[PATCH v4 2/2] gpu: nova-core: fix barrier usage in GSP->CPU messaging path

[Gary Guo <gary@garyguo.net>]

In the GSP->CPU messaging path, the code reads the write pointer from GSP,
reads the response and advances the read pointer.

A LOAD->LOAD ordering is required after the write pointer read and the data
read. Add it as this is currently missing.

A LOAD->STORE ordering is required after the data read and the advance of
read pointer. Currently a Rust `SeqCst` barrier is used, which roughly maps
to `smp_mb(Full)`; this however does not order DMA operations (notably on
ARM, the generate barrier orders inner shareable and not outer shareable,
which is ordered by `dma_mb`). This ordering does not need to be in between
read pointer read and write, because it's for ordering between the ring
buffer data and the pointer; the RMW operation does not internally need a
barrier (nor it has to be atomic, as CPU pointers are updated by CPU only),
so move it to before the RMW sequence for clarity.

Signed-off-by: Gary Guo <gary@garyguo.net>
---
 drivers/gpu/nova-core/gsp/cmdq.rs | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index bfd61e678802..14a711307654 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -2,13 +2,7 @@
 
 mod continuation;
 
-use core::{
-    mem,
-    sync::atomic::{
-        fence,
-        Ordering, //
-    },
-};
+use core::mem;
 
 use kernel::{
     device,
@@ -30,6 +24,7 @@
         barrier::{
             dma_mb,
             Full,
+            Read,
             Write, //
         },
         Mutex, //
@@ -409,7 +404,12 @@ fn allocate_command(&mut self, size: usize, timeout: Delta) -> Result<GspCommand
     //
     // - The returned value is within `0..MSGQ_NUM_PAGES`.
     fn gsp_write_ptr(&self) -> u32 {
-        MsgqTxHeader::write_ptr(io_project!(self.0, .gspq.tx)) % MSGQ_NUM_PAGES
+        let ptr = MsgqTxHeader::write_ptr(io_project!(self.0, .gspq.tx)) % MSGQ_NUM_PAGES;
+
+        // ORDERING: LOAD->LOAD ordering needed to order `gsp_write_ptr` read before data read.
+        dma_mb(Read);
+
+        ptr
     }
 
     // Returns the index of the memory page the GSP will read the next command from.
@@ -437,12 +437,11 @@ 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: LOAD->STORE ordering needed to order `cpu_read_ptr` write after data read.
+        dma_mb(Full);
+
         let rx = io_project!(self.0, .cpuq.rx);
         let rptr = MsgqRxHeader::read_ptr(rx).wrapping_add(elem_count) % MSGQ_NUM_PAGES;
-
-        // Ensure read pointer is properly ordered.
-        fence(Ordering::SeqCst);
-
         MsgqRxHeader::set_read_ptr(rx, rptr)
     }
 

-- 
2.54.0