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: (87 commits)
  mlx4_core: Fix section mismatches
  IPoIB: Allow setting policy to ignore multicast groups
  IB/mthca: Mark error paths as unlikely() in post_srq_recv functions
  IB/ipath: Minor fix to ordering of freeing and zeroing of tid pages.
  IB/ipath: Remove redundant link state checks
  IB/ipath: Fix IB_EVENT_PORT_ERR event
  IB/ipath: Better handling of unexpected GPIO interrupts
  IB/ipath: Maintain active time on all chips
  IB/ipath: Fix QHT7040 serial number check
  IB/ipath: Indicate a couple of chip bugs to userspace
  IB/ipath: iba6110 rev4 no longer needs recv header overrun workaround
  IB/ipath: Use counters in ipath_poll and cleanup interrupts in ipath_close
  IB/ipath: Remove duplicate copy of LMC
  IB/ipath: Add ability to set the LMC via the sysfs debugging interface
  IB/ipath: Optimize completion queue entry insertion and polling
  IB/ipath: Implement IB_EVENT_QP_LAST_WQE_REACHED
  IB/ipath: Generate flush CQE when QP is in error state
  IB/ipath: Remove redundant code
  IB/ipath: Future proof eeprom checksum code (contents reading)
  IB/ipath: UC RDMA WRITE with IMMEDIATE doesn't send the immediate
  ...

12 files changed, 291 insertions, 111 deletions

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index c5c33d35f87d..5381c80de10a 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -161,8 +161,7 @@ static void addr_send_arp(struct sockaddr_in *dst_in)
         if (ip_route_output_key(&rt, &fl))
                 return;
 
-        arp_send(ARPOP_REQUEST, ETH_P_ARP, rt->rt_gateway, rt->idev->dev,
-                 rt->rt_src, NULL, rt->idev->dev->dev_addr, NULL);
+        neigh_event_send(rt->u.dst.neighbour, NULL);
         ip_rt_put(rt);
 }
 
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 4df269f5d9ac..2e39236d189f 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -2219,6 +2219,9 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 {
         struct cm_id_private *cm_id_priv;
         struct ib_mad_send_buf *msg;
+        enum ib_cm_state cm_state;
+        enum ib_cm_lap_state lap_state;
+        enum cm_msg_response msg_response;
         void *data;
         unsigned long flags;
         int ret;
@@ -2235,48 +2238,40 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
         spin_lock_irqsave(&cm_id_priv->lock, flags);
         switch(cm_id_priv->id.state) {
         case IB_CM_REQ_RCVD:
-                ret = cm_alloc_msg(cm_id_priv, &msg);
-                if (ret)
-                        goto error1;
-
-                cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-                              CM_MSG_RESPONSE_REQ, service_timeout,
-                              private_data, private_data_len);
-                ret = ib_post_send_mad(msg, NULL);
-                if (ret)
-                        goto error2;
-                cm_id->state = IB_CM_MRA_REQ_SENT;
+                cm_state = IB_CM_MRA_REQ_SENT;
+                lap_state = cm_id->lap_state;
+                msg_response = CM_MSG_RESPONSE_REQ;
                 break;
         case IB_CM_REP_RCVD:
-                ret = cm_alloc_msg(cm_id_priv, &msg);
-                if (ret)
-                        goto error1;
-
-                cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-                              CM_MSG_RESPONSE_REP, service_timeout,
-                              private_data, private_data_len);
-                ret = ib_post_send_mad(msg, NULL);
-                if (ret)
-                        goto error2;
-                cm_id->state = IB_CM_MRA_REP_SENT;
+                cm_state = IB_CM_MRA_REP_SENT;
+                lap_state = cm_id->lap_state;
+                msg_response = CM_MSG_RESPONSE_REP;
                 break;
         case IB_CM_ESTABLISHED:
+                cm_state = cm_id->state;
+                lap_state = IB_CM_MRA_LAP_SENT;
+                msg_response = CM_MSG_RESPONSE_OTHER;
+                break;
+        default:
+                ret = -EINVAL;
+                goto error1;
+        }
+
+        if (!(service_timeout & IB_CM_MRA_FLAG_DELAY)) {
                 ret = cm_alloc_msg(cm_id_priv, &msg);
                 if (ret)
                         goto error1;
 
