* [PATCH for-next 2/5] IB/core: Add support for extended query device caps
[not found] ` <1415001766-8366-1-git-send-email-eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-11-03 8:02 ` [PATCH for-next 1/5] IB/mlx5: Fix sparse warnings Eli Cohen
@ 2014-11-03 8:02 ` Eli Cohen
[not found] ` <1415001766-8366-3-git-send-email-eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-11-03 8:02 ` [PATCH for-next 3/5] IB/core: Extend atomic operations Eli Cohen
` (2 subsequent siblings)
4 siblings, 1 reply; 8+ messages in thread
From: Eli Cohen @ 2014-11-03 8:02 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
ogerlitz-VPRAkNaXOzVWk0Htik3J/w, yevgenyp-VPRAkNaXOzVWk0Htik3J/w,
Eli Cohen
Add extensible query device capabilities verb to allow adding new features.
ib_uverbs_ex_query_device is added and copy_query_dev_fields is used to copy
capability fields to be used by both ib_uverbs_query_device and
ib_uverbs_ex_query_device.
Signed-off-by: Eli Cohen <eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/uverbs.h | 1 +
drivers/infiniband/core/uverbs_cmd.c | 127 +++++++++++++++++++++++-----------
drivers/infiniband/core/uverbs_main.c | 3 +-
include/uapi/rdma/ib_user_verbs.h | 12 +++-
4 files changed, 100 insertions(+), 43 deletions(-)
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 643c08a025a5..b716b0815644 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -258,5 +258,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
IB_UVERBS_DECLARE_EX_CMD(create_flow);
IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
+IB_UVERBS_DECLARE_EX_CMD(query_device);
#endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 5ba2a86aab6a..da3fd8cdd86e 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -378,6 +378,52 @@ err:
return ret;
}
+static void copy_query_dev_fields(struct ib_uverbs_file *file,
+ struct ib_uverbs_query_device_resp *resp,
+ struct ib_device_attr *attr)
+{
+ resp->fw_ver = attr->fw_ver;
+ resp->node_guid = file->device->ib_dev->node_guid;
+ resp->sys_image_guid = attr->sys_image_guid;
+ resp->max_mr_size = attr->max_mr_size;
+ resp->page_size_cap = attr->page_size_cap;
+ resp->vendor_id = attr->vendor_id;
+ resp->vendor_part_id = attr->vendor_part_id;
+ resp->hw_ver = attr->hw_ver;
+ resp->max_qp = attr->max_qp;
+ resp->max_qp_wr = attr->max_qp_wr;
+ resp->device_cap_flags = attr->device_cap_flags;
+ resp->max_sge = attr->max_sge;
+ resp->max_sge_rd = attr->max_sge_rd;
+ resp->max_cq = attr->max_cq;
+ resp->max_cqe = attr->max_cqe;
+ resp->max_mr = attr->max_mr;
+ resp->max_pd = attr->max_pd;
+ resp->max_qp_rd_atom = attr->max_qp_rd_atom;
+ resp->max_ee_rd_atom = attr->max_ee_rd_atom;
+ resp->max_res_rd_atom = attr->max_res_rd_atom;
+ resp->max_qp_init_rd_atom = attr->max_qp_init_rd_atom;
+ resp->max_ee_init_rd_atom = attr->max_ee_init_rd_atom;
+ resp->atomic_cap = attr->atomic_cap;
+ resp->max_ee = attr->max_ee;
+ resp->max_rdd = attr->max_rdd;
+ resp->max_mw = attr->max_mw;
+ resp->max_raw_ipv6_qp = attr->max_raw_ipv6_qp;
+ resp->max_raw_ethy_qp = attr->max_raw_ethy_qp;
+ resp->max_mcast_grp = attr->max_mcast_grp;
+ resp->max_mcast_qp_attach = attr->max_mcast_qp_attach;
+ resp->max_total_mcast_qp_attach = attr->max_total_mcast_qp_attach;
