[PATCH V1 net-next 0/5] Mellanox ethernet driver update Oct-30-2014

[PATCH V1 net-next 0/5] Mellanox ethernet driver update Oct-30-2014

[Or Gerlitz]

Hi Dave,

The 1st patch from Saeed fixes a bug in the last net-next batch where
a VF could get access to set port configuration, the next patch from Amir
fixes a race in the port VPI logic. Next are two performance patches from Ido.

The patch to add checksum complete status on GRE and such packets was 
preceded with a patch that converted the driver to only use napi_gro_receive 
vs. the current code which goes through napi_gro_frags on it's usual track.
Eric D. has some thoughts and suggestions on that change for which we 
want to take the time and consider, so for the time being dropped that
patch and the ones that depend on it.

Or.

Changes from V0:
  - have the caller to provide the __GFP_COLD hint to the service function
  - dropped the patch that changes the GRO logic and the subsequent dependent
    patches. 

Amir Vadai (1):
  net/mlx4_core: Protect port type setting by mutex

Ido Shamay (2):
  net/mlx4_en: Remove RX buffers alignment to IP_ALIGN
  net/mlx4_en: Add __GFP_COLD gfp flags in alloc_pages

Matan Barak (1):
  net/mlx4_core: Add retrieval of CONFIG_DEV parameters

Saeed Mahameed (1):
  net/mlx4_core: Prevent VF from changing port configuration

 drivers/net/ethernet/mellanox/mlx4/cmd.c           |    6 +-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c         |   23 ++---
 drivers/net/ethernet/mellanox/mlx4/fw.c            |  118 +++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/main.c          |    9 ++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |   10 ++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h       |    1 -
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |   17 +++
 include/linux/mlx4/cmd.h                           |   29 +++++
 include/linux/mlx4/device.h                        |    3 +-
 9 files changed, 190 insertions(+), 26 deletions(-)

[PATCH V1 net-next 1/5] net/mlx4_core: Prevent VF from changing port configuration

[Or Gerlitz]

From: Saeed Mahameed <saeedm@mellanox.com>

Added wrapper to the ACCESS_REG command for handling guest HW
registers access, preventing write operations, but do allow reads.

This will prevent SRIOV guests to change port PTYS configuration,
such as speed/advertised link modes.

Fixes: adbc7ac5c15e ('net/mlx4_core: Introduce ACCESS_REG CMD [...]')
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c  |    2 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c   |   30 ++++++++++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |    5 ++++
 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 916459e..1312ccf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1345,7 +1345,7 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = NULL,
+		.wrapper = mlx4_ACCESS_REG_wrapper,
 	},
 	/* Native multicast commands are not available for guests */
 	{
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 72289ef..e7639e3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2220,7 +2220,7 @@ static int mlx4_ACCESS_REG(struct mlx4_dev *dev, u16 reg_id,
 	memcpy(inbuf->reg_data, reg_data, reg_len);
 	err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, 0, 0,
 			   MLX4_CMD_ACCESS_REG, MLX4_CMD_TIME_CLASS_C,
-			   MLX4_CMD_NATIVE);
+			   MLX4_CMD_WRAPPED);
 	if (err)
 		goto out;
 
@@ -2263,3 +2263,31 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
 			       method, sizeof(*ptys_reg), ptys_reg);
 }
 EXPORT_SYMBOL_GPL(mlx4_ACCESS_PTYS_REG);
+
+int mlx4_ACCESS_REG_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_access_reg *inbuf = inbox->buf;
+	u8 method = inbuf->method & MLX4_ACCESS_REG_METHOD_MASK;
+	u16 reg_id = be16_to_cpu(inbuf->reg_id);
+
+	if (slave != mlx4_master_func_num(dev) &&
+	    method == MLX4_ACCESS_REG_WRITE)
+		return -EPERM;
+
+	if (reg_id == MLX4_REG_ID_PTYS) {
+		struct mlx4_ptys_reg *ptys_reg =
+			(struct mlx4_ptys_reg *)inbuf->reg_data;
+
+		ptys_reg->local_port =
+			mlx4_slave_convert_port(dev, slave,
+						ptys_reg->local_port);
+	}
+
+	return mlx4_cmd_box(dev, inbox->dma, outbox->dma, vhcr->in_modifier,
+			    0, MLX4_CMD_ACCESS_REG, MLX4_CMD_TIME_CLASS_C,
+			    MLX4_CMD_NATIVE);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index de10dbb..254ec7b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1273,6 +1273,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 					 struct mlx4_cmd_mailbox *inbox,
 					 struct mlx4_cmd_mailbox *outbox,
 					 struct mlx4_cmd_info *cmd);
+int mlx4_ACCESS_REG_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
 
 int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
 int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
-- 
1.7.1

