From nobody Sat Nov 23 23:22:13 2024 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.9]) (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 41CF41E883E; Fri, 8 Nov 2024 12:29:30 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.9 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068971; cv=none; b=eXzUe/zJLMF2wP0zlGxKVBljQgDD4btBtBHcnX0dSEo85caYzlFH7fqXR0spJ1zd+kGgFF590DzGY+apULObbxysZ8eeUCWpEhMF5/PtQbgKZJcko4rP8RLw2/CWSVRN4PIje/OedPlqZXMWet3hy8Bg+Aa0yTGWcjHK28BZ4xc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068971; c=relaxed/simple; bh=zSBLRIBbaYeA+QemFOtWX9BgOHY9bYPGcEOfeM2A010=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=c/IVZsKOEiMKF67qI1IJE3xmiqEmBO0u9HPD7qVKdsIP80IAjKP5r+dt0x9/M3bA0AB2BBAUMWEBL9+/pgb5SUuiNJFwZfUEc0L73ClziTyTZHd4n1u89kP03zSY1s28pr+fRFW3Un897dN6Gr1E2zYN4d9KMX8uNHnt+8MIZIg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com; spf=none smtp.mailfrom=linux.intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Ck1PMiQ2; arc=none smtp.client-ip=198.175.65.9 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Ck1PMiQ2" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1731068970; x=1762604970; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=zSBLRIBbaYeA+QemFOtWX9BgOHY9bYPGcEOfeM2A010=; b=Ck1PMiQ2dijzQLF9axPiki0M6dYV5ybN9a0i7wgNytV7G+0Pp8mrXFik 9U62T0Zgk9Wdd/PlBidQJpXmzhaqLH/lj8TlNhxRbgcwff1dirVRnEI/n VbRe2mj9hcq05BmRnRZe0PImulIYooGJvv1OgzS0JSaBSrRYVFd2y1RJj KoeFpVR9TsOoCVpkxzv1961VQO4jFJAzjchIFHl/NLV/u5X5b2TiaOuds N3ImhfPibOtaCsxjhInC4DYqfip07jtsgseNVYgtPPkd8yXGJ4ZXEmoBh CPxy5O1niWczFzf6PXKKDXxrL0+mDzHvOQS3ikPHqX74l5U21z/FpgQ3V g==; X-CSE-ConnectionGUID: q7ICO7dDQBCUF7dbselpjg== X-CSE-MsgGUID: 3oxBPrs0Q5uZdRcCdf6EeA== X-IronPort-AV: E=McAfee;i="6700,10204,11222"; a="53510347" X-IronPort-AV: E=Sophos;i="6.11,199,1725346800"; d="scan'208";a="53510347" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by orvoesa101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:30 -0800 X-CSE-ConnectionGUID: 8HdpXsAlRQWi9TT9ET/2qA== X-CSE-MsgGUID: XjDM3UkhSKmkGkq98pK5pw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.12,137,1728975600"; d="scan'208";a="85921049" Received: from hrotuna-mobl2.ger.corp.intel.com (HELO localhost.localdomain) ([10.245.245.89]) by orviesa007-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:27 -0800 From: Patryk Wlazlyn To: x86@kernel.org Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, rafael.j.wysocki@intel.com, len.brown@intel.com, artem.bityutskiy@linux.intel.com, dave.hansen@linux.intel.com, patryk.wlazlyn@linux.intel.com Subject: [PATCH v3 1/3] x86/smp: Allow calling mwait_play_dead with arbitrary hint Date: Fri, 8 Nov 2024 13:29:07 +0100 Message-ID: <20241108122909.763663-2-patryk.wlazlyn@linux.intel.com> X-Mailer: git-send-email 2.47.0 In-Reply-To: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> References: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" The current implementation for looking up the mwait hint for the deepest cstate depends on them to be continuous in range [0, NUM_SUBSTATES-1]. While that is correct on most Intel x86 platforms, it is not documented and may not result in reaching the most optimized idle state on some of them. For example Intel's Sierra Forest report two C6 substates in cpuid leaf 5: C6S (hint 0x22) C6SP (hint 0x23) Hints 0x20 and 0x21 are skipped entirely, causing the current implementation to compute the wrong hint, when looking for the deepest cstate for offlined CPU to enter. As a result, package with an offlined CPU can never reach PC6. Allow the idle driver to call mwait_play_dead() code with the forced mwait hint, skipping the cpuid based computation. Signed-off-by: Patryk Wlazlyn --- arch/x86/include/asm/smp.h | 6 ++++++ arch/x86/kernel/smpboot.c | 25 ++++++++++++++++++------- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index