Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

12 files changed, 118 insertions, 102 deletions

diff --git a/drivers/infiniband/hw/amso1100/c2.c b/drivers/infiniband/hw/amso1100/c2.c
index dc1ebeac35c7..9e7bd94b958a 100644
--- a/drivers/infiniband/hw/amso1100/c2.c
+++ b/drivers/infiniband/hw/amso1100/c2.c
@@ -1243,7 +1243,7 @@ static struct pci_driver c2_pci_driver = {
 
 static int __init c2_init_module(void)
 {
-	return pci_module_init(&c2_pci_driver);
+	return pci_register_driver(&c2_pci_driver);
 }
 
 static void __exit c2_exit_module(void)
diff --git a/drivers/infiniband/hw/amso1100/c2_alloc.c b/drivers/infiniband/hw/amso1100/c2_alloc.c
index 028a60bbfca9..0315f99e4191 100644
--- a/drivers/infiniband/hw/amso1100/c2_alloc.c
+++ b/drivers/infiniband/hw/amso1100/c2_alloc.c
@@ -42,13 +42,14 @@ static int c2_alloc_mqsp_chunk(struct c2_dev *c2dev, gfp_t gfp_mask,
 {
 	int i;
 	struct sp_chunk *new_head;
+	dma_addr_t dma_addr;
 
-	new_head = (struct sp_chunk *) __get_free_page(gfp_mask);
+	new_head = dma_alloc_coherent(&c2dev->pcidev->dev, PAGE_SIZE,
+				      &dma_addr, gfp_mask);
 	if (new_head == NULL)
 		return -ENOMEM;
 
-	new_head->dma_addr = dma_map_single(c2dev->ibdev.dma_device, new_head,
-					    PAGE_SIZE, DMA_FROM_DEVICE);
+	new_head->dma_addr = dma_addr;
 	pci_unmap_addr_set(new_head, mapping, new_head->dma_addr);
 
 	new_head->next = NULL;
@@ -80,10 +81,8 @@ void c2_free_mqsp_pool(struct c2_dev *c2dev, struct sp_chunk *root)
 
 	while (root) {
 		next = root->next;
-		dma_unmap_single(c2dev->ibdev.dma_device,
-				 pci_unmap_addr(root, mapping), PAGE_SIZE,
-			         DMA_FROM_DEVICE);
-		__free_page((struct page *) root);
+		dma_free_coherent(&c2dev->pcidev->dev, PAGE_SIZE, root,
+				  pci_unmap_addr(root, mapping));
 		root = next;
 	}
 }
diff --git a/drivers/infiniband/hw/amso1100/c2_cq.c b/drivers/infiniband/hw/amso1100/c2_cq.c
index 9d7bcc5ade93..05c9154d46f4 100644
--- a/drivers/infiniband/hw/amso1100/c2_cq.c
+++ b/drivers/infiniband/hw/amso1100/c2_cq.c
@@ -246,20 +246,17 @@ int c2_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify notify)
 
 static void c2_free_cq_buf(struct c2_dev *c2dev, struct c2_mq *mq)
 {
-
-	dma_unmap_single(c2dev->ibdev.dma_device, pci_unmap_addr(mq, mapping),
-			 mq->q_size * mq->msg_size, DMA_FROM_DEVICE);
-	free_pages((unsigned long) mq->msg_pool.host,
-		   get_order(mq->q_size * mq->msg_size));
+	dma_free_coherent(&c2dev->pcidev->dev, mq->q_size * mq->msg_size,
+			  mq->msg_pool.host, pci_unmap_addr(mq, mapping));
 }
 
 static int c2_alloc_cq_buf(struct c2_dev *c2dev, struct c2_mq *mq, int q_size,
 			   int msg_size)
 {
-	unsigned long pool_start;
+	u8 *pool_start;
 
-	pool_start = __get_free_pages(GFP_KERNEL,
-				      get_order(q_size * msg_size));
+	pool_start = dma_alloc_coherent(&c2dev->pcidev->dev, q_size * msg_size,
+					&mq->host_dma, GFP_KERNEL);
 	if (!pool_start)
 		return -ENOMEM;
 