[PATCH V1 net-next 2/5] net/mlx4_core: Protect port type setting by mutex

[Or Gerlitz]

From: Amir Vadai <amirv@mellanox.com>

We need to protect set_port_type() for concurrency, as the sysfs code could
call it from mutliple contexts in parallel.

The port_mutex is not enough because we need to protect from concurrent
modification of 'info' and stopping of the port sensing work.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/main.c |    9 ++++++++-
 1 files changed, 8 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 90de6e1..9f82196 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -901,9 +901,12 @@ static ssize_t set_port_type(struct device *dev,
 	struct mlx4_priv *priv = mlx4_priv(mdev);
 	enum mlx4_port_type types[MLX4_MAX_PORTS];
 	enum mlx4_port_type new_types[MLX4_MAX_PORTS];
+	static DEFINE_MUTEX(set_port_type_mutex);
 	int i;
 	int err = 0;
 
+	mutex_lock(&set_port_type_mutex);
+
 	if (!strcmp(buf, "ib\n"))
 		info->tmp_type = MLX4_PORT_TYPE_IB;
 	else if (!strcmp(buf, "eth\n"))
@@ -912,7 +915,8 @@ static ssize_t set_port_type(struct device *dev,
 		info->tmp_type = MLX4_PORT_TYPE_AUTO;
 	else {
 		mlx4_err(mdev, "%s is not supported port type\n", buf);
-		return -EINVAL;
+		err = -EINVAL;
+		goto err_out;
 	}
 
 	mlx4_stop_sense(mdev);
@@ -958,6 +962,9 @@ static ssize_t set_port_type(struct device *dev,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
+err_out:
+	mutex_unlock(&set_port_type_mutex);
+
 	return err ? err : count;
 }
 
-- 
1.7.1

[PATCH V1 net-next 3/5] net/mlx4_en: Remove RX buffers alignment to IP_ALIGN

[Or Gerlitz]

From: Ido Shamay <idos@mellanox.com>

When IP_ALIGN has a non zero value, hardware will write to a non aligned
address. The only reader from this address is when copying the header
from the first frag into the linear buffer (further access to the IP
address will be from the linear buffer, in which the headers are
aligned). Since the penalty of non align access by the hardware is
greater than the software memcpy, changing the frag_align to always be 0.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   |   16 ++++------------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |    1 -
 2 files changed, 4 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c8e75da..4cb716f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -74,7 +74,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 	page_alloc->page_size = PAGE_SIZE << order;
 	page_alloc->page = page;
 	page_alloc->dma = dma;
-	page_alloc->page_offset = frag_info->frag_align;
+	page_alloc->page_offset = 0;
 	/* Not doing get_page() for each frag is a big win
 	 * on asymetric workloads. Note we can not use atomic_set().
 	 */
@@ -945,15 +945,8 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 			(eff_mtu > buf_size + frag_sizes[i]) ?
 				frag_sizes[i] : eff_mtu - buf_size;
 		priv->frag_info[i].frag_prefix_size = buf_size;
-		if (!i)	{
-			priv->frag_info[i].frag_align = NET_IP_ALIGN;
-			priv->frag_info[i].frag_stride =
-				ALIGN(frag_sizes[i] + NET_IP_ALIGN, SMP_CACHE_BYTES);
-		} else {
-			priv->frag_info[i].frag_align = 0;
-			priv->frag_info[i].frag_stride =
-				ALIGN(frag_sizes[i], SMP_CACHE_BYTES);
-		}
+		priv->frag_info[i].frag_stride = ALIGN(frag_sizes[i],
+						       SMP_CACHE_BYTES);
 		buf_size += priv->frag_info[i].frag_size;
 		i++;
 	}
@@ -966,11 +959,10 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	       eff_mtu, priv->num_frags);
 	for (i = 0; i < priv->num_frags; i++) {
 		en_err(priv,
-		       "  frag:%d - size:%d prefix:%d align:%d stride:%d\n",
+		       "  frag:%d - size:%d prefix:%d stride:%d\n",
 		       i,
 		       priv->frag_info[i].frag_size,
 		       priv->frag_info[i].frag_prefix_size,
-		       priv->frag_info[i].frag_align,
 		       priv->frag_info[i].frag_stride);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 6beb4d3..ef83d12 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -481,7 +481,6 @@ struct mlx4_en_frag_info {
 	u16 frag_size;
 	u16 frag_prefix_size;
 	u16 frag_stride;
-	u16 frag_align;
 };
 
