diff options
79 files changed, 18130 insertions, 611 deletions
diff --git a/Documentation/ABI/stable/sysfs-driver-ib_srp b/Documentation/ABI/stable/sysfs-driver-ib_srp index 481aae95c7d..5c53d28f775 100644 --- a/Documentation/ABI/stable/sysfs-driver-ib_srp +++ b/Documentation/ABI/stable/sysfs-driver-ib_srp @@ -54,6 +54,13 @@ Description: Interface for making ib_srp connect to a new target. ib_srp. Specifying a value that exceeds cmd_sg_entries is only safe with partial memory descriptor list support enabled (allow_ext_sg=1). + * comp_vector, a number in the range 0..n-1 specifying the + MSI-X completion vector. Some HCA's allocate multiple (n) + MSI-X vectors per HCA port. If the IRQ affinity masks of + these interrupts have been configured such that each MSI-X + interrupt is handled by a different CPU then the comp_vector + parameter can be used to spread the SRP completion workload + over multiple CPU's. What: /sys/class/infiniband_srp/srp-<hca>-<port_number>/ibdev Date: January 2, 2006 diff --git a/MAINTAINERS b/MAINTAINERS index 60d6a339350..b4265364ed2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5365,6 +5365,28 @@ W: http://linuxtv.org S: Odd Fixes F: drivers/media/radio/radio-miropcm20* +Mellanox MLX5 core VPI driver +M: Eli Cohen <eli@mellanox.com> +L: netdev@vger.kernel.org +L: linux-rdma@vger.kernel.org +W: http://www.mellanox.com +Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: http://patchwork.kernel.org/project/linux-rdma/list/ +T: git://openfabrics.org/~eli/connect-ib.git +S: Supported +F: drivers/net/ethernet/mellanox/mlx5/core/ +F: include/linux/mlx5/ + +Mellanox MLX5 IB driver +M: Eli Cohen <eli@mellanox.com> +L: linux-rdma@vger.kernel.org +W: http://www.mellanox.com +Q: http://patchwork.kernel.org/project/linux-rdma/list/ +T: git://openfabrics.org/~eli/connect-ib.git +S: Supported +F: include/linux/mlx5/ +F: drivers/infiniband/hw/mlx5/ + MODULE SUPPORT M: Rusty Russell <rusty@rustcorp.com.au> S: Maintained diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index c85b56c2809..5ceda710f51 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -50,6 +50,7 @@ source "drivers/infiniband/hw/amso1100/Kconfig" source "drivers/infiniband/hw/cxgb3/Kconfig" source "drivers/infiniband/hw/cxgb4/Kconfig" source "drivers/infiniband/hw/mlx4/Kconfig" +source "drivers/infiniband/hw/mlx5/Kconfig" source "drivers/infiniband/hw/nes/Kconfig" source "drivers/infiniband/hw/ocrdma/Kconfig" diff --git a/drivers/infiniband/Makefile b/drivers/infiniband/Makefile index b126fefe0b1..1fe69888515 100644 --- a/drivers/infiniband/Makefile +++ b/drivers/infiniband/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_INFINIBAND_AMSO1100) += hw/amso1100/ obj-$(CONFIG_INFINIBAND_CXGB3) += hw/cxgb3/ obj-$(CONFIG_INFINIBAND_CXGB4) += hw/cxgb4/ obj-$(CONFIG_MLX4_INFINIBAND) += hw/mlx4/ +obj-$(CONFIG_MLX5_INFINIBAND) += hw/mlx5/ obj-$(CONFIG_INFINIBAND_NES) += hw/nes/ obj-$(CONFIG_INFINIBAND_OCRDMA) += hw/ocrdma/ obj-$(CONFIG_INFINIBAND_IPOIB) += ulp/ipoib/ diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index eaec8d7a3b7..e90f2b2eabd 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -45,6 +45,7 @@ #include <net/addrconf.h> #include <net/ip6_route.h> #include <rdma/ib_addr.h> +#include <rdma/ib.h> MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("IB Address Translation"); @@ -70,6 +71,21 @@ static LIST_HEAD(req_list); static DECLARE_DELAYED_WORK(work, process_req); static struct workqueue_struct *addr_wq; +int rdma_addr_size(struct sockaddr *addr) +{ + switch (addr->sa_family) { + case AF_INET: + return sizeof(struct sockaddr_in); + case AF_INET6: + return sizeof(struct sockaddr_in6); + case AF_IB: + return sizeof(struct sockaddr_ib); + default: + return 0; + } +} +EXPORT_SYMBOL(rdma_addr_size); + void rdma_addr_register_client(struct rdma_addr_client *client) { atomic_set(&client->refcount, 1); @@ -369,12 +385,12 @@ int rdma_resolve_ip(struct rdma_addr_client *client, goto err; } - memcpy(src_in, src_addr, ip_addr_size(src_addr)); + memcpy(src_in, src_addr, rdma_addr_size(src_addr)); } else { src_in->sa_family = dst_addr->sa_family; } - memcpy(dst_in, dst_addr, ip_addr_size(dst_addr)); + memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr)); req->addr = addr; req->callback = callback; req->context = context; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 34fbc2f60a0..f1c279fabe6 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -50,6 +50,7 @@ #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> +#include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> @@ -79,7 +80,6 @@ static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct workqueue_struct *cma_wq; -static DEFINE_IDR(sdp_ps); static DEFINE_IDR(tcp_ps); static DEFINE_IDR(udp_ps); static DEFINE_IDR(ipoib_ps); @@ -195,24 +195,7 @@ struct cma_hdr { union cma_ip_addr dst_addr; }; -struct sdp_hh { - u8 bsdh[16]; - u8 sdp_version; /* Major version: 7:4 */ - u8 ip_version; /* IP version: 7:4 */ - u8 sdp_specific1[10]; - __be16 port; - __be16 sdp_specific2; - union cma_ip_addr src_addr; - union cma_ip_addr dst_addr; -}; - -struct sdp_hah { - u8 bsdh[16]; - u8 sdp_version; -}; - #define CMA_VERSION 0x00 -#define SDP_MAJ_VERSION 0x2 static int cma_comp(struct rdma_id_private *id_priv, enum rdma_cm_state comp) { @@ -261,21 +244,6 @@ static inline void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } -static inline u8 sdp_get_majv(u8 sdp_version) -{ - return sdp_version >> 4; -} - -static inline u8 sdp_get_ip_ver(struct sdp_hh *hh) -{ - return hh->ip_version >> 4; -} - -static inline void sdp_set_ip_ver(struct sdp_hh *hh, u8 ip_ver) -{ - hh->ip_version = (ip_ver << 4) | (hh->ip_version & 0xF); -} - static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { @@ -310,16 +278,40 @@ static void cma_release_dev(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -static int cma_set_qkey(struct rdma_id_private *id_priv) +static inline struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) +{ + return (struct sockaddr *) &id_priv->id.route.addr.src_addr; +} + +static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) +{ + return (struct sockaddr *) &id_priv->id.route.addr.dst_addr; +} + +static inline unsigned short cma_family(struct rdma_id_private *id_priv) +{ + return id_priv->id.route.addr.src_addr.ss_family; +} + +static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { struct ib_sa_mcmember_rec rec; int ret = 0; - if (id_priv->qkey) + if (id_priv->qkey) { + if (qkey && id_priv->qkey != qkey) + return -EINVAL; + return 0; + } + + if (qkey) { + id_priv->qkey = qkey; return 0; + } switch (id_priv->id.ps) { case RDMA_PS_UDP: + case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: @@ -358,6 +350,27 @@ static int find_gid_port(struct ib_device *device, union ib_gid *gid, u8 port_nu return -EADDRNOTAVAIL; } +static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) +{ + dev_addr->dev_type = ARPHRD_INFINIBAND; + rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); + ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); +} + +static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) +{ + int ret; + + if (addr->sa_family != AF_IB) { + ret = rdma_translate_ip(addr, dev_addr); + } else { + cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); + ret = 0; + } + + return ret; +} + static int cma_acquire_dev(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; @@ -401,6 +414,61 @@ out: return ret; } +/* + * Select the source IB device and address to reach the destination IB address. + */ +static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) +{ + struct cma_device *cma_dev, *cur_dev; + struct sockaddr_ib *addr; + union ib_gid gid, sgid, *dgid; + u16 pkey, index; + u8 port, p; + int i; + + cma_dev = NULL; + addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); + dgid = (union ib_gid *) &addr->sib_addr; + pkey = ntohs(addr->sib_pkey); + + list_for_each_entry(cur_dev, &dev_list, list) { + if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB) + continue; + + for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { + if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) + continue; + + for (i = 0; !ib_get_cached_gid(cur_dev->device, p, i, &gid); i++) { + if (!memcmp(&gid, dgid, sizeof(gid))) { + cma_dev = cur_dev; + sgid = gid; + port = p; + goto found; + } + + if (!cma_dev && (gid.global.subnet_prefix == + dgid->global.subnet_prefix)) { + cma_dev = cur_dev; + sgid = gid; + port = p; + } + } + } + } + + if (!cma_dev) + return -ENODEV; + +found: + cma_attach_to_dev(id_priv, cma_dev); + id_priv->id.port_num = port; + addr = (struct sockaddr_ib *) cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof sgid); + cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); + return 0; +} + static void cma_deref_id(struct rdma_id_private *id_priv) { if (atomic_dec_and_test(&id_priv->refcount)) @@ -630,7 +698,7 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { - ret = cma_set_qkey(id_priv); + ret = cma_set_qkey(id_priv, 0); if (ret) return ret; @@ -679,26 +747,30 @@ EXPORT_SYMBOL(rdma_init_qp_attr); static inline int cma_zero_addr(struct sockaddr *addr) { - struct in6_addr *ip6; - - if (addr->sa_family == AF_INET) - return ipv4_is_zeronet( - ((struct sockaddr_in *)addr)->sin_addr.s_addr); - else { - ip6 = &((struct sockaddr_in6 *) addr)->sin6_addr; - return (ip6->s6_addr32[0] | ip6->s6_addr32[1] | - ip6->s6_addr32[2] | ip6->s6_addr32[3]) == 0; + switch (addr->sa_family) { + case AF_INET: + return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); + case AF_INET6: + return ipv6_addr_any(&((struct sockaddr_in6 *) addr)->sin6_addr); + case AF_IB: + return ib_addr_any(&((struct sockaddr_ib *) addr)->sib_addr); + default: + return 0; } } static inline int cma_loopback_addr(struct sockaddr *addr) { - if (addr->sa_family == AF_INET) - return ipv4_is_loopback( - ((struct sockaddr_in *) addr)->sin_addr.s_addr); - else - return ipv6_addr_loopback( - &((struct sockaddr_in6 *) addr)->sin6_addr); + switch (addr->sa_family) { + case AF_INET: + return ipv4_is_loopback(((struct sockaddr_in *) addr)->sin_addr.s_addr); + case AF_INET6: + return ipv6_addr_loopback(&((struct sockaddr_in6 *) addr)->sin6_addr); + case AF_IB: + return ib_addr_loopback(&((struct sockaddr_ib *) addr)->sib_addr); + default: + return 0; + } } static inline int cma_any_addr(struct sockaddr *addr) @@ -715,18 +787,31 @@ static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst) case AF_INET: return ((struct sockaddr_in *) src)->sin_addr.s_addr != ((struct sockaddr_in *) dst)->sin_addr.s_addr; - default: + case AF_INET6: return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr, &((struct sockaddr_in6 *) dst)->sin6_addr); + default: + return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, + &((struct sockaddr_ib *) dst)->sib_addr); } } -static inline __be16 cma_port(struct sockaddr *addr) +static __be16 cma_port(struct sockaddr *addr) { - if (addr->sa_family == AF_INET) + struct sockaddr_ib *sib; + + switch (addr->sa_family) { + case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; - else + case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; + case AF_IB: + sib = (struct sockaddr_ib *) addr; + return htons((u16) (be64_to_cpu(sib->sib_sid) & + be64_to_cpu(sib->sib_sid_mask))); + default: + return 0; + } } static inline int cma_any_port(struct sockaddr *addr) @@ -734,83 +819,92 @@ static inline int cma_any_port(struct sockaddr *addr) return !cma_port(addr); } -static int cma_get_net_info(void *hdr, enum rdma_port_space ps, - u8 *ip_ver, __be16 *port, - union cma_ip_addr **src, union cma_ip_addr **dst) +static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, |