guid_elem_t
> +*
> +* RETURN VALUES
> +*	0 if successful
> +*
> +* NOTE: the output qlist should be initialized and each item freed
> +*       by the caller, then destroyed.
> +*
> +* SEE ALSO
> +* osm_db_guid2mkey_init, osm_db_guid2mkey_guids, osm_db_guid2mkey_get
> +* osm_db_guid2mkey_set, osm_db_guid2mkey_delete
> +*********/
> +
> +/****f* OpenSM: DB-Pack/osm_db_guid2mkey_get
> +* NAME
> +*	osm_db_guid2mkey_get
> +*
> +* DESCRIPTION
> +*	Get the mkey for the given guid.
> +*
> +* SYNOPSIS
> +*/
> +int osm_db_guid2mkey_get(IN osm_db_domain_t * p_g2m, IN uint64_t guid,
> +			 OUT uint64_t * p_mkey);
> +/*
> +* PARAMETERS
> +*	p_g2m
> +*		[in] Pointer to the guid2mkey domain
> +*
> +*  guid
> +*     [in] The guid to look for
> +*
> +*  p_mkey
> +*     [out] Pointer to the resulting mkey in host order.
> +*
> +* RETURN VALUES
> +*	0 if successful. The lid will be set to 0 if not found.
> +*
> +* SEE ALSO
> +* osm_db_guid2mkey_init, osm_db_guid2mkey_guids
> +* osm_db_guid2mkey_set, osm_db_guid2mkey_delete
> +*********/
> +
> +/****f* OpenSM: DB-Pack/osm_db_guid2mkey_set
> +* NAME
> +*	osm_db_guid2mkey_set
> +*
> +* DESCRIPTION
> +*	Set the mkey for the given guid.
> +*
> +* SYNOPSIS
> +*/
> +int osm_db_guid2mkey_set(IN osm_db_domain_t * p_g2m, IN uint64_t guid,
> +			 IN uint64_t mkey);
> +/*
> +* PARAMETERS
> +*	p_g2m
> +*		[in] Pointer to the guid2mkey domain
> +*
> +*  guid
> +*     [in] The guid to look for
> +*
> +*  mkey
> +*     [in] The mkey value to set, in host order
> +*
> +* RETURN VALUES
> +*	0 if successful
> +*
> +* SEE ALSO
> +* osm_db_guid2mkey_init, osm_db_guid2mkey_guids
> +* osm_db_guid2mkey_get, osm_db_guid2mkey_delete
> +*********/
> +
> +/****f* OpenSM: DB-Pack/osm_db_guid2mkey_delete
> +* NAME
> +*	osm_db_guid2mkey_delete
> +*
> +* DESCRIPTION
> +*	Delete the entry by the given guid
> +*
> +* SYNOPSIS
> +*/
> +int osm_db_guid2mkey_delete(IN osm_db_domain_t * p_g2m, IN uint64_t guid);
> +/*
> +* PARAMETERS
> +*	p_g2m
> +*		[in] Pointer to the guid2mkey domain
> +*
> +*  guid
> +*     [in] The guid to look for
> +*
> +* RETURN VALUES
> +*	0 if successful otherwise 1
> +*
> +* SEE ALSO
> +* osm_db_guid2mkey_init, osm_db_guid2mkey_guids
> +* osm_db_guid2mkey_get, osm_db_guid2mkey_set
> +*********/
> +
>  END_C_DECLS
>  #endif				/* _OSM_DB_PACK_H_ */
> diff --git a/include/opensm/osm_port.h b/include/opensm/osm_port.h
> index 56e9c37..6b73cc7 100644
> --- a/include/opensm/osm_port.h
> +++ b/include/opensm/osm_port.h
> @@ -66,6 +66,7 @@ BEGIN_C_DECLS
>  struct osm_port;
>  struct osm_node;
>  struct osm_mgrp;
> +struct osm_sm;
>  