ca073f40698f..fbd275d6661a 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -114,6 +114,7 @@ void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); =20 void smp_kick_mwait_play_dead(void); +int mwait_play_dead_with_hint(unsigned long hint); =20 void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); @@ -164,6 +165,11 @@ static inline struct cpumask *cpu_llc_shared_mask(int = cpu) { return (struct cpumask *)cpumask_of(0); } + +static inline int mwait_play_dead_with_hint(unsigned long eax_hint) +{ + return 1; +} #endif /* CONFIG_SMP */ =20 #ifdef CONFIG_DEBUG_NMI_SELFTEST diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0c35207320cb..44c40781bad6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1270,13 +1270,14 @@ void play_dead_common(void) local_irq_disable(); } =20 +int mwait_play_dead_with_hint(unsigned long eax_hint); + /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. */ -static inline void mwait_play_dead(void) +static inline int mwait_play_dead(void) { - struct mwait_cpu_dead *md =3D this_cpu_ptr(&mwait_cpu_dead); unsigned int eax, ebx, ecx, edx; unsigned int highest_cstate =3D 0; unsigned int highest_subcstate =3D 0; @@ -1284,13 +1285,13 @@ static inline void mwait_play_dead(void) =20 if (boot_cpu_data.x86_vendor =3D=3D X86_VENDOR_AMD || boot_cpu_data.x86_vendor =3D=3D X86_VENDOR_HYGON) - return; + return 1; if (!this_cpu_has(X86_FEATURE_MWAIT)) - return; + return 1; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) - return; + return 1; if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) - return; + return 1; =20 eax =3D CPUID_MWAIT_LEAF; ecx =3D 0; @@ -1314,6 +1315,13 @@ static inline void mwait_play_dead(void) (highest_subcstate - 1); } =20 + return mwait_play_dead_with_hint(eax); +} + +int mwait_play_dead_with_hint(unsigned long eax_hint) +{ + struct mwait_cpu_dead *md =3D this_cpu_ptr(&mwait_cpu_dead); + /* Set up state for the kexec() hack below */ md->status =3D CPUDEAD_MWAIT_WAIT; md->control =3D CPUDEAD_MWAIT_WAIT; @@ -1333,7 +1341,7 @@ static inline void mwait_play_dead(void) mb(); __monitor(md, 0, 0); mb(); - __mwait(eax, 0); + __mwait(eax_hint, 0); =20 if (READ_ONCE(md->control) =3D=3D CPUDEAD_MWAIT_KEXEC_HLT) { /* @@ -1353,6 +1361,9 @@ static inline void mwait_play_dead(void) native_halt(); } } + + /* Never reached */ + return 0; } =20 /* --=20 2.47.0 From nobody Sat Nov 23 23:22:13 2024 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.9]) (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 C959B1E907C; Fri, 8 Nov 2024 12:29:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.9 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068975; cv=none; b=H3kxWk/AOxBW03E/7qptGrPD1FkfcMICdkIq8r5CYBRAeEwlQzNO14EqY9+LWJPsMEzradTcH2j/VEh3WQs9XmxNRLnuzY6YCqKojExZe2TsexnmebVz+lVP0QefLHqxGaGjW4W4vCIouZmbFLz9V1t6UdrIh2Qt7mVULt982k4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068975; c=relaxed/simple; bh=b7srFW4ztylUzGKNKDA1PC2mqEDgmyxEsntlM8t70ig=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=h9ND68t8bvbExYwfhs0Pw5mBB/+NpcEMtICemS3vNrIyjUTeEcxIfJFC6Wv8rFVeeLqdXfzyhucR/6BJCHvAWl4N7zxODrTtIQk9sl+qTzLOxXuLHX2GoQptHe8v2cJtPXZp51fcjSbX6UMNI8CwQPukZ1jlyNW9BdzztqoM0b0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com; spf=none smtp.mailfrom=linux.intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=HKbpINH0; arc=none smtp.client-ip=198.175.65.9 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="HKbpINH0" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1731068973; x=1762604973; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=b7srFW4ztylUzGKNKDA1PC2mqEDgmyxEsntlM8t70ig=; b=HKbpINH0ygkQ0QG5B0t1lGlZ36vM67tnAfxrr88e6eZ3rt5SyG/sgHdi V0Wt9AbWcwcUj7FVt9W1BHZrfSwE2khi1K9bBASOQUmZZb9uaHWDxaK4m XZ86bccWamNsO1BVRf6ZuOUwYRBu+qtIvma0KfWyHXtH3wM/drX/1mR1j yGiY9nRgupo6ARx6zNYTaYqwOIlGWZlQyB+60/Ao8ufirWrEA2Cf9Vijr DJY55xBlBj9S1LrBp93PpGZnznQGiX2SzN6lZnJQp/Cp2QFOtf2oQQ3iL gsAEF5AsoulJvxarVhwuTDnLQkeuYD/Tkq3IN3jOFacWR7wo0NYVbnuXu w==; X-CSE-ConnectionGUID: mTZgeywHTJWM/PKNIb2dTA== X-CSE-MsgGUID: UVTPy8IrRk2YGP9IWyy+MA== X-IronPort-AV: E=McAfee;i="6700,10204,11222"; a="53510361" X-IronPort-AV: E=Sophos;i="6.11,199,1725346800"; d="scan'208";a="53510361" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by orvoesa101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:33 -0800 X-CSE-ConnectionGUID: rIpTTDHIT9qMAd99VtFkqA== X-CSE-MsgGUID: pFoPAVBHQ56apGPXxetzDQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.12,137,1728975600"; d="scan'208";a="85921121" Received: from hrotuna-mobl2.ger.corp.intel.com (HELO localhost.localdomain) ([10.245.245.89]) by orviesa007-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:31 -0800 From: Patryk Wlazlyn To: x86@kernel.org Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, rafael.j.wysocki@intel.com, len.brown@intel.com, artem.bityutskiy@linux.intel.com, dave.hansen@linux.intel.com, patryk.wlazlyn@linux.intel.com Subject: [PATCH v3 2/3] x86/smp native_play_dead: Prefer cpuidle_play_dead() over mwait_play_dead() Date: Fri, 8 Nov 2024 13:29:08 +0100 Message-ID: <20241108122909.763663-3-patryk.wlazlyn@linux.intel.com> X-Mailer: git-send-email 2.47.0 In-Reply-To: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> References: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" The generic implementation, based on cpuid leaf 0x5, for looking up the mwait hint for the deepest cstate, depends on them to be continuous in range [0, NUM_SUBSTATES-1]. While that is correct on most Intel x86 platforms, it is not architectural and may not result in reaching the most optimized idle state on some of them. Prefer cpuidle_play_dead() over the generic mwait_play_dead() loop and fallback to the later in case of missing enter_dead() handler. Signed-off-by: Patryk Wlazlyn --- arch/x86/kernel/smpboot.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 44c40781bad6..721bb931181c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1416,9 +1416,9 @@ void native_play_dead(void) play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); =20 - mwait_play_dead(); if (cpuidle_play_dead()) - hlt_play_dead(); + mwait_play_dead(); + hlt_play_dead(); } =20 #else /* ... !CONFIG_HOTPLUG_CPU */ --=20 2.47.0 From nobody Sat Nov 23 23:22:13 2024 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.9]) (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 3554F1E909E; Fri, 8 Nov 2024 12:29:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.9 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068978; cv=none; b=rYpTXbWZlDtOE8bWSfBGBP/bZFDMnffl4jBiGwCaKD17h/dq8sR9hNqQPdBPTjCq/U8I5D0a4IbHeF8g/btUb4PT6y7oFWgMrOA/7hTIntXxk/C0MllsAaAql+7JRFgHMdHpN7TAcUwmhQDvis5rP+M0/vveF5v571Y4GpPJChc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731068978; c=relaxed/simple; bh=L38I2+o6gnX1T6/er6wZJJ8AUf3mBfnVxYyqd8usKPE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=X7MYCsffFcq7lRC2NbeV4nIf6SQpOTwTuJeY4SHxETWaseo3ApHqUdYhbf3TNT9Ui12VphuxANhrHpMC7tgqAWCFdGpJcqDlmX24jyfBQZxyu4KQsJSRY8CApUXeeRIzkAxQnMUkrHVN2fHI29wjN+cGVaEokB8AGaxnYgJrLT4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com; spf=none smtp.mailfrom=linux.intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=As/Zb1/X; arc=none smtp.client-ip=198.175.65.9 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="As/Zb1/X" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1731068977; x=1762604977; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=L38I2+o6gnX1T6/er6wZJJ8AUf3mBfnVxYyqd8usKPE=; b=As/Zb1/X2yKAS5VadxYiKL6frvhKt5bbcldA6GGT1n9zKb/bmUL41J1g fH8dQdZqXP5D22BR5BIDuloOtL/eufTh3vDINvcGy7aFxc11FNtfwV3c3 