diff mbox series

[net-next,13/15] net/mlx5e: multipath, support routes with more than 2 nexthops

Message ID 20221209001420.142794-14-saeed@kernel.org (mailing list archive)
State Accepted
Commit 7c33e73995e933475985ee0ca3cfa5b335da447e
Delegated to: Netdev Maintainers
Headers show
Series [net-next,01/15] net/mlx5: mlx5_ifc updates for MATCH_DEFINER general object | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Pull request is its own cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 89 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Saeed Mahameed Dec. 9, 2022, 12:14 a.m. UTC 
From: Maor Dickman <maord@nvidia.com>

Today multipath offload is only supported when the number of
nexthops is 2 which block the use of it in case of system with
2 NICs.

This patch solve it by enabling multipath offload per NIC if
2 nexthops of the route are its uplinks.

Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/lag/mp.c  | 79 +++++++++++--------
 1 file changed, 48 insertions(+), 31 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
index 0259a149a64c..d9fcb9ed726f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c
@@ -118,13 +118,41 @@  struct mlx5_fib_event_work {
 	};
 };
 
+static struct net_device*
+mlx5_lag_get_next_fib_dev(struct mlx5_lag *ldev,
+			  struct fib_info *fi,
+			  struct net_device *current_dev)
+{
+	struct net_device *fib_dev;
+	int i, ldev_idx, nhs;
+
+	nhs = fib_info_num_path(fi);
+	i = 0;
+	if (current_dev) {
+		for (; i < nhs; i++) {
+			fib_dev = fib_info_nh(fi, i)->fib_nh_dev;
+			if (fib_dev == current_dev) {
+				i++;
+				break;
+			}
+		}
+	}
+	for (; i < nhs; i++) {
+		fib_dev = fib_info_nh(fi, i)->fib_nh_dev;
+		ldev_idx = mlx5_lag_dev_get_netdev_idx(ldev, fib_dev);
+		if (ldev_idx >= 0)
+			return ldev->pf[ldev_idx].netdev;
+	}
+
+	return NULL;
+}
+
 static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event,
 				     struct fib_entry_notifier_info *fen_info)
 {
+	struct net_device *nh_dev0, *nh_dev1;
 	struct fib_info *fi = fen_info->fi;
 	struct lag_mp *mp = &ldev->lag_mp;
-	struct fib_nh *fib_nh0, *fib_nh1;
-	unsigned int nhs;
 
 	/* Handle delete event */
 	if (event == FIB_EVENT_ENTRY_DEL) {
@@ -140,16 +168,25 @@  static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event,
 	    fi->fib_priority >= mp->fib.priority)
 		return;
 
+	nh_dev0 = mlx5_lag_get_next_fib_dev(ldev, fi, NULL);
+	nh_dev1 = mlx5_lag_get_next_fib_dev(ldev, fi, nh_dev0);
+
 	/* Handle add/replace event */
-	nhs = fib_info_num_path(fi);
-	if (nhs == 1) {
-		if (__mlx5_lag_is_active(ldev)) {
-			struct fib_nh *nh = fib_info_nh(fi, 0);
-			struct net_device *nh_dev = nh->fib_nh_dev;
-			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev);
+	if (!nh_dev0) {
+		if (mp->fib.dst == fen_info->dst && mp->fib.dst_len == fen_info->dst_len)
+			mp->fib.mfi = NULL;
+		return;
+	}
 
-			if (i < 0)
-				return;
+	if (nh_dev0 == nh_dev1) {
+		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+			       "Multipath offload doesn't support routes with multiple nexthops of the same device");
+		return;
+	}
+
+	if (!nh_dev1) {
+		if (__mlx5_lag_is_active(ldev)) {
+			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev0);
 
 			i++;
 			mlx5_lag_set_port_affinity(ldev, i);
@@ -159,21 +196,6 @@  static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event,
 		return;
 	}
 
-	if (nhs != 2)
-		return;
-
-	/* Verify next hops are ports of the same hca */
-	fib_nh0 = fib_info_nh(fi, 0);
-	fib_nh1 = fib_info_nh(fi, 1);
-	if (!(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev) &&
-	    !(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev)) {
-		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
-			       "Multipath offload require two ports of the same HCA\n");
-		return;
-	}
-
 	/* First time we see multipath route */
 	if (!mp->fib.mfi && !__mlx5_lag_is_active(ldev)) {
 		struct lag_tracker tracker;
@@ -268,7 +290,6 @@  static int mlx5_lag_fib_event(struct notifier_block *nb,
 	struct mlx5_fib_event_work *fib_work;
 	struct fib_entry_notifier_info *fen_info;
 	struct fib_nh_notifier_info *fnh_info;
-	struct net_device *fib_dev;
 	struct fib_info *fi;
 
 	if (info->family != AF_INET)
@@ -285,11 +306,7 @@  static int mlx5_lag_fib_event(struct notifier_block *nb,
 		fi = fen_info->fi;
 		if (fi->nh)
 			return NOTIFY_DONE;
-		fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
-		if (fib_dev != ldev->pf[MLX5_LAG_P1].netdev &&
-		    fib_dev != ldev->pf[MLX5_LAG_P2].netdev) {
-			return NOTIFY_DONE;
-		}
+
 		fib_work = mlx5_lag_init_fib_work(ldev, event);
 		if (!fib_work)
 			return NOTIFY_DONE;