IB/core: Export ib_create/destroy_flow through uverbs

Implement ib_uverbs_create_flow() and ib_uverbs_destroy_flow() to
support flow steering for user space applications.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Hadar Hen Zion 2013-08-14 13:58:30 +03:00 committed by Roland Dreier
parent 400dbc9658
commit 436f2ad05a
5 changed files with 318 additions and 2 deletions

View File

@ -155,6 +155,7 @@ extern struct idr ib_uverbs_cq_idr;
extern struct idr ib_uverbs_qp_idr;
extern struct idr ib_uverbs_srq_idr;
extern struct idr ib_uverbs_xrcd_idr;
extern struct idr ib_uverbs_rule_idr;
void idr_remove_uobj(struct idr *idp, struct ib_uobject *uobj);
@ -215,5 +216,7 @@ IB_UVERBS_DECLARE_CMD(destroy_srq);
IB_UVERBS_DECLARE_CMD(create_xsrq);
IB_UVERBS_DECLARE_CMD(open_xrcd);
IB_UVERBS_DECLARE_CMD(close_xrcd);
IB_UVERBS_DECLARE_CMD(create_flow);
IB_UVERBS_DECLARE_CMD(destroy_flow);
#endif /* UVERBS_H */

View File

@ -54,6 +54,7 @@ static struct uverbs_lock_class qp_lock_class = { .name = "QP-uobj" };
static struct uverbs_lock_class ah_lock_class = { .name = "AH-uobj" };
static struct uverbs_lock_class srq_lock_class = { .name = "SRQ-uobj" };
static struct uverbs_lock_class xrcd_lock_class = { .name = "XRCD-uobj" };
static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
#define INIT_UDATA(udata, ibuf, obuf, ilen, olen) \
do { \
@ -330,6 +331,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
INIT_LIST_HEAD(&ucontext->srq_list);
INIT_LIST_HEAD(&ucontext->ah_list);
INIT_LIST_HEAD(&ucontext->xrcd_list);
INIT_LIST_HEAD(&ucontext->rule_list);
ucontext->closing = 0;
resp.num_comp_vectors = file->device->num_comp_vectors;
@ -2587,6 +2589,218 @@ out_put:
return ret ? ret : in_len;
}
static int kern_spec_to_ib_spec(struct ib_kern_spec *kern_spec,
union ib_flow_spec *ib_spec)
{
ib_spec->type = kern_spec->type;
switch (ib_spec->type) {
case IB_FLOW_SPEC_ETH:
ib_spec->eth.size = sizeof(struct ib_flow_spec_eth);
if (ib_spec->eth.size != kern_spec->eth.size)
return -EINVAL;
memcpy(&ib_spec->eth.val, &kern_spec->eth.val,
sizeof(struct ib_flow_eth_filter));
memcpy(&ib_spec->eth.mask, &kern_spec->eth.mask,
sizeof(struct ib_flow_eth_filter));
break;
case IB_FLOW_SPEC_IPV4:
ib_spec->ipv4.size = sizeof(struct ib_flow_spec_ipv4);
if (ib_spec->ipv4.size != kern_spec->ipv4.size)
return -EINVAL;
memcpy(&ib_spec->ipv4.val, &kern_spec->ipv4.val,
sizeof(struct ib_flow_ipv4_filter));
memcpy(&ib_spec->ipv4.mask, &kern_spec->ipv4.mask,
sizeof(struct ib_flow_ipv4_filter));
break;
case IB_FLOW_SPEC_TCP:
case IB_FLOW_SPEC_UDP:
ib_spec->tcp_udp.size = sizeof(struct ib_flow_spec_tcp_udp);
if (ib_spec->tcp_udp.size != kern_spec->tcp_udp.size)
return -EINVAL;
memcpy(&ib_spec->tcp_udp.val, &kern_spec->tcp_udp.val,
sizeof(struct ib_flow_tcp_udp_filter));
memcpy(&ib_spec->tcp_udp.mask, &kern_spec->tcp_udp.mask,
sizeof(struct ib_flow_tcp_udp_filter));
break;
default:
return -EINVAL;
}
return 0;
}
ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len)
{
struct ib_uverbs_create_flow cmd;
struct ib_uverbs_create_flow_resp resp;
struct ib_uobject *uobj;
struct ib_flow *flow_id;
struct ib_kern_flow_attr *kern_flow_attr;
struct ib_flow_attr *flow_attr;
struct ib_qp *qp;
int err = 0;
void *kern_spec;
void *ib_spec;
int i;
int kern_attr_size;
if (out_len < sizeof(resp))
return -ENOSPC;
if (copy_from_user(&cmd, buf, sizeof(cmd)))
return -EFAULT;
if ((cmd.flow_attr.type == IB_FLOW_ATTR_SNIFFER &&
!capable(CAP_NET_ADMIN)) || !capable(CAP_NET_RAW))
