From 24d44a391f1b5d56e9c7a4fc1edd085687864ff9 Mon Sep 17 00:00:00 2001
From: Steve Wise <swise@opengridcomputing.com>
Date: Thu, 4 Jul 2013 16:10:44 +0530
Subject: RDMA/cma: Add IPv6 support for iWARP

Modify the type of local_addr and remote_addr fields in struct
iw_cm_id from struct sockaddr_in to struct sockaddr_storage to hold
IPv6 and IPv4 addresses uniformly.

Change the references of local_addr and remote_addr in cxgb4, cxgb3,
nes and amso drivers to match this.  However to be able to actully run
traffic over IPv6, low-level drivers have to add code to support this.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>

[ Fix unused variable warnings when INFINIBAND_NES_DEBUG not set.
  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 include/rdma/iw_cm.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h
index 1a046b1595cc..1017e0bdf8ba 100644
--- a/include/rdma/iw_cm.h
+++ b/include/rdma/iw_cm.h
@@ -49,8 +49,8 @@ enum iw_cm_event_type {
 struct iw_cm_event {
 	enum iw_cm_event_type event;
 	int			 status;
-	struct sockaddr_in local_addr;
-	struct sockaddr_in remote_addr;
+	struct sockaddr_storage local_addr;
+	struct sockaddr_storage remote_addr;
 	void *private_data;
 	void *provider_data;
 	u8 private_data_len;
@@ -83,8 +83,8 @@ struct iw_cm_id {
 	iw_cm_handler		cm_handler;      /* client callback function */
 	void		        *context;	 /* client cb context */
 	struct ib_device	*device;
-	struct sockaddr_in      local_addr;
-	struct sockaddr_in	remote_addr;
+	struct sockaddr_storage local_addr;
+	struct sockaddr_storage	remote_addr;
 	void			*provider_data;	 /* provider private data */
 	iw_event_handler        event_handler;   /* cb for provider
 						    events */
-- 
cgit v1.2.3


From 73c40c616a33fcb7961b3c90a91b550813129b3e Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Thu, 1 Aug 2013 18:49:53 +0300
Subject: IB/core: Add locking around event dispatching on XRC target QPs

Fix a potential race when event occurrs on a target XRC QP and in the
middle of reporting that on its shared qps, one of them is destroyed
by user space application.  Also add note for kernel consumers in
ib_verbs.h that they must not destroy the QP from within the handler.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/verbs.c | 3 +++
 include/rdma/ib_verbs.h         | 6 ++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 22192deb8828..077fd641b300 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -346,10 +346,13 @@ EXPORT_SYMBOL(ib_destroy_srq);
 static void __ib_shared_qp_event_handler(struct ib_event *event, void *context)
 {
 	struct ib_qp *qp = context;
+	unsigned long flags;
 
+	spin_lock_irqsave(&qp->device->event_handler_lock, flags);
 	list_for_each_entry(event->element.qp, &qp->open_list, open_list)
 		if (event->element.qp->event_handler)
 			event->element.qp->event_handler(event, event->element.qp->qp_context);
+	spin_unlock_irqrestore(&qp->device->event_handler_lock, flags);
 }
 
 static void __ib_insert_xrcd_qp(struct ib_xrcd *xrcd, struct ib_qp *qp)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 645c3cedce9c..a84d3dfc4076 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -635,6 +635,12 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
 };
 
+
+/*
+ * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
+ * callback to destroy the passed in QP.
+ */
+
 struct ib_qp_init_attr {
 	void                  (*event_handler)(struct ib_event *, void *);
 	void		       *qp_context;
-- 
cgit v1.2.3


From 319a441d1361ea703b091caf92418f8121eadfc5 Mon Sep 17 00:00:00 2001
From: Hadar Hen Zion <hadarh@mellanox.com>
Date: Wed, 7 Aug 2013 14:01:59 +0300
Subject: IB/core: Add receive flow steering support

The RDMA stack allows for applications to create IB_QPT_RAW_PACKET
QPs, which receive plain Ethernet packets, specifically packets that
don't carry any QPN to be matched by the receiving side.  Applications
using these QPs must be provided with a method to program some
steering rule with the HW so packets arriving at the local port can be
routed to them.