>  /****h* OpenSM/Physical Port
>  * NAME
> @@ -431,22 +432,9 @@ static inline void osm_physp_set_health(IN osm_physp_t * p_physp,
>  *
>  * SYNOPSIS
>  */
> -static inline void osm_physp_set_port_info(IN osm_physp_t * p_physp,
> -					   IN const ib_port_info_t * p_pi)
> -{
> -	CL_ASSERT(p_pi);
> -	CL_ASSERT(osm_physp_is_valid(p_physp));
> -
> -	if (ib_port_info_get_port_state(p_pi) == IB_LINK_DOWN) {
> -		/* If PortState is down, only copy PortState */
> -		/* and PortPhysicalState per C14-24-2.1 */
> -		ib_port_info_set_port_state(&p_physp->port_info, IB_LINK_DOWN);
> -		ib_port_info_set_port_phys_state
> -		    (ib_port_info_get_port_phys_state(p_pi),
> -		     &p_physp->port_info);
> -	} else
> -		p_physp->port_info = *p_pi;
> -}
> +void osm_physp_set_port_info(IN osm_physp_t * p_physp,
> +					   IN const ib_port_info_t * p_pi,
> +					   IN const struct osm_sm * p_sm);
>  
>  /*
>  * PARAMETERS
> @@ -456,6 +444,9 @@ static inline void osm_physp_set_port_info(IN osm_physp_t * p_physp,
>  *	p_pi
>  *		[in] Pointer to the IBA defined PortInfo at this port number.
>  *
> +* 	p_sm
> +* 		[in] Pointer to an osm_sm_t object.
> +*
>  * RETURN VALUES
>  *	This function does not return a value.
>  *
> diff --git a/include/opensm/osm_subnet.h b/include/opensm/osm_subnet.h
> index 838ca82..c13d0c8 100644
> --- a/include/opensm/osm_subnet.h
> +++ b/include/opensm/osm_subnet.h
> @@ -54,6 +54,7 @@
>  #include <complib/cl_list.h>
>  #include <opensm/osm_base.h>
>  #include <opensm/osm_prefix_route.h>
> +#include <opensm/osm_db.h>
>  #include <stdio.h>
>  
>  #ifdef __cplusplus
> @@ -600,6 +601,7 @@ typedef struct osm_subn {
>  	boolean_t sweeping_enabled;
>  	unsigned need_update;
>  	cl_fmap_t mgrp_mgid_tbl;
> +	osm_db_domain_t *p_g2m;
>  	void *mboxes[IB_LID_MCAST_END_HO - IB_LID_MCAST_START_HO + 1];
>  	osm_log_level_t per_mod_log_tbl[256];
>  } osm_subn_t;
> diff --git a/opensm/osm_db_files.c b/opensm/osm_db_files.c
> index 7ab6b56..9f338f3 100644
> --- a/opensm/osm_db_files.c
> +++ b/opensm/osm_db_files.c
> @@ -50,6 +50,7 @@
>  #define FILE_ID OSM_FILE_DB_FILES_C
>  #include <opensm/st.h>
>  #include <opensm/osm_db.h>
> +#include <opensm/osm_log.h>
>  
>  /****d* Database/OSM_DB_MAX_LINE_LEN
>   * NAME
> diff --git a/opensm/osm_db_pack.c b/opensm/osm_db_pack.c
> index c1ec4ab..57c3a66 100644
> --- a/opensm/osm_db_pack.c
> +++ b/opensm/osm_db_pack.c
> @@ -85,6 +85,17 @@ static inline int unpack_lids(IN char *p_lid_str, OUT uint16_t * p_min_lid,
>  	return 0;
>  }
>  
> +static inline void pack_mkey(uint64_t mkey, char *p_mkey_str)
> +{
> +	sprintf(p_mkey_str, "0x%016" PRIx64, mkey);