 #ifdef CONFIG_MLX4_EN_DCB
-- 
1.7.1

[PATCH V1 net-next 4/5] net/mlx4_en: Add __GFP_COLD gfp flags in alloc_pages

[Or Gerlitz]

From: Ido Shamay <idos@mellanox.com>

Needed in order to get cache cold pages (L3 flushed) for HW scatter.

Otherwise memory may flush those entries when the packet comes from
PCI, causing back pressure resulting in BW decrease.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c |    7 ++++---
 1 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4cb716f..317abc9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -156,7 +156,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 		const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
 
 		if (mlx4_alloc_pages(priv, &ring->page_alloc[i],
-				     frag_info, GFP_KERNEL))
+				     frag_info, GFP_KERNEL | __GFP_COLD))
 			goto out;
 	}
 	return 0;
@@ -268,7 +268,7 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
 
 			if (mlx4_en_prepare_rx_desc(priv, ring,
 						    ring->actual_size,
-						    GFP_KERNEL)) {
+						    GFP_KERNEL | __GFP_COLD)) {
 				if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) {
 					en_err(priv, "Failed to allocate enough rx buffers\n");
 					return -ENOMEM;
@@ -635,7 +635,8 @@ static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
 	int index = ring->prod & ring->size_mask;
 
 	while ((u32) (ring->prod - ring->cons) < ring->actual_size) {
-		if (mlx4_en_prepare_rx_desc(priv, ring, index, GFP_ATOMIC))
+		if (mlx4_en_prepare_rx_desc(priv, ring, index,
+					    GFP_ATOMIC | __GFP_COLD))
 			break;
 		ring->prod++;
 		index = ring->prod & ring->size_mask;
-- 
1.7.1

[PATCH V1 net-next 5/5] net/mlx4_core: Add retrieval of CONFIG_DEV parameters

[Or Gerlitz]

From: Matan Barak <matanb@mellanox.com>

Add code to issue CONFIG_DEV "get" firmware command.

This command is used in order to obtain certain parameters used for
supporting various RX checksumming options and vxlan UDP port.

The GET operation is allowed for VFs too.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c           |    4 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c            |   88 +++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |    5 +
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |   17 ++++
 include/linux/mlx4/cmd.h                           |   29 +++++++
 include/linux/mlx4/device.h                        |    3 +-
 6 files changed, 139 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 1312ccf..3c05e58 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -990,11 +990,11 @@ static struct mlx4_cmd_info cmd_info[] = {
 	{
 		.opcode = MLX4_CMD_CONFIG_DEV,
 		.has_inbox = false,
-		.has_outbox = false,
+		.has_outbox = true,
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = mlx4_CMD_EPERM_wrapper
+		.wrapper = mlx4_CONFIG_DEV_wrapper
 	},
 	{
 		.opcode = MLX4_CMD_ALLOC_RES,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e7639e3..d6dba77 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -141,7 +141,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[12] = "Large cache line (>64B) CQE stride support",
 		[13] = "Large cache line (>64B) EQE stride support",
 		[14] = "Ethernet protocol control support",
-		[15] = "Ethernet Backplane autoneg support"
+		[15] = "Ethernet Backplane autoneg support",
+		[16] = "CONFIG DEV support"
 	};
 	int i;
 
