* [PATCH for-next 01/10] IB/mlx4_ib: Remove local invalidate segment unused fields
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 02/10] net/mlx4_core: Rename MPT related service routines to have mpt_ prefix Or Gerlitz
` (9 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Remove unused fields from the local invalidate WQE segment structure.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/qp.c | 6 ++----
include/linux/mlx4/qp.h | 8 +++-----
2 files changed, 5 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 19e0637..c6dde71 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1983,10 +1983,8 @@ static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg, struct ib_send_wr *wr)
static void set_local_inv_seg(struct mlx4_wqe_local_inval_seg *iseg, u32 rkey)
{
- iseg->flags = 0;
- iseg->mem_key = cpu_to_be32(rkey);
- iseg->guest_id = 0;
- iseg->pa = 0;
+ memset(iseg, 0, sizeof(*iseg));
+ iseg->mem_key = cpu_to_be32(rkey);
}
static __always_inline void set_raddr_seg(struct mlx4_wqe_raddr_seg *rseg,
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 4b4ad6f..6c8a68c 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -304,12 +304,10 @@ struct mlx4_wqe_fmr_ext_seg {
};
struct mlx4_wqe_local_inval_seg {
- __be32 flags;
- u32 reserved1;
+ u64 reserved1;
__be32 mem_key;
- u32 reserved2[2];
- __be32 guest_id;
- __be64 pa;
+ u32 reserved2;
+ u64 reserved3[2];
};
struct mlx4_wqe_raddr_seg {
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 02/10] net/mlx4_core: Rename MPT related service routines to have mpt_ prefix
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-02-06 16:19 ` [PATCH for-next 01/10] IB/mlx4_ib: Remove local invalidate segment unused fields Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 03/10] net/mlx4_core: Propogate MR deregistration failure Or Gerlitz
` (8 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
The MPT - Memory Protection Table - is used by both memory windows and memory
regions. Hence, all MPT references are relevant for both types of memory objects.
Rename the relevant functions to start with mpt_ instead of the current mr_ prefix.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 16 +++---
drivers/net/ethernet/mellanox/mlx4/mr.c | 48 ++++++++++----------
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 14 +++---
3 files changed, 39 insertions(+), 39 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 116c5c2..5075236 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -118,10 +118,10 @@ enum {
MLX4_NUM_CMPTS = MLX4_CMPT_NUM_TYPE << MLX4_CMPT_SHIFT
};
-enum mlx4_mr_state {
- MLX4_MR_DISABLED = 0,
- MLX4_MR_EN_HW,
- MLX4_MR_EN_SW
+enum mlx4_mpt_state {
+ MLX4_MPT_DISABLED = 0,
+ MLX4_MPT_EN_HW,
+ MLX4_MPT_EN_SW
};
#define MLX4_COMM_TIME 10000
@@ -871,10 +871,10 @@ int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
-int __mlx4_mr_reserve(struct mlx4_dev *dev);
-void __mlx4_mr_release(struct mlx4_dev *dev, u32 index);
-int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index);
-void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index);
+int __mlx4_mpt_reserve(struct mlx4_dev *dev);
+void __mlx4_mpt_release(struct mlx4_dev *dev, u32 index);
+int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index);
+void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index);
u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index c202d3a..49705cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -321,7 +321,7 @@ static int mlx4_mr_alloc_reserved(struct mlx4_dev *dev, u32 mridx, u32 pd,
mr->size = size;
mr->pd = pd;
mr->access = access;
- mr->enabled = MLX4_MR_DISABLED;
+ mr->enabled = MLX4_MPT_DISABLED;
mr->key = hw_index_to_key(mridx);
return mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
@@ -335,14 +335,14 @@ static int mlx4_WRITE_MTT(struct mlx4_dev *dev,
MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
-int __mlx4_mr_reserve(struct mlx4_dev *dev)
+int __mlx4_mpt_reserve(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
return mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
}
-static int mlx4_mr_reserve(struct mlx4_dev *dev)
+static int mlx4_mpt_reserve(struct mlx4_dev *dev)
{
u64 out_param;
@@ -353,17 +353,17 @@ static int mlx4_mr_reserve(struct mlx4_dev *dev)
return -1;
return get_param_l(&out_param);
}
- return __mlx4_mr_reserve(dev);
+ return __mlx4_mpt_reserve(dev);
}
-void __mlx4_mr_release(struct mlx4_dev *dev, u32 index)
+void __mlx4_mpt_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)
+static void mlx4_mpt_release(struct mlx4_dev *dev, u32 index)
{
u64 in_param;
@@ -376,17 +376,17 @@ static void mlx4_mr_release(struct mlx4_dev *dev, u32 index)
index);
return;
}
- __mlx4_mr_release(dev, index);
+ __mlx4_mpt_release(dev, index);
}
-int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
+int __mlx4_mpt_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)
+static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
{
u64 param;
@@ -397,17 +397,17 @@ static int mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_WRAPPED);
}
- return __mlx4_mr_alloc_icm(dev, index);
+ return __mlx4_mpt_alloc_icm(dev, index);
}
-void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
+void __mlx4_mpt_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)
+static void mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index)
{
u64 in_param;
@@ -420,7 +420,7 @@ static void mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
index);
return;
}
- return __mlx4_mr_free_icm(dev, index);
+ return __mlx4_mpt_free_icm(dev, index);
}
int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
@@ -429,14 +429,14 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
u32 index;
int err;
- index = mlx4_mr_reserve(dev);
+ index = mlx4_mpt_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_mr_release(dev, index);
+ mlx4_mpt_release(dev, index);
return err;
}
@@ -446,14 +446,14 @@ static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
{
int err;
- if (mr->enabled == MLX4_MR_EN_HW) {
+ if (mr->enabled == MLX4_MPT_EN_HW) {
err = mlx4_HW2SW_MPT(dev, NULL,
key_to_hw_index(mr->key) &
(dev->caps.num_mpts - 1));
if (err)
mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
- mr->enabled = MLX4_MR_EN_SW;
+ mr->enabled = MLX4_MPT_EN_SW;
}
mlx4_mtt_cleanup(dev, &mr->mtt);
}
@@ -462,8 +462,8 @@ 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));
+ mlx4_mpt_free_icm(dev, key_to_hw_index(mr->key));
+ mlx4_mpt_release(dev, key_to_hw_index(mr->key));
}
EXPORT_SYMBOL_GPL(mlx4_mr_free);
@@ -473,7 +473,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
struct mlx4_mpt_entry *mpt_entry;
int err;
- err = mlx4_mr_alloc_icm(dev, key_to_hw_index(mr->key));
+ err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key));
if (err)
return err;
@@ -520,7 +520,7 @@ 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 = MLX4_MR_EN_HW;
+ mr->enabled = MLX4_MPT_EN_HW;
mlx4_free_cmd_mailbox(dev, mailbox);
@@ -530,7 +530,7 @@ err_cmd:
mlx4_free_cmd_mailbox(dev, mailbox);
err_table:
- mlx4_mr_free_icm(dev, key_to_hw_index(mr->key));
+ mlx4_mpt_free_icm(dev, key_to_hw_index(mr->key));
return err;
}
EXPORT_SYMBOL_GPL(mlx4_mr_enable);
@@ -882,7 +882,7 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
err);
return;
}
- fmr->mr.enabled = MLX4_MR_EN_SW;
+ fmr->mr.enabled = MLX4_MPT_EN_SW;
}
EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
@@ -892,7 +892,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
return -EBUSY;
mlx4_mr_free(dev, &fmr->mr);
- fmr->mr.enabled = MLX4_MR_DISABLED;
+ fmr->mr.enabled = MLX4_MPT_DISABLED;
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 561ed2a..2287dfd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1231,14 +1231,14 @@ static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
switch (op) {
case RES_OP_RESERVE:
- index = __mlx4_mr_reserve(dev);
+ index = __mlx4_mpt_reserve(dev);
if (index == -1)
break;
id = index & mpt_mask(dev);
err = add_res_range(dev, slave, id, 1, RES_MPT, index);
if (err) {
- __mlx4_mr_release(dev, index);
+ __mlx4_mpt_release(dev, index);
break;
}
set_param_l(out_param, index);
@@ -1251,7 +1251,7 @@ static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
if (err)
return err;
- err = __mlx4_mr_alloc_icm(dev, mpt->key);
+ err = __mlx4_mpt_alloc_icm(dev, mpt->key);
if (err) {
res_abort_move(dev, slave, RES_MPT, id);
return err;
@@ -1586,7 +1586,7 @@ static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
err = rem_res_range(dev, slave, id, 1, RES_MPT, 0);
if (err)
break;
- __mlx4_mr_release(dev, index);
+ __mlx4_mpt_release(dev, index);
break;
case RES_OP_MAP_ICM:
index = get_param_l(&in_param);
@@ -1596,7 +1596,7 @@ static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
if (err)
return err;
- __mlx4_mr_free_icm(dev, mpt->key);
+ __mlx4_mpt_free_icm(dev, mpt->key);
res_end_move(dev, slave, RES_MPT, id);
return err;
break;
@@ -3480,7 +3480,7 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
while (state != 0) {
switch (state) {
case RES_MPT_RESERVED:
- __mlx4_mr_release(dev, mpt->key);
+ __mlx4_mpt_release(dev, mpt->key);
spin_lock_irq(mlx4_tlock(dev));
rb_erase(&mpt->com.node,
&tracker->res_tree[RES_MPT]);
@@ -3491,7 +3491,7 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
break;
case RES_MPT_MAPPED:
- __mlx4_mr_free_icm(dev, mpt->key);
+ __mlx4_mpt_free_icm(dev, mpt->key);
state = RES_MPT_RESERVED;
break;
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 03/10] net/mlx4_core: Propogate MR deregistration failure
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-02-06 16:19 ` [PATCH for-next 01/10] IB/mlx4_ib: Remove local invalidate segment unused fields Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 02/10] net/mlx4_core: Rename MPT related service routines to have mpt_ prefix Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 04/10] net/mlx4_core: Disable memory windows for VFs Or Gerlitz
` (7 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
MR deregistration fails when memory windows are bound to it.