                 cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
-                              CM_MSG_RESPONSE_OTHER, service_timeout,
+                              msg_response, service_timeout,
                               private_data, private_data_len);
                 ret = ib_post_send_mad(msg, NULL);
                 if (ret)
                         goto error2;
-                cm_id->lap_state = IB_CM_MRA_LAP_SENT;
-                break;
-        default:
-                ret = -EINVAL;
-                goto error1;
         }
+
+        cm_id->state = cm_state;
+        cm_id->lap_state = lap_state;
         cm_id_priv->service_timeout = service_timeout;
         cm_set_private_data(cm_id_priv, data, private_data_len);
         spin_unlock_irqrestore(&cm_id_priv->lock, flags);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 2e641b255db4..93644f82592c 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -52,6 +52,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 
 #define CMA_CM_RESPONSE_TIMEOUT 20
 #define CMA_MAX_CM_RETRIES 15
+#define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device);
@@ -138,6 +139,7 @@ struct rdma_id_private {
         u32                     qkey;
         u32                     qp_num;
         u8                      srq;
+        u8                      tos;
 };
 
 struct cma_multicast {
@@ -1089,6 +1091,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
                 event.param.ud.private_data_len =
                                 IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset;
         } else {
+                ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
                 conn_id = cma_new_conn_id(&listen_id->id, ib_event);
                 cma_set_req_event_data(&event, &ib_event->param.req_rcvd,
                                        ib_event->private_data, offset);
@@ -1474,6 +1477,15 @@ err:
 }
 EXPORT_SYMBOL(rdma_listen);
 
+void rdma_set_service_type(struct rdma_cm_id *id, int tos)
+{
+        struct rdma_id_private *id_priv;
+
+        id_priv = container_of(id, struct rdma_id_private, id);
+        id_priv->tos = (u8) tos;
+}
+EXPORT_SYMBOL(rdma_set_service_type);
+
 static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
                               void *context)
 {
@@ -1498,23 +1510,37 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
                               struct cma_work *work)
 {
-        struct rdma_dev_addr *addr = &id_priv->id.route.addr.dev_addr;
+        struct rdma_addr *addr = &id_priv->id.route.addr;
         struct ib_sa_path_rec path_rec;
+        ib_sa_comp_mask comp_mask;
+        struct sockaddr_in6 *sin6;
 
         memset(&path_rec, 0, sizeof path_rec);
-        ib_addr_get_sgid(addr, &path_rec.sgid);
-        ib_addr_get_dgid(addr, &path_rec.dgid);
-        path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(addr));
+        ib_addr_get_sgid(&addr->dev_addr, &path_rec.sgid);
+        ib_addr_get_dgid(&addr->dev_addr, &path_rec.dgid);
+        path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
         path_rec.numb_path = 1;
         path_rec.reversible = 1;
+        path_rec.service_id = cma_get_service_id(id_priv->id.ps, &addr->dst_addr);
+
+        comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
+                    IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
+                    IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;
+
+        if (addr->src_addr.sa_family == AF_INET) {
+                path_rec.qos_class = cpu_to_be16((u16) id_priv->tos);
+                comp_mask |= IB_SA_PATH_REC_QOS_CLASS;
+        } else {
+                sin6 = (struct sockaddr_in6 *) &addr->src_addr;
+                path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20);
+                comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS;
+        }
 
         id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device,
-                                id_priv->id.port_num, &path_rec,
-                                IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
-                                IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
-                                IB_SA_PATH_REC_REVERSIBLE,
-                                timeout_ms, GFP_KERNEL,
-                                cma_query_handler, work, &id_priv->query);
+                                               id_priv->id.port_num, &path_rec,
+                                               comp_mask, timeout_ms,
+                                               GFP_KERNEL, cma_query_handler,
+                                               work, &id_priv->query);
 
         return (id_priv->query_id < 0) ? id_priv->query_id : 0;
 }
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2506c43ba041..5ac5ffee05cb 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -120,12 +120,12 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 
 static int alloc_name(char *name)
 {
-        long *inuse;
+        unsigned long *inuse;
         char buf[IB_DEVICE_NAME_MAX];
         struct ib_device *device;
         int i;
 
-        inuse = (long *) get_zeroed_page(GFP_KERNEL);
+        inuse = (unsigned long *) get_zeroed_page(GFP_KERNEL);
         if (!inuse)
                 return -ENOMEM;
 
diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c
index a06bcc65a871..d7f64525469b 100644
--- a/drivers/infiniband/core/fmr_pool.c
+++ b/drivers/infiniband/core/fmr_pool.c
@@ -152,7 +152,7 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
 