@@ -574,6 +575,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MTT_ENTRY_SZ_OFFSET	0x90
 #define QUERY_DEV_CAP_D_MPT_ENTRY_SZ_OFFSET	0x92
 #define QUERY_DEV_CAP_BMME_FLAGS_OFFSET		0x94
+#define QUERY_DEV_CAP_CONFIG_DEV_OFFSET		0x94
 #define QUERY_DEV_CAP_RSVD_LKEY_OFFSET		0x98
 #define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET		0xa0
 #define QUERY_DEV_CAP_ETH_BACKPL_OFFSET		0x9c
@@ -749,6 +751,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
 	MLX4_GET(dev_cap->bmme_flags, outbox,
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_CONFIG_DEV_OFFSET);
+	if (field & 0x20)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV;
 	MLX4_GET(dev_cap->reserved_lkey, outbox,
 		 QUERY_DEV_CAP_RSVD_LKEY_OFFSET);
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_ETH_BACKPL_OFFSET);
@@ -1849,14 +1854,18 @@ int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
 
 struct mlx4_config_dev {
 	__be32	update_flags;
-	__be32	rsdv1[3];
+	__be32	rsvd1[3];
 	__be16	vxlan_udp_dport;
 	__be16	rsvd2;
+	__be32	rsvd3[27];
+	__be16	rsvd4;
+	u8	rsvd5;
+	u8	rx_checksum_val;
 };
 
 #define MLX4_VXLAN_UDP_DPORT (1 << 0)
 
-static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+static int mlx4_CONFIG_DEV_set(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
 {
 	int err;
 	struct mlx4_cmd_mailbox *mailbox;
@@ -1874,6 +1883,77 @@ static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_
 	return err;
 }
 
+static int mlx4_CONFIG_DEV_get(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+{
+	int err;
+	struct mlx4_cmd_mailbox *mailbox;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 1, MLX4_CMD_CONFIG_DEV,
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+	if (!err)
+		memcpy(config_dev, mailbox->buf, sizeof(*config_dev));
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+/* Conversion between the HW values and the actual functionality.
+ * The value represented by the array index,
+ * and the functionality determined by the flags.
+ */
+static const u8 config_dev_csum_flags[] = {
+	[0] =	0,
+	[1] =	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP,
+	[2] =	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP	|
+		MLX4_RX_CSUM_MODE_L4,
+	[3] =	MLX4_RX_CSUM_MODE_L4			|
+		MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP	|
+		MLX4_RX_CSUM_MODE_MULTI_VLAN
+};
+
+int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
+			      struct mlx4_config_dev_params *params)
+{
+	struct mlx4_config_dev config_dev;
+	int err;
+	u8 csum_mask;
+
+#define CONFIG_DEV_RX_CSUM_MODE_MASK			0x7
+#define CONFIG_DEV_RX_CSUM_MODE_PORT1_BIT_OFFSET	0
+#define CONFIG_DEV_RX_CSUM_MODE_PORT2_BIT_OFFSET	4
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_CONFIG_DEV))
+		return -ENOTSUPP;
+
+	err = mlx4_CONFIG_DEV_get(dev, &config_dev);
+	if (err)
+		return err;
+
+	csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT1_BIT_OFFSET) &
+			CONFIG_DEV_RX_CSUM_MODE_MASK;
+
+	if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0]))
+		return -EINVAL;
+	params->rx_csum_flags_port_1 = config_dev_csum_flags[csum_mask];
+
+	csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT2_BIT_OFFSET) &
+			CONFIG_DEV_RX_CSUM_MODE_MASK;
+
+	if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0]))
+		return -EINVAL;
+	params->rx_csum_flags_port_2 = config_dev_csum_flags[csum_mask];
+
+	params->vxlan_udp_dport = be16_to_cpu(config_dev.vxlan_udp_dport);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_config_dev_retrieval);
+
 int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
 {
 	struct mlx4_config_dev config_dev;
@@ -1882,7 +1962,7 @@ int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
 	config_dev.update_flags    = cpu_to_be32(MLX4_VXLAN_UDP_DPORT);
 	config_dev.vxlan_udp_dport = udp_port;
 
-	return mlx4_CONFIG_DEV(dev, &config_dev);
+	return mlx4_CONFIG_DEV_set(dev, &config_dev);
 }
 EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 254ec7b..f8fc7bd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -947,6 +947,11 @@ int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_cmd_mailbox *inbox,
 			  struct mlx4_cmd_mailbox *outbox,
 			  struct mlx4_cmd_info *cmd);
+int mlx4_CONFIG_DEV_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
 int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
 		     struct mlx4_vhcr *vhcr,
 		     struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 5d2498d..d718ca0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2872,6 +2872,23 @@ out_add:
 	return err;
 }
 