Handle such failures by propagating it to the caller ULP.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/mr.c | 13 +++++++----
drivers/net/ethernet/mellanox/mlx4/en_main.c | 4 +-
drivers/net/ethernet/mellanox/mlx4/mr.c | 29 +++++++++++++++++++------
include/linux/mlx4/device.h | 2 +-
4 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index bbaf617..254e1cf 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -68,7 +68,7 @@ struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
return &mr->ibmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_free:
kfree(mr);
@@ -163,7 +163,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
return &mr->ibmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_umem:
ib_umem_release(mr->umem);
@@ -177,8 +177,11 @@ err_free:
int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
{
struct mlx4_ib_mr *mr = to_mmr(ibmr);
+ int ret;
- mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
+ ret = mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
+ if (ret)
+ return ret;
if (mr->umem)
ib_umem_release(mr->umem);
kfree(mr);
@@ -212,7 +215,7 @@ struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
return &mr->ibmr;
err_mr:
- mlx4_mr_free(dev->dev, &mr->mmr);
+ (void) mlx4_mr_free(dev->dev, &mr->mmr);
err_free:
kfree(mr);
@@ -291,7 +294,7 @@ struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
return &fmr->ibfmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
err_free:
kfree(fmr);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 3a2b8c6..a298714 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -176,7 +176,7 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
flush_workqueue(mdev->workqueue);
destroy_workqueue(mdev->workqueue);
- mlx4_mr_free(dev, &mdev->mr);
+ (void) mlx4_mr_free(dev, &mdev->mr);
iounmap(mdev->uar_map);
mlx4_uar_free(dev, &mdev->priv_uar);
mlx4_pd_free(dev, mdev->priv_pdn);
@@ -283,7 +283,7 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
return mdev;
err_mr:
- mlx4_mr_free(dev, &mdev->mr);
+ (void) mlx4_mr_free(dev, &mdev->mr);
err_map:
if (!mdev->uar_map)
iounmap(mdev->uar_map);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 49705cf..06b16e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -442,7 +442,7 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
}
EXPORT_SYMBOL_GPL(mlx4_mr_alloc);
-static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
+static int mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
{
int err;
@@ -450,20 +450,31 @@ static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
err = mlx4_HW2SW_MPT(dev, NULL,
key_to_hw_index(mr->key) &
(dev->caps.num_mpts - 1));
- if (err)
- mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
+ if (err) {
+ mlx4_warn(dev, "HW2SW_MPT failed (%d),", err);
+ mlx4_warn(dev, "MR has MWs bound to it.\n");
+ return err;
+ }
mr->enabled = MLX4_MPT_EN_SW;
}
mlx4_mtt_cleanup(dev, &mr->mtt);
+
+ return 0;
}
-void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
+int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
{
- mlx4_mr_free_reserved(dev, mr);
+ int ret;
+
+ ret = mlx4_mr_free_reserved(dev, mr);
+ if (ret)
+ return ret;
if (mr->enabled)
mlx4_mpt_free_icm(dev, key_to_hw_index(mr->key));
mlx4_mpt_release(dev, key_to_hw_index(mr->key));
+
+ return 0;
}
EXPORT_SYMBOL_GPL(mlx4_mr_free);
@@ -831,7 +842,7 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
return 0;
err_free:
- mlx4_mr_free(dev, &fmr->mr);
+ (void) mlx4_mr_free(dev, &fmr->mr);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
@@ -888,10 +899,14 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
{
+ int ret;
+
if (fmr->maps)
return -EBUSY;
- mlx4_mr_free(dev, &fmr->mr);
+ ret = mlx4_mr_free(dev, &fmr->mr);
+ if (ret)
+ return ret;
fmr->mr.enabled = MLX4_MPT_DISABLED;
return 0;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 20ea939..e9fe8ca 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -801,7 +801,7 @@ u64 mlx4_mtt_addr(struct mlx4_dev *dev, struct mlx4_mtt *mtt);
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);
-void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr);
+int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr);
int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr);
int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
int start_index, int npages, u64 *page_list);
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 04/10] net/mlx4_core: Disable memory windows for VFs
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (2 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 03/10] net/mlx4_core: Propogate MR deregistration failure Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 05/10] net/mlx4_core: Enable memory windows in {INIT,QUERY}_HCA Or Gerlitz
` (6 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Do not enable memory windows allocation for virtual functions.
In addition, add a few safety checks, such as:
* Verifying the PD of a new MPT matches the VF.
* Making sure binding memory window isn't enabled for FMRs, and
that new memory windows are not FMR themselves.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 11 ++++-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 16 ++++++
drivers/net/ethernet/mellanox/mlx4/mr.c | 14 ------
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 49 ++++++++++++++++++++
4 files changed, 75 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 8b3d051..a389612 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -757,15 +757,19 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
u64 flags;
int err = 0;
u8 field;
+ u32 bmme_flags;
err = mlx4_cmd_box(dev, 0, outbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
if (err)
return err;
- /* add port mng change event capability unconditionally to slaves */
+ /* add port mng change event capability and disable mw type 1
+ * unconditionally to slaves
+ */
MLX4_GET(flags, outbox->buf, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
flags |= MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV;
+ flags &= ~MLX4_DEV_CAP_FLAG_MEM_WINDOW;
MLX4_PUT(outbox->buf, flags, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
/* For guests, report Blueflame disabled */
@@ -773,6 +777,11 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
field &= 0x7f;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
+ /* For guests, disable mw type 2 */
+ MLX4_GET(bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+ bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
+ MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 5075236..539212b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -268,6 +268,22 @@ struct mlx4_icm_table {
struct mlx4_icm **icm;
};
+#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 << 27)
+#define MLX4_MPT_PD_FLAG_RAE (1 << 28)
+#define MLX4_MPT_PD_FLAG_EN_INV (3 << 24)
+
+#define MLX4_MPT_QP_FLAG_BOUND_QP (1 << 7)
+
+#define MLX4_MPT_STATUS_SW 0xF0
+#define MLX4_MPT_STATUS_HW 0x00
+
/*
* Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
*/
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 06b16e4..5e785bd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -44,20 +44,6 @@
#include "mlx4.h"
#include "icm.h"
-#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 << 27)
