RDMA/rtrs-srv: Don't guard the whole __alloc_srv with srv_mutex

The purpose of srv_mutex is to protect srv_list as in put_srv, so no need
to hold it when allocate memory for srv since it could be time consuming.

Otherwise if one machine has limited memory, rsrv_close_work could be
blocked for a longer time due to the mutex is held by get_or_create_srv
since it can't get memory in time.

  INFO: task kworker/1:1:27478 blocked for more than 120 seconds.
        Tainted: G           O    4.14.171-1-storage #4.14.171-1.3~deb9
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  kworker/1:1     D    0 27478      2 0x80000000
  Workqueue: rtrs_server_wq rtrs_srv_close_work [rtrs_server]
  Call Trace:
   ? __schedule+0x38c/0x7e0
   schedule+0x32/0x80
   schedule_preempt_disabled+0xa/0x10
   __mutex_lock.isra.2+0x25e/0x4d0
   ? put_srv+0x44/0x100 [rtrs_server]
   put_srv+0x44/0x100 [rtrs_server]
   rtrs_srv_close_work+0x16c/0x280 [rtrs_server]
   process_one_work+0x1c5/0x3c0
   worker_thread+0x47/0x3e0
   kthread+0xfc/0x130
   ? trace_event_raw_event_workqueue_execute_start+0xa0/0xa0
   ? kthread_create_on_node+0x70/0x70
   ret_from_fork+0x1f/0x30

Let's move all the logics from __find_srv_and_get and __alloc_srv to
get_or_create_srv, and remove the two functions. Then it should be safe
for multiple processes to access the same srv since it is protected with
srv_mutex.

And since we don't want to allocate chunks with srv_mutex held, let's
check the srv->refcount after get srv because the chunks could not be
allocated yet.

Fixes: 9cb8374804 ("RDMA/rtrs: server: main functionality")
Link: https://lore.kernel.org/r/20201023074353.21946-6-jinpu.wang@cloud.ionos.com
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This commit is contained in:
Guoqing Jiang 2020-10-23 09:43:46 +02:00 коммит произвёл Jason Gunthorpe
Родитель f553e7601d
Коммит d715ff8acb
1 изменённых файлов: 51 добавлений и 63 удалений

Просмотреть файл

@ -1328,51 +1328,6 @@ static void rtrs_srv_dev_release(struct device *dev)
kfree(srv);
}
static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
const uuid_t *paths_uuid)
{
struct rtrs_srv *srv;
int i;
srv = kzalloc(sizeof(*srv), GFP_KERNEL);
if (!srv)
return NULL;
refcount_set(&srv->refcount, 1);
INIT_LIST_HEAD(&srv->paths_list);
mutex_init(&srv->paths_mutex);
mutex_init(&srv->paths_ev_mutex);
uuid_copy(&srv->paths_uuid, paths_uuid);
srv->queue_depth = sess_queue_depth;
srv->ctx = ctx;
device_initialize(&srv->dev);
srv->dev.release = rtrs_srv_dev_release;
srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks),
GFP_KERNEL);
if (!srv->chunks)
goto err_free_srv;
for (i = 0; i < srv->queue_depth; i++) {
srv->chunks[i] = mempool_alloc(chunk_pool, GFP_KERNEL);
if (!srv->chunks[i])
goto err_free_chunks;
}
list_add(&srv->ctx_list, &ctx->srv_list);
return srv;
err_free_chunks:
while (i--)
mempool_free(srv->chunks[i], chunk_pool);
kfree(srv->chunks);
err_free_srv:
kfree(srv);
return NULL;
}
static void free_srv(struct rtrs_srv *srv)
{
int i;
@ -1387,32 +1342,61 @@ static void free_srv(struct rtrs_srv *srv)
put_device(&srv->dev);
}
static inline struct rtrs_srv *__find_srv_and_get(struct rtrs_srv_ctx *ctx,
const uuid_t *paths_uuid)
{
struct rtrs_srv *srv;
list_for_each_entry(srv, &ctx->srv_list, ctx_list) {
if (uuid_equal(&srv->paths_uuid, paths_uuid) &&
refcount_inc_not_zero(&srv->refcount))
return srv;
}
return NULL;
}
static struct rtrs_srv *get_or_create_srv(struct rtrs_srv_ctx *ctx,
const uuid_t *paths_uuid)
{
struct rtrs_srv *srv;
int i;
mutex_lock(&ctx->srv_mutex);
srv = __find_srv_and_get(ctx, paths_uuid);
if (!srv)
srv = __alloc_srv(ctx, paths_uuid);
list_for_each_entry(srv, &ctx->srv_list, ctx_list) {
if (uuid_equal(&srv->paths_uuid, paths_uuid) &&
refcount_inc_not_zero(&srv->refcount)) {
mutex_unlock(&ctx->srv_mutex);
return srv;
}
}
/* need to allocate a new srv */
srv = kzalloc(sizeof(*srv), GFP_KERNEL);
if (!srv) {
mutex_unlock(&ctx->srv_mutex);
return NULL;
}
INIT_LIST_HEAD(&srv->paths_list);
mutex_init(&srv->paths_mutex);
mutex_init(&srv->paths_ev_mutex);
uuid_copy(&srv->paths_uuid, paths_uuid);
srv->queue_depth = sess_queue_depth;
srv->ctx = ctx;
device_initialize(&srv->dev);
srv->dev.release = rtrs_srv_dev_release;
list_add(&srv->ctx_list, &ctx->srv_list);
mutex_unlock(&ctx->srv_mutex);
srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks),
GFP_KERNEL);
if (!srv->chunks)
goto err_free_srv;
for (i = 0; i < srv->queue_depth; i++) {
srv->chunks[i] = mempool_alloc(chunk_pool, GFP_KERNEL);
if (!srv->chunks[i])
goto err_free_chunks;
}
refcount_set(&srv->refcount, 1);
return srv;
err_free_chunks:
while (i--)
mempool_free(srv->chunks[i], chunk_pool);
kfree(srv->chunks);
err_free_srv:
kfree(srv);
return NULL;
}
static void put_srv(struct rtrs_srv *srv)
@ -1813,7 +1797,11 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
}
recon_cnt = le16_to_cpu(msg->recon_cnt);
srv = get_or_create_srv(ctx, &msg->paths_uuid);
if (!srv) {
/*
* "refcount == 0" happens if a previous thread calls get_or_create_srv
* allocate srv, but chunks of srv are not allocated yet.
*/
if (!srv || refcount_read(&srv->refcount) == 0) {
err = -ENOMEM;
goto reject_w_err;
}