1 files changed, 55 insertions, 72 deletions

diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index 1c02a8f952d..a817705ce2d 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -31,9 +31,10 @@
  *
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/ratelimit.h>
 
 #include "rds.h"
-#include "rdma.h"
 #include "iw.h"
 
 
@@ -83,7 +84,8 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
 static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 			struct list_head *unmap_list,
-			struct list_head *kill_list);
+			struct list_head *kill_list,
+			int *unpinned);
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 
 static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
@@ -122,7 +124,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd
 #else
 			/* FIXME - needs to compare the local and remote
 			 * ipaddr/port tuple, but the ipaddr is the only
-			 * available infomation in the rds_sock (as the rest are
+			 * available information in the rds_sock (as the rest are
 			 * zero'ed.  It doesn't appear to be properly populated
 			 * during connection setup...
 			 */
@@ -157,7 +159,8 @@ static int rds_iw_add_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *
 	return 0;
 }
 
-void rds_iw_remove_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_id)
+static void rds_iw_remove_cm_id(struct rds_iw_device *rds_iwdev,
+				struct rdma_cm_id *cm_id)
 {
 	struct rds_iw_cm_id *i_cm_id;
 
@@ -196,7 +199,7 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i
 	return rds_iw_add_cm_id(rds_iwdev, cm_id);
 }
 
-int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
+void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
 {
 	struct rds_iw_connection *ic = conn->c_transport_data;
 
@@ -205,51 +208,48 @@ int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn
 	BUG_ON(list_empty(&iw_nodev_conns));
 	BUG_ON(list_empty(&ic->iw_node));
 	list_del(&ic->iw_node);
-	spin_unlock_irq(&iw_nodev_conns_lock);
 
-	spin_lock_irq(&rds_iwdev->spinlock);
+	spin_lock(&rds_iwdev->spinlock);
 	list_add_tail(&ic->iw_node, &rds_iwdev->conn_list);
-	spin_unlock_irq(&rds_iwdev->spinlock);
+	spin_unlock(&rds_iwdev->spinlock);
+	spin_unlock_irq(&iw_nodev_conns_lock);
 
 	ic->rds_iwdev = rds_iwdev;
-
-	return 0;
 }
 
-void rds_iw_remove_nodev_conns(void)
+void rds_iw_remove_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
 {
-	struct rds_iw_connection *ic, *_ic;
-	LIST_HEAD(tmp_list);
+	struct rds_iw_connection *ic = conn->c_transport_data;
 
-	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&iw_nodev_conns_lock);
-	list_splice(&iw_nodev_conns, &tmp_list);
-	INIT_LIST_HEAD(&iw_nodev_conns);
-	spin_unlock_irq(&iw_nodev_conns_lock);
+	/* place conn on nodev_conns_list */
+	spin_lock(&iw_nodev_conns_lock);
 
-	list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) {
-		if (ic->conn->c_passive)
-			rds_conn_destroy(ic->conn->c_passive);
-		rds_conn_destroy(ic->conn);
-	}
+	spin_lock_irq(&rds_iwdev->spinlock);
+	BUG_ON(list_empty(&ic->iw_node));
+	list_del(&ic->iw_node);
+	spin_unlock_irq(&rds_iwdev->spinlock);
+
+	list_add_tail(&ic->iw_node, &iw_nodev_conns);
+
+	spin_unlock(&iw_nodev_conns_lock);
+
+	rds_iw_remove_cm_id(ic->rds_iwdev, ic->i_cm_id);
+	ic->rds_iwdev = NULL;
 }
 
-void rds_iw_remove_conns(struct rds_iw_device *rds_iwdev)
+void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock)
 {
 	struct rds_iw_connection *ic, *_ic;
 	LIST_HEAD(tmp_list);
 
 	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&rds_iwdev->spinlock);
-	list_splice(&rds_iwdev->conn_list, &tmp_list);
-	INIT_LIST_HEAD(&rds_iwdev->conn_list);
-	spin_unlock_irq(&rds_iwdev->spinlock);
+	spin_lock_irq(list_lock);
+	list_splice(list, &tmp_list);
+	INIT_LIST_HEAD(list);
+	spin_unlock_irq(list_lock);
 