> +}
> +
> +static inline uint64_t unpack_mkey(char *p_mkey_str)
> +{
> +	return strtoull(p_mkey_str, NULL, 0);
> +}
> +
> +
>  int osm_db_guid2lid_guids(IN osm_db_domain_t * p_g2l,
>  			  OUT cl_qlist_t * p_guid_list)
>  {
> @@ -151,3 +162,65 @@ int osm_db_guid2lid_delete(IN osm_db_domain_t * p_g2l, IN uint64_t guid)
>  	pack_guid(guid, guid_str);
>  	return osm_db_delete(p_g2l, guid_str);
>  }
> +
> +int osm_db_guid2mkey_guids(IN osm_db_domain_t * p_g2m,
> +			   OUT cl_qlist_t * p_guid_list)
> +{
> +	char *p_key;
> +	cl_list_t keys;
> +	osm_db_guid_elem_t *p_guid_elem;
> +
> +	cl_list_construct(&keys);
> +	cl_list_init(&keys, 10);
> +
> +	if (osm_db_keys(p_g2m, &keys))
> +		return 1;
> +
> +	while ((p_key = cl_list_remove_head(&keys)) != NULL) {
> +		p_guid_elem =
> +		    (osm_db_guid_elem_t *) malloc(sizeof(osm_db_guid_elem_t));
> +		CL_ASSERT(p_guid_elem != NULL);
> +
> +		p_guid_elem->guid = unpack_guid(p_key);
> +		cl_qlist_insert_head(p_guid_list, &p_guid_elem->item);
> +	}
> +
> +	cl_list_destroy(&keys);
> +	return 0;
> +}
> +
> +int osm_db_guid2mkey_get(IN osm_db_domain_t * p_g2m, IN uint64_t guid,
> +			 OUT uint64_t * p_mkey)
> +{
> +	char guid_str[20];
> +	char *p_mkey_str;
> +
> +	pack_guid(guid, guid_str);
> +	p_mkey_str = osm_db_lookup(p_g2m, guid_str);
> +	if (!p_mkey_str)
> +		return 1;
> +
> +	if (p_mkey)
> +		*p_mkey = unpack_mkey(p_mkey_str);
> +
> +	return 0;
> +}
> +
> +int osm_db_guid2mkey_set(IN osm_db_domain_t * p_g2m, IN uint64_t guid,
> +			 IN uint64_t mkey)
> +{
> +	char guid_str[20];
> +	char mkey_str[20];
> +
> +	pack_guid(guid, guid_str);
> +	pack_mkey(mkey, mkey_str);
> +
> +	return osm_db_update(p_g2m, guid_str, mkey_str);
> +}
> +
> +int osm_db_guid2mkey_delete(IN osm_db_domain_t * p_g2m, IN uint64_t guid)
> +{
> +	char guid_str[20];
> +	pack_guid(guid, guid_str);
> +	return osm_db_delete(p_g2m, guid_str);
> +}
> diff --git a/opensm/osm_lid_mgr.c b/opensm/osm_lid_mgr.c
> index cb7ff0b..7799ee3 100644
> --- a/opensm/osm_lid_mgr.c
> +++ b/opensm/osm_lid_mgr.c
> @@ -800,6 +800,7 @@ static int lid_mgr_set_physp_pi(IN osm_lid_mgr_t * p_mgr,
>  	uint8_t op_vls;
>  	uint8_t port_num;
>  	boolean_t send_set = FALSE;
> +	boolean_t update_mkey = FALSE;
>  	int ret = 0;
>  
>  	OSM_LOG_ENTER(p_mgr->p_log);
> @@ -862,8 +863,10 @@ static int lid_mgr_set_physp_pi(IN osm_lid_mgr_t * p_mgr,
>  		send_set = TRUE;
>  
>  	p_pi->m_key = p_mgr->p_subn->opt.m_key;
> -	if (memcmp(&p_pi->m_key, &p_old_pi->m_key, sizeof(p_pi->m_key)))
> +	if (memcmp(&p_pi->m_key, &p_old_pi->m_key, sizeof(p_pi->m_key))) {
> +		update_mkey = TRUE;