This patch adds ib_create_flow(), which allow providing a flow
specification for a QP.  When there's a match between the
specification and a received packet, the packet is forwarded to that
QP, in a the same way one uses ib_attach_multicast() for IB UD
multicast handling.

Flow specifications are provided as instances of struct ib_flow_spec_yyy,
which describe L2, L3 and L4 headers.  Currently specs for Ethernet, IPv4,
TCP and UDP are defined.  Flow specs are made of values and masks.

The input to ib_create_flow() is a struct ib_flow_attr, which contains
a few mandatory control elements and optional flow specs.

    struct ib_flow_attr {
            enum ib_flow_attr_type type;
            u16      size;
            u16      priority;
            u32      flags;
            u8       num_of_specs;
            u8       port;
            /* Following are the optional layers according to user request
             * struct ib_flow_spec_yyy
             * struct ib_flow_spec_zzz
             */
    };

As these specs are eventually coming from user space, they are defined and
used in a way which allows adding new spec types without kernel/user ABI
change, just with a little API enhancement which defines the newly added spec.

The flow spec structures are defined with TLV (Type-Length-Value)
entries, which allows calling ib_create_flow() with a list of variable
length of optional specs.

For the actual processing of ib_flow_attr the driver uses the number
of specs and the size mandatory fields along with the TLV nature of
the specs.

Steering rules processing order is according to the domain over which
the rule is set and the rule priority.  All rules set by user space
applicatations fall into the IB_FLOW_DOMAIN_USER domain, other domains
could be used by future IPoIB RFS and Ethetool flow-steering interface
implementation.  Lower numerical value for the priority field means
higher priority.

The returned value from ib_create_flow() is a struct ib_flow, which
contains a database pointer (handle) provided by the HW driver to be
used when calling ib_destroy_flow().

Applications that offload TCP/IP traffic can also be written over IB
UD QPs.  The ib_create_flow() / ib_destroy_flow() API is designed to
support UD QPs too.  A HW driver can set IB_DEVICE_MANAGED_FLOW_STEERING
to denote support for flow steering.

The ib_flow_attr enum type supports usage of flow steering for promiscuous
and sniffer purposes:

    IB_FLOW_ATTR_NORMAL - "regular" rule, steering according to rule specification

    IB_FLOW_ATTR_ALL_DEFAULT - default unicast and multicast rule, receive
        all Ethernet traffic which isn't steered to any QP

    IB_FLOW_ATTR_MC_DEFAULT - same as IB_FLOW_ATTR_ALL_DEFAULT but only for multicast

    IB_FLOW_ATTR_SNIFFER - sniffer rule, receive all port traffic

ALL_DEFAULT and MC_DEFAULT rules options are valid only for Ethernet link type.

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>
---
 drivers/infiniband/core/verbs.c |  27 +++++++++
 include/rdma/ib_verbs.h         | 119 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 144 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 22192deb8828..87a8102c9dbe 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1254,3 +1254,30 @@ int ib_dealloc_xrcd(struct ib_xrcd *xrcd)
 	return xrcd->device->dealloc_xrcd(xrcd);
 }
 EXPORT_SYMBOL(ib_dealloc_xrcd);
+
+struct ib_flow *ib_create_flow(struct ib_qp *qp,
+			       struct ib_flow_attr *flow_attr,
+			       int domain)
+{
+	struct ib_flow *flow_id;
+	if (!qp->device->create_flow)
+		return ERR_PTR(-ENOSYS);
+
+	flow_id = qp->device->create_flow(qp, flow_attr, domain);
+	if (!IS_ERR(flow_id))
+		atomic_inc(&qp->usecnt);
+	return flow_id;
+}
+EXPORT_SYMBOL(ib_create_flow);
+
+int ib_destroy_flow(struct ib_flow *flow_id)
+{
+	int err;
+	struct ib_qp *qp = flow_id->qp;
+
+	err = qp->device->destroy_flow(flow_id);
+	if (!err)
+		atomic_dec(&qp->usecnt);
+	return err;
+}
+EXPORT_SYMBOL(ib_destroy_flow);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 645c3cedce9c..6f874b00491a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -116,7 +116,8 @@ enum ib_device_cap_flags {
 	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)
+	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<24),
+	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29)
 };
 
 enum ib_atomic_cap {
@@ -1033,7 +1034,8 @@ struct ib_qp {
 	struct ib_srq	       *srq;
 	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
 	struct list_head	xrcd_list;
-	atomic_t		usecnt; /* count times opened, mcast attaches */
+	/* count times opened, mcast attaches, flow attaches */
+	atomic_t		usecnt;
 	struct list_head	open_list;
 	struct ib_qp           *real_qp;
 	struct ib_uobject      *uobject;
@@ -1068,6 +1070,110 @@ struct ib_fmr {
 	u32			rkey;
 };
 
