net/mlx5: Fix global UAR mapping

Avoid double mapping of io mapped memory, Device page may be
mapped to non-cached(NC) or to write-combining(WC).
The code before this fix tries to map it both to WC and NC
contrary to what stated in Intel's software developer manual.

Here we remove the global WC mapping of all UARS
"dev->priv.bf_mapping", since UAR mapping should be decided
per UAR (e.g we want different mappings for EQs, CQs vs QPs).

Caller will now have to choose whether to map via
write-combining API or not.

mlx5e SQs will choose write-combining in order to perform
BlueFlame writes.

Fixes: 88a85f99e5 ('TX latency optimization to save DMA reads')
Signed-off-by: Moshe Lazer <moshel@mellanox.com>
Reviewed-by: Achiad Shochat <achiad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Moshe Lazer 2016-03-02 00:13:40 +02:00 committed by David S. Miller
parent 6b6c07bdcd
commit 0ba422410b
6 changed files with 36 additions and 56 deletions

View File

@ -388,6 +388,7 @@ struct mlx5e_sq_dma {
enum {
MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
MLX5E_SQ_STATE_BF_ENABLE,
};
struct mlx5e_sq {
@ -416,7 +417,6 @@ struct mlx5e_sq {
struct mlx5_wq_cyc wq;
u32 dma_fifo_mask;
void __iomem *uar_map;
void __iomem *uar_bf_map;
struct netdev_queue *txq;
u32 sqn;
u16 bf_buf_size;
@ -664,16 +664,12 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
* doorbell
*/
wmb();
if (bf_sz) {
__iowrite64_copy(sq->uar_bf_map + ofst, &wqe->ctrl, bf_sz);
/* flush the write-combining mapped buffer */
wmb();
} else {
if (bf_sz)
__iowrite64_copy(sq->uar_map + ofst, &wqe->ctrl, bf_sz);
else
mlx5_write64((__be32 *)&wqe->ctrl, sq->uar_map + ofst, NULL);
}
/* flush the write-combining mapped buffer */
wmb();
sq->bf_offset ^= sq->bf_buf_size;
}

View File

@ -548,7 +548,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
int txq_ix;
int err;
err = mlx5_alloc_map_uar(mdev, &sq->uar);
err = mlx5_alloc_map_uar(mdev, &sq->uar, true);
if (err)
return err;
@ -560,8 +560,12 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
goto err_unmap_free_uar;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
sq->uar_map = sq->uar.map;
sq->uar_bf_map = sq->uar.bf_map;
if (sq->uar.bf_map) {
set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
sq->uar_map = sq->uar.bf_map;
} else {
sq->uar_map = sq->uar.map;
}
sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
sq->max_inline = param->max_inline;
@ -2418,7 +2422,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev)
priv = netdev_priv(netdev);
err = mlx5_alloc_map_uar(mdev, &priv->cq_uar);
err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false);
if (err) {
mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err);
goto err_free_netdev;

View File

@ -303,7 +303,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
int bf_sz = 0;
if (bf && sq->uar_bf_map)
if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state))
bf_sz = wi->num_wqebbs << 3;
cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;

View File

@ -767,22 +767,6 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
return -ENOTSUPP;
}
static int map_bf_area(struct mlx5_core_dev *dev)
{
resource_size_t bf_start = pci_resource_start(dev->pdev, 0);
resource_size_t bf_len = pci_resource_len(dev->pdev, 0);
dev->priv.bf_mapping = io_mapping_create_wc(bf_start, bf_len);
return dev->priv.bf_mapping ? 0 : -ENOMEM;
}
static void unmap_bf_area(struct mlx5_core_dev *dev)
{
if (dev->priv.bf_mapping)
io_mapping_free(dev->priv.bf_mapping);
}
static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
{
struct mlx5_device_context *dev_ctx;
@ -1103,14 +1087,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
goto err_stop_eqs;
}
if (map_bf_area(dev))
dev_err(&pdev->dev, "Failed to map blue flame area\n");
err = mlx5_irq_set_affinity_hints(dev);
if (err) {
if (err)
dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
goto err_unmap_bf_area;
}
MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock);
@ -1169,10 +1148,6 @@ err_fs:
mlx5_cleanup_qp_table(dev);
mlx5_cleanup_cq_table(dev);
mlx5_irq_clear_affinity_hints(dev);
err_unmap_bf_area:
unmap_bf_area(dev);
free_comp_eqs(dev);
err_stop_eqs:
@ -1242,7 +1217,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
mlx5_cleanup_qp_table(dev);
mlx5_cleanup_cq_table(dev);
mlx5_irq_clear_affinity_hints(dev);
unmap_bf_area(dev);
free_comp_eqs(dev);
mlx5_stop_eqs(dev);
mlx5_free_uuars(dev, &priv->uuari);

View File

@ -226,7 +226,8 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari)
return 0;
}
int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
bool map_wc)
{
phys_addr_t pfn;
phys_addr_t uar_bar_start;
@ -240,20 +241,26 @@ int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
uar_bar_start = pci_resource_start(mdev->pdev, 0);
pfn = (uar_bar_start >> PAGE_SHIFT) + uar->index;
uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
if (!uar->map) {
mlx5_core_warn(mdev, "ioremap() failed, %d\n", err);
err = -ENOMEM;
goto err_free_uar;
}
if (mdev->priv.bf_mapping)
uar->bf_map = io_mapping_map_wc(mdev->priv.bf_mapping,
uar->index << PAGE_SHIFT);
if (map_wc) {
uar->bf_map = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE);
if (!uar->bf_map) {
mlx5_core_warn(mdev, "ioremap_wc() failed\n");
uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
if (!uar->map)
goto err_free_uar;
}
} else {
uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
if (!uar->map)
goto err_free_uar;
}
return 0;
err_free_uar:
mlx5_core_warn(mdev, "ioremap() failed\n");
err = -ENOMEM;
mlx5_cmd_free_uar(mdev, uar->index);
return err;
@ -262,8 +269,8 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar);
void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
{
io_mapping_unmap(uar->bf_map);
iounmap(uar->map);
iounmap(uar->bf_map);
mlx5_cmd_free_uar(mdev, uar->index);
}
EXPORT_SYMBOL(mlx5_unmap_free_uar);

View File

@ -460,8 +460,6 @@ struct mlx5_priv {
struct mlx5_uuar_info uuari;
MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock);
struct io_mapping *bf_mapping;
/* pages stuff */
struct workqueue_struct *pg_wq;
struct rb_root page_root;
@ -719,7 +717,8 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
bool map_wc);
void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
void mlx5_health_cleanup(struct mlx5_core_dev *dev);
int mlx5_health_init(struct mlx5_core_dev *dev);