[PATCH rdma-next 1/8] RDMA/core: Add rdma_restrack_begin/abort/commit_del() operations
From: Edward Srouji
Date: Wed Jul 01 2026 - 08:46:06 EST
From: Patrisious Haddad <phaddad@xxxxxxxxxx>
Add rdma_restrack_abort_del(), rdma_restrack_begin_del() and
rdma_restrack_commit_del() functions to allow deleting a resource from
the xarray to effectively prevent future access to it and wait for all
current users to finish while preserving its index in the xarray to
allow to re-insert it if needed with guaranteed success.
This is a preparatory change for subsequent patches in the series
which will use these functions to fix the cleanup flow.
Signed-off-by: Patrisious Haddad <phaddad@xxxxxxxxxx>
Reviewed-by: Michael Guralnik <michaelgur@xxxxxxxxxx>
Signed-off-by: Edward Srouji <edwards@xxxxxxxxxx>
---
drivers/infiniband/core/restrack.c | 167 +++++++++++++++++++++++++++++--------
drivers/infiniband/core/restrack.h | 3 +
2 files changed, 137 insertions(+), 33 deletions(-)
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index cfee2071586c16e3dfc4e21e5d58f8488dfb277f..30d433ee79a042fe270c9ed2f47b0e2d4a388ff9 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -129,6 +129,40 @@ static void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
res->user = true;
}
+static struct rdma_restrack_root *res_to_rt(struct rdma_restrack_entry *res)
+{
+ struct ib_device *dev = res_to_dev(res);
+
+ if (WARN_ON(!dev))
+ return NULL;
+
+ return &dev->res[res->type];
+}
+
+static void restrack_drain_res(struct rdma_restrack_root *rt,
+ struct rdma_restrack_entry *res)
+{
+ struct rdma_restrack_entry *old;
+
+ old = xa_cmpxchg(&rt->xa, res->id, res, XA_ZERO_ENTRY, GFP_KERNEL);
+ WARN_ON(old != res);
+
+ rdma_restrack_put(res);
+ wait_for_completion(&res->comp);
+}
+
+static void restrack_restore_res(struct rdma_restrack_root *rt,
+ struct rdma_restrack_entry *res)
+{
+ struct rdma_restrack_entry *old;
+
+ reinit_completion(&res->comp);
+ kref_init(&res->kref);
+
+ old = xa_cmpxchg(&rt->xa, res->id, XA_ZERO_ENTRY, res, GFP_KERNEL);
+ WARN_ON(old);
+}
+
/**
* rdma_restrack_set_name() - set the task for this resource
* @res: resource entry
@@ -177,22 +211,23 @@ void rdma_restrack_new(struct rdma_restrack_entry *res,
EXPORT_SYMBOL(rdma_restrack_new);
/**
- * rdma_restrack_add() - add object to the resource tracking database
+ * rdma_restrack_add() - add object to the resource tracking database.
+ * If this resource reuses an ID of a resource that was already destroyed
+ * after calling rdma_restrack_begin() but didn't yet call
+ * rdma_restrack_commit_del() it can result in an untracked QP.
* @res: resource entry
*/
void rdma_restrack_add(struct rdma_restrack_entry *res)
{
- struct ib_device *dev = res_to_dev(res);
struct rdma_restrack_root *rt;
int ret = 0;
- if (!dev)
- return;
-
if (res->no_track)
goto out;
- rt = &dev->res[res->type];
+ rt = res_to_rt(res);
+ if (!rt)
+ return;
if (res->type == RDMA_RESTRACK_QP) {
/* Special case to ensure that LQPN points to right QP */
@@ -229,6 +264,32 @@ void rdma_restrack_add(struct rdma_restrack_entry *res)
}
EXPORT_SYMBOL(rdma_restrack_add);
+/**
+ * rdma_restrack_abort_del() - re-add object to the resource tracking database
+ * it can only be used after rdma_restrack_begin_del().