+/* Supported steering options */
+enum ib_flow_attr_type {
+	/* steering according to rule specifications */
+	IB_FLOW_ATTR_NORMAL		= 0x0,
+	/* default unicast and multicast rule -
+	 * receive all Eth traffic which isn't steered to any QP
+	 */
+	IB_FLOW_ATTR_ALL_DEFAULT	= 0x1,
+	/* default multicast rule -
+	 * receive all Eth multicast traffic which isn't steered to any QP
+	 */
+	IB_FLOW_ATTR_MC_DEFAULT		= 0x2,
+	/* sniffer rule - receive all port traffic */
+	IB_FLOW_ATTR_SNIFFER		= 0x3
+};
+
+/* Supported steering header types */
+enum ib_flow_spec_type {
+	/* L2 headers*/
+	IB_FLOW_SPEC_ETH	= 0x20,
+	/* L3 header*/
+	IB_FLOW_SPEC_IPV4	= 0x30,
+	/* L4 headers*/
+	IB_FLOW_SPEC_TCP	= 0x40,
+	IB_FLOW_SPEC_UDP	= 0x41
+};
+
+/* Flow steering rule priority is set according to it's domain.
+ * Lower domain value means higher priority.
+ */
+enum ib_flow_domain {
+	IB_FLOW_DOMAIN_USER,
+	IB_FLOW_DOMAIN_ETHTOOL,
+	IB_FLOW_DOMAIN_RFS,
+	IB_FLOW_DOMAIN_NIC,
+	IB_FLOW_DOMAIN_NUM /* Must be last */
+};
+
+struct ib_flow_eth_filter {
+	u8	dst_mac[6];
+	u8	src_mac[6];
+	__be16	ether_type;
+	__be16	vlan_tag;
+};
+
+struct ib_flow_spec_eth {
+	enum ib_flow_spec_type	  type;
+	u16			  size;
+	struct ib_flow_eth_filter val;
+	struct ib_flow_eth_filter mask;
+};
+
+struct ib_flow_ipv4_filter {
+	__be32	src_ip;
+	__be32	dst_ip;
+};
+
+struct ib_flow_spec_ipv4 {
+	enum ib_flow_spec_type	   type;
+	u16			   size;
+	struct ib_flow_ipv4_filter val;
+	struct ib_flow_ipv4_filter mask;
+};
+
+struct ib_flow_tcp_udp_filter {
+	__be16	dst_port;
+	__be16	src_port;
+};
+
+struct ib_flow_spec_tcp_udp {
+	enum ib_flow_spec_type	      type;
+	u16			      size;
+	struct ib_flow_tcp_udp_filter val;
+	struct ib_flow_tcp_udp_filter mask;
+};
+
+union ib_flow_spec {
+	struct {
+		enum ib_flow_spec_type	type;
+		u16			size;
+	};
+	struct ib_flow_spec_eth		eth;
+	struct ib_flow_spec_ipv4        ipv4;
+	struct ib_flow_spec_tcp_udp	tcp_udp;
+};
+
+struct ib_flow_attr {
+	enum ib_flow_attr_type type;
+	u16	     size;
+	u16	     priority;
+	u32	     flags;
+	u8	     num_of_specs;
+	u8	     port;
+	/* Following are the optional layers according to user request
+	 * struct ib_flow_spec_xxx
+	 * struct ib_flow_spec_yyy
+	 */
+};
+
+struct ib_flow {
+	struct ib_qp		*qp;
+	struct ib_uobject	*uobject;
+};
+
 struct ib_mad;
 struct ib_grh;
 
