nvme: find numa distance only if controller has valid numa id
PATCH v2 1/1 nvme: find numa distance only if controller has valid numa id
On system where native nvme multipath is configured and iopolicy is set to numa but the nvme controller numa node id is undefined or -1 (NUMA_NO_NODE) then avoid calculating node distance for finding optimal io path. In such case we may access numa distance table with invalid index and that may potentially refer to incorrect memory. So this patch ensures that if the nvme controller numa node id is -1 then instead of calculating node distance for finding optimal io path, we set the numa node distance of such controller to default 10 (LOCAL_DISTANCE).
---
Changes from v1:
Formatting cleanups (Christoph)
drivers/nvme/host/multipath.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/nvme/host/multipath.c +2 -1
@@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)if (nvme_path_is_disabled (ns))continue ; -if (READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA ) +if (ns->ctrl->numa_node !=NUMA_NO_NODE && +READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA ) distance =node_distance (node, ns->ctrl->numa_node);else distance =LOCAL_DISTANCE ;
Signature · 1 line
2.44.0
Quoted 24 lines · Nilay Shroff
On system where native nvme multipath is configured and iopolicy is set to numa but the nvme controller numa node id is undefined or -1 (
NUMA_NO_NODE) then avoid calculating node distance for finding optimal io path. In such case we may access numa distance table with invalid index and that may potentially refer to incorrect memory. So this patch ensures that if the nvme controller numa node id is -1 then instead of calculating node distance for finding optimal io path, we set the numa node distance of such controller to default 10 (LOCAL_DISTANCE).Signed-off-by Nilay Shroff <[email protected]>---
Changes from v1:
Formatting cleanups (Christoph)drivers/nvme/host/multipath.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)drivers/nvme/host/multipath.c +0
-0
drivers/nvme/host/multipath.c static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) · line 251
Quoted 6 lines
drivers/nvme/host/multipath.c +2
-1@@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)if (nvme_path_is_disabled (ns))continue ; -if (READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA ) +if (ns->ctrl->numa_node !=NUMA_NO_NODE && +READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA )
unless something is wrong when I apply this patch, above line should be kept under 80 char ?
something like following totally untested :-
drivers/nvme/host/multipath.c +0 -0
@@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct
nvme_ns_head *head, int node)
if (nvme_path_is_disabled(ns))
continue;
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) + if (ns->ctrl->numa_node != NUMA_NO_NODE &&
+ READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
distance = node_distance(node,ns->ctrl->numa_node);
else
distance = LOCAL_DISTANCE;
-ck
Quoted 54 lines · Chaitanya Kulkarni
Quoted 24 lines · Nilay Shroff
On system where native nvme multipath is configured and iopolicy is set to numa but the nvme controller numa node id is undefined or -1 (
NUMA_NO_NODE) then avoid calculating node distance for finding optimal io path. In such case we may access numa distance table with invalid index and that may potentially refer to incorrect memory. So this patch ensures that if the nvme controller numa node id is -1 then instead of calculating node distance for finding optimal io path, we set the numa node distance of such controller to default 10 (LOCAL_DISTANCE).Signed-off-by Nilay Shroff <[email protected]>---
Changes from v1:
Formatting cleanups (Christoph)drivers/nvme/host/multipath.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)drivers/nvme/host/multipath.c +0
-0drivers/nvme/host/multipath.c static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) · line 251
Quoted 6 lines
drivers/nvme/host/multipath.c +2
-1@@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)if (nvme_path_is_disabled (ns))continue ; -if (READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA ) +if (ns->ctrl->numa_node !=NUMA_NO_NODE && +READ_ONCE (head->subsys->iopolicy) ==NVME_IOPOLICY_NUMA )unless something is wrong when I apply this patch, above line should be kept under 80 char ?
something like following totally untested :-
drivers/nvme/host/multipath.c +2
-1@@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) if (nvme_path_is_disabled(ns)) continue; - if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) + if (ns->ctrl->numa_node != NUMA_NO_NODE && + READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) distance = node_distance(node, ns->ctrl->numa_node);else
distance =LOCAL_DISTANCE;
Quoted 3 lines
-ck
I don't know but checkpatch.pl didn't complain about my patch overshooting 80 chars width. Anyways, I will reformat the patch and resend.
Thanks,
--Nilay
Quoted 5 lines · Nilay Shroff
I don't know but checkpatch.pl didn't complain about my patch overshooting 80 chars width. Anyways, I will reformat the patch and resend.
Thanks,
--Nilay
checkpatch doesn't warn that anymore from what I remember, I've been victim of relying on checkpatch then corrected on the list about 80 char.
-ck