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

Pull infiniband/rdma fixes from Roland Dreier:
 "Grab bag of InfiniBand/RDMA fixes:
   - IPoIB fixes for regressions introduced by path database conversion
   - mlx4 fixes for bugs with large memory systems and regressions from
     SR-IOV patches
   - RDMA CM fix for passing bad event up to userspace
   - Other minor fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/mlx4: Check iboe netdev pointer before dereferencing it
  mlx4_core: Clean up buddy bitmap allocation
  mlx4_core: Fix integer overflow issues around MTT table
  mlx4_core: Allow large mlx4_buddy bitmaps
  IB/srp: Fix a race condition
  IB/qib: Fix error return code in qib_init_7322_variables()
  IB: Fix typos in infiniband drivers
  IB/ipoib: Fix RCU pointer dereference of wrong object
  IB/ipoib: Add missing locking when CM object is deleted
  RDMA/ucma.c: Fix for events with wrong context on iWARP
  RDMA/ocrdma: Don't call vlan_dev_real_dev() for non-VLAN netdevs
  IB/mlx4: Fix possible deadlock on sm_lock spinlock

5 files changed, 29 insertions, 17 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 88b7b3e75ab1..daf417923661 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -358,13 +358,14 @@ void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 }
 
 int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
-			u64 virt, int obj_size,	int nobj, int reserved,
+			u64 virt, int obj_size,	u32 nobj, int reserved,
 			int use_lowmem, int use_coherent)
 {
 	int obj_per_chunk;
 	int num_icm;
 	unsigned chunk_size;
 	int i;
+	u64 size;
 
 	obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
 	num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
@@ -380,10 +381,12 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 	table->coherent = use_coherent;
 	mutex_init(&table->mutex);
 
+	size = (u64) nobj * obj_size;
 	for (i = 0; i * MLX4_TABLE_CHUNK_SIZE < reserved * obj_size; ++i) {
 		chunk_size = MLX4_TABLE_CHUNK_SIZE;
-		if ((i + 1) * MLX4_TABLE_CHUNK_SIZE > nobj * obj_size)
-			chunk_size = PAGE_ALIGN(nobj * obj_size - i * MLX4_TABLE_CHUNK_SIZE);
+		if ((i + 1) * MLX4_TABLE_CHUNK_SIZE > size)
+			chunk_size = PAGE_ALIGN(size -
+					i * MLX4_TABLE_CHUNK_SIZE);
 
 		table->icm[i] = mlx4_alloc_icm(dev, chunk_size >> PAGE_SHIFT,
 					       (use_lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index 19e4efc0b342..a67744f53506 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -78,7 +78,7 @@ int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 			  int start, int end);
 int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
-			u64 virt, int obj_size,	int nobj, int reserved,
+			u64 virt, int obj_size,	u32 nobj, int reserved,
 			int use_lowmem, int use_coherent);
 void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table);
 void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 59ebc0339638..4d9df8f2a126 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -249,7 +249,7 @@ struct mlx4_bitmap {
 struct mlx4_buddy {
 	unsigned long	      **bits;
 	unsigned int	       *num_free;
-	int			max_order;
+	u32			max_order;
 	spinlock_t		lock;
 };
 
@@ -258,7 +258,7 @@ struct mlx4_icm;
 struct mlx4_icm_table {
 	u64			virt;
 	int			num_icm;
-	int			num_obj;
+	u32			num_obj;
 	int			obj_size;
 	int			lowmem;
 	int			coherent;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index af55b7ce5341..c202d3ad2a0e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -37,6 +37,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/vmalloc.h>
 
 #include <linux/mlx4/cmd.h>
 
@@ -120,7 +121,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 	buddy->max_order = max_order;
 	spin_lock_init(&buddy->lock);
 
-	buddy->bits = kzalloc((buddy->max_order + 1) * sizeof (long *),
+	buddy->bits = kcalloc(buddy->max_order + 1, sizeof (long *),
 			      GFP_KERNEL);
 	buddy->num_free = kcalloc((buddy->max_order + 1), sizeof *buddy->num_free,
 				  GFP_KERNEL);
@@ -129,10 +130,12 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
 	for (i = 0; i <= buddy->max_order; ++i) {
 		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
-		buddy->bits[i] = kmalloc(s * sizeof (long), GFP_KERNEL);
-		if (!buddy->bits[i])
-			goto err_out_free;
-		bitmap_zero(buddy->bits[i], 1 << (buddy->max_order - i));
+		buddy->bits[i] = kcalloc(s, sizeof (long), GFP_KERNEL | __GFP_NOWARN);
+		if (!buddy->bits[i]) {
+			buddy->bits[i] = vzalloc(s * sizeof(long));
+			if (!buddy->bits[i])
+				goto err_out_free;
+		}
 	}
 
 	set_bit(0, buddy->bits[buddy->max_order]);
@@ -142,7 +145,10 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 
 err_out_free:
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		if (buddy->bits[i] && is_vmalloc_addr(buddy->bits[i]))
+			vfree(buddy->bits[i]);
+		else
+			kfree(buddy->bits[i]);
 
 err_out:
 	kfree(buddy->bits);
@@ -156,7 +162,10 @@ static void mlx4_buddy_cleanup(struct mlx4_buddy *buddy)
 	int i;
 
 	for (i = 0; i <= buddy->max_order; ++i)
-		kfree(buddy->bits[i]);
+		if (is_vmalloc_addr(buddy->bits[i]))
+			vfree(buddy->bits[i]);
+		else
+			kfree(buddy->bits[i]);
 
 	kfree(buddy->bits);
 	kfree(buddy->num_free);
@@ -668,7 +677,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 		return err;
 
 	err = mlx4_buddy_init(&mr_table->mtt_buddy,
-			      ilog2(dev->caps.num_mtts /
+			      ilog2((u32)dev->caps.num_mtts /
 			      (1 << log_mtts_per_seg)));
 	if (err)
 		goto err_buddy;
@@ -678,7 +687,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 			mlx4_alloc_mtt_range(dev,
 					     fls(dev->caps.reserved_mtts - 1));
 		if (priv->reserved_mtts < 0) {
-			mlx4_warn(dev, "MTT table of order %d is too small.\n",
+			mlx4_warn(dev, "MTT table of order %u is too small.\n",
 				  mr_table->mtt_buddy.max_order);
 			err = -ENOMEM;
 			goto err_reserve_mtts;
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 9ee4725363d5..8e0c3cc2a1ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -76,7 +76,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 		u64 size;
 		u64 start;
 		int type;
-		int num;
+		u32 num;
 		int log_num;
 	};
 
@@ -105,7 +105,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	si_meminfo(&si);
 	request->num_mtt =
 		roundup_pow_of_two(max_t(unsigned, request->num_mtt,
-					 min(1UL << 31,
+					 min(1UL << (31 - log_mtts_per_seg),
 					     si.totalram >> (log_mtts_per_seg - 1))));
 
 	profile[MLX4_RES_QP].size     = dev_cap->qpc_entry_sz;