@@ -1300,6 +1406,11 @@ struct ib_device {
 						 struct ib_ucontext *ucontext,
 						 struct ib_udata *udata);
 	int			   (*dealloc_xrcd)(struct ib_xrcd *xrcd);
+	struct ib_flow *	   (*create_flow)(struct ib_qp *qp,
+						  struct ib_flow_attr
+						  *flow_attr,
+						  int domain);
+	int			   (*destroy_flow)(struct ib_flow *flow_id);
 
 	struct ib_dma_mapping_ops   *dma_ops;
 
@@ -2260,4 +2371,8 @@ struct ib_xrcd *ib_alloc_xrcd(struct ib_device *device);
  */
 int ib_dealloc_xrcd(struct ib_xrcd *xrcd);
 
+struct ib_flow *ib_create_flow(struct ib_qp *qp,
+			       struct ib_flow_attr *flow_attr, int domain);
+int ib_destroy_flow(struct ib_flow *flow_id);
+
 #endif /* IB_VERBS_H */
-- 
cgit v1.2.3


From 400dbc96583ff3b8ad4c09bd7e9dcd35a6215922 Mon Sep 17 00:00:00 2001
From: Igor Ivanov <Igor.Ivanov@itseez.com>
Date: Wed, 14 Aug 2013 13:58:29 +0300
Subject: IB/core: Infrastructure for extensible uverbs commands

Add infrastructure to support extended uverbs capabilities in a
forward/backward manner.  Uverbs command opcodes which are based on
the verbs extensions approach should be greater or equal to
IB_USER_VERBS_CMD_THRESHOLD.  They have new header format and
processed a bit differently.

Whenever a specific IB_USER_VERBS_CMD_XXX is extended, which practically means
it needs to have additional arguments, we will be able to add them without creating
a completely new IB_USER_VERBS_CMD_YYY command or bumping the uverbs ABI version.

This patch for itself doesn't provide the whole scheme which is also dependent
on adding a comp_mask field to each extended uverbs command struct.

The new header framework allows for future extension of the CMD arguments
(ib_uverbs_cmd_hdr.in_words, ib_uverbs_cmd_hdr.out_words) for an existing
new command (that is a command that supports the new uverbs command header format
suggested in this patch) w/o bumping ABI version and with maintaining backward
and formward compatibility to new and old libibverbs versions.

In the uverbs command we are passing both uverbs arguments and the provider arguments.
We split the ib_uverbs_cmd_hdr.in_words to ib_uverbs_cmd_hdr.in_words which will now carry only
uverbs input argument struct size and  ib_uverbs_cmd_hdr.provider_in_words that will carry
the provider input argument size. Same goes for the response (the uverbs CMD output argument).

For example take the create_cq call and the mlx4_ib provider:

The uverbs layer gets libibverb's struct ibv_create_cq (named struct ib_uverbs_create_cq
in the kernel), mlx4_ib gets libmlx4's struct mlx4_create_cq (which includes struct
ibv_create_cq and is named struct mlx4_ib_create_cq in the kernel) and
in_words = sizeof(mlx4_create_cq)/4 .

Thus ib_uverbs_cmd_hdr.in_words carry both uverbs plus mlx4_ib input argument sizes,
where uverbs assumes it knows the size of its input argument - struct ibv_create_cq.

Now, if we wish to add a variable to struct ibv_create_cq, we can add a comp_mask field
to the struct which is basically bit field indicating which fields exists in the struct
(as done for the libibverbs API extension), but we need a way to tell what is the total
size of the struct and not assume the struct size is predefined (since we may get different
struct sizes from different user libibverbs versions). So we know at which point the
provider input argument (struct mlx4_create_cq) begins. Same goes for extending the
provider struct mlx4_create_cq. Thus we split the ib_uverbs_cmd_hdr.in_words to
ib_uverbs_cmd_hdr.in_words which will now carry only uverbs input argument struct size and
ib_uverbs_cmd_hdr.provider_in_words that will carry the provider (mlx4_ib) input argument size.

