Merge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband

* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband: (29 commits)
  IB/mthca: Simplify use of size0 in work request posting
  IB/mthca: Factor out setting WQE UD segment entries
  IB/mthca: Factor out setting WQE remote address and atomic segment entries
  IB/mlx4: Factor out setting other WQE segments
  IB/mlx4: Factor out setting WQE data segment entries
  IB/mthca: Factor out setting WQE data segment entries
  IB/mlx4: Return receive queue sizes for userspace QPs from query QP
  IB/mlx4: Increase max outstanding RDMA reads as target
  RDMA/cma: Remove local write permission from QP access flags
  IB/mthca: Use uninitialized_var() for f0
  IB/cm: Make internal function cm_get_ack_delay() static
  IB/ipath: Remove ipath_get_user_pages_nocopy()
  IB/ipath: Make a few functions static
  mlx4_core: Reset device when internal error is detected
  IB/iser: Make a couple of functions static
  IB/mthca: Fix printk format used for firmware version in warning
  IB/mthca: Schedule MSI support for removal
  IB/ehca: Fix warnings issued by checkpatch.pl
  IB/ehca: Restructure ehca_set_pagebuf()
  IB/ehca: MR/MW structure refactoring
  ...

Documentation/feature-removal-schedule.txt

@@ -310,3 +310,13 @@ Why:  The arch/powerpc tree is the merged architecture for ppc32 and ppc64
 Who:  linuxppc-dev@ozlabs.org
 
 ---------------------------
+
+What:	mthca driver's MSI support
+When:	January 2008
+Files:	drivers/infiniband/hw/mthca/*.[ch]
+Why:	All mthca hardware also supports MSI-X, which provides
+	strictly more functionality than MSI.  So there is no point in
+	having both MSI-X and MSI support in the driver.
+Who:	Roland Dreier <rolandd@cisco.com>
+
+---------------------------

drivers/infiniband/core/cm.c

@@ -3374,7 +3374,7 @@ int ib_cm_init_qp_attr(struct ib_cm_id *cm_id,
 }
 EXPORT_SYMBOL(ib_cm_init_qp_attr);
 
-void cm_get_ack_delay(struct cm_device *cm_dev)
+static void cm_get_ack_delay(struct cm_device *cm_dev)
 {
 	struct ib_device_attr attr;
 

drivers/infiniband/core/cma.c

@@ -573,7 +573,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 		break;
 	case RDMA_TRANSPORT_IWARP:
 		if (!id_priv->cm_id.iw) {
-			qp_attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE;
+			qp_attr->qp_access_flags = 0;
 			*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS;
 		} else
 			ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr,

drivers/infiniband/hw/cxgb3/iwch_cm.c

@@ -1914,6 +1914,7 @@ int iwch_create_listen(struct iw_cm_id *cm_id, int backlog)
 fail3:
 	cxgb3_free_stid(ep->com.tdev, ep->stid);
 fail2:
+	cm_id->rem_ref(cm_id);
 	put_ep(&ep->com);
 fail1:
 out:

drivers/infiniband/hw/ehca/ehca_classes.h

@@ -204,8 +204,8 @@ struct ehca_mr {
 	spinlock_t mrlock;
 
 	enum ehca_mr_flag flags;
-	u32 num_pages;		/* number of MR pages */
-	u32 num_4k;		/* number of 4k "page" portions to form MR */
+	u32 num_kpages;		/* number of kernel pages */
+	u32 num_hwpages;	/* number of hw pages to form MR */
 	int acl;		/* ACL (stored here for usage in reregister) */
 	u64 *start;		/* virtual start address (stored here for */
 				/* usage in reregister) */
@@ -217,9 +217,6 @@ struct ehca_mr {
 	/* fw specific data */
 	struct ipz_mrmw_handle ipz_mr_handle;	/* MR handle for h-calls */
 	struct h_galpas galpas;
-	/* data for userspace bridge */
-	u32 nr_of_pages;
-	void *pagearray;
 };
 
 struct ehca_mw {
@@ -241,26 +238,29 @@ enum ehca_mr_pgi_type {
 
 struct ehca_mr_pginfo {
 	enum ehca_mr_pgi_type type;
-	u64 num_pages;
-	u64 page_cnt;
-	u64 num_4k;       /* number of 4k "page" portions */
-	u64 page_4k_cnt;  /* counter for 4k "page" portions */
-	u64 next_4k;      /* next 4k "page" portion in buffer/chunk/listelem */
+	u64 num_kpages;
+	u64 kpage_cnt;
+	u64 num_hwpages;     /* number of hw pages */
+	u64 hwpage_cnt;      /* counter for hw pages */
+	u64 next_hwpage;     /* next hw page in buffer/chunk/listelem */
 
-	/* type EHCA_MR_PGI_PHYS section */
+	union {
+		struct { /* type EHCA_MR_PGI_PHYS section */
 			int num_phys_buf;
 			struct ib_phys_buf *phys_buf_array;
 			u64 next_buf;
-
-	/* type EHCA_MR_PGI_USER section */
+		} phy;
+		struct { /* type EHCA_MR_PGI_USER section */
 			struct ib_umem *region;
 			struct ib_umem_chunk *next_chunk;
 			u64 next_nmap;
-
-	/* type EHCA_MR_PGI_FMR section */
+		} usr;
+		struct { /* type EHCA_MR_PGI_FMR section */
+			u64 fmr_pgsize;
 			u64 *page_list;
 			u64 next_listelem;
-	/* next_4k also used within EHCA_MR_PGI_FMR */
+		} fmr;
+	} u;
 };
 
 /* output parameters for MR/FMR hipz calls */
@@ -391,6 +391,6 @@ struct ehca_alloc_qp_parms {
 
 int ehca_cq_assign_qp(struct ehca_cq *cq, struct ehca_qp *qp);
 int ehca_cq_unassign_qp(struct ehca_cq *cq, unsigned int qp_num);
-struct ehca_qp* ehca_cq_get_qp(struct ehca_cq *cq, int qp_num);
+struct ehca_qp *ehca_cq_get_qp(struct ehca_cq *cq, int qp_num);
 
 #endif

drivers/infiniband/hw/ehca/ehca_cq.c

@@ -97,7 +97,7 @@ int ehca_cq_unassign_qp(struct ehca_cq *cq, unsigned int real_qp_num)
 	return ret;
 }
 
-struct ehca_qp* ehca_cq_get_qp(struct ehca_cq *cq, int real_qp_num)
+struct ehca_qp *ehca_cq_get_qp(struct ehca_cq *cq, int real_qp_num)
 {
 	struct ehca_qp *ret = NULL;
 	unsigned int key = real_qp_num & (QP_HASHTAB_LEN-1);

drivers/infiniband/hw/ehca/ehca_eq.c

@@ -96,7 +96,8 @@ int ehca_create_eq(struct ehca_shca *shca,
 	for (i = 0; i < nr_pages; i++) {
 		u64 rpage;
 
-		if (!(vpage = ipz_qpageit_get_inc(&eq->ipz_queue))) {
+		vpage = ipz_qpageit_get_inc(&eq->ipz_queue);
+		if (!vpage) {
 			ret = H_RESOURCE;
 			goto create_eq_exit2;
 		}

drivers/infiniband/hw/ehca/ehca_hca.c

@@ -127,6 +127,7 @@ int ehca_query_port(struct ib_device *ibdev,
 		    u8 port, struct ib_port_attr *props)
 {
 	int ret = 0;
+	u64 h_ret;
 	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca,
 					      ib_device);
 	struct hipz_query_port *rblock;
@@ -137,7 +138,8 @@ int ehca_query_port(struct ib_device *ibdev,
 		return -ENOMEM;
 	}
 
-	if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) {
+	h_ret = hipz_h_query_port(shca->ipz_hca_handle, port, rblock);
+	if (h_ret != H_SUCCESS) {
 		ehca_err(&shca->ib_device, "Can't query port properties");
 		ret = -EINVAL;
 		goto query_port1;
@@ -197,6 +199,7 @@ int ehca_query_sma_attr(struct ehca_shca *shca,
 			u8 port, struct ehca_sma_attr *attr)
 {
 	int ret = 0;
+	u64 h_ret;
 	struct hipz_query_port *rblock;
 
 	rblock = ehca_alloc_fw_ctrlblock(GFP_ATOMIC);
@@ -205,7 +208,8 @@ int ehca_query_sma_attr(struct ehca_shca *shca,
 		return -ENOMEM;
 	}
 
-	if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) {
+	h_ret = hipz_h_query_port(shca->ipz_hca_handle, port, rblock);
+	if (h_ret != H_SUCCESS) {
 		ehca_err(&shca->ib_device, "Can't query port properties");
 		ret = -EINVAL;
 		goto query_sma_attr1;
@@ -230,9 +234,11 @@ int ehca_query_sma_attr(struct ehca_shca *shca,
 int ehca_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
 {
 	int ret = 0;
-	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca, ib_device);
+	u64 h_ret;
+	struct ehca_shca *shca;
 	struct hipz_query_port *rblock;
 
+	shca = container_of(ibdev, struct ehca_shca, ib_device);
 	if (index > 16) {
 		ehca_err(&shca->ib_device, "Invalid index: %x.", index);
 		return -EINVAL;
@@ -244,7 +250,8 @@ int ehca_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
 		return -ENOMEM;
 	}
 
-	if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) {
+	h_ret = hipz_h_query_port(shca->ipz_hca_handle, port, rblock);
+	if (h_ret != H_SUCCESS) {
 		ehca_err(&shca->ib_device, "Can't query port properties");
 		ret = -EINVAL;
 		goto query_pkey1;
@@ -262,6 +269,7 @@ int ehca_query_gid(struct ib_device *ibdev, u8 port,
 		   int index, union ib_gid *gid)
 {
 	int ret = 0;
+	u64 h_ret;
 	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca,
 					      ib_device);
 	struct hipz_query_port *rblock;
@@ -277,7 +285,8 @@ int ehca_query_gid(struct ib_device *ibdev, u8 port,
 		return -ENOMEM;
 	}
 
-	if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) {
+	h_ret = hipz_h_query_port(shca->ipz_hca_handle, port, rblock);
+	if (h_ret != H_SUCCESS) {
 		ehca_err(&shca->ib_device, "Can't query port properties");
 		ret = -EINVAL;
 		goto query_gid1;
@@ -302,11 +311,12 @@ int ehca_modify_port(struct ib_device *ibdev,
 		     struct ib_port_modify *props)
 {
 	int ret = 0;
-	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca, ib_device);
+	struct ehca_shca *shca;
 	struct hipz_query_port *rblock;
 	u32 cap;
 	u64 hret;
 
+	shca = container_of(ibdev, struct ehca_shca, ib_device);
 	if ((props->set_port_cap_mask | props->clr_port_cap_mask)
 	    & ~allowed_port_caps) {
 		ehca_err(&shca->ib_device, "Non-changeable bits set in masks  "
@@ -325,7 +335,8 @@ int ehca_modify_port(struct ib_device *ibdev,
 		goto modify_port1;
 	}
 