lwvFpRnupMiz/7LbXRGAUfDM/Rqmv33JkWSmIATIghk6Cer8xWZEd6Eph tZ+u9SS+CJviQdh6tx6GC1eBO/1tgfWlOchrJcZaeDSEjBA4nAec0Y2u0 QvBKrg8cJ56rljomDS1GEoOf6xUqn+dc8jC/LseCI6IbTwz8eA8p1ZyQ6 fVWfFRl+rFXBHZtG+TiYBDi96mQhmqJVcLcWFA3cqffyfLbePKZaXTeTo w==; X-CSE-ConnectionGUID: h9aHjMmIT2mZykpqGV1lbQ== X-CSE-MsgGUID: gegJLLa5QzaYaUdznr6D+g== X-IronPort-AV: E=McAfee;i="6700,10204,11222"; a="53510370" X-IronPort-AV: E=Sophos;i="6.11,199,1725346800"; d="scan'208";a="53510370" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by orvoesa101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:37 -0800 X-CSE-ConnectionGUID: YczP97SkQNOo7VhFmMiK4g== X-CSE-MsgGUID: ilEkI6JxR/+gbnobEl4f6Q== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.12,137,1728975600"; d="scan'208";a="85921168" Received: from hrotuna-mobl2.ger.corp.intel.com (HELO localhost.localdomain) ([10.245.245.89]) by orviesa007-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Nov 2024 04:29:34 -0800 From: Patryk Wlazlyn To: x86@kernel.org Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, rafael.j.wysocki@intel.com, len.brown@intel.com, artem.bityutskiy@linux.intel.com, dave.hansen@linux.intel.com, patryk.wlazlyn@linux.intel.com Subject: [PATCH v3 3/3] intel_idle: Provide enter_dead() handler for SRF Date: Fri, 8 Nov 2024 13:29:09 +0100 Message-ID: <20241108122909.763663-4-patryk.wlazlyn@linux.intel.com> X-Mailer: git-send-email 2.47.0 In-Reply-To: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> References: <20241108122909.763663-1-patryk.wlazlyn@linux.intel.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Intel's Sierra Forest report two C6 substates in cpuid leaf 5: C6S (hint 0x22) C6SP (hint 0x23) Hints 0x20 and 0x21 are skipped entirely, causing the generic implementation in mwait_play_dead() to compute the wrong hint, when looking for the deepest cstate. As a result, package with an offlined CPU can never reach PC6. Define the enter_dead() handler for SRF. Signed-off-by: Patryk Wlazlyn --- drivers/idle/intel_idle.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 9aab7abc2ae9..bd67959e5e8b 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -56,6 +56,7 @@ #include #include #include +#include =20 #define INTEL_IDLE_VERSION "0.5.1" =20 @@ -221,6 +222,17 @@ static __cpuidle int intel_idle_s2idle(struct cpuidle_= device *dev, return 0; } =20 +static __cpuidle int intel_idle_enter_dead(struct cpuidle_device *dev, + int index) +{ + struct cpuidle_driver *drv =3D cpuidle_get_cpu_driver(dev); + struct cpuidle_state *state =3D &drv->states[index]; + unsigned long eax =3D flg2MWAIT(state->flags); + + /* Retruns only in case of an error. */ + return mwait_play_dead_with_hint(eax); +} + /* * States are indexed by the cstate number, * which is also the index into the MWAIT hint array. @@ -1303,6 +1315,7 @@ static struct cpuidle_state srf_cstates[] __initdata = =3D { .exit_latency =3D 1, .target_residency =3D 1, .enter =3D &intel_idle, + .enter_dead =3D &intel_idle_enter_dead, .enter_s2idle =3D intel_idle_s2idle, }, { .name =3D "C1E", @@ -1311,6 +1324,7 @@ static struct cpuidle_state srf_cstates[] __initdata = =3D { .exit_latency =3D 2, .target_residency =3D 10, .enter =3D &intel_idle, + .enter_dead =3D &intel_idle_enter_dead, .enter_s2idle =3D intel_idle_s2idle, }, { .name =3D "C6S", @@ -1319,6 +1333,7 @@ static struct cpuidle_state srf_cstates[] __initdata = =3D { .exit_latency =3D 270, .target_residency =3D 700, .enter =3D &intel_idle, + .enter_dead =3D &intel_idle_enter_dead, .enter_s2idle =3D intel_idle_s2idle, }, { .name =3D "C6SP", @@ -1327,6 +1342,7 @@ static struct cpuidle_state srf_cstates[] __initdata = =3D { .exit_latency =3D 310, .target_residency =3D 900, .enter =3D &intel_idle, + .enter_dead =3D &intel_idle_enter_dead, .enter_s2idle =3D intel_idle_s2idle, }, { .enter =3D NULL } --=20 2.47.0