Merge branches 'bkl-removal', 'cma', 'ehca', 'for-2.6.27', 'mlx4', 'mthca' and 'nes...

[pandora-kernel.git] / drivers / net / mlx4 / mr.c

diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c
index 9c9e308..a3c04c5 100644 (file)
--- a/drivers/net/mlx4/mr.c
+++ b/drivers/net/mlx4/mr.c
@@ -47,7 +47,7 @@ struct mlx4_mpt_entry {
        __be32 flags;
        __be32 qpn;
        __be32 key;
-       __be32 pd;
+       __be32 pd_flags;
        __be64 start;
        __be64 length;
        __be32 lkey;
@@ -61,11 +61,15 @@ struct mlx4_mpt_entry {
 } __attribute__((packed));
 
 #define MLX4_MPT_FLAG_SW_OWNS      (0xfUL << 28)
+#define MLX4_MPT_FLAG_FREE         (0x3UL << 28)
 #define MLX4_MPT_FLAG_MIO          (1 << 17)
 #define MLX4_MPT_FLAG_BIND_ENABLE   (1 << 15)
 #define MLX4_MPT_FLAG_PHYSICAL     (1 <<  9)
 #define MLX4_MPT_FLAG_REGION       (1 <<  8)
 
+#define MLX4_MPT_PD_FLAG_FAST_REG   (1 << 26)
+#define MLX4_MPT_PD_FLAG_EN_INV            (3 << 24)
+
 #define MLX4_MTT_FLAG_PRESENT          1
 
 #define MLX4_MPT_STATUS_SW             0xF0
@@ -79,23 +83,26 @@ static u32 mlx4_buddy_alloc(struct mlx4_buddy *buddy, int order)
 
        spin_lock(&buddy->lock);
 
-       for (o = order; o <= buddy->max_order; ++o) {
-               m = 1 << (buddy->max_order - o);
-               seg = find_first_bit(buddy->bits[o], m);
-               if (seg < m)
-                       goto found;
-       }
+       for (o = order; o <= buddy->max_order; ++o)
+               if (buddy->num_free[o]) {
+                       m = 1 << (buddy->max_order - o);
+                       seg = find_first_bit(buddy->bits[o], m);
+                       if (seg < m)
+                               goto found;
+               }
 
        spin_unlock(&buddy->lock);
        return -1;
 
  found:
        clear_bit(seg, buddy->bits[o]);
+       --buddy->num_free[o];
 
        while (o > order) {
                --o;
                seg <<= 1;
                set_bit(seg ^ 1, buddy->bits[o]);
+               ++buddy->num_free[o];
        }
 
        spin_unlock(&buddy->lock);
@@ -113,11 +120,13 @@ static void mlx4_buddy_free(struct mlx4_buddy *buddy, u32 seg, int order)
 
        while (test_bit(seg ^ 1, buddy->bits[order])) {
                clear_bit(seg ^ 1, buddy->bits[order]);
+               --buddy->num_free[order];
                seg >>= 1;
                ++order;
        }
 
        set_bit(seg, buddy->bits[order]);
+       ++buddy->num_free[order];
 
        spin_unlock(&buddy->lock);
 }
@@ -131,7 +140,9 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
        buddy->bits = kzalloc((buddy->max_order + 1) * sizeof (long *),
                              GFP_KERNEL);
-       if (!buddy->bits)
+       buddy->num_free = kzalloc((buddy->max_order + 1) * sizeof (int *),
+                                 GFP_KERNEL);
+       if (!buddy->bits || !buddy->num_free)
                goto err_out;
 
        for (i = 0; i <= buddy->max_order; ++i) {
@@ -143,6 +154,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
        }
 
        set_bit(0, buddy->bits[buddy->max_order]);
+       buddy->num_free[buddy->max_order] = 1;
 
        return 0;
 
@@ -150,9 +162,10 @@ err_out_free:
        for (i = 0; i <= buddy->max_order; ++i)
                kfree(buddy->bits[i]);
 
+err_out:
        kfree(buddy->bits);
+       kfree(buddy->num_free);
 