-	if (hipz_h_query_port(shca->ipz_hca_handle, port, rblock) != H_SUCCESS) {
+	hret = hipz_h_query_port(shca->ipz_hca_handle, port, rblock);
+	if (hret != H_SUCCESS) {
 		ehca_err(&shca->ib_device, "Can't query port properties");
 		ret = -EINVAL;
 		goto modify_port2;
@@ -337,7 +348,8 @@ int ehca_modify_port(struct ib_device *ibdev,
 	hret = hipz_h_modify_port(shca->ipz_hca_handle, port,
 				  cap, props->init_type, port_modify_mask);
 	if (hret != H_SUCCESS) {
-		ehca_err(&shca->ib_device, "Modify port failed  hret=%lx", hret);
+		ehca_err(&shca->ib_device, "Modify port failed  hret=%lx",
+			 hret);
 		ret = -EINVAL;
 	}
 

drivers/infiniband/hw/ehca/ehca_irq.c

@@ -49,26 +49,26 @@
 #include "hipz_fns.h"
 #include "ipz_pt_fn.h"
 
-#define EQE_COMPLETION_EVENT   EHCA_BMASK_IBM(1,1)
-#define EQE_CQ_QP_NUMBER       EHCA_BMASK_IBM(8,31)
-#define EQE_EE_IDENTIFIER      EHCA_BMASK_IBM(2,7)
-#define EQE_CQ_NUMBER          EHCA_BMASK_IBM(8,31)
-#define EQE_QP_NUMBER          EHCA_BMASK_IBM(8,31)
-#define EQE_QP_TOKEN           EHCA_BMASK_IBM(32,63)
-#define EQE_CQ_TOKEN           EHCA_BMASK_IBM(32,63)
-
-#define NEQE_COMPLETION_EVENT  EHCA_BMASK_IBM(1,1)
-#define NEQE_EVENT_CODE        EHCA_BMASK_IBM(2,7)
-#define NEQE_PORT_NUMBER       EHCA_BMASK_IBM(8,15)
-#define NEQE_PORT_AVAILABILITY EHCA_BMASK_IBM(16,16)
-#define NEQE_DISRUPTIVE        EHCA_BMASK_IBM(16,16)
-
-#define ERROR_DATA_LENGTH      EHCA_BMASK_IBM(52,63)
-#define ERROR_DATA_TYPE        EHCA_BMASK_IBM(0,7)
+#define EQE_COMPLETION_EVENT   EHCA_BMASK_IBM( 1,  1)
+#define EQE_CQ_QP_NUMBER       EHCA_BMASK_IBM( 8, 31)
+#define EQE_EE_IDENTIFIER      EHCA_BMASK_IBM( 2,  7)
+#define EQE_CQ_NUMBER          EHCA_BMASK_IBM( 8, 31)
+#define EQE_QP_NUMBER          EHCA_BMASK_IBM( 8, 31)
+#define EQE_QP_TOKEN           EHCA_BMASK_IBM(32, 63)
+#define EQE_CQ_TOKEN           EHCA_BMASK_IBM(32, 63)
+
+#define NEQE_COMPLETION_EVENT  EHCA_BMASK_IBM( 1,  1)
+#define NEQE_EVENT_CODE        EHCA_BMASK_IBM( 2,  7)
+#define NEQE_PORT_NUMBER       EHCA_BMASK_IBM( 8, 15)
+#define NEQE_PORT_AVAILABILITY EHCA_BMASK_IBM(16, 16)
+#define NEQE_DISRUPTIVE        EHCA_BMASK_IBM(16, 16)
+
+#define ERROR_DATA_LENGTH      EHCA_BMASK_IBM(52, 63)
+#define ERROR_DATA_TYPE        EHCA_BMASK_IBM( 0,  7)
 
 static void queue_comp_task(struct ehca_cq *__cq);
 
-static struct ehca_comp_pool* pool;
+static struct ehca_comp_pool *pool;
 #ifdef CONFIG_HOTPLUG_CPU
 static struct notifier_block comp_pool_callback_nb;
 #endif
@@ -85,8 +85,8 @@ static inline void comp_event_callback(struct ehca_cq *cq)
 	return;
 }
 
-static void print_error_data(struct ehca_shca * shca, void* data,
-			     u64* rblock, int length)
+static void print_error_data(struct ehca_shca *shca, void *data,
+			     u64 *rblock, int length)
 {
 	u64 type = EHCA_BMASK_GET(ERROR_DATA_TYPE, rblock[2]);
 	u64 resource = rblock[1];
@@ -94,7 +94,7 @@ static void print_error_data(struct ehca_shca * shca, void* data,
 	switch (type) {
 	case 0x1: /* Queue Pair */
 	{
-		struct ehca_qp *qp = (struct ehca_qp*)data;
+		struct ehca_qp *qp = (struct ehca_qp *)data;
 
 		/* only print error data if AER is set */
 		if (rblock[6] == 0)
@@ -107,7 +107,7 @@ static void print_error_data(struct ehca_shca * shca, void* data,
 	}
 	case 0x4: /* Completion Queue */
 	{
-		struct ehca_cq *cq = (struct ehca_cq*)data;
+		struct ehca_cq *cq = (struct ehca_cq *)data;
 
 		ehca_err(&shca->ib_device,
 			 "CQ 0x%x (resource=%lx) has errors.",
@@ -572,7 +572,7 @@ void ehca_tasklet_eq(unsigned long data)
 	ehca_process_eq((struct ehca_shca*)data, 1);
 }
 
-static inline int find_next_online_cpu(struct ehca_comp_pool* pool)
+static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 {
 	int cpu;
 	unsigned long flags;
@@ -636,7 +636,7 @@ static void queue_comp_task(struct ehca_cq *__cq)
 	__queue_comp_task(__cq, cct);
 }
 
-static void run_comp_task(struct ehca_cpu_comp_task* cct)
+static void run_comp_task(struct ehca_cpu_comp_task *cct)
 {
 	struct ehca_cq *cq;
 	unsigned long flags;
@@ -666,12 +666,12 @@ static void run_comp_task(struct ehca_cpu_comp_task* cct)
 
 static int comp_task(void *__cct)
 {
-	struct ehca_cpu_comp_task* cct = __cct;
+	struct ehca_cpu_comp_task *cct = __cct;
 	int cql_empty;
 	DECLARE_WAITQUEUE(wait, current);
 
 	set_current_state(TASK_INTERRUPTIBLE);
-	while(!kthread_should_stop()) {
+	while (!kthread_should_stop()) {
 		add_wait_queue(&cct->wait_queue, &wait);
 
 		spin_lock_irq(&cct->task_lock);
@@ -745,7 +745,7 @@ static void take_over_work(struct ehca_comp_pool *pool,
 
 	list_splice_init(&cct->cq_list, &list);
 
-	while(!list_empty(&list)) {
+	while (!list_empty(&list)) {
 		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
 
 		list_del(&cq->entry);
@@ -768,7 +768,7 @@ static int comp_pool_callback(struct notifier_block *nfb,
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
-		if(!create_comp_task(pool, cpu)) {
+		if (!create_comp_task(pool, cpu)) {
 			ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
 			return NOTIFY_BAD;
 		}
@@ -838,7 +838,7 @@ int ehca_create_comp_pool(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	comp_pool_callback_nb.notifier_call = comp_pool_callback;
-	comp_pool_callback_nb.priority =0;
+	comp_pool_callback_nb.priority = 0;
 	register_cpu_notifier(&comp_pool_callback_nb);
 #endif
 

drivers/infiniband/hw/ehca/ehca_iverbs.h

@@ -81,8 +81,9 @@ struct ib_mr *ehca_reg_phys_mr(struct ib_pd *pd,
 			       int num_phys_buf,
 			       int mr_access_flags, u64 *iova_start);
 
-struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt,
-			       int mr_access_flags, struct ib_udata *udata);
+struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+			       u64 virt, int mr_access_flags,
+			       struct ib_udata *udata);
 
 int ehca_rereg_phys_mr(struct ib_mr *mr,
 		       int mr_rereg_mask,
@@ -192,7 +193,7 @@ void ehca_poll_eqs(unsigned long data);
 void *ehca_alloc_fw_ctrlblock(gfp_t flags);
 void ehca_free_fw_ctrlblock(void *ptr);
 #else
-#define ehca_alloc_fw_ctrlblock(flags) ((void *) get_zeroed_page(flags))
+#define ehca_alloc_fw_ctrlblock(flags) ((void *)get_zeroed_page(flags))
 #define ehca_free_fw_ctrlblock(ptr) free_page((unsigned long)(ptr))
 #endif
 

drivers/infiniband/hw/ehca/ehca_main.c

@@ -107,7 +107,7 @@ static DEFINE_SPINLOCK(shca_list_lock);
 static struct timer_list poll_eqs_timer;
 
 #ifdef CONFIG_PPC_64K_PAGES
-static struct kmem_cache *ctblk_cache = NULL;
+static struct kmem_cache *ctblk_cache;
 
 void *ehca_alloc_fw_ctrlblock(gfp_t flags)
 {
@@ -200,8 +200,8 @@ static void ehca_destroy_slab_caches(void)
 #endif
 }
 
-#define EHCA_HCAAVER  EHCA_BMASK_IBM(32,39)
-#define EHCA_REVID    EHCA_BMASK_IBM(40,63)
+#define EHCA_HCAAVER  EHCA_BMASK_IBM(32, 39)
+#define EHCA_REVID    EHCA_BMASK_IBM(40, 63)
 
 static struct cap_descr {
 	u64 mask;
@@ -263,22 +263,27 @@ int ehca_sense_attributes(struct ehca_shca *shca)
 
 		ehca_gen_dbg(" ... hardware version=%x:%x", hcaaver, revid);
 
-		if ((hcaaver == 1) && (revid == 0))
-			shca->hw_level = 0x11;
-		else if ((hcaaver == 1) && (revid == 1))
-			shca->hw_level = 0x12;
-		else if ((hcaaver == 1) && (revid == 2))
-			shca->hw_level = 0x13;
-		else if ((hcaaver == 2) && (revid == 0))
+		if (hcaaver == 1) {
+			if (revid <= 3)
+				shca->hw_level = 0x10 | (revid + 1);
+			else
+				shca->hw_level = 0x14;
+		} else if (hcaaver == 2) {
+			if (revid == 0)
 				shca->hw_level = 0x21;
-		else if ((hcaaver == 2) && (revid == 0x10))
+			else if (revid == 0x10)
 				shca->hw_level = 0x22;
-		else {
+			else if (revid == 0x20 || revid == 0x21)
+				shca->hw_level = 0x23;
+		}
+
+		if (!shca->hw_level) {
 			ehca_gen_warn("unknown hardware version"
 				      " - assuming default level");
 			shca->hw_level = 0x22;
 		}
-	}
+	} else
+		shca->hw_level = ehca_hw_level;
 	ehca_gen_dbg(" ... hardware level=%x", shca->hw_level);
 
 	shca->sport[0].rate = IB_RATE_30_GBPS;
@@ -290,7 +295,7 @@ int ehca_sense_attributes(struct ehca_shca *shca)
 		if (EHCA_BMASK_GET(hca_cap_descr[i].mask, shca->hca_cap))
 			ehca_gen_dbg("   %s", hca_cap_descr[i].descr);
 
