| Message ID | 1510938349-17608-7-git-send-email-brking@linux.vnet.ibm.com |
|---|---|
| State | Accepted |
| Delegated to: | Jeff Kirsher |
| Headers | show |
| Series | intel: Use smp_rmb rather than read_barrier_depends | expand |
On Fri, 17 Nov 2017 11:05:48 -0600 Brian King <brking@linux.vnet.ibm.com> wrote: > The original issue being fixed in this patch was seen with the ixgbe > driver, but the same issue exists with fm10k as well, as the code is > very similar. read_barrier_depends is not sufficient to ensure > loads following it are not speculatively loaded out of order > by the CPU, which can result in stale data being loaded, causing > potential system crashes. Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9dffaba..103c0a7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1229,7 +1229,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, break; /* prevent any other reads prior to eop_desc */ - read_barrier_depends(); + smp_rmb(); /* if DD is not set pending work has not been completed */ if (!(eop_desc->flags & FM10K_TXD_FLAG_DONE))
The original issue being fixed in this patch was seen with the ixgbe driver, but the same issue exists with fm10k as well, as the code is very similar. read_barrier_depends is not sufficient to ensure loads following it are not speculatively loaded out of order by the CPU, which can result in stale data being loaded, causing potential system crashes. Cc: stable<stable@vger.kernel.org> Signed-off-by: Brian King <brking@linux.vnet.ibm.com> --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)