diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-25 14:41:24 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-25 14:41:24 -0800 |
commit | 99f1c97dbdb30e958edfd1ced0ae43df62504e07 (patch) | |
tree | cc61393c912b3c1b095a9c74322f8e1364ab9b3a /drivers/infiniband/ulp | |
parent | b31fde6db2b76a9f7f59bf016652b46cff43f8da (diff) | |
parent | 8176d297c73a06e6076c9c31f6404047567f6324 (diff) |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (81 commits)
RDMA/cxgb3: Fix the T3A workaround checks
IB/ipath: Remove unnecessary cast
IPoIB: Constify seq_operations function pointer tables
RDMA/cxgb3: Mark QP as privileged based on user capabilities
RDMA/cxgb3: Fix page shift calculation in build_phys_page_list()
RDMA/cxgb3: Flush the receive queue when closing
IB/ipath: Trivial simplification of ipath_make_ud_req()
IB/mthca: Update latest "native Arbel" firmware revision
IPoIB: Remove redundant check of netif_queue_stopped() in xmit handler
IB/ipath: Add mappings from HW register to PortInfo port physical state
IB/ipath: Changes to support PIO bandwidth check on IBA7220
IB/ipath: Minor cleanup of unused fields and chip-specific errors
IB/ipath: New sysfs entries to control 7220 features
IB/ipath: Add new chip-specific functions to older chips, consistent init
IB/ipath: Remove unused MDIO interface code
IB/ehca: Prevent RDMA-related connection failures on some eHCA2 hardware
IB/ehca: Add "port connection autodetect mode"
IB/ehca: Define array to store SMI/GSI QPs
IB/ehca: Remove CQ-QP-link before destroying QP in error path of create_qp()
IB/iser: Add change_queue_depth method
...
Diffstat (limited to 'drivers/infiniband/ulp')
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib.h | 184 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 376 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_fs.c | 4 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 8 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 60 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 8 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 18 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/Kconfig | 4 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iscsi_iser.c | 1 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iser_initiator.c | 2 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iser_verbs.c | 8 | ||||
-rw-r--r-- | drivers/infiniband/ulp/srp/ib_srp.c | 131 | ||||
-rw-r--r-- | drivers/infiniband/ulp/srp/ib_srp.h | 5 |
13 files changed, 522 insertions, 287 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index eb7edab0e83..fe250c60607 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -56,42 +56,43 @@ /* constants */ enum { - IPOIB_PACKET_SIZE = 2048, - IPOIB_BUF_SIZE = IPOIB_PACKET_SIZE + IB_GRH_BYTES, + IPOIB_PACKET_SIZE = 2048, + IPOIB_BUF_SIZE = IPOIB_PACKET_SIZE + IB_GRH_BYTES, - IPOIB_ENCAP_LEN = 4, + IPOIB_ENCAP_LEN = 4, - IPOIB_CM_MTU = 0x10000 - 0x10, /* padding to align header to 16 */ - IPOIB_CM_BUF_SIZE = IPOIB_CM_MTU + IPOIB_ENCAP_LEN, - IPOIB_CM_HEAD_SIZE = IPOIB_CM_BUF_SIZE % PAGE_SIZE, - IPOIB_CM_RX_SG = ALIGN(IPOIB_CM_BUF_SIZE, PAGE_SIZE) / PAGE_SIZE, - IPOIB_RX_RING_SIZE = 128, - IPOIB_TX_RING_SIZE = 64, + IPOIB_CM_MTU = 0x10000 - 0x10, /* padding to align header to 16 */ + IPOIB_CM_BUF_SIZE = IPOIB_CM_MTU + IPOIB_ENCAP_LEN, + IPOIB_CM_HEAD_SIZE = IPOIB_CM_BUF_SIZE % PAGE_SIZE, + IPOIB_CM_RX_SG = ALIGN(IPOIB_CM_BUF_SIZE, PAGE_SIZE) / PAGE_SIZE, + IPOIB_RX_RING_SIZE = 128, + IPOIB_TX_RING_SIZE = 64, IPOIB_MAX_QUEUE_SIZE = 8192, IPOIB_MIN_QUEUE_SIZE = 2, + IPOIB_CM_MAX_CONN_QP = 4096, - IPOIB_NUM_WC = 4, + IPOIB_NUM_WC = 4, IPOIB_MAX_PATH_REC_QUEUE = 3, - IPOIB_MAX_MCAST_QUEUE = 3, - - IPOIB_FLAG_OPER_UP = 0, - IPOIB_FLAG_INITIALIZED = 1, - IPOIB_FLAG_ADMIN_UP = 2, - IPOIB_PKEY_ASSIGNED = 3, - IPOIB_PKEY_STOP = 4, - IPOIB_FLAG_SUBINTERFACE = 5, - IPOIB_MCAST_RUN = 6, - IPOIB_STOP_REAPER = 7, - IPOIB_MCAST_STARTED = 8, - IPOIB_FLAG_ADMIN_CM = 9, + IPOIB_MAX_MCAST_QUEUE = 3, + + IPOIB_FLAG_OPER_UP = 0, + IPOIB_FLAG_INITIALIZED = 1, + IPOIB_FLAG_ADMIN_UP = 2, + IPOIB_PKEY_ASSIGNED = 3, + IPOIB_PKEY_STOP = 4, + IPOIB_FLAG_SUBINTERFACE = 5, + IPOIB_MCAST_RUN = 6, + IPOIB_STOP_REAPER = 7, + IPOIB_MCAST_STARTED = 8, + IPOIB_FLAG_ADMIN_CM = 9, IPOIB_FLAG_UMCAST = 10, IPOIB_MAX_BACKOFF_SECONDS = 16, - IPOIB_MCAST_FLAG_FOUND = 0, /* used in set_multicast_list */ + IPOIB_MCAST_FLAG_FOUND = 0, /* used in set_multicast_list */ IPOIB_MCAST_FLAG_SENDONLY = 1, - IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */ + IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */ IPOIB_MCAST_FLAG_ATTACHED = 3, }; @@ -117,7 +118,7 @@ struct ipoib_pseudoheader { struct ipoib_mcast { struct ib_sa_mcmember_rec mcmember; struct ib_sa_multicast *mc; - struct ipoib_ah *ah; + struct ipoib_ah *ah; struct rb_node rb_node; struct list_head list; @@ -186,27 +187,29 @@ enum ipoib_cm_state { }; struct ipoib_cm_rx { - struct ib_cm_id *id; - struct ib_qp *qp; - struct list_head list; - struct net_device *dev; - unsigned long jiffies; - enum ipoib_cm_state state; + struct ib_cm_id *id; + struct ib_qp *qp; + struct ipoib_cm_rx_buf *rx_ring; + struct list_head list; + struct net_device *dev; + unsigned long jiffies; + enum ipoib_cm_state state; + int recv_count; }; struct ipoib_cm_tx { - struct ib_cm_id *id; - struct ib_qp *qp; + struct ib_cm_id *id; + struct ib_qp *qp; struct list_head list; struct net_device *dev; struct ipoib_neigh *neigh; struct ipoib_path *path; struct ipoib_tx_buf *tx_ring; - unsigned tx_head; - unsigned tx_tail; - unsigned long flags; - u32 mtu; - struct ib_wc ibwc[IPOIB_NUM_WC]; + unsigned tx_head; + unsigned tx_tail; + unsigned long flags; + u32 mtu; + struct ib_wc ibwc[IPOIB_NUM_WC]; }; struct ipoib_cm_rx_buf { @@ -215,25 +218,28 @@ struct ipoib_cm_rx_buf { }; struct ipoib_cm_dev_priv { - struct ib_srq *srq; + struct ib_srq *srq; struct ipoib_cm_rx_buf *srq_ring; - struct ib_cm_id *id; - struct list_head passive_ids; /* state: LIVE */ - struct list_head rx_error_list; /* state: ERROR */ - struct list_head rx_flush_list; /* state: FLUSH, drain not started */ - struct list_head rx_drain_list; /* state: FLUSH, drain started */ - struct list_head rx_reap_list; /* state: FLUSH, drain done */ + struct ib_cm_id *id; + struct list_head passive_ids; /* state: LIVE */ + struct list_head rx_error_list; /* state: ERROR */ + struct list_head rx_flush_list; /* state: FLUSH, drain not started */ + struct list_head rx_drain_list; /* state: FLUSH, drain started */ + struct