The cleanup tasks of kdamond threads including reset of corresponding
DAMON context's ->kdamond field and decrease of global nr_running_ctxs
counter is supposed to be executed by kdamond_fn(). However, commit
0f91d13366a4 ("mm/damon: simplify stop mechanism") made neither
damon_start() nor damon_stop() ensure the corresponding kdamond has
started the execution of kdamond_fn().
As a result, the cleanup can be skipped if damon_stop() is called fast
enough after the previous damon_start(). Especially the skipped reset
of ->kdamond could cause a use-after-free.
Fix it by waiting for start of kdamond_fn() execution from
damon_start().
Fixes: 0f91d13366a4 ("mm/damon: simplify stop mechanism")
Reported-by: Jakub Acs <acsjakub(a)amazon.de>
Cc: <stable(a)vger.kernel.org> # 5.15.x
Signed-off-by: SeongJae Park <sj(a)kernel.org>
---
Note that the report has not publicly made, so this patch doesn't have a
Closes: tag.
include/linux/damon.h | 2 ++
mm/damon/core.c | 6 ++++++
2 files changed, 8 insertions(+)
diff --git a/include/linux/damon.h b/include/linux/damon.h
index aa34ab433bc5..12510d8c51c6 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -579,6 +579,8 @@ struct damon_ctx {
* update
*/
unsigned long next_ops_update_sis;
+ /* for waiting until the execution of the kdamond_fn is started */
+ struct completion kdamond_started;
/* public: */
struct task_struct *kdamond;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index f91715a58dc7..2c0cc65d041e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void)
if (!ctx)
return NULL;
+ init_completion(&ctx->kdamond_started);
+
ctx->attrs.sample_interval = 5 * 1000;
ctx->attrs.aggr_interval = 100 * 1000;
ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
@@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx)
mutex_lock(&ctx->kdamond_lock);
if (!ctx->kdamond) {
err = 0;
+ reinit_completion(&ctx->kdamond_started);
ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
nr_running_ctxs);
if (IS_ERR(ctx->kdamond)) {
err = PTR_ERR(ctx->kdamond);
ctx->kdamond = NULL;
+ } else {
+ wait_for_completion(&ctx->kdamond_started);
}
}
mutex_unlock(&ctx->kdamond_lock);
@@ -1483,6 +1488,7 @@ static int kdamond_fn(void *data)
pr_debug("kdamond (%d) starts\n", current->pid);
+ complete(&ctx->kdamond_started);
kdamond_init_intervals_sis(ctx);
if (ctx->ops.init)
--
2.34.1
When a queue is unbound from the vfio_ap device driver, it is reset to
ensure its crypto data is not leaked when it is bound to another device
driver. If the queue is unbound due to the fact that the adapter or domain
was removed from the host's AP configuration, then attempting to reset it
will fail with response code 01 (APID not valid) getting returned from the
reset command. Let's ensure that the queue is assigned to the host's
configuration before resetting it.
Signed-off-by: Tony Krowiak <akrowiak(a)linux.ibm.com>
Fixes: eeb386aeb5b7 ("s390/vfio-ap: handle config changed and scan complete notification")
Cc: <stable(a)vger.kernel.org>
---
drivers/s390/crypto/vfio_ap_ops.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 5db11d50b4b0..b6928fc3b395 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -2214,6 +2214,8 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
q = dev_get_drvdata(&apdev->device);
get_update_locks_for_queue(q);
matrix_mdev = q->matrix_mdev;
+ apid = AP_QID_CARD(q->apqn);
+ apqi = AP_QID_QUEUE(q->apqn);
if (matrix_mdev) {
/* If the queue is assigned to the guest's AP configuration */
@@ -2231,8 +2233,16 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
}
}
- vfio_ap_mdev_reset_queue(q);
- flush_work(&q->reset_work);
+ /*
+ * If the queue is not in the host's AP configuration, then resetting
+ * it will fail with response code 01, (APQN not valid); so, let's make
+ * sure it is in the host's config.
+ */
+ if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) &&
+ test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) {
+ vfio_ap_mdev_reset_queue(q);
+ flush_work(&q->reset_work);
+ }
done:
if (matrix_mdev)
--
2.43.0