summaryrefslogtreecommitdiffstats
path: root/drivers/accel/qaic
diff options
context:
space:
mode:
authorJeffrey Hugo <quic_jhugo@quicinc.com>2023-05-17 21:35:40 +0200
committerJeffrey Hugo <quic_jhugo@quicinc.com>2023-05-23 17:51:38 +0200
commite997c218ad736fd6f524d73a987bad9d94128d3d (patch)
tree90cc9c9908228f4eae8a0f5444535ae161dfb752 /drivers/accel/qaic
parentaccel/qaic: Grab ch_lock during QAIC_ATTACH_SLICE_BO (diff)
downloadlinux-e997c218ad736fd6f524d73a987bad9d94128d3d.tar.xz
linux-e997c218ad736fd6f524d73a987bad9d94128d3d.zip
accel/qaic: Fix NNC message corruption
If msg_xfer() is unable to queue part of a NNC message because the MHI ring is full, it will attempt to give the QSM some time to drain the queue. However, if QSM fails to make any room, msg_xfer() will fail and tell the caller to try again. This is problematic because part of the message may have been committed to the ring and there is no mechanism to revoke that content. This will cause QSM to receive a corrupt message. The better way to do this is to check if the ring has enough space for the entire message before committing any of the message. Since msg_xfer() is under the cntl_mutex no one else can come in and consume the space. Fixes: 129776ac2e38 ("accel/qaic: Add control path") Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com> Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230517193540.14323-6-quic_jhugo@quicinc.com
Diffstat (limited to 'drivers/accel/qaic')
-rw-r--r--drivers/accel/qaic/qaic_control.c29
1 files changed, 21 insertions, 8 deletions
diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 9e39b1a324f7..5c57f7b4494e 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -997,14 +997,34 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u
struct xfer_queue_elem elem;
struct wire_msg *out_buf;
struct wrapper_msg *w;
+ long ret = -EAGAIN;
+ int xfer_count = 0;
int retry_count;
- long ret;
if (qdev->in_reset) {
mutex_unlock(&qdev->cntl_mutex);
return ERR_PTR(-ENODEV);
}
+ /* Attempt to avoid a partial commit of a message */
+ list_for_each_entry(w, &wrappers->list, list)
+ xfer_count++;
+
+ for (retry_count = 0; retry_count < QAIC_MHI_RETRY_MAX; retry_count++) {
+ if (xfer_count <= mhi_get_free_desc_count(qdev->cntl_ch, DMA_TO_DEVICE)) {
+ ret = 0;
+ break;
+ }
+ msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS);
+ if (signal_pending(current))
+ break;
+ }
+
+ if (ret) {
+ mutex_unlock(&qdev->cntl_mutex);
+ return ERR_PTR(ret);
+ }
+
elem.seq_num = seq_num;
elem.buf = NULL;
init_completion(&elem.xfer_done);
@@ -1038,16 +1058,9 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u
list_for_each_entry(w, &wrappers->list, list) {
kref_get(&w->ref_count);
retry_count = 0;
-retry:
ret = mhi_queue_buf(qdev->cntl_ch, DMA_TO_DEVICE, &w->msg, w->len,
list_is_last(&w->list, &wrappers->list) ? MHI_EOT : MHI_CHAIN);
if (ret) {
- if (ret == -EAGAIN && retry_count++ < QAIC_MHI_RETRY_MAX) {
- msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS);
- if (!signal_pending(current))
- goto retry;
- }
-
qdev->cntl_lost_buf = true;
kref_put(&w->ref_count, free_wrapper);
mutex_unlock(&qdev->cntl_mutex);