+ resp->max_ah = attr->max_ah;
+ resp->max_fmr = attr->max_fmr;
+ resp->max_map_per_fmr = attr->max_map_per_fmr;
+ resp->max_srq = attr->max_srq;
+ resp->max_srq_wr = attr->max_srq_wr;
+ resp->max_srq_sge = attr->max_srq_sge;
+ resp->max_pkeys = attr->max_pkeys;
+ resp->local_ca_ack_delay = attr->local_ca_ack_delay;
+ resp->phys_port_cnt = file->device->ib_dev->phys_port_cnt;
+}
+
ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
const char __user *buf,
int in_len, int out_len)
@@ -398,47 +444,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
return ret;
memset(&resp, 0, sizeof resp);
-
- resp.fw_ver = attr.fw_ver;
- resp.node_guid = file->device->ib_dev->node_guid;
- resp.sys_image_guid = attr.sys_image_guid;
- resp.max_mr_size = attr.max_mr_size;
- resp.page_size_cap = attr.page_size_cap;
- resp.vendor_id = attr.vendor_id;
- resp.vendor_part_id = attr.vendor_part_id;
- resp.hw_ver = attr.hw_ver;
- resp.max_qp = attr.max_qp;
- resp.max_qp_wr = attr.max_qp_wr;
- resp.device_cap_flags = attr.device_cap_flags;
- resp.max_sge = attr.max_sge;
- resp.max_sge_rd = attr.max_sge_rd;
- resp.max_cq = attr.max_cq;
- resp.max_cqe = attr.max_cqe;
- resp.max_mr = attr.max_mr;
- resp.max_pd = attr.max_pd;
- resp.max_qp_rd_atom = attr.max_qp_rd_atom;
- resp.max_ee_rd_atom = attr.max_ee_rd_atom;
- resp.max_res_rd_atom = attr.max_res_rd_atom;
- resp.max_qp_init_rd_atom = attr.max_qp_init_rd_atom;
- resp.max_ee_init_rd_atom = attr.max_ee_init_rd_atom;
- resp.atomic_cap = attr.atomic_cap;
- resp.max_ee = attr.max_ee;
- resp.max_rdd = attr.max_rdd;
- resp.max_mw = attr.max_mw;
- resp.max_raw_ipv6_qp = attr.max_raw_ipv6_qp;
- resp.max_raw_ethy_qp = attr.max_raw_ethy_qp;
- resp.max_mcast_grp = attr.max_mcast_grp;
- resp.max_mcast_qp_attach = attr.max_mcast_qp_attach;
- resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
- resp.max_ah = attr.max_ah;
- resp.max_fmr = attr.max_fmr;
- resp.max_map_per_fmr = attr.max_map_per_fmr;
- resp.max_srq = attr.max_srq;
- resp.max_srq_wr = attr.max_srq_wr;
- resp.max_srq_sge = attr.max_srq_sge;
- resp.max_pkeys = attr.max_pkeys;
- resp.local_ca_ack_delay = attr.local_ca_ack_delay;
- resp.phys_port_cnt = file->device->ib_dev->phys_port_cnt;
+ copy_query_dev_fields(file, &resp, &attr);
if (copy_to_user((void __user *) (unsigned long) cmd.response,
&resp, sizeof resp))
@@ -3253,3 +3259,42 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
return ret ? ret : in_len;
}
+
+int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
+ struct ib_udata *ucore,
+ struct ib_udata *uhw)
+{
+ struct ib_uverbs_ex_query_device_resp resp;
+ struct ib_uverbs_ex_query_device cmd;
+ struct ib_device_attr attr;
+ struct ib_device *device;
+ int err;
+
+ device = file->device->ib_dev;
+ if (ucore->inlen < sizeof(cmd))
+ return -EINVAL;
+
+ if (ucore->outlen < sizeof(resp))
+ return -ENOSPC;
+
+ err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+ if (err)
+ return err;
+
+ if (cmd.comp_mask)
+ return -EINVAL;
+
+ err = device->query_device(device, &attr);
+ if (err)
+ return err;
+
+ memset(&resp, 0, sizeof(resp));
+ copy_query_dev_fields(file, &resp.base, &attr);
+ resp.comp_mask = 0;
+
+ err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
+ if (err)
+ return err;
