[pull request][RESEND net 0/3] Mellanox, mlx5 fixes 2018-09-17

[pull request][RESEND net 0/3] Mellanox, mlx5 fixes 2018-09-17

[Saeed Mahameed]

Hi Dave,

Sorry about the previous submission of this series which was mistakenly
marked for net-next, here I am resending with 'net' mark.

This series provides three fixes to mlx5 core and mlx5e netdevice
driver.

Please pull and let me know if there's any problem.

For -stable v4.16:
('net/mlx5: Check for SQ and not RQ state when modifying hairpin SQ')

Thanks,
Saeed.

---

The following changes since commit c73480910e9686a5c25155cb4d418d594b678196:

  net: ethernet: Fix a unused function warning. (2018-09-17 08:24:25 -0700)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5-fixes-2018-09-17

for you to fetch changes up to 8f92e35aff9692028279d3c03e88547df6d15020:

  net/mlx5e: TLS, Read capabilities only when it is safe (2018-09-17 15:12:31 -0700)

----------------------------------------------------------------
mlx5-fixes-2018-09-17

----------------------------------------------------------------
Alaa Hleihel (1):
      net/mlx5: Check for SQ and not RQ state when modifying hairpin SQ

Eli Cohen (1):
      net/mlx5: Fix read from coherent memory

Saeed Mahameed (1):
      net/mlx5e: TLS, Read capabilities only when it is safe

 drivers/net/ethernet/mellanox/mlx5/core/cmd.c          | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c     | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

[RESEND net 1/3] net/mlx5: Fix read from coherent memory

[Saeed Mahameed]

From: Eli Cohen <eli@mellanox.com>

Use accessor function READ_ONCE to read from coherent memory modified
by the device and read by the driver. This becomes most important in
preemptive kernels where cond_resched implementation does not have the
side effect which guaranteed the updated value.

Fixes: 269d26f47f6f ("net/mlx5: Reduce command polling interval")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3ce14d42ddc8..a53736c26c0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -206,7 +206,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 	u8 own;
 
 	do {
-		own = ent->lay->status_own;
+		own = READ_ONCE(ent->lay->status_own);
 		if (!(own & CMD_OWNER_HW)) {
 			ent->ret = 0;
 			return;
-- 
2.17.1

[RESEND net 2/3] net/mlx5: Check for SQ and not RQ state when modifying hairpin SQ

[Saeed Mahameed]

From: Alaa Hleihel <alaa@mellanox.com>

When modifying hairpin SQ, instead of checking if the next state equals
to MLX5_SQC_STATE_RDY, we compare it against the MLX5_RQC_STATE_RDY enum
value.

The code worked since both of MLX5_RQC_STATE_RDY and MLX5_SQC_STATE_RDY
have the same value today.

This patch fixes this issue.

Fixes: 18e568c390c6 ("net/mlx5: Hairpin pair core object setup")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index dae1c5c5d27c..d2f76070ea7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -509,7 +509,7 @@ static int mlx5_hairpin_modify_sq(struct mlx5_core_dev *peer_mdev, u32 sqn,
 
 	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
 
-	if (next_state == MLX5_RQC_STATE_RDY) {
+	if (next_state == MLX5_SQC_STATE_RDY) {
 		MLX5_SET(sqc, sqc, hairpin_peer_rq, peer_rq);
 		MLX5_SET(sqc, sqc, hairpin_peer_vhca, peer_vhca);
 	}
-- 
2.17.1

[RESEND net 3/3] net/mlx5e: TLS, Read capabilities only when it is safe

[Saeed Mahameed]

Read TLS caps from the core driver only when TLS is supported, i.e
mlx5_accel_is_tls_device returns true.

Fixes: 790af90c00d2 ("net/mlx5e: TLS, build TLS netdev from capabilities")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index eddd7702680b..e88340e196f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -183,12 +183,13 @@ static const struct tlsdev_ops mlx5e_tls_ops = {
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
-	u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
 	struct net_device *netdev = priv->netdev;
+	u32 caps;
 
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
+	caps = mlx5_accel_tls_device_caps(priv->mdev);
 	if (caps & MLX5_ACCEL_TLS_TX) {
 		netdev->features          |= NETIF_F_HW_TLS_TX;
 		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
-- 
2.17.1

Re: [pull request][RESEND net 0/3] Mellanox, mlx5 fixes 2018-09-17

[David Miller]

From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 17 Sep 2018 20:49:25 -0700

> Sorry about the previous submission of this series which was mistakenly
> marked for net-next, here I am resending with 'net' mark.
> 
> This series provides three fixes to mlx5 core and mlx5e netdevice
> driver.
> 
> Please pull and let me know if there's any problem.

Puled.

> For -stable v4.16:
> ('net/mlx5: Check for SQ and not RQ state when modifying hairpin SQ')

Queued up.

Thanks.