-#define MLX4_MPT_PD_FLAG_RAE (1 << 28)
-#define MLX4_MPT_PD_FLAG_EN_INV (3 << 24)
-
-#define MLX4_MPT_STATUS_SW 0xF0
-#define MLX4_MPT_STATUS_HW 0x00
-
static u32 mlx4_buddy_alloc(struct mlx4_buddy *buddy, int order)
{
int o;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 2287dfd..9185e2e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1796,6 +1796,26 @@ static int mr_get_mtt_size(struct mlx4_mpt_entry *mpt)
return be32_to_cpu(mpt->mtt_sz);
}
+static u32 mr_get_pd(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->pd_flags) & 0x00ffffff;
+}
+
+static int mr_is_fmr(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->pd_flags) & MLX4_MPT_PD_FLAG_FAST_REG;
+}
+
+static int mr_is_bind_enabled(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->flags) & MLX4_MPT_FLAG_BIND_ENABLE;
+}
+
+static int mr_is_region(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->flags) & MLX4_MPT_FLAG_REGION;
+}
+
static int qp_get_mtt_addr(struct mlx4_qp_context *qpc)
{
return be32_to_cpu(qpc->mtt_base_addr_l) & 0xfffffff8;
@@ -1856,12 +1876,41 @@ int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
int mtt_base = mr_get_mtt_addr(inbox->buf) / dev->caps.mtt_entry_sz;
int phys;
int id;
+ u32 pd;
+ int pd_slave;
id = index & mpt_mask(dev);
err = mr_res_start_move_to(dev, slave, id, RES_MPT_HW, &mpt);
if (err)
return err;
+ /* Disable memory windows for VFs. */
+ if (!mr_is_region(inbox->buf)) {
+ err = -EPERM;
+ goto ex_abort;
+ }
+
+ /* Make sure that the PD bits related to the slave id are zeros. */
+ pd = mr_get_pd(inbox->buf);
+ pd_slave = (pd >> 17) & 0x7f;
+ if (pd_slave != 0 && pd_slave != slave) {
+ err = -EPERM;
+ goto ex_abort;
+ }
+
+ if (mr_is_fmr(inbox->buf)) {
+ /* FMR and Bind Enable are forbidden in slave devices. */
+ if (mr_is_bind_enabled(inbox->buf)) {
+ err = -EPERM;
+ goto ex_abort;
+ }
+ /* FMR and Memory Windows are also forbidden. */
+ if (!mr_is_region(inbox->buf)) {
+ err = -EPERM;
+ goto ex_abort;
+ }
+ }
+
phys = mr_phys_mpt(inbox->buf);
if (!phys) {
err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 05/10] net/mlx4_core: Enable memory windows in {INIT,QUERY}_HCA
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (3 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 04/10] net/mlx4_core: Disable memory windows for VFs Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 06/10] IB/core: Enhance memory windows support Or Gerlitz
` (5 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Add memory windows related code to INIT_HCA and QUERY_HCA
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 3 +++
drivers/net/ethernet/mellanox/mlx4/fw.h | 1 +
drivers/net/ethernet/mellanox/mlx4/main.c | 4 ++++
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 ++
4 files changed, 10 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index a389612..d136b36 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1207,6 +1207,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
#define INIT_HCA_FS_IB_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x26)
#define INIT_HCA_TPT_OFFSET 0x0f0
#define INIT_HCA_DMPT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x00)
+#define INIT_HCA_TPT_MW_OFFSET (INIT_HCA_TPT_OFFSET + 0x08)
#define INIT_HCA_LOG_MPT_SZ_OFFSET (INIT_HCA_TPT_OFFSET + 0x0b)
#define INIT_HCA_MTT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x10)
#define INIT_HCA_CMPT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x18)
@@ -1323,6 +1324,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
/* TPT attributes */
MLX4_PUT(inbox, param->dmpt_base, INIT_HCA_DMPT_BASE_OFFSET);
+ MLX4_PUT(inbox, param->mw_enabled, INIT_HCA_TPT_MW_OFFSET);
MLX4_PUT(inbox, param->log_mpt_sz, INIT_HCA_LOG_MPT_SZ_OFFSET);
MLX4_PUT(inbox, param->mtt_base, INIT_HCA_MTT_BASE_OFFSET);
MLX4_PUT(inbox, param->cmpt_base, INIT_HCA_CMPT_BASE_OFFSET);
@@ -1419,6 +1421,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
/* TPT attributes */
MLX4_GET(param->dmpt_base, outbox, INIT_HCA_DMPT_BASE_OFFSET);
+ MLX4_GET(param->mw_enabled, outbox, INIT_HCA_TPT_MW_OFFSET);
MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
MLX4_GET(param->mtt_base, outbox, INIT_HCA_MTT_BASE_OFFSET);
MLX4_GET(param->cmpt_base, outbox, INIT_HCA_CMPT_BASE_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index dbf2f69..9f1a25c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -170,6 +170,7 @@ struct mlx4_init_hca_param {
u8 log_mc_table_sz;
u8 log_mpt_sz;
u8 log_uar_sz;
+ u8 mw_enabled; /* Enable memory windows */
u8 uar_page_sz; /* log pg sz in 4k chunks */
u8 fs_hash_enable_bits;
u8 steering_mode; /* for QUERY_HCA */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 9a84c75..2a4dda0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1447,6 +1447,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
init_hca.uar_page_sz = PAGE_SHIFT - 12;
+ init_hca.mw_enabled = 0;
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
+ dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
+ init_hca.mw_enabled = INIT_HCA_TPT_MW_ENABLE;
err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 539212b..8b75d5e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -60,6 +60,8 @@
#define MLX4_FS_MGM_LOG_ENTRY_SIZE 7
#define MLX4_FS_NUM_MCG (1 << 17)
+#define INIT_HCA_TPT_MW_ENABLE (1 << 7)
+
enum {
MLX4_FS_L2_HASH = 0,
MLX4_FS_L2_L3_L4_HASH,
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 06/10] IB/core: Enhance memory windows support
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (4 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 05/10] net/mlx4_core: Enable memory windows in {INIT,QUERY}_HCA Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 07/10] IB/uverbs: Implement memory windows support in uverbs Or Gerlitz
` (4 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
This patch enhanced the IB core support for Memory Windows.
Memory Windows (MW) allow an application to have better/flexible control
over remote access to memory.
Two types of MWs are supported:
Type 1 - associated with PD only
Type 2A - associated with QPN only
Type 2B - associated with PD and QPN
Applications can allocate a MW once, and then repeatedly bind the MW to
different ranges in MRs that are associated to the same PD. Type 1 windows
are bound through a verb, while type 2 windows are bound by
posting a work request.
The 32-bit memory key is composed of a 24-bit index and an 8-bit key. The key is
changed with each bind, thus allowing more control over the peer's use of the
memory key.
The changes introduced are the following:
* add memory window type enum and a corresponding parameter to ib_alloc_mw.
* type 2 memory window bind work request support.
* create a struct that contains the common part of the bind verb struct
ibv_mw_bind and the bind work request into a single struct.
* add the ib_inc_rkey helper function to advance the tag part of an rkey.
Consumer interface details:
* new device capability flags IB_DEVICE_MEM_WINDOW_TYPE_2A and
IB_DEVICE_MEM_WINDOW_TYPE_2B are added to indicate device support
for these features.
Devices can set either IB_DEVICE_MEM_WINDOW_TYPE_2A or
IB_DEVICE_MEM_WINDOW_TYPE_2B if it supports type 2A or type 2B
memory windows. It can set neither to indicate it doesn't support
type 2 windows at all.
