Merge branch 'mlx4-next'

Or Gerlitz says:

====================
Mellanox ethernet driver update Oct-30-2014

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.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 159 insertions, 25 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 916459effcfa..3c05e5878b49 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,
@@ -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/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c562c1468944..b173a0cf44e0 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().
 	 */
@@ -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;
@@ -945,15 +946,8 @@ 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 +960,10 @@ 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/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 72289ef5ebbe..d6dba77ae4ba 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);
 
@@ -2220,7 +2300,7 @@ 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 +2343,31 @@ 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/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 90de6e1ad06e..9f821964a1b9 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;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index de10dbb2e6ed..f8fc7bd6f48b 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,
@@ -1273,6 +1278,11 @@ 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);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 6beb4d34dce0..ef83d127f406 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
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 5d2498dcf536..d718ca0f88da 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)
 {