Skip to content

Commit

Permalink
ptp_qoriq: fix overflow in ptp_qoriq_adjfine() u64 calcalation
Browse files Browse the repository at this point in the history
Current calculation for diff of TMR_ADD register value may have
64-bit overflow in this code line, when long type scaled_ppm is
large.

adj *= scaled_ppm;

This patch is to resolve it by using mul_u64_u64_div_u64().

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
  • Loading branch information
Yangbo Lu authored and David S. Miller committed Mar 24, 2021
1 parent 6ab4c31 commit f51d7bf
Showing 1 changed file with 7 additions and 6 deletions.
13 changes: 7 additions & 6 deletions drivers/ptp/ptp_qoriq.c
Original file line number Diff line number Diff line change
Expand Up @@ -189,15 +189,16 @@ int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
tmr_add = ptp_qoriq->tmr_add;
adj = tmr_add;

/* calculate diff as adj*(scaled_ppm/65536)/1000000
* and round() to the nearest integer
/*
* Calculate diff and round() to the nearest integer
*
* diff = adj * (ppb / 1000000000)
* = adj * scaled_ppm / 65536000000
*/
adj *= scaled_ppm;
diff = div_u64(adj, 8000000);
diff = (diff >> 13) + ((diff >> 12) & 1);
diff = mul_u64_u64_div_u64(adj, scaled_ppm, 32768000000);
diff = DIV64_U64_ROUND_UP(diff, 2);

tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;

ptp_qoriq->write(&regs->ctrl_regs->tmr_add, tmr_add);

return 0;
Expand Down

0 comments on commit f51d7bf

Please sign in to comment.