Signed-off-by: Igor Ivanov <Igor.Ivanov@itseez.com>
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>
---
 drivers/infiniband/core/uverbs_main.c | 29 ++++++++++++++++++++++++-----
 include/uapi/rdma/ib_user_verbs.h     | 10 ++++++++++
 2 files changed, 34 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 2c6f0f2ecd9d..e4e7b2449d19 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -583,9 +583,6 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(&hdr, buf, sizeof hdr))
 		return -EFAULT;
 
-	if (hdr.in_words * 4 != count)
-		return -EINVAL;
-
 	if (hdr.command >= ARRAY_SIZE(uverbs_cmd_table) ||
 	    !uverbs_cmd_table[hdr.command])
 		return -EINVAL;
@@ -597,8 +594,30 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 	if (!(file->device->ib_dev->uverbs_cmd_mask & (1ull << hdr.command)))
 		return -ENOSYS;
 
-	return uverbs_cmd_table[hdr.command](file, buf + sizeof hdr,
-					     hdr.in_words * 4, hdr.out_words * 4);
+	if (hdr.command >= IB_USER_VERBS_CMD_THRESHOLD) {
+		struct ib_uverbs_cmd_hdr_ex hdr_ex;
+
+		if (copy_from_user(&hdr_ex, buf, sizeof(hdr_ex)))
+			return -EFAULT;
+
+		if (((hdr_ex.in_words + hdr_ex.provider_in_words) * 4) != count)
+			return -EINVAL;
+
+		return uverbs_cmd_table[hdr.command](file,
+						     buf + sizeof(hdr_ex),
+						     (hdr_ex.in_words +
+						      hdr_ex.provider_in_words) * 4,
+						     (hdr_ex.out_words +
+						      hdr_ex.provider_out_words) * 4);
+	} else {
+		if (hdr.in_words * 4 != count)
+			return -EINVAL;
+
+		return uverbs_cmd_table[hdr.command](file,
+						     buf + sizeof(hdr),
+						     hdr.in_words * 4,
+						     hdr.out_words * 4);
+	}
 }
 
 static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 805711ea2005..61535aa0a62e 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -43,6 +43,7 @@
  * compatibility are made.
  */
 #define IB_USER_VERBS_ABI_VERSION	6
+#define IB_USER_VERBS_CMD_THRESHOLD    50
 
 enum {
 	IB_USER_VERBS_CMD_GET_CONTEXT,
@@ -123,6 +124,15 @@ struct ib_uverbs_cmd_hdr {
 	__u16 out_words;
 };
 
+struct ib_uverbs_cmd_hdr_ex {
+	__u32 command;
+	__u16 in_words;
+	__u16 out_words;
+	__u16 provider_in_words;
+	__u16 provider_out_words;
+	__u32 cmd_hdr_reserved;
+};
+
 struct ib_uverbs_get_context {
 	__u64 response;
 	__u64 driver_data[0];
-- 
cgit v1.2.3


From 436f2ad05a0b65b1467ddf51bc68171c381bf844 Mon Sep 17 00:00:00 2001
From: Hadar Hen Zion <hadarh@mellanox.com>
Date: Wed, 14 Aug 2013 13:58:30 +0300
Subject: 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>
---
 drivers/infiniband/core/uverbs.h      |   3 +
 drivers/infiniband/core/uverbs_cmd.c  | 214 ++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/uverbs_main.c |  13 ++-
 include/rdma/ib_verbs.h               |   1 +
 include/uapi/rdma/ib_user_verbs.h     |  89 +++++++++++++-
 5 files changed, 318 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 0fcd7aa26fa2..ad9d1028102d 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -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 */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index b3c07b0c9f26..6e98df929e29 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -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)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index e4e7b2449d19..75ad86c4abf8 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -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 =
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6f874b00491a..274205d4df97 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -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;
 };
 
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 61535aa0a62e..0b233c56b0e4 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -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;
-- 
cgit v1.2.3


From f77c0162a339400ad16f657603fdc3bf11654fd3 Mon Sep 17 00:00:00 2001
From: Hadar Hen Zion <hadarh@mellanox.com>
Date: Wed, 14 Aug 2013 13:58:31 +0300
Subject: IB/mlx4: Add receive flow steering support

Implement ib_create_flow() and ib_destroy_flow().

Translate the verbs structures provided by the user to HW structures
and call the MLX4_QP_FLOW_STEERING_ATTACH/DETACH firmware commands.

On the ATTACH command completion, the firmware provides a 64-bit
registration ID, which is placed into struct mlx4_ib_flow that wraps
the instance of struct ib_flow which is retuned to caller.  Later,
this reg ID is used for detaching that flow from the firmware.

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>
---
 drivers/infiniband/hw/mlx4/main.c    | 235 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx4/mlx4_ib.h |  12 ++
 include/linux/mlx4/device.h          |   5 -
 3 files changed, 247 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index a188d3178559..d6c5a73becf4 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -54,6 +54,8 @@
 #define DRV_VERSION	"1.0"
 #define DRV_RELDATE	"April 4, 2008"
 
+#define MLX4_IB_FLOW_MAX_PRIO 0xFFF
+
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -88,6 +90,25 @@ static void init_query_mad(struct ib_smp *mad)
 
 static union ib_gid zgid;
 
+static int check_flow_steering_support(struct mlx4_dev *dev)
+{
+	int ib_num_ports = 0;
+	int i;
+
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+		ib_num_ports++;
+
+	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		if (ib_num_ports || mlx4_is_mfunc(dev)) {
+			pr_warn("Device managed flow steering is unavailable "
+				"for IB ports or in multifunction env.\n");
+			return 0;
+		}
+		return 1;
+	}
+	return 0;
+}
+
 static int mlx4_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props)
 {
@@ -144,6 +165,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
+	if (check_flow_steering_support(dev->dev))
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
 
 	props->vendor_id	   = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
@@ -798,6 +821,209 @@ struct mlx4_ib_steering {
 	union ib_gid gid;
 };
 