>  		send_set = TRUE;
> +	}
>  
>  	p_pi->subnet_prefix = p_mgr->p_subn->opt.subnet_prefix;
>  	if (memcmp(&p_pi->subnet_prefix, &p_old_pi->subnet_prefix,
> @@ -1053,6 +1056,13 @@ static int lid_mgr_set_physp_pi(IN osm_lid_mgr_t * p_mgr,
>  			     CL_DISP_MSGID_NONE, &context);
>  	if (status != IB_SUCCESS)
>  		ret = -1;
> +	/* If we sent a new mkey above, update our guid2mkey map
> +	   now, on the assumption that the SubnSet succeeds
> +	*/
> +	if (update_mkey)
> +		osm_db_guid2mkey_set(p_mgr->p_subn->p_g2m,
> +				     cl_ntoh64(p_physp->port_guid),
> +				     cl_ntoh64(p_pi->m_key));
>  
>  Exit:
>  	OSM_LOG_EXIT(p_mgr->p_log);
> diff --git a/opensm/osm_link_mgr.c b/opensm/osm_link_mgr.c
> index 8301643..50393c5 100644
> --- a/opensm/osm_link_mgr.c
> +++ b/opensm/osm_link_mgr.c
> @@ -56,6 +56,7 @@
>  #include <opensm/osm_helper.h>
>  #include <opensm/osm_msgdef.h>
>  #include <opensm/osm_opensm.h>
> +#include <opensm/osm_db_pack.h>
>  
>  static uint8_t link_mgr_get_smsl(IN osm_sm_t * sm, IN osm_physp_t * p_physp)
>  {
> @@ -104,6 +105,7 @@ static int link_mgr_set_physp_pi(osm_sm_t * sm, IN osm_physp_t * p_physp,
>  	int qdr_change = 0, fdr10_change = 0;
>  	int ret = 0;
>  	ib_net32_t attr_mod, cap_mask;
> +	boolean_t update_mkey = FALSE;
>  
>  	OSM_LOG_ENTER(sm->p_log);
>  
> @@ -194,8 +196,10 @@ static int link_mgr_set_physp_pi(osm_sm_t * sm, IN osm_physp_t * p_physp,
>  		    port_num == 0) {
>  			p_pi->m_key = sm->p_subn->opt.m_key;
>  			if (memcmp(&p_pi->m_key, &p_old_pi->m_key,
> -				   sizeof(p_pi->m_key)))
> +				   sizeof(p_pi->m_key))) {
> +				update_mkey = TRUE;
>  				send_set = TRUE;
> +			}
>  
>  			p_pi->subnet_prefix = sm->p_subn->opt.subnet_prefix;
>  			if (memcmp(&p_pi->subnet_prefix,
> @@ -466,6 +470,14 @@ Send:
>  	if (status)
>  		ret = -1;
>  
> +	/* If we sent a new mkey above, update our guid2mkey map
> + 	   now, on the assumption that the SubnSet succeeds
> +	 */
> +	if (update_mkey)
> +		osm_db_guid2mkey_set(sm->p_subn->p_g2m,
> +				     cl_ntoh64(p_physp->port_guid),
> +				     cl_ntoh64(p_pi->m_key));
> +
>  	if (send_set2) {
>  		status = osm_req_set(sm, osm_physp_get_dr_path_ptr(p_physp),
>  				     payload2, sizeof(payload2),
> diff --git a/opensm/osm_opensm.c b/opensm/osm_opensm.c
> index 429108a..42cbb36 100644
> --- a/opensm/osm_opensm.c
> +++ b/opensm/osm_opensm.c
> @@ -413,6 +413,11 @@ ib_api_status_t osm_opensm_init(IN osm_opensm_t * p_osm,
>  	if (status != IB_SUCCESS)
>  		goto Exit;
>  
> +	/* the DB is in use by subn so init before */
> +	status = osm_db_init(&p_osm->db, &p_osm->log);