+
+ return 0;
+}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 71ab83fde472..974025028790 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -122,7 +122,8 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
struct ib_udata *ucore,
struct ib_udata *uhw) = {
[IB_USER_VERBS_EX_CMD_CREATE_FLOW] = ib_uverbs_ex_create_flow,
- [IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow
+ [IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow,
+ [IB_USER_VERBS_EX_CMD_QUERY_DEVICE] = ib_uverbs_ex_query_device
};
static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 26daf55ff76e..ed8c3d9da42c 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -90,8 +90,9 @@ enum {
};
enum {
+ IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
- IB_USER_VERBS_EX_CMD_DESTROY_FLOW
+ IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
};
/*
@@ -201,6 +202,15 @@ struct ib_uverbs_query_device_resp {
__u8 reserved[4];
};
+struct ib_uverbs_ex_query_device {
+ __u32 comp_mask;
+};
+
+struct ib_uverbs_ex_query_device_resp {
+ struct ib_uverbs_query_device_resp base;
+ __u32 comp_mask;
+};
+
struct ib_uverbs_query_port {
__u64 response;
__u8 port_num;
--
2.1.2
--
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] 8+ messages in thread* [PATCH for-next 3/5] IB/core: Extend atomic operations
[not found] ` <1415001766-8366-1-git-send-email-eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-11-03 8:02 ` [PATCH for-next 1/5] IB/mlx5: Fix sparse warnings Eli Cohen
2014-11-03 8:02 ` [PATCH for-next 2/5] IB/core: Add support for extended query device caps Eli Cohen
@ 2014-11-03 8:02 ` Eli Cohen
2014-11-03 8:02 ` [PATCH for-next 4/5] IB/mlx5: Add extended atomic support Eli Cohen
2014-11-03 8:02 ` [PATCH for-next 5/5] IB/mlx4: Modify mlx4 to comply with extended atomic definitions Eli Cohen
4 siblings, 0 replies; 8+ messages in thread
From: Eli Cohen @ 2014-11-03 8:02 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
ogerlitz-VPRAkNaXOzVWk0Htik3J/w, yevgenyp-VPRAkNaXOzVWk0Htik3J/w,
Eli Cohen
Further enhance the extended atomic operations support as was introduced
in commit 5e80ba8ff0bd "IB/core: Add support for masked atomic operations".
1. Allow arbitrary argument sizes. The original extended atomics commit defined
64 bits arguments. This patch allows arbitrary arguments which are power of 2
bytes in size.
2. Add the option to define response for atomic operations in network order.
enum ib_atomic_cap is extended to have big endian variants.
The device attributes struct defines three new fields:
log_atomic_arg_sizes - is a bit mask which encodes which argument sizes are
supported. A set bit at location n (zero based) means an argument of size 2 ^ n
is supported.
max_fa_bit_boundary - Max fetch and add bit boundary. Multi field fetch and add
operations use a bit mask that defines bit locations where carry bit is not
passed to the next higher order bit. So, if this field has the value 64, it
means that the max value subject to fetch and add is 64 bits which means no
carry from bit 63 to 64 or from bit 127 to 128 etc.
log_max_atomic_inline - atomic arguments can be inline in the WQE or be
referenced through a memory key. This value defines the max inline argument
size possible.
