From: Jesper Juhl Date: Mon, 16 Jan 2012 21:42:10 +0000 (+0100) Subject: usb: renesas: silence uninitialized variable report in usbhsg_recip_run_handle() X-Git-Tag: v3.3-rc2~5^2~4^2~7 X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=commitdiff_plain;h=7983bc74fc0bc91f026c7ba0654b08073d843657;p=linux.git usb: renesas: silence uninitialized variable report in usbhsg_recip_run_handle() In drivers/usb/renesas_usbhs/mod_gadget.c::usbhsg_recip_run_handle() the Coverity Prevent checker currently flags a warning about possibly uninitialized use of 'ret' i usbhsg_recip_run_handle(). It does this since it assumes we take one of the non-default branches in the switch and then subsequently take the false branch in the 'if (func)' case below. This exact scenario will never happen, but Coverity can't see that for some reason. This patch initializes 'ret' to '0' when it is declared which should shut up this report and won't really hurt - so why not? At least then it's clear that 'ret' is always initialized.. Signed-off-by: Jesper Juhl Signed-off-by: Felipe Balbi --- diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 528691d5f3e2..7542aa94a462 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -425,7 +425,7 @@ static int usbhsg_recip_run_handle(struct usbhs_priv *priv, struct usbhs_pipe *pipe; int recip = ctrl->bRequestType & USB_RECIP_MASK; int nth = le16_to_cpu(ctrl->wIndex) & USB_ENDPOINT_NUMBER_MASK; - int ret; + int ret = 0; int (*func)(struct usbhs_priv *priv, struct usbhsg_uep *uep, struct usb_ctrlrequest *ctrl); char *msg;