NTB: ntb_transport: Free MWs in ntb_transport_link_cleanup()
PATCH 1/1 NTB: ntb_transport: Free MWs in ntb_transport_link_cleanup()
If NTB peer host crashes or reboots, the NTB transport link will be down and the MWs of NTB transport will be invalid. But the ntb_transport_link_cleanup() does not free these invalid MWs. When the NTB peer host is recovered later, NTB transport link will be up and the ntb_set_mw() will not reset up MWs. Because the MWs of NTB transport are invalid, the NTB transport will not work.
We can fix it by freeing MWs when NTB transport link is down, then the ntb_set_mw() will reset up MWs when NTB transport link is up.
--- drivers/ntb/ntb_transport.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/ntb/ntb_transport.c +3 -0
@@ -862,6 +862,9 @@ static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)if (!nt->link_is_up)cancel_delayed_work_sync (&nt->link_work); +for (i =0 ; i < nt->mw_count; i++) +ntb_free_mw (nt, i); +/* The scratchpad registers keep the values if the remote side * goes down, blast them now to give them a sane value the next * time they are accessed
Signature · 1 line
2.7.4
Quoted 11 lines · Joey Zhang
If NTB peer host crashes or reboots, the NTB transport link will be down and the MWs of NTB transport will be invalid. But the
ntb_transport_link_cleanup()does not free these invalid MWs. When the NTB peer host is recovered later, NTB transport link will be up and thentb_set_mw()will not reset up MWs. Because the MWs of NTB transport are invalid, the NTB transport will not work.We can fix it by freeing MWs when NTB transport link is down, then the
ntb_set_mw()will reset up MWs when NTB transport link is up.Signed-off-by Joey Zhang <[email protected]>
Looks ok to me.
Reviewed By: Logan Gunthorpe <[email protected]>
Quoted 19 lines
--- drivers/ntb/ntb_transport.c | 3 +++ 1 file changed, 3 insertions(+)drivers/ntb/ntb_transport.c +3
-0@@ -862,6 +862,9 @@ static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)if (!nt->link_is_up)cancel_delayed_work_sync (&nt->link_work); +for (i =0 ; i < nt->mw_count; i++) +ntb_free_mw (nt, i); +/* The scratchpad registers keep the values if the remote side * goes down, blast them now to give them a sane value the next * time they are accessed
Jon Mason
maintainerQuoted 10 lines · Logan Gunthorpe
Quoted 7 lines · Joey Zhang
If NTB peer host crashes or reboots, the NTB transport link will be down and the MWs of NTB transport will be invalid. But the
ntb_transport_link_cleanup()does not free these invalid MWs. When the NTB peer host is recovered later, NTB transport link will be up and thentb_set_mw()will not reset up MWs. Because the MWs of NTB transport are invalid, the NTB transport will not work.
Quoted 6 lines
Quoted 4 lines
We can fix it by freeing MWs when NTB transport link is down, then the
ntb_set_mw()will reset up MWs when NTB transport link is up.Signed-off-by Joey Zhang <[email protected]>Looks ok to me.
Added to the ntb branch, thanks!
Quoted 1 line
Reviewed By: Logan Gunthorpe <[email protected]>
Looks like your missed the '-' ;-)
I took the liberity of adding it
Thanks,
Jon
Quoted 20 lines
Quoted 20 lines
--- drivers/ntb/ntb_transport.c | 3 +++ 1 file changed, 3 insertions(+)drivers/ntb/ntb_transport.c +3
-0@@ -862,6 +862,9 @@ static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)if (!nt->link_is_up)cancel_delayed_work_sync (&nt->link_work); +for (i =0 ; i < nt->mw_count; i++) +ntb_free_mw (nt, i); +/* The scratchpad registers keep the values if the remote side * goes down, blast them now to give them a sane value the next * time they are accessed