-err_out:
        return -ENOMEM;
 }
 
@@ -164,6 +177,7 @@ static void mlx4_buddy_cleanup(struct mlx4_buddy *buddy)
                kfree(buddy->bits[i]);
 
        kfree(buddy->bits);
+       kfree(buddy->num_free);
 }
 
 static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
@@ -314,21 +328,30 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 
        memset(mpt_entry, 0, sizeof *mpt_entry);
 
-       mpt_entry->flags = cpu_to_be32(MLX4_MPT_FLAG_SW_OWNS     |
-                                      MLX4_MPT_FLAG_MIO         |
+       mpt_entry->flags = cpu_to_be32(MLX4_MPT_FLAG_MIO         |
                                       MLX4_MPT_FLAG_REGION      |
                                       mr->access);
 
        mpt_entry->key         = cpu_to_be32(key_to_hw_index(mr->key));
-       mpt_entry->pd          = cpu_to_be32(mr->pd);
+       mpt_entry->pd_flags    = cpu_to_be32(mr->pd | MLX4_MPT_PD_FLAG_EN_INV);
        mpt_entry->start       = cpu_to_be64(mr->iova);
        mpt_entry->length      = cpu_to_be64(mr->size);
        mpt_entry->entity_size = cpu_to_be32(mr->mtt.page_shift);
+
        if (mr->mtt.order < 0) {
                mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_PHYSICAL);
                mpt_entry->mtt_seg = 0;
-       } else
+       } else {
                mpt_entry->mtt_seg = cpu_to_be64(mlx4_mtt_addr(dev, &mr->mtt));
+       }
+
+       if (mr->mtt.order >= 0 && mr->mtt.page_shift == 0) {
+               /* fast register MR in free state */
+               mpt_entry->flags    |= cpu_to_be32(MLX4_MPT_FLAG_FREE);
+               mpt_entry->pd_flags |= cpu_to_be32(MLX4_MPT_PD_FLAG_FAST_REG);
+       } else {
+               mpt_entry->flags    |= cpu_to_be32(MLX4_MPT_FLAG_SW_OWNS);
+       }
 
        err = mlx4_SW2HW_MPT(dev, mailbox,
                             key_to_hw_index(mr->key) & (dev->caps.num_mpts - 1));
@@ -419,9 +442,9 @@ int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 
        for (i = 0; i < buf->npages; ++i)
                if (buf->nbufs == 1)
-                       page_list[i] = buf->u.direct.map + (i << buf->page_shift);
+                       page_list[i] = buf->direct.map + (i << buf->page_shift);
                else
-                       page_list[i] = buf->u.page_list[i].map;
+                       page_list[i] = buf->page_list[i].map;
 
        err = mlx4_write_mtt(dev, mtt, 0, buf->npages, page_list);
 
@@ -551,7 +574,7 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
        u64 mtt_seg;
        int err = -ENOMEM;
 
-       if (page_shift < 12 || page_shift >= 32)
+       if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
                return -EINVAL;
 
        /* All MTTs must fit in the same page */
@@ -578,13 +601,6 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
                goto err_free;
        }
 
-       fmr->mpt = mlx4_table_find(&priv->mr_table.dmpt_table,
-                                   key_to_hw_index(fmr->mr.key), NULL);
-       if (!fmr->mpt) {
-               err = -ENOMEM;
-               goto err_free;
-       }
-
        return 0;
 
 err_free:
@@ -595,22 +611,28 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
 
 int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
 {
-       return mlx4_mr_enable(dev, &fmr->mr);
+       struct mlx4_priv *priv = mlx4_priv(dev);
+       int err;
+
+       err = mlx4_mr_enable(dev, &fmr->mr);
+       if (err)
+               return err;
+
+       fmr->mpt = mlx4_table_find(&priv->mr_table.dmpt_table,
+                                   key_to_hw_index(fmr->mr.key), NULL);
+       if (!fmr->mpt)
+               return -ENOMEM;
+
+       return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_fmr_enable);
 
 void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
                    u32 *lkey, u32 *rkey)
 {
-       u32 key;
-
        if (!fmr->maps)
                return;
 
-       key = key_to_hw_index(fmr->mr.key);
-       key &= dev->caps.num_mpts - 1;
-       *lkey = *rkey = fmr->mr.key = hw_index_to_key(key);
-
        fmr->maps = 0;
 
        *(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;