From ea51b377abcdf0f3fab0119879be373bda69afb1 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 13 Dec 2011 04:13:48 +0000 Subject: [PATCH] mlx4_core: mtt modifications for SRIOV MTTs are resources which are allocated and tracked by the PF driver. In multifunction mode, the allocation and icm mapping is done in the resource tracker (later patch in this sequence). To accomplish this, we have "work" functions whose names start with "__", and "request" functions (same name, no __). If we are operating in multifunction mode, the request function actually results in comm-channel commands being sent (ALLOC_RES or FREE_RES). The PF-driver comm-channel handler will ultimately invoke the "work" (__) function and return the result. If we are not in multifunction mode, the "work" handler is invoked immediately. Signed-off-by: Jack Morgenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + drivers/net/ethernet/mellanox/mlx4/mr.c | 401 +++++++++++++++++++--- 2 files changed, 361 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index ab06e2c8ad77..23701a25daa9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -612,6 +612,7 @@ struct mlx4_priv { struct list_head bf_list; struct mutex bf_mutex; struct io_mapping *bf_mapping; + int reserved_mtts; }; static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index 057b22d64a05..916eba4572b7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -32,9 +32,11 @@ * SOFTWARE. */ +#include #include #include #include +#include #include @@ -180,7 +182,7 @@ static void mlx4_buddy_cleanup(struct mlx4_buddy *buddy) kfree(buddy->num_free); } -static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order) +static u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order) { struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; u32 seg; @@ -198,6 +200,26 @@ static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order) return seg; } +static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order) +{ + u64 in_param; + u64 out_param; + int err; + + if (mlx4_is_mfunc(dev)) { + set_param_l(&in_param, order); + err = mlx4_cmd_imm(dev, in_param, &out_param, RES_MTT, + RES_OP_RESERVE_AND_MAP, + MLX4_CMD_ALLOC_RES, + MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_WRAPPED); + if (err) + return -1; + return get_param_l(&out_param); + } + return __mlx4_alloc_mtt_range(dev, order); +} + int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift, struct mlx4_mtt *mtt) { @@ -221,16 +243,42 @@ int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift, } EXPORT_SYMBOL_GPL(mlx4_mtt_init); -void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt) +static void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, + int order) { struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + mlx4_buddy_free(&mr_table->mtt_buddy, first_seg, order); + mlx4_table_put_range(dev, &mr_table->mtt_table, first_seg, + first_seg + (1 << order) - 1); +} + +static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order) +{ + u64 in_param; + int err; + + if (mlx4_is_mfunc(dev)) { + set_param_l(&in_param, first_seg); + set_param_h(&in_param, order); + err = mlx4_cmd(dev, in_param, RES_MTT, RES_OP_RESERVE_AND_MAP, + MLX4_CMD_FREE_RES, + MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_WRAPPED); + if (err) + mlx4_warn(dev, "Failed to free mtt range at:%d" + " order:%d\n", first_seg, order); + return; + } + __mlx4_free_mtt_range(dev, first_seg, order); +} + +void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt) +{ if (mtt->order < 0) return; - mlx4_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, mtt->order); - mlx4_table_put_range(dev, &mr_table->mtt_table, mtt->first_seg, - mtt->first_seg + (1 << mtt->order) - 1); + mlx4_free_mtt_range(dev, mtt->first_seg, mtt->order); } EXPORT_SYMBOL_GPL(mlx4_mtt_cleanup); @@ -253,8 +301,9 @@ static u32 key_to_hw_index(u32 key) static int mlx4_SW2HW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, int mpt_index) { - return mlx4_cmd(dev, mailbox->dma, mpt_index, 