-	port = (struct hipz_query_port *) rblock;
+	port = (struct hipz_query_port *)rblock;
 	h_ret = hipz_h_query_port(shca->ipz_hca_handle, 1, port);
 	if (h_ret != H_SUCCESS) {
 		ehca_gen_err("Cannot query port properties. h_ret=%lx",
@@ -439,7 +444,7 @@ static int ehca_create_aqp1(struct ehca_shca *shca, u32 port)
 		return -EPERM;
 	}
 
-	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void*)(-1), 10, 0);
+	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void *)(-1), 10, 0);
 	if (IS_ERR(ibcq)) {
 		ehca_err(&shca->ib_device, "Cannot create AQP1 CQ.");
 		return PTR_ERR(ibcq);
@@ -666,7 +671,7 @@ static int __devinit ehca_probe(struct ibmebus_dev *dev,
 	}
 
 	/* create internal protection domain */
-	ibpd = ehca_alloc_pd(&shca->ib_device, (void*)(-1), NULL);
+	ibpd = ehca_alloc_pd(&shca->ib_device, (void *)(-1), NULL);
 	if (IS_ERR(ibpd)) {
 		ehca_err(&shca->ib_device, "Cannot create internal PD.");
 		ret = PTR_ERR(ibpd);
@@ -863,18 +868,21 @@ int __init ehca_module_init(void)
 	printk(KERN_INFO "eHCA Infiniband Device Driver "
 	       "(Rel.: SVNEHCA_0023)\n");
 
-	if ((ret = ehca_create_comp_pool())) {
+	ret = ehca_create_comp_pool();
+	if (ret) {
 		ehca_gen_err("Cannot create comp pool.");
 		return ret;
 	}
 
-	if ((ret = ehca_create_slab_caches())) {
+	ret = ehca_create_slab_caches();
+	if (ret) {
 		ehca_gen_err("Cannot create SLAB caches");
 		ret = -ENOMEM;
 		goto module_init1;
 	}
 
-	if ((ret = ibmebus_register_driver(&ehca_driver))) {
+	ret = ibmebus_register_driver(&ehca_driver);
+	if (ret) {
 		ehca_gen_err("Cannot register eHCA device driver");
 		ret = -EINVAL;
 		goto module_init2;

drivers/infiniband/hw/ehca/ehca_mrmw.h

@@ -101,15 +101,10 @@ int ehca_fmr_check_page_list(struct ehca_mr *e_fmr,
 			     u64 *page_list,
 			     int list_len);
 
-int ehca_set_pagebuf(struct ehca_mr *e_mr,
-		     struct ehca_mr_pginfo *pginfo,
+int ehca_set_pagebuf(struct ehca_mr_pginfo *pginfo,
 		     u32 number,
 		     u64 *kpage);
 
-int ehca_set_pagebuf_1(struct ehca_mr *e_mr,
-		       struct ehca_mr_pginfo *pginfo,
-		       u64 *rpage);
-
 int ehca_mr_is_maxmr(u64 size,
 		     u64 *iova_start);
 
@@ -121,20 +116,6 @@ void ehca_mrmw_set_pgsize_hipz_acl(u32 *hipz_acl);
 void ehca_mrmw_reverse_map_acl(const u32 *hipz_acl,
 			       int *ib_acl);
 
-int ehca_mrmw_map_hrc_alloc(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_rrpg_last(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_rrpg_notlast(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_query_mr(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_free_mr(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_free_mw(const u64 hipz_rc);
-
-int ehca_mrmw_map_hrc_reg_smr(const u64 hipz_rc);
-
 void ehca_mr_deletenew(struct ehca_mr *mr);
 
 #endif  /*_EHCA_MRMW_H_*/

drivers/infiniband/hw/ehca/ehca_qes.h

@@ -53,13 +53,13 @@ struct ehca_vsgentry {
 	u32 length;
 };
 
-#define GRH_FLAG_MASK        EHCA_BMASK_IBM(7,7)
-#define GRH_IPVERSION_MASK   EHCA_BMASK_IBM(0,3)
-#define GRH_TCLASS_MASK      EHCA_BMASK_IBM(4,12)
-#define GRH_FLOWLABEL_MASK   EHCA_BMASK_IBM(13,31)
-#define GRH_PAYLEN_MASK      EHCA_BMASK_IBM(32,47)
-#define GRH_NEXTHEADER_MASK  EHCA_BMASK_IBM(48,55)
-#define GRH_HOPLIMIT_MASK    EHCA_BMASK_IBM(56,63)
+#define GRH_FLAG_MASK        EHCA_BMASK_IBM( 7,  7)
+#define GRH_IPVERSION_MASK   EHCA_BMASK_IBM( 0,  3)
+#define GRH_TCLASS_MASK      EHCA_BMASK_IBM( 4, 12)
+#define GRH_FLOWLABEL_MASK   EHCA_BMASK_IBM(13, 31)
+#define GRH_PAYLEN_MASK      EHCA_BMASK_IBM(32, 47)
+#define GRH_NEXTHEADER_MASK  EHCA_BMASK_IBM(48, 55)
+#define GRH_HOPLIMIT_MASK    EHCA_BMASK_IBM(56, 63)
 
 /*
  * Unreliable Datagram Address Vector Format
@@ -206,10 +206,10 @@ struct ehca_wqe {
 
 };
 
-#define WC_SEND_RECEIVE EHCA_BMASK_IBM(0,0)
-#define WC_IMM_DATA     EHCA_BMASK_IBM(1,1)
-#define WC_GRH_PRESENT  EHCA_BMASK_IBM(2,2)
-#define WC_SE_BIT       EHCA_BMASK_IBM(3,3)
+#define WC_SEND_RECEIVE EHCA_BMASK_IBM(0, 0)
+#define WC_IMM_DATA     EHCA_BMASK_IBM(1, 1)
+#define WC_GRH_PRESENT  EHCA_BMASK_IBM(2, 2)
+#define WC_SE_BIT       EHCA_BMASK_IBM(3, 3)
 #define WC_STATUS_ERROR_BIT 0x80000000
 #define WC_STATUS_REMOTE_ERROR_FLAGS 0x0000F800
 #define WC_STATUS_PURGE_BIT 0x10

drivers/infiniband/hw/ehca/ehca_qp.c

@@ -602,10 +602,10 @@ struct ehca_qp *internal_create_qp(struct ib_pd *pd,
 			/* UD circumvention */
 			parms.act_nr_send_sges -= 2;
 			parms.act_nr_recv_sges -= 2;
-			swqe_size = offsetof(struct ehca_wqe,
-					     u.ud_av.sg_list[parms.act_nr_send_sges]);
-			rwqe_size = offsetof(struct ehca_wqe,
-					     u.ud_av.sg_list[parms.act_nr_recv_sges]);
+			swqe_size = offsetof(struct ehca_wqe, u.ud_av.sg_list[
+						     parms.act_nr_send_sges]);
+			rwqe_size = offsetof(struct ehca_wqe, u.ud_av.sg_list[
+						     parms.act_nr_recv_sges]);
 		}
 
 		if (IB_QPT_GSI == qp_type || IB_QPT_SMI == qp_type) {
@@ -690,8 +690,8 @@ struct ehca_qp *internal_create_qp(struct ib_pd *pd,
 	if (my_qp->send_cq) {
 		ret = ehca_cq_assign_qp(my_qp->send_cq, my_qp);
 		if (ret) {
-			ehca_err(pd->device, "Couldn't assign qp to send_cq ret=%x",
-				 ret);
+			ehca_err(pd->device,
+				 "Couldn't assign qp to send_cq ret=%x", ret);
 			goto create_qp_exit4;
 		}
 	}
@@ -749,7 +749,7 @@ struct ib_qp *ehca_create_qp(struct ib_pd *pd,
 	struct ehca_qp *ret;
 
 	ret = internal_create_qp(pd, qp_init_attr, NULL, udata, 0);
-	return IS_ERR(ret) ? (struct ib_qp *) ret : &ret->ib_qp;
+	return IS_ERR(ret) ? (struct ib_qp *)ret : &ret->ib_qp;
 }
 
 int internal_destroy_qp(struct ib_device *dev, struct ehca_qp *my_qp,
@@ -780,7 +780,7 @@ struct ib_srq *ehca_create_srq(struct ib_pd *pd,
 
 	my_qp = internal_create_qp(pd, &qp_init_attr, srq_init_attr, udata, 1);
 	if (IS_ERR(my_qp))
-		return (struct ib_srq *) my_qp;
+		return (struct ib_srq *)my_qp;
 
 	/* copy back return values */
 	srq_init_attr->attr.max_wr = qp_init_attr.cap.max_recv_wr;
@@ -875,7 +875,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 			 my_qp, qp_num, h_ret);
 		return ehca2ib_return_code(h_ret);
 	}
-	bad_send_wqe_p = (void*)((u64)bad_send_wqe_p & (~(1L<<63)));
+	bad_send_wqe_p = (void *)((u64)bad_send_wqe_p & (~(1L << 63)));
 	ehca_dbg(&shca->ib_device, "qp_num=%x bad_send_wqe_p=%p",
 		 qp_num, bad_send_wqe_p);
 	/* convert wqe pointer to vadr */
@@ -890,7 +890,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 	}
 
 	/* loop sets wqe's purge bit */
-	wqe = (struct ehca_wqe*)ipz_qeit_calc(squeue, q_ofs);
+	wqe = (struct ehca_wqe *)ipz_qeit_calc(squeue, q_ofs);
 	*bad_wqe_cnt = 0;
 	while (wqe->optype != 0xff && wqe->wqef != 0xff) {
 		if (ehca_debug_level)
@@ -898,7 +898,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 		wqe->nr_of_data_seg = 0; /* suppress data access */
 		wqe->wqef = WQEF_PURGE; /* WQE to be purged */
 		q_ofs = ipz_queue_advance_offset(squeue, q_ofs);
-		wqe = (struct ehca_wqe*)ipz_qeit_calc(squeue, q_ofs);
+		wqe = (struct ehca_wqe *)ipz_qeit_calc(squeue, q_ofs);
 		*bad_wqe_cnt = (*bad_wqe_cnt)+1;
 	}
 	/*
@@ -1003,7 +1003,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 		goto modify_qp_exit1;
 	}
 
-	ehca_dbg(ibqp->device,"ehca_qp=%p qp_num=%x current qp_state=%x "
+	ehca_dbg(ibqp->device, "ehca_qp=%p qp_num=%x current qp_state=%x "
 		 "new qp_state=%x attribute_mask=%x",
 		 my_qp, ibqp->qp_num, qp_cur_state, attr->qp_state, attr_mask);
 
@@ -1019,7 +1019,8 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 		goto modify_qp_exit1;
 	}
 
-	if ((mqpcb->qp_state = ib2ehca_qp_state(qp_new_state)))
+	mqpcb->qp_state = ib2ehca_qp_state(qp_new_state);
+	if (mqpcb->qp_state)
 		update_mask = EHCA_BMASK_SET(MQPCB_MASK_QP_STATE, 1);
 	else {
 		ret = -EINVAL;
@@ -1077,7 +1078,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 			spin_lock_irqsave(&my_qp->spinlock_s, flags);
 			squeue_locked = 1;
 			/* mark next free wqe */
-			wqe = (struct ehca_wqe*)
+			wqe = (struct ehca_wqe *)
 				ipz_qeit_get(&my_qp->ipz_squeue);
 			wqe->optype = wqe->wqef = 0xff;
 			ehca_dbg(ibqp->device, "qp_num=%x next_free_wqe=%p",
@@ -1312,7 +1313,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 	if (h_ret != H_SUCCESS) {
 		ret = ehca2ib_return_code(h_ret);
 		ehca_err(ibqp->device, "hipz_h_modify_qp() failed rc=%lx "
-			 "ehca_qp=%p qp_num=%x",h_ret, my_qp, ibqp->qp_num);
+			 "ehca_qp=%p qp_num=%x", h_ret, my_qp, ibqp->qp_num);
 		goto modify_qp_exit2;
 	}
 
