From: Erez Alfasi <ereza@xxxxxxxxxxxx>
Introduce ODP diagnostic counters and count the following
per MR within IB/mlx5 driver:
1) Page faults:
Total number of faulted pages.
2) Page invalidations:
Total number of pages invalidated by the OS during all
invalidation events. The translations can be no longer
valid due to either non-present pages or mapping changes.
3) Prefetched pages:
When prefetching a page, page fault is generated
in order to bring the page to the main memory.
The prefetched pages counter will be updated
during a page fault flow only if it was derived
from prefetching operation.
Signed-off-by: Erez Alfasi <ereza@xxxxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
---
drivers/infiniband/hw/mlx5/mlx5_ib.h | 4 ++++
drivers/infiniband/hw/mlx5/odp.c | 18 ++++++++++++++++++
include/rdma/ib_verbs.h | 6 ++++++
3 files changed, 28 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bf30d53d94dc..5aae05ebf64b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -585,6 +585,9 @@ struct mlx5_ib_dm {
IB_ACCESS_REMOTE_READ |\
IB_ZERO_BASED)
+#define mlx5_update_odp_stats(mr, counter_name, value) \
+ atomic64_add(value, &((mr)->odp_stats.counter_name))
+
struct mlx5_ib_mr {
struct ib_mr ibmr;
void *descs;
@@ -622,6 +625,7 @@ struct mlx5_ib_mr {
wait_queue_head_t q_leaf_free;
struct mlx5_async_work cb_work;
atomic_t num_pending_prefetch;
+ struct ib_odp_counters odp_stats;
};
static inline bool is_odp_mr(struct mlx5_ib_mr *mr)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 95cf0249b015..966783bfb557 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -261,6 +261,10 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
blk_start_idx = idx;
in_block = 1;
}
+
+ /* Count page invalidations */
+ mlx5_update_odp_stats(mr, invalidations,
+ (idx - blk_start_idx + 1));
} else {
u64 umr_offset = idx & umr_block_mask;
@@ -287,6 +291,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
ib_umem_odp_unmap_dma_pages(umem_odp, start, end);
+
if (unlikely(!umem_odp->npages && mr->parent &&
!umem_odp->dying)) {
WRITE_ONCE(umem_odp->dying, 1);
@@ -801,6 +806,19 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev,
if (ret < 0)
goto srcu_unlock;
+ /*
+ * When prefetching a page, page fault is generated
+ * in order to bring the page to the main memory.
+ * In the current flow, page faults are being counted.
+ * Prefetched pages counter will be updated as well
+ * only if the current page fault flow was derived
+ * from prefetching flow.
+ */
+ mlx5_update_odp_stats(mr, faults, ret);
+
+ if (prefetch)
+ mlx5_update_odp_stats(mr, prefetched, ret);
+
npages += ret;
ret = 0;
break;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6a47ba85c54c..3990054656b9 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2218,6 +2218,12 @@ struct rdma_netdev_alloc_params {
struct net_device *netdev, void *param);
};
+struct ib_odp_counters {
+ atomic64_t faults;
+ atomic64_t invalidations;
+ atomic64_t prefetched;
+};
+
struct ib_counters {
struct ib_device *device;
struct ib_uobject *uobject;
--
2.20.1