 #ifdef DEBUG
                 if (fmr->ref_count !=0) {
-                        printk(KERN_WARNING PFX "Unmapping FMR 0x%08x with ref count %d",
+                        printk(KERN_WARNING PFX "Unmapping FMR 0x%08x with ref count %d\n",
                                fmr, fmr->ref_count);
                 }
 #endif
@@ -170,7 +170,7 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
 
         ret = ib_unmap_fmr(&fmr_list);
         if (ret)
-                printk(KERN_WARNING PFX "ib_unmap_fmr returned %d", ret);
+                printk(KERN_WARNING PFX "ib_unmap_fmr returned %d\n", ret);
 
         spin_lock_irq(&pool->pool_lock);
         list_splice(&unmap_list, &pool->free_list);
@@ -235,13 +235,13 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 
         attr = kmalloc(sizeof *attr, GFP_KERNEL);
         if (!attr) {
-                printk(KERN_WARNING PFX "couldn't allocate device attr struct");
+                printk(KERN_WARNING PFX "couldn't allocate device attr struct\n");
                 return ERR_PTR(-ENOMEM);
         }
 
         ret = ib_query_device(device, attr);
         if (ret) {
-                printk(KERN_WARNING PFX "couldn't query device: %d", ret);
+                printk(KERN_WARNING PFX "couldn't query device: %d\n", ret);
                 kfree(attr);
                 return ERR_PTR(ret);
         }
@@ -255,7 +255,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
 
         pool = kmalloc(sizeof *pool, GFP_KERNEL);
         if (!pool) {
-                printk(KERN_WARNING PFX "couldn't allocate pool struct");
+                printk(KERN_WARNING PFX "couldn't allocate pool struct\n");
                 return ERR_PTR(-ENOMEM);
         }
 
@@ -272,7 +272,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
                         kmalloc(IB_FMR_HASH_SIZE * sizeof *pool->cache_bucket,
                                 GFP_KERNEL);
                 if (!pool->cache_bucket) {
-                        printk(KERN_WARNING PFX "Failed to allocate cache in pool");
+                        printk(KERN_WARNING PFX "Failed to allocate cache in pool\n");
                         ret = -ENOMEM;
                         goto out_free_pool;
                 }
@@ -296,7 +296,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
                                       "ib_fmr(%s)",
                                       device->name);
         if (IS_ERR(pool->thread)) {
-                printk(KERN_WARNING PFX "couldn't start cleanup thread");
+                printk(KERN_WARNING PFX "couldn't start cleanup thread\n");
                 ret = PTR_ERR(pool->thread);
                 goto out_free_pool;
         }
@@ -314,7 +314,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
                                       GFP_KERNEL);
                         if (!fmr) {
                                 printk(KERN_WARNING PFX "failed to allocate fmr "
-                                       "struct for FMR %d", i);
+                                       "struct for FMR %d\n", i);
                                 goto out_fail;
                         }
 
@@ -326,7 +326,7 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd             *pd,
                         fmr->fmr = ib_alloc_fmr(pd, params->access, &fmr_attr);
                         if (IS_ERR(fmr->fmr)) {
                                 printk(KERN_WARNING PFX "fmr_create failed "
-                                       "for FMR %d", i);
+                                       "for FMR %d\n", i);
                                 kfree(fmr);
                                 goto out_fail;
                         }
@@ -381,7 +381,7 @@ void ib_destroy_fmr_pool(struct ib_fmr_pool *pool)
         }
 
         if (i < pool->pool_size)
-                printk(KERN_WARNING PFX "pool still has %d regions registered",
+                printk(KERN_WARNING PFX "pool still has %d regions registered\n",
                        pool->pool_size - i);
 
         kfree(pool->cache_bucket);
@@ -518,7 +518,7 @@ int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr)
 
 #ifdef DEBUG
         if (fmr->ref_count < 0)
-                printk(KERN_WARNING PFX "FMR %p has ref count %d < 0",
+                printk(KERN_WARNING PFX "FMR %p has ref count %d < 0\n",
                        fmr, fmr->ref_count);
 #endif
 
