linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: James Morse <james.morse@arm.com>
To: x86@kernel.org, linux-kernel@vger.kernel.org
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	H Peter Anvin <hpa@zytor.com>, Babu Moger <Babu.Moger@amd.com>,
	James Morse <james.morse@arm.com>,
	shameerali.kolothum.thodi@huawei.com,
	D Scott Phillips OS <scott@os.amperecomputing.com>,
	lcherian@marvell.com, bobo.shaobowang@huawei.com,
	tan.shaopeng@fujitsu.com, Jamie Iles <quic_jiles@quicinc.com>,
	Cristian Marussi <cristian.marussi@arm.com>,
	Xin Hao <xhao@linux.alibaba.com>,
	xingxin.hx@openanolis.org, baolin.wang@linux.alibaba.com
Subject: [PATCH v4 12/21] x86/resctrl: Calculate bandwidth from the previous __mon_event_count() chunks
Date: Tue, 12 Apr 2022 12:44:10 +0000	[thread overview]
Message-ID: <20220412124419.30689-13-james.morse@arm.com> (raw)
In-Reply-To: <20220412124419.30689-1-james.morse@arm.com>

mbm_bw_count() is only called by the mbm_handle_overflow() worker once a
second. It reads the hardware register, calculates the bandwidth and
updates m->prev_bw_msr which is used to hold the previous hardware register
value.

Operating directly on hardware register values makes it difficult to make
this code architecture independent, so that it can be moved to /fs/,
making the mba_sc feature something resctrl supports with no additional
support from the architecture.
Prior to calling mbm_bw_count(), mbm_update() reads from the same hardware
register using __mon_event_count().

Change mbm_bw_count() to use the current chunks value most recently saved by
__mon_event_count(). This removes an extra call to __rmid_read().
Instead of using m->prev_msr to calculate the number of chunks seen,
use the rr->val that was updated by __mon_event_count(). This removes an
extra call to mbm_overflow_count() and get_corrected_mbm_count().
Calculating bandwidth like this means mbm_bw_count() no longer operates
on hardware register values directly.

Reviewed-by: Jamie Iles <quic_jiles@quicinc.com>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
---
Changes since v3:
 * Reset rr.val before each use to avoid over counting.
 * Fixed typos in kerneldoc.

Changes since v2:
 * Expanded commit message

Changes since v1:
 * This patch was rewritten
---
 arch/x86/kernel/cpu/resctrl/internal.h |  4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c  | 25 ++++++++++++++++---------
 2 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3b9e43ba7590..46062099d69e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -289,7 +289,7 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
  * @prev_msr:	Value of IA32_QM_CTR for this RMID last time we read it
- * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw_chunks: Previous chunks value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
  * @delta_bw:	Difference between the current and previous bandwidth
  * @delta_comp:	Indicates whether to compute the delta_bw
@@ -297,7 +297,7 @@ struct rftype {
 struct mbm_state {
 	u64	chunks;
 	u64	prev_msr;
-	u64	prev_bw_msr;
+	u64	prev_bw_chunks;
 	u32	prev_bw;
 	u32	delta_bw;
 	bool	delta_comp;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index ac1a2e8998bb..a15f870363b2 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -315,7 +315,7 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 
 	if (rr->first) {
 		memset(m, 0, sizeof(struct mbm_state));
-		m->prev_bw_msr = m->prev_msr = tval;
+		m->prev_msr = tval;
 		return 0;
 	}
 
@@ -329,27 +329,32 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 }
 
 /*
+ * mbm_bw_count() - Update bw count from values previously read by
+ *		    __mon_event_count().
+ * @rmid:	The rmid used to identify the cached mbm_state.
+ * @rr:		The struct rmid_read populated by __mon_event_count().
+ *
  * Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps.
+ * and delta bandwidth in MBps. The chunks value previously read by
+ * __mon_event_count() is compared with the chunks value from the previous
+ * invocation. This must be called once per second to maintain values in MBps.
  */
 static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m = &rr->d->mbm_local[rmid];
-	u64 tval, cur_bw, chunks;
+	u64 cur_bw, chunks, cur_chunks;
 
-	tval = __rmid_read(rmid, rr->evtid);
-	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
-		return;
+	cur_chunks = rr->val;
+	chunks = cur_chunks - m->prev_bw_chunks;
+	m->prev_bw_chunks = cur_chunks;
 
-	chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width);
-	cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20;
+	cur_bw = (chunks * hw_res->mon_scale) >> 20;
 
 	if (m->delta_comp)
 		m->delta_bw = abs(cur_bw - m->prev_bw);
 	m->delta_comp = false;
 	m->prev_bw = cur_bw;
-	m->prev_bw_msr = tval;
 }
 