@@ -1411,7 +1412,7 @@ int ehca_query_qp(struct ib_qp *qp,
 	}
 
 	if (qp_attr_mask & QP_ATTR_QUERY_NOT_SUPPORTED) {
-		ehca_err(qp->device,"Invalid attribute mask "
+		ehca_err(qp->device, "Invalid attribute mask "
 			 "ehca_qp=%p qp_num=%x qp_attr_mask=%x ",
 			 my_qp, qp->qp_num, qp_attr_mask);
 		return -EINVAL;
@@ -1419,7 +1420,7 @@ int ehca_query_qp(struct ib_qp *qp,
 
 	qpcb = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!qpcb) {
-		ehca_err(qp->device,"Out of memory for qpcb "
+		ehca_err(qp->device, "Out of memory for qpcb "
 			 "ehca_qp=%p qp_num=%x", my_qp, qp->qp_num);
 		return -ENOMEM;
 	}
@@ -1431,7 +1432,7 @@ int ehca_query_qp(struct ib_qp *qp,
 
 	if (h_ret != H_SUCCESS) {
 		ret = ehca2ib_return_code(h_ret);
-		ehca_err(qp->device,"hipz_h_query_qp() failed "
+		ehca_err(qp->device, "hipz_h_query_qp() failed "
 			 "ehca_qp=%p qp_num=%x h_ret=%lx",
 			 my_qp, qp->qp_num, h_ret);
 		goto query_qp_exit1;
@@ -1442,7 +1443,7 @@ int ehca_query_qp(struct ib_qp *qp,
 
 	if (qp_attr->cur_qp_state == -EINVAL) {
 		ret = -EINVAL;
-		ehca_err(qp->device,"Got invalid ehca_qp_state=%x "
+		ehca_err(qp->device, "Got invalid ehca_qp_state=%x "
 			 "ehca_qp=%p qp_num=%x",
 			 qpcb->qp_state, my_qp, qp->qp_num);
 		goto query_qp_exit1;

drivers/infiniband/hw/ehca/ehca_reqs.c

@@ -79,7 +79,8 @@ static inline int ehca_write_rwqe(struct ipz_queue *ipz_rqueue,
 	}
 
 	if (ehca_debug_level) {
-		ehca_gen_dbg("RECEIVE WQE written into ipz_rqueue=%p", ipz_rqueue);
+		ehca_gen_dbg("RECEIVE WQE written into ipz_rqueue=%p",
+			     ipz_rqueue);
 		ehca_dmp( wqe_p, 16*(6 + wqe_p->nr_of_data_seg), "recv wqe");
 	}
 
@@ -99,7 +100,7 @@ static void trace_send_wr_ud(const struct ib_send_wr *send_wr)
 		struct ib_mad_hdr *mad_hdr = send_wr->wr.ud.mad_hdr;
 		struct ib_sge *sge = send_wr->sg_list;
 		ehca_gen_dbg("send_wr#%x wr_id=%lx num_sge=%x "
-			     "send_flags=%x opcode=%x",idx, send_wr->wr_id,
+			     "send_flags=%x opcode=%x", idx, send_wr->wr_id,
 			     send_wr->num_sge, send_wr->send_flags,
 			     send_wr->opcode);
 		if (mad_hdr) {
@@ -116,7 +117,7 @@ static void trace_send_wr_ud(const struct ib_send_wr *send_wr)
 				     mad_hdr->attr_mod);
 		}
 		for (j = 0; j < send_wr->num_sge; j++) {
-			u8 *data = (u8 *) abs_to_virt(sge->addr);
+			u8 *data = (u8 *)abs_to_virt(sge->addr);
 			ehca_gen_dbg("send_wr#%x sge#%x addr=%p length=%x "
 				     "lkey=%x",
 				     idx, j, data, sge->length, sge->lkey);
@@ -534,9 +535,11 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 
 	cqe_count++;
 	if (unlikely(cqe->status & WC_STATUS_PURGE_BIT)) {
-		struct ehca_qp *qp=ehca_cq_get_qp(my_cq, cqe->local_qp_number);
+		struct ehca_qp *qp;
 		int purgeflag;
 		unsigned long flags;
+
+		qp = ehca_cq_get_qp(my_cq, cqe->local_qp_number);
 		if (!qp) {
 			ehca_err(cq->device, "cq_num=%x qp_num=%x "
 				 "could not find qp -> ignore cqe",
@@ -551,8 +554,8 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 		spin_unlock_irqrestore(&qp->spinlock_s, flags);
 
 		if (purgeflag) {
-			ehca_dbg(cq->device, "Got CQE with purged bit qp_num=%x "
-				 "src_qp=%x",
+			ehca_dbg(cq->device,
+				 "Got CQE with purged bit qp_num=%x src_qp=%x",
 				 cqe->local_qp_number, cqe->remote_qp_number);
 			if (ehca_debug_level)
 				ehca_dmp(cqe, 64, "qp_num=%x src_qp=%x",

drivers/infiniband/hw/ehca/ehca_tools.h

@@ -93,14 +93,14 @@ extern int ehca_debug_level;
 #define ehca_gen_dbg(format, arg...) \
 	do { \
 		if (unlikely(ehca_debug_level)) \
-			printk(KERN_DEBUG "PU%04x EHCA_DBG:%s " format "\n",\
+			printk(KERN_DEBUG "PU%04x EHCA_DBG:%s " format "\n", \
 			       get_paca()->paca_index, __FUNCTION__, ## arg); \
 	} while (0)
 
 #define ehca_gen_warn(format, arg...) \
 	do { \
 		if (unlikely(ehca_debug_level)) \
-			printk(KERN_INFO "PU%04x EHCA_WARN:%s " format "\n",\
+			printk(KERN_INFO "PU%04x EHCA_WARN:%s " format "\n", \
 			       get_paca()->paca_index, __FUNCTION__, ## arg); \
 	} while (0)
 
@@ -117,9 +117,9 @@ extern int ehca_debug_level;
 	do { \
 		unsigned int x; \
 		unsigned int l = (unsigned int)(len); \
-		unsigned char *deb = (unsigned char*)(adr);	\
+		unsigned char *deb = (unsigned char *)(adr); \
 		for (x = 0; x < l; x += 16) { \
-			printk("EHCA_DMP:%s " format \
+			printk(KERN_INFO "EHCA_DMP:%s " format \
 			       " adr=%p ofs=%04x %016lx %016lx\n", \
 			       __FUNCTION__, ##args, deb, x, \
 			       *((u64 *)&deb[0]), *((u64 *)&deb[8])); \
@@ -128,16 +128,16 @@ extern int ehca_debug_level;
 	} while (0)
 
 /* define a bitmask, little endian version */
-#define EHCA_BMASK(pos,length) (((pos)<<16)+(length))
+#define EHCA_BMASK(pos, length) (((pos) << 16) + (length))
 
 /* define a bitmask, the ibm way... */
-#define EHCA_BMASK_IBM(from,to) (((63-to)<<16)+((to)-(from)+1))
+#define EHCA_BMASK_IBM(from, to) (((63 - to) << 16) + ((to) - (from) + 1))
 
 /* internal function, don't use */
-#define EHCA_BMASK_SHIFTPOS(mask) (((mask)>>16)&0xffff)
+#define EHCA_BMASK_SHIFTPOS(mask) (((mask) >> 16) & 0xffff)
 
 /* internal function, don't use */
-#define EHCA_BMASK_MASK(mask) (0xffffffffffffffffULL >> ((64-(mask))&0xffff))
+#define EHCA_BMASK_MASK(mask) (~0ULL >> ((64 - (mask)) & 0xffff))
 
 /**
  * EHCA_BMASK_SET - return value shifted and masked by mask
@@ -145,14 +145,14 @@ extern int ehca_debug_level;
  * variable&=~EHCA_BMASK_SET(MY_MASK,-1) clears the bits from the mask
  * in variable
  */
-#define EHCA_BMASK_SET(mask,value) \
-	((EHCA_BMASK_MASK(mask) & ((u64)(value)))<<EHCA_BMASK_SHIFTPOS(mask))
+#define EHCA_BMASK_SET(mask, value) \
+	((EHCA_BMASK_MASK(mask) & ((u64)(value))) << EHCA_BMASK_SHIFTPOS(mask))
 
 /**
  * EHCA_BMASK_GET - extract a parameter from value by mask
  */
-#define EHCA_BMASK_GET(mask,value) \
-	(EHCA_BMASK_MASK(mask)& (((u64)(value))>>EHCA_BMASK_SHIFTPOS(mask)))
+#define EHCA_BMASK_GET(mask, value) \
+	(EHCA_BMASK_MASK(mask) & (((u64)(value)) >> EHCA_BMASK_SHIFTPOS(mask)))
 
 
 /* Converts ehca to ib return code */
@@ -161,8 +161,11 @@ static inline int ehca2ib_return_code(u64 ehca_rc)
 	switch (ehca_rc) {
 	case H_SUCCESS:
 		return 0;
+	case H_RESOURCE:             /* Resource in use */
 	case H_BUSY:
 		return -EBUSY;
+	case H_NOT_ENOUGH_RESOURCES: /* insufficient resources */
+	case H_CONSTRAINED:          /* resource constraint */
 	case H_NO_MEM:
 		return -ENOMEM;
 	default:

drivers/infiniband/hw/ehca/ehca_uverbs.c

@@ -70,7 +70,7 @@ int ehca_dealloc_ucontext(struct ib_ucontext *context)
 
 static void ehca_mm_open(struct vm_area_struct *vma)
 {
-	u32 *count = (u32*)vma->vm_private_data;
+	u32 *count = (u32 *)vma->vm_private_data;
 	if (!count) {
 		ehca_gen_err("Invalid vma struct vm_start=%lx vm_end=%lx",
 			     vma->vm_start, vma->vm_end);
@@ -86,7 +86,7 @@ static void ehca_mm_open(struct vm_area_struct *vma)
 
 static void ehca_mm_close(struct vm_area_struct *vma)
 {
-	u32 *count = (u32*)vma->vm_private_data;
+	u32 *count = (u32 *)vma->vm_private_data;
 	if (!count) {
 		ehca_gen_err("Invalid vma struct vm_start=%lx vm_end=%lx",
 			     vma->vm_start, vma->vm_end);
@@ -215,7 +215,8 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 	case 2: /* qp rqueue_addr */
 		ehca_dbg(qp->ib_qp.device, "qp_num=%x rqueue",
 			 qp->ib_qp.qp_num);
-		ret = ehca_mmap_queue(vma, &qp->ipz_rqueue, &qp->mm_count_rqueue);
+		ret = ehca_mmap_queue(vma, &qp->ipz_rqueue,
+				      &qp->mm_count_rqueue);
 		if (unlikely(ret)) {
 			ehca_err(qp->ib_qp.device,
 				 "ehca_mmap_queue(rq) failed rc=%x qp_num=%x",
@@ -227,7 +228,8 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 	case 3: /* qp squeue_addr */
 		ehca_dbg(qp->ib_qp.device, "qp_num=%x squeue",
 			 qp->ib_qp.qp_num);
-		ret = ehca_mmap_queue(vma, &qp->ipz_squeue, &qp->mm_count_squeue);
+		ret = ehca_mmap_queue(vma, &qp->ipz_squeue,
+				      &qp->mm_count_squeue);
 		if (unlikely(ret)) {
 			ehca_err(qp->ib_qp.device,
 				 "ehca_mmap_queue(sq) failed rc=%x qp_num=%x",

drivers/infiniband/hw/ehca/hcp_if.c

@@ -501,8 +501,8 @@ u64 hipz_h_register_rpage_qp(const struct ipz_adapter_handle adapter_handle,
 		return H_PARAMETER;
 	}
 
