| Message ID | 7c45c0a237c02b8ba34eca49f29845a0341ecff5.1620233587.git.limings@nvidia.com |
|---|---|
| State | New |
| Headers | show |
| Series | UBUNTU: SAUCE: tmfifo: Fix a memory barrier issue | expand |
BugLink: https://bugs.launchpad.net/bugs/1927262 SRU Justification: [Impact] * The virtio framework uses wmb() when updating avail->idx. It guarantees the write order, but not necessarily loading order for the code accessing the memory. So potentially it could cause traffic stuck which has been observed in the field. [Fix] * This commit adds a load barrier after reading the avail->idx to make sure all the data in the descriptor is visible. It also adds a barrier when returning the packet to virtio framework to make sure read/writes are visible to the virtio code. [Test Case] * Just normal test. This change doesn't affect any functionality. [Regression Potential] * This version of the driver was tested by QA/verification for a while so no known regression at the moment.
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index 5739a966..92bda873 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -294,6 +294,9 @@ static irqreturn_t mlxbf_tmfifo_irq_handler(int irq, void *arg) if (vring->next_avail == virtio16_to_cpu(vdev, vr->avail->idx)) return NULL; + /* Make sure 'avail->idx' is visible already. */ + virtio_rmb(false); + idx = vring->next_avail % vr->num; head = virtio16_to_cpu(vdev, vr->avail->ring[idx]); if (WARN_ON(head >= vr->num)) @@ -322,7 +325,7 @@ static void mlxbf_tmfifo_release_desc(struct mlxbf_tmfifo_vring *vring, * done or not. Add a memory barrier here to make sure the update above * completes before updating the idx. */ - mb(); + virtio_mb(false); vr->used->idx = cpu_to_virtio16(vdev, vr_idx + 1); } @@ -730,6 +733,12 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring, desc = NULL; fifo->vring[is_rx] = NULL; + /* + * Make sure the load/store are in order before + * returning back to virtio. + */ + virtio_mb(false); + /* Notify upper layer that packet is done. */ spin_lock_irqsave(&fifo->spin_lock[is_rx], flags); vring_interrupt(0, vring->vq);
From: Liming Sun <lsun@mellanox.com> The virtio framework uses wmb() when updating avail->idx. It gurantees the write order, but not necessarily loading order for the code accessing the memory. This commit adds a load barrier after reading the avail->idx to make sure all the data in the descriptor is visible. It also adds a barrier when returning the packet to virtio framework to make sure read/writes are visible to the virtio code. RM #2269638 Change-Id: I0759e75a8863b3cee9eb0b3794cd87c113019f72 --- drivers/platform/mellanox/mlxbf-tmfifo.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)