[V2,3/5] cachefiles: resend an open request if the read request's object is closed

Message ID 20221014030745.25748-4-zhujia.zj@bytedance.com
State New
Headers
Series Introduce daemon failover mechanism to recover from crashing |

Commit Message

Jia Zhu Oct. 14, 2022, 3:07 a.m. UTC
  When an anonymous fd is closed by user daemon, if there is a new read
request for this file comes up, the anonymous fd should be re-opened
to handle that read request rather than fail it directly.

1. Introduce reopening state for objects that are closed but have
   inflight/subsequent read requests.
2. No longer flush READ requests but only CLOSE requests when anonymous
   fd is closed.
3. Enqueue the reopen work to workqueue, thus user daemon could get rid
   of daemon_read context and handle that request smoothly. Otherwise,
   the user daemon will send a reopen request and wait for itself to
   process the request.

Signed-off-by: Jia Zhu <zhujia.zj@bytedance.com>
Reviewed-by: Xin Yin <yinxin.x@bytedance.com>
---
 fs/cachefiles/internal.h |  3 ++
 fs/cachefiles/ondemand.c | 94 ++++++++++++++++++++++++++++------------
 2 files changed, 69 insertions(+), 28 deletions(-)
  

Comments

Jingbo Xu Oct. 14, 2022, 6:31 a.m. UTC | #1
On 10/14/22 11:07 AM, Jia Zhu wrote:

> +/*
> + * Reopen the closed object with associated read request.

I think "Reopen the closed object if there's any inflight or subsequent
READ request on this object" would be better?

> + * Skip read requests whose related object are reopening.
					       ^
					      is ?


> @@ -277,14 +308,18 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
>  	xa_unlock(&cache->reqs);
>  
>  	id = xas.xa_index;
> -	msg->msg_id = id;
>  
>  	if (msg->opcode == CACHEFILES_OP_OPEN) {
>  		ret = cachefiles_ondemand_get_fd(req);
> -		if (ret)
> +		if (ret) {
> +			cachefiles_ondemand_set_object_close(req->object);
>  			goto error;
> +		}
>  	}
>  
> +	msg->msg_id = id;
> +	msg->object_id = req->object->private->ondemand_id;

Since currently msg->object_id is always assigned in
cachefiles_ondemand_daemon_read(), we can remove the assignment in
cachefiles_ondemand_get_fd().


Otherwise LGTM.

Reviewed-by: Jingbo Xu <jefflexu@linux.alibaba.com>
  

Patch

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index be1e7fbdb444..21ef5007f488 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -48,9 +48,11 @@  struct cachefiles_volume {
 enum cachefiles_object_state {
 	CACHEFILES_ONDEMAND_OBJSTATE_close, /* Anonymous fd closed by daemon or initial state */
 	CACHEFILES_ONDEMAND_OBJSTATE_open, /* Anonymous fd associated with object is available */
+	CACHEFILES_ONDEMAND_OBJSTATE_reopening, /* Object that was closed and is being reopened. */
 };
 
 struct cachefiles_ondemand_info {
+	struct work_struct		work;
 	int				ondemand_id;
 	enum cachefiles_object_state	state;
 	struct cachefiles_object	*object;
@@ -324,6 +326,7 @@  cachefiles_ondemand_set_object_##_state(struct cachefiles_object *object) \
 
 CACHEFILES_OBJECT_STATE_FUNCS(open);
 CACHEFILES_OBJECT_STATE_FUNCS(close);
+CACHEFILES_OBJECT_STATE_FUNCS(reopening);
 #else
 static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 6e47667c6690..c9eea89befec 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -18,14 +18,10 @@  static int cachefiles_ondemand_fd_release(struct inode *inode,
 	info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
 	cachefiles_ondemand_set_object_close(object);
 
-	/*
-	 * Flush all pending READ requests since their completion depends on
-	 * anon_fd.
-	 */
-	xas_for_each(&xas, req, ULONG_MAX) {
+	/* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */
+	xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) {
 		if (req->msg.object_id == object_id &&
-		    req->msg.opcode == CACHEFILES_OP_READ) {
-			req->error = -EIO;
+		    req->msg.opcode == CACHEFILES_OP_CLOSE) {
 			complete(&req->done);
 			xas_store(&xas, NULL);
 		}
@@ -179,6 +175,7 @@  int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 	trace_cachefiles_ondemand_copen(req->object, id, size);
 
 	cachefiles_ondemand_set_object_open(req->object);
+	wake_up_all(&cache->daemon_pollwq);
 
 out:
 	complete(&req->done);
@@ -238,6 +235,40 @@  static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
 	return ret;
 }
 