list_head rx_reap_list; /* state: FLUSH, drain done */ struct work_struct start_task; struct work_struct reap_task; struct work_struct skb_task; struct work_struct rx_reap_task; struct delayed_work stale_task; struct sk_buff_head skb_queue; - struct list_head start_list; - struct list_head reap_list; - struct ib_wc ibwc[IPOIB_NUM_WC]; - struct ib_sge rx_sge[IPOIB_CM_RX_SG]; + struct list_head start_list; + struct list_head reap_list; + struct ib_wc ibwc[IPOIB_NUM_WC]; + struct ib_sge rx_sge[IPOIB_CM_RX_SG]; struct ib_recv_wr rx_wr; + int nonsrq_conn_qp; + int max_cm_mtu; + int num_frags; }; /* @@ -269,30 +275,30 @@ struct ipoib_dev_priv { struct work_struct pkey_event_task; struct ib_device *ca; - u8 port; - u16 pkey; - u16 pkey_index; - struct ib_pd *pd; - struct ib_mr *mr; - struct ib_cq *cq; - struct ib_qp *qp; - u32 qkey; + u8 port; + u16 pkey; + u16 pkey_index; + struct ib_pd *pd; + struct ib_mr *mr; + struct ib_cq *cq; + struct ib_qp *qp; + u32 qkey; union ib_gid local_gid; - u16 local_lid; + u16 local_lid; unsigned int admin_mtu; unsigned int mcast_mtu; struct ipoib_rx_buf *rx_ring; - spinlock_t tx_lock; + spinlock_t tx_lock; struct ipoib_tx_buf *tx_ring; - unsigned tx_head; - unsigned tx_tail; - struct ib_sge tx_sge; + unsigned tx_head; + unsigned tx_tail; + struct ib_sge tx_sge; struct ib_send_wr tx_wr; - unsigned tx_outstanding; + unsigned tx_outstanding; struct ib_wc ibwc[IPOIB_NUM_WC]; @@ -317,10 +323,10 @@ struct ipoib_dev_priv { struct ipoib_ah { struct net_device *dev; - struct ib_ah *ah; + struct ib_ah *ah; struct list_head list; - struct kref ref; - unsigned last_send; + struct kref ref; + unsigned last_send; }; struct ipoib_path { @@ -331,11 +337,11 @@ struct ipoib_path { struct list_head neigh_list; - int query_id; + int query_id; struct ib_sa_query *query; struct completion done; - struct rb_node rb_node; + struct rb_node rb_node; struct list_head list; }; @@ -344,7 +350,7 @@ struct ipoib_neigh { #ifdef CONFIG_INFINIBAND_IPOIB_CM struct ipoib_cm_tx *cm; #endif - union ib_gid dgid; + union ib_gid dgid; struct sk_buff_head queue; struct neighbour *neighbour; @@ -455,12 +461,14 @@ void ipoib_drain_cq(struct net_device *dev); #ifdef CONFIG_INFINIBAND_IPOIB_CM -#define IPOIB_FLAGS_RC 0x80 -#define IPOIB_FLAGS_UC 0x40 +#define IPOIB_FLAGS_RC 0x80 +#define IPOIB_FLAGS_UC 0x40 /* We don't support UC connections at the moment */ #define IPOIB_CM_SUPPORTED(ha) (ha[0] & (IPOIB_FLAGS_RC)) +extern int ipoib_max_conn_qp; + static inline int ipoib_cm_admin_enabled(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -491,6 +499,18 @@ static inline void ipoib_cm_set(struct ipoib_neigh *neigh, struct ipoib_cm_tx *t neigh->cm = tx; } +static inline int ipoib_cm_has_srq(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + return !!priv->cm.srq; +} + +static inline unsigned int ipoib_cm_max_mtu(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + return priv->cm.max_cm_mtu; +} + void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx); int ipoib_cm_dev_open(struct net_device *dev); void ipoib_cm_dev_stop(struct net_device *dev); @@ -500,7 +520,7 @@ void ipoib_cm_dev_cleanup(struct net_device *dev); struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path *path, struct ipoib_neigh *neigh); void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx); -void ipoib_cm_skb_too_long(struct net_device* dev, struct sk_buff *skb, +void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, unsigned int mtu); void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc); void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc); @@ -508,6 +528,8 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc); struct ipoib_cm_tx; +#define ipoib_max_conn_qp 0 + static inline int ipoib_cm_admin_enabled(struct net_device *dev) { return 0; @@ -533,6 +555,16 @@ static inline void ipoib_cm_set(struct ipoib_neigh *neigh, struct ipoib_cm_tx *t { } +static inline int ipoib_cm_has_srq(struct net_device *dev) +{ + return 0; +} + +static inline unsigned int ipoib_cm_max_mtu(struct net_device *dev) +{ + return 0; +} + static inline void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx) { @@ -582,7 +614,7 @@ int ipoib_cm_add_mode_attr(struct net_device *dev) return 0; } -static inline void ipoib_cm_skb_too_long(struct net_device* dev, struct sk_buff *skb, +static inline void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, unsigned int mtu) { dev_kfree_skb_any(skb); @@ -624,12 +656,12 @@ extern struct ib_sa_client ipoib_sa_client; extern int ipoib_debug_level; #define ipoib_dbg(priv, format, arg...) \ - do { \ + do { \ if (ipoib_debug_level > 0) \ ipoib_printk(KERN_DEBUG, priv, format , ## arg); \ } while (0) #define ipoib_dbg_mcast(priv, format, arg...) \ - do { \ + do { \ if (mcast_debug_level > 0) \ ipoib_printk(KERN_DEBUG, priv, format , ## arg); \ } while (0) @@ -642,7 +674,7 @@ extern int ipoib_debug_level; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG_DATA #define ipoib_dbg_data(priv, format, arg...) \ - do { \ + do { \ if (data_debug_level > 0) \ ipoib_printk(KERN_DEBUG, priv, format , ## arg); \ } while (0) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 059cf92b60a..1818f958c25 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -39,6 +39,15 @@ #include <linux/icmpv6.h> #include <linux/delay.h> +#include "ipoib.h" + +int ipoib_max_conn_qp = 128; + +module_param_named(max_nonsrq_conn_qp, ipoib_max_conn_qp, int, 0444); +MODULE_PARM_DESC(max_nonsrq_conn_qp, + "Max number of connected-mode QPs per interface " + "(applied only if shared receive queue is not available)"); + #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG_DATA static int data_debug_level; @@ -47,8 +56,6 @@ MODULE_PARM_DESC(cm_data_debug_level, "Enable data path debug tracing for connected mode if > 0"); #endif -#include "ipoib.h" - #define IPOIB_CM_IETF_ID 0x1000000000000000ULL #define IPOIB_CM_RX_UPDATE_TIME (256 * HZ) @@ -81,7 +88,7 @@ static void ipoib_cm_dma_unmap_rx(struct ipoib_dev_priv *priv, int frags, ib_dma_unmap_single(priv->ca, mapping[i + 1], PAGE_SIZE, DMA_FROM_DEVICE); } -static int ipoib_cm_post_receive(struct net_device *dev, int id) +static int ipoib_cm_post_receive_srq(struct net_device *dev, int id) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_recv_wr *bad_wr; @@ -89,13 +96,13 @@ static int ipoib_cm_post_receive(struct net_device *dev, int id) priv->cm.rx_wr.wr_id = id | IPOIB_OP_CM | IPOIB_OP_RECV; - for (i = 0; i < IPOIB_CM_RX_SG; ++i) + for (i = 0; i < priv->cm.num_frags; ++i) priv->cm.rx_sge[i].addr = priv->cm.srq_ring[id].mapping[i]; ret = ib_post_srq_recv(priv->cm.srq, &priv->cm.rx_wr, &bad_wr); if (unlikely(ret)) { ipoib_warn(priv, "post srq failed for buf %d (%d)\n", id, ret); - ipoib_cm_dma_unmap_rx(priv, IPOIB_CM_RX_SG - 1, + ipoib_cm_dma_unmap_rx(priv, priv->cm.num_frags - 1, priv->cm.srq_ring[id].mapping); dev_kfree_skb_any(priv->cm.srq_ring[id].skb); priv->cm.srq_ring[id].skb = NULL; @@ -104,7 +111,33 @@ static int ipoib_cm_post_receive(struct net_device *dev, int id) return ret; } -static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, int id, int frags, +static int ipoib_cm_post_receive_nonsrq(struct net_device *dev, + struct ipoib_cm_rx *rx, int id) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ib_recv_wr *bad_wr; + int i, ret; + + priv->cm.rx_wr.wr_id = id | IPOIB_OP_CM | IPOIB_OP_RECV; + + for (i = 0; i < IPOIB_CM_RX_SG; ++i) + priv->cm.rx_sge[i].addr = rx->rx_ring[id].mapping[i]; + + ret = ib_post_recv(rx->qp, &priv->cm.rx_wr, &bad_wr); + if (unlikely(ret)) { + ipoib_warn(priv, "post recv failed for buf %d (%d)\n", id, ret); + ipoib_cm_dma_unmap_rx(priv, IPOIB_CM_RX_SG - 1, + rx->rx_ring[id].mapping); + dev_kfree_skb_any(rx->rx_ring[id].skb); + rx->rx_ring[id].skb = NULL; + } + + return ret; +} + +static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, + struct ipoib_cm_rx_buf *rx_ring, + int id, int frags, u64 mapping[IPOIB_CM_RX_SG]) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -141,7 +174,7 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, int id, int goto partial_error; } - priv->cm.srq_ring[id].skb = skb; + rx_ring[id].skb = skb; return skb; partial_error: @@ -155,7 +188,23 @@ partial_error: return NULL; } -static void ipoib_cm_start_rx_drain(struct ipoib_dev_priv* priv) +static void ipoib_cm_free_rx_ring(struct net_device *dev, + struct ipoib_cm_rx_buf *rx_ring) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + int i; + + for (i = 0; i < ipoib_recvq_size; ++i) + if (rx_ring[i].skb) { + ipoib_cm_dma_unmap_rx(priv, IPOIB_CM_RX_SG - 1, + rx_ring[i].mapping); + dev_kfree_skb_any(rx_ring[i].skb); + } + + kfree(rx_ring); +} + +static void ipoib_cm_start_rx_drain(struct ipoib_dev_priv *priv) { struct ib_send_wr *bad_wr; struct ipoib_cm_rx *p; @@ -208,12 +257,18 @@ static struct ib_qp *ipoib_cm_create_rx_qp(struct net_device *dev, .qp_type = IB_QPT_RC, .qp_context = p, }; + + if (!ipoib_cm_has_srq(dev)) { + attr.cap.max_recv_wr = ipoib_recvq_size; + attr.cap.max_recv_sge = IPOIB_CM_RX_SG; + } + return ib_create_qp(priv->pd, &attr); } static int ipoib_cm_modify_rx_qp(struct net_device *dev, - struct ib_cm_id *cm_id, struct ib_qp *qp, - unsigned psn) + struct ib_cm_id *cm_id, struct ib_qp *qp, + unsigned psn) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_qp_attr qp_attr; @@ -266,6 +321,60 @@ static int ipoib_cm_modify_rx_qp(struct net_device *dev, return 0; } +static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_id, + struct ipoib_cm_rx *rx) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + int ret; + int i; + + rx->rx_ring = kcalloc(ipoib_recvq_size, sizeof *rx->rx_ring, GFP_KERNEL); + if (!rx->rx_ring) + return -ENOMEM; + + spin_lock_irq(&priv->lock); + + if (priv->cm.nonsrq_conn_qp >= ipoib_max_conn_qp) { + spin_unlock_irq(&priv->lock); + ib_send_cm_rej(cm_id, IB_CM_REJ_NO_QP, NULL, 0, NULL, 0); + ret = -EINVAL; + goto err_free; + } else + ++priv->cm.nonsrq_conn_qp; + + spin_unlock_irq(&priv->lock); + + for (i = 0; i < ipoib_recvq_size; ++i) { + if (!ipoib_cm_alloc_rx_skb(dev, rx->rx_ring, i, IPOIB_CM_RX_SG - 1, + rx->rx_ring[i].mapping)) { + ipoib_warn(priv, "failed to allocate receive buffer %d\n", i); + ret = -ENOMEM; + goto err_count; + } + ret = ipoib_cm_post_receive_nonsrq(dev, rx, i); + if (ret) { + ipoib_warn(priv, "ipoib_cm_post_receive_nonsrq " + "failed for buf %d\n", i); + ret = -EIO; + goto err_count; + } + } + + rx->recv_count = ipoib_recvq_size; + + return 0; + +err_count: + spin_lock_irq(&priv->lock); + --priv->cm.nonsrq_conn_qp; + spin_unlock_irq(&priv->lock); + +err_free: + ipoib_cm_free_rx_ring(dev, rx->rx_ring); + + return ret; +} + static int ipoib_cm_send_rep(struct net_device *dev, struct ib_cm_id *cm_id, struct ib_qp *qp, struct ib_cm_req_event_param *req, unsigned psn) @@ -281,7 +390,7 @@ static int ipoib_cm_send_rep(struct net_device *dev, struct ib_cm_id *cm_id, rep.private_data_len = sizeof data; rep.flow_control = 0; rep.rnr_retry_count = req->rnr_retry_count; - rep.srq = 1; + rep.srq = ipoib_cm_has_srq(dev); rep.qp_num = qp->qp_num; rep.starting_psn = psn; return ib_send_cm_rep(cm_id, &rep); @@ -317,6 +426,12 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even if (ret) goto err_modify; + if (!ipoib_cm_has_srq(dev)) { + ret = ipoib_cm_nonsrq_init_rx(dev, cm_id, p); + if (ret) + goto err_modify; + } + spin_lock_irq(&priv->lock); queue_delayed_work(ipoib_workqueue, &priv->cm.stale_task, IPOIB_CM_RX_DELAY); @@ -401,12 +516,14 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space, void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) { struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_cm_rx_buf *rx_ring; unsigned int wr_id = wc->wr_id & ~(IPOIB_OP_CM | IPOIB_OP_RECV); struct sk_buff *skb, *newskb; struct ipoib_cm_rx *p; unsigned long flags; u64 mapping[IPOIB_CM_RX_SG]; int frags; + int has_srq; ipoib_dbg_data(priv, "cm recv completion: id %d, status: %d\n", wr_id, wc->status); @@ -424,18 +541,32 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) return; } - skb = priv->cm.srq_ring[wr_id].skb; + p = wc->qp->qp_context; + + has_srq = ipoib_cm_has_srq(dev); + rx_ring = has_srq ? priv->cm.srq_ring : p->rx_ring; + + skb = rx_ring[wr_id].skb; if (unlikely(wc->status != IB_WC_SUCCESS)) { ipoib_dbg(priv, "cm recv error " "(status=%d, wrid=%d vend_err %x)\n", wc->status, wr_id, wc->vendor_err); ++dev->stats.rx_dropped; - goto repost; + if (has_srq) + goto repost; + else { + if (!--p->recv_count) { + spin_lock_irqsave(&priv->lock, flags); + list_move(&p->list, &priv->cm.rx_reap_list); + spin_unlock_irqrestore(&priv->lock, flags); + queue_work(ipoib_workqueue, &priv->cm.rx_reap_task); + } + return; + } } if (unlikely(!