0, MLX4_CMD_SW2HW_MPT, - MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED); + return mlx4_cmd(dev, mailbox->dma | dev->caps.function , mpt_index, + 0, MLX4_CMD_SW2HW_MPT, MLX4_CMD_TIME_CLASS_B, + MLX4_CMD_WRAPPED); } static int mlx4_HW2SW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, @@ -265,58 +314,192 @@ static int mlx4_HW2SW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED); } -int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access, - int npages, int page_shift, struct mlx4_mr *mr) +static int mlx4_mr_reserve_range(struct mlx4_dev *dev, int cnt, int align, + u32 *base_mridx) { struct mlx4_priv *priv = mlx4_priv(dev); - u32 index; - int err; + u32 mridx; - index = mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap); - if (index == -1) + mridx = mlx4_bitmap_alloc_range(&priv->mr_table.mpt_bitmap, cnt, align); + if (mridx == -1) return -ENOMEM; + *base_mridx = mridx; + return 0; + +} +EXPORT_SYMBOL_GPL(mlx4_mr_reserve_range); + +static void mlx4_mr_release_range(struct mlx4_dev *dev, u32 base_mridx, int cnt) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + mlx4_bitmap_free_range(&priv->mr_table.mpt_bitmap, base_mridx, cnt); +} +EXPORT_SYMBOL_GPL(mlx4_mr_release_range); + +static int mlx4_mr_alloc_reserved(struct mlx4_dev *dev, u32 mridx, u32 pd, + u64 iova, u64 size, u32 access, int npages, + int page_shift, struct mlx4_mr *mr) +{ mr->iova = iova; mr->size = size; mr->pd = pd; mr->access = access; - mr->enabled = 0; - mr->key = hw_index_to_key(index); + mr->enabled = MLX4_MR_DISABLED; + mr->key = hw_index_to_key(mridx); + + return mlx4_mtt_init(dev, npages, page_shift, &mr->mtt); +} +EXPORT_SYMBOL_GPL(mlx4_mr_alloc_reserved); + +static int mlx4_WRITE_MTT(struct mlx4_dev *dev, + struct mlx4_cmd_mailbox *mailbox, + int num_entries) +{ + return mlx4_cmd(dev, mailbox->dma, num_entries, 0, MLX4_CMD_WRITE_MTT, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); +} + +static int __mlx4_mr_reserve(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + return mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap); +} - err = mlx4_mtt_init(dev, npages, page_shift, &mr->mtt); +static int mlx4_mr_reserve(struct mlx4_dev *dev) +{ + u64 out_param; + + if (mlx4_is_mfunc(dev)) { + if (mlx4_cmd_imm(dev, 0, &out_param, RES_MPT, RES_OP_RESERVE, + MLX4_CMD_ALLOC_RES, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED)) + return -1; + return get_param_l(&out_param); + } + return __mlx4_mr_reserve(dev); +} + +static void __mlx4_mr_release(struct mlx4_dev *dev, u32 index) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index); +} + +static void mlx4_mr_release(struct mlx4_dev *dev, u32 index) +{ + u64 in_param; + + if (mlx4_is_mfunc(dev)) { + set_param_l(&in_param, index); + if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_RESERVE, + MLX4_CMD_FREE_RES, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED)) + mlx4_warn(dev, "Failed to release mr index:%d\n", + index); + return; + } + __mlx4_mr_release(dev, index); +} + +static int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index) +{ + struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + + return mlx4_table_get(dev, &mr_table->dmpt_table, index); +} + +static int mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index) +{ + u64 param; + + if (mlx4_is_mfunc(dev)) { + set_param_l(¶m, index); + return mlx4_cmd_imm(dev, param, ¶m, RES_MPT, RES_OP_MAP_ICM, + MLX4_CMD_ALLOC_RES, + MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_WRAPPED); + } + return __mlx4_mr_alloc_icm(dev, index); +} + +static void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index) +{ + struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + + mlx4_table_put(dev, &mr_table->dmpt_table, index); +} + +static void mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index) +{ + u64 in_param; + + if (mlx4_is_mfunc(dev)) { + set_param_l(&in_param, index); + if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_MAP_ICM, + MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_WRAPPED)) + mlx4_warn(dev, "Failed