linux-kernel - Re: [PATCH v2 2/2] scsi: ufs: core: move some irq handling back to hardirq (with time limit)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <c385f1c4-f27b-4dc7-b4a2-d35a9fc77a91@acm.org>
Date: Mon, 28 Jul 2025 08:19:11 -0700
From: Bart Van Assche <bvanassche@....org>
To: André Draszik <andre.draszik@...aro.org>,
 Neil Armstrong <neil.armstrong@...aro.org>,
 Alim Akhtar <alim.akhtar@...sung.com>, Avri Altman <avri.altman@....com>,
 "James E.J. Bottomley" <James.Bottomley@...senPartnership.com>,
 "Martin K. Petersen" <martin.petersen@...cle.com>
Cc: Peter Griffin <peter.griffin@...aro.org>,
 Tudor Ambarus <tudor.ambarus@...aro.org>,
 Will McVicker <willmcvicker@...gle.com>,
 Manivannan Sadhasivam <mani@...nel.org>, kernel-team@...roid.com,
 linux-arm-msm@...r.kernel.org, linux-samsung-soc@...r.kernel.org,
 linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org,
 stable@...r.kernel.org
Subject: Re: [PATCH v2 2/2] scsi: ufs: core: move some irq handling back to
 hardirq (with time limit)

On 7/28/25 7:49 AM, André Draszik wrote:
> Btw, my complete command was (should probably have added that
> to the commit message in the first place):
> 
> for rw in read write ; do
>      echo "rw: ${rw}"
>      for jobs in 1 8 ; do
>          echo "jobs: ${jobs}"
>          for it in $(seq 1 5) ; do
>              fio --name=rand${rw} --rw=rand${rw} \
>                  --ioengine=libaio --direct=1 \
>                  --bs=4k --numjobs=${jobs} --size=32m \
>                  --runtime=30 --time_based --end_fsync=1 \
>                  --group_reporting --filename=/foo \
>              | grep -E '(iops|sys=|READ:|WRITE:)'
>              sleep 5
>          done
>      done
> done

Please run performance tests in recovery mode against a block
device (/dev/block/sd...) instead of running performance tests on
top of a filesystem. One possible approach for retrieving the block
device name is as follows:

adb shell readlink /dev/block/by-name/userdata

There may be other approaches for retrieving the name of the block
device associated with /data. Additionally, tuning for maximum
performance is useful because it eliminates impact from the process
scheduler on block device performance measurement. An extract from a
scrip that I use myself to measure block device performance on Pixel
devices is available below.

Best regards,

Bart.


optimize() {
     local clkgate_enable c d devfreq disable_cpuidle governor nomerges 
iostats
     local target_freq ufs_irq_path

     if [ "$1" = performance ]; then
	clkgate_enable=0
	devfreq=max
	disable_cpuidle=1
	governor=performance
	# Enable I/O statistics because the performance impact is low and
	# because fio reports the I/O statistics.
	iostats=1
	# Disable merging to make tests follow the fio arguments.
	nomerges=2
	target_freq=cpuinfo_max_freq
	persist_logs=false
     else
	clkgate_enable=1
	devfreq=min
	disable_cpuidle=0
	governor=sched_pixel
	iostats=1
	nomerges=0
	target_freq=cpuinfo_min_freq
	persist_logs=true
     fi

     for c in $(adb shell "echo /sys/devices/system/cpu/cpu[0-9]*"); do
	for d in $(adb shell "echo $c/cpuidle/state[1-9]*"); do
	    adb shell "if [ -e $d ]; then echo $disable_cpuidle > $d/disable; fi"
	done
	adb shell "cat $c/cpufreq/cpuinfo_max_freq > $c/cpufreq/scaling_max_freq;
                    cat $c/cpufreq/${target_freq} > 
$c/cpufreq/scaling_min_freq;
                    echo ${governor} > $c/cpufreq/scaling_governor; true" \
             2>/dev/null
     done

     if [ "$(adb shell grep -c ufshcd /proc/interrupts)" = 1 ]; then
	# No MCQ or MCQ disabled. Make the fastest CPU core process UFS
	# interrupts.
	# shellcheck disable=SC2016
	ufs_irq_path=$(adb shell 'a=$(echo /proc/irq/*/ufshcd); echo ${a%/ufshcd}')
	adb shell "echo ${fastest_cpucore} > ${ufs_irq_path}/smp_affinity_list; 
true"
     else
	# MCQ is enabled. Distribute the completion interrupts over the
	# available CPU cores.
	local i=0
	local irqs
	irqs=$(adb shell "sed -n 's/:.*GIC.*ufshcd.*//p' /proc/interrupts")
	for irq in $irqs; do
	    adb shell "echo $i > /proc/irq/$irq/smp_affinity_list; true"
	    i=$((i+1))
	done
     fi

     for d in $(adb shell echo /sys/class/devfreq/*); do
	case "$d" in
	    *gpu0)
		continue
		;;
	esac
	local min_freq
	min_freq=$(adb shell "cat $d/available_frequencies |
		tr ' ' '\n' |
		sort -n |
		case $devfreq in
			min) head -n1;;
			max) tail -n1;;
		esac")
	adb shell "echo $min_freq > $d/min_freq"
	# shellcheck disable=SC2086
	if [ "$devfreq" = "max" ]; then
	    echo "$(basename $d)/min_freq: $(adb shell cat $d/min_freq) <> 
$min_freq"
	fi
     done

     for d in $(adb shell echo /sys/devices/platform/*.ufs); do
	adb shell "echo $clkgate_enable > $d/clkgate_enable"
     done

     adb shell setprop logd.logpersistd.enable ${persist_logs}

     adb shell "for b in /sys/class/block/{sd[a-z],dm*}; do
		    if [ -e \$b ]; then
			[ -e \$b/queue/iostats     ] && echo ${iostats}   >\$b/queue/iostats;
			[ -e \$b/queue/nomerges    ] && echo ${nomerges}  >\$b/queue/nomerges;
			[ -e \$b/queue/rq_affinity ] && echo 2            >\$b/queue/rq_affinity;
			[ -e \$b/queue/scheduler   ] && echo ${iosched}   >\$b/queue/scheduler;
		    fi
		done; true"

     adb shell "grep -q '^[^[:blank:]]* /sys/kernel/debug' /proc/mounts 
|| mount -t debugfs none /sys/kernel/debug"
}