 /*
@@ -516,10 +521,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	 */
 	if (is_mbm_total_enabled()) {
 		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
+		rr.val = 0;
 		__mon_event_count(rmid, &rr);
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		rr.val = 0;
 		__mon_event_count(rmid, &rr);
 
 		/*
-- 
2.30.2


  parent reply	other threads:[~2022-04-12 13:04 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-12 12:43 [PATCH v4 00/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes James Morse
2022-04-12 12:43 ` [PATCH v4 01/21] x86/resctrl: Kill off alloc_enabled James Morse
2022-04-12 12:44 ` [PATCH v4 02/21] x86/resctrl: Merge mon_capable and mon_enabled James Morse
2022-04-12 12:44 ` [PATCH v4 03/21] x86/resctrl: Add domain online callback for resctrl work James Morse
     [not found]   ` <3acfb11b-eba2-3eb0-94d1-d24a24d03d1f@linux.alibaba.com>
2022-05-03  7:59     ` Xin Hao
2022-04-12 12:44 ` [PATCH v4 04/21] x86/resctrl: Group struct rdt_hw_domain cleanup James Morse
2022-04-12 12:44 ` [PATCH v4 05/21] x86/resctrl: Add domain offline callback for resctrl work James Morse
2022-04-12 12:44 ` [PATCH v4 06/21] x86/resctrl: Remove set_mba_sc()s control array re-initialisation James Morse
2022-04-12 12:44 ` [PATCH v4 07/21] x86/resctrl: Create mba_sc configuration in the rdt_domain James Morse
2022-05-17 16:18   ` Reinette Chatre
2022-06-07 12:07     ` James Morse
2022-05-18 16:06   ` Reinette Chatre
2022-04-12 12:44 ` [PATCH v4 08/21] x86/resctrl: Switch over to the resctrl mbps_val list James Morse
2022-05-17 16:19   ` Reinette Chatre
2022-06-07 12:07     ` James Morse
2022-04-12 12:44 ` [PATCH v4 09/21] x86/resctrl: Remove architecture copy of mbps_val James Morse
2022-04-12 12:44 ` [PATCH v4 10/21] x86/resctrl: Abstract and use supports_mba_mbps() James Morse
2022-04-12 12:44 ` [PATCH v4 11/21] x86/resctrl: Allow update_mba_bw() to update controls directly James Morse
2022-04-12 12:44 ` James Morse [this message]
2022-04-12 12:44 ` [PATCH v4 13/21] x86/resctrl: Add per-rmid arch private storage for overflow and chunks James Morse
2022-05-18 16:06   ` Reinette Chatre
2022-04-12 12:44 ` [PATCH v4 14/21] x86/resctrl: Allow per-rmid arch private storage to be reset James Morse
2022-04-12 12:44 ` [PATCH v4 15/21] x86/resctrl: Abstract __rmid_read() James Morse
2022-05-17 21:23   ` Reinette Chatre
2022-06-07 12:07     ` James Morse
2022-06-07 15:51       ` Reinette Chatre
2022-06-07 20:44   ` Fenghua Yu
2022-06-07 21:25   ` Fenghua Yu
2022-04-12 12:44 ` [PATCH v4 16/21] x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read() James Morse
2022-06-07 21:07   ` Fenghua Yu
2022-06-22 15:16     ` James Morse
2022-04-12 12:44 ` [PATCH v4 17/21] x86/resctrl: Move mbm_overflow_count() " James Morse
2022-04-12 12:44 ` [PATCH v4 18/21] x86/resctrl: Move get_corrected_mbm_count() " James Morse
2022-04-12 12:44 ` [PATCH v4 19/21] x86/resctrl: Rename and change the units of resctrl_cqm_threshold James Morse
2022-05-17 21:23   ` Reinette Chatre
2022-06-07 22:08   ` Fenghua Yu
2022-06-22 15:16     ` James Morse
2022-04-12 12:44 ` [PATCH v4 20/21] x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's boot_cpu_data James Morse
2022-04-12 12:44 ` [PATCH v4 21/21] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes James Morse
2022-04-18  8:09 ` [PATCH v4 00/21] " tan.shaopeng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220412124419.30689-13-james.morse@arm.com \
    --to=james.morse@arm.com \
    --cc=Babu.Moger@amd.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bobo.shaobowang@huawei.com \
    --cc=bp@alien8.de \
    --cc=cristian.marussi@arm.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=lcherian@marvell.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=quic_jiles@quicinc.com \
    --cc=reinette.chatre@intel.com \
    --cc=scott@os.amperecomputing.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=tan.shaopeng@fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --cc=xhao@linux.alibaba.com \
    --cc=xingxin.hx@openanolis.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).