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index 15b4c4d3606d..1bc1fe605282 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -196,7 +196,7 @@ static void queue_join(struct mcast_member *member)
         unsigned long flags;
 
         spin_lock_irqsave(&group->lock, flags);
-        list_add(&member->list, &group->pending_list);
+        list_add_tail(&member->list, &group->pending_list);
         if (group->state == MCAST_IDLE) {
                 group->state = MCAST_BUSY;
                 atomic_inc(&group->refcount);
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index d271bd715c12..cf474ec27070 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -123,14 +123,10 @@ static u32 tid;
         .field_name          = "sa_path_rec:" #field
 
 static const struct ib_field path_rec_table[] = {
-        { RESERVED,
+        { PATH_REC_FIELD(service_id),
           .offset_words = 0,
           .offset_bits  = 0,
-          .size_bits    = 32 },
-        { RESERVED,
-          .offset_words = 1,
-          .offset_bits  = 0,
-          .size_bits    = 32 },
+          .size_bits    = 64 },
         { PATH_REC_FIELD(dgid),
           .offset_words = 2,
           .offset_bits  = 0,
@@ -179,7 +175,7 @@ static const struct ib_field path_rec_table[] = {
           .offset_words = 12,
           .offset_bits  = 16,
           .size_bits    = 16 },
-        { RESERVED,
+        { PATH_REC_FIELD(qos_class),
           .offset_words = 13,
           .offset_bits  = 0,
           .size_bits    = 12 },
@@ -531,7 +527,7 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
                                             query->sm_ah->pkey_index,
                                             0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
                                             gfp_mask);
-        if (!query->mad_buf) {
+        if (IS_ERR(query->mad_buf)) {
                 kref_put(&query->sm_ah->ref, free_sm_ah);
                 return -ENOMEM;
         }
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 53b4c94a7eb5..90d675ad9ec8 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -792,6 +792,78 @@ out:
         return ret;
 }
 
+static int ucma_set_option_id(struct ucma_context *ctx, int optname,
+                              void *optval, size_t optlen)
+{
+        int ret = 0;
+
+        switch (optname) {
+        case RDMA_OPTION_ID_TOS:
+                if (optlen != sizeof(u8)) {
+                        ret = -EINVAL;
+                        break;
+                }
+                rdma_set_service_type(ctx->cm_id, *((u8 *) optval));
+                break;
+        default:
+                ret = -ENOSYS;
+        }
+
+        return ret;
+}
+
+static int ucma_set_option_level(struct ucma_context *ctx, int level,
+                                 int optname, void *optval, size_t optlen)
+{
+        int ret;
+
+        switch (level) {
+        case RDMA_OPTION_ID:
+                ret = ucma_set_option_id(ctx, optname, optval, optlen);
+                break;
+        default:
+                ret = -ENOSYS;
+        }
+
+        return ret;
+}
+
+static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf,
+                               int in_len, int out_len)
+{
+        struct rdma_ucm_set_option cmd;
+        struct ucma_context *ctx;
+        void *optval;
+        int ret;
+
+        if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
+                return -EFAULT;
+
+        ctx = ucma_get_ctx(file, cmd.id);
+        if (IS_ERR(ctx))
+                return PTR_ERR(ctx);
+
+        optval = kmalloc(cmd.optlen, GFP_KERNEL);
+        if (!optval) {
+                ret = -ENOMEM;
+                goto out1;
+        }
+
+        if (copy_from_user(optval, (void __user *) (unsigned long) cmd.optval,
+                           cmd.optlen)) {
+                ret = -EFAULT;
+                goto out2;
+        }
+
+        ret = ucma_set_option_level(ctx, cmd.level, cmd.optname, optval,
+                                    cmd.optlen);
+out2:
+        kfree(optval);
+out1:
+        ucma_put_ctx(ctx);
+        return ret;
+}
+
 static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf,
                            int in_len, int out_len)
 {
@@ -936,7 +1008,7 @@ static ssize_t (*ucma_cmd_table[])(struct ucma_file *file,
         [RDMA_USER_CM_CMD_INIT_QP_ATTR] = ucma_init_qp_attr,
         [RDMA_USER_CM_CMD_GET_EVENT]    = ucma_get_event,
         [RDMA_USER_CM_CMD_GET_OPTION]   = NULL,
-        [RDMA_USER_CM_CMD_SET_OPTION]   = NULL,
+        [RDMA_USER_CM_CMD_SET_OPTION]   = ucma_set_option,
         [RDMA_USER_CM_CMD_NOTIFY]       = ucma_notify,
         [RDMA_USER_CM_CMD_JOIN_MCAST]   = ucma_join_multicast,
         [RDMA_USER_CM_CMD_LEAVE_MCAST]  = ucma_leave_multicast,
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 664d2faa9e74..2f54e29dc7a6 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -37,6 +37,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 
 #include "uverbs.h"
 
