IB/mlx5: Implement fragmented completion queue (CQ)

The current implementation of create CQ requires contiguous
memory, such requirement is problematic once the memory is
fragmented or the system is low in memory, it causes for
failures in dma_zalloc_coherent().

This patch implements new scheme of fragmented CQ to overcome
this issue by introducing new type: 'struct mlx5_frag_buf_ctrl'
to allocate fragmented buffers, rather than contiguous ones.

Base the Completion Queues (CQs) on this new fragmented buffer.

It fixes following crashes:
kworker/29:0: page allocation failure: order:6, mode:0x80d0
CPU: 29 PID: 8374 Comm: kworker/29:0 Tainted: G OE 3.10.0
Workqueue: ib_cm cm_work_handler [ib_cm]
Call Trace:
[<>] dump_stack+0x19/0x1b
[<>] warn_alloc_failed+0x110/0x180
[<>] __alloc_pages_slowpath+0x6b7/0x725
[<>] __alloc_pages_nodemask+0x405/0x420
[<>] dma_generic_alloc_coherent+0x8f/0x140
[<>] x86_swiotlb_alloc_coherent+0x21/0x50
[<>] mlx5_dma_zalloc_coherent_node+0xad/0x110 [mlx5_core]
[<>] ? mlx5_db_alloc_node+0x69/0x1b0 [mlx5_core]
[<>] mlx5_buf_alloc_node+0x3e/0xa0 [mlx5_core]
[<>] mlx5_buf_alloc+0x14/0x20 [mlx5_core]
[<>] create_cq_kernel+0x90/0x1f0 [mlx5_ib]
[<>] mlx5_ib_create_cq+0x3b0/0x4e0 [mlx5_ib]

Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

1 files changed, 37 insertions, 14 deletions

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2860a253275b..bfea26af6de5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -345,13 +345,6 @@ struct mlx5_buf_list {
 	dma_addr_t		map;
 };
 
-struct mlx5_buf {
-	struct mlx5_buf_list	direct;
-	int			npages;
-	int			size;
-	u8			page_shift;
-};
-
 struct mlx5_frag_buf {
 	struct mlx5_buf_list	*frags;
 	int			npages;
@@ -359,6 +352,15 @@ struct mlx5_frag_buf {
 	u8			page_shift;
 };
 
+struct mlx5_frag_buf_ctrl {
+	struct mlx5_frag_buf	frag_buf;
+	u32			sz_m1;
+	u32			frag_sz_m1;
+	u8			log_sz;
+	u8			log_stride;
+	u8			log_frag_strides;
+};
+
 struct mlx5_eq_tasklet {
 	struct list_head list;
 	struct list_head process_list;
@@ -386,7 +388,7 @@ struct mlx5_eq {
 	struct mlx5_cq_table	cq_table;
 	__be32 __iomem	       *doorbell;
 	u32			cons_index;
-	struct mlx5_buf		buf;
+	struct mlx5_frag_buf	buf;
 	int			size;
 	unsigned int		irqn;
 	u8			eqn;
@@ -932,9 +934,9 @@ struct mlx5_hca_vport_context {
 	bool			grh_required;
 };
 
-static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset)
+static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset)
 {
-		return buf->direct.buf + offset;
+		return buf->frags->buf + offset;
 }
 
 #define STRUCT_FIELD(header, field) \
@@ -973,6 +975,25 @@ static inline u32 mlx5_base_mkey(const u32 key)
 	return key & 0xffffff00u;
 }
 
+static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
+					      void *cqc)
+{
+	fbc->log_stride	= 6 + MLX5_GET(cqc, cqc, cqe_sz);
+	fbc->log_sz	= MLX5_GET(cqc, cqc, log_cq_size);
+	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
+	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
+	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
+}
+
+static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
+					  u32 ix)
+{
+	unsigned int frag = (ix >> fbc->log_frag_strides);
+
+	return fbc->frag_buf.frags[frag].buf +
+		((fbc->frag_sz_m1 & ix) << fbc->log_stride);
+}
+
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
@@ -998,9 +1019,10 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
-			struct mlx5_buf *buf, int node);
-int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
-void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf);
+			struct mlx5_frag_buf *buf, int node);
+int mlx5_buf_alloc(struct mlx5_core_dev *dev,
+		   int size, struct mlx5_frag_buf *buf);
+void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			     struct mlx5_frag_buf *buf, int node);
 void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
@@ -1045,7 +1067,8 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
 int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
 void mlx5_register_debugfs(void);
 void mlx5_unregister_debugfs(void);
-void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
+
+void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
 void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);