(wr_id & IPOIB_CM_RX_UPDATE_MASK))) { - p = wc->qp->qp_context; if (p && time_after_eq(jiffies, p->jiffies + IPOIB_CM_RX_UPDATE_TIME)) { spin_lock_irqsave(&priv->lock, flags); p->jiffies = jiffies; @@ -450,7 +581,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) frags = PAGE_ALIGN(wc->byte_len - min(wc->byte_len, (unsigned)IPOIB_CM_HEAD_SIZE)) / PAGE_SIZE; - newskb = ipoib_cm_alloc_rx_skb(dev, wr_id, frags, mapping); + newskb = ipoib_cm_alloc_rx_skb(dev, rx_ring, wr_id, frags, mapping); if (unlikely(!newskb)) { /* * If we can't allocate a new RX buffer, dump @@ -461,8 +592,8 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) goto repost; } - ipoib_cm_dma_unmap_rx(priv, frags, priv->cm.srq_ring[wr_id].mapping); - memcpy(priv->cm.srq_ring[wr_id].mapping, mapping, (frags + 1) * sizeof *mapping); + ipoib_cm_dma_unmap_rx(priv, frags, rx_ring[wr_id].mapping); + memcpy(rx_ring[wr_id].mapping, mapping, (frags + 1) * sizeof *mapping); ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n", wc->byte_len, wc->slid); @@ -483,9 +614,17 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) netif_receive_skb(skb); repost: - if (unlikely(ipoib_cm_post_receive(dev, wr_id))) - ipoib_warn(priv, "ipoib_cm_post_receive failed " - "for buf %d\n", wr_id); + if (has_srq) { + if (unlikely(ipoib_cm_post_receive_srq(dev, wr_id))) + ipoib_warn(priv, "ipoib_cm_post_receive_srq failed " + "for buf %d\n", wr_id); + } else { + if (unlikely(ipoib_cm_post_receive_nonsrq(dev, p, wr_id))) { + --p->recv_count; + ipoib_warn(priv, "ipoib_cm_post_receive_nonsrq failed " + "for buf %d\n", wr_id); + } + } } static inline int post_send(struct ipoib_dev_priv *priv, @@ -495,10 +634,10 @@ static inline int post_send(struct ipoib_dev_priv *priv, { struct ib_send_wr *bad_wr; - priv->tx_sge.addr = addr; - priv->tx_sge.length = len; + priv->tx_sge.addr = addr; + priv->tx_sge.length = len; - priv->tx_wr.wr_id = wr_id | IPOIB_OP_CM; + priv->tx_wr.wr_id = wr_id | IPOIB_OP_CM; return ib_post_send(tx->qp, &priv->tx_wr, &bad_wr); } @@ -540,7 +679,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ tx_req->mapping = addr; if (unlikely(post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), - addr, skb->len))) { + addr, skb->len))) { ipoib_warn(priv, "post_send failed\n"); ++dev->stats.tx_errors; ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE); @@ -657,10 +796,33 @@ err_cm: return ret; } +static void ipoib_cm_free_rx_reap_list(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_cm_rx *rx, *n; + LIST_HEAD(list); + + spin_lock_irq(&priv->lock); + list_splice_init(&priv->cm.rx_reap_list, &list); + spin_unlock_irq(&priv->lock); + + list_for_each_entry_safe(rx, n, &list, list) { + ib_destroy_cm_id(rx->id); + ib_destroy_qp(rx->qp); + if (!ipoib_cm_has_srq(dev)) { + ipoib_cm_free_rx_ring(priv->dev, rx->rx_ring); + spin_lock_irq(&priv->lock); + --priv->cm.nonsrq_conn_qp; + spin_unlock_irq(&priv->lock); + } + kfree(rx); + } +} + void ipoib_cm_dev_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); - struct ipoib_cm_rx *p, *n; + struct ipoib_cm_rx *p; unsigned long begin; LIST_HEAD(list); int ret; @@ -706,15 +868,9 @@ void ipoib_cm_dev_stop(struct net_device *dev) spin_lock_irq(&priv->lock); } - list_splice_init(&priv->cm.rx_reap_list, &list); - spin_unlock_irq(&priv->lock); - list_for_each_entry_safe(p, n, &list, list) { - ib_destroy_cm_id(p->id); - ib_destroy_qp(p->qp); - kfree(p); - } + ipoib_cm_free_rx_reap_list(dev); cancel_delayed_work(&priv->cm.stale_task); } @@ -799,7 +955,7 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ .sq_sig_type = IB_SIGNAL_ALL_WR, .qp_type = IB_QPT_RC, .qp_context = tx - }; + }; return ib_create_qp(priv->pd, &attr); } @@ -816,28 +972,28 @@ static int ipoib_cm_send_req(struct net_device *dev, data.qpn = cpu_to_be32(priv->qp->qp_num); data.mtu = cpu_to_be32(IPOIB_CM_BUF_SIZE); - req.primary_path = pathrec; - req.alternate_path = NULL; - req.service_id = cpu_to_be64(IPOIB_CM_IETF_ID | qpn); - req.qp_num = qp->qp_num; - req.qp_type = qp->qp_type; - req.private_data = &data; - req.private_data_len = sizeof data; - req.flow_control = 0; + req.primary_path = pathrec; + req.alternate_path = NULL; + req.service_id = cpu_to_be64(IPOIB_CM_IETF_ID | qpn); + req.qp_num = qp->qp_num; + req.qp_type = qp->qp_type; + req.private_data = &data; + req.private_data_len = sizeof data; + req.flow_control = 0; - req.starting_psn = 0; /* FIXME */ + req.starting_psn = 0; /* FIXME */ /* * Pick some arbitrary defaults here; we could make these * module parameters if anyone cared about setting them. */ - req.responder_resources = 4; - req.remote_cm_response_timeout = 20; - req.local_cm_response_timeout = 20; - req.retry_count = 0; /* RFC draft warns against retries */ - req.rnr_retry_count = 0; /* RFC draft warns against retries */ - req.max_cm_retries = 15; - req.srq = 1; + req.responder_resources = 4; + req.remote_cm_response_timeout = 20; + req.local_cm_response_timeout = 20; + req.retry_count = 0; /* RFC draft warns against retries */ + req.rnr_retry_count = 0; /* RFC draft warns against retries */ + req.max_cm_retries = 15; + req.srq = ipoib_cm_has_srq(dev); return ib_send_cm_req(id, &req); } @@ -1150,7 +1306,7 @@ static void ipoib_cm_skb_reap(struct work_struct *work) spin_unlock_irq(&priv->tx_lock); } -void ipoib_cm_skb_too_long(struct net_device* dev, struct sk_buff *skb, +void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, unsigned int mtu) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -1166,20 +1322,8 @@ void ipoib_cm_skb_too_long(struct net_device* dev, struct sk_buff *skb, static void ipoib_cm_rx_reap(struct work_struct *work) { - struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, - cm.rx_reap_task); - struct ipoib_cm_rx *p, *n; - LIST_HEAD(list); - - spin_lock_irq(&priv->lock); - list_splice_init(&priv->cm.rx_reap_list, &list); - spin_unlock_irq(&priv->lock); - - list_for_each_entry_safe(p, n, &list, list) { - ib_destroy_cm_id(p->id); - ib_destroy_qp(p->qp); - kfree(p); - } + ipoib_cm_free_rx_reap_list(container_of(work, struct ipoib_dev_priv, + cm.rx_reap_task)->dev); } static void ipoib_cm_stale_task(struct work_struct *work) @@ -1212,7 +1356,7 @@ static void ipoib_cm_stale_task(struct work_struct *work) } -static ssize_t show_mode(struct device *d, struct device_attribute *attr, +static ssize_t show_mode(struct device *d, struct device_attribute *attr, char *buf) { struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(d)); @@ -1255,16 +1399,40 @@ int ipoib_cm_add_mode_attr(struct net_device *dev) return device_create_file(&dev->dev, &dev_attr_mode); } -int ipoib_cm_dev_init(struct net_device *dev) +static void ipoib_cm_create_srq(struct net_device *dev, int max_sge) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_srq_init_attr srq_init_attr = { .attr = { .max_wr = ipoib_recvq_size, - .max_sge = IPOIB_CM_RX_SG + .max_sge = max_sge } }; - int ret, i; + + priv->cm.srq = ib_create_srq(priv->pd, &srq_init_attr); + if (IS_ERR(priv->cm.srq)) { + if (PTR_ERR(priv->cm.srq) != -ENOSYS) + printk(KERN_WARNING "%s: failed to allocate SRQ, error %ld\n", + priv->ca->name, PTR_ERR(priv->cm.srq)); + priv->cm.srq = NULL; + return; + } + + priv->cm.srq_ring = kzalloc(ipoib_recvq_size * sizeof *priv->cm.srq_ring, + GFP_KERNEL); + if (!priv->cm.srq_ring) { + printk(KERN_WARNING "%s: failed to allocate CM SRQ ring (%d entries)\n", + priv->ca->name, ipoib_recvq_size); + ib_destroy_srq(priv->cm.srq); + priv->cm.srq = NULL; + } +} + +int ipoib_cm_dev_init(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + int i, ret; + struct ib_device_attr attr; INIT_LIST_HEAD(&priv->cm.passive_ids); INIT_LIST_HEAD(&priv->cm.reap_list); @@ -1281,43 +1449,53 @@ int ipoib_cm_dev_init(struct net_device *dev) skb_queue_head_init(&priv->cm.skb_queue); - priv->cm.srq = ib_create_srq(priv->pd, &srq_init_attr); - if (IS_ERR(priv->cm.srq)) { - ret = PTR_ERR(priv->cm.srq); - priv->cm.srq = NULL; + ret = ib_query_device(priv->ca, &attr); + if (ret) { + printk(KERN_WARNING "ib_query_device() failed with %d\n", ret); return ret; } - priv->cm.srq_ring = kzalloc(ipoib_recvq_size * sizeof *priv->cm.srq_ring, - GFP_KERNEL); - if (!priv->cm.srq_ring) { - printk(KERN_WARNING "%s: failed to allocate CM ring (%d entries)\n", - priv->ca->name, ipoib_recvq_size); - ipoib_cm_dev_cleanup(dev); - return -ENOMEM; + ipoib_dbg(priv, "max_srq_sge=%d\n", attr.max_srq_sge); + + attr.max_srq_sge = min_t(int, IPOIB_CM_RX_SG, attr.max_srq_sge); + ipoib_cm_create_srq(dev, attr.max_srq_sge); + if (ipoib_cm_has_srq(dev)) { + priv->cm.max_cm_mtu = attr.max_srq_sge * PAGE_SIZE - 0x10; + priv->cm.num_frags = attr.max_srq_sge; + ipoib_dbg(priv, "max_cm_mtu = 0x%x, num_frags=%d\n", + priv->cm.max_cm_mtu, priv->cm.num_frags); + } else { + priv->cm.max_cm_mtu = IPOIB_CM_MTU; + priv->cm.num_frags = IPOIB_CM_RX_SG; } - for (i = 0; i < IPOIB_CM_RX_SG; ++i) + for (i = 0; i < priv->cm.num_frags; ++i) priv->cm.rx_sge[i].lkey = priv->mr->lkey; priv->cm.rx_sge[0].length = IPOIB_CM_HEAD_SIZE; - for (i = 1; i < IPOIB_CM_RX_SG; ++i) + for (i = 1; i < priv->cm.num_frags; ++i) priv->cm.rx_sge[i].length = PAGE_SIZE; priv->cm.rx_wr.next = NULL; priv->cm.rx_wr.sg_list = priv->cm.rx_sge; - priv->cm.rx_wr.num_sge = IPOIB_CM_RX_SG; + priv->cm.rx_wr.num_sge = priv->cm.num_frags; + + if (ipoib_cm_has_srq(dev)) { + for (i = 0; i < ipoib_recvq_size; ++i) { + if (!ipoib_cm_alloc_rx_skb(dev, priv->cm.srq_ring, i, + priv->cm.num_frags - 1, + priv->cm.srq_ring[i].mapping)) { + ipoib_warn(priv, "failed to allocate " + "receive buffer %d\n", i); + ipoib_cm_dev_cleanup(dev); + return -ENOMEM; + } - for (i = 0; i < ipoib_recvq_size; ++i) { - if (!ipoib_cm_alloc_rx_skb(dev, i, IPOIB_CM_RX_SG - 1, - priv->cm.srq_ring[i].mapping)) { - ipoib_warn(priv, "failed to allocate receive buffer %d\n", i); - ipoib_cm_dev_cleanup(dev); - return -ENOMEM; - } - if (ipoib_cm_post_receive(dev, i)) { - ipoib_warn(priv, "ipoib_ib_post_receive failed for buf %d\n", i); - ipoib_cm_dev_cleanup(dev); - return -EIO; + if (ipoib_cm_post_receive_srq(dev, i)) { + ipoib_warn(priv, "ipoib_cm_post_receive_srq " + "failed for buf %d\n", i); + ipoib_cm_dev_cleanup(dev); + return -EIO; + } } } @@ -1328,7 +1506,7 @@ int ipoib_cm_dev_init(struct net_device *dev) void ipoib_cm_dev_cleanup(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); - int i, ret; + int ret; if (!priv->cm.srq) return; @@ -1342,13 +1520,7 @@ void ipoib_cm_dev_cleanup(struct net_device *dev) priv->cm.srq = NULL; if (!priv->cm.srq_ring) return; - for (i = 0; i < ipoib_recvq_size; ++i) - if (priv->cm.srq_ring[i].skb) { - ipoib_cm_dma_unmap_rx(priv, IPOIB_CM_RX_SG - 1, - priv->cm.srq_ring[i].mapping); - dev_kfree_skb_any(priv->cm.srq_ring[i].skb); - priv->cm.srq_ring[i].skb = NULL; - } - kfree(priv->cm.srq_ring); + + ipoib_cm_free_rx_ring(dev, priv->cm.srq_ring); priv->cm.srq_ring = NULL; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c index 44c174182a8..8b882bbd1d0 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c @@ -124,7 +124,7 @@ static int ipoib_mcg_seq_show(struct seq_file *file, void *iter_ptr) return 0; } -static struct seq_operations ipoib_mcg_seq_ops = { +static const struct seq_operations ipoib_mcg_seq_ops = { .start = ipoib_mcg_seq_start, .next = ipoib_mcg_seq_next, .stop = ipoib_mcg_seq_stop, @@ -230,7 +230,7 @@ static int ipoib_path_seq_show(struct seq_file *file, void *iter_ptr) return 0; } -static struct seq_operations ipoib_path_seq_ops = { +static const struct seq_operations ipoib_path_seq_ops = { .start = ipoib_path_seq_start, .next = ipoib_path_seq_next, .stop = ipoib_path_seq_stop, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 5063dd509ad..52bc2bd5799 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -345,12 +345,12 @@ static inline int post_send(struct ipoib_dev_priv *priv, { struct ib_send_wr *bad_wr; - priv->tx_sge.addr = addr; - priv->tx_sge.length = len; + priv->tx_sge.addr = addr; + priv->tx_sge.length = len; - priv->tx_wr.wr_id = wr_id; + priv->tx_wr.wr_id = wr_id; priv->tx_wr.wr.ud.remote_qpn = qpn; - priv->tx_wr.wr.ud.ah = address; + priv->tx_wr.wr.ud.ah = address; return ib_post_send(priv->qp, &priv->tx_wr, &bad_wr); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index c9f6077b615..a082466f4a8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -182,17 +182,20 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu) struct ipoib_dev_priv *priv = netdev_priv(dev); /* dev->mtu > 2K ==> connected mode */ - if (ipoib_cm_admin_enabled(dev) && new_mtu <= IPOIB_CM_MTU) { + if (ipoib_cm_admin_enabled(dev)) { + if (new_mtu > ipoib_cm_max_mtu(dev)) + return -EINVAL; + if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); + dev->mtu = new_mtu; return 0; } - if (new_mtu > IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN) { + if (new_mtu > IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN) return -EINVAL; - } priv->admin_mtu = new_mtu; @@ -474,8 +477,8 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) INIT_LIST_HEAD(&path->neigh_list); memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid)); - path->pathrec.sgid = priv->local_gid; - path->pathrec.pkey = cpu_to_be16(priv->pkey); + path->pathrec.sgid = priv->local_gid; + path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; @@ -669,16 +672,6 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!spin_trylock_irqsave(&priv->tx_lock, flags))) return NETDEV_TX_LOCKED; - /* - * Check if our queue is stopped. Since we have the LLTX bit - * set, we can't rely on netif_stop_queue() preventing our - * xmit function from being called with a full queue. - */ - if (unlikely(netif_queue_stopped(dev))) { - spin_unlock_irqrestore(&priv->tx_lock, flags); - return NETDEV_TX_BUSY; - } - if (likely(skb->dst && skb->dst->neighbour)) { if (unlikely(!