> +	if (status != IB_SUCCESS)
> +		goto Exit;
> +
>  	status = osm_subn_init(&p_osm->subn, p_osm, p_opt);
>  	if (status != IB_SUCCESS)
>  		goto Exit;
> @@ -435,11 +440,6 @@ ib_api_status_t osm_opensm_init(IN osm_opensm_t * p_osm,
>  	if (status != IB_SUCCESS)
>  		goto Exit;
>  
> -	/* the DB is in use by the SM and SA so init before */
> -	status = osm_db_init(&p_osm->db, &p_osm->log);
> -	if (status != IB_SUCCESS)
> -		goto Exit;
> -
>  	status = osm_sm_init(&p_osm->sm, &p_osm->subn, &p_osm->db,
>  			     p_osm->p_vendor, &p_osm->mad_pool, &p_osm->vl15,
>  			     &p_osm->log, &p_osm->stats, &p_osm->disp,
> diff --git a/opensm/osm_port.c b/opensm/osm_port.c
> index 88b9fd8..0730c14 100644
> --- a/opensm/osm_port.c
> +++ b/opensm/osm_port.c
> @@ -54,6 +54,8 @@
>  #include <opensm/osm_node.h>
>  #include <opensm/osm_madw.h>
>  #include <opensm/osm_switch.h>
> +#include <opensm/osm_db_pack.h>
> +#include <opensm/osm_sm.h>
>  
>  void osm_physp_construct(IN osm_physp_t * p_physp)
>  {
> @@ -659,3 +661,33 @@ void osm_alias_guid_delete(IN OUT osm_alias_guid_t ** pp_alias_guid)
>  	free(*pp_alias_guid);
>  	*pp_alias_guid = NULL;
>  }
> +
> +void osm_physp_set_port_info(IN osm_physp_t * p_physp,
> +					   IN const ib_port_info_t * p_pi,
> +					   IN const struct osm_sm * p_sm)
> +{
> +	CL_ASSERT(p_pi);
> +	CL_ASSERT(osm_physp_is_valid(p_physp));
> +
> +	if (ib_port_info_get_port_state(p_pi) == IB_LINK_DOWN) {
> +		/* If PortState is down, only copy PortState */
> +		/* and PortPhysicalState per C14-24-2.1 */
> +		ib_port_info_set_port_state(&p_physp->port_info, IB_LINK_DOWN);
> +		ib_port_info_set_port_phys_state
> +		    (ib_port_info_get_port_phys_state(p_pi),
> +		     &p_physp->port_info);
> +	} else {
> +		p_physp->port_info = *p_pi;
> +
> +		/* The MKey in p_pi can only be considered valid if it's
> +		 * for a HCA/router or switch port 0, and it's either
> +		 * non-zero or the MKeyProtect bits are also zero.
> +		 */
> +		if ((osm_node_get_type(p_physp->p_node) != IB_NODE_TYPE_SWITCH ||
> +		     p_physp->port_num == 0) &&
> +		    (p_pi->m_key != 0 || ib_port_info_get_mpb(p_pi) == 0)) 
> +			osm_db_guid2mkey_set(p_sm->p_subn->p_g2m,
> +				     	     cl_ntoh64(p_physp->port_guid),
> +					     cl_ntoh64(p_pi->m_key));
> +	}
> +}
> diff --git a/opensm/osm_port_info_rcv.c b/opensm/osm_port_info_rcv.c
> index ab7418b..00cbfc7 100644
> --- a/opensm/osm_port_info_rcv.c
> +++ b/opensm/osm_port_info_rcv.c
> @@ -312,7 +312,7 @@ static void pi_rcv_process_switch_port(IN osm_sm_t * sm, IN osm_node_t * p_node,
>  	/*
>  	   Update the PortInfo attribute.