+int mlx4_CONFIG_DEV_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd)
+{
+	int err;
+	u8 get = vhcr->op_modifier;
+
+	if (get != 1)
+		return -EPERM;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+	return err;
+}
+
 static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start,
 			      int len, struct res_mtt **res)
 {
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index ff5f5de..64d2594 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -199,6 +199,33 @@ enum {
 	MLX4_CMD_NATIVE
 };
 
+/*
+ * MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP -
+ * Receive checksum value is reported in CQE also for non TCP/UDP packets.
+ *
+ * MLX4_RX_CSUM_MODE_L4 -
+ * L4_CSUM bit in CQE, which indicates whether or not L4 checksum
+ * was validated correctly, is supported.
+ *
+ * MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP -
+ * IP_OK CQE's field is supported also for non TCP/UDP IP packets.
+ *
+ * MLX4_RX_CSUM_MODE_MULTI_VLAN -
+ * Receive Checksum offload is supported for packets with more than 2 vlan headers.
+ */
+enum mlx4_rx_csum_mode {
+	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP		= 1UL << 0,
+	MLX4_RX_CSUM_MODE_L4				= 1UL << 1,
+	MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP		= 1UL << 2,
+	MLX4_RX_CSUM_MODE_MULTI_VLAN			= 1UL << 3
+};
+
+struct mlx4_config_dev_params {
+	u16	vxlan_udp_dport;
+	u8	rx_csum_flags_port_1;
+	u8	rx_csum_flags_port_2;
+};
+
 struct mlx4_dev;
 
 struct mlx4_cmd_mailbox {
@@ -250,6 +277,8 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos);
 int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting);
 int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf);
 int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
+int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
+			      struct mlx4_config_dev_params *params);
 /*
  * mlx4_get_slave_default_vlan -
  * return true if VST ( default vlan)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e4c136e..5cc5eac 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -188,7 +188,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_CQE_STRIDE		= 1LL <<  12,
 	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13,
 	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14,
-	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15
+	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
+	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16
 };
 
 enum {
-- 
1.7.1

Re: [PATCH V1 net-next 5/5] net/mlx4_core: Add retrieval of CONFIG_DEV parameters

[Eric Dumazet]

On Sun, 2014-11-02 at 16:26 +0200, Or Gerlitz wrote:
> From: Matan Barak <matanb@mellanox.com>
> 
> Add code to issue CONFIG_DEV "get" firmware command.
> 
> This command is used in order to obtain certain parameters used for
> supporting various RX checksumming options and vxlan UDP port.
> 
> The GET operation is allowed for VFs too.
> 
> Signed-off-by: Matan Barak <matanb@mellanox.com>
> Signed-off-by: Shani Michaeli <shanim@mellanox.com>
> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
> ---
>  drivers/net/ethernet/mellanox/mlx4/cmd.c           |    4 +-
>  drivers/net/ethernet/mellanox/mlx4/fw.c            |   88 +++++++++++++++++++-
>  drivers/net/ethernet/mellanox/mlx4/mlx4.h          |    5 +
>  .../net/ethernet/mellanox/mlx4/resource_tracker.c  |   17 ++++
>  include/linux/mlx4/cmd.h                           |   29 +++++++
>  include/linux/mlx4/device.h                        |    3 +-
>  6 files changed, 139 insertions(+), 7 deletions(-)

This added following warnings :

  CC      drivers/net/ethernet/mellanox/mlx4/fw.o
drivers/net/ethernet/mellanox/mlx4/fw.c: In function 'mlx4_config_dev_retrieval':
drivers/net/ethernet/mellanox/mlx4/fw.c:1944:12: warning: 'config_dev.rx_checksum_val' may be used uninitialized in this function [-Wmaybe-uninitialized]
In file included from include/linux/swab.h:4:0,
                 from include/uapi/linux/byteorder/little_endian.h:12,
                 from include/linux/byteorder/little_endian.h:4,
                 from ./arch/x86/include/uapi/asm/byteorder.h:4,
                 from include/asm-generic/bitops/le.h:5,
                 from ./arch/x86/include/asm/bitops.h:504,
                 from include/linux/bitops.h:33,
                 from include/linux/kernel.h:10,
                 from include/linux/skbuff.h:17,
                 from include/linux/if_ether.h:23,
                 from include/linux/etherdevice.h:25,
                 from drivers/net/ethernet/mellanox/mlx4/fw.c:35:
include/uapi/linux/swab.h:53:93: warning: 'config_dev.vxlan_udp_dport' may be used uninitialized in this function [-Wmaybe-uninitialized]
drivers/net/ethernet/mellanox/mlx4/fw.c:1922:25: note: 'config_dev.vxlan_udp_dport' was declared here