-	return hipz_h_register_rpage(adapter_handle,pagesize,queue_type,
-				     qp_handle.handle,logical_address_of_page,
+	return hipz_h_register_rpage(adapter_handle, pagesize, queue_type,
+				     qp_handle.handle, logical_address_of_page,
 				     count);
 }
 
@@ -522,9 +522,9 @@ u64 hipz_h_disable_and_get_wqe(const struct ipz_adapter_handle adapter_handle,
 				qp_handle.handle,	   /* r6 */
 				0, 0, 0, 0, 0, 0);
 	if (log_addr_next_sq_wqe2processed)
-		*log_addr_next_sq_wqe2processed = (void*)outs[0];
+		*log_addr_next_sq_wqe2processed = (void *)outs[0];
 	if (log_addr_next_rq_wqe2processed)
-		*log_addr_next_rq_wqe2processed = (void*)outs[1];
+		*log_addr_next_rq_wqe2processed = (void *)outs[1];
 
 	return ret;
 }

drivers/infiniband/hw/ehca/hcp_phyp.c

@@ -50,7 +50,7 @@ int hcall_map_page(u64 physaddr, u64 *mapaddr)
 
 int hcall_unmap_page(u64 mapaddr)
 {
-	iounmap((volatile void __iomem*)mapaddr);
+	iounmap((volatile void __iomem *) mapaddr);
 	return 0;
 }
 

drivers/infiniband/hw/ehca/hipz_fns_core.h

@@ -53,10 +53,10 @@
 #define hipz_galpa_load_cq(gal, offset) \
 	hipz_galpa_load(gal, CQTEMM_OFFSET(offset))
 
-#define hipz_galpa_store_qp(gal,offset, value) \
+#define hipz_galpa_store_qp(gal, offset, value) \
 	hipz_galpa_store(gal, QPTEMM_OFFSET(offset), value)
 #define hipz_galpa_load_qp(gal, offset) \
-	hipz_galpa_load(gal,QPTEMM_OFFSET(offset))
+	hipz_galpa_load(gal, QPTEMM_OFFSET(offset))
 
 static inline void hipz_update_sqa(struct ehca_qp *qp, u16 nr_wqes)
 {

drivers/infiniband/hw/ehca/hipz_hw.h

@@ -161,11 +161,11 @@ struct hipz_qptemm {
 /* 0x1000      */
 };
 
-#define QPX_SQADDER EHCA_BMASK_IBM(48,63)
-#define QPX_RQADDER EHCA_BMASK_IBM(48,63)
-#define QPX_AAELOG_RESET_SRQ_LIMIT EHCA_BMASK_IBM(3,3)
+#define QPX_SQADDER EHCA_BMASK_IBM(48, 63)
+#define QPX_RQADDER EHCA_BMASK_IBM(48, 63)
+#define QPX_AAELOG_RESET_SRQ_LIMIT EHCA_BMASK_IBM(3, 3)
 
-#define QPTEMM_OFFSET(x) offsetof(struct hipz_qptemm,x)
+#define QPTEMM_OFFSET(x) offsetof(struct hipz_qptemm, x)
 
 /* MRMWPT Entry Memory Map */
 struct hipz_mrmwmm {
@@ -187,7 +187,7 @@ struct hipz_mrmwmm {
 
 };
 
-#define MRMWMM_OFFSET(x) offsetof(struct hipz_mrmwmm,x)
+#define MRMWMM_OFFSET(x) offsetof(struct hipz_mrmwmm, x)
 
 struct hipz_qpedmm {
 	/* 0x00 */
@@ -238,7 +238,7 @@ struct hipz_qpedmm {
 	u64 qpedx_rrva3;
 };
 
-#define QPEDMM_OFFSET(x) offsetof(struct hipz_qpedmm,x)
+#define QPEDMM_OFFSET(x) offsetof(struct hipz_qpedmm, x)
 
 /* CQ Table Entry Memory Map */
 struct hipz_cqtemm {
@@ -263,12 +263,12 @@ struct hipz_cqtemm {
 /* 0x1000 */
 };
 
-#define CQX_FEC_CQE_CNT           EHCA_BMASK_IBM(32,63)
-#define CQX_FECADDER              EHCA_BMASK_IBM(32,63)
-#define CQX_N0_GENERATE_SOLICITED_COMP_EVENT EHCA_BMASK_IBM(0,0)
-#define CQX_N1_GENERATE_COMP_EVENT EHCA_BMASK_IBM(0,0)
+#define CQX_FEC_CQE_CNT           EHCA_BMASK_IBM(32, 63)
+#define CQX_FECADDER              EHCA_BMASK_IBM(32, 63)
+#define CQX_N0_GENERATE_SOLICITED_COMP_EVENT EHCA_BMASK_IBM(0, 0)
+#define CQX_N1_GENERATE_COMP_EVENT EHCA_BMASK_IBM(0, 0)
 
-#define CQTEMM_OFFSET(x) offsetof(struct hipz_cqtemm,x)
+#define CQTEMM_OFFSET(x) offsetof(struct hipz_cqtemm, x)
 
 /* EQ Table Entry Memory Map */
 struct hipz_eqtemm {
@@ -293,7 +293,7 @@ struct hipz_eqtemm {
 
 };
 
-#define EQTEMM_OFFSET(x) offsetof(struct hipz_eqtemm,x)
+#define EQTEMM_OFFSET(x) offsetof(struct hipz_eqtemm, x)
 
 /* access control defines for MR/MW */
 #define HIPZ_ACCESSCTRL_L_WRITE  0x00800000

drivers/infiniband/hw/ehca/ipz_pt_fn.c

@@ -114,7 +114,7 @@ int ipz_queue_ctor(struct ipz_queue *queue,
 	 */
 	f = 0;
 	while (f < nr_of_pages) {
-		u8 *kpage = (u8*)get_zeroed_page(GFP_KERNEL);
+		u8 *kpage = (u8 *)get_zeroed_page(GFP_KERNEL);
 		int k;
 		if (!kpage)
 			goto ipz_queue_ctor_exit0; /*NOMEM*/

drivers/infiniband/hw/ehca/ipz_pt_fn.h

@@ -240,7 +240,7 @@ void *ipz_qeit_eq_get_inc(struct ipz_queue *queue);
 static inline void *ipz_eqit_eq_get_inc_valid(struct ipz_queue *queue)
 {
 	void *ret = ipz_qeit_get(queue);
-	u32 qe = *(u8 *) ret;
+	u32 qe = *(u8 *)ret;
 	if ((qe >> 7) != (queue->toggle_state & 1))
 		return NULL;
 	ipz_qeit_eq_get_inc(queue); /* this is a good one */
@@ -250,7 +250,7 @@ static inline void *ipz_eqit_eq_get_inc_valid(struct ipz_queue *queue)
 static inline void *ipz_eqit_eq_peek_valid(struct ipz_queue *queue)
 {
 	void *ret = ipz_qeit_get(queue);
-	u32 qe = *(u8 *) ret;
+	u32 qe = *(u8 *)ret;
 	if ((qe >> 7) != (queue->toggle_state & 1))
 		return NULL;
 	return ret;

drivers/infiniband/hw/ipath/ipath_driver.c

@@ -1889,7 +1889,7 @@ void ipath_write_kreg_port(const struct ipath_devdata *dd, ipath_kreg regno,
 /* Below is "non-zero" to force override, but both actual LEDs are off */
 #define LED_OVER_BOTH_OFF (8)
 
-void ipath_run_led_override(unsigned long opaque)
+static void ipath_run_led_override(unsigned long opaque)
 {
 	struct ipath_devdata *dd = (struct ipath_devdata *)opaque;
 	int timeoff;

drivers/infiniband/hw/ipath/ipath_eeprom.c

@@ -426,7 +426,7 @@ static int ipath_eeprom_internal_read(struct ipath_devdata *dd,
  * @buffer: data to write
  * @len: number of bytes to write
  */
-int ipath_eeprom_internal_write(struct ipath_devdata *dd, u8 eeprom_offset,
+static int ipath_eeprom_internal_write(struct ipath_devdata *dd, u8 eeprom_offset,
 				       const void *buffer, int len)
 {
 	u8 single_byte;

drivers/infiniband/hw/ipath/ipath_intr.c

@@ -70,7 +70,7 @@ static void ipath_clrpiobuf(struct ipath_devdata *dd, u32 pnum)
  * If rewrite is true, and bits are set in the sendbufferror registers,
  * we'll write to the buffer, for error recovery on parity errors.
  */
-void ipath_disarm_senderrbufs(struct ipath_devdata *dd, int rewrite)
+static void ipath_disarm_senderrbufs(struct ipath_devdata *dd, int rewrite)
 {
 	u32 piobcnt;
 	unsigned long sbuf[4];

drivers/infiniband/hw/ipath/ipath_kernel.h

@@ -776,7 +776,6 @@ void ipath_get_eeprom_info(struct ipath_devdata *);
 int ipath_update_eeprom_log(struct ipath_devdata *dd);
 void ipath_inc_eeprom_err(struct ipath_devdata *dd, u32 eidx, u32 incr);
 u64 ipath_snap_cntr(struct ipath_devdata *, ipath_creg);
-void ipath_disarm_senderrbufs(struct ipath_devdata *, int);
 
 /*
  * Set LED override, only the two LSBs have "public" meaning, but
@@ -820,7 +819,6 @@ static inline u64 ipath_mdio_req(int cmd, int dev, int reg, int data)
 #define IPATH_MDIO_CTRL_8355_REG_10 0x1D
 
 int ipath_get_user_pages(unsigned long, size_t, struct page **);
-int ipath_get_user_pages_nocopy(unsigned long, struct page **);
 void ipath_release_user_pages(struct page **, size_t);
 void ipath_release_user_pages_on_close(struct page **, size_t);
 int ipath_eeprom_read(struct ipath_devdata *, u8, void *, int);

drivers/infiniband/hw/ipath/ipath_ruc.c

@@ -507,7 +507,7 @@ static int want_buffer(struct ipath_devdata *dd)
  *
  * Called when we run out of PIO buffers.
  */
-void ipath_no_bufs_available(struct ipath_qp *qp, struct ipath_ibdev *dev)
+static void ipath_no_bufs_available(struct ipath_qp *qp, struct ipath_ibdev *dev)
 {
 	unsigned long flags;
 

drivers/infiniband/hw/ipath/ipath_user_pages.c

@@ -171,32 +171,6 @@ int ipath_get_user_pages(unsigned long start_page, size_t num_pages,
 	return ret;
 }
 
