From: Cyrille Pitchen <redacted>

3.12-stable review patch.  If anyone has any objections, please let me know.

===============

commit 6fbb9bdf0f3fbe23aeff806489791aa876adaffb upstream.

-EDEFER error wasn't handle properly by atmel_serial_probe().
As an example, when atmel_serial_probe() is called for the first time, we pass
the test_and_set_bit() test to check whether the port has already been
initalized. Then we call atmel_init_port(), which may return -EDEFER, possibly
returned before by clk_get(). Consequently atmel_serial_probe() used to return
this error code WITHOUT clearing the port bit in the "atmel_ports_in_use" mask.
When atmel_serial_probe() was called for the second time, it used to fail on
the test_and_set_bit() function then returning -EBUSY.

When atmel_serial_probe() fails, this patch make it clear the port bit in the
"atmel_ports_in_use" mask, if needed, before returning the error code.

Signed-off-by: Cyrille Pitchen <redacted>
Acked-by: Nicolas Ferre <redacted>
Signed-off-by: Jiri Slaby <redacted>
---
 drivers/tty/serial/atmel_serial.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3b301a7ec662..ebdc00f184a1 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c

@@ -2375,7 +2375,7 @@ static int atmel_serial_probe(struct platform_device *pdev)
 
 	ret = atmel_init_port(port, pdev);
 	if (ret)
-		goto err;
+		goto err_clear_bit;
 
 	if (!atmel_use_pdc_rx(&port->uart)) {
 		ret = -ENOMEM;

@@ -2424,6 +2424,8 @@ err_alloc_ring:
 		clk_put(port->clk);
 		port->clk = NULL;
 	}
+err_clear_bit:
+	clear_bit(port->uart.line, atmel_ports_in_use);
 err:
 	return ret;
 }

-- 
2.3.0