@@ -75,6 +76,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 {
         struct ib_umem *umem;
         struct page **page_list;
+        struct vm_area_struct **vma_list;
         struct ib_umem_chunk *chunk;
         unsigned long locked;
         unsigned long lock_limit;
@@ -104,6 +106,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
          */
         umem->writable  = !!(access & ~IB_ACCESS_REMOTE_READ);
 
+        /* We assume the memory is from hugetlb until proved otherwise */
+        umem->hugetlb   = 1;
+
         INIT_LIST_HEAD(&umem->chunk_list);
 
         page_list = (struct page **) __get_free_page(GFP_KERNEL);
@@ -112,6 +117,14 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
                 return ERR_PTR(-ENOMEM);
         }
 
+        /*
+         * if we can't alloc the vma_list, it's not so bad;
+         * just assume the memory is not hugetlb memory
+         */
+        vma_list = (struct vm_area_struct **) __get_free_page(GFP_KERNEL);
+        if (!vma_list)
+                umem->hugetlb = 0;
+
         npages = PAGE_ALIGN(size + umem->offset) >> PAGE_SHIFT;
 
         down_write(&current->mm->mmap_sem);
@@ -131,7 +144,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
                 ret = get_user_pages(current, current->mm, cur_base,
                                      min_t(int, npages,
                                            PAGE_SIZE / sizeof (struct page *)),
-                                     1, !umem->writable, page_list, NULL);
+                                     1, !umem->writable, page_list, vma_list);
 
                 if (ret < 0)
                         goto out;
@@ -152,6 +165,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
                         chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK);
                         for (i = 0; i < chunk->nents; ++i) {
+                                if (vma_list &&
+                                    !is_vm_hugetlb_page(vma_list[i + off]))
+                                        umem->hugetlb = 0;
                                 chunk->page_list[i].page   = page_list[i + off];
                                 chunk->page_list[i].offset = 0;
                                 chunk->page_list[i].length = PAGE_SIZE;
@@ -186,6 +202,8 @@ out:
                 current->mm->locked_vm = locked;
 
         up_write(&current->mm->mmap_sem);
+        if (vma_list)
+                free_page((unsigned long) vma_list);
         free_page((unsigned long) page_list);
 
         return ret < 0 ? ERR_PTR(ret) : umem;
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index d97ded25c4ff..b53eac4611de 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -44,6 +44,7 @@
 #include <linux/poll.h>
 #include <linux/rwsem.h>
 #include <linux/kref.h>
+#include <linux/compat.h>
 
 #include <asm/uaccess.h>
 #include <asm/semaphore.h>
@@ -118,6 +119,8 @@ struct ib_umad_file {
         wait_queue_head_t       recv_wait;
         struct ib_mad_agent    *agent[IB_UMAD_MAX_AGENTS];
         int                     agents_dead;
+        u8                      use_pkey_index;
+        u8                      already_used;
 };
 
 struct ib_umad_packet {
@@ -147,6 +150,12 @@ static void ib_umad_release_dev(struct kref *ref)
         kfree(dev);
 }
 
+static int hdr_size(struct ib_umad_file *file)
+{
+        return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
+                sizeof (struct ib_user_mad_hdr_old);
+}
+
 /* caller must hold port->mutex at least for reading */
 static struct ib_mad_agent *__get_agent(struct ib_umad_file *file, int id)
 {
@@ -221,13 +230,13 @@ static void recv_handler(struct ib_mad_agent *agent,
         packet->length = mad_recv_wc->mad_len;
         packet->recv_wc = mad_recv_wc;
 