Re: [PATCH V1 net-next 5/5] net/mlx4_core: Add retrieval of CONFIG_DEV parameters

[Or Gerlitz]

On 11/4/2014 6:48 PM, Eric Dumazet wrote:

> This added following warnings :
>
>    CC      drivers/net/ethernet/mellanox/mlx4/fw.o
> drivers/net/ethernet/mellanox/mlx4/fw.c: In function 'mlx4_config_dev_retrieval':
> drivers/net/ethernet/mellanox/mlx4/fw.c:1944:12: warning: 'config_dev.rx_checksum_val' may be used uninitialized in this function [-Wmaybe-uninitialized]
> In file included from include/linux/swab.h:4:0,
>                   from include/uapi/linux/byteorder/little_endian.h:12,
>                   from include/linux/byteorder/little_endian.h:4,
>                   from ./arch/x86/include/uapi/asm/byteorder.h:4,
>                   from include/asm-generic/bitops/le.h:5,
>                   from ./arch/x86/include/asm/bitops.h:504,
>                   from include/linux/bitops.h:33,
>                   from include/linux/kernel.h:10,
>                   from include/linux/skbuff.h:17,
>                   from include/linux/if_ether.h:23,
>                   from include/linux/etherdevice.h:25,
>                   from drivers/net/ethernet/mellanox/mlx4/fw.c:35:
> include/uapi/linux/swab.h:53:93: warning: 'config_dev.vxlan_udp_dport' may be used uninitialized in this function [-Wmaybe-uninitialized]
> drivers/net/ethernet/mellanox/mlx4/fw.c:1922:25: note: 'config_dev.vxlan_udp_dport' was declared here
>
>

Oh, missed that since we build with CONFIG_CC_OPTIMIZE_FOR_SIZE which 
for some reason cause the kernel Makefile to mask away that warning?!

> ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
> KBUILD_CFLAGS   += -Os $(call cc-disable-warning,maybe-uninitialized,)
> else
> KBUILD_CFLAGS   += -O2
> endif

Anyway, this seems as false positive since just before using the struct 
mlx4_config_dev instance we go through mlx4_CONFIG_DEV_get() which 
either fills in values for the fields or return error and in that case, 
we don't use them... the below patch makes gcc (4.8.2) happy, but it's 
not really needed... thoughts?

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c 
b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d6dba77..9a4703f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1929,7 +1929,7 @@ int mlx4_config_dev_retrieval(struct mlx4_dev *dev,

         if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_CONFIG_DEV))
                 return -ENOTSUPP;
-
+       memset(&config_dev, 0, sizeof(config_dev));
         err = mlx4_CONFIG_DEV_get(dev, &config_dev);
         if (err)
                 return err;

Or.

Re: [PATCH V1 net-next 0/5] Mellanox ethernet driver update Oct-30-2014

[David Miller]

From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun,  2 Nov 2014 16:26:12 +0200

> The 1st patch from Saeed fixes a bug in the last net-next batch where
> a VF could get access to set port configuration, the next patch from Amir
> fixes a race in the port VPI logic. Next are two performance patches from Ido.
> 
> The patch to add checksum complete status on GRE and such packets was 
> preceded with a patch that converted the driver to only use napi_gro_receive 
> vs. the current code which goes through napi_gro_frags on it's usual track.
> Eric D. has some thoughts and suggestions on that change for which we 
> want to take the time and consider, so for the time being dropped that
> patch and the ones that depend on it.
 ...
> Changes from V0:
>   - have the caller to provide the __GFP_COLD hint to the service function
>   - dropped the patch that changes the GRO logic and the subsequent dependent
>     patches. 

Series applied, thanks.