>  	 */
> -	osm_physp_set_port_info(p_physp, p_pi);
> +	osm_physp_set_port_info(p_physp, p_pi, sm);
>  
>  	if (port_num == 0) {
>  		/* Determine if base switch port 0 */
> @@ -337,7 +337,7 @@ static void pi_rcv_process_ca_or_router_port(IN osm_sm_t * sm,
>  
>  	pi_rcv_check_and_fix_lid(sm->p_log, p_pi, p_physp);
>  
> -	osm_physp_set_port_info(p_physp, p_pi);
> +	osm_physp_set_port_info(p_physp, p_pi, sm);
>  
>  	pi_rcv_process_endport(sm, p_physp, p_pi);
>  
> @@ -475,7 +475,7 @@ static void pi_rcv_process_set(IN osm_sm_t * sm, IN osm_node_t * p_node,
>  		cl_ntoh64(osm_node_get_node_guid(p_node)),
>  		cl_ntoh64(p_smp->trans_id));
>  
> -	osm_physp_set_port_info(p_physp, p_pi);
> +	osm_physp_set_port_info(p_physp, p_pi, sm);
>  
>  	OSM_LOG_EXIT(sm->p_log);
>  }
> diff --git a/opensm/osm_req.c b/opensm/osm_req.c
> index 2532f9c..51220f3 100644
> --- a/opensm/osm_req.c
> +++ b/opensm/osm_req.c
> @@ -58,6 +58,7 @@
>  #include <opensm/osm_vl15intf.h>
>  #include <opensm/osm_msgdef.h>
>  #include <opensm/osm_opensm.h>
> +#include <opensm/osm_db_pack.h>
>  
>  /**********************************************************************
>    The plock MAY or MAY NOT be held before calling this function.
> diff --git a/opensm/osm_state_mgr.c b/opensm/osm_state_mgr.c
> index 143b744..74114af 100644
> --- a/opensm/osm_state_mgr.c
> +++ b/opensm/osm_state_mgr.c
> @@ -66,6 +66,7 @@
>  #include <vendor/osm_vendor_api.h>
>  #include <opensm/osm_inform.h>
>  #include <opensm/osm_opensm.h>
> +#include <opensm/osm_db.h>
>  
>  extern void osm_drop_mgr_process(IN osm_sm_t * sm);
>  extern int osm_qos_setup(IN osm_opensm_t * p_osm);
> @@ -1440,6 +1441,9 @@ repeat_discovery:
>  	if (sm->p_subn->force_heavy_sweep
>  	    || sm->p_subn->subnet_initialization_error)
>  		osm_sm_signal(sm, OSM_SIGNAL_SWEEP);
> +
> +	/* Write a new copy of our persistent guid2mkey database */
> +	osm_db_store(sm->p_subn->p_g2m);
>  }
>  
>  static void do_process_mgrp_queue(osm_sm_t * sm)
> diff --git a/opensm/osm_subnet.c b/opensm/osm_subnet.c
> index 7fb5c8f..47a5606 100644
> --- a/opensm/osm_subnet.c
> +++ b/opensm/osm_subnet.c
> @@ -75,6 +75,8 @@
>  #include <opensm/osm_event_plugin.h>
>  #include <opensm/osm_qos_policy.h>
>  #include <opensm/osm_service.h>
> +#include <opensm/osm_db.h>
> +#include <opensm/osm_db_pack.h>
>  
>  static const char null_str[] = "(null)";
>  
> @@ -538,6 +540,52 @@ static int compar_mgids(const void *m1, const void *m2)
>  	return memcmp(m1, m2, sizeof(ib_gid_t));
>  }
>  
> +static void subn_validate_g2m(osm_subn_t *p_subn)
> +{
> +	cl_qlist_t guids;
> +	osm_db_guid_elem_t *p_item;
> +	uint64_t mkey;
> +	boolean_t valid_entry;
> +