* modify existing provides and consumers code to the new param of ib_alloc_mw
and the ib_mw_bind_info structure
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/verbs.c | 5 +-
drivers/infiniband/hw/cxgb3/iwch_provider.c | 5 ++-
drivers/infiniband/hw/cxgb3/iwch_qp.c | 15 +++---
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 2 +-
drivers/infiniband/hw/cxgb4/mem.c | 5 ++-
drivers/infiniband/hw/ehca/ehca_iverbs.h | 2 +-
drivers/infiniband/hw/ehca/ehca_mrmw.c | 5 ++-
drivers/infiniband/hw/nes/nes_verbs.c | 19 ++++---
include/rdma/ib_verbs.h | 73 +++++++++++++++++++++++---
net/sunrpc/xprtrdma/verbs.c | 20 ++++----
10 files changed, 110 insertions(+), 41 deletions(-)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 30f199e..a8fdd33 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1099,18 +1099,19 @@ EXPORT_SYMBOL(ib_free_fast_reg_page_list);
/* Memory windows */
-struct ib_mw *ib_alloc_mw(struct ib_pd *pd)
+struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
struct ib_mw *mw;
if (!pd->device->alloc_mw)
return ERR_PTR(-ENOSYS);
- mw = pd->device->alloc_mw(pd);
+ mw = pd->device->alloc_mw(pd, type);
if (!IS_ERR(mw)) {
mw->device = pd->device;
mw->pd = pd;
mw->uobject = NULL;
+ mw->type = type;
atomic_inc(&pd->usecnt);
}
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 0bdf09a..074d5c2 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -738,7 +738,7 @@ static struct ib_mr *iwch_get_dma_mr(struct ib_pd *pd, int acc)
return ibmr;
}
-static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd)
+static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
struct iwch_dev *rhp;
struct iwch_pd *php;
@@ -747,6 +747,9 @@ static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd)
u32 stag = 0;
int ret;
+ if (type != IB_MW_TYPE_1)
+ return ERR_PTR(-EINVAL);
+
php = to_iwch_pd(pd);
rhp = php->rhp;
mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index 6de8463..e5649e8 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -567,18 +567,19 @@ int iwch_bind_mw(struct ib_qp *qp,
if (mw_bind->send_flags & IB_SEND_SIGNALED)
t3_wr_flags = T3_COMPLETION_FLAG;
- sgl.addr = mw_bind->addr;
- sgl.lkey = mw_bind->mr->lkey;
- sgl.length = mw_bind->length;
+ sgl.addr = mw_bind->bind_info.addr;
+ sgl.lkey = mw_bind->bind_info.mr->lkey;
+ sgl.length = mw_bind->bind_info.length;
wqe->bind.reserved = 0;
wqe->bind.type = TPT_VATO;
/* TBD: check perms */
- wqe->bind.perms = iwch_ib_to_tpt_bind_access(mw_bind->mw_access_flags);
- wqe->bind.mr_stag = cpu_to_be32(mw_bind->mr->lkey);
+ wqe->bind.perms = iwch_ib_to_tpt_bind_access(
+ mw_bind->bind_info.mw_access_flags);
+ wqe->bind.mr_stag = cpu_to_be32(mw_bind->bind_info.mr->lkey);
wqe->bind.mw_stag = cpu_to_be32(mw->rkey);
- wqe->bind.mw_len = cpu_to_be32(mw_bind->length);
- wqe->bind.mw_va = cpu_to_be64(mw_bind->addr);
+ wqe->bind.mw_len = cpu_to_be32(mw_bind->bind_info.length);
+ wqe->bind.mw_va = cpu_to_be64(mw_bind->bind_info.addr);
err = iwch_sgl2pbl_map(rhp, &sgl, 1, &pbl_addr, &page_size);
if (err) {
spin_unlock_irqrestore(&qhp->lock, flag);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 9c1644f..c8bd239 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -866,7 +866,7 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(
int page_list_len);
struct ib_mr *c4iw_alloc_fast_reg_mr(struct ib_pd *pd, int pbl_depth);
int c4iw_dealloc_mw(struct ib_mw *mw);
-struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd);
+struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
u64 length, u64 virt, int acc,
struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index afd8179..903a92d 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -650,7 +650,7 @@ err:
return ERR_PTR(err);
}
-struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd)
+struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
struct c4iw_dev *rhp;
struct c4iw_pd *php;
@@ -659,6 +659,9 @@ struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd)
u32 stag = 0;
int ret;
+ if (type != IB_MW_TYPE_1)
+ return ERR_PTR(-EINVAL);
+
php = to_c4iw_pd(pd);
rhp = php->rhp;
mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/infiniband/hw/ehca/ehca_iverbs.h
index 8f7f282..22f79af 100644
--- a/drivers/infiniband/hw/ehca/ehca_iverbs.h
+++ b/drivers/infiniband/hw/ehca/ehca_iverbs.h
@@ -95,7 +95,7 @@ int ehca_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
int ehca_dereg_mr(struct ib_mr *mr);
-struct ib_mw *ehca_alloc_mw(struct ib_pd *pd);
+struct ib_mw *ehca_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
int ehca_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
struct ib_mw_bind *mw_bind);
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index 8784486..bcfb0c1 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -688,7 +688,7 @@ dereg_mr_exit0:
/*----------------------------------------------------------------------*/
-struct ib_mw *ehca_alloc_mw(struct ib_pd *pd)
+struct ib_mw *ehca_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
struct ib_mw *ib_mw;
u64 h_ret;
@@ -698,6 +698,9 @@ struct ib_mw *ehca_alloc_mw(struct ib_pd *pd)
container_of(pd->device, struct ehca_shca, ib_device);
struct ehca_mw_hipzout_parms hipzout;
+ if (type != IB_MW_TYPE_1)
+ return ERR_PTR(-EINVAL);
+
e_mw = ehca_mw_new();
if (!e_mw) {
ib_mw = ERR_PTR(-ENOMEM);
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 07e4fba..8f67fe2 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -55,7 +55,8 @@ static void nes_unregister_ofa_device(struct nes_ib_device *nesibdev);
/**
* nes_alloc_mw
*/
-static struct ib_mw *nes_alloc_mw(struct ib_pd *ibpd) {
+static struct ib_mw *nes_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type)
+{
struct nes_pd *nespd = to_nespd(ibpd);
struct nes_vnic *nesvnic = to_nesvnic(ibpd->device);
struct nes_device *nesdev = nesvnic->nesdev;
@@ -71,6 +72,9 @@ static struct ib_mw *nes_alloc_mw(struct ib_pd *ibpd) {
u32 driver_key = 0;
u8 stag_key = 0;
+ if (type != IB_MW_TYPE_1)
+ return ERR_PTR(-EINVAL);
+
get_random_bytes(&next_stag_index, sizeof(next_stag_index));
stag_key = (u8)next_stag_index;
@@ -244,20 +248,19 @@ static int nes_bind_mw(struct ib_qp *ibqp, struct ib_mw *ibmw,
if (ibmw_bind->send_flags & IB_SEND_SIGNALED)
wqe_misc |= NES_IWARP_SQ_WQE_SIGNALED_COMPL;
- if (ibmw_bind->mw_access_flags & IB_ACCESS_REMOTE_WRITE) {
+ if (ibmw_bind->bind_info.mw_access_flags & IB_ACCESS_REMOTE_WRITE)
wqe_misc |= NES_CQP_STAG_RIGHTS_REMOTE_WRITE;
- }
- if (ibmw_bind->mw_access_flags & IB_ACCESS_REMOTE_READ) {
+ if (ibmw_bind->bind_info.mw_access_flags & IB_ACCESS_REMOTE_READ)
wqe_misc |= NES_CQP_STAG_RIGHTS_REMOTE_READ;
- }
set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_WQE_MISC_IDX, wqe_misc);
- set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_MR_IDX, ibmw_bind->mr->lkey);
+ set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_MR_IDX,
+ ibmw_bind->bind_info.mr->lkey);
set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_MW_IDX, ibmw->rkey);
set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_LENGTH_LOW_IDX,
- ibmw_bind->length);
+ ibmw_bind->bind_info.length);
wqe->wqe_words[NES_IWARP_SQ_BIND_WQE_LENGTH_HIGH_IDX] = 0;
- u64temp = (u64)ibmw_bind->addr;
+ u64temp = (u64)ibmw_bind->bind_info.addr;
set_wqe_64bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_VA_FBO_LOW_IDX, u64temp);
head++;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 46bc045..98cc4b2 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -115,6 +115,8 @@ enum ib_device_cap_flags {
IB_DEVICE_XRC = (1<<20),
IB_DEVICE_MEM_MGT_EXTENSIONS = (1<<21),
IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22),
+ IB_DEVICE_MEM_WINDOW_TYPE_2A = (1<<23),
+ IB_DEVICE_MEM_WINDOW_TYPE_2B = (1<<24)
};
enum ib_atomic_cap {
@@ -715,6 +717,11 @@ enum ib_mig_state {
IB_MIG_ARMED
};
+enum ib_mw_type {
+ IB_MW_TYPE_1 = 1,
+ IB_MW_TYPE_2 = 2
+};
+
struct ib_qp_attr {
enum ib_qp_state qp_state;
enum ib_qp_state cur_qp_state;
@@ -758,6 +765,7 @@ enum ib_wr_opcode {
IB_WR_FAST_REG_MR,
IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+ IB_WR_BIND_MW,
};
enum ib_send_flags {
@@ -780,6 +788,23 @@ struct ib_fast_reg_page_list {
unsigned int max_page_list_len;
};
+/**
+ * struct ib_mw_bind_info - Parameters for a memory window bind operation.
+ * @mr: A memory region to bind the memory window to.
+ * @addr: The address where the memory window should begin.
+ * @length: The length of the memory window, in bytes.
+ * @mw_access_flags: Access flags from enum ib_access_flags for the window.
+ *
+ * This struct contains the shared parameters for type 1 and type 2
+ * memory window bind operations.
