From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A0AEF25A323; Tue, 27 May 2025 17:05:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748365516; cv=none; b=KeRI6NRNoFlOcTpyEcXtn1Q2d9Ifp9yXLWLurmjtx7O8M7/GvViXSrONjlVvWisLS5BbwoPZ0m0IIIAT8/NMrkO/YA8QrvNMR2FLlOKqibs1tPn44bO1RTN2vZgklt5+uxZtLM2PgnYNI7CEgN8dawM1abXwoIAvM14/YvAQyMw= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748365516; c=relaxed/simple; bh=3wQLB1djwlESRWfexQdm2oOlTMNb09FgYwJ3qReJhS4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=uWpaZDpnpD98TxDppGNwdgGZBfyWecUiAXtRyAzISFFw6YRG/mWo+JRwlQJfbEAS8Im5pFAjtCUZeEVNl91riLfLVJzEi6L0OdKS7JS4WCzVsnK9lu5S1hWzLuBOLYin7zGmxTHTJZLPPdytUuQMzgO7SoD4ox3qCEAZWq9a2Pc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=UBPAD94V; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="UBPAD94V" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 106EBC4CEE9; Tue, 27 May 2025 17:05:15 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1748365516; bh=3wQLB1djwlESRWfexQdm2oOlTMNb09FgYwJ3qReJhS4=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=UBPAD94VDjQKcZ/zq/bdsEN+8Lu5Z763ZBdKcUqx/JmWSMIq4hzN1hkTK9VwouiSt ywesc2R3PHFxQzuPZy/IUDPtMjA+uaYTDwUvUXGxDnYbTz8oFaU30PXGCp28xUkzeD PZLrWVuk+MHzf3A2RiLfb/fTn3HgurMAFrBdtwd4= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, Lijo Lazar , Hawking Zhang , Alex Deucher , Sasha Levin Subject: [PATCH 6.12 401/626] drm/amdgpu: Use active umc info from discovery Date: Tue, 27 May 2025 18:24:54 +0200 Message-ID: <20250527162501.308782693@linuxfoundation.org> X-Mailer: git-send-email 2.49.0 In-Reply-To: <20250527162445.028718347@linuxfoundation.org> References: <20250527162445.028718347@linuxfoundation.org> User-Agent: quilt/0.68 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: stable@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 6.12-stable review patch. If anyone has any objections, please let me know. ------------------ From: Lijo Lazar [ Upstream commit f7a594e40517fa2ab25d5ca10e7b6a158f529fb5 ] There could be configs where some UMC instances are harvested. This information is obtained through discovery data and populated in umc.active_mask. Avoid reassigning this as AID mask, instead use the mask directly while iterating through umc instances. This is to avoid accesses to harvested UMC instances. v2: fix warning (Alex) Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 42 +++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 1 - 2 files changed, 42 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index bb7b9b2eaac1a..8da0bddab3d23 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -383,6 +383,45 @@ int amdgpu_umc_fill_error_record(struct ras_err_data *err_data, return 0; } +static int amdgpu_umc_loop_all_aid(struct amdgpu_device *adev, umc_func func, + void *data) +{ + uint32_t umc_node_inst; + uint32_t node_inst; + uint32_t umc_inst; + uint32_t ch_inst; + int ret; + + /* + * This loop is done based on the following - + * umc.active mask = mask of active umc instances across all nodes + * umc.umc_inst_num = maximum number of umc instancess per node + * umc.node_inst_num = maximum number of node instances + * Channel instances are not assumed to be harvested. + */ + dev_dbg(adev->dev, "active umcs :%lx umc_inst per node: %d", + adev->umc.active_mask, adev->umc.umc_inst_num); + for_each_set_bit(umc_node_inst, &(adev->umc.active_mask), + adev->umc.node_inst_num * adev->umc.umc_inst_num) { + node_inst = umc_node_inst / adev->umc.umc_inst_num; + umc_inst = umc_node_inst % adev->umc.umc_inst_num; + LOOP_UMC_CH_INST(ch_inst) { + dev_dbg(adev->dev, + "node_inst :%d umc_inst: %d ch_inst: %d", + node_inst, umc_inst, ch_inst); + ret = func(adev, node_inst, umc_inst, ch_inst, data); + if (ret) { + dev_err(adev->dev, + "Node %d umc %d ch %d func returns %d\n", + node_inst, umc_inst, ch_inst, ret); + return ret; + } + } + } + + return 0; +} + int amdgpu_umc_loop_channels(struct amdgpu_device *adev, umc_func func, void *data) { @@ -391,6 +430,9 @@ int amdgpu_umc_loop_channels(struct amdgpu_device *adev, uint32_t ch_inst = 0; int ret = 0; + if (adev->aid_mask) + return amdgpu_umc_loop_all_aid(adev, func, data); + if (adev->umc.node_inst_num) { LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) { ret = func(adev, node_inst, umc_inst, ch_inst, data); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 9a212413c6d3a..78c527b56f7c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1461,7 +1461,6 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.umc_inst_num = UMC_V12_0_UMC_INSTANCE_NUM; adev->umc.node_inst_num /= UMC_V12_0_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V12_0_PER_CHANNEL_OFFSET; - adev->umc.active_mask = adev->aid_mask; adev->umc.retire_unit = UMC_V12_0_BAD_PAGE_NUM_PER_CHANNEL; if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu) adev->umc.ras = &umc_v12_0_ras; -- 2.39.5