-/**
- * ipath_get_user_pages_nocopy - lock a single page for I/O and mark shared
- * @start_page: the page to lock
- * @p: the output page structure
- *
- * This is similar to ipath_get_user_pages, but it's always one page, and we
- * mark the page as locked for I/O, and shared.  This is used for the user
- * process page that contains the destination address for the rcvhdrq tail
- * update, so we need to have the vma. If we don't do this, the page can be
- * taken away from us on fork, even if the child never touches it, and then
- * the user process never sees the tail register updates.
- */
-int ipath_get_user_pages_nocopy(unsigned long page, struct page **p)
-{
-	struct vm_area_struct *vma;
-	int ret;
-
-	down_write(&current->mm->mmap_sem);
-
-	ret = __get_user_pages(page, 1, p, &vma);
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
 void ipath_release_user_pages(struct page **p, size_t num_pages)
 {
 	down_write(&current->mm->mmap_sem);

drivers/infiniband/hw/ipath/ipath_verbs.c

@@ -488,7 +488,7 @@ bail:;
  * This is called from ipath_do_rcv_timer() at interrupt level to check for
  * QPs which need retransmits and to collect performance numbers.
  */
-void ipath_ib_timer(struct ipath_ibdev *dev)
+static void ipath_ib_timer(struct ipath_ibdev *dev)
 {
 	struct ipath_qp *resend = NULL;
 	struct list_head *last;

drivers/infiniband/hw/ipath/ipath_verbs.h

@@ -782,8 +782,6 @@ void ipath_update_mmap_info(struct ipath_ibdev *dev,
 
 int ipath_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
 
-void ipath_no_bufs_available(struct ipath_qp *qp, struct ipath_ibdev *dev);
-
 void ipath_insert_rnr_queue(struct ipath_qp *qp);
 
 int ipath_get_rwqe(struct ipath_qp *qp, int wr_id_only);
@@ -807,8 +805,6 @@ void ipath_ib_rcv(struct ipath_ibdev *, void *, void *, u32);
 
 int ipath_ib_piobufavail(struct ipath_ibdev *);
 
-void ipath_ib_timer(struct ipath_ibdev *);
-
 unsigned ipath_get_npkeys(struct ipath_devdata *);
 
 u32 ipath_get_cr_errpkey(struct ipath_devdata *);

drivers/infiniband/hw/mlx4/qp.c

@@ -1183,6 +1183,43 @@ static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq
 	return cur + nreq >= wq->max_post;
 }
 
+static __always_inline void set_raddr_seg(struct mlx4_wqe_raddr_seg *rseg,
+					  u64 remote_addr, u32 rkey)
+{
+	rseg->raddr    = cpu_to_be64(remote_addr);
+	rseg->rkey     = cpu_to_be32(rkey);
+	rseg->reserved = 0;
+}
+
+static void set_atomic_seg(struct mlx4_wqe_atomic_seg *aseg, struct ib_send_wr *wr)
+{
+	if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP) {
+		aseg->swap_add = cpu_to_be64(wr->wr.atomic.swap);
+		aseg->compare  = cpu_to_be64(wr->wr.atomic.compare_add);
+	} else {
+		aseg->swap_add = cpu_to_be64(wr->wr.atomic.compare_add);
+		aseg->compare  = 0;
+	}
+
+}
+
+static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg,
+			     struct ib_send_wr *wr)
+{
+	memcpy(dseg->av, &to_mah(wr->wr.ud.ah)->av, sizeof (struct mlx4_av));
+	dseg->dqpn = cpu_to_be32(wr->wr.ud.remote_qpn);
+	dseg->qkey = cpu_to_be32(wr->wr.ud.remote_qkey);
+
+}
+
+static void set_data_seg(struct mlx4_wqe_data_seg *dseg,
+			 struct ib_sge *sg)
+{
+	dseg->byte_count = cpu_to_be32(sg->length);
+	dseg->lkey       = cpu_to_be32(sg->lkey);
+	dseg->addr       = cpu_to_be64(sg->addr);
+}
+
 int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		      struct ib_send_wr **bad_wr)
 {
@@ -1238,26 +1275,13 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			switch (wr->opcode) {
 			case IB_WR_ATOMIC_CMP_AND_SWP:
 			case IB_WR_ATOMIC_FETCH_AND_ADD:
-				((struct mlx4_wqe_raddr_seg *) wqe)->raddr =
-					cpu_to_be64(wr->wr.atomic.remote_addr);
-				((struct mlx4_wqe_raddr_seg *) wqe)->rkey =
-					cpu_to_be32(wr->wr.atomic.rkey);
-				((struct mlx4_wqe_raddr_seg *) wqe)->reserved = 0;
-
+				set_raddr_seg(wqe, wr->wr.atomic.remote_addr,
+					      wr->wr.atomic.rkey);
 				wqe  += sizeof (struct mlx4_wqe_raddr_seg);
 
-				if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP) {
-					((struct mlx4_wqe_atomic_seg *) wqe)->swap_add =
-						cpu_to_be64(wr->wr.atomic.swap);
-					((struct mlx4_wqe_atomic_seg *) wqe)->compare =
-						cpu_to_be64(wr->wr.atomic.compare_add);
-				} else {
-					((struct mlx4_wqe_atomic_seg *) wqe)->swap_add =
-						cpu_to_be64(wr->wr.atomic.compare_add);
-					((struct mlx4_wqe_atomic_seg *) wqe)->compare = 0;
-				}
-
+				set_atomic_seg(wqe, wr);
 				wqe  += sizeof (struct mlx4_wqe_atomic_seg);
+
 				size += (sizeof (struct mlx4_wqe_raddr_seg) +
 					 sizeof (struct mlx4_wqe_atomic_seg)) / 16;
 
@@ -1266,15 +1290,10 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			case IB_WR_RDMA_READ:
 			case IB_WR_RDMA_WRITE:
 			case IB_WR_RDMA_WRITE_WITH_IMM:
-				((struct mlx4_wqe_raddr_seg *) wqe)->raddr =
-					cpu_to_be64(wr->wr.rdma.remote_addr);
-				((struct mlx4_wqe_raddr_seg *) wqe)->rkey =
-					cpu_to_be32(wr->wr.rdma.rkey);
-				((struct mlx4_wqe_raddr_seg *) wqe)->reserved = 0;
-
+				set_raddr_seg(wqe, wr->wr.rdma.remote_addr,
+					      wr->wr.rdma.rkey);
 				wqe  += sizeof (struct mlx4_wqe_raddr_seg);
 				size += sizeof (struct mlx4_wqe_raddr_seg) / 16;
-
 				break;
 
 			default:
@@ -1284,13 +1303,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			break;
 
 		case IB_QPT_UD:
-			memcpy(((struct mlx4_wqe_datagram_seg *) wqe)->av,
-			       &to_mah(wr->wr.ud.ah)->av, sizeof (struct mlx4_av));
-			((struct mlx4_wqe_datagram_seg *) wqe)->dqpn =
-				cpu_to_be32(wr->wr.ud.remote_qpn);
-			((struct mlx4_wqe_datagram_seg *) wqe)->qkey =
-				cpu_to_be32(wr->wr.ud.remote_qkey);
-
+			set_datagram_seg(wqe, wr);
 			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
 			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
 			break;
@@ -1313,12 +1326,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mlx4_wqe_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mlx4_wqe_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mlx4_wqe_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			set_data_seg(wqe, wr->sg_list + i);
 
 			wqe  += sizeof (struct mlx4_wqe_data_seg);
 			size += sizeof (struct mlx4_wqe_data_seg) / 16;
@@ -1498,7 +1506,7 @@ static int to_ib_qp_access_flags(int mlx4_flags)
 static void to_ib_ah_attr(struct mlx4_dev *dev, struct ib_ah_attr *ib_ah_attr,
 				struct mlx4_qp_path *path)
 {
-	memset(ib_ah_attr, 0, sizeof *path);
+	memset(ib_ah_attr, 0, sizeof *ib_ah_attr);
 	ib_ah_attr->port_num	  = path->sched_queue & 0x40 ? 2 : 1;
 
 	if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->caps.num_ports)
@@ -1515,7 +1523,7 @@ static void to_ib_ah_attr(struct mlx4_dev *dev, struct ib_ah_attr *ib_ah_attr,
 		ib_ah_attr->grh.traffic_class =
 			(be32_to_cpu(path->tclass_flowlabel) >> 20) & 0xff;
 		ib_ah_attr->grh.flow_label =
-			be32_to_cpu(path->tclass_flowlabel) & 0xffffff;
+			be32_to_cpu(path->tclass_flowlabel) & 0xfffff;
 		memcpy(ib_ah_attr->grh.dgid.raw,
 			path->rgid, sizeof ib_ah_attr->grh.dgid.raw);
 	}
@@ -1560,6 +1568,9 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 	}
 
 	qp_attr->pkey_index = context.pri_path.pkey_index & 0x7f;
+	if (qp_attr->qp_state == IB_QPS_INIT)
+		qp_attr->port_num = qp->port;
+	else
 		qp_attr->port_num = context.pri_path.sched_queue & 0x40 ? 2 : 1;
 
 	/* qp_attr->en_sqd_async_notify is only applicable in modify qp */
@@ -1578,17 +1589,25 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 
 done:
 	qp_attr->cur_qp_state	     = qp_attr->qp_state;
+	qp_attr->cap.max_recv_wr     = qp->rq.wqe_cnt;
+	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
+
 	if (!ibqp->uobject) {
 		qp_attr->cap.max_send_wr  = qp->sq.wqe_cnt;
-		qp_attr->cap.max_recv_wr     = qp->rq.wqe_cnt;
 		qp_attr->cap.max_send_sge = qp->sq.max_gs;
-		qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
-		qp_attr->cap.max_inline_data = (1 << qp->sq.wqe_shift) -
-			send_wqe_overhead(qp->ibqp.qp_type) -
-			sizeof (struct mlx4_wqe_inline_seg);
-		qp_init_attr->cap	     = qp_attr->cap;
+	} else {
+		qp_attr->cap.max_send_wr  = 0;
+		qp_attr->cap.max_send_sge = 0;
 	}
 
+	/*
+	 * We don't support inline sends for kernel QPs (yet), and we
+	 * don't know what userspace's value should be.
+	 */
+	qp_attr->cap.max_inline_data = 0;
+
+	qp_init_attr->cap	     = qp_attr->cap;
+
 	return 0;
 }
 

drivers/infiniband/hw/mthca/mthca_main.c

@@ -67,7 +67,7 @@ MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");
 
 static int msi = 0;
 module_param(msi, int, 0444);
-MODULE_PARM_DESC(msi, "attempt to use MSI if nonzero");
+MODULE_PARM_DESC(msi, "attempt to use MSI if nonzero (deprecated, use MSI-X instead)");
 
