[ofa-general] [PATCH] IB/mthca: Keep free count for MTT buddy allocator

[Roland Dreier]

MTT entries are allocated with a buddy allocator, which just keeps
bitmaps for each level of the buddy table.  However, all free space
starts out at the highest order, and small allocations start scanning
from the lowest order.  When the lowest order tables have no free
space, this can lead to scanning potentially millions of bits before
finding a free entry at a higher order.

We can avoid this by just keeping a count of how many free entries
each order has, and skipping the bitmap scan when an order is
completely empty.  This provides a nice performance boost for a
negligible increase in memory usage.

Signed-off-by: Roland Dreier <rolandd at cisco.com>
---
 drivers/infiniband/hw/mthca/mthca_dev.h |    1 +
 drivers/infiniband/hw/mthca/mthca_mr.c  |   26 ++++++++++++++++++--------
 2 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index ee4d073..2525901 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -202,6 +202,7 @@ struct mthca_pd_table {
 
 struct mthca_buddy {
 	unsigned long **bits;
+	int	       *num_free;
 	int             max_order;
 	spinlock_t      lock;
 };
diff --git a/drivers/infiniband/hw/mthca/mthca_mr.c b/drivers/infiniband/hw/mthca/mthca_mr.c
index 8489b1e..882e6b7 100644
--- a/drivers/infiniband/hw/mthca/mthca_mr.c
+++ b/drivers/infiniband/hw/mthca/mthca_mr.c
@@ -89,23 +89,26 @@ static u32 mthca_buddy_alloc(struct mthca_buddy *buddy, int order)
 
 	spin_lock(&buddy->lock);
 
-	for (o = order; o <= buddy->max_order; ++o) {
-		m = 1 << (buddy->max_order - o);
-		seg = find_first_bit(buddy->bits[o], m);
-		if (seg < m)
-			goto found;
-	}
+	for (o = order; o <= buddy->max_order; ++o)
+		if (buddy->num_free[o]) {
+			m = 1 << (buddy->max_order - o);
+			seg = find_first_bit(buddy->bits[o], m);
+			if (seg < m)
+				goto found;
+		}
 
 	spin_unlock(&buddy->lock);
 	return -1;
 
  found:
 	clear_bit(seg, buddy->bits[o]);
+	--buddy->num_free[o];
 
 	while (o > order) {
 		--o;
 		seg <<= 1;
 		set_bit(seg ^ 1, buddy->bits[o]);
+		++buddy->num_free[o];
 	}
 
 	spin_unlock(&buddy->lock);
@@ -123,11 +126,13 @@ static void mthca_buddy_free(struct mthca_buddy *buddy, u32 seg, int order)
 
 	while (test_bit(seg ^ 1, buddy->bits[order])) {
 		clear_bit(seg ^ 1, buddy->bits[order]);
+		--buddy->num_free[order];
 		seg >>= 1;
 		++order;
 	}
 
 	set_bit(seg, buddy->bits[order]);
+	++buddy->num_free[order];
 
 	spin_unlock(&buddy->lock);
 }
@@ -141,7 +146,9 @@ static int mthca_buddy_init(struct mthca_buddy *buddy, int max_order)
 
 	buddy->bits = kzalloc((buddy->max_order + 1) * sizeof (long *),
 			      GFP_KERNEL);
-	if (!buddy->bits)
+	buddy->num_free = kzalloc((buddy->max_order + 1) * sizeof (int *),
+				  GFP_KERNEL);
+	if (!buddy->bits || !buddy->num_free)
 		goto err_out;
 
 	for (i = 0; i <= buddy->max_order; ++i) {
@@ -154,6 +161,7 @@ static int mthca_buddy_init(struct mthca_buddy *buddy, int max_order)
 	}
 
 	set_bit(0, buddy->bits[buddy->max_order]);
+	buddy->num_free[buddy->max_order] = 1;
 
 	return 0;
 
@@ -161,9 +169,10 @@ err_out_free:
 	for (i = 0; i <= buddy->max_order; ++i)
 		kfree(buddy->bits[i]);
 
+err_out:
 	kfree(buddy->bits);
+	kfree(buddy->num_free);
 
-err_out:
 	return -ENOMEM;
 }
 
@@ -175,6 +184,7 @@ static void mthca_buddy_cleanup(struct mthca_buddy *buddy)
 		kfree(buddy->bits[i]);
 
 	kfree(buddy->bits);
+	kfree(buddy->num_free);
 }
 
 static u32 mthca_alloc_mtt_range(struct mthca_dev *dev, int order,
-- 
1.5.6.2