-        packet->mad.hdr.status    = 0;
-        packet->mad.hdr.length    = sizeof (struct ib_user_mad) +
-                                    mad_recv_wc->mad_len;
-        packet->mad.hdr.qpn       = cpu_to_be32(mad_recv_wc->wc->src_qp);
-        packet->mad.hdr.lid       = cpu_to_be16(mad_recv_wc->wc->slid);
-        packet->mad.hdr.sl        = mad_recv_wc->wc->sl;
-        packet->mad.hdr.path_bits = mad_recv_wc->wc->dlid_path_bits;
+        packet->mad.hdr.status     = 0;
+        packet->mad.hdr.length     = hdr_size(file) + mad_recv_wc->mad_len;
+        packet->mad.hdr.qpn        = cpu_to_be32(mad_recv_wc->wc->src_qp);
+        packet->mad.hdr.lid        = cpu_to_be16(mad_recv_wc->wc->slid);
+        packet->mad.hdr.sl         = mad_recv_wc->wc->sl;
+        packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
+        packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;
         packet->mad.hdr.grh_present = !!(mad_recv_wc->wc->wc_flags & IB_WC_GRH);
         if (packet->mad.hdr.grh_present) {
                 struct ib_ah_attr ah_attr;
@@ -253,8 +262,8 @@ err1:
         ib_free_recv_mad(mad_recv_wc);
 }
 
-static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
-                             size_t count)
+static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
+                             struct ib_umad_packet *packet, size_t count)
 {
         struct ib_mad_recv_buf *recv_buf;
         int left, seg_payload, offset, max_seg_payload;
@@ -262,15 +271,15 @@ static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
         /* We need enough room to copy the first (or only) MAD segment. */
         recv_buf = &packet->recv_wc->recv_buf;
         if ((packet->length <= sizeof (*recv_buf->mad) &&
-             count < sizeof (packet->mad) + packet->length) ||
+             count < hdr_size(file) + packet->length) ||
             (packet->length > sizeof (*recv_buf->mad) &&
-             count < sizeof (packet->mad) + sizeof (*recv_buf->mad)))
+             count < hdr_size(file) + sizeof (*recv_buf->mad)))
                 return -EINVAL;
 
-        if (copy_to_user(buf, &packet->mad, sizeof (packet->mad)))
+        if (copy_to_user(buf, &packet->mad, hdr_size(file)))
                 return -EFAULT;
 
-        buf += sizeof (packet->mad);
+        buf += hdr_size(file);
         seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
         if (copy_to_user(buf, recv_buf->mad, seg_payload))
                 return -EFAULT;
@@ -280,7 +289,7 @@ static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
                  * Multipacket RMPP MAD message. Copy remainder of message.
                  * Note that last segment may have a shorter payload.
                  */
-                if (count < sizeof (packet->mad) + packet->length) {
+                if (count < hdr_size(file) + packet->length) {
                         /*
                          * The buffer is too small, return the first RMPP segment,
                          * which includes the RMPP message length.
@@ -300,18 +309,23 @@ static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
                                 return -EFAULT;
                 }
         }
-        return sizeof (packet->mad) + packet->length;
+        return hdr_size(file) + packet->length;
 }
 
-static ssize_t copy_send_mad(char __user *buf, struct ib_umad_packet *packet,
-                             size_t count)
+static ssize_t copy_send_mad(struct ib_umad_file *file, char __user *buf,
+                             struct ib_umad_packet *packet, size_t count)
 {
-        ssize_t size = sizeof (packet->mad) + packet->length;
+        ssize_t size = hdr_size(file) + packet->length;
 
         if (count < size)
                 return -EINVAL;
 
-        if (copy_to_user(buf, &packet->mad, size))
+        if (copy_to_user(buf, &packet->mad, hdr_size(file)))
+                return -EFAULT;
+
+        buf += hdr_size(file);
+
+        if (copy_to_user(buf, packet->mad.data, packet->length))
                 return -EFAULT;
 
         return size;
@@ -324,7 +338,7 @@ static ssize_t ib_umad_read(struct file *filp, char __user *buf,
         struct ib_umad_packet *packet;
         ssize_t ret;
 
-        if (count < sizeof (struct ib_user_mad))
+        if (count < hdr_size(file))
                 return -EINVAL;
 
         spin_lock_irq(&file->recv_lock);
@@ -348,9 +362,9 @@ static ssize_t ib_umad_read(struct file *filp, char __user *buf,
         spin_unlock_irq(&file->recv_lock);
 
         if (packet->recv_wc)
-                ret = copy_recv_mad(buf, packet, count);
+                ret = copy_recv_mad(file, buf, packet, count);
         else
-                ret = copy_send_mad(buf, packet, count);
+                ret = copy_send_mad(file, buf, packet, count);
 
         if (ret < 0) {
                 /* Requeue packet */
@@ -442,15 +456,14 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
         __be64 *tid;
         int ret, data_len, hdr_len, copy_offset, rmpp_active;
 
