mlx4_core: Support multiple pre-reserved QP regions

For ethernet support, we need to reserve QPs for the ethernet and
fibre channel driver.  The QPs are reserved at the end of the QP
table.  (This way we assure that they are aligned to their size)

We need to consider these reserved ranges in bitmap creation, so we
extend the mlx4 bitmap utility functions to allow reserved ranges at
both the bottom and the top of the range.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

12 files changed, 126 insertions, 28 deletions

diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index e6c0d5bb5dc..e2bc7ecf162 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -47,13 +47,16 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 
 	obj = find_next_zero_bit(bitmap->table, bitmap->max, bitmap->last);
 	if (obj >= bitmap->max) {
-		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
 		obj = find_first_zero_bit(bitmap->table, bitmap->max);
 	}
 
 	if (obj < bitmap->max) {
 		set_bit(obj, bitmap->table);
-		bitmap->last = (obj + 1) & (bitmap->max - 1);
+		bitmap->last = (obj + 1);
+		if (bitmap->last == bitmap->max)
+			bitmap->last = 0;
 		obj |= bitmap->top;
 	} else
 		obj = -1;
@@ -109,9 +112,9 @@ u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
 	obj = find_aligned_range(bitmap->table, bitmap->last,
 				 bitmap->max, cnt, align);
 	if (obj >= bitmap->max) {
-		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
-		obj = find_aligned_range(bitmap->table, 0,
-					 bitmap->max,
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
+		obj = find_aligned_range(bitmap->table, 0, bitmap->max,
 					 cnt, align);
 	}
 
@@ -136,17 +139,19 @@ void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
 {
 	u32 i;
 
-	obj &= bitmap->max - 1;
+	obj &= bitmap->max + bitmap->reserved_top - 1;
 
 	spin_lock(&bitmap->lock);
 	for (i = 0; i < cnt; i++)
 		clear_bit(obj + i, bitmap->table);
 	bitmap->last = min(bitmap->last, obj);
-	bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+	bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+			& bitmap->mask;
 	spin_unlock(&bitmap->lock);
 }
 
-int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved)
+int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
+		     u32 reserved_bot, u32 reserved_top)
 {
 	int i;
 
@@ -156,14 +161,16 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved
 
 	bitmap->last = 0;
 	bitmap->top  = 0;
-	bitmap->max  = num;
+	bitmap->max  = num - reserved_top;
 	bitmap->mask = mask;
+	bitmap->reserved_top = reserved_top;
 	spin_lock_init(&bitmap->lock);
-	bitmap->table = kzalloc(BITS_TO_LONGS(num) * sizeof (long), GFP_KERNEL);
+	bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
+				sizeof (long), GFP_KERNEL);
 	if (!bitmap->table)
 		return -ENOMEM;
 
-	for (i = 0; i < reserved; ++i)
+	for (i = 0; i < reserved_bot; ++i)
 		set_bit(i, bitmap->table);
 
 	return 0;
diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 9bb50e3f897..b7ad2829d67 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -300,7 +300,7 @@ int mlx4_init_cq_table(struct mlx4_dev *dev)
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
 	err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
-			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs);
+			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 8a8b56135a5..de169338cd9 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -558,7 +558,7 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	int i;
 
 	err = mlx4_bitmap_init(&priv->eq_table.bitmap, dev->caps.num_eqs,
-			       dev->caps.num_eqs - 1, dev->caps.reserved_eqs);
+			       dev->caps.num_eqs - 1, dev->caps.reserved_eqs, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 7e32955da98..40d8142c23b 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -357,6 +357,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_PORT_MTU_OFFSET			0x01
 #define QUERY_PORT_WIDTH_OFFSET			0x06
 #define QUERY_PORT_MAX_GID_PKEY_OFFSET		0x07
+#define QUERY_PORT_MAX_MACVLAN_OFFSET		0x0a
 #define QUERY_PORT_MAX_VL_OFFSET		0x0b
 
 		for (i = 1; i <= dev_cap->num_ports; ++i) {
@@ -374,6 +375,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			dev_cap->max_pkeys[i]	   = 1 << (field & 0xf);
 			MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
 			dev_cap->max_vl[i]	   = field & 0xf;
+			MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
+			dev_cap->log_max_macs[i]  = field & 0xf;
+			dev_cap->log_max_vlans[i] = field >> 4;
+
 		}
 	}
 
