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 96E35F41811 for ; Mon, 9 Mar 2026 16:35:23 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 7367F10E558; Mon, 9 Mar 2026 16:35:21 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=kernel.org header.i=@kernel.org header.b="nE9CPFES"; 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 5102010E558; Mon, 9 Mar 2026 16:35:19 +0000 (UTC) Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sea.source.kernel.org (Postfix) with ESMTP id 3180644510; Mon, 9 Mar 2026 16:35:19 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPS id C224BC2BCB7; Mon, 9 Mar 2026 16:35:18 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1773074118; bh=fssZhaE39h8/ifGb5lyKDHlx9SyrHqGfVID8VjmY0ME=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=nE9CPFESeIElYpdFRVFYi/eDY9RoazP12jcTKXLiS3P7dRa9zphKtGh1pPAm0qMUf Si1w3fT84m6mtNoKkiABeBnJPXnSSW1pcCw5+SieCJkAQsC0XZRTZbvXQhkysdgEm9 B56/DvoqOv6oxIeGkLvbO/i/fL6vA8SyOZbjKIf6Ub6oMWmKpiG3trmrmtJGoc+9ut oISHSJI+QPG7Oi1wFCM0b/vDyzjppoceO75Z3Y3wZExWRhgsBxLQdEUmL3sEVDuhK9 Xmb/yGfDEC15+YoOym7ExlwwmTmLi825LE4F0VxIHZet28u3jXNL+ZEPYjOhdEi7rC oLdNDkjd3nh2g== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id B1174F41812; Mon, 9 Mar 2026 16:35:18 +0000 (UTC) From: Tim Kovalenko via B4 Relay Date: Mon, 09 Mar 2026 12:34:21 -0400 Subject: [PATCH v4 4/4] gpu: nova-core: fix stack overflow in GSP memory allocation MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Message-Id: <20260309-drm-rust-next-v4-4-4ef485b19a4c@proton.me> References: <20260309-drm-rust-next-v4-0-4ef485b19a4c@proton.me> In-Reply-To: <20260309-drm-rust-next-v4-0-4ef485b19a4c@proton.me> To: Alexandre Courbot , Danilo Krummrich , Alice Ryhl , David Airlie , Simona Vetter , Miguel Ojeda , Gary Guo , =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= , Benno Lossin , Andreas Hindborg , Trevor Gross , Boqun Feng , Nathan Chancellor , Nicolas Schier , Abdiel Janulgue , Daniel Almeida , Robin Murphy , Boqun Feng Cc: nouveau@lists.freedesktop.org, dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org, rust-for-linux@vger.kernel.org, linux-kbuild@vger.kernel.org, driver-core@lists.linux.dev, Tim Kovalenko X-Mailer: b4 0.14.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1773074117; l=3986; i=tim.kovalenko@proton.me; s=20260212; h=from:subject:message-id; bh=02lIiBKVUWPZgiHflont6ppBx+2QAZbO4PzXiivsIkE=; b=pE0ZKAo+0q+3X2PamEznSFPbbQiSdIw7Xy/EgQG+Zfy/iiwn0Rb6Om2UKZsCeEXyeudQjTtkF +jL/j8+uX6ICxdDQJsEfm++qZt+CwLBc7cGDTtVkdNtnXo/EFKH2KKd X-Developer-Key: i=tim.kovalenko@proton.me; a=ed25519; pk=/+OiulEpgeZifgP4mDE4e5YlV6nMeY+frze/lY/xiHI= X-Endpoint-Received: by B4 Relay for tim.kovalenko@proton.me/20260212 with auth_id=635 X-Original-From: Tim Kovalenko 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: tim.kovalenko@proton.me Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" From: Tim Kovalenko The `Cmdq::new` function was allocating a `PteArray` struct on the stack and was causing a stack overflow with 8216 bytes. Modify the `PteArray` to calculate and write the Page Table Entries directly into the coherent DMA buffer one-by-one. This reduces the stack usage quite a lot. Signed-off-by: Tim Kovalenko --- drivers/gpu/nova-core/gsp.rs | 34 +++++++++++++++++++--------------- drivers/gpu/nova-core/gsp/cmdq.rs | 15 ++++++++++++++- 2 files changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs index 25cd48514c777cb405a2af0acf57196b2e2e7837..20170e483e04c476efce8997b3916b0ad829ed38 100644 --- a/drivers/gpu/nova-core/gsp.rs +++ b/drivers/gpu/nova-core/gsp.rs @@ -47,16 +47,11 @@ unsafe impl AsBytes for PteArray {} impl PteArray { - /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`. - fn new(start: DmaAddress) -> Result { - let mut ptes = [0u64; NUM_PAGES]; - for (i, pte) in ptes.iter_mut().enumerate() { - *pte = start - .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT) - .ok_or(EOVERFLOW)?; - } - - Ok(Self(ptes)) + /// Returns the page table entry for `index`, for a mapping starting at `start` DmaAddress. + fn entry(start: DmaAddress, index: usize) -> Result { + start + .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT) + .ok_or(EOVERFLOW) } } @@ -86,16 +81,25 @@ fn new(dev: &device::Device) -> Result { NUM_PAGES * GSP_PAGE_SIZE, GFP_KERNEL | __GFP_ZERO, )?); - let ptes = PteArray::::new(obj.0.dma_handle())?; + + let start_addr = obj.0.dma_handle(); // SAFETY: `obj` has just been created and we are its sole user. - unsafe { - // Copy the self-mapping PTE at the expected location. + let pte_region = unsafe { obj.0 - .as_slice_mut(size_of::(), size_of_val(&ptes))? - .copy_from_slice(ptes.as_bytes()) + .as_slice_mut(size_of::(), NUM_PAGES * size_of::())? }; + // This is a one by one GSP Page write to the memory + // to avoid stack overflow when allocating the whole array at once. + for (i, chunk) in pte_region.chunks_exact_mut(size_of::()).enumerate() { + let pte_value = start_addr + .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT) + .ok_or(EOVERFLOW)?; + + chunk.copy_from_slice(&pte_value.to_ne_bytes()); + } + Ok(obj) } } diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 0056bfbf0a44cfbc5a0ca08d069f881b877e1edc..c8327d3098f73f9b880eee99038ad10a16e1e32d 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -202,7 +202,20 @@ fn new(dev: &device::Device) -> Result { let gsp_mem = CoherentAllocation::::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?); + + const NUM_PTES: usize = GSP_PAGE_SIZE / size_of::(); + + let start = gsp_mem.dma_handle(); + // One by one GSP Page write to the memory to avoid stack overflow when allocating + // the whole array at once. + for i in 0..NUM_PTES { + dma_write!( + gsp_mem, + [0]?.ptes.0[i], + PteArray::::entry(start, i)? + ); + } + dma_write!( gsp_mem, [0]?.cpuq.tx, -- 2.53.0