From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 A1A982E0923 for ; Mon, 11 Aug 2025 18:17:32 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936255; cv=none; b=L8hbl+a21GaRnnB9mEy+YAYGxE7mgW6IeCutsPr+UOASiJ4jGjDEBg+nWHyxpYNgdXHqxDO7ogepxpdINHXGnPfoSPybTSS4+h9NNaEqf0bF4YI7Q1Kn2SKiPKGpajy6El2DLBgX3XrRRIOdBcTeoCnBaZEOai8K0gGIjWPPUGs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936255; c=relaxed/simple; bh=KQC4IXN5w5C/nDLMZOPXo7/9Tk1KyuWT0KnhDFzVnms=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=BdDNomiWDwDbYNTMJql5MaWrCxLW5IxSJW1EONGEw6AmASLKRZYJutTtfGH/5PqryG65zbstwkE1Jk7VU1JElp1BGmWsYoSOXqZk0n6wo9KwcuKjundrbXpjVWIJKKuA2PoMBOM24+TlDhEvEEudlFG1o19EW29tAetg84FwRw8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=mWbiJ+Fp; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="mWbiJ+Fp" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936254; x=1786472254; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=KQC4IXN5w5C/nDLMZOPXo7/9Tk1KyuWT0KnhDFzVnms=; b=mWbiJ+FpKjnvwhWLSef5IOeRm9zxY7v9MzL/7vEhAPwZPw1/7RRISIHo b1Rhb7jbCHRrzr8V+HFvQlcApDcNmOjfk/mvzfBufo0g4EXj0wQIf38fv fOcViBQu7JzOG3Te+Bi546nvfvYcZzloYu9BAGSsv1dp5JJ4yn0HLRq6L 8LYTysHYtztjocQwl5uFhmoLQyG9M7nSnjA+IVGgXRyz/tsJBMjtI+6WP E/zSBCR/a8zic3d6nHxzdIpi9eYpOf4bgfh28CIwHVAKIxAlZUTbauHn1 bPPFB3UvU9mEo55lMt3RxfLozEd22iqOFQF+gKBVmWB4v0StwbCkCbzSG Q==; X-CSE-ConnectionGUID: QnJNnh8SQIaS6FKkhvhrIw== X-CSE-MsgGUID: oJBfdFc3QHOzOGiIxe0/Cg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277343" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277343" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: pHEEAr65QWqUWxf6rnX95g== X-CSE-MsgGUID: P3J576ORSfWoc9E3+VwzAQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825612" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:22 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 01/32] x86,fs/resctrl: Consolidate monitor event descriptions Date: Mon, 11 Aug 2025 11:16:35 -0700 Message-ID: <20250811181709.6241-2-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" There are currently only three monitor events, all associated with the RDT_RESOURCE_L3 resource. Growing support for additional events will be easier with some restructuring to have a single point in file system code where all attributes of all events are defined. Place all event descriptions into an array mon_event_all[]. Doing this has the beneficial side effect of removing the need for rdt_resource::evt_list. Add resctrl_event_id::QOS_FIRST_EVENT for a lower bound on range checks for event ids and as the starting index to scan mon_event_all[]. Drop the code that builds evt_list and change the two places where the list is scanned to scan mon_event_all[] instead using a new helper macro for_each_mon_event(). Architecture code now informs file system code which events are available with resctrl_enable_mon_event(). Signed-off-by: Tony Luck Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre --- include/linux/resctrl.h | 4 +- include/linux/resctrl_types.h | 12 ++++-- fs/resctrl/internal.h | 13 ++++-- arch/x86/kernel/cpu/resctrl/core.c | 12 ++++-- fs/resctrl/monitor.c | 63 +++++++++++++++--------------- fs/resctrl/rdtgroup.c | 11 +++--- 6 files changed, 66 insertions(+), 49 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 6fb4894b8cfd..2944042bd84c 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -269,7 +269,6 @@ enum resctrl_schema_fmt { * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. * @schema_fmt: Which format string and parser is used for this schema. - * @evt_list: List of monitoring events * @mbm_cfg_mask: Bandwidth sources that can be tracked when bandwidth * monitoring events can be configured. * @cdp_capable: Is the CDP feature available on this resource @@ -287,7 +286,6 @@ struct rdt_resource { struct list_head mon_domains; char *name; enum resctrl_schema_fmt schema_fmt; - struct list_head evt_list; unsigned int mbm_cfg_mask; bool cdp_capable; }; @@ -372,6 +370,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); =20 +void resctrl_enable_mon_event(enum resctrl_event_id eventid); + bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); =20 /** diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h index a25fb9c4070d..2dadbc54e4b3 100644 --- a/include/linux/resctrl_types.h +++ b/include/linux/resctrl_types.h @@ -34,11 +34,15 @@ /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS GENMASK(6, 0) =20 -/* - * Event IDs, the values match those used to program IA32_QM_EVTSEL before - * reading IA32_QM_CTR on RDT systems. - */ +/* Event IDs */ enum resctrl_event_id { + /* Must match value of first event below */ + QOS_FIRST_EVENT =3D 0x01, + + /* + * These values match those used to program IA32_QM_EVTSEL before + * reading IA32_QM_CTR on RDT systems. + */ QOS_L3_OCCUP_EVENT_ID =3D 0x01, QOS_L3_MBM_TOTAL_EVENT_ID =3D 0x02, QOS_L3_MBM_LOCAL_EVENT_ID =3D 0x03, diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 0a1eedba2b03..4f315b7e9ec0 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -52,19 +52,26 @@ static inline struct rdt_fs_context *rdt_fc2context(str= uct fs_context *fc) } =20 /** - * struct mon_evt - Entry in the event list of a resource + * struct mon_evt - Properties of a monitor event * @evtid: event id + * @rid: resource id for this event * @name: name of the event * @configurable: true if the event is configurable - * @list: entry in &rdt_resource->evt_list + * @enabled: true if the event is enabled */ struct mon_evt { enum resctrl_event_id evtid; + enum resctrl_res_level rid; char *name; bool configurable; - struct list_head list; + bool enabled; }; =20 +extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; + +#define for_each_mon_event(mevt) for (mevt =3D &mon_event_all[QOS_FIRST_EV= ENT]; \ + mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++) + /** * struct mon_data - Monitoring details for each event file. * @list: Member of the global @mon_data_kn_priv_list list. diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 187d527ef73b..7fcae25874fe 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -864,12 +864,18 @@ static __init bool get_rdt_mon_resources(void) { struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; =20 - if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID); rdt_mon_features |=3D (1 << QOS_L3_OCCUP_EVENT_ID); - if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) + } + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID); rdt_mon_features |=3D (1 << QOS_L3_MBM_TOTAL_EVENT_ID); - if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) + } + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID); rdt_mon_features |=3D (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + } =20 if (!rdt_mon_features) return false; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index f5637855c3ac..2313e48de55f 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -844,38 +844,39 @@ static void dom_data_exit(struct rdt_resource *r) mutex_unlock(&rdtgroup_mutex); } =20 -static struct mon_evt llc_occupancy_event =3D { - .name =3D "llc_occupancy", - .evtid =3D QOS_L3_OCCUP_EVENT_ID, -}; - -static struct mon_evt mbm_total_event =3D { - .name =3D "mbm_total_bytes", - .evtid =3D QOS_L3_MBM_TOTAL_EVENT_ID, -}; - -static struct mon_evt mbm_local_event =3D { - .name =3D "mbm_local_bytes", - .evtid =3D QOS_L3_MBM_LOCAL_EVENT_ID, -}; - /* - * Initialize the event list for the resource. - * - * Note that MBM events are also part of RDT_RESOURCE_L3 resource - * because as per the SDM the total and local memory bandwidth - * are enumerated as part of L3 monitoring. + * All available events. Architecture code marks the ones that + * are supported by a system using resctrl_enable_mon_event() + * to set .enabled. */ -static void l3_mon_evt_init(struct rdt_resource *r) +struct mon_evt mon_event_all[QOS_NUM_EVENTS] =3D { + [QOS_L3_OCCUP_EVENT_ID] =3D { + .name =3D "llc_occupancy", + .evtid =3D QOS_L3_OCCUP_EVENT_ID, + .rid =3D RDT_RESOURCE_L3, + }, + [QOS_L3_MBM_TOTAL_EVENT_ID] =3D { + .name =3D "mbm_total_bytes", + .evtid =3D QOS_L3_MBM_TOTAL_EVENT_ID, + .rid =3D RDT_RESOURCE_L3, + }, + [QOS_L3_MBM_LOCAL_EVENT_ID] =3D { + .name =3D "mbm_local_bytes", + .evtid =3D QOS_L3_MBM_LOCAL_EVENT_ID, + .rid =3D RDT_RESOURCE_L3, + }, +}; + +void resctrl_enable_mon_event(enum resctrl_event_id eventid) { - INIT_LIST_HEAD(&r->evt_list); + if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >=3D QOS_NUM_EVENTS= )) + return; + if (mon_event_all[eventid].enabled) { + pr_warn("Duplicate enable for event %d\n", eventid); + return; + } =20 - if (resctrl_arch_is_llc_occupancy_enabled()) - list_add_tail(&llc_occupancy_event.list, &r->evt_list); - if (resctrl_arch_is_mbm_total_enabled()) - list_add_tail(&mbm_total_event.list, &r->evt_list); - if (resctrl_arch_is_mbm_local_enabled()) - list_add_tail(&mbm_local_event.list, &r->evt_list); + mon_event_all[eventid].enabled =3D true; } =20 /** @@ -902,15 +903,13 @@ int resctrl_mon_resource_init(void) if (ret) return ret; =20 - l3_mon_evt_init(r); - if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) { - mbm_total_event.configurable =3D true; + mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable =3D true; resctrl_file_fflags_init("mbm_total_bytes_config", RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) { - mbm_local_event.configurable =3D true; + mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].configurable =3D true; resctrl_file_fflags_init("mbm_local_bytes_config", RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 77d08229d855..b95501d4b5de 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -1152,7 +1152,9 @@ static int rdt_mon_features_show(struct kernfs_open_f= ile *of, struct rdt_resource *r =3D rdt_kn_parent_priv(of->kn); struct mon_evt *mevt; =20 - list_for_each_entry(mevt, &r->evt_list, list) { + for_each_mon_event(mevt) { + if (mevt->rid !=3D r->rid || !mevt->enabled) + continue; seq_printf(seq, "%s\n", mevt->name); if (mevt->configurable) seq_printf(seq, "%s_config\n", mevt->name); @@ -3057,10 +3059,9 @@ static int mon_add_all_files(struct kernfs_node *kn,= struct rdt_mon_domain *d, struct mon_evt *mevt; int ret, domid; =20 - if (WARN_ON(list_empty(&r->evt_list))) - return -EPERM; - - list_for_each_entry(mevt, &r->evt_list, list) { + for_each_mon_event(mevt) { + if (mevt->rid !=3D r->rid || !mevt->enabled) + continue; domid =3D do_sum ? d->ci_id : d->hdr.id; priv =3D mon_get_kn_priv(r->rid, domid, mevt, do_sum); if (WARN_ON_ONCE(!priv)) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 355C22E0B5A for ; Mon, 11 Aug 2025 18:17:32 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936253; cv=none; b=ZK21S5ZswNhzOx8oXZeG2GzXB4r8AZyO2eaKpAns+cFpXUUYPfbUI+7GKnxav9gnjeITzhlWVIG+3vgKSImj6tRASUq1XtqFYy7DB2IeWyKGMdXHkENO+ojTPwtEkcIa0Z5c95IxGL33f5KatqT+j2Pn1bCicyYHN2SS7BO+Hvs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936253; c=relaxed/simple; bh=DZNiWihZkWjzoSMzNQ9vWuh6BX5+qnFWuXszP/HRXQ4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=H/LT9bXbaWf3yUxv2lApRC4ivvINzSvSf3BCmYaKDrLJ0plEYvjCvDhQeaAVB9aDLy4BjP2tvN5E1ZMmVemgVhDxi1vB7Gaq2GXzp+qFN8q0P3Z0jTEcsYYtfuBibHjVpQn65iMom0erYNt5XxxNGTzdE6B6+k4mojaQ7kKVHfk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=PvuJxMXj; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="PvuJxMXj" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936253; x=1786472253; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=DZNiWihZkWjzoSMzNQ9vWuh6BX5+qnFWuXszP/HRXQ4=; b=PvuJxMXj26/SwVso349Sib+Kf5bp9kWNKHZtBnlsmEVZtemY2sousBhm wm7fcvnQdePRl0pcqcJlpfUDW8ho20FSam+qP0xzPbY23VnzZ2w3ghq3k 7kBlrx3Wk9fjd+BG+oE7wvpJT9bvOGOfcWJ8xUHjTzESr9W8Z2x0y/J9p pqUzN8WwQI/MC67e78/xZ8Q5bESwaQN4uef/F/m2pjTk6qnE7mzBPcyCd GJKXTzZZQj6o3dKePZYx+tTTw6Kh5pHpwdNhN0Ieq1bLmP2pDTuaY5mxq xUvY8fm1vPl4l+QfGw87ORDHqootC/oFBnusGA/yEOS6PzFg47AqvPVGV Q==; X-CSE-ConnectionGUID: PIiF0+huTOGo/Vz0lDurfg== X-CSE-MsgGUID: sqnYeaLbS9yRuO6usPpELw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277345" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277345" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: Y2YToH4HQliH5aRE+0Dxsw== X-CSE-MsgGUID: ZZEWSkwGT2iBsQdMeLtUJg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825615" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:22 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 02/32] x86,fs/resctrl: Replace architecture event enabled checks Date: Mon, 11 Aug 2025 11:16:36 -0700 Message-ID: <20250811181709.6241-3-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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 resctrl file system now has complete knowledge of the status of every event. So there is no need for per-event function calls to check. Replace each of the resctrl_arch_is_{event}enabled() calls with resctrl_is_mon_event_enabled(QOS_{EVENT}). No functional change. Signed-off-by: Tony Luck Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre --- include/linux/resctrl.h | 2 ++ arch/x86/include/asm/resctrl.h | 15 --------------- arch/x86/kernel/cpu/resctrl/core.c | 4 ++-- arch/x86/kernel/cpu/resctrl/monitor.c | 4 ++-- fs/resctrl/ctrlmondata.c | 4 ++-- fs/resctrl/monitor.c | 16 +++++++++++----- fs/resctrl/rdtgroup.c | 18 +++++++++--------- 7 files changed, 28 insertions(+), 35 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 2944042bd84c..40aba6b5d4f0 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -372,6 +372,8 @@ int resctrl_arch_update_domains(struct rdt_resource *r,= u32 closid); =20 void resctrl_enable_mon_event(enum resctrl_event_id eventid); =20 +bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); + bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); =20 /** diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index feb93b50e990..b1dd5d6b87db 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -84,21 +84,6 @@ static inline void resctrl_arch_disable_mon(void) static_branch_dec_cpuslocked(&rdt_enable_key); } =20 -static inline bool resctrl_arch_is_llc_occupancy_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); -} - -static inline bool resctrl_arch_is_mbm_total_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); -} - -static inline bool resctrl_arch_is_mbm_local_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); -} - /* * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 7fcae25874fe..1a319ce9328c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -402,13 +402,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct= rdt_hw_mon_domain *hw_dom) { size_t tsize; =20 - if (resctrl_arch_is_mbm_total_enabled()) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) { tsize =3D sizeof(*hw_dom->arch_mbm_total); hw_dom->arch_mbm_total =3D kcalloc(num_rmid, tsize, GFP_KERNEL); if (!hw_dom->arch_mbm_total) return -ENOMEM; } - if (resctrl_arch_is_mbm_local_enabled()) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) { tsize =3D sizeof(*hw_dom->arch_mbm_local); hw_dom->arch_mbm_local =3D kcalloc(num_rmid, tsize, GFP_KERNEL); if (!hw_dom->arch_mbm_local) { diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index c261558276cd..61d38517e2bf 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -207,11 +207,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource = *r, struct rdt_mon_domain * { struct rdt_hw_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); =20 - if (resctrl_arch_is_mbm_total_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) memset(hw_dom->arch_mbm_total, 0, sizeof(*hw_dom->arch_mbm_total) * r->num_rmid); =20 - if (resctrl_arch_is_mbm_local_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) memset(hw_dom->arch_mbm_local, 0, sizeof(*hw_dom->arch_mbm_local) * r->num_rmid); } diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index d98e0d2de09f..ad7ffc6acf13 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -473,12 +473,12 @@ ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_o= pen_file *of, rdt_last_cmd_clear(); =20 if (!strcmp(buf, "mbm_local_bytes")) { - if (resctrl_arch_is_mbm_local_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) rdtgrp->mba_mbps_event =3D QOS_L3_MBM_LOCAL_EVENT_ID; else ret =3D -EINVAL; } else if (!strcmp(buf, "mbm_total_bytes")) { - if (resctrl_arch_is_mbm_total_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) rdtgrp->mba_mbps_event =3D QOS_L3_MBM_TOTAL_EVENT_ID; else ret =3D -EINVAL; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 2313e48de55f..9e988b2c1a22 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -336,7 +336,7 @@ void free_rmid(u32 closid, u32 rmid) =20 entry =3D __rmid_entry(idx); =20 - if (resctrl_arch_is_llc_occupancy_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) add_rmid_to_limbo(entry); else list_add_tail(&entry->list, &rmid_free_lru); @@ -637,10 +637,10 @@ static void mbm_update(struct rdt_resource *r, struct= rdt_mon_domain *d, * This is protected from concurrent reads from user as both * the user and overflow handler hold the global mutex. */ - if (resctrl_arch_is_mbm_total_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID); =20 - if (resctrl_arch_is_mbm_local_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID); } =20 @@ -879,6 +879,12 @@ void resctrl_enable_mon_event(enum resctrl_event_id ev= entid) mon_event_all[eventid].enabled =3D true; } =20 +bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid) +{ + return eventid >=3D QOS_FIRST_EVENT && eventid < QOS_NUM_EVENTS && + mon_event_all[eventid].enabled; +} + /** * resctrl_mon_resource_init() - Initialise global monitoring structures. * @@ -914,9 +920,9 @@ int resctrl_mon_resource_init(void) RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } =20 - if (resctrl_arch_is_mbm_local_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) mba_mbps_default_event =3D QOS_L3_MBM_LOCAL_EVENT_ID; - else if (resctrl_arch_is_mbm_total_enabled()) + else if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) mba_mbps_default_event =3D QOS_L3_MBM_TOTAL_EVENT_ID; =20 return 0; diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index b95501d4b5de..a7eeb33501da 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -123,8 +123,8 @@ void rdt_staged_configs_clear(void) =20 static bool resctrl_is_mbm_enabled(void) { - return (resctrl_arch_is_mbm_total_enabled() || - resctrl_arch_is_mbm_local_enabled()); + return (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID) || + resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)); } =20 static bool resctrl_is_mbm_event(int e) @@ -196,7 +196,7 @@ static int closid_alloc(void) lockdep_assert_held(&rdtgroup_mutex); =20 if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) && - resctrl_arch_is_llc_occupancy_enabled()) { + resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) { cleanest_closid =3D resctrl_find_cleanest_closid(); if (cleanest_closid < 0) return cleanest_closid; @@ -4051,7 +4051,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *= r, struct rdt_mon_domain *d =20 if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); - if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) { + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(= d)) { /* * When a package is going down, forcefully * decrement rmid->ebusy. There is no way to know @@ -4087,12 +4087,12 @@ static int domain_setup_mon_state(struct rdt_resour= ce *r, struct rdt_mon_domain u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); size_t tsize; =20 - if (resctrl_arch_is_llc_occupancy_enabled()) { + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) { d->rmid_busy_llc =3D bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } - if (resctrl_arch_is_mbm_total_enabled()) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) { tsize =3D sizeof(*d->mbm_total); d->mbm_total =3D kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_total) { @@ -4100,7 +4100,7 @@ static int domain_setup_mon_state(struct rdt_resource= *r, struct rdt_mon_domain return -ENOMEM; } } - if (resctrl_arch_is_mbm_local_enabled()) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) { tsize =3D sizeof(*d->mbm_local); d->mbm_local =3D kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_local) { @@ -4145,7 +4145,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r,= struct rdt_mon_domain *d) RESCTRL_PICK_ANY_CPU); } =20 - if (resctrl_arch_is_llc_occupancy_enabled()) + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); =20 /* @@ -4220,7 +4220,7 @@ void resctrl_offline_cpu(unsigned int cpu) cancel_delayed_work(&d->mbm_over); mbm_setup_overflow_handler(d, 0, cpu); } - if (resctrl_arch_is_llc_occupancy_enabled() && + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && cpu =3D=3D d->cqm_work_cpu && has_busy_rmid(d)) { cancel_delayed_work(&d->cqm_limbo); cqm_setup_limbo_handler(d, 0, cpu); --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 153A72E0915 for ; Mon, 11 Aug 2025 18:17:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936251; cv=none; b=DviuKtKSa/RI9lQSjgb+8wiKq0YoIzH8w0AWRjNnMbFygSGacz9lURiHwXNrbUjEkeI+2/RBTMZkYxQNyWNypuRURG8M2Qd25fctpEhZ9SHXQd4D5ZOts8Nv/CnPafKlSmTjxxxgOzmJ+xA0R9CZhulsI9F/13tKL//RaR4wdUo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936251; c=relaxed/simple; bh=cuuTo5sNTseROX6Fc5025NznVenN1rKXjVTNonpnXq0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=tbJHHcTBLizUuI/KXfNHm6WWz/PSL6zQVB4sJuaYFAVner/WIZX232rRnco0pp+9i2xXFA8HX2KTGS0UCjItNkon1pTI+bdF1QhbC1S9RMYeLwBSSkSweAXWKUO7prei9qRvlMhO7a0IOvndwGjr4N/5FdOrEPbtWj+zX6Bpyc0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=CkzKyMQD; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="CkzKyMQD" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936251; x=1786472251; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=cuuTo5sNTseROX6Fc5025NznVenN1rKXjVTNonpnXq0=; b=CkzKyMQDGovH0QhHn1CLQzWrLTHNXRFLfRTlED9Sc+60seHWtEC3ayjW KQIGVCujVIsfkUx5xkRZLcdwwRFXGHPeyqTJhgMYsyWAwIdGkJg06HI8s mE7y4bG4p+t5gHC7nqy0B1LQrvN2DgaQOnuQy06xvh9w/h3WJbs4BAX0P gdcfz2hbyoeXtqZVnZ/q3NbA/S/nMI5XRHN2isdUe2PKVKHydw9pd46qF 3J4LEAdttxz1baxNUeFszwK4E6T6Ke7QPAYpASi2WsYtuMAhe291t2eJq Mlj0Hpnso83ri3cZRgt8Letm3pzdCmUbeCGzCGAMm/LE2Zi0XPvdAWBz7 A==; X-CSE-ConnectionGUID: EO2JgOUOQKys45u3T2fJLw== X-CSE-MsgGUID: BiY4K1oySCKjDpXt7T7TYQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277341" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277341" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: s5kNTx0gTFOFvhSLU8COdg== X-CSE-MsgGUID: RSKYOJVcS+OIca5O2wX+Yg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825618" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:22 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 03/32] x86/resctrl: Remove 'rdt_mon_features' global variable Date: Mon, 11 Aug 2025 11:16:37 -0700 Message-ID: <20250811181709.6241-4-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" rdt_mon_features is used as a bitmask of enabled monitor events. A monitor event's status is now maintained in mon_evt::enabled with all monitor events' mon_evt structures found in the filesystem's mon_event_all[] array. Remove the remaining uses of rdt_mon_features. Signed-off-by: Tony Luck Reviewed-by: Reinette Chatre --- arch/x86/include/asm/resctrl.h | 1 - arch/x86/kernel/cpu/resctrl/core.c | 9 +++++---- arch/x86/kernel/cpu/resctrl/monitor.c | 5 ----- 3 files changed, 5 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index b1dd5d6b87db..575f8408a9e7 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -44,7 +44,6 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); =20 extern bool rdt_alloc_capable; extern bool rdt_mon_capable; -extern unsigned int rdt_mon_features; =20 DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 1a319ce9328c..5d14f9a14eda 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -863,21 +863,22 @@ static __init bool get_rdt_alloc_resources(void) static __init bool get_rdt_mon_resources(void) { struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + bool ret =3D false; =20 if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID); - rdt_mon_features |=3D (1 << QOS_L3_OCCUP_EVENT_ID); + ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID); - rdt_mon_features |=3D (1 << QOS_L3_MBM_TOTAL_EVENT_ID); + ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID); - rdt_mon_features |=3D (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + ret =3D true; } =20 - if (!rdt_mon_features) + if (!ret) return false; =20 return !rdt_get_mon_l3_config(r); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index 61d38517e2bf..07f8ab097cbe 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -31,11 +31,6 @@ */ bool rdt_mon_capable; =20 -/* - * Global to indicate which monitoring events are enabled. - */ -unsigned int rdt_mon_features; - #define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5)) =20 static int snc_nodes_per_l3_cache =3D 1; --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 3CFA52E172C for ; Mon, 11 Aug 2025 18:17:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936257; cv=none; b=deWb5Mnx7oj0NCX4/W2fXQoKs3bZAmFME2p4Rtjd6gcylGCDTNLYky0/8iwDklRTC8Fp6VTwaeCw9TRG2YSxwMG13vhLrjnJJHgaohXA6Ia/9Hz8IeMJOJe/YKWWJav9dGkiNus6UGpuJZS0Ph9B6acAhVaEvXU2EZ2Zr0f7EGI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936257; c=relaxed/simple; bh=fUdkXscjPI036bxdzub+7Fth+HryKRFKLxsGhalvKhw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=VkRhJNqO/L2vpKr0rK7mNvMUqfjnY4VJuy9h48IKkNGqeZzGVyiBjp5zRv/KUcrDUNh0KXbA/lc/LJ9UnSnfFD1q+tqppJlh/qn8nGnb5GbMhe0bogGYBA9UvxVHSvv5rtFyph9zt7wJhkT/TaoqZI3fMzNDv9N9kq4HnpO5yno= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=AO1N6Dvz; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="AO1N6Dvz" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936256; x=1786472256; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=fUdkXscjPI036bxdzub+7Fth+HryKRFKLxsGhalvKhw=; b=AO1N6DvzpSDdiFvoYk6RrOJ2cPCvoSWBsTFb2onHupmghMJXL1OPqTju Khzbf6e1WJ9ACVujW2EIGMium6hGUKmKTJruAZBhWhGnA5FcSpgeY8WDw WSv61RQQWCrSSjjXR7ha6aNd6O9WhzBjE0eJcOZFmwAj0gCGVRIE3+AQQ JrdJNEI2b34HyhJUA1Hjo5oz1J3LWa31ACSUVRCBVutttT/SR0IH2JJIp l4l0VR9E0sTu1VVLUXfT8BGb0bfpx4AYwGf+NmenzXYuQYUQICL2gSQMp 4IyebsTvmRxVPubHkXn4OTtsBCvrLgfdRx0CXdyfOiKIE00dM1HZCVc4w g==; X-CSE-ConnectionGUID: mNgO6WwHQzij80nuKvNnxA== X-CSE-MsgGUID: usX4tpDeRTGqtnanLGUCuQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277352" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277352" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: MxYipvr1RT6c0zTbAxYvng== X-CSE-MsgGUID: GhmWh3BsQWS37K0nuQVQeg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825621" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:22 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 04/32] x86,fs/resctrl: Prepare for more monitor events Date: Mon, 11 Aug 2025 11:16:38 -0700 Message-ID: <20250811181709.6241-5-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" There's a rule in computer programming that objects appear zero, once, or many times. So code accordingly. There are two MBM events and resctrl is coded with a lot of if (local) do one thing if (total) do a different thing Change the rdt_mon_domain and rdt_hw_mon_domain structures to hold arrays of pointers to per event data instead of explicit fields for total and local bandwidth. Simplify by coding for many events using loops on which are enabled. Move resctrl_is_mbm_event() to so it can be used more widely. Also provide a for_each_mbm_event_id() helper macro. Cleanup variable names in functions touched to consistently use "eventid" for those with type enum resctrl_event_id. Signed-off-by: Tony Luck Reviewed-by: Reinette Chatre --- include/linux/resctrl.h | 23 +++++++++--- include/linux/resctrl_types.h | 3 ++ arch/x86/kernel/cpu/resctrl/internal.h | 8 ++--- arch/x86/kernel/cpu/resctrl/core.c | 40 +++++++++++---------- arch/x86/kernel/cpu/resctrl/monitor.c | 36 +++++++++---------- fs/resctrl/monitor.c | 13 ++++--- fs/resctrl/rdtgroup.c | 50 +++++++++++++------------- 7 files changed, 96 insertions(+), 77 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 40aba6b5d4f0..478d7a935ca3 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -161,8 +161,9 @@ struct rdt_ctrl_domain { * @hdr: common header for different domain types * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold - * @mbm_total: saved state for MBM total bandwidth - * @mbm_local: saved state for MBM local bandwidth + * @mbm_states: Per-event pointer to the MBM event's saved state. + * An MBM event's state is an array of struct mbm_state + * indexed by RMID on x86 or combined CLOSID, RMID on Arm. * @mbm_over: worker to periodically read MBM h/w counters * @cqm_limbo: worker to periodically read CQM h/w counters * @mbm_work_cpu: worker CPU for MBM h/w counters @@ -172,8 +173,7 @@ struct rdt_mon_domain { struct rdt_domain_hdr hdr; unsigned int ci_id; unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; + struct mbm_state *mbm_states[QOS_NUM_L3_MBM_EVENTS]; struct delayed_work mbm_over; struct delayed_work cqm_limbo; int mbm_work_cpu; @@ -376,6 +376,21 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_i= d eventid); =20 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); =20 +static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid) +{ + return (eventid >=3D QOS_L3_MBM_TOTAL_EVENT_ID && + eventid <=3D QOS_L3_MBM_LOCAL_EVENT_ID); +} + +/* Iterate over all memory bandwidth events */ +#define for_each_mbm_event_id(eventid) \ + for (eventid =3D QOS_L3_MBM_TOTAL_EVENT_ID; \ + eventid <=3D QOS_L3_MBM_LOCAL_EVENT_ID; eventid++) + +/* Iterate over memory bandwidth arrays in domain structures */ +#define for_each_mbm_idx(idx) \ + for (idx =3D 0; idx < QOS_NUM_L3_MBM_EVENTS; idx++) + /** * resctrl_arch_mon_event_config_write() - Write the config for an event. * @config_info: struct resctrl_mon_config_info describing the resource, d= omain diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h index 2dadbc54e4b3..d98351663c2c 100644 --- a/include/linux/resctrl_types.h +++ b/include/linux/resctrl_types.h @@ -51,4 +51,7 @@ enum resctrl_event_id { QOS_NUM_EVENTS, }; =20 +#define QOS_NUM_L3_MBM_EVENTS (QOS_L3_MBM_LOCAL_EVENT_ID - QOS_L3_MBM_TOTA= L_EVENT_ID + 1) +#define MBM_STATE_IDX(evt) ((evt) - QOS_L3_MBM_TOTAL_EVENT_ID) + #endif /* __LINUX_RESCTRL_TYPES_H */ diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index 5e3c41b36437..58dca892a5df 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -54,15 +54,15 @@ struct rdt_hw_ctrl_domain { * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs tha= t share * a resource for a monitor function * @d_resctrl: Properties exposed to the resctrl file system - * @arch_mbm_total: arch private state for MBM total bandwidth - * @arch_mbm_local: arch private state for MBM local bandwidth + * @arch_mbm_states: Per-event pointer to the MBM event's saved state. + * An MBM event's state is an array of struct arch_mbm_state + * indexed by RMID on x86. * * Members of this structure are accessed via helpers that provide abstrac= tion. */ struct rdt_hw_mon_domain { struct rdt_mon_domain d_resctrl; - struct arch_mbm_state *arch_mbm_total; - struct