+ */
+struct ib_mw_bind_info {
+ struct ib_mr *mr;
+ u64 addr;
+ u64 length;
+ int mw_access_flags;
+};
+
struct ib_send_wr {
struct ib_send_wr *next;
u64 wr_id;
@@ -823,6 +848,12 @@ struct ib_send_wr {
int access_flags;
u32 rkey;
} fast_reg;
+ struct {
+ struct ib_mw *mw;
+ /* The new rkey for the memory window. */
+ u32 rkey;
+ struct ib_mw_bind_info bind_info;
+ } bind_mw;
} wr;
u32 xrc_remote_srq_num; /* XRC TGT QPs only */
};
@@ -839,7 +870,8 @@ enum ib_access_flags {
IB_ACCESS_REMOTE_WRITE = (1<<1),
IB_ACCESS_REMOTE_READ = (1<<2),
IB_ACCESS_REMOTE_ATOMIC = (1<<3),
- IB_ACCESS_MW_BIND = (1<<4)
+ IB_ACCESS_MW_BIND = (1<<4),
+ IB_ZERO_BASED = (1<<5)
};
struct ib_phys_buf {
@@ -862,13 +894,16 @@ enum ib_mr_rereg_flags {
IB_MR_REREG_ACCESS = (1<<2)
};
+/**
+ * struct ib_mw_bind - Parameters for a type 1 memory window bind operation.
+ * @wr_id: Work request id.
+ * @send_flags: Flags from ib_send_flags enum.
+ * @bind_info: More parameters of the bind operation.
+ */
struct ib_mw_bind {
- struct ib_mr *mr;
- u64 wr_id;
- u64 addr;
- u32 length;
- int send_flags;
- int mw_access_flags;
+ u64 wr_id;
+ int send_flags;
+ struct ib_mw_bind_info bind_info;
};
struct ib_fmr_attr {
@@ -991,6 +1026,7 @@ struct ib_mw {
struct ib_pd *pd;
struct ib_uobject *uobject;
u32 rkey;
+ enum ib_mw_type type;
};
struct ib_fmr {
@@ -1202,7 +1238,8 @@ struct ib_device {
int num_phys_buf,
int mr_access_flags,
u64 *iova_start);
- struct ib_mw * (*alloc_mw)(struct ib_pd *pd);
+ struct ib_mw * (*alloc_mw)(struct ib_pd *pd,
+ enum ib_mw_type type);
int (*bind_mw)(struct ib_qp *qp,
struct ib_mw *mw,
struct ib_mw_bind *mw_bind);
@@ -2019,6 +2056,8 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
* ib_dereg_mr - Deregisters a memory region and removes it from the
* HCA translation table.
* @mr: The memory region to deregister.
+ *
+ * This function can fail, if the memory region has memory windows bound to it.
*/
int ib_dereg_mr(struct ib_mr *mr);
@@ -2071,10 +2110,22 @@ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey)
}
/**
+ * ib_inc_rkey - increments the key portion of the given rkey. Can be used
+ * for calculating a new rkey for type 2 memory windows.
+ * @rkey - the rkey to increment.
+ */
+static inline u32 ib_inc_rkey(u32 rkey)
+{
+ const u32 mask = 0x000000ff;
+ return ((rkey + 1) & mask) | (rkey & ~mask);
+}
+
+/**
* ib_alloc_mw - Allocates a memory window.
* @pd: The protection domain associated with the memory window.
+ * @type: The type of the memory window (1 or 2).
*/
-struct ib_mw *ib_alloc_mw(struct ib_pd *pd);
+struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
/**
* ib_bind_mw - Posts a work request to the send queue of the specified
@@ -2084,6 +2135,10 @@ struct ib_mw *ib_alloc_mw(struct ib_pd *pd);
* @mw: The memory window to bind.
* @mw_bind: Specifies information about the memory window, including
* its address range, remote access rights, and associated memory region.
+ *
+ * If there is no immediate error, the function will update the rkey member
+ * of the mw parameter to its new value. The bind operation can still fail
+ * asynchronously.
*/
static inline int ib_bind_mw(struct ib_qp *qp,
struct ib_mw *mw,
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 745973b..9372656 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1086,7 +1086,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
case RPCRDMA_MEMWINDOWS:
/* Allocate one extra request's worth, for full cycling */
for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) {
- r->r.mw = ib_alloc_mw(ia->ri_pd);
+ r->r.mw = ib_alloc_mw(ia->ri_pd, IB_MW_TYPE_1);
if (IS_ERR(r->r.mw)) {
rc = PTR_ERR(r->r.mw);
dprintk("RPC: %s: ib_alloc_mw"
@@ -1673,12 +1673,12 @@ rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg,
*nsegs = 1;
rpcrdma_map_one(ia, seg, writing);
- param.mr = ia->ri_bind_mem;
+ param.bind_info.mr = ia->ri_bind_mem;
param.wr_id = 0ULL; /* no send cookie */
- param.addr = seg->mr_dma;
- param.length = seg->mr_len;
+ param.bind_info.addr = seg->mr_dma;
+ param.bind_info.length = seg->mr_len;
param.send_flags = 0;
- param.mw_access_flags = mem_priv;
+ param.bind_info.mw_access_flags = mem_priv;
DECR_CQCOUNT(&r_xprt->rx_ep);
rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, ¶m);
@@ -1690,7 +1690,7 @@ rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg,
rpcrdma_unmap_one(ia, seg);
} else {
seg->mr_rkey = seg->mr_chunk.rl_mw->r.mw->rkey;
- seg->mr_base = param.addr;
+ seg->mr_base = param.bind_info.addr;
seg->mr_nsegs = 1;
}
return rc;
@@ -1706,10 +1706,10 @@ rpcrdma_deregister_memwin_external(struct rpcrdma_mr_seg *seg,
int rc;
BUG_ON(seg->mr_nsegs != 1);
- param.mr = ia->ri_bind_mem;
- param.addr = 0ULL; /* unbind */
- param.length = 0;
- param.mw_access_flags = 0;
+ param.bind_info.mr = ia->ri_bind_mem;
+ param.bind_info.addr = 0ULL; /* unbind */
+ param.bind_info.length = 0;
+ param.bind_info.mw_access_flags = 0;
if (*r) {
param.wr_id = (u64) (unsigned long) *r;
param.send_flags = IB_SEND_SIGNALED;
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 07/10] IB/uverbs: Implement memory windows support in uverbs
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (5 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 06/10] IB/core: Enhance memory windows support Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 08/10] mlx4: Implement memory windows allocation and deallocation Or Gerlitz
` (3 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
The existing user/kernel uverbs API has IB_USER_VERBS_CMD_ALLOC/DEALLOC_MW,
implement these calls, along with destroying user memory windows
during process cleanup.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/uverbs.h | 2 +
drivers/infiniband/core/uverbs_cmd.c | 121 +++++++++++++++++++++++++++++++++
drivers/infiniband/core/uverbs_main.c | 13 +++-
include/uapi/rdma/ib_user_verbs.h | 16 +++++
4 files changed, 150 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 5bcb2af..0fcd7aa 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -188,6 +188,8 @@ IB_UVERBS_DECLARE_CMD(alloc_pd);
IB_UVERBS_DECLARE_CMD(dealloc_pd);
IB_UVERBS_DECLARE_CMD(reg_mr);
IB_UVERBS_DECLARE_CMD(dereg_mr);
+IB_UVERBS_DECLARE_CMD(alloc_mw);
+IB_UVERBS_DECLARE_CMD(dealloc_mw);
IB_UVERBS_DECLARE_CMD(create_comp_channel);
IB_UVERBS_DECLARE_CMD(create_cq);
IB_UVERBS_DECLARE_CMD(resize_cq);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 0cb0007..3983a05 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -48,6 +48,7 @@ struct uverbs_lock_class {
static struct uverbs_lock_class pd_lock_class = { .name = "PD-uobj" };
static struct uverbs_lock_class mr_lock_class = { .name = "MR-uobj" };
+static struct uverbs_lock_class mw_lock_class = { .name = "MW-uobj" };
static struct uverbs_lock_class cq_lock_class = { .name = "CQ-uobj" };
static struct uverbs_lock_class qp_lock_class = { .name = "QP-uobj" };
static struct uverbs_lock_class ah_lock_class = { .name = "AH-uobj" };
@@ -1049,6 +1050,126 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file,
return in_len;
}
+ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file,
+ const char __user *buf, int in_len,
+ int out_len)
+{
+ struct ib_uverbs_alloc_mw cmd;
+ struct ib_uverbs_alloc_mw_resp resp;
+ struct ib_uobject *uobj;
+ struct ib_pd *pd;
+ struct ib_mw *mw;
+ int ret;
+
+ if (out_len < sizeof(resp))
+ return -ENOSPC;
+
+ if (copy_from_user(&cmd, buf, sizeof(cmd)))
+ return -EFAULT;
+
+ uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
+ if (!uobj)
+ return -ENOMEM;
+
+ init_uobj(uobj, 0, file->ucontext, &mw_lock_class);
+ down_write(&uobj->mutex);
+
+ pd = idr_read_pd(cmd.pd_handle, file->ucontext);
+ if (!pd) {
+ ret = -EINVAL;
+ goto err_free;
+ }
+
+ mw = pd->device->alloc_mw(pd, cmd.mw_type);
+ if (IS_ERR(mw)) {
+ ret = PTR_ERR(mw);
+ goto err_put;
+ }
+
+ mw->device = pd->device;
+ mw->pd = pd;
+ mw->uobject = uobj;
+ atomic_inc(&pd->usecnt);
+
+ uobj->object = mw;
+ ret = idr_add_uobj(&ib_uverbs_mw_idr, uobj);
+ if (ret)
+ goto err_unalloc;
+
+ memset(&resp, 0, sizeof(resp));
+ resp.rkey = mw->rkey;