@@ -267,13 +264,10 @@ static int c2_alloc_cq_buf(struct c2_dev *c2dev, struct c2_mq *mq, int q_size,
 		       0,		/* index (currently unknown) */
 		       q_size,
 		       msg_size,
-		       (u8 *) pool_start,
+		       pool_start,
 		       NULL,	/* peer (currently unknown) */
 		       C2_MQ_HOST_TARGET);
 
-	mq->host_dma = dma_map_single(c2dev->ibdev.dma_device,
-				      (void *)pool_start,
-				      q_size * msg_size, DMA_FROM_DEVICE);
 	pci_unmap_addr_set(mq, mapping, mq->host_dma);
 
 	return 0;
diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c
index e37c5688c214..21d9612a56cc 100644
--- a/drivers/infiniband/hw/amso1100/c2_rnic.c
+++ b/drivers/infiniband/hw/amso1100/c2_rnic.c
@@ -150,8 +150,8 @@ static int c2_rnic_query(struct c2_dev *c2dev, struct ib_device_attr *props)
 	    (struct c2wr_rnic_query_rep *) (unsigned long) (vq_req->reply_msg);
 	if (!reply)
 		err = -ENOMEM;
-
-	err = c2_errno(reply);
+	else
+		err = c2_errno(reply);
 	if (err)
 		goto bail2;
 
@@ -517,14 +517,12 @@ int c2_rnic_init(struct c2_dev *c2dev)
 	/* Initialize the Verbs Reply Queue */
 	qsize = be32_to_cpu(readl(mmio_regs + C2_REGS_Q1_QSIZE));
 	msgsize = be32_to_cpu(readl(mmio_regs + C2_REGS_Q1_MSGSIZE));
-	q1_pages = kmalloc(qsize * msgsize, GFP_KERNEL);
+	q1_pages = dma_alloc_coherent(&c2dev->pcidev->dev, qsize * msgsize,
+				      &c2dev->rep_vq.host_dma, GFP_KERNEL);
 	if (!q1_pages) {
 		err = -ENOMEM;
 		goto bail1;
 	}
-	c2dev->rep_vq.host_dma = dma_map_single(c2dev->ibdev.dma_device,
-					        (void *)q1_pages, qsize * msgsize,
-				      		DMA_FROM_DEVICE);
 	pci_unmap_addr_set(&c2dev->rep_vq, mapping, c2dev->rep_vq.host_dma);
 	pr_debug("%s rep_vq va %p dma %llx\n", __FUNCTION__, q1_pages,
 		 (unsigned long long) c2dev->rep_vq.host_dma);
@@ -540,17 +538,15 @@ int c2_rnic_init(struct c2_dev *c2dev)
 	/* Initialize the Asynchronus Event Queue */
 	qsize = be32_to_cpu(readl(mmio_regs + C2_REGS_Q2_QSIZE));
 	msgsize = be32_to_cpu(readl(mmio_regs + C2_REGS_Q2_MSGSIZE));
-	q2_pages = kmalloc(qsize * msgsize, GFP_KERNEL);
+	q2_pages = dma_alloc_coherent(&c2dev->pcidev->dev, qsize * msgsize,
+				      &c2dev->aeq.host_dma, GFP_KERNEL);
 	if (!q2_pages) {
 		err = -ENOMEM;
 		goto bail2;
 	}
-	c2dev->aeq.host_dma = dma_map_single(c2dev->ibdev.dma_device,
-					        (void *)q2_pages, qsize * msgsize,
-				      		DMA_FROM_DEVICE);
 	pci_unmap_addr_set(&c2dev->aeq, mapping, c2dev->aeq.host_dma);
-	pr_debug("%s aeq va %p dma %llx\n", __FUNCTION__, q1_pages,
-		 (unsigned long long) c2dev->rep_vq.host_dma);
+	pr_debug("%s aeq va %p dma %llx\n", __FUNCTION__, q2_pages,
+		 (unsigned long long) c2dev->aeq.host_dma);
 	c2_mq_rep_init(&c2dev->aeq,
 		       2,
 		       qsize,
@@ -597,17 +593,13 @@ int c2_rnic_init(struct c2_dev *c2dev)
       bail4:
 	vq_term(c2dev);
       bail3:
-	dma_unmap_single(c2dev->ibdev.dma_device,
-			 pci_unmap_addr(&c2dev->aeq, mapping),
-			 c2dev->aeq.q_size * c2dev->aeq.msg_size,
-		  	 DMA_FROM_DEVICE);
-	kfree(q2_pages);
+	dma_free_coherent(&c2dev->pcidev->dev,
+			  c2dev->aeq.q_size * c2dev->aeq.msg_size,
+			  q2_pages, pci_unmap_addr(&c2dev->aeq, mapping));
       bail2:
-	dma_unmap_single(c2dev->ibdev.dma_device,
-			 pci_unmap_addr(&c2dev->rep_vq, mapping),
-			 c2dev->rep_vq.q_size * c2dev->rep_vq.msg_size,
-		  	 DMA_FROM_DEVICE);
-	kfree(q1_pages);
+	dma_free_coherent(&c2dev->pcidev->dev,
+			  c2dev->rep_vq.q_size * c2dev->rep_vq.msg_size,
+			  q1_pages, pci_unmap_addr(&c2dev->rep_vq, mapping));
       bail1:
 	c2_free_mqsp_pool(c2dev, c2dev->kern_mqsp_pool);
       bail0:
@@ -640,19 +632,17 @@ void c2_rnic_term(struct c2_dev *c2dev)
 	/* Free the verbs request allocator */
 	vq_term(c2dev);
 
