[1/3] common/sfc_efx/base: fix MAE match spec validation helper

Message ID 20210106100601.29299-1-ivan.malov@oktetlabs.ru (mailing list archive)
State Accepted, archived
Delegated to: Ferruh Yigit
Headers
Series [1/3] common/sfc_efx/base: fix MAE match spec validation helper |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Ivan Malov Jan. 6, 2021, 10:05 a.m. UTC
  A particular FW version is aware of some set of match fields.
Depending on FW configuration and match specification type, a
known field may not necessarily be allowed to have a non-zero
mask. FW communicates such restrictions via field capabilities
MCDI. Newer FW may be aware of more fields. For such fields,
older FW simply does not report any capabilities.

A situation may occur when libefx is aware of a match field
which the FW is unaware of (eg., older FW), that is, FW does
not report capability status for this field. In this case,
libefx must consider such field as unsupported and demand
all-zeros mask for it when validating match specifications.

Currently, the helper in question simply exits and reports
that the specification is valid when it encounters a field
with no capability status available. This is clearly wrong.

Introduce the missing check to fix the problem.

Fixes: 34285fd0891d ("common/sfc_efx/base: add match spec validate API")
Cc: stable@dpdk.org

Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
---
 drivers/common/sfc_efx/base/efx_mae.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
  

Comments

Ferruh Yigit Jan. 18, 2021, 9:05 a.m. UTC | #1
On 1/6/2021 10:05 AM, Ivan Malov wrote:
> A particular FW version is aware of some set of match fields.
> Depending on FW configuration and match specification type, a
> known field may not necessarily be allowed to have a non-zero
> mask. FW communicates such restrictions via field capabilities
> MCDI. Newer FW may be aware of more fields. For such fields,
> older FW simply does not report any capabilities.
> 
> A situation may occur when libefx is aware of a match field
> which the FW is unaware of (eg., older FW), that is, FW does
> not report capability status for this field. In this case,
> libefx must consider such field as unsupported and demand
> all-zeros mask for it when validating match specifications.
> 
> Currently, the helper in question simply exits and reports
> that the specification is valid when it encounters a field
> with no capability status available. This is clearly wrong.
> 
> Introduce the missing check to fix the problem.
> 
> Fixes: 34285fd0891d ("common/sfc_efx/base: add match spec validate API")
> Cc: stable@dpdk.org
> 
> Reviewed-by: Andy Moreton <amoreton@xilinx.com>
> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
> Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>

Series applied to dpdk-next-net/main, thanks.
  

Patch

diff --git a/drivers/common/sfc_efx/base/efx_mae.c b/drivers/common/sfc_efx/base/efx_mae.c
index a54d5f6e6..ef15deb10 100644
--- a/drivers/common/sfc_efx/base/efx_mae.c
+++ b/drivers/common/sfc_efx/base/efx_mae.c
@@ -885,8 +885,17 @@  efx_mae_match_spec_is_valid(
 		if (m_size == 0)
 			continue; /* Skip array gap */
 
-		if ((unsigned int)field_cap_id >= field_ncaps)
-			break;
+		if ((unsigned int)field_cap_id >= field_ncaps) {
+			/*
+			 * The FW has not reported capability status for
+			 * this field. Make sure that its mask is zeroed.
+			 */
+			is_valid = efx_mask_is_all_zeros(m_size, m_buf);
+			if (is_valid != B_FALSE)
+				continue;
+			else
+				break;
+		}
 
 		switch (field_caps[field_cap_id].emfc_support) {
 		case MAE_FIELD_SUPPORTED_MATCH_MASK: