Merge tag 'rdma-next-2017-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma into rdma-netlink

RDMA netlink infrastructure v2

Signed-off-by: Doug Ledford <dledford@redhat.com>

6 files changed, 159 insertions, 23 deletions

diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index b73a14edc85e..7aca12188ef3 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -304,7 +304,13 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
 
 static inline int rdma_is_multicast_addr(struct in6_addr *addr)
 {
-	return addr->s6_addr[0] == 0xff;
+	u32 ipv4_addr;
+
+	if (addr->s6_addr[0] == 0xff)
+		return 1;
+
+	memcpy(&ipv4_addr, addr->s6_addr + 12, 4);
+	return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr));
 }
 
 static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h
index 5519f31f043a..c124d515f7d5 100644
--- a/include/rdma/ib_hdrs.h
+++ b/include/rdma/ib_hdrs.h
@@ -193,8 +193,12 @@ static inline void put_ib_ateth_compare(u64 val, struct ib_atomic_eth *ateth)
 #define IB_LNH_MASK		3
 #define IB_SC_MASK		0xf
 #define IB_SC_SHIFT		12
+#define IB_SC5_MASK		0x10
 #define IB_SL_MASK		0xf
 #define IB_SL_SHIFT		4
+#define IB_SL_SHIFT		4
+#define IB_LVER_MASK	0xf
+#define IB_LVER_SHIFT	8
 
 static inline u8 ib_get_lnh(struct ib_header *hdr)
 {
@@ -206,6 +210,11 @@ static inline u8 ib_get_sc(struct ib_header *hdr)
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SC_SHIFT) & IB_SC_MASK);
 }
 
+static inline bool ib_is_sc5(u16 sc5)
+{
+	return !!(sc5 & IB_SC5_MASK);
+}
+
 static inline u8 ib_get_sl(struct ib_header *hdr)
 {
 	return ((be16_to_cpu(hdr->lrh[0]) >> IB_SL_SHIFT) & IB_SL_MASK);
@@ -221,6 +230,27 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 	return (be16_to_cpu(hdr->lrh[3]));
 }
 
+static inline u8 ib_get_lver(struct ib_header *hdr)
+{
+	return (u8)((be16_to_cpu(hdr->lrh[0]) >> IB_LVER_SHIFT) &
+		   IB_LVER_MASK);
+}
+
+static inline u16 ib_get_len(struct ib_header *hdr)
+{
+	return (u16)(be16_to_cpu(hdr->lrh[2]));
+}
+
+static inline u32 ib_get_qkey(struct ib_other_headers *ohdr)
+{
+	return be32_to_cpu(ohdr->u.ud.deth[0]);
+}
+
+static inline u32 ib_get_sqpn(struct ib_other_headers *ohdr)
+{
+	return ((be32_to_cpu(ohdr->u.ud.deth[1])) & IB_QPN_MASK);
+}
+
 /*
  * BTH
  */
@@ -229,6 +259,14 @@ static inline u16 ib_get_slid(struct ib_header *hdr)
 #define IB_BTH_PAD_MASK	3
 #define IB_BTH_PKEY_MASK	0xffff
 #define IB_BTH_PAD_SHIFT	20
+#define IB_BTH_A_MASK		1
+#define IB_BTH_A_SHIFT		31
+#define IB_BTH_M_MASK		1
+#define IB_BTH_M_SHIFT		22
+#define IB_BTH_SE_MASK		1
+#define IB_BTH_SE_SHIFT	23
+#define IB_BTH_TVER_MASK	0xf
+#define IB_BTH_TVER_SHIFT	16
 
 static inline u8 ib_bth_get_pad(struct ib_other_headers *ohdr)
 {
@@ -247,4 +285,50 @@ static inline u8 ib_bth_get_opcode(struct ib_other_headers *ohdr)
 		   IB_BTH_OPCODE_MASK);
 }
 
+static inline u8 ib_bth_get_ackreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[2]) >> IB_BTH_A_SHIFT) &
+		   IB_BTH_A_MASK);
+}
+
+static inline u8 ib_bth_get_migreq(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_M_SHIFT) &
+		    IB_BTH_M_MASK);
+}
+
+static inline u8 ib_bth_get_se(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_SE_SHIFT) &
+		    IB_BTH_SE_MASK);
+}
+
+static inline u32 ib_bth_get_psn(struct ib_other_headers *ohdr)
+{
+	return (u32)(be32_to_cpu(ohdr->bth[2]));
+}
+
+static inline u32 ib_bth_get_qpn(struct ib_other_headers *ohdr)
+{
+	return (u32)((be32_to_cpu(ohdr->bth[1])) & IB_QPN_MASK);
+}
+
+static inline u8 ib_bth_get_becn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
+		     IB_BECN_MASK);
+}
+
+static inline u8 ib_bth_get_fecn(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
+		    IB_FECN_MASK);
+}
+
+static inline u8 ib_bth_get_tver(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_TVER_SHIFT)  &
+		    IB_BTH_TVER_MASK);
+}
+
 #endif                          /* IB_HDRS_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b5732432bb29..e0e87a1f66fb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 
+#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
+
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 
@@ -577,7 +579,8 @@ struct ib_device_modify {
 enum ib_port_modify_flags {
 	IB_PORT_SHUTDOWN		= 1,
 	IB_PORT_INIT_TYPE		= (1<<2),
-	IB_PORT_RESET_QKEY_CNTR		= (1<<3)
+	IB_PORT_RESET_QKEY_CNTR		= (1<<3),
+	IB_PORT_OPA_MASK_CHG		= (1<<4)
 };
 
 struct ib_port_modify {
@@ -664,6 +667,8 @@ union rdma_network_hdr {
 	};
 };
 