-	/* Unmap and free the asynchronus event queue */
-	dma_unmap_single(c2dev->ibdev.dma_device,
-			 pci_unmap_addr(&c2dev->aeq, mapping),
-			 c2dev->aeq.q_size * c2dev->aeq.msg_size,
-		  	 DMA_FROM_DEVICE);
-	kfree(c2dev->aeq.msg_pool.host);
-
-	/* Unmap and free the verbs reply queue */
-	dma_unmap_single(c2dev->ibdev.dma_device,
-			 pci_unmap_addr(&c2dev->rep_vq, mapping),
-			 c2dev->rep_vq.q_size * c2dev->rep_vq.msg_size,
-		  	 DMA_FROM_DEVICE);
-	kfree(c2dev->rep_vq.msg_pool.host);
+	/* Free the asynchronus event queue */
+	dma_free_coherent(&c2dev->pcidev->dev,
+			  c2dev->aeq.q_size * c2dev->aeq.msg_size,
+			  c2dev->aeq.msg_pool.host,
+			  pci_unmap_addr(&c2dev->aeq, mapping));
+
+	/* Free the verbs reply queue */
+	dma_free_coherent(&c2dev->pcidev->dev,
+			  c2dev->rep_vq.q_size * c2dev->rep_vq.msg_size,
+			  c2dev->rep_vq.msg_pool.host,
+			  pci_unmap_addr(&c2dev->rep_vq, mapping));
 
 	/* Free the MQ shared pointer pool */
 	c2_free_mqsp_pool(c2dev, c2dev->kern_mqsp_pool);
diff --git a/drivers/infiniband/hw/ehca/ehca_tools.h b/drivers/infiniband/hw/ehca/ehca_tools.h
index 809da3ef706b..973c4b591545 100644
--- a/drivers/infiniband/hw/ehca/ehca_tools.h
+++ b/drivers/infiniband/hw/ehca/ehca_tools.h
@@ -63,6 +63,7 @@
 #include <asm/ibmebus.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
+#include <asm/hvcall.h>
 
 extern int ehca_debug_level;
 
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index 29958b6e0214..28c087b824c2 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -67,19 +67,54 @@ static struct file_operations diag_file_ops = {
 	.release = ipath_diag_release
 };
 