> +	OSM_LOG_ENTER(&(p_subn->p_osm->log));
> +	cl_qlist_init(&guids);
> +
> +	if (osm_db_guid2mkey_guids(p_subn->p_g2m, &guids)) {
> +		OSM_LOG(&(p_subn->p_osm->log), OSM_LOG_ERROR, "ERR 7506: "
> +			"could not get mkey guid list\n");
> +		goto Exit;
> +	}
> +
> +	while ((p_item = (osm_db_guid_elem_t *) cl_qlist_remove_head(&guids))
> +	       != (osm_db_guid_elem_t *) cl_qlist_end(&guids)) {
> +		valid_entry = TRUE;
> +
> +		if (p_item->guid == 0) {
> +			OSM_LOG(&(p_subn->p_osm->log), OSM_LOG_ERROR,
> +				"ERR 7507: found invalid zero guid");
> +			valid_entry = FALSE;
> +		} else if (osm_db_guid2mkey_get(p_subn->p_g2m, p_item->guid,
> +						&mkey)) {
> +			OSM_LOG(&(p_subn->p_osm->log), OSM_LOG_ERROR,
> +				"ERR 7508: could not get mkey for guid:0x%016"
> +				PRIx64 "\n", p_item->guid);
> +			valid_entry = FALSE;
> +		}
> +
> +		if (valid_entry == FALSE) {
> +			if (osm_db_guid2mkey_delete(p_subn->p_g2m,
> +                                                        p_item->guid))
> +                                OSM_LOG(&(p_subn->p_osm->log), OSM_LOG_ERROR,
> +                                        "ERR 7509: failed to delete entry for "
> +                                        "guid:0x%016" PRIx64 "\n",
> +                                        p_item->guid);
> +		}
> +	}
> +
> +Exit:
> +	OSM_LOG_EXIT(&(p_subn->p_osm->log));
> +}
> +
>  void osm_subn_construct(IN osm_subn_t * p_subn)
>  {
>  	memset(p_subn, 0, sizeof(*p_subn));
> @@ -744,6 +792,35 @@ ib_api_status_t osm_subn_init(IN osm_subn_t * p_subn, IN osm_opensm_t * p_osm,
>  	p_subn->sweeping_enabled = TRUE;
>  	p_subn->last_sm_port_state = 1;
>  
> +	/* Initialize the guid2mkey database */
> +	p_subn->p_g2m = osm_db_domain_init(&(p_osm->db), "guid2mkey");
> +	if (!p_subn->p_g2m) {
> +		OSM_LOG(&(p_osm->log), OSM_LOG_ERROR, "ERR 7510: "
> +			"Error initializing Guid-to-MKey persistent database\n");
> +		return IB_ERROR;
> +	}
> +
> +	if (osm_db_restore(p_subn->p_g2m)) {
> +#ifndef __WIN__
> +		/*
> +		 * When Windows is BSODing, it might corrupt files that
> +		 * were previously opened for writing, even if the files
> +		 * are closed, so we might see corrupted guid2mkey file.
> +		 */
> +		if (p_subn->opt.exit_on_fatal) {
> +			osm_log(&(p_osm->log), OSM_LOG_SYS, 
> +				"FATAL: Error restoring Guid-to-Mkey "
> +				"persistent database\n");
> +			return IB_ERROR;
> +		} else
> +#endif
> +			OSM_LOG(&(p_osm->log), OSM_LOG_ERROR,
> +				"ERR 7511: Error restoring Guid-to-Mkey "
> +				"persistent database\n");
> +	}
> +
> +	subn_validate_g2m(p_subn);
> +
>  	return IB_SUCCESS;
>  }
>  
> -- 
> 1.7.9.2
> 
> --
> 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