summaryrefslogtreecommitdiff
path: root/drivers/misc
diff options
context:
space:
mode:
authorDani Liberman <dliberman@habana.ai>2021-10-03 15:57:44 +0300
committerOded Gabbay <ogabbay@kernel.org>2021-10-18 12:05:47 +0300
commitea6eb91c09cd4f2f92ba28ba277d2ecf63cdc237 (patch)
tree63d1036082eb6d0fb8cb2aa512565e2a427f6d8f /drivers/misc
parent1d16a46b1a83ea44a73964fe28492656c70da831 (diff)
downloadlinux-ea6eb91c09cd4f2f92ba28ba277d2ecf63cdc237.tar.xz
habanalabs: fix race condition in multi CS completion
Race condition occurs when CS fence completes and multi CS did not completed yet, while waiting for multi CS ends and returns indication to user that the CS completed. Next wait for multi CS may be triggered by previous multi CS completion without any current CS completed, causing an error. Example scenario : 1. User do multi CS wait for CSs 1 and 2 on master QID 0 2. CS 1 and 2 reached the "cs release" code. The thread of CS 1 completed both the CS and multi CS handling but the completion thread of CS 2 completed the CS but still did not executed complete_multi_cs (note that in CS completion the sequence is to first do complete all for the CS and then another complete all to signal the multi_cs) 3. User received indication that CS 1 and 2 completed (since we check the CS fence and both indicated as completed) and immediately waits on CS 3 and 4, also on master QID 0. 4. Completion thread of CS2 executed complete_multi_cs before completion of CS 3 and 4 and so will trigger the multi CS wait of CSs 3 and 4 as they wait on master QID 0. This will trigger multi CS completion although none of its current CS has been completed. Fixed by adding multi CS complete handling indication for each CS. CS will be marked to the user as completed only if its fence completed and multi CS handling is done. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Diffstat (limited to 'drivers/misc')
-rw-r--r--drivers/misc/habanalabs/common/command_submission.c20
-rw-r--r--drivers/misc/habanalabs/common/habanalabs.h4
2 files changed, 23 insertions, 1 deletions
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 4bc24852a283..8e4dc1441fff 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -143,6 +143,7 @@ static void hl_fence_init(struct hl_fence *fence, u64 sequence)
fence->cs_sequence = sequence;
fence->error = 0;
fence->timestamp = ktime_set(0, 0);
+ fence->mcs_handling_done = false;
init_completion(&fence->completion);
}
@@ -535,10 +536,21 @@ static void complete_multi_cs(struct hl_device *hdev, struct hl_cs *cs)
mcs_compl->timestamp =
ktime_to_ns(fence->timestamp);
complete_all(&mcs_compl->completion);
+
+ /*
+ * Setting mcs_handling_done inside the lock ensures
+ * at least one fence have mcs_handling_done set to
+ * true before wait for mcs finish. This ensures at
+ * least one CS will be set as completed when polling
+ * mcs fences.
+ */
+ fence->mcs_handling_done = true;
}
spin_unlock(&mcs_compl->lock);
}
+ /* In case CS completed without mcs completion initialized */
+ fence->mcs_handling_done = true;
}
static inline void cs_release_sob_reset_handler(struct hl_device *hdev,
@@ -2372,7 +2384,13 @@ static int hl_cs_poll_fences(struct multi_cs_data *mcs_data)
mcs_data->stream_master_qid_map |= fence->stream_master_qid_map;
- if (status == CS_WAIT_STATUS_BUSY)
+ /*
+ * Using mcs_handling_done to avoid possibility of mcs_data
+ * returns to user indicating CS completed before it finished
+ * all of its mcs handling, to avoid race the next time the
+ * user waits for mcs.
+ */
+ if (status == CS_WAIT_STATUS_BUSY || !fence->mcs_handling_done)
continue;
mcs_data->completion_bitmap |= BIT(i);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index a06135155b57..48f0e52cd5be 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -610,6 +610,9 @@ struct asic_fixed_properties {
* @error: mark this fence with error
* @timestamp: timestamp upon completion
* @take_timestamp: timestamp shall be taken upon completion
+ * @mcs_handling_done: indicates that corresponding command submission has
+ * finished msc handling, this does not mean it was part
+ * of the mcs
*/
struct hl_fence {
struct completion completion;
@@ -619,6 +622,7 @@ struct hl_fence {
int error;
ktime_t timestamp;
u8 take_timestamp;
+ u8 mcs_handling_done;
};
/**