net/wan/fsl_ucc_hdlc: reject muram offsets above 64K

Qiang Zhao points out that these offsets get written to 16-bit
registers, and there are some QE platforms with more than 64K
muram. So it is possible that qe_muram_alloc() gives us an allocation
that can't actually be used by the hardware, so detect and reject
that.

Reported-by: Qiang Zhao <qiang.zhao@nxp.com>
Reviewed-by: Timur Tabi <timur@kernel.org>
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Li Yang <leoyang.li@nxp.com>

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 8d13586..f029eaa 100644 (file)
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -245,6 +245,11 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
                ret = -ENOMEM;
                goto free_riptr;
        }
+       if (riptr != (u16)riptr || tiptr != (u16)tiptr) {
+               dev_err(priv->dev, "MURAM allocation out of addressable range\n");
+               ret = -ENOMEM;
+               goto free_tiptr;
+       }
 
        /* Set RIPTR, TIPTR */
        iowrite16be(riptr, &priv->ucc_pram->riptr);