-        if (count < sizeof (struct ib_user_mad) + IB_MGMT_RMPP_HDR)
+        if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
                 return -EINVAL;
 
         packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
         if (!packet)
                 return -ENOMEM;
 
-        if (copy_from_user(&packet->mad, buf,
-                            sizeof (struct ib_user_mad) + IB_MGMT_RMPP_HDR)) {
+        if (copy_from_user(&packet->mad, buf, hdr_size(file))) {
                 ret = -EFAULT;
                 goto err;
         }
@@ -461,6 +474,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
                 goto err;
         }
 
+        buf += hdr_size(file);
+
+        if (copy_from_user(packet->mad.data, buf, IB_MGMT_RMPP_HDR)) {
+                ret = -EFAULT;
+                goto err;
+        }
+
         down_read(&file->port->mutex);
 
         agent = __get_agent(file, packet->mad.hdr.id);
@@ -500,11 +520,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
                               IB_MGMT_RMPP_FLAG_ACTIVE;
         }
 
-        data_len = count - sizeof (struct ib_user_mad) - hdr_len;
+        data_len = count - hdr_size(file) - hdr_len;
         packet->msg = ib_create_send_mad(agent,
                                          be32_to_cpu(packet->mad.hdr.qpn),
-                                         0, rmpp_active, hdr_len,
-                                         data_len, GFP_KERNEL);
+                                         packet->mad.hdr.pkey_index, rmpp_active,
+                                         hdr_len, data_len, GFP_KERNEL);
         if (IS_ERR(packet->msg)) {
                 ret = PTR_ERR(packet->msg);
                 goto err_ah;
@@ -517,7 +537,6 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 
         /* Copy MAD header.  Any RMPP header is already in place. */
         memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);
-        buf += sizeof (struct ib_user_mad);
 
         if (!rmpp_active) {
                 if (copy_from_user(packet->msg->mad + copy_offset,
@@ -589,7 +608,8 @@ static unsigned int ib_umad_poll(struct file *filp, struct poll_table_struct *wa
         return mask;
 }
 
-static int ib_umad_reg_agent(struct ib_umad_file *file, unsigned long arg)
+static int ib_umad_reg_agent(struct ib_umad_file *file, void __user *arg,
+                             int compat_method_mask)
 {
         struct ib_user_mad_reg_req ureq;
         struct ib_mad_reg_req req;
@@ -604,7 +624,7 @@ static int ib_umad_reg_agent(struct ib_umad_file *file, unsigned long arg)
                 goto out;
         }
 
-        if (copy_from_user(&ureq, (void __user *) arg, sizeof ureq)) {
+        if (copy_from_user(&ureq, arg, sizeof ureq)) {
                 ret = -EFAULT;
                 goto out;
         }
@@ -625,8 +645,18 @@ found:
         if (ureq.mgmt_class) {
                 req.mgmt_class         = ureq.mgmt_class;
                 req.mgmt_class_version = ureq.mgmt_class_version;
-                memcpy(req.method_mask, ureq.method_mask, sizeof req.method_mask);
-                memcpy(req.oui,         ureq.oui,         sizeof req.oui);
+                memcpy(req.oui, ureq.oui, sizeof req.oui);
+
+                if (compat_method_mask) {
+                        u32 *umm = (u32 *) ureq.method_mask;
+                        int i;
+
+                        for (i = 0; i < BITS_TO_LONGS(IB_MGMT_MAX_METHODS); ++i)
+                                req.method_mask[i] =
+                                        umm[i * 2] | ((u64) umm[i * 2 + 1] << 32);
+                } else
+                        memcpy(req.method_mask, ureq.method_mask,
+                               sizeof req.method_mask);
         }
 
         agent = ib_register_mad_agent(file->port->ib_dev, file->port->port_num,
@@ -646,6 +676,16 @@ found:
                 goto out;
         }
 
+        if (!file->already_used) {
+                file->already_used = 1;
+                if (!file->use_pkey_index) {
+                        printk(KERN_WARNING "user_mad: process %s did not enable "
+                               "P_Key index support.\n", current->comm);
+                        printk(KERN_WARNING "user_mad:   Documentation/infiniband/user_mad.txt "
+                               "has info on the new ABI.\n");
+                }
+        }
+
         file->agent[agent_id] = agent;
         ret = 0;
 