+ resp.mw_handle = uobj->id;
+
+ if (copy_to_user((void __user *)(unsigned long)cmd.response,
+ &resp, sizeof(resp))) {
+ ret = -EFAULT;
+ goto err_copy;
+ }
+
+ put_pd_read(pd);
+
+ mutex_lock(&file->mutex);
+ list_add_tail(&uobj->list, &file->ucontext->mw_list);
+ mutex_unlock(&file->mutex);
+
+ uobj->live = 1;
+
+ up_write(&uobj->mutex);
+
+ return in_len;
+
+err_copy:
+ idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+
+err_unalloc:
+ ib_dealloc_mw(mw);
+
+err_put:
+ put_pd_read(pd);
+
+err_free:
+ put_uobj_write(uobj);
+ return ret;
+}
+
+ssize_t ib_uverbs_dealloc_mw(struct ib_uverbs_file *file,
+ const char __user *buf, int in_len,
+ int out_len)
+{
+ struct ib_uverbs_dealloc_mw cmd;
+ struct ib_mw *mw;
+ struct ib_uobject *uobj;
+ int ret = -EINVAL;
+
+ if (copy_from_user(&cmd, buf, sizeof(cmd)))
+ return -EFAULT;
+
+ uobj = idr_write_uobj(&ib_uverbs_mw_idr, cmd.mw_handle, file->ucontext);
+ if (!uobj)
+ return -EINVAL;
+
+ mw = uobj->object;
+
+ ret = ib_dealloc_mw(mw);
+ if (!ret)
+ uobj->live = 0;
+
+ put_uobj_write(uobj);
+
+ if (ret)
+ return ret;
+
+ idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+
+ mutex_lock(&file->mutex);
+ list_del(&uobj->list);
+ mutex_unlock(&file->mutex);
+
+ put_uobj(uobj);
+
+ return in_len;
+}
+
ssize_t ib_uverbs_create_comp_channel(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 6f2ce6f..2c6f0f2 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -87,6 +87,8 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
[IB_USER_VERBS_CMD_DEALLOC_PD] = ib_uverbs_dealloc_pd,
[IB_USER_VERBS_CMD_REG_MR] = ib_uverbs_reg_mr,
[IB_USER_VERBS_CMD_DEREG_MR] = ib_uverbs_dereg_mr,
+ [IB_USER_VERBS_CMD_ALLOC_MW] = ib_uverbs_alloc_mw,
+ [IB_USER_VERBS_CMD_DEALLOC_MW] = ib_uverbs_dealloc_mw,
[IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL] = ib_uverbs_create_comp_channel,
[IB_USER_VERBS_CMD_CREATE_CQ] = ib_uverbs_create_cq,
[IB_USER_VERBS_CMD_RESIZE_CQ] = ib_uverbs_resize_cq,
@@ -201,6 +203,15 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
kfree(uobj);
}
+ /* Remove MWs before QPs, in order to support type 2A MWs. */
+ list_for_each_entry_safe(uobj, tmp, &context->mw_list, list) {
+ struct ib_mw *mw = uobj->object;
+
+ idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+ ib_dealloc_mw(mw);
+ kfree(uobj);
+ }
+
list_for_each_entry_safe(uobj, tmp, &context->qp_list, list) {
struct ib_qp *qp = uobj->object;
struct ib_uqp_object *uqp =
@@ -240,8 +251,6 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
kfree(uevent);
}
- /* XXX Free MWs */
-
list_for_each_entry_safe(uobj, tmp, &context->mr_list, list) {
struct ib_mr *mr = uobj->object;
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 81aba3a..805711e 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -261,6 +261,22 @@ struct ib_uverbs_dereg_mr {
__u32 mr_handle;
};
+struct ib_uverbs_alloc_mw {
+ __u64 response;
+ __u32 pd_handle;
+ __u8 mw_type;
+ __u8 reserved[3];
+};
+
+struct ib_uverbs_alloc_mw_resp {
+ __u32 mw_handle;
+ __u32 rkey;
+};
+
+struct ib_uverbs_dealloc_mw {
+ __u32 mw_handle;
+};
+
struct ib_uverbs_create_comp_channel {
__u64 response;
};
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 08/10] mlx4: Implement memory windows allocation and deallocation
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (6 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 07/10] IB/uverbs: Implement memory windows support in uverbs Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 09/10] IB/mlx4_ib: Support memory window binding Or Gerlitz
` (2 subsequent siblings)
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Implement MW allocation and deallocation in mlx4_core and mlx4_ib.
Pass down the enable bind flag when registering memory regions.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/mlx4_ib.h | 12 ++++
drivers/infiniband/hw/mlx4/mr.c | 52 +++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/mr.c | 95 +++++++++++++++++++++++++++++++
include/linux/mlx4/device.h | 20 ++++++-
4 files changed, 178 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index dcd845b..6d28491 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -116,6 +116,11 @@ struct mlx4_ib_mr {
struct ib_umem *umem;
};
+struct mlx4_ib_mw {
+ struct ib_mw ibmw;
+ struct mlx4_mw mmw;
+};
+
struct mlx4_ib_fast_reg_page_list {
struct ib_fast_reg_page_list ibfrpl;
__be64 *mapped_page_list;
@@ -533,6 +538,11 @@ static inline struct mlx4_ib_mr *to_mmr(struct ib_mr *ibmr)
return container_of(ibmr, struct mlx4_ib_mr, ibmr);
}
+static inline struct mlx4_ib_mw *to_mmw(struct ib_mw *ibmw)
+{
+ return container_of(ibmw, struct mlx4_ib_mw, ibmw);
+}
+
static inline struct mlx4_ib_fast_reg_page_list *to_mfrpl(struct ib_fast_reg_page_list *ibfrpl)
{
return container_of(ibfrpl, struct mlx4_ib_fast_reg_page_list, ibfrpl);
@@ -581,6 +591,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int access_flags,
struct ib_udata *udata);
int mlx4_ib_dereg_mr(struct ib_mr *mr);
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
+int mlx4_ib_dealloc_mw(struct ib_mw *mw);
struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len);
struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 254e1cf..5adf4c4 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -41,9 +41,19 @@ static u32 convert_access(int acc)
(acc & IB_ACCESS_REMOTE_WRITE ? MLX4_PERM_REMOTE_WRITE : 0) |
(acc & IB_ACCESS_REMOTE_READ ? MLX4_PERM_REMOTE_READ : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? MLX4_PERM_LOCAL_WRITE : 0) |
+ (acc & IB_ACCESS_MW_BIND ? MLX4_PERM_BIND_MW : 0) |
MLX4_PERM_LOCAL_READ;
}
+static enum mlx4_mw_type to_mlx4_type(enum ib_mw_type type)
+{
+ switch (type) {
+ case IB_MW_TYPE_1: return MLX4_MW_TYPE_1;
+ case IB_MW_TYPE_2: return MLX4_MW_TYPE_2;
+ default: return -1;
+ }
+}
+
struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
{
struct mlx4_ib_mr *mr;
@@ -189,6 +199,48 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
return 0;
}
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
+{
+ struct mlx4_ib_dev *dev = to_mdev(pd->device);
+ struct mlx4_ib_mw *mw;
+ int err;
+
+ mw = kmalloc(sizeof(*mw), GFP_KERNEL);
+ if (!mw)
+ return ERR_PTR(-ENOMEM);
+
+ err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
+ to_mlx4_type(type), &mw->mmw);
+ if (err)
+ goto err_free;
+
+ err = mlx4_mw_enable(dev->dev, &mw->mmw);
+ if (err)
+ goto err_mw;
+
+ mw->ibmw.rkey = mw->mmw.key;
+
+ return &mw->ibmw;
+
+err_mw:
+ mlx4_mw_free(dev->dev, &mw->mmw);
+
+err_free:
+ kfree(mw);
+
+ return ERR_PTR(err);
+}
+
+int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
+{
+ struct mlx4_ib_mw *mw = to_mmw(ibmw);
+
+ mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
+ kfree(mw);
+
+ return 0;
+}
+
struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len)
{
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 5e785bd..602ca9b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -654,6 +654,101 @@ int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
}
EXPORT_SYMBOL_GPL(mlx4_buf_write_mtt);
+int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type,
+ struct mlx4_mw *mw)
+{
+ u32 index;
+
+ if ((type == MLX4_MW_TYPE_1 &&
+ !(dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW)) ||
+ (type == MLX4_MW_TYPE_2 &&
+ !(dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)))
+ return -ENOTSUPP;
+
+ index = mlx4_mpt_reserve(dev);
+ if (index == -1)
+ return -ENOMEM;
+
+ mw->key = hw_index_to_key(index);
+ mw->pd = pd;
+ mw->type = type;
+ mw->enabled = MLX4_MPT_DISABLED;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_alloc);
+
+int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_mpt_entry *mpt_entry;
+ int err;
+
+ err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key));
+ if (err)
+ return err;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ err = PTR_ERR(mailbox);
+ goto err_table;
+ }
+ mpt_entry = mailbox->buf;
+
+ memset(mpt_entry, 0, sizeof(*mpt_entry));
+
+ /* Note that the MLX4_MPT_FLAG_REGION bit in mpt_entry->flags is turned
+ * off, thus creating a memory window and not a memory region.
