RDMA/mlx5: Fix calculation of total invalidated pages

[ Upstream commit 79195147644653ebffadece31a42181e4c48c07d ]

When invalidating an address range in mlx5, there is an optimization to
do UMR operations in chunks.
Previously, the invalidation counter was incorrectly updated for the
same indexes within a chunk. Now, the invalidation counter is updated
only when a chunk is complete and mlx5r_umr_update_xlt() is called.
This ensures that the counter accurately represents the number of pages
invalidated using UMR.

Fixes: a3de94e3d6 ("IB/mlx5: Introduce ODP diagnostic counters")
Signed-off-by: Chiara Meiohas <cmeiohas@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/560deb2433318e5947282b070c915f3c81fef77f.1741875692.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Chiara Meiohas 2025-03-13 16:29:54 +02:00 committed by Greg Kroah-Hartman
parent d5212b9964
commit 7844932c18

View File

@ -275,9 +275,6 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
blk_start_idx = idx;
in_block = 1;
}
/* Count page invalidations */
invalidations += idx - blk_start_idx + 1;
} else {
u64 umr_offset = idx & umr_block_mask;
@ -287,14 +284,19 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
MLX5_IB_UPD_XLT_ZAP |
MLX5_IB_UPD_XLT_ATOMIC);
in_block = 0;
/* Count page invalidations */
invalidations += idx - blk_start_idx + 1;
}
}
}
if (in_block)
if (in_block) {
mlx5r_umr_update_xlt(mr, blk_start_idx,
idx - blk_start_idx + 1, 0,
MLX5_IB_UPD_XLT_ZAP |
MLX5_IB_UPD_XLT_ATOMIC);
/* Count page invalidations */
invalidations += idx - blk_start_idx + 1;
}
mlx5_update_odp_stats(mr, invalidations, invalidations);