+static int parse_flow_attr(struct mlx4_dev *dev,
+			   union ib_flow_spec *ib_spec,
+			   struct _rule_hw *mlx4_spec)
+{
+	enum mlx4_net_trans_rule_id type;
+
+	switch (ib_spec->type) {
+	case IB_FLOW_SPEC_ETH:
+		type = MLX4_NET_TRANS_RULE_ID_ETH;
+		memcpy(mlx4_spec->eth.dst_mac, ib_spec->eth.val.dst_mac,
+		       ETH_ALEN);
+		memcpy(mlx4_spec->eth.dst_mac_msk, ib_spec->eth.mask.dst_mac,
+		       ETH_ALEN);
+		mlx4_spec->eth.vlan_tag = ib_spec->eth.val.vlan_tag;
+		mlx4_spec->eth.vlan_tag_msk = ib_spec->eth.mask.vlan_tag;
+		break;
+
+	case IB_FLOW_SPEC_IPV4:
+		type = MLX4_NET_TRANS_RULE_ID_IPV4;
+		mlx4_spec->ipv4.src_ip = ib_spec->ipv4.val.src_ip;
+		mlx4_spec->ipv4.src_ip_msk = ib_spec->ipv4.mask.src_ip;
+		mlx4_spec->ipv4.dst_ip = ib_spec->ipv4.val.dst_ip;
+		mlx4_spec->ipv4.dst_ip_msk = ib_spec->ipv4.mask.dst_ip;
+		break;
+
+	case IB_FLOW_SPEC_TCP:
+	case IB_FLOW_SPEC_UDP:
+		type = ib_spec->type == IB_FLOW_SPEC_TCP ?
+					MLX4_NET_TRANS_RULE_ID_TCP :
+					MLX4_NET_TRANS_RULE_ID_UDP;
+		mlx4_spec->tcp_udp.dst_port = ib_spec->tcp_udp.val.dst_port;
+		mlx4_spec->tcp_udp.dst_port_msk = ib_spec->tcp_udp.mask.dst_port;
+		mlx4_spec->tcp_udp.src_port = ib_spec->tcp_udp.val.src_port;
+		mlx4_spec->tcp_udp.src_port_msk = ib_spec->tcp_udp.mask.src_port;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (mlx4_map_sw_to_hw_steering_id(dev, type) < 0 ||
+	    mlx4_hw_rule_sz(dev, type) < 0)
+		return -EINVAL;
+	mlx4_spec->id = cpu_to_be16(mlx4_map_sw_to_hw_steering_id(dev, type));
+	mlx4_spec->size = mlx4_hw_rule_sz(dev, type) >> 2;
+	return mlx4_hw_rule_sz(dev, type);
+}
+
+static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr,
+			  int domain,
+			  enum mlx4_net_trans_promisc_mode flow_type,
+			  u64 *reg_id)
+{
+	int ret, i;
+	int size = 0;
+	void *ib_flow;
+	struct mlx4_ib_dev *mdev = to_mdev(qp->device);
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
+	size_t rule_size = sizeof(struct mlx4_net_trans_rule_hw_ctrl) +
+			   (sizeof(struct _rule_hw) * flow_attr->num_of_specs);
+
+	static const u16 __mlx4_domain[] = {
+		[IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
+		[IB_FLOW_DOMAIN_ETHTOOL] = MLX4_DOMAIN_ETHTOOL,
+		[IB_FLOW_DOMAIN_RFS] = MLX4_DOMAIN_RFS,
+		[IB_FLOW_DOMAIN_NIC] = MLX4_DOMAIN_NIC,
+	};
+
+	if (flow_attr->priority > MLX4_IB_FLOW_MAX_PRIO) {
+		pr_err("Invalid priority value %d\n", flow_attr->priority);
+		return -EINVAL;
+	}
+
+	if (domain >= IB_FLOW_DOMAIN_NUM) {
+		pr_err("Invalid domain value %d\n", domain);
+		return -EINVAL;
+	}
+
+	if (mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type) < 0)
+		return -EINVAL;
+
+	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	memset(mailbox->buf, 0, rule_size);
+	ctrl = mailbox->buf;
+
+	ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
+				 flow_attr->priority);
+	ctrl->type = mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type);
+	ctrl->port = flow_attr->port;
+	ctrl->qpn = cpu_to_be32(qp->qp_num);
+
+	ib_flow = flow_attr + 1;
+	size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
+	for (i = 0; i < flow_attr->num_of_specs; i++) {
+		ret = parse_flow_attr(mdev->dev, ib_flow, mailbox->buf + size);
+		if (ret < 0) {
+			mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+			return -EINVAL;
+		}
+		ib_flow += ((union ib_flow_spec *) ib_flow)->size;
+		size += ret;
+	}
+
+	ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0,
+			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
+			   MLX4_CMD_NATIVE);
+	if (ret == -ENOMEM)
+		pr_err("mcg table is full. Fail to register network rule.\n");
+	else if (ret == -ENXIO)
+		pr_err("Device managed flow steering is disabled. Fail to register network rule.\n");
+	else if (ret)
+		pr_err("Invalid argumant. Fail to register network rule.\n");
+
+	mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+	return ret;
+}
+
+static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id)
+{
+	int err;
+	err = mlx4_cmd(dev, reg_id, 0, 0,
+		       MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
+		       MLX4_CMD_NATIVE);
+	if (err)
+		pr_err("Fail to detach network rule. registration id = 0x%llx\n",
+		       reg_id);
+	return err;
+}
+
+static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
+				    struct ib_flow_attr *flow_attr,
+				    int domain)
+{
+	int err = 0, i = 0;
+	struct mlx4_ib_flow *mflow;
+	enum mlx4_net_trans_promisc_mode type[2];
+
+	memset(type, 0, sizeof(type));
+
+	mflow = kzalloc(sizeof(*mflow), GFP_KERNEL);
+	if (!mflow) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	switch (flow_attr->type) {
+	case IB_FLOW_ATTR_NORMAL:
+		type[0] = MLX4_FS_REGULAR;
+		break;
+
+	case IB_FLOW_ATTR_ALL_DEFAULT:
+		type[0] = MLX4_FS_ALL_DEFAULT;
+		break;
+
+	case IB_FLOW_ATTR_MC_DEFAULT:
+		type[0] = MLX4_FS_MC_DEFAULT;
+		break;
+
+	case IB_FLOW_ATTR_SNIFFER:
+		type[0] = MLX4_FS_UC_SNIFFER;
+		type[1] = MLX4_FS_MC_SNIFFER;
+		break;
+
+	default:
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	while (i < ARRAY_SIZE(type) && type[i]) {
+		err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i],
+					    &mflow->reg_id[i]);
+		if (err)
+			goto err_free;
+		i++;
+	}
+
+	return &mflow->ibflow;
+
+err_free:
+	kfree(mflow);
+	return ERR_PTR(err);
+}
+
+static int mlx4_ib_destroy_flow(struct ib_flow *flow_id)
+{
+	int err, ret = 0;
+	int i = 0;
+	struct mlx4_ib_dev *mdev = to_mdev(flow_id->qp->device);
+	struct mlx4_ib_flow *mflow = to_mflow(flow_id);
+
+	while (i < ARRAY_SIZE(mflow->reg_id) && mflow->reg_id[i]) {
+		err = __mlx4_ib_destroy_flow(mdev->dev, mflow->reg_id[i]);
+		if (err)
+			ret = err;
+		i++;
+	}
+
+	kfree(mflow);
+	return ret;
+}
+
 static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	int err;
@@ -1461,6 +1687,15 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
 	}
 