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index decbb5c2ad4..c34e726d66e 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -102,6 +102,8 @@ struct mlx4_dev_cap {
 	u32 reserved_lkey;
 	u64 max_icm_sz;
 	int max_gso_sz;
+	u8  log_max_macs[MLX4_MAX_PORTS + 1];
+	u8  log_max_vlans[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_adapter {
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 1252a919de2..560e1962212 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -85,6 +85,19 @@ static struct mlx4_profile default_profile = {
 	.num_mtt	= 1 << 20,
 };
 
+static int log_num_mac = 2;
+module_param_named(log_num_mac, log_num_mac, int, 0444);
+MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
+
+static int log_num_vlan;
+module_param_named(log_num_vlan, log_num_vlan, int, 0444);
+MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
+
+static int use_prio;
+module_param_named(use_prio, use_prio, bool, 0444);
+MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
+		  "(0/1, default 0)");
+
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	int err;
@@ -134,7 +147,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rq_sg	     = dev_cap->max_rq_sg;
 	dev->caps.max_wqes	     = dev_cap->max_qp_sz;
 	dev->caps.max_qp_init_rdma   = dev_cap->max_requester_per_qp;
-	dev->caps.reserved_qps	     = dev_cap->reserved_qps;
 	dev->caps.max_srq_wqes	     = dev_cap->max_srq_sz;
 	dev->caps.max_srq_sge	     = dev_cap->max_rq_sg - 1;
 	dev->caps.reserved_srqs	     = dev_cap->reserved_srqs;
@@ -163,6 +175,39 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
+	dev->caps.log_num_macs  = log_num_mac;
+	dev->caps.log_num_vlans = log_num_vlan;
+	dev->caps.log_num_prios = use_prio ? 3 : 0;
+
+	for (i = 1; i <= dev->caps.num_ports; ++i) {
+		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
+			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
+			mlx4_warn(dev, "Requested number of MACs is too much "
+				  "for port %d, reducing to %d.\n",
+				  i, 1 << dev->caps.log_num_macs);
+		}
+		if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
+			dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
+			mlx4_warn(dev, "Requested number of VLANs is too much "
+				  "for port %d, reducing to %d.\n",
+				  i, 1 << dev->caps.log_num_vlans);
+		}
+	}
+
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
+		(1 << dev->caps.log_num_macs) *
+		(1 << dev->caps.log_num_vlans) *
+		(1 << dev->caps.log_num_prios) *
+		dev->caps.num_ports;
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
+
+	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH];
+
 	return 0;
 }
 
@@ -211,7 +256,8 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 				  ((u64) (MLX4_CMPT_TYPE_QP *
 					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
 				  cmpt_entry_sz, dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err)
 		goto err;
 
@@ -336,7 +382,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->qpc_base,
 				  dev_cap->qpc_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map QP context memory, aborting.\n");
 		goto err_unmap_dmpt;
@@ -346,7 +393,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->auxc_base,
 				  dev_cap->aux_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n");
 		goto err_unmap_qp;
@@ -356,7 +404,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->altc_base,
 				  dev_cap->altc_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n");
 		goto err_unmap_auxc;
@@ -366,7 +415,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->rdmarc_base,
 				  dev_cap->rdmarc_entry_sz << priv->qp_table.rdmarc_shift,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map RDMARC context memory, aborting\n");
 		goto err_unmap_altc;
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index c83f88ce073..592c01ae2c5 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -368,8 +368,8 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int err;
 
