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>
This commit is contained in:
Rasmus Villemoes 2019-11-28 15:55:51 +01:00 committed by Li Yang
parent 49b865b332
commit 148587a59f
1 changed files with 5 additions and 0 deletions

View File

@ -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);