+static ssize_t ipath_diagpkt_write(struct file *fp,
+				   const char __user *data,
+				   size_t count, loff_t *off);
+
+static struct file_operations diagpkt_file_ops = {
+	.owner = THIS_MODULE,
+	.write = ipath_diagpkt_write,
+};
+
+static atomic_t diagpkt_count = ATOMIC_INIT(0);
+static struct cdev *diagpkt_cdev;
+static struct class_device *diagpkt_class_dev;
+
 int ipath_diag_add(struct ipath_devdata *dd)
 {
 	char name[16];
+	int ret = 0;
+
+	if (atomic_inc_return(&diagpkt_count) == 1) {
+		ret = ipath_cdev_init(IPATH_DIAGPKT_MINOR,
+				      "ipath_diagpkt", &diagpkt_file_ops,
+				      &diagpkt_cdev, &diagpkt_class_dev);
+
+		if (ret) {
+			ipath_dev_err(dd, "Couldn't create ipath_diagpkt "
+				      "device: %d", ret);
+			goto done;
+		}
+	}
 
 	snprintf(name, sizeof(name), "ipath_diag%d", dd->ipath_unit);
 
-	return ipath_cdev_init(IPATH_DIAG_MINOR_BASE + dd->ipath_unit, name,
-			       &diag_file_ops, &dd->diag_cdev,
-			       &dd->diag_class_dev);
+	ret = ipath_cdev_init(IPATH_DIAG_MINOR_BASE + dd->ipath_unit, name,
+			      &diag_file_ops, &dd->diag_cdev,
+			      &dd->diag_class_dev);
+	if (ret)
+		ipath_dev_err(dd, "Couldn't create %s device: %d",
+			      name, ret);
+
+done:
+	return ret;
 }
 
 void ipath_diag_remove(struct ipath_devdata *dd)
 {
+	if (atomic_dec_and_test(&diagpkt_count))
+		ipath_cdev_cleanup(&diagpkt_cdev, &diagpkt_class_dev);
+
 	ipath_cdev_cleanup(&dd->diag_cdev, &dd->diag_class_dev);
 }
 
@@ -275,30 +310,6 @@ bail:
 	return ret;
 }
 
-static ssize_t ipath_diagpkt_write(struct file *fp,
-				   const char __user *data,
-				   size_t count, loff_t *off);
-
-static struct file_operations diagpkt_file_ops = {
-	.owner = THIS_MODULE,
-	.write = ipath_diagpkt_write,
-};
-
-static struct cdev *diagpkt_cdev;
-static struct class_device *diagpkt_class_dev;
-
-int __init ipath_diagpkt_add(void)
-{
-	return ipath_cdev_init(IPATH_DIAGPKT_MINOR,
-			       "ipath_diagpkt", &diagpkt_file_ops,
-			       &diagpkt_cdev, &diagpkt_class_dev);
-}
-
-void __exit ipath_diagpkt_remove(void)
-{
-	ipath_cdev_cleanup(&diagpkt_cdev, &diagpkt_class_dev);
-}
-
 /**
  * ipath_diagpkt_write - write an IB packet
  * @fp: the diag data device file pointer
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index 12cefa658f3b..b4ffaa7bcbb7 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -2005,18 +2005,8 @@ static int __init infinipath_init(void)
 		goto bail_group;
 	}
 
-	ret = ipath_diagpkt_add();
-	if (ret < 0) {
-		printk(KERN_ERR IPATH_DRV_NAME ": Unable to create "
-		       "diag data device: error %d\n", -ret);
-		goto bail_ipathfs;
-	}
-
 	goto bail;
 
-bail_ipathfs:
-	ipath_exit_ipathfs();
-
 bail_group:
 	ipath_driver_remove_group(&ipath_driver.driver);
 
diff --git a/drivers/infiniband/hw/ipath/ipath_kernel.h b/drivers/infiniband/hw/ipath/ipath_kernel.h
index 7c436697d0e4..06d5020a2f60 100644
--- a/drivers/infiniband/hw/ipath/ipath_kernel.h
+++ b/drivers/infiniband/hw/ipath/ipath_kernel.h
@@ -869,9 +869,6 @@ int ipath_device_create_group(struct device *, struct ipath_devdata *);
 void ipath_device_remove_group(struct device *, struct ipath_devdata *);
 int ipath_expose_reset(struct device *);
 