Signed-off-by: Eli Cohen <eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/uverbs_cmd.c | 16 +++++++++++++++-
include/rdma/ib_verbs.h | 7 ++++++-
include/uapi/rdma/ib_user_verbs.h | 14 ++++++++++++++
3 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index da3fd8cdd86e..f66686e40ae6 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -445,6 +445,8 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
memset(&resp, 0, sizeof resp);
copy_query_dev_fields(file, &resp, &attr);
+ if (resp.atomic_cap > IB_ATOMIC_GLOB)
+ resp.atomic_cap = IB_ATOMIC_NONE;
if (copy_to_user((void __user *) (unsigned long) cmd.response,
&resp, sizeof resp))
@@ -3281,7 +3283,7 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
if (err)
return err;
- if (cmd.comp_mask)
+ if (cmd.comp_mask & ~IB_UVERBS_EX_QUERY_DEV_MAX_MASK)
return -EINVAL;
err = device->query_device(device, &attr);
@@ -3292,6 +3294,18 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
copy_query_dev_fields(file, &resp.base, &attr);
resp.comp_mask = 0;
+ if (cmd.comp_mask & IB_UVERBS_EX_QUERY_DEV_MASKED_ATOMIC) {
+ resp.atomics.masked_atomic_cap = attr.masked_atomic_cap;
+ resp.atomics.log_atomic_arg_sizes = attr.log_atomic_arg_sizes;
+ resp.atomics.max_fa_bit_boundary = attr.max_fa_bit_boundary;
+ resp.atomics.log_max_atomic_inline = attr.log_max_atomic_inline;
+ resp.comp_mask |= IB_UVERBS_EX_QUERY_DEV_MASKED_ATOMIC;
+ } else {
+ resp.atomics.masked_atomic_cap = IB_ATOMIC_NONE;
+ resp.atomics.log_atomic_arg_sizes = 0;
+ resp.atomics.max_fa_bit_boundary = 0;
+ resp.atomics.log_max_atomic_inline = 0;
+ }
err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
if (err)
return err;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 470a011d6fa4..7f1d20a3f4c7 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -140,7 +140,9 @@ enum ib_signature_guard_cap {
enum ib_atomic_cap {
IB_ATOMIC_NONE,
IB_ATOMIC_HCA,
- IB_ATOMIC_GLOB
+ IB_ATOMIC_GLOB,
+ IB_ATOMIC_HCA_REPLY_BE,
+ IB_ATOMIC_GLOB_REPLY_BE,
};
struct ib_device_attr {
@@ -186,6 +188,9 @@ struct ib_device_attr {
u8 local_ca_ack_delay;
int sig_prot_cap;
int sig_guard_cap;
+ u32 log_atomic_arg_sizes; /* bit-mask of supported sizes */
+ u32 max_fa_bit_boundary;
+ u32 log_max_atomic_inline;
};
enum ib_mtu {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index ed8c3d9da42c..ec98fe636f2b 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -202,13 +202,27 @@ struct ib_uverbs_query_device_resp {
__u8 reserved[4];
};
+enum {
+ IB_UVERBS_EX_QUERY_DEV_MASKED_ATOMIC = 1 << 0,
+ IB_UVERBS_EX_QUERY_DEV_LAST = 1 << 1,
+ IB_UVERBS_EX_QUERY_DEV_MAX_MASK = IB_UVERBS_EX_QUERY_DEV_LAST - 1,
+};
+
struct ib_uverbs_ex_query_device {
__u32 comp_mask;
};
+struct ib_uverbs_ex_atomic_caps {
+ __u32 masked_atomic_cap;
+ __u32 log_atomic_arg_sizes; /* bit-mask of supported sizes */
+ __u32 max_fa_bit_boundary;
+ __u32 log_max_atomic_inline;
+};
+
struct ib_uverbs_ex_query_device_resp {
struct ib_uverbs_query_device_resp base;
__u32 comp_mask;
+ struct ib_uverbs_ex_atomic_caps atomics;
};
struct ib_uverbs_query_port {
--
2.1.2
--
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] 8+ messages in thread* [PATCH for-next 4/5] IB/mlx5: Add extended atomic support
[not found] ` <1415001766-8366-1-git-send-email-eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
` (2 preceding siblings ...)
