nvme: remove stale namespaces by NSID range during scan
PATCH v2 1/1 nvme: remove stale namespaces by NSID range during scan
nvme_scan_ns_list() drops the stale namespaces in each gap in the reported NSID list one NSID at a time. Every iteration calls nvme_find_get_ns() to look the namespace up and removes it if it is present. The loop runs once per NSID in the gap rather than once per namespace actually present.
NSIDs are 32-bit, so a target with a sparse NSID space can make a single gap spin the loop billions of times with nothing to remove.
watchdog: BUG: soft lockup - CPU#4 stuck for 26s! Workqueue: nvme-wq nvme_scan_work [nvme_core] RIP: 0010:__srcu_read_unlock+0xb/0x20 Call Trace: nvme_find_get_ns+0x7d/0xb0 [nvme_core] nvme_scan_ns_list+0xe8/0x280 [nvme_core] nvme_scan_work+0x18a/0x280 [nvme_core] process_one_work+0x197/0x380 worker_thread+0x2fe/0x410 kthread+0xe0/0x100
Rename nvme_remove_invalid_namespaces() to nvme_remove_nsid_range() and give it an open (start, end) NSID range. ctrl->namespaces is sorted by NSID, so the whole gap is dropped in a single walk that stops once end is reached. This bounds the work by the namespaces that are present instead of by the size of the gap.
--- drivers/nvme/host/core.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)
drivers/nvme/host/core.c +9 -9
@@ -155,8 +155,6 @@ static const struct class nvme_ns_chr_class = { };static void nvme_put_subsystem (struct nvme_subsystem *subsys); -static void nvme_remove_invalid_namespaces (struct nvme_ctrl *ctrl, -unsigned nsid);static void nvme_update_keep_alive (struct nvme_ctrl *ctrl,struct nvme_command *cmd); static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page,
@@ -4513,15 +4511,16 @@ static void nvme_scan_ns_async(void *data, async_cookie_t cookie)nvme_scan_ns (scan_info->ctrl, nsid); } -static void nvme_remove_invalid_namespaces (struct nvme_ctrl *ctrl, -unsigned nsid) +static void nvme_remove_nsid_range (struct nvme_ctrl *ctrl,u32 start,u32 end) {struct nvme_ns *ns, *next;LIST_HEAD (rm_list);mutex_lock (&ctrl->namespaces_lock);list_for_each_entry_safe (ns, next, &ctrl->namespaces, list) { -if (ns->head->ns_id > nsid) { +if (ns->head->ns_id >= end) +break ; +if (ns->head->ns_id > start) {list_del_rcu (&ns->list);synchronize_srcu (&ctrl->srcu);list_add_tail_rcu (&ns->list, &rm_list);
@@ -4571,13 +4570,14 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) goto out;async_schedule_domain (nvme_scan_ns_async, &scan_info, &domain); -while (++prev < nsid) -nvme_ns_remove_by_nsid (ctrl, prev); +if (prev +1 < nsid) +nvme_remove_nsid_range (ctrl, prev, nsid); + prev =max (prev +1 , nsid); }async_synchronize_full_domain (&domain); } out: -nvme_remove_invalid_namespaces (ctrl, prev); +nvme_remove_nsid_range (ctrl, prev,UINT_MAX ); free:async_synchronize_full_domain (&domain);kfree (ns_list);
@@ -4597,7 +4597,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl)for (i =1 ; i <= nn; i++)nvme_scan_ns (ctrl, i); -nvme_remove_invalid_namespaces (ctrl, nn); +nvme_remove_nsid_range (ctrl, nn,UINT_MAX ); }static void nvme_clear_changed_ns_log (struct nvme_ctrl *ctrl)
Signature · 1 line
2.54.0
Quoted 27 lines · Mohamed Khalfella
nvme_scan_ns_list()drops the stale namespaces in each gap in the reported NSID list one NSID at a time. Every iteration callsnvme_find_get_ns()to look the namespace up and removes it if it is present. The loop runs once per NSID in the gap rather than once per namespace actually present.NSIDs are 32-bit, so a target with a sparse NSID space can make a single gap spin the loop billions of times with nothing to remove.
watchdog: BUG: soft lockup - CPU#4 stuck for 26s! Workqueue: nvme-wq nvme_scan_work [nvme_core] RIP: 0010:__srcu_read_unlock+0xb/0x20 Call Trace: nvme_find_get_ns+0x7d/0xb0 [nvme_core] nvme_scan_ns_list+0xe8/0x280 [nvme_core] nvme_scan_work+0x18a/0x280 [nvme_core] process_one_work+0x197/0x380 worker_thread+0x2fe/0x410 kthread+0xe0/0x100Rename
nvme_remove_invalid_namespaces()tonvme_remove_nsid_range()and give it an open (start, end) NSID range.ctrl->namespacesis sorted by NSID, so the whole gap is dropped in a single walk that stops once end is reached. This bounds the work by the namespaces that are present instead of by the size of the gap.