-int ipath_diagpkt_add(void);
-void ipath_diagpkt_remove(void);
-
 int ipath_init_ipathfs(void);
 void ipath_exit_ipathfs(void);
 int ipathfs_add_device(struct ipath_devdata *);
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 99a94d710935..768df7265b81 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1820,11 +1820,11 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 #define MAD_IFC_BOX_SIZE      0x400
 #define MAD_IFC_MY_QPN_OFFSET 0x100
-#define MAD_IFC_RQPN_OFFSET   0x104
-#define MAD_IFC_SL_OFFSET     0x108
-#define MAD_IFC_G_PATH_OFFSET 0x109
-#define MAD_IFC_RLID_OFFSET   0x10a
-#define MAD_IFC_PKEY_OFFSET   0x10e
+#define MAD_IFC_RQPN_OFFSET   0x108
+#define MAD_IFC_SL_OFFSET     0x10c
+#define MAD_IFC_G_PATH_OFFSET 0x10d
+#define MAD_IFC_RLID_OFFSET   0x10e
+#define MAD_IFC_PKEY_OFFSET   0x112
 #define MAD_IFC_GRH_OFFSET    0x140
 
 	inmailbox = mthca_alloc_mailbox(dev, GFP_KERNEL);
@@ -1862,7 +1862,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 		val = in_wc->dlid_path_bits |
 			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
-		MTHCA_PUT(inbox, val,               MAD_IFC_GRH_OFFSET);
+		MTHCA_PUT(inbox, val,               MAD_IFC_G_PATH_OFFSET);
 
 		MTHCA_PUT(inbox, in_wc->slid,       MAD_IFC_RLID_OFFSET);
 		MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
@@ -1870,7 +1870,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 		if (in_grh)
 			memcpy(inbox + MAD_IFC_GRH_OFFSET, in_grh, 40);
 
-		op_modifier |= 0x10;
+		op_modifier |= 0x4;
 
 		in_modifier |= in_wc->slid << 16;
 	}
diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index e393681ba7d4..149b36901239 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -39,6 +39,8 @@
 #include <linux/init.h>
 #include <linux/hardirq.h>
 
+#include <asm/io.h>
+
 #include <rdma/ib_pack.h>
 
 #include "mthca_dev.h"
@@ -210,6 +212,11 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq,
 		mthca_write64(doorbell,
 			      dev->kar + MTHCA_CQ_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
+		/*
+		 * Make sure doorbells don't leak out of CQ spinlock
+		 * and reach the HCA out of order:
+		 */
+		mmiowb();
 	}
 }
 
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 5e5c58b9920b..6a7822e0fc19 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -39,6 +39,8 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 
+#include <asm/io.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
@@ -1732,6 +1734,11 @@ out:
 		mthca_write64(doorbell,
 			      dev->kar + MTHCA_SEND_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
+		/*
+		 * Make sure doorbells don't leak out of SQ spinlock
+		 * and reach the HCA out of order:
+		 */
+		mmiowb();
 	}
 
 	qp->sq.next_ind = ind;
@@ -1851,6 +1858,12 @@ out:
 	qp->rq.next_ind = ind;
 	qp->rq.head    += nreq;
 
+	/*
+	 * Make sure doorbells don't leak out of RQ spinlock and reach
+	 * the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
 	return err;
 }
@@ -2112,6 +2125,12 @@ out:
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
+	/*
+	 * Make sure doorbells don't leak out of SQ spinlock and reach
+	 * the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c
index 92a72f521528..f5d7677d1079 100644
--- a/drivers/infiniband/hw/mthca/mthca_srq.c
+++ b/drivers/infiniband/hw/mthca/mthca_srq.c
@@ -35,6 +35,8 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+#include <asm/io.h>
+
 #include "mthca_dev.h"
 #include "mthca_cmd.h"
 #include "mthca_memfree.h"
@@ -595,6 +597,12 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
+	/*
+	 * Make sure doorbells don't leak out of SRQ spinlock and
+	 * reach the HCA out of order:
+	 */
+	mmiowb();
+
 	spin_unlock_irqrestore(&srq->lock, flags);
 	return err;
 }