From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 0A906CC6B3F for ; Thu, 2 Apr 2026 15:25:43 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 5AA0910F2B8; Thu, 2 Apr 2026 15:25:42 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=kernel.org header.i=@kernel.org header.b="WWFy+j0h"; dkim-atps=neutral Received: from sea.source.kernel.org (sea.source.kernel.org [172.234.252.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 49A7F10F2BD; Thu, 2 Apr 2026 15:25:41 +0000 (UTC) Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sea.source.kernel.org (Postfix) with ESMTP id 2E73843ABE; Thu, 2 Apr 2026 15:25:41 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id F3369C116C6; Thu, 2 Apr 2026 15:25:35 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1775143541; bh=H/ah7c8QblLITP8uZx6rQ0un/4q3xoSn//XPdWvMKg4=; h=From:To:Cc:Subject:Date:In-Reply-To:References:Reply-To:From; b=WWFy+j0hRa4F4bO2EyJSlQJHcjpjpFFyjoTGDTtQjbjJzxTkfZTuhsSiTyyWfX0O6 g8vteUT5Rt/P+nSlO8IOZsb+5RgeXoASrPj02F/QUpNaVWyonQeoCTK9x4dhl1XXbs jfZ5iC7mVVQxOEJ7Oxyyam5pxByJzK8iKhMs07MX/0bItN4OcZZPImdZqt6HGC7kk6 k1DslyAQTlkKWRLMW/s0H9WLkaxQtKFuZ2+GXcIanu5Y7IzXiD3HdRl/3lW8+iDFO8 eYEYAdmUgrqDX7WspZto8eIeJbVIsour5bzkBTq/QAEZZOebr9ozUc6D3ldNaWNAzo GYbFhHKTSAcFw== From: Gary Guo To: Miguel Ojeda , Boqun Feng , Gary Guo , =?UTF-8?q?Bj=C3=B6rn=20Roy=20Baron?= , Benno Lossin , Andreas Hindborg , Alice Ryhl , Trevor Gross , Danilo Krummrich , Alexandre Courbot , David Airlie , Simona Vetter Cc: Alan Stern , Andrea Parri , Will Deacon , Peter Zijlstra , Nicholas Piggin , David Howells , Jade Alglave , Luc Maranget , "Paul E. McKenney" , Akira Yokosawa , Daniel Lustig , Joel Fernandes , rust-for-linux@vger.kernel.org, nouveau@lists.freedesktop.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, lkmm@lists.linux.dev, dri-devel@lists.freedesktop.org Subject: [PATCH 3/3] gpu: nova-core: fix wrong use of barriers in GSP code Date: Thu, 2 Apr 2026 16:24:36 +0100 Message-ID: <20260402152443.1059634-5-gary@kernel.org> X-Mailer: git-send-email 2.51.2 In-Reply-To: <20260402152443.1059634-2-gary@kernel.org> References: <20260402152443.1059634-2-gary@kernel.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: Gary Guo Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" From: Gary Guo 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 --- 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) -> Result { 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) -> u32 { pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &Coherent, 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, 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