+	if (check_flow_steering_support(dev)) {
+		ibdev->ib_dev.create_flow	= mlx4_ib_create_flow;
+		ibdev->ib_dev.destroy_flow	= mlx4_ib_destroy_flow;
+
+		ibdev->ib_dev.uverbs_cmd_mask	|=
+			(1ull << IB_USER_VERBS_CMD_CREATE_FLOW) |
+			(1ull << IB_USER_VERBS_CMD_DESTROY_FLOW);
+	}
+
 	mlx4_ib_alloc_eqs(dev, ibdev);
 
 	spin_lock_init(&iboe->lock);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index f61ec26500c4..036b663dd26e 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -132,6 +132,12 @@ struct mlx4_ib_fmr {
 	struct mlx4_fmr         mfmr;
 };
 
+struct mlx4_ib_flow {
+	struct ib_flow ibflow;
+	/* translating DMFS verbs sniffer rule to FW API requires two reg IDs */
+	u64 reg_id[2];
+};
+
 struct mlx4_ib_wq {
 	u64		       *wrid;
 	spinlock_t		lock;
@@ -552,6 +558,12 @@ static inline struct mlx4_ib_fmr *to_mfmr(struct ib_fmr *ibfmr)
 {
 	return container_of(ibfmr, struct mlx4_ib_fmr, ibfmr);
 }
+
+static inline struct mlx4_ib_flow *to_mflow(struct ib_flow *ibflow)
+{
+	return container_of(ibflow, struct mlx4_ib_flow, ibflow);
+}
+
 static inline struct mlx4_ib_qp *to_mqp(struct ib_qp *ibqp)
 {
 	return container_of(ibqp, struct mlx4_ib_qp, ibqp);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 52c23a892bab..d73423c37c25 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1052,11 +1052,6 @@ struct _rule_hw {
 	};
 };
 
-/* translating DMFS verbs sniffer rule to the FW API would need two reg IDs */
-struct mlx4_flow_handle {
-	u64 reg_id[2];
-};
-
 int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn,
 				enum mlx4_net_trans_promisc_mode mode);
 int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
-- 
cgit v1.2.3


From 22878dbc9173a7f0322dd697b1b5b49a83a1d4d5 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Sun, 1 Sep 2013 18:39:52 +0300
Subject: IB/core: Better checking of userspace values for receive flow
 steering

  - Don't allow unsupported comp_mask values, user should check
    ibv_query_device to know which features are supported.
  - Add a check in ib_uverbs_create_flow() to verify the size passed
    from the user space.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 16 +++++++++++++++-
 include/rdma/ib_verbs.h              |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 6e98df929e29..9112410da11d 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2652,17 +2652,31 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof(cmd)))
 		return -EFAULT;
 
+	if (cmd.comp_mask)
+		return -EINVAL;
+
 	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 < 0 ||
+	    cmd.flow_attr.num_of_specs > IB_FLOW_SPEC_SUPPORT_LAYERS)
+		return -EINVAL;
+
+	kern_attr_size = cmd.flow_attr.size - sizeof(cmd) -
+			 sizeof(struct ib_uverbs_cmd_hdr_ex);
+
+	if (cmd.flow_attr.size < 0 || cmd.flow_attr.size > in_len ||
+	    kern_attr_size < 0 || kern_attr_size >
+	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_kern_spec)))
+		return -EINVAL;
+
 	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;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 274205d4df97..bd151eac1e61 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1098,6 +1098,8 @@ enum ib_flow_spec_type {
 	IB_FLOW_SPEC_UDP	= 0x41
 };
 
+#define IB_FLOW_SPEC_SUPPORT_LAYERS 4
+
 /* Flow steering rule priority is set according to it's domain.
  * Lower domain value means higher priority.
  */
-- 
cgit v1.2.3