@@ -654,13 +694,13 @@ out:
         return ret;
 }
 
-static int ib_umad_unreg_agent(struct ib_umad_file *file, unsigned long arg)
+static int ib_umad_unreg_agent(struct ib_umad_file *file, u32 __user *arg)
 {
         struct ib_mad_agent *agent = NULL;
         u32 id;
         int ret = 0;
 
-        if (get_user(id, (u32 __user *) arg))
+        if (get_user(id, arg))
                 return -EFAULT;
 
         down_write(&file->port->mutex);
@@ -682,18 +722,51 @@ out:
         return ret;
 }
 
+static long ib_umad_enable_pkey(struct ib_umad_file *file)
+{
+        int ret = 0;
+
+        down_write(&file->port->mutex);
+        if (file->already_used)
+                ret = -EINVAL;
+        else
+                file->use_pkey_index = 1;
+        up_write(&file->port->mutex);
+
+        return ret;
+}
+
 static long ib_umad_ioctl(struct file *filp, unsigned int cmd,
                           unsigned long arg)
 {
         switch (cmd) {
         case IB_USER_MAD_REGISTER_AGENT:
-                return ib_umad_reg_agent(filp->private_data, arg);
+                return ib_umad_reg_agent(filp->private_data, (void __user *) arg, 0);
+        case IB_USER_MAD_UNREGISTER_AGENT:
+                return ib_umad_unreg_agent(filp->private_data, (__u32 __user *) arg);
+        case IB_USER_MAD_ENABLE_PKEY:
+                return ib_umad_enable_pkey(filp->private_data);
+        default:
+                return -ENOIOCTLCMD;
+        }
+}
+
+#ifdef CONFIG_COMPAT
+static long ib_umad_compat_ioctl(struct file *filp, unsigned int cmd,
+                                 unsigned long arg)
+{
+        switch (cmd) {
+        case IB_USER_MAD_REGISTER_AGENT:
+                return ib_umad_reg_agent(filp->private_data, compat_ptr(arg), 1);
         case IB_USER_MAD_UNREGISTER_AGENT:
-                return ib_umad_unreg_agent(filp->private_data, arg);
+                return ib_umad_unreg_agent(filp->private_data, compat_ptr(arg));
+        case IB_USER_MAD_ENABLE_PKEY:
+                return ib_umad_enable_pkey(filp->private_data);
         default:
                 return -ENOIOCTLCMD;
         }
 }
+#endif
 
 static int ib_umad_open(struct inode *inode, struct file *filp)
 {
@@ -782,7 +855,9 @@ static const struct file_operations umad_fops = {
         .write          = ib_umad_write,
         .poll           = ib_umad_poll,
         .unlocked_ioctl = ib_umad_ioctl,
-        .compat_ioctl   = ib_umad_ioctl,
+#ifdef CONFIG_COMPAT
+        .compat_ioctl   = ib_umad_compat_ioctl,
+#endif
         .open           = ib_umad_open,
         .release        = ib_umad_close
 };
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index c33546f9e961..c75eb6c9bd49 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -148,7 +148,6 @@ void idr_remove_uobj(struct idr *idp, struct ib_uobject *uobj);
 
 struct file *ib_uverbs_alloc_event_file(struct ib_uverbs_file *uverbs_file,
                                         int is_async, int *fd);
-void ib_uverbs_release_event_file(struct kref *ref);
 struct ib_uverbs_event_file *ib_uverbs_lookup_comp_file(int fd);
 
 void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 14d7ccd89195..7c2ac3905582 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -125,6 +125,14 @@ static void ib_uverbs_release_dev(struct kref *ref)
         complete(&dev->comp);
 }
 
+static void ib_uverbs_release_event_file(struct kref *ref)
+{
+        struct ib_uverbs_event_file *file =
+                container_of(ref, struct ib_uverbs_event_file, ref);
+
+        kfree(file);
+}
+
 void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
                           struct ib_uverbs_event_file *ev_file,
                           struct ib_ucq_object *uobj)
@@ -331,14 +339,6 @@ static unsigned int ib_uverbs_event_poll(struct file *filp,
         return pollflags;
 }
 
-void ib_uverbs_release_event_file(struct kref *ref)
-{
-        struct ib_uverbs_event_file *file =
-                container_of(ref, struct ib_uverbs_event_file, ref);
-
-        kfree(file);
-}
-
 static int ib_uverbs_event_fasync(int fd, struct file *filp, int on)
 {
         struct ib_uverbs_event_file *file = filp->private_data;