 #else /* CONFIG_PCI_MSI */
 
@@ -1117,9 +1117,21 @@ static int __mthca_init_one(struct pci_dev *pdev, int hca_type)
 
 	if (msi_x && !mthca_enable_msi_x(mdev))
 		mdev->mthca_flags |= MTHCA_FLAG_MSI_X;
-	if (msi && !(mdev->mthca_flags & MTHCA_FLAG_MSI_X) &&
-	    !pci_enable_msi(pdev))
+	else if (msi) {
+		static int warned;
+
+		if (!warned) {
+			printk(KERN_WARNING PFX "WARNING: MSI support will be "
+			       "removed from the ib_mthca driver in January 2008.\n");
+			printk(KERN_WARNING "    If you are using MSI and cannot "
+			       "switch to MSI-X, please tell "
+			       "<general@lists.openfabrics.org>.\n");
+			++warned;
+		}
+
+		if (!pci_enable_msi(pdev))
 			mdev->mthca_flags |= MTHCA_FLAG_MSI;
+	}
 
 	if (mthca_cmd_init(mdev)) {
 		mthca_err(mdev, "Failed to init command interface, aborting.\n");
@@ -1135,7 +1147,7 @@ static int __mthca_init_one(struct pci_dev *pdev, int hca_type)
 		goto err_cmd;
 
 	if (mdev->fw_ver < mthca_hca_table[hca_type].latest_fw) {
-		mthca_warn(mdev, "HCA FW version %d.%d.%3d is old (%d.%d.%3d is current).\n",
+		mthca_warn(mdev, "HCA FW version %d.%d.%03d is old (%d.%d.%03d is current).\n",
 			   (int) (mdev->fw_ver >> 32), (int) (mdev->fw_ver >> 16) & 0xffff,
 			   (int) (mdev->fw_ver & 0xffff),
 			   (int) (mthca_hca_table[hca_type].latest_fw >> 32),

drivers/infiniband/hw/mthca/mthca_srq.c

@@ -543,20 +543,12 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
 			wqe += sizeof (struct mthca_data_seg);
 		}
 
-		if (i < srq->max_gs) {
-			((struct mthca_data_seg *) wqe)->byte_count = 0;
-			((struct mthca_data_seg *) wqe)->lkey = cpu_to_be32(MTHCA_INVAL_LKEY);
-			((struct mthca_data_seg *) wqe)->addr = 0;
-		}
+		if (i < srq->max_gs)
+			mthca_set_data_seg_inval(wqe);
 
 		((struct mthca_next_seg *) prev_wqe)->nda_op =
 			cpu_to_be32((ind << srq->wqe_shift) | 1);
@@ -662,20 +654,12 @@ int mthca_arbel_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
 			wqe += sizeof (struct mthca_data_seg);
 		}
 
-		if (i < srq->max_gs) {
-			((struct mthca_data_seg *) wqe)->byte_count = 0;
-			((struct mthca_data_seg *) wqe)->lkey = cpu_to_be32(MTHCA_INVAL_LKEY);
-			((struct mthca_data_seg *) wqe)->addr = 0;
-		}
+		if (i < srq->max_gs)
+			mthca_set_data_seg_inval(wqe);
 
 		srq->wrid[ind]  = wr->wr_id;
 		srq->first_free = next_ind;

drivers/infiniband/hw/mthca/mthca_wqe.h

@@ -113,4 +113,19 @@ struct mthca_mlx_seg {
 	__be16 vcrc;
 };
 
+static __always_inline void mthca_set_data_seg(struct mthca_data_seg *dseg,
+					       struct ib_sge *sg)
+{
+	dseg->byte_count = cpu_to_be32(sg->length);
+	dseg->lkey       = cpu_to_be32(sg->lkey);
+	dseg->addr       = cpu_to_be64(sg->addr);
+}
+
+static __always_inline void mthca_set_data_seg_inval(struct mthca_data_seg *dseg)
+{
+	dseg->byte_count = 0;
+	dseg->lkey       = cpu_to_be32(MTHCA_INVAL_LKEY);
+	dseg->addr       = 0;
+}
+
 #endif /* MTHCA_WQE_H */

drivers/infiniband/ulp/iser/iscsi_iser.h

@@ -310,8 +310,6 @@ int  iser_conn_init(struct iser_conn **ib_conn);
 
 void iser_conn_terminate(struct iser_conn *ib_conn);
 
-void iser_conn_release(struct iser_conn *ib_conn);
-
 void iser_rcv_completion(struct iser_desc *desc,
 			 unsigned long    dto_xfer_len);
 
@@ -329,9 +327,6 @@ void iser_reg_single(struct iser_device      *device,
 		     struct iser_regd_buf    *regd_buf,
 		     enum dma_data_direction direction);
 
-int  iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task    *ctask,
-				  enum iser_data_dir            cmd_dir);
-
 void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_cmd_task *ctask,
 				     enum iser_data_dir         cmd_dir);
 

drivers/infiniband/ulp/iser/iser_memory.c

@@ -103,7 +103,7 @@ void iser_reg_single(struct iser_device *device,
 /**
  * iser_start_rdma_unaligned_sg
  */
-int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task  *iser_ctask,
+static int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask,
 					enum iser_data_dir cmd_dir)
 {
 	int dma_nents;

drivers/infiniband/ulp/iser/iser_verbs.c

@@ -310,6 +310,29 @@ static int iser_conn_state_comp_exch(struct iser_conn *ib_conn,
 	return ret;
 }
 
+/**
+ * Frees all conn objects and deallocs conn descriptor
+ */
+static void iser_conn_release(struct iser_conn *ib_conn)
+{
+	struct iser_device  *device = ib_conn->device;
+
+	BUG_ON(ib_conn->state != ISER_CONN_DOWN);
+
+	mutex_lock(&ig.connlist_mutex);
+	list_del(&ib_conn->conn_list);
+	mutex_unlock(&ig.connlist_mutex);
+
+	iser_free_ib_conn_res(ib_conn);
+	ib_conn->device = NULL;
+	/* on EVENT_ADDR_ERROR there's no device yet for this conn */
+	if (device != NULL)
+		iser_device_try_release(device);
+	if (ib_conn->iser_conn)
+		ib_conn->iser_conn->ib_conn = NULL;
+	kfree(ib_conn);
+}
+
 /**
  * triggers start of the disconnect procedures and wait for them to be done
  */
@@ -549,30 +572,6 @@ int iser_connect(struct iser_conn   *ib_conn,
 	return err;
 }
 
-/**
- * Frees all conn objects and deallocs conn descriptor
- */
-void iser_conn_release(struct iser_conn *ib_conn)
-{
-	struct iser_device  *device = ib_conn->device;
-
-	BUG_ON(ib_conn->state != ISER_CONN_DOWN);
-
-	mutex_lock(&ig.connlist_mutex);
-	list_del(&ib_conn->conn_list);
-	mutex_unlock(&ig.connlist_mutex);
-
-	iser_free_ib_conn_res(ib_conn);
-	ib_conn->device = NULL;
-	/* on EVENT_ADDR_ERROR there's no device yet for this conn */
-	if (device != NULL)
-		iser_device_try_release(device);
-	if (ib_conn->iser_conn)
-		ib_conn->iser_conn->ib_conn = NULL;
-	kfree(ib_conn);
-}
-
-
 /**
  * iser_reg_page_vec - Register physical memory
  *

drivers/net/mlx4/catas.c

@@ -30,41 +30,133 @@
  * SOFTWARE.
  */
 
+#include <linux/workqueue.h>
+
 #include "mlx4.h"
 
-void mlx4_handle_catas_err(struct mlx4_dev *dev)
+enum {
+	MLX4_CATAS_POLL_INTERVAL	= 5 * HZ,
+};
+
+static DEFINE_SPINLOCK(catas_lock);
+
+static LIST_HEAD(catas_list);
+static struct workqueue_struct *catas_wq;
+static struct work_struct catas_work;
+
+static int internal_err_reset = 1;
+module_param(internal_err_reset, int, 0644);
+MODULE_PARM_DESC(internal_err_reset,
+		 "Reset device on internal errors if non-zero (default 1)");
+
+static void dump_err_buf(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	int i;
 
-	mlx4_err(dev, "Catastrophic error detected:\n");
+	mlx4_err(dev, "Internal error detected:\n");
 	for (i = 0; i < priv->fw.catas_size; ++i)
 		mlx4_err(dev, "  buf[%02x]: %08x\n",
 			 i, swab32(readl(priv->catas_err.map + i)));
+}
+
+static void poll_catas(unsigned long dev_ptr)
+{
+	struct mlx4_dev *dev = (struct mlx4_dev *) dev_ptr;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (readl(priv->catas_err.map)) {
+		dump_err_buf(dev);
 
 		mlx4_dispatch_event(dev, MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR, 0, 0);
+
+		if (internal_err_reset) {
+			spin_lock(&catas_lock);
+			list_add(&priv->catas_err.list, &catas_list);
+			spin_unlock(&catas_lock);
+
+			queue_work(catas_wq, &catas_work);
+		}
+	} else
+		mod_timer(&priv->catas_err.timer,
+			  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
 }
 
-void mlx4_map_catas_buf(struct mlx4_dev *dev)
+static void catas_reset(struct work_struct *work)
+{
+	struct mlx4_priv *priv, *tmppriv;
+	struct mlx4_dev *dev;
+
+	LIST_HEAD(tlist);
+	int ret;
+
+	spin_lock_irq(&catas_lock);
+	list_splice_init(&catas_list, &tlist);
+	spin_unlock_irq(&catas_lock);
+
+	list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) {
+		ret = mlx4_restart_one(priv->dev.pdev);
+		dev = &priv->dev;
+		if (ret)
+			mlx4_err(dev, "Reset failed (%d)\n", ret);
+		else
+			mlx4_dbg(dev, "Reset succeeded\n");
+	}
+}
+
+void mlx4_start_catas_poll(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	unsigned long addr;
 
+	INIT_LIST_HEAD(&priv->catas_err.list);
+	init_timer(&priv->catas_err.timer);
+	priv->catas_err.map = NULL;
+
 	addr = pci_resource_start(dev->pdev, priv->fw.catas_bar) +
 		priv->fw.catas_offset;
 
 	priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
-	if (!priv->catas_err.map)
-		mlx4_warn(dev, "Failed to map catastrophic error buffer at 0x%lx\n",
+	if (!priv->catas_err.map) {
+		mlx4_warn(dev, "Failed to map internal error buffer at 0x%lx\n",
 			  addr);
+		return;
+	}
 
+	priv->catas_err.timer.data     = (unsigned long) dev;
+	priv->catas_err.timer.function = poll_catas;
+	priv->catas_err.timer.expires  =
+		round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
+	add_timer(&priv->catas_err.timer);
 }
 