*to_ipoib_neigh(skb->dst->neighbour))) { ipoib_path_lookup(skb, dev); @@ -950,34 +943,34 @@ static void ipoib_setup(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); - dev->open = ipoib_open; - dev->stop = ipoib_stop; - dev->change_mtu = ipoib_change_mtu; - dev->hard_start_xmit = ipoib_start_xmit; - dev->tx_timeout = ipoib_timeout; - dev->header_ops = &ipoib_header_ops; - dev->set_multicast_list = ipoib_set_mcast_list; - dev->neigh_setup = ipoib_neigh_setup_dev; + dev->open = ipoib_open; + dev->stop = ipoib_stop; + dev->change_mtu = ipoib_change_mtu; + dev->hard_start_xmit = ipoib_start_xmit; + dev->tx_timeout = ipoib_timeout; + dev->header_ops = &ipoib_header_ops; + dev->set_multicast_list = ipoib_set_mcast_list; + dev->neigh_setup = ipoib_neigh_setup_dev; netif_napi_add(dev, &priv->napi, ipoib_poll, 100); - dev->watchdog_timeo = HZ; + dev->watchdog_timeo = HZ; - dev->flags |= IFF_BROADCAST | IFF_MULTICAST; + dev->flags |= IFF_BROADCAST | IFF_MULTICAST; /* * We add in INFINIBAND_ALEN to allow for the destination * address "pseudoheader" for skbs without neighbour struct. */ - dev->hard_header_len = IPOIB_ENCAP_LEN + INFINIBAND_ALEN; - dev->addr_len = INFINIBAND_ALEN; - dev->type = ARPHRD_INFINIBAND; - dev->tx_queue_len = ipoib_sendq_size * 2; - dev->features = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX; + dev->hard_header_len = IPOIB_ENCAP_LEN + INFINIBAND_ALEN; + dev->addr_len = INFINIBAND_ALEN; + dev->type = ARPHRD_INFINIBAND; + dev->tx_queue_len = ipoib_sendq_size * 2; + dev->features = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX; /* MTU will be reset when mcast join happens */ - dev->mtu = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN; - priv->mcast_mtu = priv->admin_mtu = dev->mtu; + dev->mtu = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN; + priv->mcast_mtu = priv->admin_mtu = dev->mtu; memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); @@ -1268,6 +1261,9 @@ static int __init ipoib_init_module(void) ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max(ipoib_sendq_size, IPOIB_MIN_QUEUE_SIZE); +#ifdef CONFIG_INFINIBAND_IPOIB_CM + ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); +#endif ret = ipoib_register_debugfs(); if (ret) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 9bcfc7ad6aa..2628339e3a9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -702,7 +702,7 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb) out: if (mcast && mcast->ah) { - if (skb->dst && + if (skb->dst && skb->dst->neighbour && !*to_ipoib_neigh(skb->dst->neighbour)) { struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour, @@ -710,7 +710,7 @@ out: if (neigh) { kref_get(&mcast->ah->ref); - neigh->ah = mcast->ah; + neigh->ah = mcast->ah; list_add_tail(&neigh->list, &mcast->neigh_list); } } @@ -788,10 +788,6 @@ void ipoib_mcast_restart_task(struct work_struct *work) memcpy(mgid.raw, mclist->dmi_addr + 4, sizeof mgid); - /* Add in the P_Key */ - mgid.raw[4] = (priv->pkey >> 8) & 0xff; - mgid.raw[5] = priv->pkey & 0xff; - mcast = __ipoib_mcast_find(dev, &mgid); if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) { struct ipoib_mcast *nmcast; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index 3c6e45db0ab..433e99ac227 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -172,8 +172,12 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) size = ipoib_sendq_size + ipoib_recvq_size + 1; ret = ipoib_cm_dev_init(dev); - if (!ret) - size += ipoib_recvq_size + 1 /* 1 extra for rx_drain_qp */; + if (!ret) { + if (ipoib_cm_has_srq(dev)) + size += ipoib_recvq_size + 1; /* 1 extra for rx_drain_qp */ + else + size += ipoib_recvq_size * ipoib_max_conn_qp; + } priv->cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0); if (IS_ERR(priv->cq)) { @@ -197,12 +201,12 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->dev->dev_addr[2] = (priv->qp->qp_num >> 8) & 0xff; priv->dev->dev_addr[3] = (priv->qp->qp_num ) & 0xff; - priv->tx_sge.lkey = priv->mr->lkey; + priv->tx_sge.lkey = priv->mr->lkey; - priv->tx_wr.opcode = IB_WR_SEND; - priv->tx_wr.sg_list = &priv->tx_sge; - priv->tx_wr.num_sge = 1; - priv->tx_wr.send_flags = IB_SEND_SIGNALED; + priv->tx_wr.opcode = IB_WR_SEND; + priv->tx_wr.sg_list = &priv->tx_sge; + priv->tx_wr.num_sge = 1; + priv->tx_wr.send_flags = IB_SEND_SIGNALED; return 0; diff --git a/drivers/infiniband/ulp/iser/Kconfig b/drivers/infiniband/ulp/iser/Kconfig index fe604c8d299..77dedba829e 100644 --- a/drivers/infiniband/ulp/iser/Kconfig +++ b/drivers/infiniband/ulp/iser/Kconfig @@ -8,5 +8,5 @@ config INFINIBAND_ISER that speak iSCSI over iSER over InfiniBand. The iSER protocol is defined by IETF. - See <http://www.ietf.org/internet-drafts/draft-ietf-ips-iser-05.txt> - and <http://www.infinibandta.org/members/spec/iser_annex_060418.pdf> + See <http://www.ietf.org/rfc/rfc5046.txt> + and <http://www.infinibandta.org/members/spec/Annex_iSER.PDF> diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index bad8dacafd1..dfa5a454418 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -551,6 +551,7 @@ static struct scsi_host_template iscsi_iser_sht = { .module = THIS_MODULE, .name = "iSCSI Initiator over iSER, v." DRV_VER, .queuecommand = iscsi_queuecommand, + .change_queue_depth = iscsi_change_queue_depth, .can_queue = ISCSI_DEF_XMIT_CMDS_MAX - 1, .sg_tablesize = ISCSI_ISER_SG_TABLESIZE, .max_sectors = 1024, diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index a6f2303ed14..ba1b455949c 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -561,7 +561,7 @@ void iser_rcv_completion(struct iser_desc *rx_desc, if (opcode == ISCSI_OP_SCSI_CMD_RSP) { itt = get_itt(hdr->itt); /* mask out cid and age bits */ if (!