+ * @res: resource entry
+ */
+void rdma_restrack_abort_del(struct rdma_restrack_entry *res)
+{
+ struct rdma_restrack_root *rt;
+
+ if (!res->valid)
+ return;
+
+ if (res->no_track) {
+ reinit_completion(&res->comp);
+ kref_init(&res->kref);
+ return;
+ }
+
+ rt = res_to_rt(res);
+ if (!rt)
+ return;
+
+ restrack_restore_res(rt, res);
+}
+EXPORT_SYMBOL(rdma_restrack_abort_del);
+
int __must_check rdma_restrack_get(struct rdma_restrack_entry *res)
{
return kref_get_unless_zero(&res->kref);
@@ -265,7 +326,7 @@ static void restrack_release(struct kref *kref)
struct rdma_restrack_entry *res;
res = container_of(kref, struct rdma_restrack_entry, kref);
- if (res->task) {
+ if (res->task && !res->valid) {
put_task_struct(res->task);
res->task = NULL;
}
@@ -291,37 +352,20 @@ EXPORT_SYMBOL(rdma_restrack_put);
*/
void rdma_restrack_sync(struct rdma_restrack_entry *res)
{
- struct rdma_restrack_entry *old;
struct rdma_restrack_root *rt;
- struct task_struct *task;
- struct ib_device *dev;
if (!res->valid || res->no_track)
return;
- dev = res_to_dev(res);
- if (WARN_ON(!dev))
+ rt = res_to_rt(res);
+ if (!rt)
return;
- rt = &dev->res[res->type];
if (WARN_ON(xa_get_mark(&rt->xa, res->id, RESTRACK_DD)))
return;
- old = xa_cmpxchg(&rt->xa, res->id, res, XA_ZERO_ENTRY, GFP_KERNEL);
- if (WARN_ON(old != res))
- return;
-
- task = res->task;
- if (task)
- get_task_struct(task);
- rdma_restrack_put(res);
- wait_for_completion(&res->comp);
- reinit_completion(&res->comp);
- if (task)
- res->task = task;
- kref_init(&res->kref);
-
- xa_cmpxchg(&rt->xa, res->id, XA_ZERO_ENTRY, res, GFP_KERNEL);
+ restrack_drain_res(rt, res);
+ restrack_restore_res(rt, res);
}
EXPORT_SYMBOL(rdma_restrack_sync);
@@ -333,7 +377,6 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
{
struct rdma_restrack_entry *old;
struct rdma_restrack_root *rt;
- struct ib_device *dev;
if (!res->valid) {
if (res->task) {
@@ -346,12 +389,10 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
if (res->no_track)
goto out;
- dev = res_to_dev(res);
- if (WARN_ON(!dev))
+ rt = res_to_rt(res);
+ if (!rt)
return;
- rt = &dev->res[res->type];
-
old = xa_erase(&rt->xa, res->id);
WARN_ON(old != res);
@@ -359,5 +400,65 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
res->valid = false;
rdma_restrack_put(res);
wait_for_completion(&res->comp);
+ if (res->task) {
+ put_task_struct(res->task);
+ res->task = NULL;
+ }
}
EXPORT_SYMBOL(rdma_restrack_del);
+
+/**
+ * rdma_restrack_begin_del() - invalidate the object from the resource tracking
+ * database but preserve its index in the array.
+ * Since this preserves the index in the array until rdma_restrack_commit_del()
+ * is called, if rdma_restrack_add() is called in between with an old QP ID it
+ * can result in an untracked QP.
+ * @res: resource entry
+ */
+void rdma_restrack_begin_del(struct rdma_restrack_entry *res)
+{
+ struct rdma_restrack_root *rt;
+
+ if (!res->valid)
+ return;
+
+ if (res->no_track) {
+ rdma_restrack_put(res);
+ wait_for_completion(&res->comp);
+ return;
+ }
+
+ rt = res_to_rt(res);
+ if (!rt)
+ return;
+
+ restrack_drain_res(rt, res);
+}
+EXPORT_SYMBOL(rdma_restrack_begin_del);
+
+/**
+ * rdma_restrack_commit_del() - delete object from the resource tracking
+ * database and free the task.
+ * @res: resource entry
+ */
+void rdma_restrack_commit_del(struct rdma_restrack_entry *res)
+{
+ struct rdma_restrack_root *rt;
+
+ if (!res->valid || res->no_track)
+ goto out;
+
+ rt = res_to_rt(res);
+ if (!rt)
+ return;
+
+ xa_erase(&rt->xa, res->id);
+
+out:
+ res->valid = false;
+ if (res->task) {
+ put_task_struct(res->task);
+ res->task = NULL;
+ }
+}
+EXPORT_SYMBOL(rdma_restrack_commit_del);
diff --git a/drivers/infiniband/core/restrack.h b/drivers/infiniband/core/restrack.h
index 75b8d1005a984b21896e296ac6ace1415a90905f..2df78e084e107c517a2468982add74ce3562e5f2 100644
--- a/drivers/infiniband/core/restrack.h
+++ b/drivers/infiniband/core/restrack.h
@@ -26,8 +26,11 @@ struct rdma_restrack_root {
int rdma_restrack_init(struct ib_device *dev);
void rdma_restrack_clean(struct ib_device *dev);
void rdma_restrack_add(struct rdma_restrack_entry *res);
+void rdma_restrack_abort_del(struct rdma_restrack_entry *res);
void rdma_restrack_del(struct rdma_restrack_entry *res);
void rdma_restrack_sync(struct rdma_restrack_entry *res);
+void rdma_restrack_begin_del(struct rdma_restrack_entry *res);
+void rdma_restrack_commit_del(struct rdma_restrack_entry *res);
void rdma_restrack_new(struct rdma_restrack_entry *res,
enum rdma_restrack_type type);
void rdma_restrack_set_name(struct rdma_restrack_entry *res,
--
2.49.0