return -EPERM;
if (cmd.flow_attr.num_of_specs) {
kern_flow_attr = kmalloc(cmd.flow_attr.size, GFP_KERNEL);
if (!kern_flow_attr)
return -ENOMEM;
memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
kern_attr_size = cmd.flow_attr.size - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr_ex);
if (copy_from_user(kern_flow_attr + 1, buf + sizeof(cmd),
kern_attr_size)) {
err = -EFAULT;
goto err_free_attr;
}
} else {
kern_flow_attr = &cmd.flow_attr;
kern_attr_size = sizeof(cmd.flow_attr);
}
uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
if (!uobj) {
err = -ENOMEM;
goto err_free_attr;
}
init_uobj(uobj, 0, file->ucontext, &rule_lock_class);
down_write(&uobj->mutex);
qp = idr_read_qp(cmd.qp_handle, file->ucontext);
if (!qp) {
err = -EINVAL;
goto err_uobj;
}
flow_attr = kmalloc(cmd.flow_attr.size, GFP_KERNEL);
if (!flow_attr) {
err = -ENOMEM;
goto err_put;
}
flow_attr->type = kern_flow_attr->type;
flow_attr->priority = kern_flow_attr->priority;
flow_attr->num_of_specs = kern_flow_attr->num_of_specs;
flow_attr->port = kern_flow_attr->port;
flow_attr->flags = kern_flow_attr->flags;
flow_attr->size = sizeof(*flow_attr);
kern_spec = kern_flow_attr + 1;
ib_spec = flow_attr + 1;
for (i = 0; i < flow_attr->num_of_specs && kern_attr_size > 0; i++) {
err = kern_spec_to_ib_spec(kern_spec, ib_spec);
if (err)
goto err_free;
flow_attr->size +=
((union ib_flow_spec *) ib_spec)->size;
kern_attr_size -= ((struct ib_kern_spec *) kern_spec)->size;
kern_spec += ((struct ib_kern_spec *) kern_spec)->size;
ib_spec += ((union ib_flow_spec *) ib_spec)->size;
}
if (kern_attr_size) {
pr_warn("create flow failed, %d bytes left from uverb cmd\n",
kern_attr_size);
goto err_free;
}
flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
if (IS_ERR(flow_id)) {
err = PTR_ERR(flow_id);
goto err_free;
}
flow_id->qp = qp;
flow_id->uobject = uobj;
uobj->object = flow_id;
err = idr_add_uobj(&ib_uverbs_rule_idr, uobj);
if (err)
goto destroy_flow;
memset(&resp, 0, sizeof(resp));
resp.flow_handle = uobj->id;
if (copy_to_user((void __user *)(unsigned long) cmd.response,
&resp, sizeof(resp))) {
err = -EFAULT;
goto err_copy;
}
put_qp_read(qp);
mutex_lock(&file->mutex);
list_add_tail(&uobj->list, &file->ucontext->rule_list);
mutex_unlock(&file->mutex);
uobj->live = 1;
up_write(&uobj->mutex);
kfree(flow_attr);
if (cmd.flow_attr.num_of_specs)
kfree(kern_flow_attr);
return in_len;
err_copy:
idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
destroy_flow:
ib_destroy_flow(flow_id);
err_free:
kfree(flow_attr);
err_put:
put_qp_read(qp);
err_uobj:
put_uobj_write(uobj);
err_free_attr:
if (cmd.flow_attr.num_of_specs)
kfree(kern_flow_attr);
return err;
}
ssize_t ib_uverbs_destroy_flow(struct ib_uverbs_file *file,
const char __user *buf, int in_len,
int out_len) {
struct ib_uverbs_destroy_flow cmd;
struct ib_flow *flow_id;
struct ib_uobject *uobj;
int ret;
if (copy_from_user(&cmd, buf, sizeof(cmd)))
return -EFAULT;
uobj = idr_write_uobj(&ib_uverbs_rule_idr, cmd.flow_handle,
file->ucontext);
if (!uobj)
return -EINVAL;
flow_id = uobj->object;
ret = ib_destroy_flow(flow_id);
if (!ret)
uobj->live = 0;
put_uobj_write(uobj);
idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
mutex_lock(&file->mutex);
list_del(&uobj->list);
mutex_unlock(&file->mutex);
put_uobj(uobj);
return ret ? ret : in_len;
}
static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
struct ib_uverbs_create_xsrq *cmd,
struct ib_udata *udata)