-	list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) {
-		if (ic->conn->c_passive)
-			rds_conn_destroy(ic->conn->c_passive);
+	list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node)
 		rds_conn_destroy(ic->conn);
-	}
 }
 
 static void rds_iw_set_scatterlist(struct rds_iw_scatterlist *sg,
@@ -263,18 +263,12 @@ static void rds_iw_set_scatterlist(struct rds_iw_scatterlist *sg,
 }
 
 static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
-			struct rds_iw_scatterlist *sg,
-			unsigned int dma_page_shift)
+			struct rds_iw_scatterlist *sg)
 {
 	struct ib_device *dev = rds_iwdev->dev;
 	u64 *dma_pages = NULL;
-	u64 dma_mask;
-	unsigned int dma_page_size;
 	int i, j, ret;
 
-	dma_page_size = 1 << dma_page_shift;
-	dma_mask = dma_page_size - 1;
-
 	WARN_ON(sg->dma_len);
 
 	sg->dma_len = ib_dma_map_sg(dev, sg->list, sg->len, DMA_BIDIRECTIONAL);
@@ -295,18 +289,18 @@ static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
 		sg->bytes += dma_len;
 
 		end_addr = dma_addr + dma_len;
-		if (dma_addr & dma_mask) {
+		if (dma_addr & PAGE_MASK) {
 			if (i > 0)
 				goto out_unmap;
-			dma_addr &= ~dma_mask;
+			dma_addr &= ~PAGE_MASK;
 		}
-		if (end_addr & dma_mask) {
+		if (end_addr & PAGE_MASK) {
 			if (i < sg->dma_len - 1)
 				goto out_unmap;
-			end_addr = (end_addr + dma_mask) & ~dma_mask;
+			end_addr = (end_addr + PAGE_MASK) & ~PAGE_MASK;
 		}
 
-		sg->dma_npages += (end_addr - dma_addr) >> dma_page_shift;
+		sg->dma_npages += (end_addr - dma_addr) >> PAGE_SHIFT;
 	}
 
 	/* Now gather the dma addrs into one list */
@@ -325,8 +319,8 @@ static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev,
 		u64 end_addr;
 
 		end_addr = dma_addr + dma_len;
-		dma_addr &= ~dma_mask;
-		for (; dma_addr < end_addr; dma_addr += dma_page_size)
+		dma_addr &= ~PAGE_MASK;
+		for (; dma_addr < end_addr; dma_addr += PAGE_SIZE)
 			dma_pages[j++] = dma_addr;
 		BUG_ON(j > sg->dma_npages);
 	}
@@ -483,17 +477,6 @@ void rds_iw_sync_mr(void *trans_private, int direction)
 	}
 }
 
-static inline unsigned int rds_iw_flush_goal(struct rds_iw_mr_pool *pool, int free_all)
-{
-	unsigned int item_count;
-
-	item_count = atomic_read(&pool->item_count);
-	if (free_all)
-		return item_count;
-
-	return 0;
-}
-
 /*
  * Flush our pool of MRs.
  * At a minimum, all currently unused MRs are unmapped.
@@ -506,7 +489,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 	LIST_HEAD(unmap_list);
 	LIST_HEAD(kill_list);
 	unsigned long flags;
-	unsigned int nfreed = 0, ncleaned = 0, free_goal;
+	unsigned int nfreed = 0, ncleaned = 0, unpinned = 0;
 	int ret = 0;
 
 	rds_iw_stats_inc(s_iw_rdma_mr_pool_flush);
@@ -520,8 +503,6 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 		list_splice_init(&pool->clean_list, &kill_list);
 	spin_unlock_irqrestore(&pool->list_lock, flags);
 