+#define IB_QPN_MASK		0xFFFFFF
+
 enum {
 	IB_MULTICAST_QPN = 0xffffff
 };
@@ -1059,6 +1064,7 @@ enum ib_qp_create_flags {
 	/* FREE					= 1 << 7, */
 	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
+	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1086,6 +1092,7 @@ struct ib_qp_init_attr {
 	 */
 	u8			port_num;
 	struct ib_rwq_ind_table *rwq_ind_tbl;
+	u32			source_qpn;
 };
 
 struct ib_qp_open_attr {
@@ -1546,6 +1553,10 @@ enum ib_raw_packet_caps {
 	IB_RAW_PACKET_CAP_SCATTER_FCS		= (1 << 1),
 	/* Checksum offloads are supported (for both send and receive). */
 	IB_RAW_PACKET_CAP_IP_CSUM		= (1 << 2),
+	/* When a packet is received for an RQ with no receive WQEs, the
+	 * packet processing is delayed.
+	 */
+	IB_RAW_PACKET_CAP_DELAY_DROP		= (1 << 3),
 };
 
 enum ib_wq_type {
@@ -1574,6 +1585,7 @@ struct ib_wq {
 enum ib_wq_flags {
 	IB_WQ_FLAGS_CVLAN_STRIPPING	= 1 << 0,
 	IB_WQ_FLAGS_SCATTER_FCS		= 1 << 1,
+	IB_WQ_FLAGS_DELAY_DROP		= 1 << 2,
 };
 
 struct ib_wq_init_attr {
@@ -2288,6 +2300,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this
@@ -2295,7 +2309,7 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
-	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	void (*get_dev_fw_str)(struct ib_device *, char *str);
 };
 
 struct ib_client {
@@ -2331,7 +2345,7 @@ struct ib_client {
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
-void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+void ib_get_device_fw_str(struct ib_device *device, char *str);
 
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
@@ -3555,6 +3569,7 @@ void ib_drain_qp(struct ib_qp *qp);
 
 int ib_resolve_eth_dmac(struct ib_device *device,
 			struct rdma_ah_attr *ah_attr);
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
 
 static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
 {
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 348c102cb5f6..e25bf1988846 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -5,29 +5,31 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
-	struct module *module;
+	u8 flags;
+};
+
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
 /**
- * Add a a client to the list of IB netlink exporters.
+ * Register client in RDMA netlink.
  * @index: Index of the added client
- * @nops: Number of supported ops by the added client.
  * @cb_table: A table for op->callback
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[]);
+void rdma_nl_register(unsigned int index,
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
  * @index: Index of the removed IB client.
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_remove_client(int index);
+void rdma_nl_unregister(unsigned int index);
 
 /**
  * Put a new message in a supplied skb.
@@ -56,22 +58,32 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
+
+/**
+ * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int rdma_nl_chk_listeners(unsigned int group);
 #endif /* _RDMA_NETLINK_H */
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 55af69271053..fdfac0fd2f82 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -57,11 +57,21 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_mad.h>
 #include <rdma/rdmavt_mr.h>
 #include <rdma/rdmavt_qp.h>
 
 #define RVT_MAX_PKEY_VALUES 16
 
+#define RVT_MAX_TRAP_LEN 100 /* Limit pending trap list */
+#define RVT_MAX_TRAP_LISTS ((IB_NOTICE_TYPE_INFO & 0x0F) + 1)
+#define RVT_TRAP_TIMEOUT 4096 /* 4.096 usec */
+
+struct trap_list {
+	u32 list_len;
+	struct list_head list;
+};
+
 struct rvt_ibport {
 	struct rvt_qp __rcu *qp[2];
 	struct ib_mad_agent *send_agent;	/* agent for SMI (traps) */
@@ -75,6 +85,7 @@ struct rvt_ibport {
 	__be64 mkey;
 	u64 tid;
 	u32 port_cap_flags;
+	u16 port_cap3_flags;
 	u32 pma_sample_start;
 	u32 pma_sample_interval;
 	__be16 pma_counter_select[5];
@@ -127,6 +138,13 @@ struct rvt_ibport {
 	u16 *pkey_table;
 
 	struct rvt_ah *sm_ah;
+
+	/*
+	 * Keep a list of traps that have not been repressed.  They will be
+	 * resent based on trap_timer.
+	 */
+	struct trap_list trap_lists[RVT_MAX_TRAP_LISTS];
+	struct timer_list trap_timer;
 };
 
 #define RVT_CQN_MAX 16 /* maximum length of cq name */
@@ -514,7 +532,8 @@ int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey);
 int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc);
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc);
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc);
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid,
 				 u16 lid);
 
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index d664d2e76280..07e2fffa6de6 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -396,7 +396,7 @@ struct rvt_srq {
 #define RVT_QPNMAP_ENTRIES          (RVT_QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE           (PAGE_SIZE * BITS_PER_BYTE)
 #define RVT_BITS_PER_PAGE_MASK      (RVT_BITS_PER_PAGE - 1)
-#define RVT_QPN_MASK		    0xFFFFFF
+#define RVT_QPN_MASK		    IB_QPN_MASK
 
 /*
  * QPN-map pages start out as NULL, they get allocated upon