View File

@ -73,6 +73,7 @@ DEFINE_IDR(ib_uverbs_cq_idr);
DEFINE_IDR(ib_uverbs_qp_idr);
DEFINE_IDR(ib_uverbs_srq_idr);
DEFINE_IDR(ib_uverbs_xrcd_idr);
DEFINE_IDR(ib_uverbs_rule_idr);
static DEFINE_SPINLOCK(map_lock);
static DECLARE_BITMAP(dev_map, IB_UVERBS_MAX_DEVICES);
@ -113,7 +114,9 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
[IB_USER_VERBS_CMD_OPEN_XRCD] = ib_uverbs_open_xrcd,
[IB_USER_VERBS_CMD_CLOSE_XRCD] = ib_uverbs_close_xrcd,
[IB_USER_VERBS_CMD_CREATE_XSRQ] = ib_uverbs_create_xsrq,
[IB_USER_VERBS_CMD_OPEN_QP] = ib_uverbs_open_qp
[IB_USER_VERBS_CMD_OPEN_QP] = ib_uverbs_open_qp,
[IB_USER_VERBS_CMD_CREATE_FLOW] = ib_uverbs_create_flow,
[IB_USER_VERBS_CMD_DESTROY_FLOW] = ib_uverbs_destroy_flow
};
static void ib_uverbs_add_one(struct ib_device *device);
@ -212,6 +215,14 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
kfree(uobj);
}
list_for_each_entry_safe(uobj, tmp, &context->rule_list, list) {
struct ib_flow *flow_id = uobj->object;
idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
ib_destroy_flow(flow_id);
kfree(uobj);
}
list_for_each_entry_safe(uobj, tmp, &context->qp_list, list) {
struct ib_qp *qp = uobj->object;
struct ib_uqp_object *uqp =

View File

@ -954,6 +954,7 @@ struct ib_ucontext {
struct list_head srq_list;
struct list_head ah_list;
struct list_head xrcd_list;
struct list_head rule_list;
int closing;
};

View File

@ -86,7 +86,9 @@ enum {
IB_USER_VERBS_CMD_OPEN_XRCD,
IB_USER_VERBS_CMD_CLOSE_XRCD,
IB_USER_VERBS_CMD_CREATE_XSRQ,
IB_USER_VERBS_CMD_OPEN_QP
IB_USER_VERBS_CMD_OPEN_QP,
IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
IB_USER_VERBS_CMD_DESTROY_FLOW
};
/*
@ -694,6 +696,91 @@ struct ib_uverbs_detach_mcast {
__u64 driver_data[0];
};
struct ib_kern_eth_filter {
__u8 dst_mac[6];
__u8 src_mac[6];
__be16 ether_type;
__be16 vlan_tag;
};
struct ib_kern_spec_eth {
__u32 type;
__u16 size;
__u16 reserved;
struct ib_kern_eth_filter val;
struct ib_kern_eth_filter mask;
};
struct ib_kern_ipv4_filter {
__be32 src_ip;
__be32 dst_ip;
};
struct ib_kern_spec_ipv4 {
__u32 type;
__u16 size;
__u16 reserved;
struct ib_kern_ipv4_filter val;
struct ib_kern_ipv4_filter mask;
};
struct ib_kern_tcp_udp_filter {
__be16 dst_port;
__be16 src_port;
};
struct ib_kern_spec_tcp_udp {
__u32 type;
__u16 size;
__u16 reserved;
struct ib_kern_tcp_udp_filter val;
struct ib_kern_tcp_udp_filter mask;
};
struct ib_kern_spec {
union {
struct {
__u32 type;
__u16 size;
__u16 reserved;
};
struct ib_kern_spec_eth eth;
struct ib_kern_spec_ipv4 ipv4;
struct ib_kern_spec_tcp_udp tcp_udp;
};
};
struct ib_kern_flow_attr {
__u32 type;
__u16 size;
__u16 priority;
__u8 num_of_specs;
__u8 reserved[2];
__u8 port;
__u32 flags;
/* Following are the optional layers according to user request
* struct ib_flow_spec_xxx
* struct ib_flow_spec_yyy
*/
};
struct ib_uverbs_create_flow {
__u32 comp_mask;
__u64 response;
__u32 qp_handle;
struct ib_kern_flow_attr flow_attr;
};
struct ib_uverbs_create_flow_resp {
__u32 comp_mask;
__u32 flow_handle;
};
struct ib_uverbs_destroy_flow {
__u32 comp_mask;
__u32 flow_handle;
};
struct ib_uverbs_create_srq {
__u64 response;
__u64 user_handle;