FAILED: patch "[PATCH] usb: dwc3: gadget: Use list_replace_init() before traversing" failed to apply to 5.10-stable tree

The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From d25d85061bd856d6be221626605319154f9b5043 Mon Sep 17 00:00:00 2001
From: Wesley Cheng <[email protected]>
Date: Thu, 29 Jul 2021 00:33:14 -0700
Subject: [PATCH] usb: dwc3: gadget: Use list_replace_init() before traversing
lists

The list_for_each_entry_safe() macro saves the current item (n) and the item after (n+1), so that n can be safely removed without corrupting the list. However, when traversing the list and removing items using gadget giveback, the DWC3 lock is briefly released, allowing other routines to execute. There is a situation where, while items are being removed from the cancelled_list using dwc3_gadget_ep_cleanup_cancelled_requests(), the pullup disable routine is running in parallel (due to UDC unbind). As the cleanup routine removes n, and the pullup disable removes n+1, once the cleanup retakes the DWC3 lock, it references a request who was already removed/handled. With list debug enabled, this leads to a panic. Ensure all instances of the macro are replaced where gadget giveback is used.

Example call stack:

Thread#1:
__dwc3_gadget_ep_set_halt() - CLEAR HALT
-> dwc3_gadget_ep_cleanup_cancelled_requests()

    ->list_for_each_entry_safe()
    ->dwc3_gadget_giveback(n)
      ->dwc3_gadget_del_and_unmap_request()- n deleted[cancelled_list]
      ->spin_unlock
      ->Thread#2 executes
      ...
    ->dwc3_gadget_giveback(n+1)
      ->Already removed!

Thread#2:
dwc3_gadget_pullup()
->waiting for dwc3 spin_lock
...
->Thread#1 released lock
->dwc3_stop_active_transfers()

    ->dwc3_remove_requests()
      ->fetches n+1 item from cancelled_list (n removed by Thread#1)
      ->dwc3_gadget_giveback()
        ->dwc3_gadget_del_and_unmap_request()- n+1
deleted[cancelled_list]
        ->spin_unlock

Fix this condition by utilizing list_replace_init(), and traversing through a local copy of the current elements in the endpoint lists. This will also set the parent list as empty, so if another thread is also looping through the list, it will be empty on the next iteration.

index 45f2bc0807e8..a1b262669574 100644
@@ -1741,9 +1741,13 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep)
 {
 	struct dwc3_request		*req;
 	struct dwc3_request		*tmp;
+	struct list_head		local;
 	struct dwc3			*dwc = dep->dwc;
 
-	list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) {
+restart:
+	list_replace_init(&dep->cancelled_list, &local);
+
+	list_for_each_entry_safe(req, tmp, &local, list) {
 		dwc3_gadget_ep_skip_trbs(dep, req);
 		switch (req->status) {
 		case DWC3_REQUEST_STATUS_DISCONNECTED:

@@ -1761,6 +1765,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep)
 			break;
 		}
 	}
+
+	if (!list_empty(&dep->cancelled_list))
+		goto restart;
 }
 
 static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,

@@ -2958,8 +2965,12 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep,
 {
 	struct dwc3_request	*req;
 	struct dwc3_request	*tmp;
+	struct list_head	local;
 
-	list_for_each_entry_safe(req, tmp, &dep->started_list, list) {
+restart:
+	list_replace_init(&dep->started_list, &local);
+
+	list_for_each_entry_safe(req, tmp, &local, list) {
 		int ret;
 
 		ret = dwc3_gadget_ep_cleanup_completed_request(dep, event,

@@ -2967,6 +2978,9 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep,
 		if (ret)
 			break;
 	}
+
+	if (!list_empty(&dep->started_list))
+		goto restart;
 }
 
 static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep)

Hi Greg,

Here is the backport, will also apply to 5.4-stable and 4.19-stable.

--
Regards
Sudip

From e01c2051bac15d89168e30c2cfa2cd828104ed4d Mon Sep 17 00:00:00 2001
From: Wesley Cheng <[email protected]>
Date: Thu, 29 Jul 2021 00:33:14 -0700
Subject: [PATCH] usb: dwc3: gadget: Use list_replace_init() before traversing
lists

commit d25d85061bd856d6be221626605319154f9b5043 upstream

The list_for_each_entry_safe() macro saves the current item (n) and the item after (n+1), so that n can be safely removed without corrupting the list. However, when traversing the list and removing items using gadget giveback, the DWC3 lock is briefly released, allowing other routines to execute. There is a situation where, while items are being removed from the cancelled_list using dwc3_gadget_ep_cleanup_cancelled_requests(), the pullup disable routine is running in parallel (due to UDC unbind). As the cleanup routine removes n, and the pullup disable removes n+1, once the cleanup retakes the DWC3 lock, it references a request who was already removed/handled. With list debug enabled, this leads to a panic. Ensure all instances of the macro are replaced where gadget giveback is used.

Example call stack:

Thread#1:
__dwc3_gadget_ep_set_halt() - CLEAR HALT
-> dwc3_gadget_ep_cleanup_cancelled_requests()

    ->list_for_each_entry_safe()
    ->dwc3_gadget_giveback(n)
      ->dwc3_gadget_del_and_unmap_request()- n deleted[cancelled_list]
      ->spin_unlock
      ->Thread#2 executes
      ...
    ->dwc3_gadget_giveback(n+1)
      ->Already removed!

Thread#2:
dwc3_gadget_pullup()
->waiting for dwc3 spin_lock
...
->Thread#1 released lock
->dwc3_stop_active_transfers()

    ->dwc3_remove_requests()
      ->fetches n+1 item from cancelled_list (n removed by Thread#1)
      ->dwc3_gadget_giveback()
        ->dwc3_gadget_del_and_unmap_request()- n+1
deleted[cancelled_list]
        ->spin_unlock

Fix this condition by utilizing list_replace_init(), and traversing through a local copy of the current elements in the endpoint lists. This will also set the parent list as empty, so if another thread is also looping through the list, it will be empty on the next iteration.

---
 drivers/usb/dwc3/gadget.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

index 756839e0e91d..788bbb38cf79 100644
@@ -1733,11 +1733,18 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep)
 {
 	struct dwc3_request		*req;
 	struct dwc3_request		*tmp;
+	struct list_head		local;
 
-	list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) {
+restart:
+	list_replace_init(&dep->cancelled_list, &local);
+
+	list_for_each_entry_safe(req, tmp, &local, list) {
 		dwc3_gadget_ep_skip_trbs(dep, req);
 		dwc3_gadget_giveback(dep, req, -ECONNRESET);
 	}
+
+	if (!list_empty(&dep->cancelled_list))
+		goto restart;
 }
 
 static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,

@@ -2867,8 +2874,12 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep,
 {
 	struct dwc3_request	*req;
 	struct dwc3_request	*tmp;
+	struct list_head	local;
 
-	list_for_each_entry_safe(req, tmp, &dep->started_list, list) {
+restart:
+	list_replace_init(&dep->started_list, &local);
+
+	list_for_each_entry_safe(req, tmp, &local, list) {
 		int ret;
 
 		ret = dwc3_gadget_ep_cleanup_completed_request(dep, event,

@@ -2876,6 +2887,9 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep,
 		if (ret)
 			break;
 	}
+
+	if (!list_empty(&dep->started_list))
+		goto restart;
 }
 
 static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep)

2.30.2

This breaks systems, and is reverted in my tree and will be sent to Linus later today (the revert), so I'll drop this from the stable trees for now.

thanks,

greg k-h