2014-11-03 8:02 ` [PATCH for-next 3/5] IB/core: Extend atomic operations Eli Cohen
@ 2014-11-03 8:02 ` Eli Cohen
2014-11-03 8:02 ` [PATCH for-next 5/5] IB/mlx4: Modify mlx4 to comply with extended atomic definitions Eli Cohen
4 siblings, 0 replies; 8+ messages in thread
From: Eli Cohen @ 2014-11-03 8:02 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
ogerlitz-VPRAkNaXOzVWk0Htik3J/w, yevgenyp-VPRAkNaXOzVWk0Htik3J/w,
Eli Cohen
Connect-IB extended atomic operations provides masked compare and swap and
multi field fetch and add operations with arguments sizes bigger than 64 bits.
Also, Connect-IB supports BE replies to atomic opertation, add that
to the advertized capabilities.
Add the required functionality to mlx5 and publish capabilities.
Signed-off-by: Eli Cohen <eli-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/hw/mlx5/main.c | 47 +++++++++++++++++++++-
drivers/infiniband/hw/mlx5/qp.c | 26 ++++++++++--
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 51 +++++++++++++++++++++++-
drivers/net/ethernet/mellanox/mlx5/core/main.c | 21 +++-------
include/linux/mlx5/device.h | 4 +-
include/linux/mlx5/driver.h | 55 ++++++++++++++++++++++----
include/linux/mlx5/mlx5_ifc.h | 20 ++++++++++
7 files changed, 194 insertions(+), 30 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 1ba6c42e4df8..3c6fa99c4256 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -151,6 +151,47 @@ static void free_comp_eqs(struct mlx5_ib_dev *dev)
spin_unlock(&table->lock);
}
+static void update_atomic_caps(struct mlx5_caps *caps,
+ struct ib_device_attr *props)
+{
+ struct mlx5_atomic_caps *atom = &caps->atom;
+ unsigned long last;
+ unsigned long arg;
+ int tmp;
+
+ tmp = MLX5_ATOMIC_OPS_CMP_SWAP | MLX5_ATOMIC_OPS_FETCH_ADD;
+ if (((atom->atomic_ops & tmp) == tmp) && (atom->atomic_sizes_qp & 8)) {
+ if (atom->requestor_endianess)
+ props->atomic_cap = IB_ATOMIC_HCA;
+ else
+ props->atomic_cap = IB_ATOMIC_HCA_REPLY_BE;
+ } else {
+ props->atomic_cap = IB_ATOMIC_NONE;
+ }
+
+ tmp = MLX5_ATOMIC_OPS_MASKED_CMP_SWAP | MLX5_ATOMIC_OPS_MASKED_FETCH_ADD;
+ if (((atom->atomic_ops & tmp) == tmp)) {
+ if (atom->requestor_endianess)
+ props->masked_atomic_cap = IB_ATOMIC_HCA;
+ else
+ props->masked_atomic_cap = IB_ATOMIC_HCA_REPLY_BE;
+ } else {
+ props->masked_atomic_cap = IB_ATOMIC_NONE;
+ }
+ if ((props->atomic_cap != IB_ATOMIC_NONE) ||
+ (props->masked_atomic_cap != IB_ATOMIC_NONE)) {
+ props->log_atomic_arg_sizes = caps->atom.atomic_sizes_qp;
+ props->max_fa_bit_boundary = 64;
+ arg = (unsigned long)props->log_atomic_arg_sizes;
+ last = find_last_bit(&arg, sizeof(arg));
+ props->log_max_atomic_inline = min_t(unsigned long, last, 6);
+ } else {
+ props->log_atomic_arg_sizes = 0;
+ props->max_fa_bit_boundary = 0;
+ props->log_max_atomic_inline = 0;
+ }
+}
+
static int mlx5_ib_query_device(struct ib_device *ibdev,
struct ib_device_attr *props)
{
@@ -235,8 +276,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->max_srq_sge = max_rq_sg - 1;
props->max_fast_reg_page_list_len = (unsigned int)-1;