arch_mbm_state *arch_mbm_local; + struct arch_mbm_state *arch_mbm_states[QOS_NUM_L3_MBM_EVENTS]; }; =20 static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct r= dt_ctrl_domain *r) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 5d14f9a14eda..fbf019c1ff11 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -365,8 +365,10 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain= *hw_dom) =20 static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom) { - kfree(hw_dom->arch_mbm_total); - kfree(hw_dom->arch_mbm_local); + int idx; + + for_each_mbm_idx(idx) + kfree(hw_dom->arch_mbm_states[idx]); kfree(hw_dom); } =20 @@ -400,25 +402,27 @@ static int domain_setup_ctrlval(struct rdt_resource *= r, struct rdt_ctrl_domain * */ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *h= w_dom) { - size_t tsize; - - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) { - tsize =3D sizeof(*hw_dom->arch_mbm_total); - hw_dom->arch_mbm_total =3D kcalloc(num_rmid, tsize, GFP_KERNEL); - if (!hw_dom->arch_mbm_total) - return -ENOMEM; - } - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) { - tsize =3D sizeof(*hw_dom->arch_mbm_local); - hw_dom->arch_mbm_local =3D kcalloc(num_rmid, tsize, GFP_KERNEL); - if (!hw_dom->arch_mbm_local) { - kfree(hw_dom->arch_mbm_total); - hw_dom->arch_mbm_total =3D NULL; - return -ENOMEM; - } + size_t tsize =3D sizeof(*hw_dom->arch_mbm_states[0]); + enum resctrl_event_id eventid; + int idx; + + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx =3D MBM_STATE_IDX(eventid); + hw_dom->arch_mbm_states[idx] =3D kcalloc(num_rmid, tsize, GFP_KERNEL); + if (!hw_dom->arch_mbm_states[idx]) + goto cleanup; } =20 return 0; +cleanup: + for_each_mbm_idx(idx) { + kfree(hw_dom->arch_mbm_states[idx]); + hw_dom->arch_mbm_states[idx] =3D NULL; + } + + return -ENOMEM; } =20 static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index 07f8ab097cbe..f01db2034d08 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -161,18 +161,14 @@ static struct arch_mbm_state *get_arch_mbm_state(stru= ct rdt_hw_mon_domain *hw_do u32 rmid, enum resctrl_event_id eventid) { - switch (eventid) { - case QOS_L3_OCCUP_EVENT_ID: - return NULL; - case QOS_L3_MBM_TOTAL_EVENT_ID: - return &hw_dom->arch_mbm_total[rmid]; - case QOS_L3_MBM_LOCAL_EVENT_ID: - return &hw_dom->arch_mbm_local[rmid]; - default: - /* Never expect to get here */ - WARN_ON_ONCE(1); + struct arch_mbm_state *state; + + if (!resctrl_is_mbm_event(eventid)) return NULL; - } + + state =3D hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)]; + + return state ? &state[rmid] : NULL; } =20 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain= *d, @@ -201,14 +197,16 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, = struct rdt_mon_domain *d, void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_do= main *d) { struct rdt_hw_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); - - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) - memset(hw_dom->arch_mbm_total, 0, - sizeof(*hw_dom->arch_mbm_total) * r->num_rmid); - - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) - memset(hw_dom->arch_mbm_local, 0, - sizeof(*hw_dom->arch_mbm_local) * r->num_rmid); + enum resctrl_event_id eventid; + int idx; + + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx =3D MBM_STATE_IDX(eventid); + memset(hw_dom->arch_mbm_states[idx], 0, + sizeof(*hw_dom->arch_mbm_states[0]) * r->num_rmid); + } } =20 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int widt= h) diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 9e988b2c1a22..dcc6c00eb362 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -346,15 +346,14 @@ static struct mbm_state *get_mbm_state(struct rdt_mon= _domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { u32 idx =3D resctrl_arch_rmid_idx_encode(closid, rmid); + struct mbm_state *state; =20 - switch (evtid) { - case QOS_L3_MBM_TOTAL_EVENT_ID: - return &d->mbm_total[idx]; - case QOS_L3_MBM_LOCAL_EVENT_ID: - return &d->mbm_local[idx]; - default: + if (!resctrl_is_mbm_event(evtid)) return NULL; - } + + state =3D d->mbm_states[MBM_STATE_IDX(evtid)]; + + return state ? &state[idx] : NULL; } =20 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index a7eeb33501da..77336d5e4915 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -127,12 +127,6 @@ static bool resctrl_is_mbm_enabled(void) resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)); } =20 -static bool resctrl_is_mbm_event(int e) -{ - return (e >=3D QOS_L3_MBM_TOTAL_EVENT_ID && - e <=3D QOS_L3_MBM_LOCAL_EVENT_ID); -} - /* * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap * of free CLOSIDs. @@ -4023,9 +4017,13 @@ static void rdtgroup_setup_default(void) =20 static void domain_destroy_mon_state(struct rdt_mon_domain *d) { + int idx; + bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); + for_each_mbm_idx(idx) { + kfree(d->mbm_states[idx]); + d->mbm_states[idx] =3D NULL; + } } =20 void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_d= omain *d) @@ -4085,32 +4083,34 @@ void resctrl_offline_mon_domain(struct rdt_resource= *r, struct rdt_mon_domain *d static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_d= omain *d) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); - size_t tsize; + size_t tsize =3D sizeof(*d->mbm_states[0]); + enum resctrl_event_id eventid; + int idx; =20 if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) { d->rmid_busy_llc =3D bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) { - tsize =3D sizeof(*d->mbm_total); - d->mbm_total =3D kcalloc(idx_limit, tsize, GFP_KERNEL); - if (!d->mbm_total) { - bitmap_free(d->rmid_busy_llc); - return -ENOMEM; - } - } - if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) { - tsize =3D sizeof(*d->mbm_local); - d->mbm_local =3D kcalloc(idx_limit, tsize, GFP_KERNEL); - if (!d->mbm_local) { - bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); - return -ENOMEM; - } + + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx =3D MBM_STATE_IDX(eventid); + d->mbm_states[idx] =3D kcalloc(idx_limit, tsize, GFP_KERNEL); + if (!d->mbm_states[idx]) + goto cleanup; } =20 return 0; +cleanup: + bitmap_free(d->rmid_busy_llc); + for_each_mbm_idx(idx) { + kfree(d->mbm_states[idx]); + d->mbm_states[idx] =3D NULL; + } + + return -ENOMEM; } =20 int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_dom= ain *d) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 14A802E11C3 for ; Mon, 11 Aug 2025 18:17:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936255; cv=none; b=ImyoffXmps+W6oAANgy32Oxr1F/fMe5jAsPztlqMjEv0BwyuAG4bI6D31r+D+nc4fUVJRKj7CXIk4bGvbotVZezptGiCfvmE0t+l4/3u3JPaoqLFI6xdhgpS+F3VqXLPztVJoyBFe8Ohel+pldmOsFI67RpeWtYB5ZbkLEgOHPI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936255; c=relaxed/simple; bh=7QBrtRskse4L3xMOD1F3XTtyuESFrW+HXy/mdDGVhc8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=a/Ha92mRA6faoHx6oCkMsMkok5I4Csm2u26yXcemvhKsgsIB+ul6yZ7nCVyQaBIvY8ZqV6oOCjxqPVHyzWVdVHkYTmqy/EMXAECpVfoDmySmTFMW0I1YDkDZXdtfVkaLDqN70bQxdv1I+hxI0+2bC5XumwTdnClKWPGePBQ/VPE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=iKsEEmAZ; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="iKsEEmAZ" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936254; x=1786472254; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=7QBrtRskse4L3xMOD1F3XTtyuESFrW+HXy/mdDGVhc8=; b=iKsEEmAZGD0QWd4H2Rh2lUHkfKHlFW7zx98EgKAP+7stxUAr9u2p1T8X zAVKz/Xg0N4Lqo7xbxGU+XUNQjCxuS2EI3Q8F553x6AB9GLScQ5iQlQ0H Kjaf6lDgdK0djU4/foAaAZAfHhlANO/a7lgMuxdVkvBiICJpJvb0Mg6+e r962m1n4Oih3Qp88U/RHQyqiqdJ6CPB9EkL8me9x//KDKgFd6hSHRxDYE kFc9gZYeR0pAO0wmzOEakcq0Mx3umYOzrC+4yZ18mGGfTJ2QFBz99DdR3 KActjQRrOng3dS3FfvlmnHlh9Rw6cUHjOEgukHu2ij1gCI8QDybdD6mxK g==; X-CSE-ConnectionGUID: LZfWHDQhQ9yWrkjfdM/HKA== X-CSE-MsgGUID: KLUF2VkyRAeGj9IYeggNRA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277362" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277362" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: ya4PTvRHRIuCMFq4sjjCzw== X-CSE-MsgGUID: qQH+J6ZaRw2VaKdg0mjWCw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825624" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:22 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 05/32] x86,fs/resctrl: Improve domain type checking Date: Mon, 11 Aug 2025 11:16:39 -0700 Message-ID: <20250811181709.6241-6-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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 rdt_domain_hdr structure is used in both control and monitor domain structures to provide common methods for operations such as adding a CPU to a domain, removing a CPU from a domain, accessing the mask of all CPUs in a domain. The "type" field provides a simple check whether a domain is a control or monitor domain so that programming errors operating on domains will be quickly caught. This is insufficient to catch errors when other resources besides L3 support monitor events. Add a new rdt_domain_hdr::rid field that is initialized when domain structures are allocated. Call domain_header_is_valid() to sanity check both the type and resource id before using container_of() to get a pointer to the associated domain. Signed-off-by: Tony Luck --- include/linux/resctrl.h | 9 +++++++++ arch/x86/kernel/cpu/resctrl/core.c | 10 ++++++---- fs/resctrl/ctrlmondata.c | 2 +- 3 files changed, 16 insertions(+), 5 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 478d7a935ca3..091135eca2b8 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -131,15 +131,24 @@ enum resctrl_domain_type { * @list: all instances of this resource * @id: unique id for this instance * @type: type of this instance + * @rid: resource id for this instance * @cpu_mask: which CPUs share this resource */ struct rdt_domain_hdr { struct list_head list; int id; enum resctrl_domain_type type; + enum resctrl_res_level rid; struct cpumask cpu_mask; }; =20 +static inline bool domain_header_is_valid(struct rdt_domain_hdr *hdr, + enum resctrl_domain_type type, + enum resctrl_res_level rid) +{ + return !WARN_ON_ONCE(hdr->type !=3D type || hdr->rid !=3D rid); +} + /** * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resour= ce * @hdr: common header for different domain types diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index fbf019c1ff11..420e4eb7c160 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -459,7 +459,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_res= ource *r) =20 hdr =3D resctrl_find_domain(&r->ctrl_domains, id, &add_pos); if (hdr) { - if (WARN_ON_ONCE(hdr->type !=3D RESCTRL_CTRL_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; d =3D container_of(hdr, struct rdt_ctrl_domain, hdr); =20 @@ -476,6 +476,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_res= ource *r) d =3D &hw_dom->d_resctrl; d->hdr.id =3D id; d->hdr.type =3D RESCTRL_CTRL_DOMAIN; + d->hdr.rid =3D r->rid; cpumask_set_cpu(cpu, &d->hdr.cpu_mask); =20 rdt_domain_reconfigure_cdp(r); @@ -515,7 +516,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_reso= urce *r) =20 hdr =3D resctrl_find_domain(&r->mon_domains, id, &add_pos); if (hdr) { - if (WARN_ON_ONCE(hdr->type !=3D RESCTRL_MON_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid)) return; d =3D container_of(hdr, struct rdt_mon_domain, hdr); =20 @@ -530,6 +531,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_reso= urce *r) d =3D &hw_dom->d_resctrl; d->hdr.id =3D id; d->hdr.type =3D RESCTRL_MON_DOMAIN; + d->hdr.rid =3D r->rid; ci =3D get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) { pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->nam= e); @@ -586,7 +588,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_= resource *r) return; } =20 - if (WARN_ON_ONCE(hdr->type !=3D RESCTRL_CTRL_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; =20 d =3D container_of(hdr, struct rdt_ctrl_domain, hdr); @@ -632,7 +634,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_r= esource *r) return; } =20 - if (WARN_ON_ONCE(hdr->type !=3D RESCTRL_MON_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid)) return; =20 d =3D container_of(hdr, struct rdt_mon_domain, hdr); diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index ad7ffc6acf13..a7d60e74a29d 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -643,7 +643,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) * the resource to find the domain with "domid". */ hdr =3D resctrl_find_domain(&r->mon_domains, domid, NULL); - if (!hdr || WARN_ON_ONCE(hdr->type !=3D RESCTRL_MON_DOMAIN)) { + if (!hdr || !domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, resid)) { ret =3D -ENOENT; goto out; } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 3E16F2E1754 for ; Mon, 11 Aug 2025 18:17:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936258; cv=none; b=PR3qpCS6f5LyDiQoBcQSSI6oKIEzEy5KcVlP3NQaroSK2FFjuBDqBgM5rsPhJoqiOOg7ZPFOjITaYW5guiGW7S7BiFdoGffRoY0fa11AXnwuQk5UH3zpk6EYYhxSoMqsF7XECe+yZaK9zDML7TbxA7FRq+V2qMMHzChDehyFgFI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936258; c=relaxed/simple; bh=LtCIWxRjo81w25b5/equjWzNBh8gkG5EfSSMHGMzUKM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=XmMJqJ1SSNzEtLGdCBUIL0dQGYyoAAKpIjBGICFQDk4ca5+aaw6yXP958Fn1GAs+Ksnr8J71gXPK2js05cMeltoLJEFgMZ7ZsVDZS9xo7OHVTj3A8WVhF6u4XlrETI9FeM5Ojx5773sJg7kvFEaD6hkzhWZKZ/mJ7VnLhrwFHEs= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=QTOBmBL6; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="QTOBmBL6" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936257; x=1786472257; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=LtCIWxRjo81w25b5/equjWzNBh8gkG5EfSSMHGMzUKM=; b=QTOBmBL6qRQcIYLL3OLgt5Z4UXKu7Rnxw4Jft2CTfCs9ITzD+BEaHa4q sBr59HSm7ZDoNHVHDoHotN6bxtaLRCAdJpOrYwk9aeQcXBctK2Me+mWTH ZNDWfuIvsYH0e2s6462YMjY+LEZThguAIN4jt3iChRqYQqGEvTkgejsly JdRZzAhsFLrpI2tHhRV5qfS23tFhin2UJSh1/1wh+yYm9DAxB7Udac0S/ 5eZbUNISOw03SC47QPzgNNCcoGQQKGeutlc/VOdeNrvUH+3FNZVuQUcJB eTtQR3obBWY7G/TZscG3mcno8ui1orag6owZ47OE6dVWJBIQZ/dPmDIrU A==; X-CSE-ConnectionGUID: vPe18kSJT7a1tUHQ/SENRg== X-CSE-MsgGUID: 8GXkfnQ+Q+GRaItKxTAkqw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277364" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277364" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: 4bXFEu6iROmp1QBhPDy8Gg== X-CSE-MsgGUID: SSa0qaHTSeWvG2kb1DlBDw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825627" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 06/32] x86/resctrl: Move L3 initialization into new helper function Date: Mon, 11 Aug 2025 11:16:40 -0700 Message-ID: <20250811181709.6241-7-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All resctrl monitor events are associated with the L3 resource, but this is about to change. To prepare for additional types of monitoring domains, move open coded L3 resource monitoring domain initialization from domain_add_cpu_mon() into a new helper l3_mon_domain_setup() called by domain_add_cpu_mon(). Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/core.c | 56 ++++++++++++++++++------------ 1 file changed, 34 insertions(+), 22 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 420e4eb7c160..66270c230b4e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -496,34 +496,13 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_r= esource *r) } } =20 -static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) +static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, s= truct list_head *add_pos) { - int id =3D get_domain_id_from_scope(cpu, r->mon_scope); - struct list_head *add_pos =3D NULL; struct rdt_hw_mon_domain *hw_dom; - struct rdt_domain_hdr *hdr; struct rdt_mon_domain *d; struct cacheinfo *ci; int err; =20 - lockdep_assert_held(&domain_list_lock); - - if (id < 0) { - pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resou= rce %s\n", - cpu, r->mon_scope, r->name); - return; - } - - hdr =3D resctrl_find_domain(&r->mon_domains, id, &add_pos); - if (hdr) { - if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid)) - return; - d =3D container_of(hdr, struct rdt_mon_domain, hdr); - - cpumask_set_cpu(cpu, &d->hdr.cpu_mask); - return; - } - hw_dom =3D kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); if (!hw_dom) return; @@ -558,6 +537,39 @@ static void domain_add_cpu_mon(int cpu, struct rdt_res= ource *r) } } =20 +static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) +{ + int id =3D get_domain_id_from_scope(cpu, r->mon_scope); + struct list_head *add_pos =3D NULL; + struct rdt_domain_hdr *hdr; + + lockdep_assert_held(&domain_list_lock); + + if (id < 0) { + pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resou= rce %s\n", + cpu, r->mon_scope, r->name); + return; + } + + hdr =3D resctrl_find_domain(&r->mon_domains, id, &add_pos); + if (hdr) { + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid)) + return; + cpumask_set_cpu(cpu, &hdr->cpu_mask); + + return; + } + + switch (r->rid) { + case RDT_RESOURCE_L3: + l3_mon_domain_setup(cpu, id, r, add_pos); + break; + default: + WARN_ON_ONCE(1); + break; + } +} + static void domain_add_cpu(int cpu, struct rdt_resource *r) { if (r->alloc_capable) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 B9EB82E1741 for ; Mon, 11 Aug 2025 18:17:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936257; cv=none; b=ATRmkT/ItDNQYLdhDHhkP9u0/6PNdWp34Cb9yjvVZ35Oa/Bj2iGCec/1HCuG9tAMn6GBdjgjJW9PcjGGToifWeEDqv1xfc1RdndrNvqKAjXO2UWaazAdRY5CqCUNlkJ+2EYmitnWNIm6+BIiimnVIyBs+79suep6KJz3YNe+E00= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936257; c=relaxed/simple; bh=a3IoQ4GLCGMOmHG8RwRmViQVRz47yCvJdkrtlgqqV3Y=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=rU5bcIzIe+wnRGlkdWn37T/N+HSTKTmfLf0d3qWqlz+NTuNU0pv8WsguV9T64fOx3ajSB3KzVmYECVUAhI/JuGcw1aHcfSLX3YaFZyNv7ofA68FRI5EtT0dYrw6CSy5CdVQg6KuII3xwzqS6w4TT7uS8FKfm3GWCylpjjQGNRPg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=I1qtIsTn; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="I1qtIsTn" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936256; x=1786472256; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=a3IoQ4GLCGMOmHG8RwRmViQVRz47yCvJdkrtlgqqV3Y=; b=I1qtIsTnmRQ9MehXRm52ShNqsRQ93DUGaJBVDpIqNO4RL6elJd1LwIW0 ezkemXYTyvXSmNbA7ZxPOTFpLf9P+JNsJ7toyQVssVofYCrljekMwv8CA 6d3hKTe1g0z2ZcbZOij+9T5j9Hd3n7zwKgrKWAi6cJwdMqYptV/K8qNO/ GTnyDoBXfJM6Dbn8ZkHUjsZ0IbW2zMMKdyGW/Q0lpns/PPY+y1yywQWEb o7o2/2U/jS4ka/CkndAYrPxOT91j6GWsbyDDu0yRfTBegd5ijkLYnA+vG P1wSIp/FUfollTsGx5Got5qc3/IbWF2f/gNk0NCTkh0xe84qJxy7uKlM5 Q==; X-CSE-ConnectionGUID: KmB6Ojk8T1uHD+ljlt+80g== X-CSE-MsgGUID: vYG4xxCtRhmgSUXQHbQudg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277371" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277371" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 X-CSE-ConnectionGUID: cKmOIHcTRaiza2KEJwTpxA== X-CSE-MsgGUID: 2UofFD33R6OOrswfaDe9DQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825631" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 07/32] x86,fs/resctrl: Refactor domain_remove_cpu_mon() ready for new domain types Date: Mon, 11 Aug 2025 11:16:41 -0700 Message-ID: <20250811181709.6241-8-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All monitoring events are associated with the L3 resource. The RDT_RESOURCE_L3 resource carries a lot of state in the domain structures which needs to be dealt with when a domain is taken offline by removing the last CPU in the domain. New telemetry events will be associated with a new package scoped resource with new domain structures. Refactor domain_remove_cpu_mon() so all the L3 processing is separated from general actions of clearing the CPU bit in the mask and removing sub-directories from the mon_data directory. resctrl_offline_mon_domain() continues to remove domain specific directories and files from the "mon_data" directories, but can skip the L3 resource specific cleanup when called for other resource types. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/core.c | 17 +++++++++++------ fs/resctrl/rdtgroup.c | 5 ++++- 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 66270c230b4e..448c2bf9837d 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -649,17 +649,22 @@ static void domain_remove_cpu_mon(int cpu, struct rdt= _resource *r) if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid)) return; =20 - d =3D container_of(hdr, struct rdt_mon_domain, hdr); - hw_dom =3D resctrl_to_arch_mon_dom(d); + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) + return; =20 - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { + switch (r->rid) { + case RDT_RESOURCE_L3: + d =3D container_of(hdr, struct rdt_mon_domain, hdr); + hw_dom =3D resctrl_to_arch_mon_dom(d); resctrl_offline_mon_domain(r, d); list_del_rcu(&d->hdr.list); synchronize_rcu(); mon_domain_free(hw_dom); - - return; + break; + default: + pr_warn_once("Unknown resource rid=3D%d\n", r->rid); + break; } } =20 diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 77336d5e4915..05438e15e2ca 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -4047,6 +4047,9 @@ void resctrl_offline_mon_domain(struct rdt_resource *= r, struct rdt_mon_domain *d if (resctrl_mounted && resctrl_arch_mon_capable()) rmdir_mondata_subdir_allrdtgrp(r, d); =20 + if (r->rid !=3D RDT_RESOURCE_L3) + goto out_unlock; + if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(= d)) { @@ -4063,7 +4066,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *= r, struct rdt_mon_domain *d } =20 domain_destroy_mon_state(d); - +out_unlock: mutex_unlock(&rdtgroup_mutex); } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 7ED802E2DCA for ; Mon, 11 Aug 2025 18:17:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936262; cv=none; b=illfOVTLSJ+m6QCz8niNxwl7FwbZ1Ih5wlAR1+U++ipQYB4pjGHscp/dudIdjJiW3ONGyNZUJo76ta+JNqtVNlQ0tkOCHu72hR7gNa3+36gvGi3jINVZEjOiwrOICu/RJGnfHTt9L2uTv3dMaD7laIeoOnwZzdjeBHjBM9iWWC8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936262; c=relaxed/simple; bh=gnLa9WvyRdjIUFjfbMI1N4aTtFJiDEPN/R7F6YbjB9M=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=ApxR5FCvuPNC8c4Md3TempaSHTKZfulXK3s6F1De44tilf9+CCyf4NYYLtE642r6x/DmLDL9fc+U33cLBjLxVoeBqeYkOzxCO3tzLK7o8wkq38VTseToFZnhgqj3E0WRNAvsKlBdgYoMjbNmhFR3h1C8+ugrN/43RO9IRzlehtg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=YZkXJeB7; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="YZkXJeB7" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936261; x=1786472261; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=gnLa9WvyRdjIUFjfbMI1N4aTtFJiDEPN/R7F6YbjB9M=; b=YZkXJeB7BROifefMXoLoZf7/wPDt+DHkoDn4KvZVuG/PGmv2RKCJk/Zb 354HUoWxYNWbsTetahiiA0RYHDFc11cC430lvltdud8LY/FM7PL22iAKo g1UWCGm+LvSwE1vvqeX+Gdjs3zmgiX1VTR3gt9RpLRyyCsN4zdcZXkWZD p1WZDhUbQLXHHqnkG5ywrxN4mZw1ly/dP5j6MJ3Fd8hIR3D6astQ5Lg8v 9PbswOnTmEzVsBF3uSc3bwkiPNTJg2UFeW6XIZVnTy8Az6jwxh2lp47Bb k80C4WMLm+hxh1DyM1LsOw6DCfS2cS9hVWia3n8BgzIhQgp97xNRIHkxy Q==; X-CSE-ConnectionGUID: t26UEsBuS0amyoCy40dTWw== X-CSE-MsgGUID: 6nQmyErmQ3GK/stIxctkOg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277382" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277382" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: /FtfbUo3QRChOZIC8+aMDg== X-CSE-MsgGUID: lP23JNMuSN6SmvVVc9cE9w== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825635" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 08/32] x86/resctrl: Clean up domain_remove_cpu_ctrl() Date: Mon, 11 Aug 2025 11:16:42 -0700 Message-ID: <20250811181709.6241-9-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" For symmetry with domain_remove_cpu_mon() refactor to take an early return when removing a CPU does not empty the domain. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/core.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 448c2bf9837d..911100994fcd 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -603,25 +603,24 @@ static void domain_remove_cpu_ctrl(int cpu, struct rd= t_resource *r) if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; =20 + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) + return; + d =3D container_of(hdr, struct rdt_ctrl_domain, hdr); hw_dom =3D resctrl_to_arch_ctrl_dom(d); =20 - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { - resctrl_offline_ctrl_domain(r, d); - list_del_rcu(&d->hdr.list); - synchronize_rcu(); - - /* - * rdt_ctrl_domain "d" is going to be freed below, so clear - * its pointer from pseudo_lock_region struct. - */ - if (d->plr) - d->plr->d =3D NULL; - ctrl_domain_free(hw_dom); + resctrl_offline_ctrl_domain(r, d); + list_del_rcu(&d->hdr.list); + synchronize_rcu(); =20 - return; - } + /* + * rdt_ctrl_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d =3D NULL; + ctrl_domain_free(hw_dom); } =20 static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 816122E2653 for ; Mon, 11 Aug 2025 18:17:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936261; cv=none; b=EDVuFX5S0llXLw3VD6UUJ7VixmBdn9JyzlaXBPnK+x8Nd9XMA5WNmXOC+dL9C3j8LjZttHMXPpa4G3m4p7MxhJ6pr+LRwl9ssMdiFXl731qR7r7cxEEniD62qhdeG3NMhAip441FUAwHGLjTaAOLNk00eTW2eW0fvIhf5YKb4h4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936261; c=relaxed/simple; bh=OF2LD6D2PvDePU/n6jEogfJbfYtkjT4cf17TO8nUMQg=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=CP0dybQdNiGGiBMWhE7Rm/U73L0bwi+4ivrKHnYPb+pVHNlk+q272G20sY/aY8b2KVdvbjv9tToGgLtjTHTdFKWT9qQ1RfFam7T3722irVGgS6zwIwWh3t0kM2z4f1hG49f/r1v9303AiNf0BMVyabA006cHDDSXl7GEJ7dgeAc= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=g2TbkKou; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="g2TbkKou" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936258; x=1786472258; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=OF2LD6D2PvDePU/n6jEogfJbfYtkjT4cf17TO8nUMQg=; b=g2TbkKouCbFrCdNAKviPIQDXvkCwsxcgpBY2ejBLWi9eg3fpjvoC8TBB nin5j4iryr/RBKJkrdlElDYAF5kKTdR+Yl2LeTgce2J1AcGDaXLX4OwcX FWIzCCSkrUKJvqUOjJuxmk1pBlK3HQHZsyMJwXNrb9VPMf/MFUEM6fWcI VKEMtLVml0Jl6iLWD8VumRk7RE0YS+Jj6VxijVcWCaiLiDbsgJ/61XGrV YVBfWtAmiKc3fZYq0mPRhuX3tj+ng+yOoK/T1vtN7g7XuoCtkeqiTDu3m 0MKCtnq5I470UimcPfCcHCPRlvN1A8xfzFoFMl95UHdxxgj61aP9dR/5g w==; X-CSE-ConnectionGUID: xnpdXbV3SMCB1mgQ6RVhFQ== X-CSE-MsgGUID: MT9Wg9NISzCETMsZs2nlrw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277391" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277391" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: C/GQEeBOR/SxrOP0GG5IQg== X-CSE-MsgGUID: vRdW/2kqQWC26oHUgcclUA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825638" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 09/32] x86,fs/resctrl: Use struct rdt_domain_hdr instead of struct rdt_mon_domain Date: Mon, 11 Aug 2025 11:16:43 -0700 Message-ID: <20250811181709.6241-10-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All monitoring events are associated with the L3 resource and it made sense to use the L3 specific "struct rdt_mon_domain *" arguments to functions manipulating domains. But the addition of monitor events tied to other resources changes this assumption. Change the calling sequence to use the generic struct rdt_domain_hdr for domain addition and deletion to preserve as much common code as possible. This will simplify enabling of enumeration of domains for events in other resources. Make the same change to allow reading events in other resources. In this case the code flow passes from mon_event_read() via smp_call*() eventually to __mon_event_count() so the rmid_read::d field is replaced with the new rmid_read::hdr field. The mon_data structure is unchanged, but documentation is updated to note that mon_data::sum is only used for RDT_RESOURCE_L3. Signed-off-by: Tony Luck --- include/linux/resctrl.h | 8 +- fs/resctrl/internal.h | 14 ++-- arch/x86/kernel/cpu/resctrl/core.c | 6 +- arch/x86/kernel/cpu/resctrl/monitor.c | 18 ++++- fs/resctrl/ctrlmondata.c | 14 ++-- fs/resctrl/monitor.c | 30 +++++--- fs/resctrl/rdtgroup.c | 103 ++++++++++++++++++-------- 7 files changed, 129 insertions(+), 64 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 091135eca2b8..c8200626b91a 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -452,9 +452,9 @@ int resctrl_arch_update_one(struct rdt_resource *r, str= uct rdt_ctrl_domain *d, u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain= *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_dom= ain *d); -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domai= n *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hd= r *hdr); void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_d= omain *d); -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_dom= ain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_= hdr *hdr); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); =20 @@ -462,7 +462,7 @@ void resctrl_offline_cpu(unsigned int cpu); * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rm= id * for this resource and domain. * @r: resource that the counter should be read from. - * @d: domain that the counter should be read from. + * @hdr: Header of domain that the counter should be read from. * @closid: closid that matches the rmid. Depending on the architecture, = the * counter may match traffic of both @closid and @rmid, or @rmid * only. @@ -483,7 +483,7 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *= d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *= hdr, u32 closid, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *arch_mon_ctx); =20 diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 4f315b7e9ec0..b19e974b7865 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -77,8 +77,8 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; * @list: Member of the global @mon_data_kn_priv_list list. * @rid: Resource id associated with the event file. * @evtid: Event id associated with the event file. - * @sum: Set when event must be summed across multiple - * domains. + * @sum: Set for RDT_RESOURCE_L3 when event must be summed + * across multiple domains. * @domid: When @sum is zero this is the domain to which * the event file belongs. When @sum is one this * is the id of the L3 cache that all domains to be @@ -101,22 +101,22 @@ struct mon_data { * resource group then its event count is summed with the count from all * its child resource groups. * @r: Resource describing the properties of the event being read. - * @d: Domain that the counter should be read from. If NULL then sum all + * @hdr: Header of domain that the counter should be read from. If NULL = then sum all * domains in @r sharing L3 @ci.id * @evtid: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summin= g domains. + * @ci_id: Cacheinfo id for L3. Only set when @hdr is NULL. Used when summ= ing domains. * @err: Error encountered when reading counter. * @val: Returned value of event counter. If @rgrp is a parent resource = group, * @val includes the sum of event counts from its child resource groups. - * If @d is NULL, @val includes the sum of all domains in @r sharing @c= i.id, + * If @hdr is NULL, @val includes the sum of all domains in @r sharing = @ci.id, * (summed across child resource groups if @rgrp is a parent resource g= roup). * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM o= nly). */ struct rmid_read { struct rdtgroup *rgrp; struct rdt_resource *r; - struct rdt_mon_domain *d; + struct rdt_domain_hdr *hdr; enum resctrl_event_id evtid; bool first; unsigned int ci_id; @@ -352,7 +352,7 @@ void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); =20 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first); =20 int resctrl_mon_resource_init(void); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 911100994fcd..7fd6cd7348fb 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -529,7 +529,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct= rdt_resource *r, struct =20 list_add_tail_rcu(&d->hdr.list, add_pos); =20 - err =3D resctrl_online_mon_domain(r, d); + err =3D resctrl_online_mon_domain(r, &d->hdr); if (err) { list_del_rcu(&d->hdr.list); synchronize_rcu(); @@ -611,7 +611,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_= resource *r) hw_dom =3D resctrl_to_arch_ctrl_dom(d); =20 resctrl_offline_ctrl_domain(r, d); - list_del_rcu(&d->hdr.list); + list_del_rcu(&hdr->list); synchronize_rcu(); =20 /* @@ -656,7 +656,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_r= esource *r) case RDT_RESOURCE_L3: d =3D container_of(hdr, struct rdt_mon_domain, hdr); hw_dom =3D resctrl_to_arch_mon_dom(d); - resctrl_offline_mon_domain(r, d); + resctrl_offline_mon_domain(r, hdr); list_del_rcu(&d->hdr.list); synchronize_rcu(); mon_domain_free(hw_dom); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index f01db2034d08..b31794c5dcd4 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -217,20 +217,30 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_m= sr, unsigned int width) return chunks >> shift; } =20 -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *= d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *= hdr, u32 unused, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *ignored) { - struct rdt_hw_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); - struct rdt_hw_resource *hw_res =3D resctrl_to_arch_res(r); - int cpu =3D cpumask_any(&d->hdr.cpu_mask); + int cpu =3D cpumask_any(&hdr->cpu_mask); + struct rdt_hw_mon_domain *hw_dom; + struct rdt_hw_resource *hw_res; struct arch_mbm_state *am; + struct rdt_mon_domain *d; u64 msr_val, chunks; u32 prmid; int ret; =20 resctrl_arch_rmid_read_context_check(); =20 + if (r->rid !