+static void ondemand_object_worker(struct work_struct *work)
+{
+	struct cachefiles_object *object =
+		((struct cachefiles_ondemand_info *)work)->object;
+
+	cachefiles_ondemand_init_object(object);
+}
+
+/*
+ * Reopen the closed object with associated read request.
+ * Skip read requests whose related object are reopening.
+ */
+static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xas,
+							      unsigned long xa_max)
+{
+	struct cachefiles_req *req;
+	struct cachefiles_ondemand_info *info;
+
+	xas_for_each_marked(xas, req, xa_max, CACHEFILES_REQ_NEW) {
+		if (req->msg.opcode != CACHEFILES_OP_READ)
+			return req;
+		info = req->object->private;
+		if (info->state == CACHEFILES_ONDEMAND_OBJSTATE_close) {
+			cachefiles_ondemand_set_object_reopening(req->object);
+			queue_work(fscache_wq, &info->work);
+			continue;
+		} else if (info->state == CACHEFILES_ONDEMAND_OBJSTATE_reopening) {
+			continue;
+		}
+		return req;
+	}
+	return NULL;
+}
+
 ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
 {
@@ -248,16 +279,16 @@  ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	int ret = 0;
 	XA_STATE(xas, &cache->reqs, cache->req_id_next);
 
+	xa_lock(&cache->reqs);
 	/*
 	 * Cyclically search for a request that has not ever been processed,
 	 * to prevent requests from being processed repeatedly, and make
 	 * request distribution fair.
 	 */
-	xa_lock(&cache->reqs);
-	req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW);
+	req = cachefiles_ondemand_select_req(&xas, ULONG_MAX);
 	if (!req && cache->req_id_next > 0) {
 		xas_set(&xas, 0);
-		req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW);
+		req = cachefiles_ondemand_select_req(&xas, cache->req_id_next - 1);
 	}
 	if (!req) {
 		xa_unlock(&cache->reqs);
@@ -277,14 +308,18 @@  ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	xa_unlock(&cache->reqs);
 
 	id = xas.xa_index;
-	msg->msg_id = id;
 
 	if (msg->opcode == CACHEFILES_OP_OPEN) {
 		ret = cachefiles_ondemand_get_fd(req);
-		if (ret)
+		if (ret) {
+			cachefiles_ondemand_set_object_close(req->object);
 			goto error;
+		}
 	}
 
+	msg->msg_id = id;
+	msg->object_id = req->object->private->ondemand_id;
+
 	if (copy_to_user(_buffer, msg, n) != 0) {
 		ret = -EFAULT;
 		goto err_put_fd;
@@ -317,19 +352,23 @@  static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 					void *private)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
-	struct cachefiles_req *req;
+	struct cachefiles_req *req = NULL;
 	XA_STATE(xas, &cache->reqs, 0);
 	int ret;
 
 	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
 		return 0;
 
-	if (test_bit(CACHEFILES_DEAD, &cache->flags))
-		return -EIO;
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL);
-	if (!req)
-		return -ENOMEM;
+	if (!req) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	req->object = object;
 	init_completion(&req->done);
@@ -367,7 +406,7 @@  static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 		/* coupled with the barrier in cachefiles_flush_reqs() */
 		smp_mb();
 
-		if (opcode != CACHEFILES_OP_OPEN &&
+		if (opcode == CACHEFILES_OP_CLOSE &&
 			!cachefiles_ondemand_object_is_open(object)) {
 			WARN_ON_ONCE(object->private->ondemand_id == 0);
 			xas_unlock(&xas);
@@ -392,7 +431,15 @@  static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 	wake_up_all(&cache->daemon_pollwq);
 	wait_for_completion(&req->done);
 	ret = req->error;
+	kfree(req);
+	return ret;
 out:
+	/* Reset the object to close state in error handling path.
+	 * If error occurs after creating the anonymous fd,
+	 * cachefiles_ondemand_fd_release() will set object to close.
+	 */
+	if (opcode == CACHEFILES_OP_OPEN)
+		cachefiles_ondemand_set_object_close(req->object);
 	kfree(req);
 	return ret;
 }
@@ -439,7 +486,6 @@  static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req,
 	if (!cachefiles_ondemand_object_is_open(object))
 		return -ENOENT;
 
-	req->msg.object_id = object->private->ondemand_id;
 	trace_cachefiles_ondemand_close(object, &req->msg);
 	return 0;
 }
@@ -455,16 +501,7 @@  static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req,
 	struct cachefiles_object *object = req->object;
 	struct cachefiles_read *load = (void *)req->msg.data;
 	struct cachefiles_read_ctx *read_ctx = private;
-	int object_id = object->private->ondemand_id;
-
-	/* Stop enqueuing requests when daemon has closed anon_fd. */
-	if (!cachefiles_ondemand_object_is_open(object)) {
-		WARN_ON_ONCE(object_id == 0);
-		pr_info_once("READ: anonymous fd closed prematurely.\n");
-		return -EIO;
-	}
 
-	req->msg.object_id = object_id;
 	load->off = read_ctx->off;
 	load->len = read_ctx->len;
 	trace_cachefiles_ondemand_read(object, &req->msg, load);
@@ -513,6 +550,7 @@  int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object,
 		return -ENOMEM;
 
 	object->private->object = object;
+	INIT_WORK(&object->private->work, ondemand_object_worker);
 	return 0;
 }