props->local_ca_ack_delay = gen->local_ca_ack_delay;
- props->atomic_cap = IB_ATOMIC_NONE;
- props->masked_atomic_cap = IB_ATOMIC_NONE;
+ update_atomic_caps(&dev->mdev->caps, props);
props->max_pkeys = be16_to_cpup((__be16 *)(out_mad->data + 28));
props->max_mcast_grp = 1 << gen->log_max_mcg;
props->max_mcast_qp_attach = gen->max_qp_mcg;
@@ -1374,6 +1414,9 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
}
+ dev->ib_dev.uverbs_ex_cmd_mask |=
+ (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE);
+
err = init_node_data(dev);
if (err)
goto err_eqs;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9ca39ad68cb8..47ca93ce214f 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1254,7 +1254,27 @@ int mlx5_ib_destroy_qp(struct ib_qp *qp)
return 0;
}
-static __be32 to_mlx5_access_flags(struct mlx5_ib_qp *qp, const struct ib_qp_attr *attr,
+static u32 atomic_mode_qp(struct mlx5_ib_dev *dev)
+{
+ struct mlx5_atomic_caps *acaps = &dev->mdev->caps.atom;
+ unsigned long mask;
+ unsigned long tmp;
+
+ mask = acaps->atomic_sizes_qp & acaps->atomic_sizes_dc;
+
+ tmp = find_last_bit(&mask, 8 * sizeof(mask));
+ if (tmp < 2 || tmp >= 16)
+ return MLX5_ATOMIC_MODE_NONE << 16;
+
+ if (tmp == 2)
+ return MLX5_ATOMIC_MODE_CX << 16;
+
+ return tmp << 16;
+}
+
+static __be32 to_mlx5_access_flags(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_qp *qp,
+ const struct ib_qp_attr *attr,
int attr_mask)
{
u32 hw_access_flags = 0;
@@ -1277,7 +1297,7 @@ static __be32 to_mlx5_access_flags(struct mlx5_ib_qp *qp, const struct ib_qp_att
if (access_flags & IB_ACCESS_REMOTE_READ)
hw_access_flags |= MLX5_QP_BIT_RRE;
if (access_flags & IB_ACCESS_REMOTE_ATOMIC)
- hw_access_flags |= (MLX5_QP_BIT_RAE | MLX5_ATOMIC_MODE_CX);
+ hw_access_flags |= (MLX5_QP_BIT_RAE | atomic_mode_qp(dev));
if (access_flags & IB_ACCESS_REMOTE_WRITE)
hw_access_flags |= MLX5_QP_BIT_RWE;
@@ -1620,7 +1640,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
}
if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC))
- context->params2 |= to_mlx5_access_flags(qp, attr, attr_mask);
+ context->params2 |= to_mlx5_access_flags(dev, qp, attr, attr_mask);
if (attr_mask & IB_QP_MIN_RNR_TIMER)
context->rnr_nextrecvpsn |= cpu_to_be32(attr->min_rnr_timer << 24);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 087c4c797deb..b1d2d7a44b6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -33,6 +33,7 @@
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
#include <linux/module.h>
+#include <linux/mlx5/mlx5_ifc.h>
#include "mlx5_core.h"
int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev)
@@ -64,9 +65,57 @@ out_out:
return err;
}
+static int handle_atomic_caps(struct mlx5_core_dev *dev,
+ struct mlx5_caps *caps)
+{
+ u16 opmod = HCA_CAP_OPMOD_ATOMIC | HCA_CAP_OPMOD_GET_CUR;
+ u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
+ int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+ void *cap_ptr;
+ void *out;
+ int err;
+
+ memset(in, 0, sizeof(in));
+ out = kzalloc(out_sz, GFP_KERNEL);