=3D RDT_RESOURCE_L3) + return -EINVAL; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; + + d =3D container_of(hdr, struct rdt_mon_domain, hdr); + hw_dom =3D resctrl_to_arch_mon_dom(d); + hw_res =3D resctrl_to_arch_res(r); prmid =3D logical_rmid_to_physical_rmid(cpu, rmid); ret =3D __rmid_read_phys(prmid, eventid, &msr_val); if (ret) diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index a7d60e74a29d..1c1c0e7bbc11 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -547,7 +547,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_= head *h, int id, } =20 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first) { int cpu; @@ -561,7 +561,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_re= source *r, rr->rgrp =3D rdtgrp; rr->evtid =3D evtid; rr->r =3D r; - rr->d =3D d; + rr->hdr =3D hdr; rr->first =3D first; rr->arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(r, evtid); if (IS_ERR(rr->arch_mon_ctx)) { @@ -592,7 +592,6 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) enum resctrl_event_id evtid; struct rdt_domain_hdr *hdr; struct rmid_read rr =3D {0}; - struct rdt_mon_domain *d; struct rdtgroup *rdtgrp; int domid, cpu, ret =3D 0; struct rdt_resource *r; @@ -617,6 +616,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *ar= g) r =3D resctrl_arch_get_resource(resid); =20 if (md->sum) { + struct rdt_mon_domain *d; + + if (WARN_ON_ONCE(resid !=3D RDT_RESOURCE_L3)) { + ret =3D -EIO; + goto out; + } /* * This file requires summing across all domains that share * the L3 cache id that was provided in the "domid" field of the @@ -647,8 +652,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) ret =3D -ENOENT; goto out; } - d =3D container_of(hdr, struct rdt_mon_domain, hdr); - mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false); + mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evtid, false); } =20 checkresult: diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index dcc6c00eb362..713396cbda32 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -159,7 +159,7 @@ void __check_limbo(struct rdt_mon_domain *d, bool force= _free) break; =20 entry =3D __rmid_entry(idx); - if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, + if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val, arch_mon_ctx)) { rmid_dirty =3D true; @@ -365,19 +365,22 @@ static int __mon_event_count(u32 closid, u32 rmid, st= ruct rmid_read *rr) int err, ret; u64 tval =3D 0; =20 - if (rr->first) { - resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); - m =3D get_mbm_state(rr->d, closid, rmid, rr->evtid); + if (rr->r->rid =3D=3D RDT_RESOURCE_L3 && rr->first) { + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3= )) + return -EINVAL; + d =3D container_of(rr->hdr, struct rdt_mon_domain, hdr); + resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evtid); + m =3D get_mbm_state(d, closid, rmid, rr->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; } =20 - if (rr->d) { + if (rr->hdr) { /* Reading a single domain, must be on a CPU in that domain. */ - if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask)) + if (!cpumask_test_cpu(cpu, &rr->hdr->cpu_mask)) return -EINVAL; - rr->err =3D resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, + rr->err =3D resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; @@ -387,6 +390,9 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) return 0; } =20 + if (WARN_ON_ONCE(rr->r->rid !=3D RDT_RESOURCE_L3)) + return -EINVAL; + /* Summing domains that share a cache, must be on a CPU for that cache. */ ci =3D get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci || ci->id !=3D rr->ci_id) @@ -403,7 +409,7 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { if (d->ci_id !=3D rr->ci_id) continue; - err =3D resctrl_arch_rmid_read(rr->r, d, closid, rmid, + err =3D resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); if (!err) { rr->val +=3D tval; @@ -432,9 +438,13 @@ static int __mon_event_count(u32 closid, u32 rmid, str= uct rmid_read *rr) static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { u64 cur_bw, bytes, cur_bytes; + struct rdt_mon_domain *d; struct mbm_state *m; =20 - m =3D get_mbm_state(rr->d, closid, rmid, rr->evtid); + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + d =3D container_of(rr->hdr, struct rdt_mon_domain, hdr); + m =3D get_mbm_state(d, closid, rmid, rr->evtid); if (WARN_ON_ONCE(!m)) return; =20 @@ -608,7 +618,7 @@ static void mbm_update_one_event(struct rdt_resource *r= , struct rdt_mon_domain * struct rmid_read rr =3D {0}; =20 rr.r =3D r; - rr.d =3D d; + rr.hdr =3D &d->hdr; rr.evtid =3D evtid; rr.arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); if (IS_ERR(rr.arch_mon_ctx)) { diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 05438e15e2ca..2cff82208327 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -2887,7 +2887,8 @@ static void rmdir_all_sub(void) * @rid: The resource id for the event file being created. * @domid: The domain id for the event file being created. * @mevt: The type of event file being created. - * @do_sum: Whether SNC summing monitors are being created. + * @do_sum: Whether SNC summing monitors are being created. Only set + * when @rid =3D=3D RDT_RESOURCE_L3. */ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int do= mid, struct mon_evt *mevt, @@ -2897,6 +2898,9 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_= res_level rid, int domid, =20 lockdep_assert_held(&rdtgroup_mutex); =20 + if (WARN_ON_ONCE(do_sum && rid !=3D RDT_RESOURCE_L3)) + return NULL; + list_for_each_entry(priv, &mon_data_kn_priv_list, list) { if (priv->rid =3D=3D rid && priv->domid =3D=3D domid && priv->sum =3D=3D do_sum && priv->evtid =3D=3D mevt->evtid) @@ -3024,17 +3028,27 @@ static void mon_rmdir_one_subdir(struct kernfs_node= *pkn, char *name, char *subn * when last domain being summed is removed. */ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) + struct rdt_domain_hdr *hdr) { struct rdtgroup *prgrp, *crgrp; + int domid =3D hdr->id; char subname[32]; - bool snc_mode; char name[32]; =20 - snc_mode =3D r->mon_scope =3D=3D RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); - if (snc_mode) - sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id); + if (r->rid =3D=3D RDT_RESOURCE_L3) { + struct rdt_mon_domain *d; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + d =3D container_of(hdr, struct rdt_mon_domain, hdr); + + /* SNC mode? */ + if (r->mon_scope =3D=3D RESCTRL_L3_NODE) { + domid =3D d->ci_id; + sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id); + } + } + sprintf(name, "mon_%s_%02d", r->name, domid); =20 list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname); @@ -3044,19 +3058,18 @@ static void rmdir_mondata_subdir_allrdtgrp(struct r= dt_resource *r, } } =20 -static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain= *d, +static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr= *hdr, struct rdt_resource *r, struct rdtgroup *prgrp, - bool do_sum) + int domid, bool do_sum) { struct rmid_read rr =3D {0}; struct mon_data *priv; struct mon_evt *mevt; - int ret, domid; + int ret; =20 for_each_mon_event(mevt) { if (mevt->rid !=3D r->rid || !mevt->enabled) continue; - domid =3D do_sum ? d->ci_id : d->hdr.id; priv =3D mon_get_kn_priv(r->rid, domid, mevt, do_sum); if (WARN_ON_ONCE(!priv)) return -EINVAL; @@ -3065,26 +3078,38 @@ static int mon_add_all_files(struct kernfs_node *kn= , struct rdt_mon_domain *d, if (ret) return ret; =20 - if (!do_sum && resctrl_is_mbm_event(mevt->evtid)) - mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true); + if (r->rid =3D=3D RDT_RESOURCE_L3 && !do_sum && resctrl_is_mbm_event(mev= t->evtid)) + mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt->evtid, true); } =20 return 0; } =20 static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, - struct rdt_mon_domain *d, + struct rdt_domain_hdr *hdr, struct rdt_resource *r, struct rdtgroup *prgrp) { struct kernfs_node *kn, *ckn; + bool snc_mode =3D false; + int domid =3D hdr->id; char name[32]; - bool snc_mode; int ret =3D 0; =20 lockdep_assert_held(&rdtgroup_mutex); =20 - snc_mode =3D r->mon_scope =3D=3D RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); + if (r->rid =3D=3D RDT_RESOURCE_L3) { + snc_mode =3D r->mon_scope =3D=3D RESCTRL_L3_NODE; + if (snc_mode) { + struct rdt_mon_domain *d; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; + d =3D container_of(hdr, struct rdt_mon_domain, hdr); + domid =3D d->ci_id; + } + } + sprintf(name, "mon_%s_%02d", r->name, domid); + kn =3D kernfs_find_and_get(parent_kn, name); if (kn) { /* @@ -3100,13 +3125,13 @@ static int mkdir_mondata_subdir(struct kernfs_node = *parent_kn, ret =3D rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; - ret =3D mon_add_all_files(kn, d, r, prgrp, snc_mode); + ret =3D mon_add_all_files(kn, hdr, r, prgrp, domid, snc_mode); if (ret) goto out_destroy; } =20 if (snc_mode) { - sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id); + sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id); ckn =3D kernfs_create_dir(kn, name, parent_kn->mode, prgrp); if (IS_ERR(ckn)) { ret =3D -EINVAL; @@ -3117,7 +3142,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *p= arent_kn, if (ret) goto out_destroy; =20 - ret =3D mon_add_all_files(ckn, d, r, prgrp, false); + ret =3D mon_add_all_files(ckn, hdr, r, prgrp, hdr->id, false); if (ret) goto out_destroy; } @@ -3135,7 +3160,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *p= arent_kn, * and "monitor" groups with given domain id. */ static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) + struct rdt_domain_hdr *hdr) { struct kernfs_node *parent_kn; struct rdtgroup *prgrp, *crgrp; @@ -3143,12 +3168,12 @@ static void mkdir_mondata_subdir_allrdtgrp(struct r= dt_resource *r, =20 list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { parent_kn =3D prgrp->mon.mon_data_kn; - mkdir_mondata_subdir(parent_kn, d, r, prgrp); + mkdir_mondata_subdir(parent_kn, hdr, r, prgrp); =20 head =3D &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) { parent_kn =3D crgrp->mon.mon_data_kn; - mkdir_mondata_subdir(parent_kn, d, r, crgrp); + mkdir_mondata_subdir(parent_kn, hdr, r, crgrp); } } } @@ -3157,14 +3182,14 @@ static int mkdir_mondata_subdir_alldom(struct kernf= s_node *parent_kn, struct rdt_resource *r, struct rdtgroup *prgrp) { - struct rdt_mon_domain *dom; + struct rdt_domain_hdr *hdr; int ret; =20 /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); =20 - list_for_each_entry(dom, &r->mon_domains, hdr.list) { - ret =3D mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + list_for_each_entry(hdr, &r->mon_domains, list) { + ret =3D mkdir_mondata_subdir(parent_kn, hdr, r, prgrp); if (ret) return ret; } @@ -4036,8 +4061,10 @@ void resctrl_offline_ctrl_domain(struct rdt_resource= *r, struct rdt_ctrl_domain mutex_unlock(&rdtgroup_mutex); } =20 -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_dom= ain *d) +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_= hdr *hdr) { + struct rdt_mon_domain *d; + mutex_lock(&rdtgroup_mutex); =20 /* @@ -4045,11 +4072,15 @@ void resctrl_offline_mon_domain(struct rdt_resource= *r, struct rdt_mon_domain *d * per domain monitor data directories. */ if (resctrl_mounted && resctrl_arch_mon_capable()) - rmdir_mondata_subdir_allrdtgrp(r, d); + rmdir_mondata_subdir_allrdtgrp(r, hdr); =20 if (r->rid !=3D RDT_RESOURCE_L3) goto out_unlock; =20 + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d =3D container_of(hdr, struct rdt_mon_domain, hdr); if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(= d)) { @@ -4132,12 +4163,20 @@ int resctrl_online_ctrl_domain(struct rdt_resource = *r, struct rdt_ctrl_domain *d return err; } =20 -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domai= n *d) +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hd= r *hdr) { - int err; + struct rdt_mon_domain *d; + int err =3D -EINVAL; =20 mutex_lock(&rdtgroup_mutex); =20 + if (r->rid !=3D RDT_RESOURCE_L3) + goto mkdir; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d =3D container_of(hdr, struct rdt_mon_domain, hdr); err =3D domain_setup_mon_state(r, d); if (err) goto out_unlock; @@ -4151,6 +4190,8 @@ int resctrl_online_mon_domain(struct rdt_resource *r,= struct rdt_mon_domain *d) if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); =20 +mkdir: + err =3D 0; /* * If the filesystem is not mounted then only the default resource group * exists. Creation of its directories is deferred until mount time @@ -4158,7 +4199,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r,= struct rdt_mon_domain *d) * If resctrl is mounted, add per domain monitor data directories. */ if (resctrl_mounted && resctrl_arch_mon_capable()) - mkdir_mondata_subdir_allrdtgrp(r, d); + mkdir_mondata_subdir_allrdtgrp(r, hdr); =20 out_unlock: mutex_unlock(&rdtgroup_mutex); --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 3973B2E1C7C for ; Mon, 11 Aug 2025 18:17:37 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; cv=none; b=dEZeP4k1omFEEZfl+fBTgSQpK7X2+we4ExHhnVXI6j36v3TVEVF5l6pVuWkRi36g1ZImj4DHfUjuRI2nuMxQpTeTd0++y/cSfB25waaXiRo7nC7BnP2wLL4KTXjC9hctIG0/T6Zuti2xGQWd+l53LednwX0Rn5bpXXYInPDyxZY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; c=relaxed/simple; bh=2WubqsM1uzo/jwVOxHdUDxkk/HmZe2UtR0eWyGofOj0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=ZClatjiCxlUcUmUbZTaPNkcW2bCQqXSMldnslI1tYwhcrZiq+8aflqWK0/3IG34LkTOYsXNg8IT4uz53k86mz6y3HBSZ6HrsSEAetXvaCCx9JUTjuE+gQ27mPWOEIIpPwkaVb8NGNy2rLECkWagz/booccZAAzxKWexhhSzvrLY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=QrPO+e8P; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="QrPO+e8P" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936258; x=1786472258; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=2WubqsM1uzo/jwVOxHdUDxkk/HmZe2UtR0eWyGofOj0=; b=QrPO+e8PRaP1zz6w/k1Hw1ZCpPMjSPy3PDJGcpfOC3yy5XXQo86CdaHt EEmLLzKcm99mAJTVEOEb5w0pdJCnl+9i0y0VhY+gNu6ItgV5XnKwMl5NU 857hpbt9VbLNgzvMwQ9eiR6O4B2MMD2kwmXTm8IYk2si5GufTfj2hE91e HhKgoAs7Z77v/5vgBjRfGUtKsHLXSGd4VAyEP/4iPkOI3BzIxuXnR1wXA XT0QOfKvFoCp4dw7gY7FWCKdMGtaCZCodu+vSaS03IcqVEDzZ84oMRrLb is/v57B6Tyto80O/N0DR7LKd4embhub4M14UmDltsRkI/XV0G/+RNHwpO A==; X-CSE-ConnectionGUID: y1cxHEf+Qvixf9Vhfw9gNQ== X-CSE-MsgGUID: +n7TF8BnTgWDQh0N/uqWCQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277392" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277392" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: 6fjCDsxBR6Gpf7NBcsTFBA== X-CSE-MsgGUID: PFRqlJcoQpuMsg09t3qK0A== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825642" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 10/32] x86,fs/resctrl: Rename struct rdt_mon_domain and rdt_hw_mon_domain Date: Mon, 11 Aug 2025 11:16:44 -0700 Message-ID: <20250811181709.6241-11-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All monitoring events are associated with the L3 resource. This will change when support for telemetry events is added. The structures to track monitor domains of the L3 resource at both the file system and architecture level have generic names. This may cause confusion when support for monitoring events in other resources is added. Rename by adding "l3_" into the names: rdt_mon_domain -> rdt_l3_mon_domain rdt_hw_mon_domain -> rdt_hw_l3_mon_domain No functional change. Signed-off-by: Tony Luck --- include/linux/resctrl.h | 16 ++++++------ arch/x86/kernel/cpu/resctrl/internal.h | 16 ++++++------ fs/resctrl/internal.h | 8 +++--- arch/x86/kernel/cpu/resctrl/core.c | 14 +++++----- arch/x86/kernel/cpu/resctrl/monitor.c | 18 ++++++------- fs/resctrl/ctrlmondata.c | 2 +- fs/resctrl/monitor.c | 34 ++++++++++++------------ fs/resctrl/rdtgroup.c | 36 +++++++++++++------------- 8 files changed, 72 insertions(+), 72 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index c8200626b91a..5788e1970d8c 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -166,7 +166,7 @@ struct rdt_ctrl_domain { }; =20 /** - * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * struct rdt_l3_mon_domain - group of CPUs sharing a resctrl monitor reso= urce * @hdr: common header for different domain types * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold @@ -178,7 +178,7 @@ struct rdt_ctrl_domain { * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters */ -struct rdt_mon_domain { +struct rdt_l3_mon_domain { struct rdt_domain_hdr hdr; unsigned int ci_id; unsigned long *rmid_busy_llc; @@ -334,10 +334,10 @@ struct resctrl_cpu_defaults { }; =20 struct resctrl_mon_config_info { - struct rdt_resource *r; - struct rdt_mon_domain *d; - u32 evtid; - u32 mon_config; + struct rdt_resource *r; + struct rdt_l3_mon_domain *d; + u32 evtid; + u32 mon_config; }; =20 /** @@ -530,7 +530,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_= head *h, int id, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain= *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_dom= ain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); =20 @@ -543,7 +543,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, st= ruct rdt_mon_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_do= main *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon= _domain *d); =20 /** * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to i= ts diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index 58dca892a5df..684a1b830ced 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -51,17 +51,17 @@ struct rdt_hw_ctrl_domain { }; =20 /** - * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs tha= t share - * a resource for a monitor function - * @d_resctrl: Properties exposed to the resctrl file system + * struct rdt_hw_l3_mon_domain - Arch private attributes of a set of CPUs = that share + * a resource for a monitor function + * @d_resctrl: Properties exposed to the resctrl file system * @arch_mbm_states: Per-event pointer to the MBM event's saved state. * An MBM event's state is an array of struct arch_mbm_state * indexed by RMID on x86. * * Members of this structure are accessed via helpers that provide abstrac= tion. */ -struct rdt_hw_mon_domain { - struct rdt_mon_domain d_resctrl; +struct rdt_hw_l3_mon_domain { + struct rdt_l3_mon_domain d_resctrl; struct arch_mbm_state *arch_mbm_states[QOS_NUM_L3_MBM_EVENTS]; }; =20 @@ -70,9 +70,9 @@ static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_= ctrl_dom(struct rdt_ctr return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl); } =20 -static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt= _mon_domain *r) +static inline struct rdt_hw_l3_mon_domain *resctrl_to_arch_mon_dom(struct = rdt_l3_mon_domain *r) { - return container_of(r, struct rdt_hw_mon_domain, d_resctrl); + return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl); } =20 /** @@ -124,7 +124,7 @@ static inline struct rdt_hw_resource *resctrl_to_arch_r= es(struct rdt_resource *r =20 extern struct rdt_hw_resource rdt_resources_all[]; =20 -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain = *d); +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_doma= in *d); =20 /* CPUID.(EAX=3D10H, ECX=3DResID=3D1).EAX */ union cpuid_0x10_1_eax { diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index b19e974b7865..e4f06f700063 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -357,7 +357,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_re= source *r, =20 int resctrl_mon_resource_init(void); =20 -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); =20 @@ -365,14 +365,14 @@ void mbm_handle_overflow(struct work_struct *work); =20 bool is_mba_sc(struct rdt_resource *r); =20 -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long del= ay_ms, +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long = delay_ms, int exclude_cpu); =20 void cqm_handle_limbo(struct work_struct *work); =20 -bool has_busy_rmid(struct rdt_mon_domain *d); +bool has_busy_rmid(struct rdt_l3_mon_domain *d); =20 -void __check_limbo(struct rdt_mon_domain *d, bool force_free); +void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free); =20 void resctrl_file_fflags_init(const char *config, unsigned long fflags); =20 diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 7fd6cd7348fb..54d99e3b8fd9 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -363,7 +363,7 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain = *hw_dom) kfree(hw_dom); } =20 -static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom) +static void mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom) { int idx; =20 @@ -400,7 +400,7 @@ static int domain_setup_ctrlval(struct rdt_resource *r,= struct rdt_ctrl_domain * * @num_rmid: The size of the MBM counter array * @hw_dom: The domain that owns the allocated arrays */ -static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *h= w_dom) +static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain= *hw_dom) { size_t tsize =3D sizeof(*hw_dom->arch_mbm_states[0]); enum resctrl_event_id eventid; @@ -498,8 +498,8 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_res= ource *r) =20 static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, s= truct list_head *add_pos) { - struct rdt_hw_mon_domain *hw_dom; - struct rdt_mon_domain *d; + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; struct cacheinfo *ci; int err; =20 @@ -626,9 +626,9 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_= resource *r) static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) { int id =3D get_domain_id_from_scope(cpu, r->mon_scope); - struct rdt_hw_mon_domain *hw_dom; + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; struct rdt_domain_hdr *hdr; - struct rdt_mon_domain *d; =20 lockdep_assert_held(&domain_list_lock); =20 @@ -654,7 +654,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_r= esource *r) =20 switch (r->rid) { case RDT_RESOURCE_L3: - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); hw_dom =3D resctrl_to_arch_mon_dom(d); resctrl_offline_mon_domain(r, hdr); list_del_rcu(&d->hdr.list); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index b31794c5dcd4..043f777378a6 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -157,7 +157,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_eve= nt_id eventid, u64 *val) return 0; } =20 -static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain = *hw_dom, +static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_l3_mon_doma= in *hw_dom, u32 rmid, enum resctrl_event_id eventid) { @@ -171,11 +171,11 @@ static struct arch_mbm_state *get_arch_mbm_state(stru= ct rdt_hw_mon_domain *hw_do return state ? &state[rmid] : NULL; } =20 -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain= *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_dom= ain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid) { - struct rdt_hw_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); int cpu =3D cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; u32 prmid; @@ -194,9 +194,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, st= ruct rdt_mon_domain *d, * Assumes that hardware counters are also reset and thus that there is * no need to record initial non-zero counts. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_do= main *d) +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon= _domain *d) { - struct rdt_hw_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom =3D resctrl_to_arch_mon_dom(d); enum resctrl_event_id eventid; int idx; =20 @@ -222,10 +222,10 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, st= ruct rdt_domain_hdr *hdr, u64 *val, void *ignored) { int cpu =3D cpumask_any(&hdr->cpu_mask); - struct rdt_hw_mon_domain *hw_dom; + struct rdt_hw_l3_mon_domain *hw_dom; struct rdt_hw_resource *hw_res; + struct rdt_l3_mon_domain *d; struct arch_mbm_state *am; - struct rdt_mon_domain *d; u64 msr_val, chunks; u32 prmid; int ret; @@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, stru= ct rdt_domain_hdr *hdr, if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) return -EINVAL; =20 - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); hw_dom =3D resctrl_to_arch_mon_dom(d); hw_res =3D resctrl_to_arch_res(r); prmid =3D logical_rmid_to_physical_rmid(cpu, rmid); @@ -275,7 +275,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, stru= ct rdt_domain_hdr *hdr, * must adjust RMID counter numbers based on SNC node. See * logical_rmid_to_physical_rmid() for code that does this. */ -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain = *d) +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_doma= in *d) { if (snc_nodes_per_l3_cache > 1) msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index 1c1c0e7bbc11..1d7086509bfa 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -616,7 +616,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) r =3D resctrl_arch_get_resource(resid); =20 if (md->sum) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 if (WARN_ON_ONCE(resid !