-	err = mlx4_bitmap_init(&priv->mcg_table.bitmap,
-			       dev->caps.num_amgms, dev->caps.num_amgms - 1, 0);
+	err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms,
+			       dev->caps.num_amgms - 1, 0, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index b55ddab73f6..9e2f44c3181 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -111,6 +111,7 @@ struct mlx4_bitmap {
 	u32			last;
 	u32			top;
 	u32			max;
+	u32                     reserved_top;
 	u32			mask;
 	spinlock_t		lock;
 	unsigned long	       *table;
@@ -290,7 +291,8 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj);
 u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt);
-int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved);
+int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
+		     u32 reserved_bot, u32 resetrved_top);
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap);
 
 int mlx4_reset(struct mlx4_dev *dev);
diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c
index d1dd5b48dbd..0caf74cae8b 100644
--- a/drivers/net/mlx4/mr.c
+++ b/drivers/net/mlx4/mr.c
@@ -461,7 +461,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 	int err;
 
 	err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts,
-			       ~0, dev->caps.reserved_mrws);
+			       ~0, dev->caps.reserved_mrws, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c
index aa616892d09..26d1a7a9e37 100644
--- a/drivers/net/mlx4/pd.c
+++ b/drivers/net/mlx4/pd.c
@@ -62,7 +62,7 @@ int mlx4_init_pd_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	return mlx4_bitmap_init(&priv->pd_bitmap, dev->caps.num_pds,
-				(1 << 24) - 1, dev->caps.reserved_pds);
+				(1 << 24) - 1, dev->caps.reserved_pds, 0);
 }
 
 void mlx4_cleanup_pd_table(struct mlx4_dev *dev)
@@ -100,7 +100,7 @@ int mlx4_init_uar_table(struct mlx4_dev *dev)
 
 	return mlx4_bitmap_init(&mlx4_priv(dev)->uar_table.bitmap,
 				dev->caps.num_uars, dev->caps.num_uars - 1,
-				max(128, dev->caps.reserved_uars));
+				max(128, dev->caps.reserved_uars), 0);
 }
 
 void mlx4_cleanup_uar_table(struct mlx4_dev *dev)
diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c
index 98e0c40ba36..1c565ef8d17 100644
--- a/drivers/net/mlx4/qp.c
+++ b/drivers/net/mlx4/qp.c
@@ -272,6 +272,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
 	int err;
+	int reserved_from_top = 0;
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
@@ -281,9 +282,40 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	 * block of special QPs must be aligned to a multiple of 8, so
 	 * round up.
 	 */
-	dev->caps.sqp_start = ALIGN(dev->caps.reserved_qps, 8);
+	dev->caps.sqp_start =
+		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
+
+	{
+		int sort[MLX4_NUM_QP_REGION];
+		int i, j, tmp;
+		int last_base = dev->caps.num_qps;
+
+		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
+			sort[i] = i;
+
+		for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
+			for (j = 2; j < i; ++j) {
+				if (dev->caps.reserved_qps_cnt[sort[j]] >
+				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
+					tmp             = sort[j];
+					sort[j]         = sort[j - 1];
+					sort[j - 1]     = tmp;
+				}
+			}
+		}
+
+		for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
+			last_base -= dev->caps.reserved_qps_cnt[sort[i]];
+			dev->caps.reserved_qps_base[sort[i]] = last_base;
+			reserved_from_top +=
+				dev->caps.reserved_qps_cnt[sort[i]];
+		}
+
+	}
+
 	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
-			       (1 << 24) - 1, dev->caps.sqp_start + 8);
+			       (1 << 23) - 1, dev->caps.sqp_start + 8,
+			       reserved_from_top);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/srq.c b/drivers/net/mlx4/srq.c
index 533eb6db24b..fe9f218691f 100644
--- a/drivers/net/mlx4/srq.c
+++ b/drivers/net/mlx4/srq.c
@@ -245,7 +245,7 @@ int mlx4_init_srq_table(struct mlx4_dev *dev)
 	INIT_RADIX_TREE(&srq_table->tree, GFP_ATOMIC);
 
 	err = mlx4_bitmap_init(&srq_table->bitmap, dev->caps.num_srqs,
-			       dev->caps.num_srqs - 1, dev->caps.reserved_srqs);
+			       dev->caps.num_srqs - 1, dev->caps.reserved_srqs, 0);
 	if (err)
 		return err;