[PATCH 3/3] gpu: nova-core: fix wrong use of barriers in GSP code

[Gary Guo <gary@kernel.org>]

From: Gary Guo <gary@garyguo.net>

Currently, in the GSP->CPU messaging path, the current code misses a read
barrier before data read. The barrier after read is updated to a DMA
barrier (with release ordering desired), instead of the existing (Rust)
SeqCst SMP barrier; the location of barrier is also moved to the beginning
of function, because the barrier is needed to synchronizing between data
and ring-buffer pointer, the RMW operation does not internally need a
barrier (nor it has to be atomic, as CPU pointers are updated by CPU only).

In the CPU->GSP messaging path, the current code misses a write barrier
after data write and before updating the CPU write pointer. Barrier is not
needed before data write due to control dependency, this fact is documented
explicitly. This could be replaced with an acquire barrier if needed.

Signed-off-by: Gary Guo <gary@garyguo.net>
---
 drivers/gpu/nova-core/gsp/cmdq.rs | 19 +++++++++++++++++++
 drivers/gpu/nova-core/gsp/fw.rs   | 12 ------------
 2 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 2224896ccc89..7e4315b13984 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -19,6 +19,12 @@
     prelude::*,
     sync::{
         aref::ARef,
+        barrier::{
+            dma_mb,
+            Read,
+            Release,
+            Write, //
+        },
         Mutex, //
     },
     time::Delta,
@@ -258,6 +264,9 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {
         let tx = self.cpu_write_ptr() as usize;
         let rx = self.gsp_read_ptr() as usize;
 
+        // ORDERING: control dependency provides necessary LOAD->STORE ordering.
+        // `dma_mb(Acquire)` may be used here if we don't want to rely on control dependency.
+
         // SAFETY:
         // - We will only access the driver-owned part of the shared memory.
         // - Per the safety statement of the function, no concurrent access will be performed.
@@ -311,6 +320,9 @@ fn driver_write_area_size(&self) -> usize {
         let tx = self.gsp_write_ptr() as usize;
         let rx = self.cpu_read_ptr() as usize;
 
+        // ORDERING: Ensure data load is ordered after load of GSP write pointer.
+        dma_mb(Read);
+
         // SAFETY:
         // - We will only access the driver-owned part of the shared memory.
         // - Per the safety statement of the function, no concurrent access will be performed.
@@ -408,6 +420,10 @@ fn cpu_read_ptr(&self) -> u32 {
 
     // Informs the GSP that it can send `elem_count` new pages into the message queue.
     fn advance_cpu_read_ptr(&mut self, elem_count: u32) {
+        // ORDERING: Ensure read pointer is properly ordered.
+        //
+        dma_mb(Release);
+
         super::fw::gsp_mem::advance_cpu_read_ptr(&self.0, elem_count)
     }
 
@@ -422,6 +438,9 @@ fn cpu_write_ptr(&self) -> u32 {
 
     // Informs the GSP that it can process `elem_count` new pages from the command queue.
     fn advance_cpu_write_ptr(&mut self, elem_count: u32) {
+        // ORDERING: Ensure all command data is visible before updateing ring buffer pointer.
+        dma_mb(Write);
+
         super::fw::gsp_mem::advance_cpu_write_ptr(&self.0, elem_count)
     }
 }
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index 0c8a74f0e8ac..62c2cf1b030c 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -42,11 +42,6 @@
 
 // TODO: Replace with `IoView` projections once available.
 pub(super) mod gsp_mem {
-    use core::sync::atomic::{
-        fence,
-        Ordering, //
-    };
-
     use kernel::{
         dma::Coherent,
         dma_read,
@@ -72,10 +67,6 @@ pub(in crate::gsp) fn cpu_read_ptr(qs: &Coherent<GspMem>) -> u32 {
 
     pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &Coherent<GspMem>, count: u32) {
         let rptr = cpu_read_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
-
-        // Ensure read pointer is properly ordered.
-        fence(Ordering::SeqCst);
-
         dma_write!(qs, .cpuq.rx.0.readPtr, rptr);
     }
 
@@ -87,9 +78,6 @@ pub(in crate::gsp) fn advance_cpu_write_ptr(qs: &Coherent<GspMem>, count: u32) {
         let wptr = cpu_write_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
 
         dma_write!(qs, .cpuq.tx.0.writePtr, wptr);
-
-        // Ensure all command data is visible before triggering the GSP read.
-        fence(Ordering::SeqCst);
     }
 }
 
-- 
2.51.2