-void mlx4_unmap_catas_buf(struct mlx4_dev *dev)
+void mlx4_stop_catas_poll(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
+	del_timer_sync(&priv->catas_err.timer);
+
 	if (priv->catas_err.map)
 		iounmap(priv->catas_err.map);
+
+	spin_lock_irq(&catas_lock);
+	list_del(&priv->catas_err.list);
+	spin_unlock_irq(&catas_lock);
+}
+
+int __init mlx4_catas_init(void)
+{
+	INIT_WORK(&catas_work, catas_reset);
+
+	catas_wq = create_singlethread_workqueue("mlx4_err");
+	if (!catas_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx4_catas_cleanup(void)
+{
+	destroy_workqueue(catas_wq);
 }

drivers/net/mlx4/eq.c

@@ -89,14 +89,12 @@ struct mlx4_eq_context {
 			       (1ull << MLX4_EVENT_TYPE_PATH_MIG_FAILED)    | \
 			       (1ull << MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR) | \
 			       (1ull << MLX4_EVENT_TYPE_WQ_ACCESS_ERROR)    | \
-			       (1ull << MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR)  | \
 			       (1ull << MLX4_EVENT_TYPE_PORT_CHANGE)	    | \
 			       (1ull << MLX4_EVENT_TYPE_ECC_DETECT)	    | \
 			       (1ull << MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)    | \
 			       (1ull << MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE)    | \
 			       (1ull << MLX4_EVENT_TYPE_SRQ_LIMIT)	    | \
 			       (1ull << MLX4_EVENT_TYPE_CMD))
-#define MLX4_CATAS_EVENT_MASK  (1ull << MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR)
 
 struct mlx4_eqe {
 	u8			reserved1;
@@ -264,7 +262,7 @@ static irqreturn_t mlx4_interrupt(int irq, void *dev_ptr)
 
 	writel(priv->eq_table.clr_mask, priv->eq_table.clr_int);
 
-	for (i = 0; i < MLX4_EQ_CATAS; ++i)
+	for (i = 0; i < MLX4_NUM_EQ; ++i)
 		work |= mlx4_eq_int(dev, &priv->eq_table.eq[i]);
 
 	return IRQ_RETVAL(work);
@@ -281,14 +279,6 @@ static irqreturn_t mlx4_msi_x_interrupt(int irq, void *eq_ptr)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t mlx4_catas_interrupt(int irq, void *dev_ptr)
-{
-	mlx4_handle_catas_err(dev_ptr);
-
-	/* MSI-X vectors always belong to us */
-	return IRQ_HANDLED;
-}
-
 static int mlx4_MAP_EQ(struct mlx4_dev *dev, u64 event_mask, int unmap,
 			int eq_num)
 {
@@ -490,11 +480,9 @@ static void mlx4_free_irqs(struct mlx4_dev *dev)
 
 	if (eq_table->have_irq)
 		free_irq(dev->pdev->irq, dev);
-	for (i = 0; i < MLX4_EQ_CATAS; ++i)
+	for (i = 0; i < MLX4_NUM_EQ; ++i)
 		if (eq_table->eq[i].have_irq)
 			free_irq(eq_table->eq[i].irq, eq_table->eq + i);
-	if (eq_table->eq[MLX4_EQ_CATAS].have_irq)
-		free_irq(eq_table->eq[MLX4_EQ_CATAS].irq, dev);
 }
 
 static int __devinit mlx4_map_clr_int(struct mlx4_dev *dev)
@@ -598,32 +586,19 @@ int __devinit mlx4_init_eq_table(struct mlx4_dev *dev)
 	if (dev->flags & MLX4_FLAG_MSI_X) {
 		static const char *eq_name[] = {
 			[MLX4_EQ_COMP]  = DRV_NAME " (comp)",
-			[MLX4_EQ_ASYNC] = DRV_NAME " (async)",
-			[MLX4_EQ_CATAS] = DRV_NAME " (catas)"
+			[MLX4_EQ_ASYNC] = DRV_NAME " (async)"
 		};
 
-		err = mlx4_create_eq(dev, 1, MLX4_EQ_CATAS,
-				     &priv->eq_table.eq[MLX4_EQ_CATAS]);
-		if (err)
-			goto err_out_async;
-
-		for (i = 0; i < MLX4_EQ_CATAS; ++i) {
+		for (i = 0; i < MLX4_NUM_EQ; ++i) {
 			err = request_irq(priv->eq_table.eq[i].irq,
 					  mlx4_msi_x_interrupt,
 					  0, eq_name[i], priv->eq_table.eq + i);
 			if (err)
-				goto err_out_catas;
+				goto err_out_async;
 
 			priv->eq_table.eq[i].have_irq = 1;
 		}
 
-		err = request_irq(priv->eq_table.eq[MLX4_EQ_CATAS].irq,
-				  mlx4_catas_interrupt, 0,
-				  eq_name[MLX4_EQ_CATAS], dev);
-		if (err)
-			goto err_out_catas;
-
-		priv->eq_table.eq[MLX4_EQ_CATAS].have_irq = 1;
 	} else {
 		err = request_irq(dev->pdev->irq, mlx4_interrupt,
 				  IRQF_SHARED, DRV_NAME, dev);
@@ -639,22 +614,11 @@ int __devinit mlx4_init_eq_table(struct mlx4_dev *dev)
 		mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n",
 			   priv->eq_table.eq[MLX4_EQ_ASYNC].eqn, err);
 
-	for (i = 0; i < MLX4_EQ_CATAS; ++i)
+	for (i = 0; i < MLX4_NUM_EQ; ++i)
 		eq_set_ci(&priv->eq_table.eq[i], 1);
 
-	if (dev->flags & MLX4_FLAG_MSI_X) {
-		err = mlx4_MAP_EQ(dev, MLX4_CATAS_EVENT_MASK, 0,
-				  priv->eq_table.eq[MLX4_EQ_CATAS].eqn);
-		if (err)
-			mlx4_warn(dev, "MAP_EQ for catas EQ %d failed (%d)\n",
-				  priv->eq_table.eq[MLX4_EQ_CATAS].eqn, err);
-	}
-
 	return 0;
 
-err_out_catas:
-	mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_CATAS]);
-
 err_out_async:
 	mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_ASYNC]);
 
@@ -675,19 +639,13 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
-	if (dev->flags & MLX4_FLAG_MSI_X)
-		mlx4_MAP_EQ(dev, MLX4_CATAS_EVENT_MASK, 1,
-			    priv->eq_table.eq[MLX4_EQ_CATAS].eqn);
-
 	mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1,
 		    priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
 
 	mlx4_free_irqs(dev);
 
-	for (i = 0; i < MLX4_EQ_CATAS; ++i)
+	for (i = 0; i < MLX4_NUM_EQ; ++i)
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
-	if (dev->flags & MLX4_FLAG_MSI_X)
-		mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_CATAS]);
 
 	mlx4_unmap_clr_int(dev);
 

drivers/net/mlx4/intf.c

@@ -142,6 +142,7 @@ int mlx4_register_device(struct mlx4_dev *dev)
 		mlx4_add_device(intf, priv);
 
 	mutex_unlock(&intf_mutex);
+	mlx4_start_catas_poll(dev);
 
 	return 0;
 }
@@ -151,6 +152,7 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_interface *intf;
 
+	mlx4_stop_catas_poll(dev);
 	mutex_lock(&intf_mutex);
 
 	list_for_each_entry(intf, &intf_list, list)

drivers/net/mlx4/main.c

@@ -78,7 +78,7 @@ static const char mlx4_version[] __devinitdata =
 static struct mlx4_profile default_profile = {
 	.num_qp		= 1 << 16,
 	.num_srq	= 1 << 16,
-	.rdmarc_per_qp	= 4,
+	.rdmarc_per_qp	= 1 << 4,
 	.num_cq		= 1 << 16,
 	.num_mcg	= 1 << 13,
 	.num_mpt	= 1 << 17,
@@ -583,13 +583,11 @@ static int __devinit mlx4_setup_hca(struct mlx4_dev *dev)
 		goto err_pd_table_free;
 	}
 
-	mlx4_map_catas_buf(dev);
-
 	err = mlx4_init_eq_table(dev);
 	if (err) {
 		mlx4_err(dev, "Failed to initialize "
 			 "event queue table, aborting.\n");
-		goto err_catas_buf;
+		goto err_mr_table_free;
 	}
 
 	err = mlx4_cmd_use_events(dev);
@@ -659,8 +657,7 @@ static int __devinit mlx4_setup_hca(struct mlx4_dev *dev)
 err_eq_table_free:
 	mlx4_cleanup_eq_table(dev);
 
-err_catas_buf:
-	mlx4_unmap_catas_buf(dev);
+err_mr_table_free:
 	mlx4_cleanup_mr_table(dev);
 
 err_pd_table_free:
@@ -836,9 +833,6 @@ static int __devinit mlx4_init_one(struct pci_dev *pdev,
 	mlx4_cleanup_cq_table(dev);
 	mlx4_cmd_use_polling(dev);
 	mlx4_cleanup_eq_table(dev);
-
-	mlx4_unmap_catas_buf(dev);
-
 	mlx4_cleanup_mr_table(dev);
 	mlx4_cleanup_pd_table(dev);
 	mlx4_cleanup_uar_table(dev);
@@ -885,9 +879,6 @@ static void __devexit mlx4_remove_one(struct pci_dev *pdev)
 		mlx4_cleanup_cq_table(dev);
 		mlx4_cmd_use_polling(dev);
 		mlx4_cleanup_eq_table(dev);
-
-		mlx4_unmap_catas_buf(dev);
-
 		mlx4_cleanup_mr_table(dev);
 		mlx4_cleanup_pd_table(dev);
 
@@ -908,6 +899,12 @@ static void __devexit mlx4_remove_one(struct pci_dev *pdev)
 	}
 }
 
+int mlx4_restart_one(struct pci_dev *pdev)
+{
+	mlx4_remove_one(pdev);
+	return mlx4_init_one(pdev, NULL);
+}
+
 static struct pci_device_id mlx4_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x6340) }, /* MT25408 "Hermon" SDR */
 	{ PCI_VDEVICE(MELLANOX, 0x634a) }, /* MT25408 "Hermon" DDR */
@@ -930,6 +927,10 @@ static int __init mlx4_init(void)
 {
 	int ret;
 
+	ret = mlx4_catas_init();
+	if (ret)
+		return ret;
+
 	ret = pci_register_driver(&mlx4_driver);
 	return ret < 0 ? ret : 0;
 }
@@ -937,6 +938,7 @@ static int __init mlx4_init(void)
 static void __exit mlx4_cleanup(void)
 {
 	pci_unregister_driver(&mlx4_driver);
+	mlx4_catas_cleanup();
 }
 
 module_init(mlx4_init);

drivers/net/mlx4/mlx4.h

@@ -39,6 +39,7 @@
 
 #include <linux/mutex.h>
 #include <linux/radix-tree.h>
+#include <linux/timer.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -67,7 +68,6 @@ enum {
 enum {
 	MLX4_EQ_ASYNC,
 	MLX4_EQ_COMP,
-	MLX4_EQ_CATAS,
 	MLX4_NUM_EQ
 };
 
@@ -248,7 +248,8 @@ struct mlx4_mcg_table {
 
 struct mlx4_catas_err {
 	u32 __iomem	       *map;
-	int			size;
+	struct timer_list	timer;
+	struct list_head	list;
 };
 
 struct mlx4_priv {
@@ -311,9 +312,11 @@ void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
 void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
 
-void mlx4_map_catas_buf(struct mlx4_dev *dev);
-void mlx4_unmap_catas_buf(struct mlx4_dev *dev);
-
+void mlx4_start_catas_poll(struct mlx4_dev *dev);
+void mlx4_stop_catas_poll(struct mlx4_dev *dev);
+int mlx4_catas_init(void);
+void mlx4_catas_cleanup(void);
+int mlx4_restart_one(struct pci_dev *pdev);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_event type,