+ */
+ mpt_entry->key = cpu_to_be32(key_to_hw_index(mw->key));
+ mpt_entry->pd_flags = cpu_to_be32(mw->pd);
+ if (mw->type == MLX4_MW_TYPE_2) {
+ mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_FREE);
+ mpt_entry->qpn = cpu_to_be32(MLX4_MPT_QP_FLAG_BOUND_QP);
+ mpt_entry->pd_flags |= cpu_to_be32(MLX4_MPT_PD_FLAG_EN_INV);
+ }
+
+ err = mlx4_SW2HW_MPT(dev, mailbox,
+ key_to_hw_index(mw->key) &
+ (dev->caps.num_mpts - 1));
+ if (err) {
+ mlx4_warn(dev, "SW2HW_MPT failed (%d)\n", err);
+ goto err_cmd;
+ }
+ mw->enabled = MLX4_MPT_EN_HW;
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+
+ return 0;
+
+err_cmd:
+ mlx4_free_cmd_mailbox(dev, mailbox);
+
+err_table:
+ mlx4_mpt_free_icm(dev, key_to_hw_index(mw->key));
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_enable);
+
+void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw)
+{
+ int err;
+
+ if (mw->enabled == MLX4_MPT_EN_HW) {
+ err = mlx4_HW2SW_MPT(dev, NULL,
+ key_to_hw_index(mw->key) &
+ (dev->caps.num_mpts - 1));
+ if (err)
+ mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
+
+ mw->enabled = MLX4_MPT_EN_SW;
+ }
+ if (mw->enabled)
+ mlx4_mpt_free_icm(dev, key_to_hw_index(mw->key));
+ mlx4_mpt_release(dev, key_to_hw_index(mw->key));
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_free);
+
int mlx4_init_mr_table(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e9fe8ca..966211b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -170,6 +170,7 @@ enum {
#define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90)
enum {
+ MLX4_BMME_FLAG_WIN_TYPE_2B = 1 << 1,
MLX4_BMME_FLAG_LOCAL_INV = 1 << 6,
MLX4_BMME_FLAG_REMOTE_INV = 1 << 7,
MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9,
@@ -237,7 +238,8 @@ enum {
MLX4_PERM_LOCAL_WRITE = 1 << 11,
MLX4_PERM_REMOTE_READ = 1 << 12,
MLX4_PERM_REMOTE_WRITE = 1 << 13,
- MLX4_PERM_ATOMIC = 1 << 14
+ MLX4_PERM_ATOMIC = 1 << 14,
+ MLX4_PERM_BIND_MW = 1 << 15,
};
enum {
@@ -503,6 +505,18 @@ struct mlx4_mr {
int enabled;
};
+enum mlx4_mw_type {
+ MLX4_MW_TYPE_1 = 1,
+ MLX4_MW_TYPE_2 = 2,
+};
+
+struct mlx4_mw {
+ u32 key;
+ u32 pd;
+ enum mlx4_mw_type type;
+ int enabled;
+};
+
struct mlx4_fmr {
struct mlx4_mr mr;
struct mlx4_mpt_entry *mpt;
@@ -803,6 +817,10 @@ 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);
int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr);
int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr);
+int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type,
+ struct mlx4_mw *mw);
+void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw);
+int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw);
int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
int start_index, int npages, u64 *page_list);
int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 09/10] IB/mlx4_ib: Support memory window binding
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (7 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 08/10] mlx4: Implement memory windows allocation and deallocation Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-06 16:19 ` [PATCH for-next 10/10] IB/mlx4_ib: Advertize MW support Or Gerlitz
2013-02-18 16:47 ` [PATCH for-next 00/10] mlx4: Add Memory Windows support Or Gerlitz
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
* Implement memory windows binding in mlx4_ib_post_send.
* Implement mlx4_ib_bind_mw by deferring to mlx4_ib_post_send.
* Rename MLX4_WQE_FMR_PERM_* flags to MLX4_WQE_FMR_AND_BIND_PERM_*,
indicating that they are used both for fast registration work
requests, and for memory window bind work requests.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/mlx4_ib.h | 2 +
drivers/infiniband/hw/mlx4/mr.c | 22 +++++++++++++++++++++
drivers/infiniband/hw/mlx4/qp.c | 35 +++++++++++++++++++++++++++++++--
include/linux/mlx4/qp.h | 11 +++++++--
4 files changed, 64 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6d28491..5a21783 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -592,6 +592,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
struct ib_udata *udata);
int mlx4_ib_dereg_mr(struct ib_mr *mr);
struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
+int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind);
int mlx4_ib_dealloc_mw(struct ib_mw *mw);
struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 5adf4c4..e471f08 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -231,6 +231,28 @@ err_free:
return ERR_PTR(err);
}
+int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind)
+{
+ struct ib_send_wr wr;
+ struct ib_send_wr *bad_wr;
+ int ret;
+
+ memset(&wr, 0, sizeof(wr));
+ wr.opcode = IB_WR_BIND_MW;
+ wr.wr_id = mw_bind->wr_id;
+ wr.send_flags = mw_bind->send_flags;
+ wr.wr.bind_mw.mw = mw;
+ wr.wr.bind_mw.bind_info = mw_bind->bind_info;
+ wr.wr.bind_mw.rkey = ib_inc_rkey(mw->rkey);
+
+ ret = mlx4_ib_post_send(qp, &wr, &bad_wr);
+ if (!ret)
+ mw->rkey = wr.wr.bind_mw.rkey;
+
+ return ret;
+}
+
int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
{
struct mlx4_ib_mw *mw = to_mmw(ibmw);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index c6dde71..93bdae5 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -104,6 +104,7 @@ static const __be32 mlx4_ib_opcode[] = {
[IB_WR_FAST_REG_MR] = cpu_to_be32(MLX4_OPCODE_FMR),
[IB_WR_MASKED_ATOMIC_CMP_AND_SWP] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
+ [IB_WR_BIND_MW] = cpu_to_be32(MLX4_OPCODE_BIND_MW),
};
static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
@@ -1953,9 +1954,12 @@ static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq
static __be32 convert_access(int acc)
{
- return (acc & IB_ACCESS_REMOTE_ATOMIC ? cpu_to_be32(MLX4_WQE_FMR_PERM_ATOMIC) : 0) |
- (acc & IB_ACCESS_REMOTE_WRITE ? cpu_to_be32(MLX4_WQE_FMR_PERM_REMOTE_WRITE) : 0) |
- (acc & IB_ACCESS_REMOTE_READ ? cpu_to_be32(MLX4_WQE_FMR_PERM_REMOTE_READ) : 0) |
+ return (acc & IB_ACCESS_REMOTE_ATOMIC ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC) : 0) |
+ (acc & IB_ACCESS_REMOTE_WRITE ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE) : 0) |
+ (acc & IB_ACCESS_REMOTE_READ ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ) : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_WRITE) : 0) |
cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_READ);
}
@@ -1981,6 +1985,24 @@ static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg, struct ib_send_wr *wr)
fseg->reserved[1] = 0;
}
+static void set_bind_seg(struct mlx4_wqe_bind_seg *bseg, struct ib_send_wr *wr)
+{
+ bseg->flags1 =
+ convert_access(wr->wr.bind_mw.bind_info.mw_access_flags) &
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ |
+ MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE |
+ MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC);
+ bseg->flags2 = 0;
+ if (wr->wr.bind_mw.mw->type == IB_MW_TYPE_2)
+ bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_TYPE_2);
+ if (wr->wr.bind_mw.bind_info.mw_access_flags & IB_ZERO_BASED)
+ bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_ZERO_BASED);
+ bseg->new_rkey = cpu_to_be32(wr->wr.bind_mw.rkey);
+ bseg->lkey = cpu_to_be32(wr->wr.bind_mw.bind_info.mr->lkey);
+ bseg->addr = cpu_to_be64(wr->wr.bind_mw.bind_info.addr);