Quoted 3 lines
Fixes 540c801c65eb ("NVMe: Implement namespace list scanning")Signed-off-by Mohamed Khalfella <[email protected]>Reviewed-by Sagi Grimberg <[email protected]>
drivers/nvme/host/core.c static void nvme_scan_ns_async(void *data, async_cookie_t cookie) · line 4514
Quoted 6 lines
--- drivers/nvme/host/core.c | 18 +++++++++---------drivers/nvme/host/core.c +1
-2-static void nvme_remove_invalid_namespaces (struct nvme_ctrl *ctrl, -unsigned nsid) +static void nvme_remove_nsid_range (struct nvme_ctrl *ctrl,u32 start,u32 end)
It is not intuitive to me that start is non-inclusive. May we add a comment to that effect?
Quoted 11 lines
{ struct nvme_ns *ns, *next; LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {drivers/nvme/host/core.c +3
-1-if (ns->head->ns_id > nsid) { +if (ns->head->ns_id >= end) +break ; +if (ns->head->ns_id > start) {list_del_rcu (&ns->list);
Quoted 34 lines · Randy Jennings
Quoted 27 lines · Mohamed Khalfella
nvme_scan_ns_list()drops the stale namespaces in each gap in the reported NSID list one NSID at a time. Every iteration callsnvme_find_get_ns()to look the namespace up and removes it if it is present. The loop runs once per NSID in the gap rather than once per namespace actually present.NSIDs are 32-bit, so a target with a sparse NSID space can make a single gap spin the loop billions of times with nothing to remove.
watchdog: BUG: soft lockup - CPU#4 stuck for 26s! Workqueue: nvme-wq nvme_scan_work [nvme_core] RIP: 0010:__srcu_read_unlock+0xb/0x20 Call Trace: nvme_find_get_ns+0x7d/0xb0 [nvme_core] nvme_scan_ns_list+0xe8/0x280 [nvme_core] nvme_scan_work+0x18a/0x280 [nvme_core] process_one_work+0x197/0x380 worker_thread+0x2fe/0x410 kthread+0xe0/0x100Rename
nvme_remove_invalid_namespaces()tonvme_remove_nsid_range()and give it an open (start, end) NSID range.ctrl->namespacesis sorted by NSID, so the whole gap is dropped in a single walk that stops once end is reached. This bounds the work by the namespaces that are present instead of by the size of the gap.Quoted 3 lines
Fixes 540c801c65eb ("NVMe: Implement namespace list scanning")Signed-off-by Mohamed Khalfella <[email protected]>Reviewed-by Sagi Grimberg <[email protected]>Reviewed-by Randy Jennings <[email protected]>
Quoted 8 lines
drivers/nvme/host/core.c static void nvme_scan_ns_async(void *data, async_cookie_t cookie) · line 4514
Quoted 6 lines
--- drivers/nvme/host/core.c | 18 +++++++++---------drivers/nvme/host/core.c +1
-2-static void nvme_remove_invalid_namespaces (struct nvme_ctrl *ctrl, -unsigned nsid) +static void nvme_remove_nsid_range (struct nvme_ctrl *ctrl,u32 start,u32 end)It is not intuitive to me that start is non-inclusive. May we add a comment to that effect?
Yes, it is not intuitive. [start, end) makes more sense IMO. That is said, this is how nvme_remove_invalid_namespaces() worked and I decided not to change that because it is not part of the fix. I do not think a comment will make a big difference here. The next person who works on this code will read the nvme_remove_nsid_range(), it is a short function, and figure out how it works.
Quoted 12 lines
Quoted 12 lines
{ struct nvme_ns *ns, *next; LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {drivers/nvme/host/core.c +3
-1-if (ns->head->ns_id > nsid) { +if (ns->head->ns_id >= end) +break ; +if (ns->head->ns_id > start) {list_del_rcu (&ns->list);
Quoted 8 lines · Mohamed Khalfella
nvme_scan_ns_list()drops the stale namespaces in each gap in the reported NSID list one NSID at a time. Every iteration callsnvme_find_get_ns()to look the namespace up and removes it if it is present. The loop runs once per NSID in the gap rather than once per namespace actually present.NSIDs are 32-bit, so a target with a sparse NSID space can make a single gap spin the loop billions of times with nothing to remove.
Thanks, applied to nvme-7.3.