-	free_goal = rds_iw_flush_goal(pool, free_all);
-
 	/* Batched invalidate of dirty MRs.
 	 * For FMR based MRs, the mappings on the unmap list are
 	 * actually members of an ibmr (ibmr->mapping). They either
@@ -531,7 +512,8 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 	 * will be destroyed by the unmap function.
 	 */
 	if (!list_empty(&unmap_list)) {
-		ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list, &kill_list);
+		ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list,
+						     &kill_list, &unpinned);
 		/* If we've been asked to destroy all MRs, move those
 		 * that were simply cleaned to the kill list */
 		if (free_all)
@@ -555,6 +537,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 		spin_unlock_irqrestore(&pool->list_lock, flags);
 	}
 
+	atomic_sub(unpinned, &pool->free_pinned);
 	atomic_sub(ncleaned, &pool->dirty_count);
 	atomic_sub(nfreed, &pool->item_count);
 
@@ -582,8 +565,8 @@ void rds_iw_free_mr(void *trans_private, int invalidate)
 	rds_iw_free_fastreg(pool, ibmr);
 
 	/* If we've pinned too many pages, request a flush */
-	if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned
-	 || atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+	if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned ||
+	    atomic_read(&pool->dirty_count) >= pool->max_items / 10)
 		queue_work(rds_wq, &pool->flush_worker);
 
 	if (invalidate) {
@@ -727,7 +710,7 @@ static int rds_iw_rdma_build_fastreg(struct rds_iw_mapping *mapping)
 	f_wr.wr.fast_reg.rkey = mapping->m_rkey;
 	f_wr.wr.fast_reg.page_list = ibmr->page_list;
 	f_wr.wr.fast_reg.page_list_len = mapping->m_sg.dma_len;
-	f_wr.wr.fast_reg.page_shift = ibmr->device->page_shift;
+	f_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
 	f_wr.wr.fast_reg.access_flags = IB_ACCESS_LOCAL_WRITE |
 				IB_ACCESS_REMOTE_READ |
 				IB_ACCESS_REMOTE_WRITE;
@@ -737,8 +720,8 @@ static int rds_iw_rdma_build_fastreg(struct rds_iw_mapping *mapping)
 	failed_wr = &f_wr;
 	ret = ib_post_send(ibmr->cm_id->qp, &f_wr, &failed_wr);
 	BUG_ON(failed_wr != &f_wr);
-	if (ret && printk_ratelimit())
-		printk(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n",
+	if (ret)
+		printk_ratelimited(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n",
 			__func__, __LINE__, ret);
 	return ret;
 }
@@ -759,8 +742,8 @@ static int rds_iw_rdma_fastreg_inv(struct rds_iw_mr *ibmr)
 
 	failed_wr = &s_wr;
 	ret = ib_post_send(ibmr->cm_id->qp, &s_wr, &failed_wr);
-	if (ret && printk_ratelimit()) {
-		printk(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n",
+	if (ret) {
+		printk_ratelimited(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n",
 			__func__, __LINE__, ret);
 		goto out;
 	}
@@ -780,9 +763,7 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
 
 	rds_iw_set_scatterlist(&mapping->m_sg, sg, sg_len);
 
-	dma_pages = rds_iw_map_scatterlist(rds_iwdev,
-				&mapping->m_sg,
-				rds_iwdev->page_shift);
+	dma_pages = rds_iw_map_scatterlist(rds_iwdev, &mapping->m_sg);
 	if (IS_ERR(dma_pages)) {
 		ret = PTR_ERR(dma_pages);
 		dma_pages = NULL;
@@ -837,7 +818,8 @@ static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool,
 
 static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 				struct list_head *unmap_list,
-				struct list_head *kill_list)
+				struct list_head *kill_list,
+				int *unpinned)
 {
 	struct rds_iw_mapping *mapping, *next;
 	unsigned int ncleaned = 0;
@@ -864,6 +846,7 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 
 		spin_lock_irqsave(&pool->list_lock, flags);
 		list_for_each_entry_safe(mapping, next, unmap_list, m_list) {
+			*unpinned += mapping->m_sg.len;
 			list_move(&mapping->m_list, &laundered);
 			ncleaned++;
 		}