+ if (!out)
+ return -ENOMEM;
+
+ MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+ MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
+ if (err)
+ goto query_ex;
+
+ err = mlx5_cmd_status_to_err_v2(out);
+ if (err) {
+ mlx5_core_warn(dev, "query atomic caps failed, %d\n", err);
+ goto query_ex;
+ }
+ mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod));
+ cap_ptr = MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct);
+ caps->atom.requestor_endianess = MLX5_GET_PR(atomic_cap, cap_ptr, atomic_req_endianess);
+ caps->atom.atomic_ops = MLX5_GET_PR(atomic_cap, cap_ptr, atomic_operations);
+ caps->atom.atomic_sizes_qp = MLX5_GET_PR(atomic_cap, cap_ptr, atomic_size_qp);
+ caps->atom.atomic_sizes_dc = MLX5_GET_PR(atomic_cap, cap_ptr, atomic_size_dc);
+
+query_ex:
+ kfree(out);
+ return err;
+}
+
int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, struct mlx5_caps *caps)
{
- return mlx5_core_get_caps(dev, caps, HCA_CAP_OPMOD_GET_CUR);
+ int err;
+
+ err = mlx5_core_get_caps(dev, caps,
+ HCA_CAP_OPMOD_GET_CUR | HCA_CAP_OPMOD_GENERAL);
+ if (err)
+ return err;
+
+ if (caps->gen.flags & MLX5_DEV_CAP_FLAG_ATOMIC)
+ err = handle_atomic_caps(dev, caps);
+
+ return err;
}
int mlx5_cmd_init_hca(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3d8e8e489b2d..88b2ffa0edfb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -345,18 +345,6 @@ static void fw2drv_caps(struct mlx5_caps *caps, void *out)
gen->log_uar_page_sz = MLX5_GET_PR(cmd_hca_cap, out, log_uar_page_sz);
}
-static const char *caps_opmod_str(u16 opmod)
-{
- switch (opmod) {
- case HCA_CAP_OPMOD_GET_MAX:
- return "GET_MAX";
- case HCA_CAP_OPMOD_GET_CUR:
- return "GET_CUR";
- default:
- return "Invalid";
- }
-}
-
int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
u16 opmod)
{
@@ -377,7 +365,8 @@ int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
err = mlx5_cmd_status_to_err_v2(out);
if (err) {
- mlx5_core_warn(dev, "query max hca cap failed, %d\n", err);
+ mlx5_core_warn(dev, "query %s hca caps failed, %d\n",
+ caps_opmod_str(opmod), err);
goto query_ex;
}
mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod));
@@ -426,11 +415,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
if (!cur_caps)
goto query_ex;
- err = mlx5_core_get_caps(dev, max_caps, HCA_CAP_OPMOD_GET_MAX);
+ err = mlx5_core_get_caps(dev, max_caps,
+ HCA_CAP_OPMOD_GET_MAX | HCA_CAP_OPMOD_GENERAL);
if (err)
goto query_ex;
- err = mlx5_core_get_caps(dev, cur_caps, HCA_CAP_OPMOD_GET_CUR);
+ err = mlx5_core_get_caps(dev, cur_caps,
+ HCA_CAP_OPMOD_GET_CUR | HCA_CAP_OPMOD_GENERAL);
if (err)
goto query_ex;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 1d67fd32e71c..6e9661105dfa 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -227,12 +227,12 @@ enum {
MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8,
MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9,
MLX5_DEV_CAP_FLAG_APM = 1LL << 17,
- MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18,
MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23,
MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24,
MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29,
MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30,
MLX5_DEV_CAP_FLAG_RESIZE_SRQ = 1LL << 32,
+ MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 33,
MLX5_DEV_CAP_FLAG_DCT = 1LL << 37,
MLX5_DEV_CAP_FLAG_REMOTE_FENCE = 1LL << 38,
MLX5_DEV_CAP_FLAG_TLP_HINTS = 1LL << 39,
@@ -298,6 +298,8 @@ enum {
enum {
HCA_CAP_OPMOD_GET_MAX = 0,
HCA_CAP_OPMOD_GET_CUR = 1,
+ HCA_CAP_OPMOD_GENERAL = 0 << 1,
+ HCA_CAP_OPMOD_ATOMIC = 3 << 1,
};
struct mlx5_inbox_hdr {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 246310dc8bef..bdca5d94e6fc 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -89,14 +89,22 @@ enum {
};
enum {
- MLX5_ATOMIC_MODE_IB_COMP = 1 << 16,
- MLX5_ATOMIC_MODE_CX = 2 << 16,
- MLX5_ATOMIC_MODE_8B = 3 << 16,
- MLX5_ATOMIC_MODE_16B = 4 << 16,
- MLX5_ATOMIC_MODE_32B = 5 << 16,
- MLX5_ATOMIC_MODE_64B = 6 << 16,
- MLX5_ATOMIC_MODE_128B = 7 << 16,
- MLX5_ATOMIC_MODE_256B = 8 << 16,
+ MLX5_ATOMIC_MODE_NONE = 0,
+ MLX5_ATOMIC_MODE_IB_COMP = 1,
+ MLX5_ATOMIC_MODE_CX = 2,
+ MLX5_ATOMIC_MODE_8B = 3,
+ MLX5_ATOMIC_MODE_16B = 4,
+ MLX5_ATOMIC_MODE_32B = 5,
+ MLX5_ATOMIC_MODE_64B = 6,
+ MLX5_ATOMIC_MODE_128B = 7,
+ MLX5_ATOMIC_MODE_256B = 8,
+};
+
+enum {
+ MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0,
+ MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1,
+ MLX5_ATOMIC_OPS_MASKED_CMP_SWAP = 1 << 2,
+ MLX5_ATOMIC_OPS_MASKED_FETCH_ADD = 1 << 3,
};
enum {
@@ -307,8 +315,16 @@ struct mlx5_general_caps {
u16 log_uar_page_sz;
};
+struct mlx5_atomic_caps {
+ int requestor_endianess;
+ u16 atomic_ops;
+ u16 atomic_sizes_qp;
+ u16 atomic_sizes_dc;
+};
+
struct mlx5_caps {
struct mlx5_general_caps gen;
+ struct mlx5_atomic_caps atom;
};
struct mlx5_cmd_mailbox {
@@ -793,4 +809,27 @@ struct mlx5_profile {
} mr_cache[MAX_MR_CACHE_ENTRIES];
};
+static inline const char *caps_opmod_str(u16 opmod)
+{
+ if (opmod & 1) {
+ switch (opmod & 0xfffe) {
+ case HCA_CAP_OPMOD_GENERAL:
+ return "CUR GENERAL";
+ case HCA_CAP_OPMOD_ATOMIC:
+ return "CUR ATOMIC";
+ default:
+ return "Invalid";
+ }
+ } else {
+ switch (opmod & 0xfffe) {
+ case HCA_CAP_OPMOD_GENERAL:
+ return "MAX GENERAL";
+ case HCA_CAP_OPMOD_ATOMIC:
+ return "MAX ATOMIC";
+ default:
+ return "Invalid";
+ }
+ }
+}
+
#endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5f48b8f592c5..a3e6148066ce 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -346,4 +346,24 @@ struct mlx5_ifc_set_hca_cap_out_bits {
u8 reserved_1[0x40];
};
+struct mlx5_ifc_atomic_cap_bits {
+ u8 reserved_0[0x40];
+
+ u8 atomic_req_endianess[0x1];
+ u8 reserved_1[0x1f];
+
+ u8 reserved_2[0x20];
+
+ u8 reserved_3[0x10];
+ u8 atomic_operations[0x10];
+
+ u8 reserved_4[0x10];
+ u8 atomic_size_qp[0x10];
+
+ u8 reserved_5[0x10];
+ u8 atomic_size_dc[0x10];
+
+ u8 reserved_6[0x720];
+};
+
#endif /* MLX5_IFC_H */
--
2.1.2
--
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] 8+ messages in thread