=3D RDT_RESOURCE_L3)) { ret =3D -EIO; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 713396cbda32..8d4e3adc1fe8 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -130,7 +130,7 @@ static void limbo_release_entry(struct rmid_entry *entr= y) * decrement the count. If the busy count gets to zero on an RMID, we * free the RMID */ -void __check_limbo(struct rdt_mon_domain *d, bool force_free) +void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); @@ -188,7 +188,7 @@ void __check_limbo(struct rdt_mon_domain *d, bool force= _free) resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); } =20 -bool has_busy_rmid(struct rdt_mon_domain *d) +bool has_busy_rmid(struct rdt_l3_mon_domain *d) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); =20 @@ -289,7 +289,7 @@ int alloc_rmid(u32 closid) static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; u32 idx; =20 lockdep_assert_held(&rdtgroup_mutex); @@ -342,7 +342,7 @@ void free_rmid(u32 closid, u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } =20 -static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closi= d, +static struct mbm_state *get_mbm_state(struct rdt_l3_mon_domain *d, u32 cl= osid, u32 rmid, enum resctrl_event_id evtid) { u32 idx =3D resctrl_arch_rmid_idx_encode(closid, rmid); @@ -359,7 +359,7 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_d= omain *d, u32 closid, static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { int cpu =3D smp_processor_id(); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct cacheinfo *ci; struct mbm_state *m; int err, ret; @@ -368,7 +368,7 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (rr->r->rid =3D=3D RDT_RESOURCE_L3 && rr->first) { if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3= )) return -EINVAL; - d =3D container_of(rr->hdr, struct rdt_mon_domain, hdr); + d =3D container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evtid); m =3D get_mbm_state(d, closid, rmid, rr->evtid); if (m) @@ -438,12 +438,12 @@ static int __mon_event_count(u32 closid, u32 rmid, st= ruct rmid_read *rr) static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { u64 cur_bw, bytes, cur_bytes; - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct mbm_state *m; =20 if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) return; - d =3D container_of(rr->hdr, struct rdt_mon_domain, hdr); + d =3D container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); m =3D get_mbm_state(d, closid, rmid, rr->evtid); if (WARN_ON_ONCE(!m)) return; @@ -544,7 +544,7 @@ static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu= (int cpu, * throttle MSRs already have low percentage values. To avoid * unnecessarily restricting such rdtgroups, we also increase the bandwidt= h. */ -static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *do= m_mbm) +static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_l3_mon_domain = *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; @@ -612,7 +612,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct= rdt_mon_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } =20 -static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_do= main *d, +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon= _domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { struct rmid_read rr =3D {0}; @@ -639,7 +639,7 @@ static void mbm_update_one_event(struct rdt_resource *r= , struct rdt_mon_domain * resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } =20 -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, +static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 closid, u32 rmid) { /* @@ -660,12 +660,12 @@ static void mbm_update(struct rdt_resource *r, struct= rdt_mon_domain *d, void cqm_handle_limbo(struct work_struct *work) { unsigned long delay =3D msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 cpus_read_lock(); mutex_lock(&rdtgroup_mutex); =20 - d =3D container_of(work, struct rdt_mon_domain, cqm_limbo.work); + d =3D container_of(work, struct rdt_l3_mon_domain, cqm_limbo.work); =20 __check_limbo(d, false); =20 @@ -688,7 +688,7 @@ void cqm_handle_limbo(struct work_struct *work) * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long del= ay_ms, +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long = delay_ms, int exclude_cpu) { unsigned long delay =3D msecs_to_jiffies(delay_ms); @@ -705,7 +705,7 @@ void mbm_handle_overflow(struct work_struct *work) { unsigned long delay =3D msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct list_head *head; struct rdt_resource *r; =20 @@ -720,7 +720,7 @@ void mbm_handle_overflow(struct work_struct *work) goto out_unlock; =20 r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); - d =3D container_of(work, struct rdt_mon_domain, mbm_over.work); + d =3D container_of(work, struct rdt_l3_mon_domain, mbm_over.work); =20 list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); @@ -754,7 +754,7 @@ void mbm_handle_overflow(struct work_struct *work) * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long = delay_ms, +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned lo= ng delay_ms, int exclude_cpu) { unsigned long delay =3D msecs_to_jiffies(delay_ms); diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 2cff82208327..9f295cd8f0e5 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -1617,7 +1617,7 @@ static void mondata_config_read(struct resctrl_mon_co= nfig_info *mon_info) static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32= evtid) { struct resctrl_mon_config_info mon_info; - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; bool sep =3D false; =20 cpus_read_lock(); @@ -1665,7 +1665,7 @@ static int mbm_local_bytes_config_show(struct kernfs_= open_file *of, } =20 static void mbm_config_write_domain(struct rdt_resource *r, - struct rdt_mon_domain *d, u32 evtid, u32 val) + struct rdt_l3_mon_domain *d, u32 evtid, u32 val) { struct resctrl_mon_config_info mon_info =3D {0}; =20 @@ -1706,8 +1706,8 @@ static void mbm_config_write_domain(struct rdt_resour= ce *r, static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { char *dom_str =3D NULL, *id_str; + struct rdt_l3_mon_domain *d; unsigned long dom_id, val; - struct rdt_mon_domain *d; =20 /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); @@ -2581,7 +2581,7 @@ static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx =3D rdt_fc2context(fc); unsigned long flags =3D RFTYPE_CTRL_BASE; - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; struct rdt_resource *r; int ret; =20 @@ -3036,11 +3036,11 @@ static void rmdir_mondata_subdir_allrdtgrp(struct r= dt_resource *r, char name[32]; =20 if (r->rid =3D=3D RDT_RESOURCE_L3) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) return; - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); =20 /* SNC mode? */ if (r->mon_scope =3D=3D RESCTRL_L3_NODE) { @@ -3100,11 +3100,11 @@ static int mkdir_mondata_subdir(struct kernfs_node = *parent_kn, if (r->rid =3D=3D RDT_RESOURCE_L3) { snc_mode =3D r->mon_scope =3D=3D RESCTRL_L3_NODE; if (snc_mode) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) return -EINVAL; - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); domid =3D d->ci_id; } } @@ -4040,7 +4040,7 @@ static void rdtgroup_setup_default(void) mutex_unlock(&rdtgroup_mutex); } =20 -static void domain_destroy_mon_state(struct rdt_mon_domain *d) +static void domain_destroy_mon_state(struct rdt_l3_mon_domain *d) { int idx; =20 @@ -4063,7 +4063,7 @@ void resctrl_offline_ctrl_domain(struct rdt_resource = *r, struct rdt_ctrl_domain =20 void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_= hdr *hdr) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 mutex_lock(&rdtgroup_mutex); =20 @@ -4080,7 +4080,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *= r, struct rdt_domain_hdr *h if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) goto out_unlock; =20 - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(= d)) { @@ -4114,7 +4114,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *= r, struct rdt_domain_hdr *h * * Returns 0 for success, or -ENOMEM. */ -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_d= omain *d) +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_l3_mo= n_domain *d) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); size_t tsize =3D sizeof(*d->mbm_states[0]); @@ -4165,7 +4165,7 @@ int resctrl_online_ctrl_domain(struct rdt_resource *r= , struct rdt_ctrl_domain *d =20 int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hd= r *hdr) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; int err =3D -EINVAL; =20 mutex_lock(&rdtgroup_mutex); @@ -4176,7 +4176,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r,= struct rdt_domain_hdr *hdr if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) goto out_unlock; =20 - d =3D container_of(hdr, struct rdt_mon_domain, hdr); + d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); err =3D domain_setup_mon_state(r, d); if (err) goto out_unlock; @@ -4225,10 +4225,10 @@ static void clear_childcpus(struct rdtgroup *r, uns= igned int cpu) } } =20 -static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, - struct rdt_resource *r) +static struct rdt_l3_mon_domain *get_mon_domain_from_cpu(int cpu, + struct rdt_resource *r) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; =20 lockdep_assert_cpus_held(); =20 @@ -4244,7 +4244,7 @@ static struct rdt_mon_domain *get_mon_domain_from_cpu= (int cpu, void resctrl_offline_cpu(unsigned int cpu) { struct rdt_resource *l3 =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct rdtgroup *rdtgrp; =20 mutex_lock(&rdtgroup_mutex); --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 206412E267C for ; Mon, 11 Aug 2025 18:17:38 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; cv=none; b=Bcd/jB0m9OztidXByZYkZrbzunZz1WGeoWI5gAZweCpfNZ0QMx7mqYda5laGBqKdlUaE8jz/ydJZJ/SMkPvI0zPlFgPUDLYRj9jx+XAm4Xf+skF323/sZkGOmx0g+jySNDPjjq02APE0Ef4wvYDtKCbUT8/tvQdTo7nldzYG6XE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; c=relaxed/simple; bh=/BL1FVM1V2q4vn1Rgw6/FpqvyS2J9Y+sKSPU0W+WxdU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=brNdM2nznjyhXtDywqLEkS4o3y/hUb2fkfepLjzAzZQt41oapM1S8sj+rrvgZTMT1lt7LAVHDs7UQcd4tqXaZotCZUgLXdh6CcrRs0IXOExfBMdflJvpuyV7+tGvHhjDoJr9p/5oWKuYN/vX+4sn08H8+a8caVFnEgZNpj0bdSU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=bvFI8Yl8; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="bvFI8Yl8" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936258; x=1786472258; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=/BL1FVM1V2q4vn1Rgw6/FpqvyS2J9Y+sKSPU0W+WxdU=; b=bvFI8Yl8JJSIBuvtKf4dhgUy1TFV83QO4Gj74bxL1Tj+KKdcZcFtHel9 yrDa+ZTbFz9+isT0ix7lNryRCIVk29BjXZxvxUs+xiqHMD0TvBUabpu3c 09qF2uP6t4fDc6rNS+Wdeze6tudFhdacmvdFVqcoiN+a4PUNYLZ/e+8c0 BZ45DxpzCWh/Wo7XYyrtpJih4TRf0mTpKI7sLowTK2UTNWmpTMZBywZDj h1WRp9weotYoUcphRkYGOsPc0xSWlp1isJahpjj07Rxn26cGVSetNdR5+ 77BEQR/cVxegp8LXnI+9dYciI0SXKshjTmX6+WjFKD5bYnrJoBw2JmUjd w==; X-CSE-ConnectionGUID: Xr4AdZnLSMuG9tTT+BkRvw== X-CSE-MsgGUID: OI6picIkTd6fBcfbtL21XA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277402" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277402" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: cMKEKwlESs+qnzcYX/NIPQ== X-CSE-MsgGUID: BpzZFsFMTNOHC8EmuM3ecA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825646" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:23 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 11/32] x86,fs/resctrl: Rename some L3 specific functions Date: Mon, 11 Aug 2025 11:16:45 -0700 Message-ID: <20250811181709.6241-12-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All monitor functions are tied to the RDT_RESOURCE_L3 resource, so generic function names to setup and tear down domains makes sense. With the arrival of monitor events tied to new domains associated with different resources it would be clearer if these functions are more accurately named. Two groups of functions renamed here: Functions that allocate/free architecture per-RMID MBM state information: arch_domain_mbm_alloc() -> l3_mon_domain_mbm_alloc() mon_domain_free() -> l3_mon_domain_free() Functions that allocate/free filesystem per-RMID MBM state information: domain_setup_mon_state() -> domain_setup_l3_mon_state() domain_destroy_mon_state() -> domain_destroy_l3_mon_state() Initialization/exit: resctrl_mon_resource_init -> resctrl_mon_l3_resource_init() resctrl_mon_resource_exit() -> resctrl_mon_l3_resource_exit() Signed-off-by: Tony Luck --- fs/resctrl/internal.h | 6 +++--- arch/x86/kernel/cpu/resctrl/core.c | 16 ++++++++-------- fs/resctrl/monitor.c | 6 +++--- fs/resctrl/rdtgroup.c | 22 +++++++++++----------- 4 files changed, 25 insertions(+), 25 deletions(-) diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index e4f06f700063..baab3c87f323 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -345,7 +345,9 @@ int alloc_rmid(u32 closid); =20 void free_rmid(u32 closid, u32 rmid); =20 -void resctrl_mon_resource_exit(void); +int resctrl_mon_l3_resource_init(void); + +void resctrl_mon_l3_resource_exit(void); =20 void mon_event_count(void *info); =20 @@ -355,8 +357,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_re= source *r, struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first); =20 -int resctrl_mon_resource_init(void); - void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 54d99e3b8fd9..fe8af1c69c24 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -363,7 +363,7 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain = *hw_dom) kfree(hw_dom); } =20 -static void mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom) +static void l3_mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom) { int idx; =20 @@ -396,11 +396,11 @@ static int domain_setup_ctrlval(struct rdt_resource *= r, struct rdt_ctrl_domain * } =20 /** - * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM cou= nters + * l3_mon_domain_mbm_alloc() - Allocate arch private storage for the MBM c= ounters * @num_rmid: The size of the MBM counter array * @hw_dom: The domain that owns the allocated arrays */ -static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain= *hw_dom) +static int l3_mon_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_doma= in *hw_dom) { size_t tsize =3D sizeof(*hw_dom->arch_mbm_states[0]); enum resctrl_event_id eventid; @@ -514,7 +514,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct= rdt_resource *r, struct ci =3D get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) { pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->nam= e); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); return; } d->ci_id =3D ci->id; @@ -522,8 +522,8 @@ static void l3_mon_domain_setup(int cpu, int id, struct= rdt_resource *r, struct =20 arch_mon_domain_online(r, d); =20 - if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { - mon_domain_free(hw_dom); + if (l3_mon_domain_mbm_alloc(r->num_rmid, hw_dom)) { + l3_mon_domain_free(hw_dom); return; } =20 @@ -533,7 +533,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct= rdt_resource *r, struct if (err) { list_del_rcu(&d->hdr.list); synchronize_rcu(); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); } } =20 @@ -659,7 +659,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_r= esource *r) resctrl_offline_mon_domain(r, hdr); list_del_rcu(&d->hdr.list); synchronize_rcu(); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); break; default: pr_warn_once("Unknown resource rid=3D%d\n", r->rid); diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 8d4e3adc1fe8..59d72c3ad579 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -895,7 +895,7 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id= eventid) } =20 /** - * resctrl_mon_resource_init() - Initialise global monitoring structures. + * resctrl_mon_l3_resource_init() - Initialise global monitoring structure= s. * * Allocate and initialise global monitor resources that do not belong to a * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists. @@ -906,7 +906,7 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id= eventid) * * Returns 0 for success, or -ENOMEM. */ -int resctrl_mon_resource_init(void) +int resctrl_mon_l3_resource_init(void) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); int ret; @@ -937,7 +937,7 @@ int resctrl_mon_resource_init(void) return 0; } =20 -void resctrl_mon_resource_exit(void) +void resctrl_mon_l3_resource_exit(void) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); =20 diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 9f295cd8f0e5..db63da7f3152 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -4040,7 +4040,7 @@ static void rdtgroup_setup_default(void) mutex_unlock(&rdtgroup_mutex); } =20 -static void domain_destroy_mon_state(struct rdt_l3_mon_domain *d) +static void domain_destroy_l3_mon_state(struct rdt_l3_mon_domain *d) { int idx; =20 @@ -4096,13 +4096,13 @@ void resctrl_offline_mon_domain(struct rdt_resource= *r, struct rdt_domain_hdr *h cancel_delayed_work(&d->cqm_limbo); } =20 - domain_destroy_mon_state(d); + domain_destroy_l3_mon_state(d); out_unlock: mutex_unlock(&rdtgroup_mutex); } =20 /** - * domain_setup_mon_state() - Initialise domain monitoring structures. + * domain_setup_l3_mon_state() - Initialise domain monitoring structures. * @r: The resource for the newly online domain. * @d: The newly online domain. * @@ -4110,11 +4110,11 @@ void resctrl_offline_mon_domain(struct rdt_resource= *r, struct rdt_domain_hdr *h * Called when the first CPU of a domain comes online, regardless of wheth= er * the filesystem is mounted. * During boot this may be called before global allocations have been made= by - * resctrl_mon_resource_init(). + * resctrl_mon_l3_resource_init(). * * Returns 0 for success, or -ENOMEM. */ -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_l3_mo= n_domain *d) +static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3= _mon_domain *d) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); size_t tsize =3D sizeof(*d->mbm_states[0]); @@ -4177,7 +4177,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r,= struct rdt_domain_hdr *hdr goto out_unlock; =20 d =3D container_of(hdr, struct rdt_l3_mon_domain, hdr); - err =3D domain_setup_mon_state(r, d); + err =3D domain_setup_l3_mon_state(r, d); if (err) goto out_unlock; =20 @@ -4294,13 +4294,13 @@ int resctrl_init(void) =20 thread_throttle_mode_init(); =20 - ret =3D resctrl_mon_resource_init(); + ret =3D resctrl_mon_l3_resource_init(); if (ret) return ret; =20 ret =3D sysfs_create_mount_point(fs_kobj, "resctrl"); if (ret) { - resctrl_mon_resource_exit(); + resctrl_mon_l3_resource_exit(); return ret; } =20 @@ -4335,7 +4335,7 @@ int resctrl_init(void) =20 cleanup_mountpoint: sysfs_remove_mount_point(fs_kobj, "resctrl"); - resctrl_mon_resource_exit(); + resctrl_mon_l3_resource_exit(); =20 return ret; } @@ -4371,7 +4371,7 @@ static bool resctrl_online_domains_exist(void) * When called by the architecture code, all CPUs and resctrl domains must= be * offline. This ensures the limbo and overflow handlers are not scheduled= to * run, meaning the data structures they access can be freed by - * resctrl_mon_resource_exit(). + * resctrl_mon_l3_resource_exit(). * * After resctrl_exit() returns, the architecture code should return an * error from all resctrl_arch_ functions that can do this. @@ -4398,5 +4398,5 @@ void resctrl_exit(void) * it can be used to umount resctrl. */ =20 - resctrl_mon_resource_exit(); + resctrl_mon_l3_resource_exit(); } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 440A42E267F for ; Mon, 11 Aug 2025 18:17:38 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; cv=none; b=lxdB0n6bv8yCjJFtYzTJgd/L878JsMedO0A+fD42QAwj+rqJYBRolCC45m9eur0/RyHTX/Y3ubplZpixuJYCXmSI6uZ13zJ/m29iSolu+LqMROHLWgfqasSNvhJJAsLFsxHJfxNkjA4bhkaeIs/Wn3rQnGj3nTQGVZcRMFGMXNE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936260; c=relaxed/simple; bh=X3qMAegbrvvVKnCTh2BttCuhvKkOq9VZBu9Q+n+xwJQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Imcq514llHfGX6f90y2CWpVS34ur5D1GLoCd/hEh2v3FNXWRsklN/cCahj1GXSNFVdVNWRyamL41N/th+PH6BXtenPbMXCbU8u83t83LlJI5Ql1vWXD6aS2Pocu+1rZsFyPf0hQiFfYhng4ozyJ9Fiu9aTJrApw6mplcnkcCiVg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=GAHAm7px; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="GAHAm7px" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936259; x=1786472259; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=X3qMAegbrvvVKnCTh2BttCuhvKkOq9VZBu9Q+n+xwJQ=; b=GAHAm7pxq6SSNQcFjPDWTBnLoklrJ0bSoO6XtSkXfDgK46PIWg8pz5RT K6O+l+/noZkb+38aZgTRYCeyJFej55qpDGSic//sXQzSSzt5GX2VIgqpn jY1OfQeHkeKATMmlF8u3FCSPo6AG1M5TeV/FNslqnYzPJczD3PDWe3DbB d4tZhbJ8f4KadoTzqKFnu+Sci3ayaQJZwvHBDRCuQwzb9Dp2f4dA6xotV CivrbK2DXkG+el6KPRdIrldDG1punOhhSNJkB7YE4xR9OwYcoE1beO2/T WR8jy9fa0jmSBxWTA4sE3FAtsCqgGSX7Gwl7E/uWY7cfMwKLngMeBWugC g==; X-CSE-ConnectionGUID: 7R5x1J0xRC+NVK/mfdpgQw== X-CSE-MsgGUID: K4/UhnN9TN+zj4J11gsHRg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277408" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277408" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: VNtOV2rgQXan13cNsEpj4Q== X-CSE-MsgGUID: emH1XCyrSeuMbUQVF6yOMg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825650" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:24 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 12/32] fs/resctrl: Make event details accessible to functions when reading events Date: Mon, 11 Aug 2025 11:16:46 -0700 Message-ID: <20250811181709.6241-13-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All details about a monitor event are kept in the mon_evt structure. Upper levels of code only provide the event id to lower levels. But those lower levels need more than just the event id, they need the attributes of the event too. Change the mon_data and rmid_read structures to hold a pointer to the mon_evt structure instead of just taking a copy of the event id. No functional change. Signed-off-by: Tony Luck --- fs/resctrl/internal.h | 10 +++++----- fs/resctrl/ctrlmondata.c | 16 ++++++++-------- fs/resctrl/monitor.c | 17 +++++++++-------- fs/resctrl/rdtgroup.c | 6 +++--- 4 files changed, 25 insertions(+), 24 deletions(-) diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index baab3c87f323..eb45cf746c5c 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -76,7 +76,7 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; * struct mon_data - Monitoring details for each event file. * @list: Member of the global @mon_data_kn_priv_list list. * @rid: Resource id associated with the event file. - * @evtid: Event id associated with the event file. + * @evt: Event structure associated with the event file. * @sum: Set for RDT_RESOURCE_L3 when event must be summed * across multiple domains. * @domid: When @sum is zero this is the domain to which @@ -90,7 +90,7 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; struct mon_data { struct list_head list; enum resctrl_res_level rid; - enum resctrl_event_id evtid; + struct mon_evt *evt; int domid; bool sum; }; @@ -103,7 +103,7 @@ struct mon_data { * @r: Resource describing the properties of the event being read. * @hdr: Header of domain that the counter should be read from. If NULL = then sum all * domains in @r sharing L3 @ci.id - * @evtid: Which monitor event to read. + * @evt: Which monitor event to read. * @first: Initialize MBM counter when true. * @ci_id: Cacheinfo id for L3. Only set when @hdr is NULL. Used when summ= ing domains. * @err: Error encountered when reading counter. @@ -117,7 +117,7 @@ struct rmid_read { struct rdtgroup *rgrp; struct rdt_resource *r; struct rdt_domain_hdr *hdr; - enum resctrl_event_id evtid; + struct mon_evt *evt; bool first; unsigned int ci_id; int err; @@ -355,7 +355,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg= ); =20 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first); + cpumask_t *cpumask, struct mon_evt *evt, int first); =20 void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index 1d7086509bfa..a99903ac5d27 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -548,7 +548,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_= head *h, int id, =20 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first) + cpumask_t *cpumask, struct mon_evt *evt, int first) { int cpu; =20 @@ -559,11 +559,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_= resource *r, * Setup the parameters to pass to mon_event_count() to read the data. */ rr->rgrp =3D rdtgrp; - rr->evtid =3D evtid; + rr->evt =3D evt; rr->r =3D r; rr->hdr =3D hdr; rr->first =3D first; - rr->arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(r, evtid); + rr->arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(r, evt->evtid); if (IS_ERR(rr->arch_mon_ctx)) { rr->err =3D -EINVAL; return; @@ -582,20 +582,20 @@ void mon_event_read(struct rmid_read *rr, struct rdt_= resource *r, else smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); =20 - resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); + resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx); } =20 int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of =3D m->private; enum resctrl_res_level resid; - enum resctrl_event_id evtid; struct rdt_domain_hdr *hdr; struct rmid_read rr =3D {0}; struct rdtgroup *rdtgrp; int domid, cpu, ret =3D 0; struct rdt_resource *r; struct cacheinfo *ci; + struct mon_evt *evt; struct mon_data *md; =20 rdtgrp =3D rdtgroup_kn_lock_live(of->kn); @@ -612,7 +612,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) =20 resid =3D md->rid; domid =3D md->domid; - evtid =3D md->evtid; + evt =3D md->evt; r =3D resctrl_arch_get_resource(resid); =20 if (md->sum) { @@ -636,7 +636,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) if (!ci) continue; mon_event_read(&rr, r, NULL, rdtgrp, - &ci->shared_cpu_map, evtid, false); + &ci->shared_cpu_map, evt, false); goto checkresult; } } @@ -652,7 +652,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) ret =3D -ENOENT; goto out; } - mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evtid, false); + mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evt, false); } =20 checkresult: diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 59d72c3ad579..c3f697da612b 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -369,8 +369,8 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3= )) return -EINVAL; d =3D container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); - resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evtid); - m =3D get_mbm_state(d, closid, rmid, rr->evtid); + resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evt->evtid); + m =3D get_mbm_state(d, closid, rmid, rr->evt->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; @@ -381,7 +381,7 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (!cpumask_test_cpu(cpu, &rr->hdr->cpu_mask)) return -EINVAL; rr->err =3D resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); + rr->evt->evtid, &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; =20 @@ -410,7 +410,7 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (d->ci_id !=3D rr->ci_id) continue; err =3D resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); + rr->evt->evtid, &tval, rr->arch_mon_ctx); if (!err) { rr->val +=3D tval; ret =3D 0; @@ -444,7 +444,7 @@ static void mbm_bw_count(u32 closid, u32 rmid, struct r= mid_read *rr) if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) return; d =3D container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); - m =3D get_mbm_state(d, closid, rmid, rr->evtid); + m =3D get_mbm_state(d, closid, rmid, rr->evt->evtid); if (WARN_ON_ONCE(!m)) return; =20 @@ -615,12 +615,13 @@ static void update_mba_bw(struct rdtgroup *rgrp, stru= ct rdt_l3_mon_domain *dom_m static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon= _domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { + struct mon_evt *evt =3D &mon_event_all[evtid]; struct rmid_read rr =3D {0}; =20 rr.r =3D r; rr.hdr =3D &d->hdr; - rr.evtid =3D evtid; - rr.arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + rr.evt =3D evt; + rr.arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(rr.r, evt->evtid); if (IS_ERR(rr.arch_mon_ctx)) { pr_warn_ratelimited("Failed to allocate monitor context: %ld", PTR_ERR(rr.arch_mon_ctx)); @@ -636,7 +637,7 @@ static void mbm_update_one_event(struct rdt_resource *r= , struct rdt_l3_mon_domai if (is_mba_sc(NULL)) mbm_bw_count(closid, rmid, &rr); =20 - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); + resctrl_arch_mon_ctx_free(rr.r, evt->evtid, rr.arch_mon_ctx); } =20 static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d, diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index db63da7f3152..b917d48a806a 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -2903,7 +2903,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_= res_level rid, int domid, =20 list_for_each_entry(priv, &mon_data_kn_priv_list, list) { if (priv->rid =3D=3D rid && priv->domid =3D=3D domid && - priv->sum =3D=3D do_sum && priv->evtid =3D=3D mevt->evtid) + priv->sum =3D=3D do_sum && priv->evt =3D=3D mevt) return priv; } =20 @@ -2914,7 +2914,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_= res_level rid, int domid, priv->rid =3D rid; priv->domid =3D domid; priv->sum =3D do_sum; - priv->evtid =3D mevt->evtid; + priv->evt =3D mevt; list_add_tail(&priv->list, &mon_data_kn_priv_list); =20 return priv; @@ -3079,7 +3079,7 @@ static int mon_add_all_files(struct kernfs_node *kn, = struct rdt_domain_hdr *hdr, return ret; =20 if (r->rid =3D=3D RDT_RESOURCE_L3 && !do_sum && resctrl_is_mbm_event(mev= t->evtid)) - mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt->evtid, true); + mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt, true); } =20 return 0; --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 844012E2DCF for ; Mon, 11 Aug 2025 18:17:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936262; cv=none; b=c6Sf7AZXr7sA5IHulbQ6wr/Pn5kDlQZU6r0/J0Zbs9sTaDPZUtKLNwgiI9nK7cgCPN5RsUVmqYGirv+VYkrjthPTucmUUdVCo5/LGMPr8rd7AQmn8UptgmPKIeTGvY9zZirNku8mi77uBjW6h2u3Y6ad6tsxmThG2/U4D56HMpk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936262; c=relaxed/simple; bh=ZmeQeFg8lywN223cH0bKDo/2rtDccmyi41nxp+QJit4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=fsg2N8Y1BoZKFb+xtBGqgMk+mvAwSBmx9U0z3yKI/MVtTLGte/D8QO5+/g+ZLO1zo+gWgkNh+fgIRvz2Pf1pw8qR7o9bR/ROBab0FaMnJOum2bYXfWnnxfmla9/nSsnjquIy+MbglhuDgFHMzBHK/YY2SAbrXJWhdam0Ve38GC8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=TiGGwW9f; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="TiGGwW9f" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936261; x=1786472261; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=ZmeQeFg8lywN223cH0bKDo/2rtDccmyi41nxp+QJit4=; b=TiGGwW9fDqN46MKJG7YbHCwiKoawCZZl0CWXW4HrUsqPlgvG92+Qj9Tm dOLbjYAJo/u9GKpedT58attwtlE6HwxGkXkAjPHub8M0m5cWcvqgZXq5w ojEnzSA6Kfsvx9vK5/nlvRp/HXPyWudxTWMhUk+2WdWXTQuGPAnt0jnNh 4gjef4qYtlOdMkDa/kk/6NBiHNzvArUTcBZScNJPCQf0vNzDyNLqT+GhH YBJLR4kLtRr2UoLX/0tZjHZCNEME224vAs0pOWdmGymulmCXLaonSg8mb kjUMwmljZ+y7q8DU8LBEPIAs3/Bu40mx6gHh3SPMCd9x+CdmT9uLgIcuu A==; X-CSE-ConnectionGUID: rTSeQed4SxaQ9bAbqNQ4Dg== X-CSE-MsgGUID: REpTdKKhTYif6CoNjHv14Q== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277416" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277416" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: gGOMIKmjSyO+70k20ogRmg== X-CSE-MsgGUID: SmYEEH8kSFuaOuUO1NhTYw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825654" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:24 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 13/32] x86,fs/resctrl: Handle events that can be read from any CPU Date: Mon, 11 Aug 2025 11:16:47 -0700 Message-ID: <20250811181709.6241-14-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" resctrl assumes that monitor events can only be read from a CPU in the cpumask_t set of each domain. This is true for x86 events accessed with an MSR interface, but may not be true for other access methods such as MMIO. Add a flag to struct mon_evt to indicate if the event can be read on any CPU. Architecture uses resctrl_enable_mon_event() to enable an event and set the flag appropriately. Bypass all the smp_call*() code for events that can be read on any CPU and call mon_event_count() directly from mon_event_read(). Add a test for events that can be read from any domain to skip checks in __mon_event_count() that the read is being done from a CPU in the correct domain or cache scope. Signed-off-by: Tony Luck --- include/linux/resctrl.h | 2 +- fs/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/core.c | 6 ++-- fs/resctrl/ctrlmondata.c | 7 +++- fs/resctrl/monitor.c | 53 ++++++++++++++++++++++-------- 5 files changed, 51 insertions(+), 19 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 5788e1970d8c..17a21f193a3d 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -379,7 +379,7 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); =20 -void resctrl_enable_mon_event(enum resctrl_event_id eventid); +void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu); =20 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); =20 diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index eb45cf746c5c..45a81be7f241 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struc= t fs_context *fc) * @rid: resource id for this event * @name: name of the event * @configurable: true if the event is configurable + * @any_cpu: true if the event can be read from any CPU * @enabled: true if the event is enabled */ struct mon_evt { @@ -64,6 +65,7 @@ struct mon_evt { enum resctrl_res_level rid; char *name; bool configurable; + bool any_cpu; bool enabled; }; =20 diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index fe8af1c69c24..a1c1d6b9e64a 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -888,15 +888,15 @@ static __init bool get_rdt_mon_resources(void) bool ret =3D false; =20 if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { - resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false); ret =3D true; } =20 diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index a99903ac5d27..2e65fddc3408 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -569,6 +569,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_r= esource *r, return; } =20 + if (evt->any_cpu) { + mon_event_count(rr); + goto out_ctx_free; + } + cpu =3D cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU); =20 /* @@ -581,7 +586,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_re= source *r, smp_call_function_any(cpumask, mon_event_count, rr, 1); else smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); - +out_ctx_free: resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx); } =20 diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index c3f697da612b..d6585f7d1c9e 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -356,15 +356,47 @@ static struct mbm_state *get_mbm_state(struct rdt_l3_= mon_domain *d, u32 closid, return state ? &state[idx] : NULL; } =20 +/* + * Called from preemptible context via a direct call of mon_event_count() = for + * events that can be read on any CPU. + * Called from preemptible but non-migratable process context (mon_event_c= ount() + * via smp_call_on_cpu()) OR non-preemptible context (mon_event_count() via + * smp_call_function_any()) for events that need to be read on a specific = CPU. + */ +static bool cpu_on_correct_domain(struct rmid_read *rr) +{ + struct cacheinfo *ci; + int cpu; + + /* Any CPU is OK for this event */ + if (rr->evt->any_cpu) + return true; + + cpu =3D smp_processor_id(); + + /* Single domain. Must be on a CPU in that domain. */ + if (rr->hdr) + return cpumask_test_cpu(cpu, &rr->hdr->cpu_mask); + + if (WARN_ON_ONCE(rr->r->rid !