RDMA/mlx5: Implement mkeys management via LIFO queue

Currently, mkeys are managed via xarray. This implementation leads to
a degradation in cases many MRs are unregistered in parallel, due to xarray
internal implementation, for example: deregistration 1M MRs via 64 threads
is taking ~15% more time[1].

Hence, implement mkeys management via LIFO queue, which solved the
degradation.

[1]
2.8us in kernel v5.19 compare to 3.2us in kernel v6.4

Signed-off-by: Shay Drory <shayd@nvidia.com>
Link: https://lore.kernel.org/r/fde3d4cfab0f32f0ccb231cd113298256e1502c5.1695283384.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -753,10 +753,25 @@ struct umr_common {
 	unsigned int state;
 };
 
+#define NUM_MKEYS_PER_PAGE \
+	((PAGE_SIZE - sizeof(struct list_head)) / sizeof(u32))
+
+struct mlx5_mkeys_page {
+	u32 mkeys[NUM_MKEYS_PER_PAGE];
+	struct list_head list;
+};
+static_assert(sizeof(struct mlx5_mkeys_page) == PAGE_SIZE);
+
+struct mlx5_mkeys_queue {
+	struct list_head pages_list;
+	u32 num_pages;
+	unsigned long ci;
+	spinlock_t lock; /* sync list ops */
+};
+
 struct mlx5_cache_ent {
-	struct xarray		mkeys;
-	unsigned long		stored;
-	unsigned long		reserved;
+	struct mlx5_mkeys_queue	mkeys_queue;
+	u32			pending;
 
 	char                    name[4];