| Message ID | 20241010154519.768785-1-colin.i.king@gmail.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 637c4f6fe40befa04f19c38b5d15429cbb9191d9 |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [next,V2] octeontx2-af: Fix potential integer overflows on integer shifts | expand |
On Thu, Oct 10, 2024 at 04:45:19PM +0100, Colin Ian King wrote: > The left shift int 32 bit integer constants 1 is evaluated using 32 bit > arithmetic and then assigned to a 64 bit unsigned integer. In the case > where the shift is 32 or more this can lead to an overflow. Avoid this > by shifting using the BIT_ULL macro instead. > > Fixes: 019aba04f08c ("octeontx2-af: Modify SMQ flush sequence to drop packets") > Signed-off-by: Colin Ian King <colin.i.king@gmail.com> > --- > > V2: Fix both (1 << i) shifts, thanks to Dan Carpenter for spotting the > second shift that I overlooked in the first patch. Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org> regards, dan carpenter
On 10/10/24 17:45, Colin Ian King wrote: > The left shift int 32 bit integer constants 1 is evaluated using 32 bit > arithmetic and then assigned to a 64 bit unsigned integer. In the case > where the shift is 32 or more this can lead to an overflow. Avoid this > by shifting using the BIT_ULL macro instead. > > Fixes: 019aba04f08c ("octeontx2-af: Modify SMQ flush sequence to drop packets") > Signed-off-by: Colin Ian King <colin.i.king@gmail.com> > --- > > V2: Fix both (1 << i) shifts, thanks to Dan Carpenter for spotting the > second shift that I overlooked in the first patch. The blamed commit is in the 'net' tree already, I'm applying the patch there. Cheers, Paolo
Hello: This patch was applied to netdev/net.git (main) by Paolo Abeni <pabeni@redhat.com>: On Thu, 10 Oct 2024 16:45:19 +0100 you wrote: > The left shift int 32 bit integer constants 1 is evaluated using 32 bit > arithmetic and then assigned to a 64 bit unsigned integer. In the case > where the shift is 32 or more this can lead to an overflow. Avoid this > by shifting using the BIT_ULL macro instead. > > Fixes: 019aba04f08c ("octeontx2-af: Modify SMQ flush sequence to drop packets") > Signed-off-by: Colin Ian King <colin.i.king@gmail.com> > > [...] Here is the summary with links: - [next,V2] octeontx2-af: Fix potential integer overflows on integer shifts https://git.kernel.org/netdev/net/c/637c4f6fe40b You are awesome, thank you!
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 82832a24fbd8..da69350c6f76 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2411,7 +2411,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link)); if (!(cfg & BIT_ULL(12))) continue; - bmap |= (1 << i); + bmap |= BIT_ULL(i); cfg &= ~BIT_ULL(12); rvu_write64(rvu, blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg); @@ -2432,7 +2432,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, /* Set NIX_AF_TL3_TL2_LINKX_CFG[ENA] for the TL3/TL2 queue */ for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) { - if (!(bmap & (1 << i))) + if (!(bmap & BIT_ULL(i))) continue; cfg = rvu_read64(rvu, blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link));
The left shift int 32 bit integer constants 1 is evaluated using 32 bit arithmetic and then assigned to a 64 bit unsigned integer. In the case where the shift is 32 or more this can lead to an overflow. Avoid this by shifting using the BIT_ULL macro instead. Fixes: 019aba04f08c ("octeontx2-af: Modify SMQ flush sequence to drop packets") Signed-off-by: Colin Ian King <colin.i.king@gmail.com> --- V2: Fix both (1 << i) shifts, thanks to Dan Carpenter for spotting the second shift that I overlooked in the first patch. --- drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)