=3D RDT_RESOURCE_L3)) + return -EINVAL; + + /* Summing domains that share a cache, must be on a CPU for that cache. */ + ci =3D get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + + return ci && ci->id =3D=3D rr->ci_id; +} + static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { - int cpu =3D smp_processor_id(); struct rdt_l3_mon_domain *d; - struct cacheinfo *ci; struct mbm_state *m; int err, ret; u64 tval =3D 0; =20 + if (!cpu_on_correct_domain(rr)) + return -EINVAL; + if (rr->r->rid =3D=3D RDT_RESOURCE_L3 && rr->first) { if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3= )) return -EINVAL; @@ -377,9 +409,7 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) } =20 if (rr->hdr) { - /* Reading a single domain, must be on a CPU in that domain. */ - if (!cpumask_test_cpu(cpu, &rr->hdr->cpu_mask)) - return -EINVAL; + /* Single domain. */ rr->err =3D resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, rr->evt->evtid, &tval, rr->arch_mon_ctx); if (rr->err) @@ -390,15 +420,9 @@ static int __mon_event_count(u32 closid, u32 rmid, str= uct rmid_read *rr) return 0; } =20 - if (WARN_ON_ONCE(rr->r->rid !=3D RDT_RESOURCE_L3)) - return -EINVAL; - - /* Summing domains that share a cache, must be on a CPU for that cache. */ - ci =3D get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci || ci->id !=3D rr->ci_id) - return -EINVAL; - /* + * Sum across multiple domains. + * * Legacy files must report the sum of an event across all * domains that share the same L3 cache instance. * Report success if a read from any domain succeeds, -EINVAL @@ -877,7 +901,7 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] =3D { }, }; =20 -void resctrl_enable_mon_event(enum resctrl_event_id eventid) +void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu) { if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >=3D QOS_NUM_EVENTS= )) return; @@ -886,6 +910,7 @@ void resctrl_enable_mon_event(enum resctrl_event_id eve= ntid) return; } =20 + mon_event_all[eventid].any_cpu =3D any_cpu; mon_event_all[eventid].enabled =3D true; } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 C1A232E2DEC for ; Mon, 11 Aug 2025 18:17:41 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936264; cv=none; b=TlY4Psoe1C6if7MMolQ6ti/y48pXDieR/roixWmOby1ZDN/WPYXuhg7uFd6x0f9/mG8UKtlfLpppyEGgfbK3i8NvxPdiZ1dsWkxQuSfxxG3DHd/wvkVU8DZIUVdgVMZufmONTaj58Q9kXvW3HKHH5WGLQj07O5hhDAXw1J/6LwY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936264; c=relaxed/simple; bh=j3r0LJBXKjWB9brfBN1NF7bKdy1qke64ilQrt0kZVM8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=OBwjtIlhKN6VVZD3rtuL0UIAwdeB0i0ZxEKQOK/e58DzZYY8AdWvRQnoYXAU8/6Xd6I0QIr8Lm1FtRyg/zNF1xEODaz+uNnJw2He5CUG5Bb+NMHnxEInhzyrFGPASx96cPIK7mRukXZ7fWsnxcM2xcgzUorEOOoiNps0WdYG4LU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=kGB9yhAH; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="kGB9yhAH" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936262; x=1786472262; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=j3r0LJBXKjWB9brfBN1NF7bKdy1qke64ilQrt0kZVM8=; b=kGB9yhAHeL9KBBCW33ZHZSKo+UoqAixTH0nGuCr/zL6+NqPxqLU3ceCI HwUYaf6QIalvhzrwG5XsyEHIWgPoil3lMkJrGBzYmA4SGt+8ZRnReW+m8 gfclw3zpOvExOO8svsDNyS++moxPg78XVuJX7xJOE+QTipOeKaVxh9kOn MRSvnL8yZwTo8Oj2RRDWvJwIIwm3SAbHhoKJIMCZM1gUUFp2feC6dhVyf +08c0C7dYGgTzra1BLeXflqCw/fdiZJPjsEzcZLrPgnb1qToeX3fy+nPB aP8LNkRG4TrEcGb50PBCrX1f9WCfXqEYsgE497bEKK5nSA9TfzG65+QWq Q==; X-CSE-ConnectionGUID: uXhbL5egSni65sGRAG21vQ== X-CSE-MsgGUID: SNUkAu1oSeCWanIE1fq9yA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277423" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277423" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: OF4GfwsGRvSK2xl7IcB7jA== X-CSE-MsgGUID: j08/fp/2RdifE0dZHX+MBA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825657" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:24 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 14/32] x86,fs/resctrl: Support binary fixed point event counters Date: Mon, 11 Aug 2025 11:16:48 -0700 Message-ID: <20250811181709.6241-15-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" resctrl assumes that all monitor events can be displayed as unsigned decimal integers. Hardware architecture counters may provide some telemetry events with greater precision where the event is not a simple count, but is a measurement of some sort (e.g. Joules for energy consumed). Add a new argument to resctrl_enable_mon_event() for architecture code to inform the file system that the value for a counter is a fixed-point value with a specific number of binary places. Only allow architecture to use floating point format on events that it marked with mon_evt::is_floating_point. Display fixed point values with values rounded to an appropriate number of decimal places for the precision of the number of binary places provided. Add one extra decimal place for every three additional binary places, except for low precision binary values where exact representation is possible: 1 binary place is 0.0 or 0.5. =3D> 1 decimal place 2 binary places is 0.0, 0.25, 0.5, 0.75 =3D> 2 decimal places 3 binary places is 0.0, 0.125, etc. =3D> 3 decimal places Signed-off-by: Tony Luck --- include/linux/resctrl.h | 5 +- fs/resctrl/internal.h | 5 ++ arch/x86/kernel/cpu/resctrl/core.c | 6 +-- fs/resctrl/ctrlmondata.c | 84 ++++++++++++++++++++++++++++++ fs/resctrl/monitor.c | 10 +++- 5 files changed, 104 insertions(+), 6 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 17a21f193a3d..38809c497b44 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -379,7 +379,10 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r= ); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); =20 -void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu); +#define MAX_BINARY_BITS 27 + +void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits); =20 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); =20 diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 45a81be7f241..00cd93661650 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -58,6 +58,9 @@ static inline struct rdt_fs_context *rdt_fc2context(struc= t fs_context *fc) * @name: name of the event * @configurable: true if the event is configurable * @any_cpu: true if the event can be read from any CPU + * @is_floating_point: event values are displayed in floating point format + * @binary_bits: number of fixed-point binary bits from architecture, + * only valid if @is_floating_point is true * @enabled: true if the event is enabled */ struct mon_evt { @@ -66,6 +69,8 @@ struct mon_evt { char *name; bool configurable; bool any_cpu; + bool is_floating_point; + unsigned int binary_bits; bool enabled; }; =20 diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index a1c1d6b9e64a..f6fda15da9c1 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -888,15 +888,15 @@ static __init bool get_rdt_mon_resources(void) bool ret =3D false; =20 if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { - resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false); + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false); + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false); + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0); ret =3D true; } =20 diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index 2e65fddc3408..458388378c8a 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -17,6 +17,7 @@ =20 #include #include +#include #include #include #include @@ -590,6 +591,87 @@ void mon_event_read(struct rmid_read *rr, struct rdt_r= esource *r, resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx); } =20 +/* + * Decimal place precision to use for each number of fixed-point + * binary bits. + */ +static unsigned int decplaces[MAX_BINARY_BITS + 1] =3D { + [1] =3D 1, + [2] =3D 2, + [3] =3D 3, + [4] =3D 3, + [5] =3D 3, + [6] =3D 3, + [7] =3D 3, + [8] =3D 3, + [9] =3D 3, + [10] =3D 4, + [11] =3D 4, + [12] =3D 4, + [13] =3D 5, + [14] =3D 5, + [15] =3D 5, + [16] =3D 6, + [17] =3D 6, + [18] =3D 6, + [19] =3D 7, + [20] =3D 7, + [21] =3D 7, + [22] =3D 8, + [23] =3D 8, + [24] =3D 8, + [25] =3D 9, + [26] =3D 9, + [27] =3D 9 +}; + +static void print_event_value(struct seq_file *m, unsigned int binary_bits= , u64 val) +{ + unsigned long long frac; + char buf[10]; + + if (!binary_bits) { + seq_printf(m, "%llu.0\n", val); + return; + } + + /* Mask off the integer part of the fixed-point value. */ + frac =3D val & GENMASK_ULL(binary_bits, 0); + + /* + * Multiply by 10^{desired decimal places}. The integer part of + * the fixed point value is now almost what is needed. + */ + frac *=3D int_pow(10ull, decplaces[binary_bits]); + + /* + * Round to nearest by adding a value that would be a "1" in the + * binary_bits + 1 place. Integer part of fixed point value is + * now the needed value. + */ + frac +=3D 1ull << (binary_bits - 1); + + /* + * Extract the integer part of the value. This is the decimal + * representation of the original fixed-point fractional value. + */ + frac >>=3D binary_bits; + + /* + * "frac" is now in the range [0 .. 10^decplaces). I.e. string + * representation will fit into chosen number of decimal places. + */ + snprintf(buf, sizeof(buf), "%0*llu", decplaces[binary_bits], frac); + + /* Trim trailing zeroes */ + for (int i =3D decplaces[binary_bits] - 1; i > 0; i--) { + if (buf[i] !=3D '0') + break; + buf[i] =3D '\0'; + } + seq_printf(m, "%llu.%s\n", val >> binary_bits, buf); +} + int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of =3D m->private; @@ -666,6 +748,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) seq_puts(m, "Error\n"); else if (rr.err =3D=3D -EINVAL) seq_puts(m, "Unavailable\n"); + else if (evt->is_floating_point) + print_event_value(m, evt->binary_bits, rr.val); else seq_printf(m, "%llu\n", rr.val); =20 diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index d6585f7d1c9e..eeba9e1f4a34 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -901,16 +901,22 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] =3D { }, }; =20 -void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu) +void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,= unsigned int binary_bits) { - if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >=3D QOS_NUM_EVENTS= )) + if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >=3D QOS_NUM_EVENTS= || + binary_bits > MAX_BINARY_BITS)) return; if (mon_event_all[eventid].enabled) { pr_warn("Duplicate enable for event %d\n", eventid); return; } + if (binary_bits && !mon_event_all[eventid].is_floating_point) { + pr_warn("Event %d may not be floating point\n", eventid); + return; + } =20 mon_event_all[eventid].any_cpu =3D any_cpu; + mon_event_all[eventid].binary_bits =3D binary_bits; mon_event_all[eventid].enabled =3D true; } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 6F0252E2DFC for ; Mon, 11 Aug 2025 18:17:42 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936264; cv=none; b=G6NE3auQAsBq+MeksylNe2i8Pwo9tNNcXUR+Nc/CUuBCUbF1jD1tRE00XEKbRG0mETlPF7HVGPyoGUuP0cZnykdqreSf3sxvhSR3OeLckG1H6KPY8StyzvixUv2LVmax4nVq84qW8CGJwrbFOmXybzpTy6PQ9LuT7liLq1PCNFU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936264; c=relaxed/simple; bh=tiN+hbV8N2y0qYnYfboP2LM2eI9E8FHvJartB9jdL6E=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=TvBdYQPRKvnRfG82BcM5RvFkRHRL6PQmNdMVLRuOk0oHqjOnmH1r67Rsbnug0aAJpj7ZUUySTGFjM5n6VCTfYxrj2EabBTdCT6qWoq0nNcyPMIlnqWivKI02cDN63FUnmPh9yhtKRo+EaU+S7EgXE4nps+LAgHTYTWxvHIGXPJk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=M63EKbeM; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="M63EKbeM" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936263; x=1786472263; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=tiN+hbV8N2y0qYnYfboP2LM2eI9E8FHvJartB9jdL6E=; b=M63EKbeMhYZolHgLT6Cfl4xWvCfLLDSQPZ8rVRFv7maSMI/rLckFV5ZG 2lqgm0OOPQHGd/YwnENFrv1xbAJoYmoAQzr4b6ydVm57lBrLscqLxmEpM h4fQDVXga2kk/gpbFMBW7UHZr/Y/sOJh51lg0n8qkpIR84Pr3GaNE3rHy P/xBmaG1qPJOQNpNSerxZ3rguFAzVAXRyj4+bIJ/NGGmyCEHdzL9AP+9X CruAw1VoNcObsrYMc+HqK7POA9yJwOk5OK+n21wNF3KzvXV04RR/ZOwET 0JSURc/uolmupPKB5kiOxr1eBElkJloo4kuKpLuS2IHyftz98rqwTvv5s Q==; X-CSE-ConnectionGUID: 9mjhvPibTtu+VwTp7vqAlw== X-CSE-MsgGUID: NDiGjEuEQB6agu1HRGq8JQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277431" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277431" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: OoFydq4GRMuuVhIE5KtHQA== X-CSE-MsgGUID: hzh363I5Rlm/p216ei15RA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825661" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:24 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 15/32] x86,fs/resctrl: Add an architectural hook called for each mount Date: Mon, 11 Aug 2025 11:16:49 -0700 Message-ID: <20250811181709.6241-16-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Enumeration of Intel telemetry events is an asyncronnous process involving several mutually dependent drivers added as auxiliary devices during the device_initcall() phase of Linux boot. The process completes after the probe functions for these drivers are called. But this happens after resctrl_arch_late_init() is executed. Tracing the enumeration process shows that it does complete a full seven seconds before the earliest possible mount of the resctrl file system (when included in /etc/fstab for automatic mount by systemd). Add a hook at the beginning of the mount code that will be used to check for telemetry events and initialize if any are found. Call the hook on every attempted mount. But expectations are that most actions (like enumeration) will only need to be performed on the first call. The call is made with no locks held. Architecture code is responsible for any required locking. Signed-off-by: Tony Luck --- include/linux/resctrl.h | 6 ++++++ arch/x86/kernel/cpu/resctrl/core.c | 9 +++++++++ fs/resctrl/rdtgroup.c | 2 ++ 3 files changed, 17 insertions(+) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 38809c497b44..19409227ccd0 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -461,6 +461,12 @@ void resctrl_offline_mon_domain(struct rdt_resource *r= , struct rdt_domain_hdr *h void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); =20 +/* + * Architecture hook called at beginning of each file system mount attempt. + * No locks are held. + */ +void resctrl_arch_pre_mount(void); + /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rm= id * for this resource and domain. diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index f6fda15da9c1..480e381d416e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -718,6 +718,15 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) return 0; } =20 +void resctrl_arch_pre_mount(void) +{ + static atomic_t only_once =3D ATOMIC_INIT(0); + int old =3D 0; + + if (!atomic_try_cmpxchg(&only_once, &old, 1)) + return; +} + enum { RDT_FLAG_CMT, RDT_FLAG_MBM_TOTAL, diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index b917d48a806a..31f9425783ef 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -2585,6 +2585,8 @@ static int rdt_get_tree(struct fs_context *fc) struct rdt_resource *r; int ret; =20 + resctrl_arch_pre_mount(); + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 D1DDE2E2DD5 for ; Mon, 11 Aug 2025 18:17:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936263; cv=none; b=RKnv3eBXYvydiY+RVBUq5fEDFY4RrVDYfynlCp+4u6GEyTkWCYdvOUHPcDVJDGb0LIQR3MN5ClBbOTANueLYB4VnAbMvs/8fUgeO7qcba/JAtX6tvlAFNnRS1ql9bAv7PC55aqOR68XAR1CarBKFuH9PwwVhmQMNZbz9dfcnLsk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936263; c=relaxed/simple; bh=H/CL40qmwKzhEkdxKODAv/wPY/R63z2nHv7mHfvz3BE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=AclWWiX7eChRKuFkV43s3r0x+FkGf4TRp5xi3VbF3LywdWO5blKKlgrWLe6QD80fwNiE1E7opMQ/R4mYjeSwFo5NMfvBxbHldO+GdPunfu7L7hrP/LC1ZZSZiSXyinxphC8CEI+ckV2YT9Tnkxp0CydVPKhXCL+ZyWPNghR8wkM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=I4S6b2Xb; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="I4S6b2Xb" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936262; x=1786472262; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=H/CL40qmwKzhEkdxKODAv/wPY/R63z2nHv7mHfvz3BE=; b=I4S6b2XbaPMijEFsZIfQ2PXjAlZKV17A4ZGs/eR2gLn1CJpC0HiXyGbO EHZFj8BjM5rZBdE1ThhvuPKpkgIEfGsWnz0OBK7tSQk6RAe81t/vxApJS leNdsn/menM8De/0cHfYFITPjZ0ZHBGVlGSFXGHAIdfbUugJV6lkZOmYY Zz4sz2oWxLif+1md6TsS2LRFVfYXiOZfHdqfa9xZR7yrhE9lQiNnFuCQf L589YJnG85PAD1roj90tqnWXVFqpl0fd6Tm6nyYNOxqRX0Q7f5EoyO/H0 1ymWoaKXJvkQ+sJ41E96zU9AIv4/JIr17w6JU1dskVVgVoqv4HQaiox8j w==; X-CSE-ConnectionGUID: LywiYNL/RI6b6UJHqaazOQ== X-CSE-MsgGUID: rQ6yctY8TBu0PHTuPOuQlg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277436" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277436" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: KeR5gTGyTWGvigyQw77MXQ== X-CSE-MsgGUID: Ru68FjGoRr2iKKgRIeOpbQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825665" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:24 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 16/32] x86,fs/resctrl: Add and initialize rdt_resource for package scope monitor Date: Mon, 11 Aug 2025 11:16:50 -0700 Message-ID: <20250811181709.6241-17-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Add a new PERF_PKG resource and introduce package level scope for monitoring telemetry events so that CPU hotplug notifiers can build domains at the package granularity. Use the physical package ID available via topology_physical_package_id() to identify the monitoring domains with package level scope. This enables user space to use: /sys/devices/system/cpu/cpuX/topology/physical_package_id to identify the monitoring domain a CPU is associated with. Signed-off-by: Tony Luck Reviewed-by: Reinette Chatre --- include/linux/resctrl.h | 2 ++ fs/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/core.c | 10 ++++++++++ fs/resctrl/rdtgroup.c | 2 ++ 4 files changed, 16 insertions(+) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 19409227ccd0..61c73772a177 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -53,6 +53,7 @@ enum resctrl_res_level { RDT_RESOURCE_L2, RDT_RESOURCE_MBA, RDT_RESOURCE_SMBA, + RDT_RESOURCE_PERF_PKG, =20 /* Must be the last */ RDT_NUM_RESOURCES, @@ -252,6 +253,7 @@ enum resctrl_scope { RESCTRL_L2_CACHE =3D 2, RESCTRL_L3_CACHE =3D 3, RESCTRL_L3_NODE, + RESCTRL_PACKAGE, }; =20 /** diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 00cd93661650..b16e2fc42b3f 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -240,6 +240,8 @@ struct rdtgroup { =20 #define RFTYPE_DEBUG BIT(10) =20 +#define RFTYPE_RES_PERF_PKG BIT(11) + #define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) =20 #define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 480e381d416e..ec29b7f250ab 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -100,6 +100,14 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOU= RCES] =3D { .schema_fmt =3D RESCTRL_SCHEMA_RANGE, }, }, + [RDT_RESOURCE_PERF_PKG] =3D + { + .r_resctrl =3D { + .name =3D "PERF_PKG", + .mon_scope =3D RESCTRL_PACKAGE, + .mon_domains =3D mon_domain_init(RDT_RESOURCE_PERF_PKG), + }, + }, }; =20 u32 resctrl_arch_system_num_rmid_idx(void) @@ -433,6 +441,8 @@ static int get_domain_id_from_scope(int cpu, enum resct= rl_scope scope) return get_cpu_cacheinfo_id(cpu, scope); case RESCTRL_L3_NODE: return cpu_to_node(cpu); + case RESCTRL_PACKAGE: + return topology_physical_package_id(cpu); default: break; } diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 31f9425783ef..26928ad0a35a 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -2195,6 +2195,8 @@ static unsigned long fflags_from_resource(struct rdt_= resource *r) case RDT_RESOURCE_MBA: case RDT_RESOURCE_SMBA: return RFTYPE_RES_MB; + case RDT_RESOURCE_PERF_PKG: + return RFTYPE_RES_PERF_PKG; } =20 return WARN_ON_ONCE(1); --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 B023F2E2EE5 for ; Mon, 11 Aug 2025 18:17:42 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936265; cv=none; b=N/pU9pHnZgYd7xLmfeRwPQmp31Qs+m2W6Rx8igIIAb5ulSNJi4AHuyS1gxdkS8062cY5vi63UJ9fpIBg/+kyrPaV6KnaZBCaK6QoiQwg8QdIG4Wzn7SEksMyTksa503fZlYsINWR5q5eZm1dXv2Ws5EmKCVfGKS/Kzjd3fkySBc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936265; c=relaxed/simple; bh=vgJ9zQWK+5JzRjVDNt7iEf0tUgKpQctOz1vVeDHoBlQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=JS1Qz4dy0P7fhDjkCRR3wXZkpT0UhHzpQAOGekHOrXqhXOEefC/U9x7o2uVHwZA2Ze03t8zfZHpzzTtkKedNdPNh1+5UFHknBLGFxLkWaiWZN6NsF9k5db78xjU+jw5OAsTn/FfphSdw90yvyC9B8tm4AgUcyO1lMCPMP8qLKDc= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=ltjSF79j; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="ltjSF79j" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936263; x=1786472263; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=vgJ9zQWK+5JzRjVDNt7iEf0tUgKpQctOz1vVeDHoBlQ=; b=ltjSF79jWG6ndu4VimjJPNpDVbU4xjGAyjkt3wFZCLg2kdwrrhvAy7Px KIDZ8nc0FW4GK/gE73k/S1gbVJZogpCvpRVFQ54dXR5ea7jhDJl1aUOZb kuHgjpBCKTC+qptj+iNR38RQoYbgjHOTAJ6JFmxp4oLgutAb+SpAvvYoD OPY2PLR0Ohr13mk9TpDneeaFeyjyWnd3JHrOO8XF5f5SlQ8Uvi3y7qxW0 ykhmYwyu2ehd5qxEUUKL9uxAzfGaqc3W98xK/rxDs19UDD7Gq9ELRViaU hgFtJQ3j/WuzYdM/JgKJOtk/jy7Tpmtg3xsmrdBthO9Vx+aWs/2rH5R52 w==; X-CSE-ConnectionGUID: R4EySxYBTZ+mLfc0Ip8ZfQ== X-CSE-MsgGUID: cmPIwk51SmqDQXGpG2zaqw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277447" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277447" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: bvVhzxW4SLGICtWC6kIMHA== X-CSE-MsgGUID: lKXV9ksSQue+zWIHi5Vbjw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825668" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 17/32] x86/resctrl: Discover hardware telemetry events Date: Mon, 11 Aug 2025 11:16:51 -0700 Message-ID: <20250811181709.6241-18-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Data for telemetry events is collected by each CPU and sent to a nearby telemetry event aggregator either when the value of IA32_PQR_ASSOC.RMID is changed, or when two milliseconds have elapsed. The telemetry event aggregators maintain per-RMID per-event counts of the total seen for all the CPUs. There may be more than one telemetry event aggregator per package. Each telemetry event aggregator is responsible for a specific group of events. E.g. on the Intel Clearwater Forest CPU there are two types of aggregators. One type tracks a pair of energy related events. The other type tracks a subset of "perf" type events. The event counts are made available to Linux in a region of MMIO space for each aggregator. All details about the layout of counters in each aggregator MMIO region are described in XML files published by Intel and mad available in a GitHub repository: https://github.com/intel/Intel-PMT. The key to matching a specific telemetry aggregator to the XML file that describes the MMIO layout is a 32-bit value. The Linux telemetry subsystem refers to this as a "guid" while the XML files call it a "uniqueid". Each XML file provides the following information: 1) Which telemetry events are included in the group. 2) The order in which the event counters appear for each RMID. 3) The value type of each event counter (integer or fixed-point). 4) The number of RMIDs supported. 5) Which additional aggregator status registers are included. 6) The total size of the MMIO region for this aggregator. Enumeration of support for telemetry events is done by the INTEL_PMT_DISCOVERY driver (a subcomponent of the INTEL_PMT_TELEMETRY driver). This driver provides intel_pmt_get_regions_by_feature() to list all available telemetry event aggregators. The list includes the "guid", the base address in MMIO space for the region where the event counters are exposed, and the package id where the CPUs that report to this aggregator are located. Add a new Kconfig option CONFIG_X86_CPU_RESCTRL_INTEL_AET for the Intel specific parts of telemetry code. This depends on the INTEL_PMT_TELEMETRY and INTEL_TPMI drivers being built-in to the kernel for enumeration of telemetry features. Call intel_pmt_get_regions_by_feature() for each pmt_feature_id that indicates per-RMID telemetry. Save the returned pmt_feature_group pointers with guids that are known to resctrl for use at run time. Those pointers will be returned to the INTEL_PMT_TELEMETRY subsystem at resctrl_arch_exit() time. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/internal.h | 8 ++ arch/x86/kernel/cpu/resctrl/core.c | 5 + arch/x86/kernel/cpu/resctrl/intel_aet.c | 120 ++++++++++++++++++++++++ arch/x86/Kconfig | 13 +++ arch/x86/kernel/cpu/resctrl/Makefile | 1 + 5 files changed, 147 insertions(+) create mode 100644 arch/x86/kernel/cpu/resctrl/intel_aet.c diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index 684a1b830ced..710493ec6548 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -169,4 +169,12 @@ void __init intel_rdt_mbm_apply_quirk(void); =20 void rdt_domain_reconfigure_cdp(struct rdt_resource *r); =20 +#ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET +bool intel_aet_get_events(void); +void __exit intel_aet_exit(void); +#else +static inline bool intel_aet_get_events(void) { return false; } +static inline void __exit intel_aet_exit(void) { } +#endif + #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index ec29b7f250ab..58756d216fe8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -735,6 +735,9 @@ void resctrl_arch_pre_mount(void) =20 if (!atomic_try_cmpxchg(&only_once, &old, 1)) return; + + if (!intel_aet_get_events()) + return; } =20 enum { @@ -1087,6 +1090,8 @@ late_initcall(resctrl_arch_late_init); =20 static void __exit resctrl_arch_exit(void) { + intel_aet_exit(); + cpuhp_remove_state(rdt_online); =20 resctrl_exit(); diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c new file mode 100644 index 000000000000..25075f369148 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Intel Application Energy Telemetry + * + * Copyright (C) 2025 Intel Corporation + * + * Author: + * Tony Luck + */ + +#define pr_fmt(fmt) "resctrl: " fmt + +#include +#include +#include +#include + +#include "internal.h" + +/** + * struct event_group - All information about a group of telemetry events. + * @pfg: Points to the aggregated telemetry space information + * within the OOBMSM driver that contains data for all + * telemetry regions. + * @guid: Unique number per XML description file. + */ +struct event_group { + /* Data fields for additional structures to manage this group. */ + struct pmt_feature_group *pfg; + + /* Remaining fields initialized from XML file. */ + u32 guid; +}; + +/* + * Link: https://github.com/intel/Intel-PMT + * File: xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml + */ +static struct event_group energy_0x26696143 =3D { + .guid =3D 0x26696143, +}; + +/* + * Link: https://github.com/intel/Intel-PMT + * File: xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml + */ +static struct event_group perf_0x26557651 =3D { + .guid =3D 0x26557651, +}; + +static struct event_group *known_energy_event_groups[] =3D { + &energy_0x26696143, +}; + +static struct event_group *known_perf_event_groups[] =3D { + &perf_0x26557651, +}; + +/* Stub for now */ +static int discover_events(struct event_group *e, struct pmt_feature_group= *p) +{ + return -EINVAL; +} + +DEFINE_FREE(intel_pmt_put_feature_group, struct pmt_feature_group *, + if (!IS_ERR_OR_NULL(_T)) + intel_pmt_put_feature_group(_T)) + +/* + * Make a request to the INTEL_PMT_DISCOVERY driver for the + * pmt_feature_group for a specific feature. If there is + * one the returned structure has an array of telemetry_region + * structures. Each describes one telemetry aggregator. + * Try to use every telemetry aggregator with a known guid. + */ +static bool get_pmt_feature(enum pmt_feature_id feature, struct event_grou= p **evgs, + unsigned int num_evg) +{ + struct pmt_feature_group *p __free(intel_pmt_put_feature_group) =3D NULL; + struct event_group **peg; + int ret; + + p =3D intel_pmt_get_regions_by_feature(feature); + + if (IS_ERR_OR_NULL(p)) + return false; + + for (peg =3D evgs; peg < &evgs[num_evg]; peg++) { + ret =3D discover_events(*peg, p); + if (!ret) { + (*peg)->pfg =3D no_free_ptr(p); + return true; + } + } + + return false; +} + +/* + * Ask OOBMSM discovery driver for all the RMID based telemetry groups + * that it supports. + */ +bool intel_aet_get_events(void) +{ + bool ret1, ret2; + + ret1 =3D get_pmt_feature(FEATURE_PER_RMID_ENERGY_TELEM, + known_energy_event_groups, + ARRAY_SIZE(known_energy_event_groups)); + ret2 =3D get_pmt_feature(FEATURE_PER_RMID_PERF_TELEM, + known_perf_event_groups, + ARRAY_SIZE(known_perf_event_groups)); + + return ret1 || ret2; +} + +void __exit intel_aet_exit(void) +{ +} diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58d890fe2100..56f0ff94c430 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -525,6 +525,19 @@ config X86_CPU_RESCTRL =20 Say N if unsure. =20 +config X86_CPU_RESCTRL_INTEL_AET + bool "Intel Application Energy Telemetry" if INTEL_PMT_TELEMETRY=3Dy && I= NTEL_TPMI=3Dy + depends on X86_CPU_RESCTRL && CPU_SUP_INTEL + help + Enable per-RMID telemetry events in resctrl + + Intel feature that collects per-RMID execution data + about energy consumption, measure of frequency independent + activity and other performance metrics. Data is aggregated + per package. + + Say N if unsure. + config X86_FRED bool "Flexible Return and Event Delivery" depends on X86_64 diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/res= ctrl/Makefile index d8a04b195da2..273ddfa30836 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_X86_CPU_RESCTRL) +=3D core.o rdtgroup.o monitor.o obj-$(CONFIG_X86_CPU_RESCTRL) +=3D ctrlmondata.o +obj-$(CONFIG_X86_CPU_RESCTRL_INTEL_AET) +=3D intel_aet.o obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) +=3D pseudo_lock.o =20 # To allow define_trace.h's recursive include: --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 7C79F2E3394 for ; Mon, 11 Aug 2025 18:17:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936266; cv=none; b=ltf1Cy9f7Jq5L8O9yVyRCmlQ1NllQvRw5VklWXRxMO6j7AR27E2cH+CoZjqVu6Thzb3dEIOm7ra3hQ0tEWrBTgbsm7uXocvH4gWCl67aTNWRnUItYzdIwrQFkeo8JBPhW88kZuoGC6vrfaRxu2fn03XTg6Tj0QfYGIY5zdfxkrY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936266; c=relaxed/simple; bh=vPpRkpA1kWmXaq2JdSwo7aDBLrJCy4yxm2yZynCIedU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=INpArtrXRildj6gDI8IfK1c65Sy5EwL5cM+agRa1WOevRKNKM6yf9uw3JMAs4VCqi0PAdMuToDUb1EQVNofx1/wBodnQ4TPcrVXarnYpQCh187UhoOsCLDAu1OlWn+dwVkaLgxk/h5z6GX+7Wg+qnUhATj/BH4vMEqXUaYIExmQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Ypuhw+x/; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Ypuhw+x/" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936265; x=1786472265; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=vPpRkpA1kWmXaq2JdSwo7aDBLrJCy4yxm2yZynCIedU=; b=Ypuhw+x/eUD5y2MZuIN6q/fMvF3IXtGQ4KRON+vnqTRZi6FdjDIlBKJo b5scKLB2xfWLBbDPPOvc8f7G4EOFEXu8u3Z8jDdG0HNdpV9ukINgOraFs Ri1FRGzNoYaORL+79wC6M/5FUSbdTea12i14sagUrkpA8/IIU82lUaMtF gpC33MHHt8qzGBhhD6YMDDuSNMGabDJFyotRs2+WIe5OzMUrCcUyv/Dxx G6q6d4Ox8E9F7cG3jHgKfJs/OKW5CVA0seNbiwonqk45HKHAe/8y+aYEC +ZPdvpvbSPGtN5dWHvCGj4M5XfDDFNBxp7XmV6p9gOyQK6O3aA97Cw1QG A==; X-CSE-ConnectionGUID: cuQH2q9bS6u102C2gt9AKw== X-CSE-MsgGUID: ss/fp2RKS56irIkRa73P4A== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277448" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277448" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: nNl86vasQSiq0P/dhuCtvg== X-CSE-MsgGUID: SA0v9RB2Tm6i41lEr3y7Tg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825672" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 18/32] x86/resctrl: Count valid telemetry aggregators per package Date: Mon, 11 Aug 2025 11:16:52 -0700 Message-ID: <20250811181709.6241-19-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" There may be multiple telemetry aggregators per package, each enumerated by a telemetry region structure in the feature group. Linux can only use telemetry regions when all of the following conditions are met: 1) The "guid" of the region is known to Linux 2) The package id for the region is valid (less than topology_max_packages()) 3) The size of the MMIO region exactly matches the expected size for this "guid" (as implied from description in the XML file for this "guid"). Scan the array of telemetry region structures and count how many are usable in each package in preparation to allocate structures to save the MMIO addresses for each in a convenient format for use when reading event counters. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/intel_aet.c | 56 ++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 25075f369148..09043d36e08c 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -15,6 +15,7 @@ #include #include #include +#include =20 #include "internal.h" =20 @@ -24,6 +25,7 @@ * within the OOBMSM driver that contains data for all * telemetry regions. * @guid: Unique number per XML description file. + * @mmio_size: Number of bytes of MMIO registers for this group. */ struct event_group { /* Data fields for additional structures to manage this group. */ @@ -31,14 +33,19 @@ struct event_group { =20 /* Remaining fields initialized from XML file. */ u32 guid; + size_t mmio_size; }; =20 +#define XML_MMIO_SIZE(num_rmids, num_events, num_extra_status) \ + (((num_rmids) * (num_events) + (num_extra_status)) * sizeof(u64)) + /* * Link: https://github.com/intel/Intel-PMT * File: xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml */ static struct event_group energy_0x26696143 =3D { .guid =3D 0x26696143, + .mmio_size =3D XML_MMIO_SIZE(576, 2, 3), }; =20 /* @@ -47,6 +54,7 @@ static struct event_group energy_0x26696143 =3D { */ static struct event_group perf_0x26557651 =3D { .guid =3D 0x26557651, + .mmio_size =3D XML_MMIO_SIZE(576, 7, 3), }; =20 static struct event_group *known_energy_event_groups[] =3D { @@ -57,10 +65,54 @@ static struct event_group *known_perf_event_groups[] = =3D { &perf_0x26557651, }; =20 -/* Stub for now */ +static bool skip_this_region(struct telemetry_region *tr, struct event_gro= up *e) +{ + if (tr->guid !=3D e->guid) + return true; + if (tr->plat_info.package_id >=3D topology_max_packages()) { + pr_warn_once("Bad package %d in guid 0x%x\n", tr->plat_info.package_id, + tr->guid); + return true; + } + if (tr->size !=3D e->mmio_size) { + pr_warn_once("MMIO space %zu wrong size for guid 0x%x\n", tr->size, e->g= uid); + return true; + } + + return false; +} + +/* + * Discover events from one pmt_feature_group. + * 1) Count how many usable telemetry regions per package. + * 2...) To be continued. + */ static int discover_events(struct event_group *e, struct pmt_feature_group= *p) { - return -EINVAL; + int *pkgcounts __free(kfree) =3D NULL; + struct telemetry_region *tr; + int num_pkgs; + + num_pkgs =3D topology_max_packages(); + + /* Get per-package counts of telemetry regions for this event group */ + for (int i =3D 0; i < p->count; i++) { + tr =3D &p->regions[i]; + if (skip_this_region(tr, e)) + continue; + + if (!pkgcounts) { + pkgcounts =3D kcalloc(num_pkgs, sizeof(*pkgcounts), GFP_KERNEL); + if (!pkgcounts) + return -ENOMEM; + } + pkgcounts[tr->plat_info.package_id]++; + } + + if (!pkgcounts) + return -ENODEV; + + return 0; } =20 DEFINE_FREE(intel_pmt_put_feature_group, struct pmt_feature_group *, --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 627952E2838 for ; Mon, 11 Aug 2025 18:17:43 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936265; cv=none; b=kedzdCzCYug7I/mNJq4McVsGsv2X7FFwAJJVLoAScxVh2R1VAKVLmrI9Tgdl14I7gIJwXiIr+5+p4SxlT26ST6fUyjlnV7QVMoOW3WzKamzIuokHGp9vdVzoZOgEd+dY+kFCp4tphcsUrjNKVbE7MmgUIRCsl1zHtGyMIxnykP4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936265; c=relaxed/simple; bh=ISWJubg+Z8gzEXFfg1gd+vXjO/Geh6wfJL0ida/t5SQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Q4M7gpuDdCMIvCuAiEv0CRjIx/q2Frjk6fMNcVMBl9uiKMf/q4aKJwQj6hEx9wu+3CqXeGy5JWZqXu0P2Eg2XK8jCsMl++Iq5PxfrGyDvt/G1FsKDGt000WTV2SbV4RZRgFStYYoLCzRP7eJPRafi4Esum9UTv7yhc7kZeXQXdk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=KQML5QfW; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="KQML5QfW" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936264; x=1786472264; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=ISWJubg+Z8gzEXFfg1gd+vXjO/Geh6wfJL0ida/t5SQ=; b=KQML5QfW7Qj+fMHyLrgWaZqj+pub+XzcxHer1nNlmZmIa28QpUHc6qrM bDHWNVbxL3o/QN4IgCRt5sQNpP4kzixHuZ7EZm1WFMD735wdY2YnoAbgX EonY2EyaDyR1cBG3K/BL/bLwQRCJ9VfqO1OqIpEVcfkI3Mwo9dEMHF333 OQCuIAxhyO4t3EpjNFPZ/nAOs7qjT6sKcKqVKernZS8BV2gMGaxolneZc iyNNsoPcGHrCzVZ7yeBvmvLIfhZXI09goHWEDlMbX9/w4vKOhomUKFW/Q GNNCdLlXyfGQ4o0bKkL2sXbcPcK8Z+ZDz4Hy1UryXgW5RDXkkM6fWk4bk A==; X-CSE-ConnectionGUID: mgJ9BH0ZRNuvDJRQc0DJeg== X-CSE-MsgGUID: p8Tef+/CSCKdSuy/YHDH1g== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277456" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277456" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: aHeaqpjtRgK24ypppLxpQQ== X-CSE-MsgGUID: 6nG6ElQWSgOwsbpXVNCFDQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825675" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 19/32] x86/resctrl: Complete telemetry event enumeration Date: Mon, 11 Aug 2025 11:16:53 -0700 Message-ID: <20250811181709.6241-20-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Counters for telemetry events are in MMIO space. Each telemetry_region structure returned in the pmt_feature_group returned from OOBMSM contains the base MMIO address for the counters. There may be multiple aggregators per package. Scan all the telemetry_region structures again and save the number of regions together with a flex array of the MMIO addresses for each region indexed by package id. Completed structure for each event group looks like this: +---------------------+---------------------+ pkginfo** -->|pkginfo[package ID 0]|pkginfo[package ID 1]| +---------------------+---------------------+ | | v v +--------------------+ +--------------------+ |struct pkg_mmio_info| |struct pkg_mmio_info| +--------------------+ +--------------------+ |num_regions =3D M | |num_regions =3D N | | addrs[0] | | addrs[0] | | addrs[1] | | addrs[1] | | ... | | ... | | addrs[M-1] | | addrs[N-1] | +--------------------+ +--------------------+ Build a list (active_event_groups) of all the event groups that were successfully enabled. Use it to clean up in intel_aet_exit(). Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/intel_aet.c | 76 ++++++++++++++++++++++++- 1 file changed, 75 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 09043d36e08c..151e4b56ab36 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -19,23 +19,43 @@ =20 #include "internal.h" =20 +/** + * struct pkg_mmio_info - MMIO address information for one event group of = a package. + * @num_regions: Number of telemetry regions on this package. + * @addrs: Array of MMIO addresses, one per telemetry region on this pack= age. + * + * Provides convenient access to all MMIO addresses of one event group + * for one package. Used when reading event data on a package. + */ +struct pkg_mmio_info { + unsigned int num_regions; + void __iomem *addrs[] __counted_by(num_regions); +}; + /** * struct event_group - All information about a group of telemetry events. * @pfg: Points to the aggregated telemetry space information * within the OOBMSM driver that contains data for all * telemetry regions. + * @list: Member of active_event_groups. + * @pkginfo: Per-package MMIO addresses of telemetry regions belonging to= this group. * @guid: Unique number per XML description file. * @mmio_size: Number of bytes of MMIO registers for this group. */ struct event_group { /* Data fields for additional structures to manage this group. */ struct pmt_feature_group *pfg; + struct list_head list; + struct pkg_mmio_info **pkginfo; =20 /* Remaining fields initialized from XML file. */ u32 guid; size_t mmio_size; }; =20 +/* All successfully enabled event groups */ +static LIST_HEAD(active_event_groups); + #define XML_MMIO_SIZE(num_rmids, num_events, num_extra_status) \ (((num_rmids) * (num_events) + (num_extra_status)) * sizeof(u64)) =20 @@ -82,15 +102,32 @@ static bool skip_this_region(struct telemetry_region *= tr, struct event_group *e) return false; } =20 +static void free_pkg_mmio_info(struct pkg_mmio_info **mmi) +{ + int num_pkgs =3D topology_max_packages(); + + if (!mmi) + return; + + for (int i =3D 0; i < num_pkgs; i++) + kfree(mmi[i]); + kfree(mmi); +} + +DEFINE_FREE(pkg_mmio_info, struct pkg_mmio_info **, free_pkg_mmio_info(_T)) + /* * Discover events from one pmt_feature_group. * 1) Count how many usable telemetry regions per package. - * 2...) To be continued. + * 2) Allocate per-package structures and populate with MMIO + * addresses of the telemetry regions. */ static int discover_events(struct event_group *e, struct pmt_feature_group= *p) { + struct pkg_mmio_info **pkginfo __free(pkg_mmio_info) =3D NULL; int *pkgcounts __free(kfree) =3D NULL; struct telemetry_region *tr; + struct pkg_mmio_info *mmi; int num_pkgs; =20 num_pkgs =3D topology_max_packages(); @@ -112,6 +149,34 @@ static int discover_events(struct event_group *e, stru= ct pmt_feature_group *p) if (!pkgcounts) return -ENODEV; =20 + /* Allocate array for per-package struct pkg_mmio_info data */ + pkginfo =3D kcalloc(num_pkgs, sizeof(*pkginfo), GFP_KERNEL); + if (!pkginfo) + return -ENOMEM; + + /* + * Allocate per-package pkg_mmio_info structures and initialize + * count of telemetry_regions in each one. + */ + for (int i =3D 0; i < num_pkgs; i++) { + pkginfo[i] =3D kzalloc(struct_size(pkginfo[i], addrs, pkgcounts[i]), GFP= _KERNEL); + if (!pkginfo[i]) + return -ENOMEM; + pkginfo[i]->num_regions =3D pkgcounts[i]; + } + + /* Save MMIO address(es) for each telemetry region in per-package structu= res */ + for (int i =3D 0; i < p->count; i++) { + tr =3D &p->regions[i]; + if (skip_this_region(tr, e)) + continue; + mmi =3D pkginfo[tr->plat_info.package_id]; + mmi->addrs[--pkgcounts[tr->plat_info.package_id]] =3D tr->addr; + } + e->pkginfo =3D no_free_ptr(pkginfo); + + list_add(&e->list, &active_event_groups); + return 0; } =20 @@ -169,4 +234,13 @@ bool intel_aet_get_events(void) =20 void __exit intel_aet_exit(void) { + struct event_group *evg, *tmp; + + list_for_each_entry_safe(evg, tmp, &active_event_groups, list) { + intel_pmt_put_feature_group(evg->pfg); + evg->pfg =3D NULL; + free_pkg_mmio_info(evg->pkginfo); + evg->pkginfo =3D NULL; + list_del(&evg->list); + } } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 2A39E2E3384 for ; Mon, 11 Aug 2025 18:17:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936266; cv=none; b=nNIepiSnOlL4tPAWNzmthP46YCqkY5l8bSTGK9DQ9GyxYTgOkl22mwUHtknr5jlVbp2QKjTqjjRu4LIKCZXUAnJL/iPv5ModAKoAS6kHJJHjZ+kEIw0aTpTm0UNa5FgcDXfb2I2vtarttw4eO9joQYuAYBIXB+zR0lZg3s1spz8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936266; c=relaxed/simple; bh=ho626nVkVV9f3SlhzfLY0uCk4T/zkT/+ZAKlSUvYqW8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Ym4YyYKkov0Eg4wzIw3oh5WMeC8qmYNZo9o7iPiAVpmpSp2+AcAAQv/cBNGL1YKgpHJCibNHF3fn5Ya018Yjx4Cs5nTcNoIL24ViLvFO448ynm1zK2THrROvcxcu9WIgEPBYmEG+fSFJpdoa4PV0fBpxwEz4B5T8KTichSX3RLo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=P3NRVyXh; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="P3NRVyXh" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936265; x=1786472265; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=ho626nVkVV9f3SlhzfLY0uCk4T/zkT/+ZAKlSUvYqW8=; b=P3NRVyXheysObVGXGSYUSARwHU9JfJZwcfDqpLxAW3q1VSYe9byPkoKl OeftmVosx/BwkKaR5nLulwJauzI17oKqo+dFRhHDFgsDeVRScBBh7NcA/ 7du1ql5pGTf/cZcGd1nWCI1EqslNAfbaQuehfks2y6/cj5Ij4dPhP68Rb IRa8QnFpcWv0/XPzXFVClWF3oOkqjboYrZnmtghNiybX9pjn+PSCZbhUm XJfNlkL9CjNQbI/hKPejdaDrS2f0Jr8sIHl1rZBfgb8t4C1U8QbTelN7Q ENwmJfV4f6+BDWaf0Sxaa1SqjoqpLtzhuqxgc3HPjhr1KgGJpj6SUe3cm A==; X-CSE-ConnectionGUID: mkDax2apRsugWe9oXXaDFQ== X-CSE-MsgGUID: 8cTnrW7jQdKm0uMBNnARGA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277461" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277461" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: 3B8n2KkIRVqqT2bmGP4egg== X-CSE-MsgGUID: e7c955U5Svie7zg8RWMxYg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825680" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 20/32] x86,fs/resctrl: Fill in details of events for guid 0x26696143 and 0x26557651 Date: Mon, 11 Aug 2025 11:16:54 -0700 Message-ID: <20250811181709.6241-21-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" These two guids describe the events supported on Clearwater Forest. The offsets in MMIO space are arranged in groups for each RMID. E.g the "energy" counters for guid 0x26696143 are arranged like this: MMIO offset:0x0000 Counter for RMID 0 PMT_EVENT_ENERGY MMIO offset:0x0008 Counter for RMID 0 PMT_EVENT_ACTIVITY MMIO offset:0x0010 Counter for RMID 1 PMT_EVENT_ENERGY MMIO offset:0x0018 Counter for RMID 1 PMT_EVENT_ACTIVITY ... MMIO offset:0x23F0 Counter for RMID 575 PMT_EVENT_ENERGY MMIO offset:0x23F8 Counter for RMID 575 PMT_EVENT_ACTIVITY Define these events in the file system code and add the events to the event_group structures. PMT_EVENT_ENERGY and PMT_EVENT_ACTIVITY are produced in fixed point format. File system code must output as floating point values. Signed-off-by: Tony Luck --- include/linux/resctrl_types.h | 11 ++++++++ arch/x86/kernel/cpu/resctrl/intel_aet.c | 34 ++++++++++++++++++++++++ fs/resctrl/monitor.c | 35 ++++++++++++++----------- 3 files changed, 65 insertions(+), 15 deletions(-) diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h index d98351663c2c..6838b02d5ca3 100644 --- a/include/linux/resctrl_types.h +++ b/include/linux/resctrl_types.h @@ -47,6 +47,17 @@ enum resctrl_event_id { QOS_L3_MBM_TOTAL_EVENT_ID =3D 0x02, QOS_L3_MBM_LOCAL_EVENT_ID =3D 0x03, =20 + /* Intel Telemetry Events */ + PMT_EVENT_ENERGY, + PMT_EVENT_ACTIVITY, + PMT_EVENT_STALLS_LLC_HIT, + PMT_EVENT_C1_RES, + PMT_EVENT_UNHALTED_CORE_CYCLES, + PMT_EVENT_STALLS_LLC_MISS, + PMT_EVENT_AUTO_C6_RES, + PMT_EVENT_UNHALTED_REF_CYCLES, + PMT_EVENT_UOPS_RETIRED, + /* Must be the last */ QOS_NUM_EVENTS, }; diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 151e4b56ab36..dbd317e99ee0 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -32,6 +32,21 @@ struct pkg_mmio_info { void __iomem *addrs[] __counted_by(num_regions); }; =20 +/** + * struct pmt_event - Telemetry event. + * @id: Resctrl event id. + * @idx: Counter index within each per-RMID block of counters. + * @bin_bits: Zero for integer valued events, else number bits in fraction + * part of fixed-point. + */ +struct pmt_event { + enum resctrl_event_id id; + unsigned int idx; + unsigned int bin_bits; +}; + +#define EVT(_id, _idx, _bits) { .id =3D _id, .idx =3D _idx, .bin_bits =3D = _bits } + /** * struct event_group - All information about a group of telemetry events. * @pfg: Points to the aggregated telemetry space information @@ -41,6 +56,8 @@ struct pkg_mmio_info { * @pkginfo: Per-package MMIO addresses of telemetry regions belonging to= this group. * @guid: Unique number per XML description file. * @mmio_size: Number of bytes of MMIO registers for this group. + * @num_events: Number of events in this group. + * @evts: Array of event descriptors. */ struct event_group { /* Data fields for additional structures to manage this group. */ @@ -51,6 +68,8 @@ struct event_group { /* Remaining fields initialized from XML file. */ u32 guid; size_t mmio_size; + unsigned int num_events; + struct pmt_event evts[] __counted_by(num_events); }; =20 /* All successfully enabled event groups */ @@ -66,6 +85,11 @@ static LIST_HEAD(active_event_groups); static struct event_group energy_0x26696143 =3D { .guid =3D 0x26696143, .mmio_size =3D XML_MMIO_SIZE(576, 2, 3), + .num_events =3D 2, + .evts =3D { + EVT(PMT_EVENT_ENERGY, 0, 18), + EVT(PMT_EVENT_ACTIVITY, 1, 18), + } }; =20 /* @@ -75,6 +99,16 @@ static struct event_group energy_0x26696143 =3D { static struct event_group perf_0x26557651 =3D { .guid =3D 0x26557651, .mmio_size =3D XML_MMIO_SIZE(576, 7, 3), + .num_events =3D 7, + .evts =3D { + EVT(PMT_EVENT_STALLS_LLC_HIT, 0, 0), + EVT(PMT_EVENT_C1_RES, 1, 0), + EVT(PMT_EVENT_UNHALTED_CORE_CYCLES, 2, 0), + EVT(PMT_EVENT_STALLS_LLC_MISS, 3, 0), + EVT(PMT_EVENT_AUTO_C6_RES, 4, 0), + EVT(PMT_EVENT_UNHALTED_REF_CYCLES, 5, 0), + EVT(PMT_EVENT_UOPS_RETIRED, 6, 0), + } }; =20 static struct event_group *known_energy_event_groups[] =3D { diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index eeba9e1f4a34..879263db8fa3 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -878,27 +878,32 @@ static void dom_data_exit(struct rdt_resource *r) mutex_unlock(&rdtgroup_mutex); } =20 +#define MON_EVENT(_eventid, _name, _res, _fp) \ + [_eventid] =3D { \ + .name =3D _name, \ + .evtid =3D _eventid, \ + .rid =3D _res, \ + .is_floating_point =3D _fp, \ +} + /* * All available events. Architecture code marks the ones that * are supported by a system using resctrl_enable_mon_event() * to set .enabled. */ struct mon_evt mon_event_all[QOS_NUM_EVENTS] =3D { - [QOS_L3_OCCUP_EVENT_ID] =3D { - .name =3D "llc_occupancy", - .evtid =3D QOS_L3_OCCUP_EVENT_ID, - .rid =3D RDT_RESOURCE_L3, - }, - [QOS_L3_MBM_TOTAL_EVENT_ID] =3D { - .name =3D "mbm_total_bytes", - .evtid =3D QOS_L3_MBM_TOTAL_EVENT_ID, - .rid =3D RDT_RESOURCE_L3, - }, - [QOS_L3_MBM_LOCAL_EVENT_ID] =3D { - .name =3D "mbm_local_bytes", - .evtid =3D QOS_L3_MBM_LOCAL_EVENT_ID, - .rid =3D RDT_RESOURCE_L3, - }, + MON_EVENT(QOS_L3_OCCUP_EVENT_ID, "llc_occupancy", RDT_RESOURCE_L3, false= ), + MON_EVENT(QOS_L3_MBM_TOTAL_EVENT_ID, "mbm_total_bytes", RDT_RESOURCE_L3,= false), + MON_EVENT(QOS_L3_MBM_LOCAL_EVENT_ID, "mbm_local_bytes", RDT_RESOURCE_L3,= false), + MON_EVENT(PMT_EVENT_ENERGY, "core_energy", RDT_RESOURCE_PERF_PKG, true= ), + MON_EVENT(PMT_EVENT_ACTIVITY, "activity", RDT_RESOURCE_PERF_PKG, true), + MON_EVENT(PMT_EVENT_STALLS_LLC_HIT, "stalls_llc_hit", RDT_RESOURCE_PERF_= PKG, false), + MON_EVENT(PMT_EVENT_C1_RES, "c1_res", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UNHALTED_CORE_CYCLES, "unhalted_core_cycles", RDT_RES= OURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_STALLS_LLC_MISS, "stalls_llc_miss", RDT_RESOURCE_PER= F_PKG, false), + MON_EVENT(PMT_EVENT_AUTO_C6_RES, "c6_res", RDT_RESOURCE_PERF_PKG, false= ), + MON_EVENT(PMT_EVENT_UNHALTED_REF_CYCLES, "unhalted_ref_cycles", RDT_RESOU= RCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UOPS_RETIRED, "uops_retired", RDT_RESOURCE_PERF_PKG= , false), }; =20 void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,= unsigned int binary_bits) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 7D3412E426A for ; Mon, 11 Aug 2025 18:17:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; cv=none; b=FXjkKTwcap+5eCeuGdTUxRyItzDmickpBt3LQSw1p3+0/JVW/OvuDPUAAfJdzftb7yw9yNfU12By4ulk0FFr0SJy3z9S+esMmylSQh3E88Rp3Ga5dKwQHvZ1NlEArS5/jb/l4xIQIzPXGNiw0VNtxSTHC/4Ul7zm03OsFUTUK/A= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; c=relaxed/simple; bh=2hBTZeKFe7at29k2ndEbuBEXfv3Umu+oVEsKx4SAiMk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=uJ7uy4a1j6dh46EQPGnGCZpXAP9wLL0M7U6GSGQX1Y+8xz/G38QbwjAWhY0jdAdQDfwf5r2ZufmQ1NNSz4lF5h4kBm5Vx5p/LZdDwSR9cJ6QQ9BjKHq5zdJ+kksxqSjBJzqlhH93VhPWTf5UPrp5LeVgQALNAbxiczTKKfauP6k= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Wx/f0bgu; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Wx/f0bgu" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936267; x=1786472267; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=2hBTZeKFe7at29k2ndEbuBEXfv3Umu+oVEsKx4SAiMk=; b=Wx/f0bgu3gvQT1xrtVlUCwwOpBLrd3S49ZUz9Roz5ckM6OSyOlHTXPBh pO7UEPk6FU+aZK5ATx2ooFC4gq9B1/Hj0ngHfXJ+5I3Qa3GRWOa8KyHos es+FQHJhabtXgn77iIzEtB5Ug/ZkZkSeRMeHJqe8uSxhR/tHdwSLWMtU8 vxR0jE+FBpQ1XIuTSgitJyZccaszW+zJ2dTBiossEFaAoPLNpJKfjc/X0 HnAwJK9VwIQvvC5h6szzZNQaYMAWX+XaGndcO/wp3ELEKDZV22D+eCqSB 9C5pXWADcNCNy7+aXhvnwQ2h/Jaqg8kcVRZ41TcScj7vuvyzDp3o3aJg8 A==; X-CSE-ConnectionGUID: 2SAdUkdGSr2eSUlRco3rqA== X-CSE-MsgGUID: f4Nn8eHlSXyratUYC3RF2Q== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277473" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277473" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: 7XrgbcmkS0SeVwsbGWYyFw== X-CSE-MsgGUID: dw/XFai1QpGTP4zAi9wSBQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825683" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 21/32] x86,fs/resctrl: Add architectural event pointer Date: Mon, 11 Aug 2025 11:16:55 -0700 Message-ID: <20250811181709.6241-22-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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 resctrl file system layer passes the domain, RMID, and event id to resctrl_arch_rmid_read() to fetch an event counter. For some resources this is not enough information to efficiently access the counter. Fetching a telemetry event counter requires additional information that is private to the architecture, for example, the offset into MMIO space from where counter should be read. Add mon_evt::arch_priv void pointer. Architecture code can initialize this when marking each event enabled. File system code passes this pointer to resctrl_arch_rmid_read(). Suggested-by: Reinette Chatre Signed-off-by: Tony Luck --- include/linux/resctrl.h | 7 +++++-- fs/resctrl/internal.h | 4 ++++ arch/x86/kernel/cpu/resctrl/core.c | 6 +++--- arch/x86/kernel/cpu/resctrl/monitor.c | 2 +- fs/resctrl/monitor.c | 14 ++++++++++---- 5 files changed, 23 insertions(+), 10 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 61c73772a177..d729e988a475 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -384,7 +384,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r,= u32 closid); #define MAX_BINARY_BITS 27 =20 void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, - unsigned int binary_bits); + unsigned int binary_bits, void *arch_priv); =20 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); =20 @@ -479,6 +479,9 @@ void resctrl_arch_pre_mount(void); * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). * @val: result of the counter read in bytes. * @arch_mon_ctx: An architecture specific value from * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies @@ -496,7 +499,7 @@ void resctrl_arch_pre_mount(void); */ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *= hdr, u32 closid, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *arch_mon_ctx); + void *arch_priv, u64 *val, void *arch_mon_ctx); =20 /** * resctrl_arch_rmid_read_context_check() - warn about invalid contexts diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index b16e2fc42b3f..9c1f821279bb 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -62,6 +62,9 @@ static inline struct rdt_fs_context *rdt_fc2context(struc= t fs_context *fc) * @binary_bits: number of fixed-point binary bits from architecture, * only valid if @is_floating_point is true * @enabled: true if the event is enabled + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). */ struct mon_evt { enum resctrl_event_id evtid; @@ -72,6 +75,7 @@ struct mon_evt { bool is_floating_point; unsigned int binary_bits; bool enabled; + void *arch_priv; }; =20 extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 58756d216fe8..6f455454f38d 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -910,15 +910,15 @@ static __init bool get_rdt_mon_resources(void) bool ret =3D false; =20 if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { - resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0); + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0, NULL); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0); + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0, NULL); ret =3D true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0); + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0, NULL); ret =3D true; } =20 diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index 043f777378a6..185b203f6321 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -219,7 +219,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr= , unsigned int width) =20 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *= hdr, u32 unused, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *ignored) + void *arch_priv, u64 *val, void *ignored) { int cpu =3D cpumask_any(&hdr->cpu_mask); struct rdt_hw_l3_mon_domain *hw_dom; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 879263db8fa3..40c66caf299d 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -137,9 +137,11 @@ void __check_limbo(struct rdt_l3_mon_domain *d, bool f= orce_free) struct rmid_entry *entry; u32 idx, cur_idx =3D 1; void *arch_mon_ctx; + void *arch_priv; bool rmid_dirty; u64 val =3D 0; =20 + arch_priv =3D mon_event_all[QOS_L3_OCCUP_EVENT_ID].arch_priv; arch_mon_ctx =3D resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); if (IS_ERR(arch_mon_ctx)) { pr_warn_ratelimited("Failed to allocate monitor context: %ld", @@ -160,7 +162,7 @@ void __check_limbo(struct rdt_l3_mon_domain *d, bool fo= rce_free) =20 entry =3D __rmid_entry(idx); if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val, + QOS_L3_OCCUP_EVENT_ID, arch_priv, &val, arch_mon_ctx)) { rmid_dirty =3D true; } else { @@ -411,7 +413,8 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (rr->hdr) { /* Single domain. */ rr->err =3D resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, - rr->evt->evtid, &tval, rr->arch_mon_ctx); + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; =20 @@ -434,7 +437,8 @@ static int __mon_event_count(u32 closid, u32 rmid, stru= ct rmid_read *rr) if (d->ci_id !=3D rr->ci_id) continue; err =3D resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid, - rr->evt->evtid, &tval, rr->arch_mon_ctx); + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); if (!err) { rr->val +=3D tval; ret =3D 0; @@ -906,7 +910,8 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] =3D { MON_EVENT(PMT_EVENT_UOPS_RETIRED, "uops_retired", RDT_RESOURCE_PERF_PKG= , false), }; =20 -void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,= unsigned int binary_bits) +void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits, void *arch_priv) { if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >=3D QOS_NUM_EVENTS= || binary_bits > MAX_BINARY_BITS)) @@ -922,6 +927,7 @@ void resctrl_enable_mon_event(enum resctrl_event_id eve= ntid, bool any_cpu, unsig =20 mon_event_all[eventid].any_cpu =3D any_cpu; mon_event_all[eventid].binary_bits =3D binary_bits; + mon_event_all[eventid].arch_priv =3D arch_priv; mon_event_all[eventid].enabled =3D true; } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 379F42E3AF7 for ; Mon, 11 Aug 2025 18:17:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936267; cv=none; b=pqEtpC8IMn9fQxHXYqcxn/CDwrjkX5gBhCpBZXejacPGAgpKyQ+fO7Lut+c/WqC54OQg6lA3zp8GqMSDGPL3SDsvATDz/ffRe1S5KSsEl+bJMgFc6IWb7qKzCo02u0nLo4beJbpzhfMjRlkOq1VQicA0ZKmOmS2igQtOiGixM1I= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936267; c=relaxed/simple; bh=fcNC4h2TEkm1ATe2ICOxIcVqPMlso311x+so9qRG1J4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=FRUOS3msiQKjOviD5pXWxMfkVyAORVNVcZsZZlpH4A7MA+dZQ0Tq/rBeBjB0DB3C8JyoNBnnziWifNq8OOZdmYwI5gk/w73QK1ia/y3mIrmfF6tKUwI70AmA/rUopYtpD59Eo7RGH4SXj8tf8XmNZ/tjugrNQhRuS6QiJkDUpGQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=JBKBIVoU; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="JBKBIVoU" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936266; x=1786472266; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=fcNC4h2TEkm1ATe2ICOxIcVqPMlso311x+so9qRG1J4=; b=JBKBIVoUol41thSgSXcVzI0+VYikz3cOcMeaeioqONEEJq8l62IrIAMl GXCRX6wUmBeMFhfyMUNM04foMOAUtI7IbQCyAZpaLPILPN7fa34QBjyyE uHzC+aARpuuoq0QUW+bfUSSMdc9WVnmwfGSqnp7fLg3YNNVi6rt+DnwLZ /5s/YDUfzuPuyBtHeU6H0w2sXXbWKOIj/ltyqtoPLGP/RubTGhYHeeTk3 wuqRCqeLqeefx0ULvhNsaHS7JM/AN5Z1K6Ao/ASqbP6J1Gp0N9BKs2kSW FwkJHyf6CcqRfIDxRdyrtxM5781BP3Ojh012128ciQUWKBBn3jx0lefJV g==; X-CSE-ConnectionGUID: ADxpXVlDTYex4CfcCqXOZg== X-CSE-MsgGUID: 0gpEzp8eSz2EMufrKJOCZw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277477" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277477" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: B/1Jy3UvTYu4Ka7d1Mo80g== X-CSE-MsgGUID: Iz8qZpK0TY2BtOEEAORk7A== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825687" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:25 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 22/32] x86/resctrl: Read telemetry events Date: Mon, 11 Aug 2025 11:16:56 -0700 Message-ID: <20250811181709.6241-23-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Telemetry events are enumerated by the INTEL_PMT_TELEMETRY subsystem. resctrl enables events with resctrl_enable_mon_event() passing a pointer to the pmt_event structure for the event within the struct event_group. The file system stores it in mon_evt::arch_priv. Add a check to resctrl_arch_rmid_read() for resource id RDT_RESOURCE_PERF_PKG and directly call intel_aet_read_event() passing the enum resctrl_event_id for the event and the arch_priv pointer that was supplied when the event was enabled. There may be multiple aggregators tracking each package, so scan all of them and add up all counters. Resctrl now uses readq() so depends on X86_64. Update Kconfig. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/internal.h | 7 ++++ arch/x86/kernel/cpu/resctrl/intel_aet.c | 44 +++++++++++++++++++++++++ arch/x86/kernel/cpu/resctrl/monitor.c | 3 ++ arch/x86/Kconfig | 2 +- 4 files changed, 55 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index 710493ec6548..b2f0769f63f6 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -172,9 +172,16 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r= ); #ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET bool intel_aet_get_events(void); void __exit intel_aet_exit(void); +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id evtid, + void *arch_priv, u64 *val); #else static inline bool intel_aet_get_events(void) { return false; } static inline void __exit intel_aet_exit(void) { } +static inline int intel_aet_read_event(int domid, int rmid, enum resctrl_e= vent_id evtid, + void *arch_priv, u64 *val) +{ + return -EINVAL; +} #endif =20 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index dbd317e99ee0..5d49ed446b94 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include =20 @@ -211,6 +212,9 @@ static int discover_events(struct event_group *e, struc= t pmt_feature_group *p) =20 list_add(&e->list, &active_event_groups); =20 + for (int i =3D 0; i < e->num_events; i++) + resctrl_enable_mon_event(e->evts[i].id, true, e->evts[i].bin_bits, &e->e= vts[i]); + return 0; } =20 @@ -278,3 +282,43 @@ void __exit intel_aet_exit(void) list_del(&evg->list); } } + +#define DATA_VALID BIT_ULL(63) +#define DATA_BITS GENMASK_ULL(62, 0) + +/* + * Read counter for an event on a domain (summing all aggregators + * on the domain). + */ +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id eventi= d, + void *arch_priv, u64 *val) +{ + struct pmt_event *pevt =3D arch_priv; + struct pkg_mmio_info *mmi; + struct event_group *e; + bool valid =3D false; + u64 evtcount; + void *pevt0; + int idx; + + pevt0 =3D pevt - pevt->idx; + e =3D container_of(pevt0, struct event_group, evts); + idx =3D rmid * e->num_events; + idx +=3D pevt->idx; + mmi =3D e->pkginfo[domid]; + + if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) { + pr_warn_once("MMIO index %d out of range\n", idx); + return -EIO; + } + + for (int i =3D 0; i < mmi->num_regions; i++) { + evtcount =3D readq(mmi->addrs[i] + idx * sizeof(u64)); + if (!(evtcount & DATA_VALID)) + continue; + *val +=3D evtcount & DATA_BITS; + valid =3D true; + } + + return valid ? 0 : -EINVAL; +} diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/re= sctrl/monitor.c index 185b203f6321..51d7d99336c6 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -232,6 +232,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, stru= ct rdt_domain_hdr *hdr, =20 resctrl_arch_rmid_read_context_check(); =20 + if (r->rid =3D=3D RDT_RESOURCE_PERF_PKG) + return intel_aet_read_event(hdr->id, rmid, eventid, arch_priv, val); + if (r->rid !=3D RDT_RESOURCE_L3) return -EINVAL; =20 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 56f0ff94c430..32beb66f0a92 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -527,7 +527,7 @@ config X86_CPU_RESCTRL =20 config X86_CPU_RESCTRL_INTEL_AET bool "Intel Application Energy Telemetry" if INTEL_PMT_TELEMETRY=3Dy && I= NTEL_TPMI=3Dy - depends on X86_CPU_RESCTRL && CPU_SUP_INTEL + depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL help Enable per-RMID telemetry events in resctrl =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 BB9502E3B19 for ; Mon, 11 Aug 2025 18:17:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; cv=none; b=NFFVOMz1zWBqS1AlkSDTbsJ/4fUUylP0xBeI6HDB1iwb0imhU3vbLa8Pkp8ROtdnh4l3546MFy8bsg4e7/3GzM+BqOqHShQg2M+uTKZ/MGHZeYcCEhZv9wgJgayRd/1RCyJHsqZ/c1RKJhP1eWDCo0rNUAboxiktC4IAQM0rDbA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; c=relaxed/simple; bh=/pAri7fod0roEkNmWrBw8vjJ/Nnx6xwnZY2N/OS7pIc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=lygN+ZuTT563JjLkkDFrNp/CWy3loRjAHo3/imCe4yylqvR1a4HAJQRRjQe+kTWkXLhIlSMFwRXUXiQTBgALWU8TGwP0BSxazhlvBP4XA4gglESoPQV4koncRj7n5rpoSG7MkdQEKiWqfhcJOSlZIAmDIXyjnqymCbuT58xj3+o= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=mhMKNQeM; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="mhMKNQeM" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936266; x=1786472266; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=/pAri7fod0roEkNmWrBw8vjJ/Nnx6xwnZY2N/OS7pIc=; b=mhMKNQeM+twTjxGorNhvhRnpH+Wfh+NwP0uXpgKI31e8OA4ySiHJNSyd evuwYsQ/F9moFcywJ1d5HSeNhr+TW4fjXjLS3C0CrhfBib9u8p8V8ztDA tNWyTiZ33hdHCgCeGolhdIduBX/zzUjTsctYF41i2fUIuLfdal6QQdiBQ s1oilUbSNN2AmasUlfKKJ+hc3TvqHp+k/v7lrxRXF/32TSqh9OaKo1l96 JF9iYVmVhWe3HewCuYFb9dkOIwhsiNnE4Vq4RCXRYzIxomwoE8Kt66Ssy kz4aOt5W0HPRi033227EaVjaNKq1fPdwNlSqjTK12E5GNTsqRq15o8QJ+ w==; X-CSE-ConnectionGUID: aO8llEyiQAiPITvnnGKX/A== X-CSE-MsgGUID: a++G01FBToC3oabelz9hQA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277482" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277482" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: f4mc2EIoQX2sudf39pbiHw== X-CSE-MsgGUID: 4U6KxNosSPK4jXAre2JM3w== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825690" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 23/32] x86/resctrl: Handle domain creation/deletion for RDT_RESOURCE_PERF_PKG Date: Mon, 11 Aug 2025 11:16:57 -0700 Message-ID: <20250811181709.6241-24-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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 L3 resource has several requirements for domains. There are structures that hold the 64-bit values of counters, and elements to keep track of the overflow and limbo threads. None of these are needed for the PERF_PKG resource. The hardware counters are wide enough that they do not wrap around for decades. Define a new rdt_perf_pkg_mon_domain structure which just consists of the standard rdt_domain_hdr to keep track of domain id and CPU mask. Add a case RDT_RESOURCE_PERF_PKG to domain_add_cpu_mon() to call intel_aet_setup_mon_domain() to allocate and initialize the rdt_perf_pkg_mon_domain structure. Also add a case to domain_remove_cpu_mon() cleanup when the last CPU of a domain is removed. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/internal.h | 13 +++++++++++++ arch/x86/kernel/cpu/resctrl/core.c | 9 +++++++++ arch/x86/kernel/cpu/resctrl/intel_aet.c | 24 ++++++++++++++++++++++++ 3 files changed, 46 insertions(+) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index b2f0769f63f6..cd911591625f 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -75,6 +75,14 @@ static inline struct rdt_hw_l3_mon_domain *resctrl_to_ar= ch_mon_dom(struct rdt_l3 return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl); } =20 +/** + * struct rdt_perf_pkg_mon_domain - CPUs sharing an package scoped resctrl= monitor resource + * @hdr: common header for different domain types + */ +struct rdt_perf_pkg_mon_domain { + struct rdt_domain_hdr hdr; +}; + /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use @@ -174,6 +182,8 @@ bool intel_aet_get_events(void); void __exit intel_aet_exit(void); int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id evtid, void *arch_priv, u64 *val); +void intel_aet_setup_mon_domain(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos); #else static inline bool intel_aet_get_events(void) { return false; } static inline void __exit intel_aet_exit(void) { } @@ -182,6 +192,9 @@ static inline int intel_aet_read_event(int domid, int r= mid, enum resctrl_event_i { return -EINVAL; } + +static inline void intel_aet_setup_mon_domain(int cpu, int id, struct rdt_= resource *r, + struct list_head *add_pos) { } #endif =20 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 6f455454f38d..7a0d81b4c230 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -574,6 +574,9 @@ static void domain_add_cpu_mon(int cpu, struct rdt_reso= urce *r) case RDT_RESOURCE_L3: l3_mon_domain_setup(cpu, id, r, add_pos); break; + case RDT_RESOURCE_PERF_PKG: + intel_aet_setup_mon_domain(cpu, id, r, add_pos); + break; default: WARN_ON_ONCE(1); break; @@ -671,6 +674,12 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_= resource *r) synchronize_rcu(); l3_mon_domain_free(hw_dom); break; + case RDT_RESOURCE_PERF_PKG: + resctrl_offline_mon_domain(r, hdr); + list_del_rcu(&hdr->list); + synchronize_rcu(); + kfree(container_of(hdr, struct rdt_perf_pkg_mon_domain, hdr)); + break; default: pr_warn_once("Unknown resource rid=3D%d\n", r->rid); break; diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 5d49ed446b94..7db03e24d4b2 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -322,3 +322,27 @@ int intel_aet_read_event(int domid, int rmid, enum res= ctrl_event_id eventid, =20 return valid ? 0 : -EINVAL; } + +void intel_aet_setup_mon_domain(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos) +{ + struct rdt_perf_pkg_mon_domain *d; + int err; + + d =3D kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->hdr.id =3D id; + d->hdr.type =3D RESCTRL_MON_DOMAIN; + d->hdr.rid =3D r->rid; + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + list_add_tail_rcu(&d->hdr.list, add_pos); + + err =3D resctrl_online_mon_domain(r, &d->hdr); + if (err) { + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + kfree(d); + } +} --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 BA96B2E4271 for ; Mon, 11 Aug 2025 18:17:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; cv=none; b=mqxOZa6wL42ULD3jqFDmCwBu7Qiczfjatz26JXNcZG9YfhPAfgpWcxycjG3JYvIv4Y39vcnYAaN0BPHJyLy/y6EmT3rTp/eopBAQwTJrbURdI6H736MIoe+EJGZ0BijnG6E/bYeI6usibEDvJ0CIZl+Kdnq2NEEWBhc46mLWYwg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936268; c=relaxed/simple; bh=ssZTE+z9V//W/s5k1s1ZiZYrrJ05FU0h4Tp1p6ePZS0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=tl/2eH6+0/JKHG6FViXnzomKdla6h8niJxRQ9Scw32vEoPJfzY1ALEcBLC+mjrc+/TQf1k4WTAC5x4oZWZJCKu9wp7v5TCpg8JZHzWlQeHPJOEAlFqCsCtXOGOh8zcSbHbPrnA5Dd95p2ocaZOOonW87fqNUjLy/2DajInZpUeI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=kacmu8yH; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="kacmu8yH" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936267; x=1786472267; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=ssZTE+z9V//W/s5k1s1ZiZYrrJ05FU0h4Tp1p6ePZS0=; b=kacmu8yHNIaJbYrY8s+F/YIvcwpw8jAM4dkJ1z1HD15juDbAJkzj/uTi LJ7OEOjdRW8YDs1GLqejhIvwlPGSgw4ux0dYyMaJTYUCko+8vE+jVzuQE QmIqrLldomZN2xsLmQaN4rFQ2pCxn0+ovpmmjmQCh+BP602PrdaQpaNtE l0TJC2scA2P4MhWxYXF0qSCqnhHl+x5aDFgz657r/ApUiBewW14MDQhe9 rBHQzdMBCVPzsDobl8LO4ETKaoyqqb8xts/U5Cp/CIGvUmeA2zQz3xUlc NyxHS+TSG2nhI3UEPjYYXeg1Hc+AETWG6Kl3L2bJ6csPGixGEp8WkgPxe g==; X-CSE-ConnectionGUID: 6W5qyo2MSdScVj4fkfKXeg== X-CSE-MsgGUID: dE6+zqVWSkGDukYyPrEpiQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277492" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277492" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: pEyZBfZtSMapvlXkxpcvew== X-CSE-MsgGUID: gz6+gE8VQuajB3dcFaYXDg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825694" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 24/32] x86/resctrl: Add energy/perf choices to rdt boot option Date: Mon, 11 Aug 2025 11:16:58 -0700 Message-ID: <20250811181709.6241-25-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Legacy resctrl features are enumerated by X86_FEATURE_* flags. These may be overridden by quirks to disable features in the case of errata. Users can use kernel command line options to either disable a feature, or to force enable a feature that was disabled by a quirk. Provide similar functionality for hardware features that do not have an X86_FEATURE_* flag. Unlike other features that are tied to X86_FEATURE_* flags, these must be queried by name. Add rdt_is_feature_enabled() to check whether quirks or kernel command line have disabled a feature. Just like the legacy features the command line enable overrides quirk disable. Signed-off-by: Tony Luck --- .../admin-guide/kernel-parameters.txt | 2 +- arch/x86/kernel/cpu/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/core.c | 30 +++++++++++++++++++ 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentatio= n/admin-guide/kernel-parameters.txt index 747a55abf494..b600e1b47b0c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6154,7 +6154,7 @@ rdt=3D [HW,X86,RDT] Turn on/off individual RDT features. List is: cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, - mba, smba, bmec. + mba, smba, bmec, energy, perf. E.g. to turn on cmt and turn off mba use: rdt=3Dcmt,!mba =20 diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index cd911591625f..e76b5e35351b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -177,6 +177,8 @@ void __init intel_rdt_mbm_apply_quirk(void); =20 void rdt_domain_reconfigure_cdp(struct rdt_resource *r); =20 +bool rdt_is_feature_enabled(char *name); + #ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET bool intel_aet_get_events(void); void __exit intel_aet_exit(void); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 7a0d81b4c230..d151aabe2b93 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -760,6 +760,8 @@ enum { RDT_FLAG_MBA, RDT_FLAG_SMBA, RDT_FLAG_BMEC, + RDT_FLAG_ENERGY, + RDT_FLAG_PERF, }; =20 #define RDT_OPT(idx, n, f) \ @@ -785,6 +787,8 @@ static struct rdt_options rdt_options[] __ro_after_ini= t =3D { RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), RDT_OPT(RDT_FLAG_SMBA, "smba", X86_FEATURE_SMBA), RDT_OPT(RDT_FLAG_BMEC, "bmec", X86_FEATURE_BMEC), + RDT_OPT(RDT_FLAG_ENERGY, "energy", 0), + RDT_OPT(RDT_FLAG_PERF, "perf", 0), }; #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) =20 @@ -834,6 +838,32 @@ bool rdt_cpu_has(int flag) return ret; } =20 +/* + * Hardware features that do not have X86_FEATURE_* bits. + * There is no "hardware does not support this at all" case. + * Assume that the caller has already determined that hardware + * support is present and just needs to check if the feature has been + * disabled by a quirk that has not been overridden by a command + * line option. + */ +bool rdt_is_feature_enabled(char *name) +{ + struct rdt_options *o; + bool ret =3D true; + + for (o =3D rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (!strcmp(name, o->name)) { + if (o->force_off) + ret =3D false; + if (o->force_on) + ret =3D true; + break; + } + } + + return ret; +} + bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt) { if (!rdt_cpu_has(X86_FEATURE_BMEC)) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 27FC22E5434 for ; Mon, 11 Aug 2025 18:17:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936270; cv=none; b=fzdZ4bA/IUukzjRBLQrMd2fV/nj0RuxhgSZWzGsQLPNWPfLq3vGdUfGWYd91u1JapmuVFMtfcEJexuV7Vl7YG50E27cx3w5smGnkD+gx/CGP89VHoQakwnyvQSEadWlB4nMLQZomEflc9sSeFGKfw9SIdDdxUA9jBMkZzFPLVPs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936270; c=relaxed/simple; bh=I7V5rvBsGe1JDp56MACDgj0Jg42lsEAPwGwQulYwT2U=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=uZW7TLS/xjcIWujVhwlTDdFkCt6LMXqelbUTW/QBw+nZOCuA83XtAD80eDP7hyh9pEzQ2RK1F9oF/gbVMoT82DmlnZo3P58DINwwWVWdIlNSC2zJAxYyv7EuLxN+vwpuWtMWQC0ER3uFYr/AQ4AEgayLmZtFns2WvcKEH2rX6as= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Qq+XrbTy; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Qq+XrbTy" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936269; x=1786472269; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=I7V5rvBsGe1JDp56MACDgj0Jg42lsEAPwGwQulYwT2U=; b=Qq+XrbTyI4ULvinhNVb7S/6MUtnvYy7lmKTgY3+GykjSbS4KevXs1yjF JwICh50KbN3dDF59XzZuwDzfdBlRkCUT1doNt8pAoeiDWS3nw79f1eSEE hcX7IJTWWT1647euOOAOPOdjPhsqIIH0Q0Ey1M9nMMZTM/k7rS9fVTHrD qiB0K12DhlqnFmpY9kLTf/SOF6osalLv29Qpa1Obd7h9vtZe5EqSvlvnq xYjaZJDDQToQebBxWl6SLaKPzYkTW2nPnzy059w2jVTxtM500SnqdoEDx 1e2mfVRGqy0yGCzVnYn6Ed3qDxhFzzBfNUpBzp7lcOTYDegbGRgsRu3g6 g==; X-CSE-ConnectionGUID: jK89ZouhQ8aMvJdX3riD9w== X-CSE-MsgGUID: MByfXZNhQKGu85oPnbMvAg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277498" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277498" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: eqopBtCCTPeCb5A3nN0koA== X-CSE-MsgGUID: 9y8tvfKYRo+KoAFXnSUS6Q== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825698" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 25/32] x86/resctrl: Handle number of RMIDs supported by telemetry resources Date: Mon, 11 Aug 2025 11:16:59 -0700 Message-ID: <20250811181709.6241-26-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" There are now three meanings for "number of RMIDs": 1) The number for legacy features enumerated by CPUID leaf 0xF. This is the maximum number of distinct values that can be loaded into the IA32_PQR_ASSOC MSR. Note that systems with Sub-NUMA Cluster mode enabled will force scaling down the CPUID enumerated value by the number of SNC nodes per L3-cache. 2) The number of registers in MMIO space for each event. This is enumerated in the XML files and is the value initialized into event_group::num_rmids. This will be overwritten with a lower value if hardware does not support all these registers at the same time (see next case). 3) The number of "hardware counters" (this isn't a strictly accurate description of how things work, but serves as a useful analogy that does describe the limitations) feeding to those MMIO registers. This is enumerated in telemetry_region::num_rmids returned from the call to intel_pmt_get_regions_by_feature() Event groups with insufficient "hardware counters" to track all RMIDs are difficult for users to use, since the system may reassign "hardware counters" at any time. This means that users cannot reliably collect two consecutive event counts to compute the rate at which events are occurring. Use rdt_set_feature_disabled() to mark any under-resourced event groups (those with telemetry_region::num_rmids < event_group::num_rmids) as unusable. Note that the rdt_options[] structure must now be writable at run-time. The request to disable will be overridden if the user explicitly requests to enable using the "rdt=3D" Linux boot argument. Scan all enabled event groups and assign the RDT_RESOURCE_PERF_PKG resource "num_rmids" value to the smallest of these values as this value will be used later to compare against the number of RMIDs supported by other resources. N.B. Changed type of rdt_resource::num_rmid to u32 to match type of event_group::num_rmids so that min(r->num_rmid, e->num_rmids) won't complain about mixing signed and unsigned types. Print r->num_rmid as unsigned value in rdt_num_rmids_show(). Signed-off-by: Tony Luck --- include/linux/resctrl.h | 2 +- arch/x86/kernel/cpu/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/core.c | 18 ++++++++++- arch/x86/kernel/cpu/resctrl/intel_aet.c | 43 +++++++++++++++++++++++++ fs/resctrl/rdtgroup.c | 2 +- 5 files changed, 64 insertions(+), 3 deletions(-) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index d729e988a475..c1cfba3c8422 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -288,7 +288,7 @@ struct rdt_resource { int rid; bool alloc_capable; bool mon_capable; - int num_rmid; + u32 num_rmid; enum resctrl_scope ctrl_scope; enum resctrl_scope mon_scope; struct resctrl_cache cache; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/r= esctrl/internal.h index e76b5e35351b..0e292c2d78a1 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -179,6 +179,8 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r); =20 bool rdt_is_feature_enabled(char *name); =20 +void rdt_set_feature_disabled(char *name); + #ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET bool intel_aet_get_events(void); void __exit intel_aet_exit(void); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index d151aabe2b93..2b011f9efc73 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -776,7 +776,7 @@ struct rdt_options { bool force_off, force_on; }; =20 -static struct rdt_options rdt_options[] __ro_after_init =3D { +static struct rdt_options rdt_options[] =3D { RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC), RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL), RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL), @@ -838,6 +838,22 @@ bool rdt_cpu_has(int flag) return ret; } =20 +/* + * Can be called during feature enumeration if sanity check of + * a feature's parameters indicates problems with the feature. + */ +void rdt_set_feature_disabled(char *name) +{ + struct rdt_options *o; + + for (o =3D rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (!strcmp(name, o->name)) { + o->force_off =3D true; + return; + } + } +} + /* * Hardware features that do not have X86_FEATURE_* bits. * There is no "hardware does not support this at all" case. diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 7db03e24d4b2..96c454748320 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include =20 @@ -50,24 +51,30 @@ struct pmt_event { =20 /** * struct event_group - All information about a group of telemetry events. + * @name: Name for this group (used by boot rdt=3D option) * @pfg: Points to the aggregated telemetry space information * within the OOBMSM driver that contains data for all * telemetry regions. * @list: Member of active_event_groups. * @pkginfo: Per-package MMIO addresses of telemetry regions belonging to= this group. * @guid: Unique number per XML description file. + * @num_rmids: Number of RMIDS supported by this group. Adjusted downwards + * if enumeration from intel_pmt_get_regions_by_feature() indicates + * fewer RMIDs can be tracked simultaneously. * @mmio_size: Number of bytes of MMIO registers for this group. * @num_events: Number of events in this group. * @evts: Array of event descriptors. */ struct event_group { /* Data fields for additional structures to manage this group. */ + char *name; struct pmt_feature_group *pfg; struct list_head list; struct pkg_mmio_info **pkginfo; =20 /* Remaining fields initialized from XML file. */ u32 guid; + u32 num_rmids; size_t mmio_size; unsigned int num_events; struct pmt_event evts[] __counted_by(num_events); @@ -84,7 +91,9 @@ static LIST_HEAD(active_event_groups); * File: xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml */ static struct event_group energy_0x26696143 =3D { + .name =3D "energy", .guid =3D 0x26696143, + .num_rmids =3D 576, .mmio_size =3D XML_MMIO_SIZE(576, 2, 3), .num_events =3D 2, .evts =3D { @@ -98,7 +107,9 @@ static struct event_group energy_0x26696143 =3D { * File: xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml */ static struct event_group perf_0x26557651 =3D { + .name =3D "perf", .guid =3D 0x26557651, + .num_rmids =3D 576, .mmio_size =3D XML_MMIO_SIZE(576, 7, 3), .num_events =3D 7, .evts =3D { @@ -137,6 +148,22 @@ static bool skip_this_region(struct telemetry_region *= tr, struct event_group *e) return false; } =20 +static bool check_rmid_count(struct event_group *e, struct pmt_feature_gro= up *p) +{ + struct telemetry_region *tr; + + for (int i =3D 0; i < p->count; i++) { + tr =3D &p->regions[i]; + if (skip_this_region(tr, e)) + continue; + + if (tr->num_rmids < e->num_rmids) + return false; + } + + return true; +} + static void free_pkg_mmio_info(struct pkg_mmio_info **mmi) { int num_pkgs =3D topology_max_packages(); @@ -159,12 +186,21 @@ DEFINE_FREE(pkg_mmio_info, struct pkg_mmio_info **, f= ree_pkg_mmio_info(_T)) */ static int discover_events(struct event_group *e, struct pmt_feature_group= *p) { + struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_re= sctrl; struct pkg_mmio_info **pkginfo __free(pkg_mmio_info) =3D NULL; int *pkgcounts __free(kfree) =3D NULL; struct telemetry_region *tr; struct pkg_mmio_info *mmi; int num_pkgs; =20 + /* Potentially disable feature if insufficient RMIDs */ + if (!check_rmid_count(e, p)) + rdt_set_feature_disabled(e->name); + + /* User can override above disable from kernel command line */ + if (!rdt_is_feature_enabled(e->name)) + return -EINVAL; + num_pkgs =3D topology_max_packages(); =20 /* Get per-package counts of telemetry regions for this event group */ @@ -173,6 +209,8 @@ static int discover_events(struct event_group *e, struc= t pmt_feature_group *p) if (skip_this_region(tr, e)) continue; =20 + e->num_rmids =3D min(e->num_rmids, tr->num_rmids); + if (!pkgcounts) { pkgcounts =3D kcalloc(num_pkgs, sizeof(*pkgcounts), GFP_KERNEL); if (!pkgcounts) @@ -215,6 +253,11 @@ static int discover_events(struct event_group *e, stru= ct pmt_feature_group *p) for (int i =3D 0; i < e->num_events; i++) resctrl_enable_mon_event(e->evts[i].id, true, e->evts[i].bin_bits, &e->e= vts[i]); =20 + if (r->num_rmid) + r->num_rmid =3D min(r->num_rmid, e->num_rmids); + else + r->num_rmid =3D e->num_rmids; + return 0; } =20 diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 26928ad0a35a..55ad99bd77d2 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -1135,7 +1135,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file= *of, { struct rdt_resource *r =3D rdt_kn_parent_priv(of->kn); =20 - seq_printf(seq, "%d\n", r->num_rmid); + seq_printf(seq, "%u\n", r->num_rmid); =20 return 0; } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 9DD392E541A for ; Mon, 11 Aug 2025 18:17:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936269; cv=none; b=DkcUfQMeINXj5GsPl4tZxVpShMyBmVP3ROkREMbZ5eLTQ7jd29svRvbkAtd27wocPHyGMDQsdt0SBrrWw+KZOYUbnxof88apt/JwGyh88nl8smrx4vAUavoXWqeCYTHHwEMrumJmopyi5zo4vFhgkQdu7lfqqa8T1qpB4xtNpLs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936269; c=relaxed/simple; bh=b6IVqR9pDUjerzkW1aPFwxLkZVvGGdytWKlMSyP1xH8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=i2r+6+UdyWzZpobjcJ7B8Y5iHNg84n4uJ9VWDzm0+A2XFI+iZeL0wwnYPg7dDMJhVLgatq8LrHWIiMsPqtj6g7L1OFx1aJ+vxWmkq/k7Tlqt5k54cFdHsrY9t1az3W5FEkNNkSBFVCmspvbNsLIw+tWnY4j2/I5ED789cG2ljuI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Qg90mH7i; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Qg90mH7i" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936268; x=1786472268; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=b6IVqR9pDUjerzkW1aPFwxLkZVvGGdytWKlMSyP1xH8=; b=Qg90mH7irnr/HhgLp1sMLbp5dATrsoViVpZiFdCMHiTAaGnyKwPWvKws SPKJlobATLZxOaP4rJqHhzTpuwiU1aGF4E7JIhCG6P83ZIDH6nDEnETqF 3tLH9sUZVgr69REi8wGWjJkokN647ashRXCppMLpnFpcsH7IV/Q9I1kH+ nyzbnreA3jD2JPRxSI+mfqlkxBL27bVPvptrz7cF6cNouKhqlYQ6kJVO4 U5XkCVbgJOZ/FjFUk5L7jqeeR1DmUb/pfcD+jsd1pL6/NixF+vXr950/8 G5PaZJvSwxivtVIxsdB3CMiLLusyLFVDaZNUAajCgd5u+KLtUSTk23l1i g==; X-CSE-ConnectionGUID: k97X4CgNRZqdDN0qb+q8rw== X-CSE-MsgGUID: 5XNQq5rWR6qZjrtvdpvcGg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277499" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277499" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: zuPWe7FZTe+htSNyvV3dVw== X-CSE-MsgGUID: cu2geDdiTKu24k7Sm9UdyQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825702" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 26/32] fs/resctrl: Move allocation/free of closid_num_dirty_rmid Date: Mon, 11 Aug 2025 11:17:00 -0700 Message-ID: <20250811181709.6241-27-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" closid_num_dirty_rmid[] is allocated in dom_data_init() and freed by dom_data_exit() giving it the same life cycle as rmid_ptrs[]. Move the alloc/free out to resctrl_mon_l3_resource_init() and resctrl_mon_l3_resource_exit() in preparation for rmid_ptrs[] to be allocated on resctrl mount in support of the new telemetry events. Signed-off-by: Tony Luck --- fs/resctrl/monitor.c | 56 ++++++++++++++++++++++---------------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 40c66caf299d..0d9c8d4e0e9c 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -805,36 +805,14 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_dom= ain *dom, unsigned long del static int dom_data_init(struct rdt_resource *r) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); - u32 num_closid =3D resctrl_arch_get_num_closid(r); struct rmid_entry *entry =3D NULL; int err =3D 0, i; u32 idx; =20 mutex_lock(&rdtgroup_mutex); - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - u32 *tmp; - - /* - * If the architecture hasn't provided a sanitised value here, - * this may result in larger arrays than necessary. Resctrl will - * use a smaller system wide value based on the resources in - * use. - */ - tmp =3D kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); - if (!tmp) { - err =3D -ENOMEM; - goto out_unlock; - } - - closid_num_dirty_rmid =3D tmp; - } =20 rmid_ptrs =3D kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); if (!rmid_ptrs) { - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid =3D NULL; - } err =3D -ENOMEM; goto out_unlock; } @@ -870,11 +848,6 @@ static void dom_data_exit(struct rdt_resource *r) if (!r->mon_capable) goto out_unlock; =20 - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid =3D NULL; - } - kfree(rmid_ptrs); rmid_ptrs =3D NULL; =20 @@ -957,9 +930,31 @@ int resctrl_mon_l3_resource_init(void) if (!r->mon_capable) return 0; =20 + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 num_closid =3D resctrl_arch_get_num_closid(r); + u32 *tmp; + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp =3D kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + closid_num_dirty_rmid =3D tmp; + } + ret =3D dom_data_init(r); - if (ret) + if (ret) { + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid =3D NULL; + } return ret; + } =20 if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) { mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable =3D true; @@ -984,5 +979,10 @@ void resctrl_mon_l3_resource_exit(void) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); =20 + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid =3D NULL; + } + dom_data_exit(r); } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 E6A722E54BD for ; Mon, 11 Aug 2025 18:17:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936271; cv=none; b=dhcIYPg32bH0WgEsuXlwHKF1wmrS/py0TX0DJfp6Kxs35JEXU7Nnelruo/2XLo4tNlBG6WJ+BKdAOG3g9YXpY1JfOV8pbZNpHdiPlhoWvFEOiy7gdotfD3VgYWkxe4PFPfF5go+3Eg9tw+Df2KhxiyoicTQwoVKK8N1p+vZes2w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936271; c=relaxed/simple; bh=sw+euk2AZUSojRcvrV7jLAishCzKBceO1HRJvLkyXvw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=F3ETa4z+3I3X9nvHdrG6eVsoVOq1p09NF1iVGgjnWhck8W0FNU5p7gTDSd0zrs956HHT1O65dhp9/EHm27NztqhPVj6DK3isVOdrECFANqMQEyCci0IydAGHIoKineU1j0D6RKlyo+DbnPtcl92cY1i2TxVw857oIfxUin3Sgig= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=AJr+UKKA; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="AJr+UKKA" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936269; x=1786472269; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=sw+euk2AZUSojRcvrV7jLAishCzKBceO1HRJvLkyXvw=; b=AJr+UKKAj+5AVr4HnroKhdIrR72dmCZc+qltdgJy8YZVWsmAtIcRPFZ/ HKbXpMfvG3hCrNsawkjUpyN8LTAaEFqgg/nxMAMsIJCDRxX9U866G9fAV sLvsIgQHqdI5kC70QRo1Ez0CGi7vcgwyj4WSZxEzOgV2Xm7D2vx0QV8lA EvHIEAFelX8Do4LBg8uJN+1OiPemvyqF7BXEWHXJutk1OQYd1Z57CC9EB pnqL5oHGb92X+9dHI4iUWBBDEfC1NlUrsl29yiGNJsttYX6JE8OKezS+H 3euSxRkwmplOKe2hctH2nv0iZEDFGw25IMLroWpmLhrnMHSLqr/yiY4K6 Q==; X-CSE-ConnectionGUID: FXP517CJTjyVc3/nyFI2Rg== X-CSE-MsgGUID: mFOg0AoaSR2BIygjcIyIJA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277523" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277523" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: u+tWpg20QKCVbNa/HSGLXw== X-CSE-MsgGUID: nEo+oUipT6ieuRz44QGeQg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825705" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 27/32] fs,x86/resctrl: Compute number of RMIDs as minimum across resources Date: Mon, 11 Aug 2025 11:17:01 -0700 Message-ID: <20250811181709.6241-28-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" resctrl assumes that only the L3 resource supports monitor events, so it simply takes the rdt_resource::num_rmid from RDT_RESOURCE_L3 as the number of RMIDs. The addition of telemetry events in a different resource breaks that assumption. Compute the number of available RMIDs as the minimum value across all mon capable resources (analogous to how the number of CLOSIDs is computed across alloc capable resources). Note that mount time enumeration of the telemetry resource means that this number can be reduced. If this happens, then some memory will be wasted as the allocations for rdt_l3_mon_domain::states[] will be larger than needed. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/core.c | 15 +++++++++++++-- fs/resctrl/rdtgroup.c | 5 +++++ 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 2b011f9efc73..0284da075ea6 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -110,12 +110,23 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESO= URCES] =3D { }, }; =20 +/** + * resctrl_arch_system_num_rmid_idx - Compute number of supported RMIDs + * (minimum across all mon capable resource) + * + * Return: Number of supported RMIDs at time of call. Note that mount time + * enumeration of resources may reduce the number. + */ u32 resctrl_arch_system_num_rmid_idx(void) { - struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 num_rmids =3D U32_MAX; + struct rdt_resource *r; + + for_each_mon_capable_rdt_resource(r) + num_rmids =3D min(num_rmids, r->num_rmid); =20 /* RMID are independent numbers for x86. num_rmid_idx =3D=3D num_rmid */ - return r->num_rmid; + return num_rmids =3D=3D U32_MAX ? 0 : num_rmids; } =20 struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 55ad99bd77d2..5352480eb55c 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -4116,6 +4116,11 @@ void resctrl_offline_mon_domain(struct rdt_resource = *r, struct rdt_domain_hdr *h * During boot this may be called before global allocations have been made= by * resctrl_mon_l3_resource_init(). * + * This routine is called at resctrl init time. The number of supported RM= IDs + * may be reduced if additional mon capable resources are enumerated at mo= unt + * time. This means the rdt_l3_mon_domain::states[] allocations may be lar= ger + * than needed. + * * Returns 0 for success, or -ENOMEM. */ static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3= _mon_domain *d) --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 1434B2E2DD5 for ; Mon, 11 Aug 2025 18:17:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936271; cv=none; b=EMSY0cH3IjLWDfW/2JJUvoLQ1NvTlku8bfPCCLqOZ/uPLpELKlsJiVi1wl8lAhFZGd12Xn+f+keu8kGzQ0+WCJXwzwYfPTrLXtwPARKGPYN3FIAbNhskeJV0chb4Che/Hx9fJucoiLDYdoPBEulz0dElg8wIqJCrwGxUGHlQLns= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936271; c=relaxed/simple; bh=IKYOQlaLkDfqxldhdwZ4iBsq80GjbczOCwCWrZU2NHQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SQFMUxzoP23lIa2iNZI9ux27GPYxuTVGvXCqN6hWraV7OmdFl2d7xti5hfA6cyjIpCAcEdXhh9HHPhbvepQ2MsQAL07UtfpeOwH5sg6jZB3eYBEJFPk+QJm8r7GrAY78RU1FXqF9ERFzhdzMcPIApNlMG5aEwKgTn6qpathGF40= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=ak+g1wHJ; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="ak+g1wHJ" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936269; x=1786472269; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=IKYOQlaLkDfqxldhdwZ4iBsq80GjbczOCwCWrZU2NHQ=; b=ak+g1wHJdtgf9juPHjCwUVK0p81p7e3uFY+rPWTJ4GFUxF+vKHi2bhsP it5akpsNYhsyyURG+cxGRiceQxj+Iy55XTIKYadKtz1gGmpUu7GVddgfB 0NVxwc9mnT/GwN+zZ6+9GR2eF3fCYGpxNp04WUd6Ul0JStIwOttp2e2S5 d5O2Se0ouK7/XCJu+hNymHvdrmG3si2sh7LKZaNAUOVq7BQX00NpAJzkQ gs+qTHe0cgA84c6QX260s3YKFS+6MzYdsr/yfjefSAvbqUT4aspyvh5mG Le5y4HaSjVAmoy311RnEpui4Xf/sMBRr2MQDW+ms4it6dzM/IK+YGLGJF g==; X-CSE-ConnectionGUID: LUET71rwTJm8NJyww/I0Zw== X-CSE-MsgGUID: VI+caHamSvG2ABVXELS8vA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277539" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277539" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: TU5NnaykTSWYst8ZBkie9g== X-CSE-MsgGUID: VfFlBiyVSrCGX3kemrFEyw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825708" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:26 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 28/32] fs/resctrl: Move RMID initialization to first mount Date: Mon, 11 Aug 2025 11:17:02 -0700 Message-ID: <20250811181709.6241-29-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" resctrl assumesthat the number of supported RMIDs is enumerated during early initialization. Telemetry monitor events break that assumption because they are not enumerated in early initialization and may support a different number of RMIDs compared to L3 monitor features. Delay allocation and initialization of rmid_ptrs[] until first mount. Rename routines to match what they now do: dom_data_init() -> setup_rmid_lru_list() dom_data_exit() -> free_rmid_lru_list() Signed-off-by: Tony Luck --- fs/resctrl/internal.h | 4 ++++ fs/resctrl/monitor.c | 47 ++++++++++--------------------------------- fs/resctrl/rdtgroup.c | 7 +++++++ 3 files changed, 22 insertions(+), 36 deletions(-) diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 9c1f821279bb..7abe3cb5c7ff 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -354,6 +354,10 @@ int closids_supported(void); =20 void closid_free(int closid); =20 +int setup_rmid_lru_list(void); + +void free_rmid_lru_list(void); + int alloc_rmid(u32 closid); =20 void free_rmid(u32 closid, u32 rmid); diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 0d9c8d4e0e9c..4c13b55db995 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -802,20 +802,19 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_dom= ain *dom, unsigned long del schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } =20 -static int dom_data_init(struct rdt_resource *r) +int setup_rmid_lru_list(void) { u32 idx_limit =3D resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry =3D NULL; - int err =3D 0, i; u32 idx; + int i; =20 - mutex_lock(&rdtgroup_mutex); + if (rmid_ptrs) + return 0; =20 rmid_ptrs =3D kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) { - err =3D -ENOMEM; - goto out_unlock; - } + if (!rmid_ptrs) + return -ENOMEM; =20 for (i =3D 0; i < idx_limit; i++) { entry =3D &rmid_ptrs[i]; @@ -828,31 +827,20 @@ static int dom_data_init(struct rdt_resource *r) /* * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and * are always allocated. These are used for the rdtgroup_default - * control group, which will be setup later in resctrl_init(). + * control group, which was setup earlier in rdtgroup_setup_default(). */ idx =3D resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID); entry =3D __rmid_entry(idx); list_del(&entry->list); =20 -out_unlock: - mutex_unlock(&rdtgroup_mutex); - - return err; + return 0; } =20 -static void dom_data_exit(struct rdt_resource *r) +void free_rmid_lru_list(void) { - mutex_lock(&rdtgroup_mutex); - - if (!r->mon_capable) - goto out_unlock; - kfree(rmid_ptrs); rmid_ptrs =3D NULL; - -out_unlock: - mutex_unlock(&rdtgroup_mutex); } =20 #define MON_EVENT(_eventid, _name, _res, _fp) \ @@ -914,7 +902,8 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id= eventid) * resctrl_mon_l3_resource_init() - Initialise global monitoring structure= s. * * Allocate and initialise global monitor resources that do not belong to a - * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists. + * specific domain. i.e. the closid_num_dirty_rmid[] used to find the CLOS= ID + * with the cleanest set of RMIDs. * Called once during boot after the struct rdt_resource's have been confi= gured * but before the filesystem is mounted. * Resctrl's cpuhp callbacks may be called before this point to bring a do= main @@ -925,7 +914,6 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id= eventid) int resctrl_mon_l3_resource_init(void) { struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); - int ret; =20 if (!r->mon_capable) return 0; @@ -947,15 +935,6 @@ int resctrl_mon_l3_resource_init(void) closid_num_dirty_rmid =3D tmp; } =20 - ret =3D dom_data_init(r); - if (ret) { - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid =3D NULL; - } - return ret; - } - if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) { mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable =3D true; resctrl_file_fflags_init("mbm_total_bytes_config", @@ -977,12 +956,8 @@ int resctrl_mon_l3_resource_init(void) =20 void resctrl_mon_l3_resource_exit(void) { - struct rdt_resource *r =3D resctrl_arch_get_resource(RDT_RESOURCE_L3); - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { kfree(closid_num_dirty_rmid); closid_num_dirty_rmid =3D NULL; } - - dom_data_exit(r); } diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 5352480eb55c..d1ecc5cd3089 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -2599,6 +2599,12 @@ static int rdt_get_tree(struct fs_context *fc) goto out; } =20 + if (resctrl_arch_mon_capable()) { + ret =3D setup_rmid_lru_list(); + if (ret) + goto out; + } + ret =3D rdtgroup_setup_root(ctx); if (ret) goto out; @@ -4408,4 +4414,5 @@ void resctrl_exit(void) */ =20 resctrl_mon_l3_resource_exit(); + free_rmid_lru_list(); } --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 AEAF82E5B23 for ; Mon, 11 Aug 2025 18:17:50 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936273; cv=none; b=lRtfbOnss5XW8nn2aPz3ZjwKPMfwA2PH8G1f5BgeqlQXLCGV8nRgMsn3y6U1RkPWr8MqQI4taVrtpapgtf0Ui5kfE7ep2+0nIFl9t4hmtozjd0Je3ZFEnKBhRFwGqD7THwRzDqA4wLT0rxwpILv/w96VJGJF8J0ND4Jaly/K4B4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936273; c=relaxed/simple; bh=sgId1FpAHkWwdJsgc/05Ii+a6vl/BCuVqfaaJBncn0M=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=euVe+OrvEMPVEroO/huB4NGC8GIs1JVFH0do8p6fE7+/XlESFX8EQe2QV+ZDABt2Naa11tDXYptGap4vyhgyPHEsBso2+BrgQ4t0lFwr0F1sVrZYGeIa1vwsNY5BNXog0imDUcAbiohb0iQv+Djs1pUA+0N5s2kzJxuXWfFfJG4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Diu+mZCa; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Diu+mZCa" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936271; x=1786472271; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=sgId1FpAHkWwdJsgc/05Ii+a6vl/BCuVqfaaJBncn0M=; b=Diu+mZCaLPxCLMKsDYavX/jC+L9Ju+k7XT6wr5ruljEEefI21OQS3InH xJmY6uJgtpsjjNRJ9Jh10gIauEaHwHl5/AeB80+NsG/qUmOltzPCyE/vH 42n63UUYTt3Za95cMOcAs4PVtr1dsCZuqwFjtoytfsUgTbpGrBNV6HmnX dvJNr5EmIUFiu6D31vJG/Cj1bjBL73peHxNSa+XvCLgEcuHLtL21Wo3RS L4nG+jYYSex7n1inch7qYfnx2H1X/SBCba9r2yKlqIy9wuX05Wb/AeLEw msA4+s7R7eJRvanjIOH20NDm9n/fUzITgEETmJJo9oM2diS71+gZoHfyK A==; X-CSE-ConnectionGUID: xh1Vkn5iQZGe3UZQAvkwhQ== X-CSE-MsgGUID: IvgC2/XNTgW65oDWMs1vJw== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277556" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277556" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 X-CSE-ConnectionGUID: 6BUEeamvQ42pTXGhWEsb6g== X-CSE-MsgGUID: QphSABpkSg2MdlbDwJY3kw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825711" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 29/32] x86/resctrl: Enable RDT_RESOURCE_PERF_PKG Date: Mon, 11 Aug 2025 11:17:03 -0700 Message-ID: <20250811181709.6241-30-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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 RDT_RESOURCE_PERF_PKG resource is not marked as "mon_capable" during early resctrl initialization. This means that the domain lists for the resource are not built when the CPU hot plug notifiers are registered. Set the global rdt_mon_capable (to cover the case when none of the L3 monitor events are enabled). Mark the resource as mon_capable and call domain_add_cpu_mon() for each online CPU to build the domain lists in the first call to the resctrl_arch_pre_mount() hook. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/core.c | 17 ++++++++++++++++- arch/x86/kernel/cpu/resctrl/intel_aet.c | 4 ++++ 2 files changed, 20 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resct= rl/core.c index 0284da075ea6..d1e2c5e2501f 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -750,14 +750,29 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) =20 void resctrl_arch_pre_mount(void) { + struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_re= sctrl; static atomic_t only_once =3D ATOMIC_INIT(0); - int old =3D 0; + int cpu, old =3D 0; =20 if (!atomic_try_cmpxchg(&only_once, &old, 1)) return; =20 if (!intel_aet_get_events()) return; + + if (!r->mon_capable) + return; + + /* + * Late discovery of telemetry events means the domains for the + * resource were not built. Do that now. + */ + cpus_read_lock(); + mutex_lock(&domain_list_lock); + for_each_online_cpu(cpu) + domain_add_cpu_mon(cpu, r); + mutex_unlock(&domain_list_lock); + cpus_read_unlock(); } =20 enum { diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 96c454748320..4afc99e74cef 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -258,6 +258,10 @@ static int discover_events(struct event_group *e, stru= ct pmt_feature_group *p) else r->num_rmid =3D e->num_rmids; =20 + pr_info("%s %s monitoring detected\n", r->name, e->name); + r->mon_capable =3D true; + rdt_mon_capable =3D true; + return 0; } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 EE52B2C21D0 for ; Mon, 11 Aug 2025 18:17:50 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936273; cv=none; b=GITEf/uWyRQBF2dPx2ryfbk/KkfcmNUU+tuY6WCmCLsGL/WfdElnCqzUtamysP9BxPp2dF+PnVCxjG1M26dtwm+mIbVjZmzG1WpOX+SleZjsqD+Ey2gSRrJknf7b+qPxhe0DlwE4POTN1qpU4wc0/Degllfj9QFHP4+DjUuWzjg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936273; c=relaxed/simple; bh=EddyqxZoO2oB2oKRo3cjCHXi9KMfEvhPkZ+9MhTxLTw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=iMvmVzEFaaEy2lsjw4MKfKNPXPmAg9oyW2HcOmTkM0hbIsqZf7xcieCr38kDYzhVWGwrKH8aggYfagEkKPZwcrpFASvTQ35236Pq8YmfqFvsG37hQtT7fFNW9Cm+PGsRTIyCs9wb0ysdaPc0sDxTEzI0ztcYejngf/C3E8OfdGA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=WTs5I/2N; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="WTs5I/2N" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936271; x=1786472271; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=EddyqxZoO2oB2oKRo3cjCHXi9KMfEvhPkZ+9MhTxLTw=; b=WTs5I/2Nh2dVH0wQXRDreNTuqFha8GIlSo9xOoxNmNnZLnp7/vX2uar7 +pQO3JnQxiicjiNMCjwM+jy72ixUu/i+LKZCCywe2CBmxwM8rFYhJGidu jL5yDTQED/oDBBHJLLnkjM7lwn/Nin01MLMgzpmxcGFoTIQOI1l4jY/jA rApLqnZLkWQktBdgAIMuynAwA3Z3Aw94+GHB+2GlY8srEu+ADK0V6839B H+sJhQ9vNFr+8HYZHttQrVnKG6Fr/7o71GSC24iYF1+Xulgpy7B4LOF6R Bp0utnx7zusVIpWAJ7t0cB3PziueA4jc4ruy5wU+Rc+GeAoOcLAy1ULds g==; X-CSE-ConnectionGUID: I5c529LsSPeTCmeVPHlWdA== X-CSE-MsgGUID: q/MQ5hiWRlCiVbq1VBbCkg== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277571" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277571" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:28 -0700 X-CSE-ConnectionGUID: j6FQF43vTnWqpZnBthawCg== X-CSE-MsgGUID: 6F+KuQiOTXW7zskkXqh8iA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825714" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 30/32] fs/resctrl: Provide interface to create architecture specific debugfs area Date: Mon, 11 Aug 2025 11:17:04 -0700 Message-ID: <20250811181709.6241-31-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" All files below /sys/fs/resctrl are considered user ABI. This leaves no place for architectures to provide additional interfaces. Add resctrl_debugfs_mon_info_arch_mkdir() which creates a directory in the debugfs file system for a resource. Naming follows the layout of the main resctrl hierarchy: /sys/kernel/debug/resctrl/info/{resource}_MON/{arch} The {arch} last level directory name matches the output of the user level "uname -m" command. Architecture code may use this directory for debug information, or for minor tuning of features. It must not be used for basic feature enabling as debugfs may not be configured/mounted on production systems. Suggested-by: Reinette Chatre Signed-off-by: Tony Luck --- include/linux/resctrl.h | 9 +++++++++ fs/resctrl/rdtgroup.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index c1cfba3c8422..b6af933ca3f9 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -571,6 +571,15 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource = *r); extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; =20 +/** + * resctrl_debugfs_mon_info_arch_mkdir() - Create a debugfs info directory. + * Removed by resctrl_exit(). + * @r: Resource (must be mon_capable). + * + * Return: dentry pointer on success, or NULL on error. + */ +struct dentry *resctrl_debugfs_mon_info_arch_mkdir(struct rdt_resource *r); + int resctrl_init(void); void resctrl_exit(void); =20 diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index d1ecc5cd3089..fccac3da90cb 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -24,6 +24,7 @@ #include #include #include +#include =20 #include =20 @@ -75,6 +76,8 @@ static void rdtgroup_destroy_root(void); =20 struct dentry *debugfs_resctrl; =20 +static struct dentry *debugfs_resctrl_info; + /* * Memory bandwidth monitoring event to use for the default CTRL_MON group * and each new CTRL_MON group created by the user. Only relevant when @@ -4355,6 +4358,31 @@ int resctrl_init(void) return ret; } =20 +/* + * Create /sys/kernel/debug/resctrl/info/{r->name}_MON/{arch} directory + * by request for architecture to use for debugging or minor tuning. + * Basic functionality of features must not be controlled by files + * added to this directory as debugfs may not be configured/mounted + * on production systems. + */ +struct dentry *resctrl_debugfs_mon_info_arch_mkdir(struct rdt_resource *r) +{ + struct dentry *moninfodir; + char name[32]; + + if (!r->mon_capable) + return NULL; + + if (!debugfs_resctrl_info) + debugfs_resctrl_info =3D debugfs_create_dir("info", debugfs_resctrl); + + sprintf(name, "%s_MON", r->name); + + moninfodir =3D debugfs_create_dir(name, debugfs_resctrl_info); + + return debugfs_create_dir(utsname()->machine, moninfodir); +} + static bool resctrl_online_domains_exist(void) { struct rdt_resource *r; @@ -4406,6 +4434,7 @@ void resctrl_exit(void) =20 debugfs_remove_recursive(debugfs_resctrl); debugfs_resctrl =3D NULL; + debugfs_resctrl_info =3D NULL; unregister_filesystem(&rdt_fs_type); =20 /* --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 9FA222E610C for ; Mon, 11 Aug 2025 18:17:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936274; cv=none; b=aJsudOSFu6bOaCTpyEZ4d0k/SfcBe9JdR/AhKN+hYB8EhHMGkwTcmrxhyNIW9bJNKucm5mOC3c2MJNGUO0qIhekGvhpje/WcAnsk69WuGjyTGq74kxYQOItdw5DLCa9Fgr2j9bLM986iEWiXBRWKsrtyCT2uH5w2gT+q4hveoiw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936274; c=relaxed/simple; bh=47HI7bCkBNvQJ+DtUST6W3uW4FMOR3SyHta8tGZ5LJM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=E7vYFyq9bKyrb3yr90coa86kQx1qNX9RsXvOIQl31LpamH6Z7V+BswjbtPgsHbKtela8uL+o2fe5VtUu4YtRsoLqRMGGTdnKn8IH18RCBkWSNwIU4zSd4W0zXO4AKMqmNU38TTRNRMEqwDBQT724CKIsT6Fka18+XNVGoN6yN4M= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Y3jyZmKB; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Y3jyZmKB" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936272; x=1786472272; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=47HI7bCkBNvQJ+DtUST6W3uW4FMOR3SyHta8tGZ5LJM=; b=Y3jyZmKB2bm6AKQktlzQy3rUU2i1W0rYnNVAYiKhLY+aDgU0lm/H4Ghu graXKkG/ncZqgrq99X3yt0S7iRo5kvHpKj9R3VepK/FwuQj0BmwRtEbXa ekny4R/+AgNQHA4LdgJ5VHkFB0Q0EIhmqq7iFUDh8E4sQ8tTCdA62WQZi vbB0YPOp9OiaTKMx0g4TjxbEhUbSxomIHg/aYwA25vJKgZFuavaZ85Z7e PGYz0MB1JEXcq8rfowDuiW/wZu25xsaOleX/hQgHJDSMUbCDIldRKBi6F PqL2ezVQ97D6L/9HV3v0oKONCxXcXLBHtXHqv7A9cJLk/e5K4AnB/beyZ Q==; X-CSE-ConnectionGUID: 72dtMDMGRKGdpH5q1FI9Wg== X-CSE-MsgGUID: RcC/XAsITBCnUTofeDBhBA== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277586" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277586" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:28 -0700 X-CSE-ConnectionGUID: VB9MA2rvSBGOEPbA8oYohw== X-CSE-MsgGUID: 4+yvT43TR0qx8FG1fov7pA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825717" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 31/32] x86/resctrl: Add debugfs files to show telemetry aggregator status Date: Mon, 11 Aug 2025 11:17:05 -0700 Message-ID: <20250811181709.6241-32-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Each telemetry aggregator provides three status registers at the top end of MMIO space after all the per-RMID per-event counters: agg_data_loss_count: This counts the number of times that this aggregator failed to accumulate a counter value supplied by a CPU core. agg_data_loss_timestamp: This is a "timestamp" from a free running 25MHz uncore timer indicating when the most recent data loss occurred. last_update_timestamp: Another 25MHz timestamp indicating when the most recent counter update was successfully applied. Create files in /sys/kernel/debug/resctrl/info/PERF_PKG_MON/x86_64/ to display the value of each of these status registers for each aggregator in each enabled event group. Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/resctrl/intel_aet.c | 53 +++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/= resctrl/intel_aet.c index 4afc99e74cef..ff70f2b18165 100644 --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -13,6 +13,7 @@ =20 #include #include +#include #include #include #include @@ -299,6 +300,55 @@ static bool get_pmt_feature(enum pmt_feature_id featur= e, struct event_group **ev return false; } =20 +static int status_read(void *priv, u64 *val) +{ + void __iomem *info =3D (void __iomem *)priv; + + *val =3D readq(info); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, status_read, NULL, "%llu\n"); + +static void make_status_files(struct dentry *dir, struct event_group *e, i= nt pkg, int instance) +{ + void *info =3D (void __force *)e->pkginfo[pkg]->addrs[instance] + e->mmio= _size; + char name[64]; + + sprintf(name, "%s_pkg%d_agg%d_data_loss_count", e->name, pkg, instance); + debugfs_create_file(name, 0400, dir, info - 24, &status_fops); + + sprintf(name, "%s_pkg%d_agg%d_data_loss_timestamp", e->name, pkg, instanc= e); + debugfs_create_file(name, 0400, dir, info - 16, &status_fops); + + sprintf(name, "%s_pkg%d_agg%d_last_update_timestamp", e->name, pkg, insta= nce); + debugfs_create_file(name, 0400, dir, info - 8, &status_fops); +} + +static void create_debug_event_status_files(struct dentry *dir, struct eve= nt_group *e) +{ + int num_pkgs =3D topology_max_packages(); + + for (int i =3D 0; i < num_pkgs; i++) + for (int j =3D 0; j < e->pkginfo[i]->num_regions; j++) + make_status_files(dir, e, i, j); +} + +static void create_debugfs_status_file(void) +{ + struct rdt_resource *r =3D &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_re= sctrl; + struct event_group *evg; + struct dentry *infodir; + + infodir =3D resctrl_debugfs_mon_info_arch_mkdir(r); + if (!infodir) + return; + + list_for_each_entry(evg, &active_event_groups, list) + create_debug_event_status_files(infodir, evg); +} + /* * Ask OOBMSM discovery driver for all the RMID based telemetry groups * that it supports. @@ -314,6 +364,9 @@ bool intel_aet_get_events(void) known_perf_event_groups, ARRAY_SIZE(known_perf_event_groups)); =20 + if (ret1 || ret2) + create_debugfs_status_file(); + return ret1 || ret2; } =20 --=20 2.50.1 From nobody Sun Oct 5 00:12:25 2025 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.13]) (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 9E07F2E6105 for ; Mon, 11 Aug 2025 18:17:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.13 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936274; cv=none; b=UVpJ96cCimaWzRkqrufA3P/E5btN1KR6w+Ihv82eJ6aVeSEki7xqhfubnh88SrdZVxGQbVFWv9vT6QzkU2U2cMo+hE+KD1U/tiHob6scOL48GCfrFdLV1gwhGORFvhOYUIFj2wEQcNFU8FBOmWsnI8JCxP7b6w3pFWiUGceD0RM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754936274; c=relaxed/simple; bh=gKPqMlcKrpchqfWY2TEm0WmAYj3krKqq8dwDF38mFfg=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=BR6B6vHqIxLPc87DYk73m6muOn1lnwKrBsFkqfJEwhZNEKgu+QfC9Lzs2JrHSLav2cEq4Uqkps5rc7ZNg3oc0lEM4G7xC6WEp2AiOLIt7K+E2HTOeXxP6VIJAZBgfLtY27VhKlCcbNF1GDlrtTraRqrByvM7zTIzoPQ5j3x1PG0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=BZUhF0Zn; arc=none smtp.client-ip=198.175.65.13 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="BZUhF0Zn" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754936272; x=1786472272; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=gKPqMlcKrpchqfWY2TEm0WmAYj3krKqq8dwDF38mFfg=; b=BZUhF0Zn8fsgZbRw8Jf0KyRSg6rfhIQKEbdjsmn4Dmu2+j5x17HS3o+H g/oD5p0xH6NRg3eh0dcbf2ty731Ivqf8HONW7lmVdltyR6lX4/Z/CGg/V ioNYXjvqhrdzfzbJa91FpUQ+aWYemOjyBP2s6ipaaATq3zmnjfTY7jQPF 3Ca762UdUZVyhNlaTsmsg8U/LDe+7fKaVGE8Tp+BHnObrUNbucNGMe+Ks phI7T8zviJTYldKCat7Xgl9/ZvcjO0kektv/+ydDisp3RMIb3nS+CDNeA bpDWvFKXqFzog9t/LMcHURAw9V2rGykoxipGPtswT8YY+jjKDovSwLNCv A==; X-CSE-ConnectionGUID: xyR7qe7TTSuR7Lab1XIeaw== X-CSE-MsgGUID: SR2qB3ZIS/m/xGGTrRdiOQ== X-IronPort-AV: E=McAfee;i="6800,10657,11518"; a="68277596" X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="68277596" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:28 -0700 X-CSE-ConnectionGUID: vDECg1C4TAu3nfKZyCzbAg== X-CSE-MsgGUID: oD4e0b4SSu+OJYiphBdpiw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,278,1747724400"; d="scan'208";a="196825720" Received: from puneetse-mobl.amr.corp.intel.com (HELO agluck-desk3.home.arpa) ([10.124.221.229]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Aug 2025 11:17:27 -0700 From: Tony Luck To: Fenghua Yu , Reinette Chatre , Maciej Wieczor-Retman , Peter Newman , James Morse , Babu Moger , Drew Fustini , Dave Martin , Anil Keshavamurthy , Chen Yu Cc: x86@kernel.org, linux-kernel@vger.kernel.org, patches@lists.linux.dev, Tony Luck Subject: [PATCH v8 32/32] x86,fs/resctrl: Update Documentation for package events Date: Mon, 11 Aug 2025 11:17:06 -0700 Message-ID: <20250811181709.6241-33-tony.luck@intel.com> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250811181709.6241-1-tony.luck@intel.com> References: <20250811181709.6241-1-tony.luck@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" Each "mon_data" directory is now divided between L3 events and package events. The "info/PERF_PKG_MON" directory contains parameters for perf events. Signed-off-by: Tony Luck --- Documentation/filesystems/resctrl.rst | 85 +++++++++++++++++++++++---- 1 file changed, 75 insertions(+), 10 deletions(-) diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesyst= ems/resctrl.rst index c7949dd44f2f..065f9fdd8f95 100644 --- a/Documentation/filesystems/resctrl.rst +++ b/Documentation/filesystems/resctrl.rst @@ -167,7 +167,7 @@ with respect to allocation: bandwidth percentages are directly applied to the threads running on the core =20 -If RDT monitoring is available there will be an "L3_MON" directory +If L3 monitoring is available there will be an "L3_MON" directory with the following files: =20 "num_rmids": @@ -261,6 +261,18 @@ with the following files: bytes) at which a previously used LLC_occupancy counter can be considered for re-use. =20 +If telemetry monitoring is available there will be an "PERF_PKG_MON" direc= tory +with the following files: + +"num_rmids": + The number of telemetry RMIDs supported. If this is different + from the number reported in the L3_MON directory the limit + on the number of "CTRL_MON" + "MON" directories is the + minimum of the values. + +"mon_features": + Lists the telemetry monitoring events that are enabled on this system. + Finally, in the top level of the "info" directory there is a file named "last_cmd_status". This is reset with every "command" issued via the file system (making new directories or writing to any of the @@ -366,15 +378,36 @@ When control is enabled all CTRL_MON groups will also= contain: When monitoring is enabled all MON groups will also contain: =20 "mon_data": - This contains a set of files organized by L3 domain and by - RDT event. E.g. on a system with two L3 domains there will - be subdirectories "mon_L3_00" and "mon_L3_01". Each of these - directories have one file per event (e.g. "llc_occupancy", - "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these - files provide a read out of the current value of the event for - all tasks in the group. In CTRL_MON groups these files provide - the sum for all tasks in the CTRL_MON group and all tasks in - MON groups. Please see example section for more details on usage. + This contains a set of directories, one for each instance + of an L3 cache, or of a processor package. The L3 cache + directories are named "mon_L3_00", "mon_L3_01" etc. The + package directories "mon_PERF_PKG_00", "mon_PERF_PKG_01" etc. + + Within each directory there is one file per event. In + the L3 directories: "llc_occupancy", "mbm_total_bytes", + and "mbm_local_bytes". In the PERF_PKG directories: "core_energy", + "activity", etc. + + "core_energy" reports a floating point number for the energy + (in Joules) used by CPUs for each RMID. + + "activity" also reports a floating point value (in Farads). + This provides an estimate of work done independent of the + frequency that the CPUs used for execution. + + Note that these two counters only measure energy/activity + in the "core" of the CPU (arithmetic units, TLB, L1 and L2 + caches, etc.). They do not include L3 cache, memory, I/O + devices etc. + + All other events report decimal integer values. + + In a MON group these files provide a read out of the current + value of the event for all tasks in the group. In CTRL_MON groups + these files provide the sum for all tasks in the CTRL_MON group + and all tasks in MON groups. Please see example section for more + details on usage. + On systems with Sub-NUMA Cluster (SNC) enabled there are extra directories for each node (located within the "mon_L3_XX" directory for the L3 cache they occupy). These are named "mon_sub_L3_YY" @@ -1300,6 +1333,38 @@ Example with C:: resctrl_release_lock(fd); } =20 +Debugfs +=3D=3D=3D=3D=3D=3D=3D +In addition to the use of debugfs for tracing of pseudo-locking +performance, architecture code may create debugfs directories +associated with monitoring features for a specific resource. + +The full pathname for these is in the form: + + /sys/kernel/debug/resctrl/info/{resource_name}_MON/{arch}/ + +The prescence, names, and format of these files will vary +between architectures even if the same resource is present. + +PERF_PKG_MON/x86_64 +------------------- +Three files are present per telemetry aggregator instance +that show when and how often the hardware has failed to +collect and accumulate data from the CPUs. + +agg_data_loss_count: + This counts the number of times that this aggregator + failed to accumulate a counter value supplied by a CPU. + +agg_data_loss_timestamp: + This is a "timestamp" from a free running 25MHz uncore + timer indicating when the most recent data loss occurred. + +last_update_timestamp: + Another 25MHz timestamp indicating when the + most recent counter update was successfully applied. + + Examples for RDT Monitoring along with allocation usage =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D Reading monitored data --=20 2.50.1