RDMA/cxgb4: Support on-chip SQs

T4 support on-chip SQs to reduce latency.  This patch adds support for
this in iw_cxgb4:

 - Manage ocqp memory like other adapter mem resources.
 - Allocate user mode SQs from ocqp mem if available.
 - Map ocqp mem to user process using write combining.
 - Map PCIE_MA_SYNC reg to user process.

Bump uverbs ABI.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 56 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index 26365f6ed84b..4fb50d58b493 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -422,3 +422,59 @@ void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 {
 	gen_pool_destroy(rdev->rqt_pool);
 }
+
+/*
+ * On-Chip QP Memory.
+ */
+#define MIN_OCQP_SHIFT 12	/* 4KB == min ocqp size */
+
+u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size)
+{
+	unsigned long addr = gen_pool_alloc(rdev->ocqp_pool, size);
+	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	return (u32)addr;
+}
+
+void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size)
+{
+	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
+	gen_pool_free(rdev->ocqp_pool, (unsigned long)addr, size);
+}
+
+int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev)
+{
+	unsigned start, chunk, top;
+
+	rdev->ocqp_pool = gen_pool_create(MIN_OCQP_SHIFT, -1);
+	if (!rdev->ocqp_pool)
+		return -ENOMEM;
+
+	start = rdev->lldi.vr->ocq.start;
+	chunk = rdev->lldi.vr->ocq.size;
+	top = start + chunk;
+
+	while (start < top) {
+		chunk = min(top - start + 1, chunk);
+		if (gen_pool_add(rdev->ocqp_pool, start, chunk, -1)) {
+			PDBG("%s failed to add OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			if (chunk <= 1024 << MIN_OCQP_SHIFT) {
+				printk(KERN_WARNING MOD
+				       "Failed to add all OCQP chunks (%x/%x)\n",
+				       start, top - start);
+				return 0;
+			}
+			chunk >>= 1;
+		} else {
+			PDBG("%s added OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			start += chunk;
+		}
+	}
+	return 0;
+}
+
+void c4iw_ocqp_pool_destroy(struct c4iw_rdev *rdev)
+{
+	gen_pool_destroy(rdev->ocqp_pool);
+}