to free icm of mr index:%d\n", + index); + return; + } + return __mlx4_mr_free_icm(dev, index); +} + +int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access, + int npages, int page_shift, struct mlx4_mr *mr) +{ + u32 index; + int err; + + index = mlx4_mr_reserve(dev); + if (index == -1) + return -ENOMEM; + + err = mlx4_mr_alloc_reserved(dev, index, pd, iova, size, + access, npages, page_shift, mr); if (err) - mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index); + mlx4_mr_release(dev, index); return err; } EXPORT_SYMBOL_GPL(mlx4_mr_alloc); -void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr) +static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr) { - struct mlx4_priv *priv = mlx4_priv(dev); int err; - if (mr->enabled) { + if (mr->enabled == MLX4_MR_EN_HW) { err = mlx4_HW2SW_MPT(dev, NULL, key_to_hw_index(mr->key) & (dev->caps.num_mpts - 1)); if (err) - mlx4_warn(dev, "HW2SW_MPT failed (%d)\n", err); - } + mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err); + mr->enabled = MLX4_MR_EN_SW; + } mlx4_mtt_cleanup(dev, &mr->mtt); - mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, key_to_hw_index(mr->key)); +} +EXPORT_SYMBOL_GPL(mlx4_mr_free_reserved); + +void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr) +{ + mlx4_mr_free_reserved(dev, mr); + if (mr->enabled) + mlx4_mr_free_icm(dev, key_to_hw_index(mr->key)); + mlx4_mr_release(dev, key_to_hw_index(mr->key)); } EXPORT_SYMBOL_GPL(mlx4_mr_free); int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr) { - struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; struct mlx4_cmd_mailbox *mailbox; struct mlx4_mpt_entry *mpt_entry; int err; - err = mlx4_table_get(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key)); + err = mlx4_mr_alloc_icm(dev, key_to_hw_index(mr->key)); if (err) return err; @@ -363,8 +546,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr) mlx4_warn(dev, "SW2HW_MPT failed (%d)\n", err); goto err_cmd; } - - mr->enabled = 1; + mr->enabled = MLX4_MR_EN_HW; mlx4_free_cmd_mailbox(dev, mailbox); @@ -374,7 +556,7 @@ err_cmd: mlx4_free_cmd_mailbox(dev, mailbox); err_table: - mlx4_table_put(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key)); + mlx4_mr_free_icm(dev, key_to_hw_index(mr->key)); return err; } EXPORT_SYMBOL_GPL(mlx4_mr_enable); @@ -413,27 +595,74 @@ static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt, return 0; } -int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, - int start_index, int npages, u64 *page_list) +static int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, + int start_index, int npages, u64 *page_list) { + int err = 0; int chunk; - int err; - - if (mtt->order < 0) - return -EINVAL; while (npages > 0) { chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages); err = mlx4_write_mtt_chunk(dev, mtt, start_index, chunk, page_list); if (err) return err; - npages -= chunk; start_index += chunk; page_list += chunk; } + return err; +} - return 0; +int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, + int start_index, int npages, u64 *page_list) +{ + struct mlx4_cmd_mailbox *mailbox = NULL; + __be64 *inbox = NULL; + int chunk; + int err = 0; + int i; + + if (mtt->order < 0) + return -EINVAL; + + if (mlx4_is_mfunc(dev)) { + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + inbox = mailbox->buf; + + while (npages > 0) { + int s = mtt->first_seg * dev->caps.mtts_per_seg + + start_index; + chunk = min_t(int, MLX4_MAILBOX_SIZE / sizeof(u64) - + dev->caps.mtts_per_seg, npages); + if (s / (PAGE_SIZE / sizeof(u64)) != + (s + chunk - 1) / (PAGE_SIZE / sizeof(u64))) + chunk = PAGE_SIZE / sizeof(u64) - + (s % (PAGE_SIZE / sizeof(u64))); + + inbox[0] = cpu_to_be64(mtt->first_seg * + dev->caps.mtts_per_seg + + start_index); + inbox[1] = 0; + for (i = 0; i < chunk; ++i) + inbox[i + 2] = cpu_to_be64(page_list[i] | + MLX4_MTT_FLAG_PRESENT); + err = mlx4_WRITE_MTT(dev, mailbox, chunk); + if (err) { + mlx4_free_cmd_mailbox(dev, mailbox); + return err; + } + + npages -= chunk; + start_index += chunk; + page_list += chunk; + } + mlx4_free_cmd_mailbox(dev, mailbox); + return err; + } + + return __mlx4_write_mtt(dev, mtt, start_index, npages, page_list); } EXPORT_SYMBOL_GPL(mlx4_write_mtt); @@ -463,9 +692,18 @@ EXPORT_SYMBOL_GPL(mlx4_buf_write_mtt); int mlx4_init_mr_table(struct mlx4_dev *dev) { - struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_mr_table *mr_table = &priv->mr_table; int err; + if (!is_power_of_2(dev->caps.num_mpts)) + return -EINVAL; + + /* Nothing to do for slaves - all MR handling is forwarded + * to the master */ + if (mlx4_is_slave(dev)) + return 0; + err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts, ~0, dev->caps.reserved_mrws, 0); if (err) @@ -477,7 +715,10 @@ int mlx4_init_mr_table(struct mlx4_dev *dev) goto err_buddy; if (dev->caps.reserved_mtts) { - if (mlx4_alloc_mtt_range(dev, fls(dev->caps.reserved_mtts - 1)) == -1) { + priv->reserved_mtts = + mlx4_alloc_mtt_range(dev, + fls(dev->caps.reserved_mtts - 1)); + if (priv->reserved_mtts < 0) { mlx4_warn(dev, "MTT table of order %d is too small.\n", mr_table->mtt_buddy.max_order); err = -ENOMEM; @@ -498,8 +739,14 @@ err_buddy: void mlx4_cleanup_mr_table(struct mlx4_dev *dev) { - struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_mr_table *mr_table = &priv->mr_table; + if (mlx4_is_slave(dev)) + return; + if (priv->reserved_mtts >= 0) + mlx4_free_mtt_range(dev, priv->reserved_mtts, + fls(dev->caps.reserved_mtts - 1)); mlx4_buddy_cleanup(&mr_table->mtt_buddy); mlx4_bitmap_cleanup(&mr_table->mpt_bitmap); } @@ -620,6 +867,46 @@ err_free: } EXPORT_SYMBOL_GPL(mlx4_fmr_alloc); +static int mlx4_fmr_alloc_reserved(struct mlx4_dev *dev, u32 mridx, + u32 pd, u32 access, int max_pages, + int max_maps, u8 page_shift, struct mlx4_fmr *fmr) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int err = -ENOMEM; + + if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32) + return -EINVAL; + + /* All MTTs must fit in the same page */ + if (max_pages * sizeof *fmr->mtts > PAGE_SIZE) + return -EINVAL; + + fmr->page_shift = page_shift; + fmr->max_pages = max_pages; + fmr->max_maps = max_maps; + fmr->maps = 0; + + err = mlx4_mr_alloc_reserved(dev, mridx, pd, 0, 0, access, max_pages, + page_shift, &fmr->mr); + if (err) + return err; + + fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table, + fmr->mr.mtt.first_seg, + &fmr->dma_handle); + if (!fmr->mtts) { + err = -ENOMEM; + goto err_free; + } + + return 0; + +err_free: + mlx4_mr_free_reserved(dev, &fmr->mr); + return err; +} +EXPORT_SYMBOL_GPL(mlx4_fmr_alloc_reserved); + int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -641,12 +928,32 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_enable); void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u32 *lkey, u32 *rkey) { + struct mlx4_cmd_mailbox *mailbox; + int err; + if (!fmr->maps) return; fmr->maps = 0; - *(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW; + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) { + err = PTR_ERR(mailbox); + printk(KERN_WARNING "mlx4_ib: mlx4_alloc_cmd_mailbox" + " failed (%d)\n", err); + return; + } + + err = mlx4_HW2SW_MPT(dev, NULL, + key_to_hw_index(fmr->mr.key) & + (dev->caps.num_mpts - 1)); + mlx4_free_cmd_mailbox(dev, mailbox); + if (err) { + printk(KERN_WARNING "mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n", + err); + return; + } + fmr->mr.enabled = MLX4_MR_EN_SW; } EXPORT_SYMBOL_GPL(mlx4_fmr_unmap); @@ -655,13 +962,25 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr) if (fmr->maps) return -EBUSY; - fmr->mr.enabled = 0; mlx4_mr_free(dev, &fmr->mr); + fmr->mr.enabled = MLX4_MR_DISABLED; return 0; } EXPORT_SYMBOL_GPL(mlx4_fmr_free); +static int mlx4_fmr_free_reserved(struct mlx4_dev *dev, struct mlx4_fmr *fmr) +{ + if (fmr->maps) + return -EBUSY; + + mlx4_mr_free_reserved(dev, &fmr->mr); + fmr->mr.enabled = MLX4_MR_DISABLED; + + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_fmr_free_reserved); + int mlx4_SYNC_TPT(struct mlx4_dev *dev) { return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000, -- 2.20.1