(itt < session->cmds_max)) - iser_err("itt can't be matched to task!!!" + iser_err("itt can't be matched to task!!! " "conn %p opcode %d cmds_max %d itt %d\n", conn->iscsi_conn,opcode,session->cmds_max,itt); /* use the mapping given with the cmds array indexed by itt */ diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 654a4dce023..714b8db02b2 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -105,7 +105,7 @@ pd_err: } /** - * iser_free_device_ib_res - destory/dealloc/dereg the DMA MR, + * iser_free_device_ib_res - destroy/dealloc/dereg the DMA MR, * CQ and PD created with the device associated with the adapator. */ static void iser_free_device_ib_res(struct iser_device *device) @@ -475,13 +475,11 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve iser_disconnected_handler(cma_id); break; case RDMA_CM_EVENT_DEVICE_REMOVAL: + iser_err("Device removal is currently unsupported\n"); BUG(); break; - case RDMA_CM_EVENT_CONNECT_RESPONSE: - BUG(); - break; - case RDMA_CM_EVENT_CONNECT_REQUEST: default: + iser_err("Unexpected RDMA CM event (%d)\n", event->event); break; } return ret; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index bdb6f851740..f2d2c7e2c76 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -272,7 +272,8 @@ static void srp_path_rec_completion(int status, target->status = status; if (status) - printk(KERN_ERR PFX "Got failed path rec status %d\n", status); + shost_printk(KERN_ERR, target->scsi_host, + PFX "Got failed path rec status %d\n", status); else target->path = *pathrec; complete(&target->done); @@ -303,7 +304,8 @@ static int srp_lookup_path(struct srp_target_port *target) wait_for_completion(&target->done); if (target->status < 0) - printk(KERN_WARNING PFX "Path record query failed\n"); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Path record query failed\n"); return target->status; } @@ -379,9 +381,10 @@ static int srp_send_req(struct srp_target_port *target) * the second 8 bytes to the local node GUID. */ if (srp_target_is_topspin(target)) { - printk(KERN_DEBUG PFX "Topspin/Cisco initiator port ID workaround " - "activated for target GUID %016llx\n", - (unsigned long long) be64_to_cpu(target->ioc_guid)); + shost_printk(KERN_DEBUG, target->scsi_host, + PFX "Topspin/Cisco initiator port ID workaround " + "activated for target GUID %016llx\n", + (unsigned long long) be64_to_cpu(target->ioc_guid)); memset(req->priv.initiator_port_id, 0, 8); memcpy(req->priv.initiator_port_id + 8, &target->srp_host->dev->dev->node_guid, 8); @@ -400,7 +403,8 @@ static void srp_disconnect_target(struct srp_target_port *target) init_completion(&target->done); if (ib_send_cm_dreq(target->cm_id, NULL, 0)) { - printk(KERN_DEBUG PFX "Sending CM DREQ failed\n"); + shost_printk(KERN_DEBUG, target->scsi_host, + PFX "Sending CM DREQ failed\n"); return; } wait_for_completion(&target->done); @@ -568,7 +572,8 @@ static int srp_reconnect_target(struct srp_target_port *target) return ret; err: - printk(KERN_ERR PFX "reconnect failed (%d), removing target port.\n", ret); + shost_printk(KERN_ERR, target->scsi_host, + PFX "reconnect failed (%d), removing target port.\n", ret); /* * We couldn't reconnect, so kill our target port off. @@ -683,8 +688,9 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target, if (scmnd->sc_data_direction != DMA_FROM_DEVICE && scmnd->sc_data_direction != DMA_TO_DEVICE) { - printk(KERN_WARNING PFX "Unhandled data direction %d\n", - scmnd->sc_data_direction); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Unhandled data direction %d\n", + scmnd->sc_data_direction); return -EINVAL; } @@ -786,8 +792,9 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp) } else { scmnd = req->scmnd; if (!scmnd) - printk(KERN_ERR "Null scmnd for RSP w/tag %016llx\n", - (unsigned long long) rsp->tag); + shost_printk(KERN_ERR, target->scsi_host, + "Null scmnd for RSP w/tag %016llx\n", + (unsigned long long) rsp->tag); scmnd->result = rsp->status; if (rsp->flags & SRP_RSP_FLAG_SNSVALID) { @@ -831,7 +838,8 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) if (0) { int i; - printk(KERN_ERR PFX "recv completion, opcode 0x%02x\n", opcode); + shost_printk(KERN_ERR, target->scsi_host, + PFX "recv completion, opcode 0x%02x\n", opcode); for (i = 0; i < wc->byte_len; ++i) { if (i % 8 == 0) @@ -852,11 +860,13 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) case SRP_T_LOGOUT: /* XXX Handle target logout */ - printk(KERN_WARNING PFX "Got target logout request\n"); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Got target logout request\n"); break; default: - printk(KERN_WARNING PFX "Unhandled SRP opcode 0x%02x\n", opcode); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Unhandled SRP opcode 0x%02x\n", opcode); break; } @@ -872,9 +882,10 @@ static void srp_completion(struct ib_cq *cq, void *target_ptr) ib_req_notify_cq(cq, IB_CQ_NEXT_COMP); while (ib_poll_cq(cq, 1, &wc) > 0) { if (wc.status) { - printk(KERN_ERR PFX "failed %s status %d\n", - wc.wr_id & SRP_OP_RECV ? "receive" : "send", - wc.status); + shost_printk(KERN_ERR, target->scsi_host, + PFX "failed %s status %d\n", + wc.wr_id & SRP_OP_RECV ? "receive" : "send", + wc.status); target->qp_in_error = 1; break; } @@ -930,13 +941,18 @@ static int srp_post_recv(struct srp_target_port *target) * req_lim and tx_head. Lock cannot be dropped between call here and * call to __srp_post_send(). */ -static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target) +static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target, + enum srp_request_type req_type) { + s32 min = (req_type == SRP_REQ_TASK_MGMT) ? 1 : 2; + if (target->tx_head - target->tx_tail >= SRP_SQ_SIZE) return NULL; - if (unlikely(target->req_lim < 1)) + if (target->req_lim < min) { ++target->zero_req_lim; + return NULL; + } return target->tx_ring[target->tx_head & SRP_SQ_SIZE]; } @@ -993,7 +1009,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, return 0; } - iu = __srp_get_tx_iu(target); + iu = __srp_get_tx_iu(target, SRP_REQ_NORMAL); if (!iu) goto err; @@ -1022,12 +1038,13 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, len = srp_map_data(scmnd, target, req); if (len < 0) { - printk(KERN_ERR PFX "Failed to map data\n"); + shost_printk(KERN_ERR, target->scsi_host, + PFX "Failed to map data\n"); goto err; } if (__srp_post_recv(target)) { - printk(KERN_ERR PFX "Recv failed\n"); + shost_printk(KERN_ERR, target->scsi_host, PFX "Recv failed\n"); goto err_unmap; } @@ -1035,7 +1052,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, DMA_TO_DEVICE); if (__srp_post_send(target, iu, len)) { - printk(KERN_ERR PFX "Send failed\n"); + shost_printk(KERN_ERR, target->scsi_host, PFX "Send failed\n"); goto err_unmap; } @@ -1090,6 +1107,7 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event, struct srp_target_port *target) { + struct Scsi_Host *shost = target->scsi_host; struct ib_class_port_info *cpi; int opcode; @@ -1115,19 +1133,22 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, memcpy(target->path.dgid.raw, event->param.rej_rcvd.ari, 16); - printk(KERN_DEBUG PFX "Topspin/Cisco redirect to target port GID %016llx%016llx\n", - (unsigned long long) be64_to_cpu(target->path.dgid.global.subnet_prefix), - (unsigned long long) be64_to_cpu(target->path.dgid.global.interface_id)); + shost_printk(KERN_DEBUG, shost, + PFX "Topspin/Cisco redirect to target port GID %016llx%016llx\n", + (unsigned long long) be64_to_cpu(target->path.dgid.global.subnet_prefix), + (unsigned long long) be64_to_cpu(target->path.dgid.global.interface_id)); target->status = SRP_PORT_REDIRECT; } else { - printk(KERN_WARNING " REJ reason: IB_CM_REJ_PORT_REDIRECT\n"); + shost_printk(KERN_WARNING, shost, + " REJ reason: IB_CM_REJ_PORT_REDIRECT\n"); target->status = -ECONNRESET; } break; case IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID: - printk(KERN_WARNING " REJ reason: IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID\n"); + shost_printk(KERN_WARNING, shost, + " REJ reason: IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID\n"); target->status = -ECONNRESET; break; @@ -1138,20 +1159,21 @@ static void srp_cm_rej_handler(struct ib_cm_id *cm_id, u32 reason = be32_to_cpu(rej->reason); if (reason == SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE) - printk(KERN_WARNING PFX - "SRP_LOGIN_REJ: requested max_it_iu_len too large\n"); + shost_printk(KERN_WARNING, shost, + PFX "SRP_LOGIN_REJ: requested max_it_iu_len too large\n"); else - printk(KERN_WARNING PFX - "SRP LOGIN REJECTED, reason 0x%08x\n", reason); + shost_printk(KERN_WARNING, shost, + PFX "SRP LOGIN REJECTED, reason 0x%08x\n", reason); } else - printk(KERN_WARNING " REJ reason: IB_CM_REJ_CONSUMER_DEFINED," - " opcode 0x%02x\n", opcode); + shost_printk(KERN_WARNING, shost, + " REJ reason: IB_CM_REJ_CONSUMER_DEFINED," + " opcode 0x%02x\n", opcode); target->status = -ECONNRESET; break; default: - printk(KERN_WARNING " REJ reason 0x%x\n", - event->param.rej_rcvd.reason); + shost_printk(KERN_WARNING, shost, " REJ reason 0x%x\n", + event->param.rej_rcvd.reason); target->status = -ECONNRESET; } } @@ -1166,7 +1188,8 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) switch (event->event) { case IB_CM_REQ_ERROR: - printk(KERN_DEBUG PFX "Sending CM REQ failed\n"); + shost_printk(KERN_DEBUG, target->scsi_host, + PFX "Sending CM REQ failed\n"); comp = 1; target->status = -ECONNRESET; break; @@ -1184,7 +1207,8 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) target->scsi_host->can_queue = min(target->req_lim, target->scsi_host->can_queue); } else { - printk(KERN_WARNING PFX "Unhandled RSP opcode %#x\n", opcode); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Unhandled RSP opcode %#x\n", opcode); target->status = -ECONNRESET; break; } @@ -1230,20 +1254,23 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) break; case IB_CM_REJ_RECEIVED: - printk(KERN_DEBUG PFX "REJ received\n"); + shost_printk(KERN_DEBUG, target->scsi_host, PFX "REJ received\n"); comp = 1; srp_cm_rej_handler(cm_id, event, target); break; case IB_CM_DREQ_RECEIVED: - printk(KERN_WARNING PFX "DREQ received - connection closed\n"); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "DREQ received - connection closed\n"); if (ib_send_cm_drep(cm_id, NULL, 0)) - printk(KERN_ERR PFX "Sending CM DREP failed\n"); + shost_printk(KERN_ERR, target->scsi_host, + PFX "Sending CM DREP failed\n"); break; case IB_CM_TIMEWAIT_EXIT: - printk(KERN_ERR PFX "connection closed\n"); + shost_printk(KERN_ERR, target->scsi_host, + PFX "connection closed\n"); comp = 1; target->status = 0; @@ -1255,7 +1282,8 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) break; default: - printk(KERN_WARNING PFX "Unhandled CM event %d\n", event->event); + shost_printk(KERN_WARNING, target->scsi_host, + PFX "Unhandled CM event %d\n", event->event); break; } @@ -1283,7 +1311,7 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target, init_completion(&req->done); - iu = __srp_get_tx_iu(target); + iu = __srp_get_tx_iu(target, SRP_REQ_TASK_MGMT); if (!iu) goto out; @@ -1332,7 +1360,7 @@ static int srp_abort(struct scsi_cmnd *scmnd) struct srp_request *req; int ret = SUCCESS; - printk(KERN_ERR "SRP abort called\n"); + shost_printk(KERN_ERR, target->scsi_host, "SRP abort called\n"); if (target->qp_in_error) return FAILED; @@ -1362,7 +1390,7 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_request *req, *tmp; - printk(KERN_ERR "SRP reset_device called\n"); + shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); if (target->qp_in_error) return FAILED; @@ -1389,7 +1417,7 @@ static int srp_reset_host(struct scsi_cmnd *scmnd) struct srp_target_port *target = host_to_target(scmnd->device->host); int ret = FAILED; - printk(KERN_ERR PFX "SRP reset_host called\n"); + shost_printk(KERN_ERR, target->scsi_host, PFX "SRP reset_host called\n"); if (!srp_reconnect_target(target)) ret = SUCCESS; @@ -1543,6 +1571,7 @@ static struct scsi_host_template srp_template = { .this_id = -1, .cmd_per_lun = SRP_SQ_SIZE, .use_clustering = ENABLE_CLUSTERING, + .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = srp_host_attrs }; @@ -1814,8 +1843,9 @@ static ssize_t srp_create_target(struct class_device *class_dev, ib_get_cached_gid(host->dev->dev, host->port, 0, &target->path.sgid); - printk(KERN_DEBUG PFX "new target: id_ext %016llx ioc_guid %016llx pkey %04x " - "service_id %016llx dgid %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + shost_printk(KERN_DEBUG, target->scsi_host, PFX + "new target: id_ext %016llx ioc_guid %016llx pkey %04x " + "service_id %016llx dgid %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", (unsigned long long) be64_to_cpu(target->id_ext), (unsigned long long) be64_to_cpu(target->ioc_guid), be16_to_cpu(target->path.pkey), @@ -1842,7 +1872,8 @@ static ssize_t srp_create_target(struct class_device *class_dev, target->qp_in_error = 0; ret = srp_connect_target(target); if (ret) { - printk(KERN_ERR PFX "Connection failed\n"); + shost_printk(KERN_ERR, target->scsi_host, + PFX "Connection failed\n"); goto err_cm_id; } diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index e3573e7038c..4a3c1f37e4c 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -79,6 +79,11 @@ enum srp_target_state { SRP_TARGET_REMOVED }; +enum srp_request_type { + SRP_REQ_NORMAL, + SRP_REQ_TASK_MGMT, +}; + struct srp_device { struct list_head dev_list; struct ib_device *dev; |