+ bseg->length = cpu_to_be64(wr->wr.bind_mw.bind_info.length);
+}
+
static void set_local_inv_seg(struct mlx4_wqe_local_inval_seg *iseg, u32 rkey)
{
memset(iseg, 0, sizeof(*iseg));
@@ -2289,6 +2311,13 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
size += sizeof (struct mlx4_wqe_fmr_seg) / 16;
break;
+ case IB_WR_BIND_MW:
+ ctrl->srcrb_flags |=
+ cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
+ set_bind_seg(wqe, wr);
+ wqe += sizeof(struct mlx4_wqe_bind_seg);
+ size += sizeof(struct mlx4_wqe_bind_seg) / 16;
+ break;
default:
/* No extra segments required for sends */
break;
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 6c8a68c..77ca1a4 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -265,6 +265,11 @@ struct mlx4_wqe_lso_seg {
__be32 header[0];
};
+enum mlx4_wqe_bind_seg_flags2 {
+ MLX4_WQE_BIND_TYPE_2 = (1<<31),
+ MLX4_WQE_BIND_ZERO_BASED = (1<<30),
+};
+
struct mlx4_wqe_bind_seg {
__be32 flags1;
__be32 flags2;
@@ -277,9 +282,9 @@ struct mlx4_wqe_bind_seg {
enum {
MLX4_WQE_FMR_PERM_LOCAL_READ = 1 << 27,
MLX4_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28,
- MLX4_WQE_FMR_PERM_REMOTE_READ = 1 << 29,
- MLX4_WQE_FMR_PERM_REMOTE_WRITE = 1 << 30,
- MLX4_WQE_FMR_PERM_ATOMIC = 1 << 31
+ MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ = 1 << 29,
+ MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE = 1 << 30,
+ MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC = 1 << 31
};
struct mlx4_wqe_fmr_seg {
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH for-next 10/10] IB/mlx4_ib: Advertize MW support
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (8 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 09/10] IB/mlx4_ib: Support memory window binding Or Gerlitz
@ 2013-02-06 16:19 ` Or Gerlitz
2013-02-18 16:47 ` [PATCH for-next 00/10] mlx4: Add Memory Windows support Or Gerlitz
10 siblings, 0 replies; 16+ messages in thread
From: Or Gerlitz @ 2013-02-06 16:19 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
haggaie-VPRAkNaXOzVWk0Htik3J/w, monis-VPRAkNaXOzVWk0Htik3J/w,
shanim-xlywION9k29BDgjK7y7TUQ, Shani Michaeli, Or Gerlitz
From: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Indicate memory windows support through device capabilities, kernel
verb entries and the relevant uverbs command mask entries.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shani Michaeli <shanim-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx4/main.c | 19 +++++++++++++++++++
1 files changed, 19 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index e7d81c0..f77ff4f 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -137,6 +137,14 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)
props->device_cap_flags |= IB_DEVICE_XRC;
+ if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW)
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW;
+ if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
+ if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_WIN_TYPE_2B)
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
+ else
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
+ }
props->vendor_id = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
0xffffff;
@@ -1434,6 +1442,17 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc;
}
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
+ dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
+ ibdev->ib_dev.alloc_mw = mlx4_ib_alloc_mw;
+ ibdev->ib_dev.bind_mw = mlx4_ib_bind_mw;
+ ibdev->ib_dev.dealloc_mw = mlx4_ib_dealloc_mw;
+
+ ibdev->ib_dev.uverbs_cmd_mask |=
+ (1ull << IB_USER_VERBS_CMD_ALLOC_MW) |
+ (1ull << IB_USER_VERBS_CMD_DEALLOC_MW);
+ }
+
if (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) {
ibdev->ib_dev.alloc_xrcd = mlx4_ib_alloc_xrcd;
ibdev->ib_dev.dealloc_xrcd = mlx4_ib_dealloc_xrcd;
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH for-next 00/10] mlx4: Add Memory Windows support
[not found] ` <1360167556-20756-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (9 preceding siblings ...)
2013-02-06 16:19 ` [PATCH for-next 10/10] IB/mlx4_ib: Advertize MW support Or Gerlitz
@ 2013-02-18 16:47 ` Or Gerlitz
[not found] ` <CAJZOPZJwcLyhc88WCjmnrBRDLo9qp6snSLxQGEZUfYOTyuVMCg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
10 siblings, 1 reply; 16+ messages in thread
From: Or Gerlitz @ 2013-02-18 16:47 UTC (permalink / raw)
To: Roland Dreier
Cc: linux-rdma, haggaie-VPRAkNaXOzVWk0Htik3J/w,
monis-VPRAkNaXOzVWk0Htik3J/w, shanim-xlywION9k29BDgjK7y7TUQ
On Wed, Feb 6, 2013 at 6:19 PM, Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org> wrote:
> Here's a series from Shani Michaeli and Haggai Eran adds mlx4 driver
> support for Memory Windows.
Hi Roland,
So things are warming up for the 3.9 merge window, I see that this
series is marked as "new" in your patchwork - any comments? is it be
condisred in for 3.9?
Or.
> The first entries in this set are "pre patches" preparing the grounds for the
> actual implementation of MWs. Later there're two core patches, one to
> ib_verbs.h adding support for type 2 MWs and another one to uverbs that
> exposes MW commands to user space. And finally the actual mlx4 driver
> MWs patches.
> Shani Michaeli (10):
> IB/mlx4_ib: Remove local invalidate segment unused fields
> net/mlx4_core: Rename MPT related service routines to have mpt_ prefix
> net/mlx4_core: Propogate MR deregistration failure
> net/mlx4_core: Disable memory windows for VFs
> net/mlx4_core: Enable memory windows in {INIT,QUERY}_HCA
> IB/core: Enhance memory windows support
> IB/uverbs: Implement memory windows support in uverbs
> mlx4: Implement memory windows allocation and deallocation
> IB/mlx4_ib: Support memory window binding
> IB/mlx4_ib: Advertize MW support
>
> drivers/infiniband/core/uverbs.h | 2 +
> drivers/infiniband/core/uverbs_cmd.c | 121 +++++++++++++
> drivers/infiniband/core/uverbs_main.c | 13 ++-
> drivers/infiniband/core/verbs.c | 5 +-
> drivers/infiniband/hw/cxgb3/iwch_provider.c | 5 +-
> drivers/infiniband/hw/cxgb3/iwch_qp.c | 15 +-
> drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 2 +-
> drivers/infiniband/hw/cxgb4/mem.c | 5 +-
> drivers/infiniband/hw/ehca/ehca_iverbs.h | 2 +-
> drivers/infiniband/hw/ehca/ehca_mrmw.c | 5 +-
> drivers/infiniband/hw/mlx4/main.c | 19 ++
> drivers/infiniband/hw/mlx4/mlx4_ib.h | 14 ++
> drivers/infiniband/hw/mlx4/mr.c | 87 +++++++++-
> drivers/infiniband/hw/mlx4/qp.c | 41 ++++-
> drivers/infiniband/hw/nes/nes_verbs.c | 19 ++-
> drivers/net/ethernet/mellanox/mlx4/en_main.c | 4 +-
> drivers/net/ethernet/mellanox/mlx4/fw.c | 14 ++-
> drivers/net/ethernet/mellanox/mlx4/fw.h | 1 +
> drivers/net/ethernet/mellanox/mlx4/main.c | 4 +
> drivers/net/ethernet/mellanox/mlx4/mlx4.h | 34 +++-
> drivers/net/ethernet/mellanox/mlx4/mr.c | 186
> +++++++++++++++-----
> .../net/ethernet/mellanox/mlx4/resource_tracker.c | 63 ++++++-
> include/linux/mlx4/device.h | 22 ++-
> include/linux/mlx4/qp.h | 19 ++-
> include/rdma/ib_verbs.h | 73 +++++++-
> include/uapi/rdma/ib_user_verbs.h | 16 ++
> net/sunrpc/xprtrdma/verbs.c | 20 +-
> 27 files changed, 683 insertions(+), 128 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 16+ messages in thread