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 BE25E1C6FFE; Wed, 5 Mar 2025 17:58:19 +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=1741197499; cv=none; b=tX3gYAn6VjtHSm4O0qgdey+n0p0ybakTKCl4md4NlC/tJJPLCqW5eJM61+2n3POo0FNkCkPiivSRFajqWRZ+voQ69IseEr3LIhj6PHrTS2ovofX9szqO/YDMorTHnN4vIM6/6zlKytxQCUCwyOVM4VVDUAjWrvHVzuxYTwGYBMk= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1741197499; c=relaxed/simple; bh=vBrvbcEHef14tOD01uujXOoGTVoMKFpyLnfU2fYI8+A=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=bpOvAd/QZNPam0Ewov6uBH2S0U7WyhvNAEp9yIvlGTHDj2GvusFVUjdBtmkYWjSVpMGb1qrVFlAXvilJw7u/KiS551wfpw29dgyZyg+8A1qWH40//A4HFdhy1Qt52FIU8nfCshEiLbN0u4+WpKoAPnmDdr1HVEukerGn21p1PWU= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=PW8ozBPN; 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="PW8ozBPN" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 44F4DC4CED1; Wed, 5 Mar 2025 17:58:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1741197499; bh=vBrvbcEHef14tOD01uujXOoGTVoMKFpyLnfU2fYI8+A=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=PW8ozBPNfmxR0ta/im2vTUiFCFhfTPi8yX1/6aO/yrwB0NL6RP4JTdXdb2OYh4COA hGyCVWc8HltEzajRNGp+j6y1G27hUsHHXPPOR4UipcU//A3wRB8Y7701Z3Mh9Dj0ea iSIyptCmEGJpRzDk+BIUgaBExKU+ZrZH7amRbGCU= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, Lijo Lazar , "chr[]" , Alex Deucher , "Maciej S. Szmigiero" Subject: [PATCH 6.1 170/176] amdgpu/pm/legacy: fix suspend/resume issues Date: Wed, 5 Mar 2025 18:48:59 +0100 Message-ID: <20250305174512.265134017@linuxfoundation.org> X-Mailer: git-send-email 2.48.1 In-Reply-To: <20250305174505.437358097@linuxfoundation.org> References: <20250305174505.437358097@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 6.1-stable review patch. If anyone has any objections, please let me know. ------------------ From: chr[] commit 91dcc66b34beb72dde8412421bdc1b4cd40e4fb8 upstream. resume and irq handler happily races in set_power_state() * amdgpu_legacy_dpm_compute_clocks() needs lock * protect irq work handler * fix dpm_enabled usage v2: fix clang build, integrate Lijo's comments (Alex) Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2524 Fixes: 3712e7a49459 ("drm/amd/pm: unified lock protections in amdgpu_dpm.c") Reviewed-by: Lijo Lazar Tested-by: Maciej S. Szmigiero # on Oland PRO Signed-off-by: chr[] Signed-off-by: Alex Deucher (cherry picked from commit ee3dc9e204d271c9c7a8d4d38a0bce4745d33e71) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c | 25 ++++++++++++++++++------ drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c | 8 +++++-- drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 26 +++++++++++++++++++------ 3 files changed, 45 insertions(+), 14 deletions(-) --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -3056,6 +3056,7 @@ static int kv_dpm_hw_init(void *handle) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); if (ret) @@ -3063,6 +3064,8 @@ static int kv_dpm_hw_init(void *handle) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); + return ret; } @@ -3080,32 +3083,42 @@ static int kv_dpm_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ kv_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } return 0; } static int kv_dpm_resume(void *handle) { - int ret; + int ret = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); /* asic init will reset to the boot state */ kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + return ret; } static bool kv_dpm_is_idle(void *handle) --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1018,9 +1018,12 @@ void amdgpu_dpm_thermal_work_handler(str enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL; int temp, size = sizeof(temp); - if (!adev->pm.dpm_enabled) - return; + mutex_lock(&adev->pm.mutex); + if (!adev->pm.dpm_enabled) { + mutex_unlock(&adev->pm.mutex); + return; + } if (!pp_funcs->read_sensor(adev->powerplay.pp_handle, AMDGPU_PP_SENSOR_GPU_TEMP, (void *)&temp, @@ -1042,4 +1045,5 @@ void amdgpu_dpm_thermal_work_handler(str adev->pm.dpm.state = dpm_state; amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle); + mutex_unlock(&adev->pm.mutex); } --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -7796,6 +7796,7 @@ static int si_dpm_hw_init(void *handle) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); if (ret) @@ -7803,6 +7804,7 @@ static int si_dpm_hw_init(void *handle) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); return ret; } @@ -7820,32 +7822,44 @@ static int si_dpm_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ si_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } + return 0; } static int si_dpm_resume(void *handle) { - int ret; + int ret = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { /* asic init will reset to the boot state */ + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + + return ret; } static bool si_dpm_is_idle(void *handle)