Merge branch 'pci/bwctrl'

- Add read/modify/write locking for Link Control 2, which is used to manage
  Link speed (Ilpo Järvinen)

- Cache all supported Link speeds for use by the PCIe bandwidth controller
  (Ilpo Järvinen)

- Extract the Link Bandwidth Management Status check into pcie_lbms_seen(),
  where it can be shared between the bandwidth controller and quirks that
  use it to help retrain failed links (Ilpo Järvinen)

- Re-add Link Bandwidth notification support with updates to address the
  reasons it was previously reverted (Alexandru Gagniuc, Ilpo Järvinen)

- Add pcie_set_target_speed() and related functionality to manage PCIe Link
  speed based on thermal constraints (Ilpo Järvinen)

- Add a thermal cooling driver to throttle PCIe Links via the existing
  thermal management framework (Ilpo Järvinen)

- Add a userspace selftest for the PCIe bandwidth controller (Ilpo
  Järvinen)

- Drop duplicate pcie_get_speed_cap(), pcie_get_width_cap() declarations
  (Bjorn Helgaas)

* pci/bwctrl:
  PCI: Drop duplicate pcie_get_speed_cap(), pcie_get_width_cap() declarations
  selftests/pcie_bwctrl: Create selftests
  thermal: Add PCIe cooling driver
  PCI/bwctrl: Add pcie_set_target_speed() to set PCIe Link Speed
  PCI/bwctrl: Re-add BW notification portdrv as PCIe BW controller
  PCI: Abstract LBMS seen check into pcie_lbms_seen()
  PCI: Refactor pcie_update_link_speed()
  PCI: Store all PCIe Supported Link Speeds
  PCI: Protect Link Control 2 Register with RMW locking
  Documentation PCI: Reformat RMW ops documentation

4 files changed, 192 insertions, 0 deletions

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b38199965f99..7181756f47ff 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -72,6 +72,7 @@ TARGETS += net/packetdrill
 TARGETS += net/rds
 TARGETS += net/tcp_ao
 TARGETS += nsfs
+TARGETS += pcie_bwctrl
 TARGETS += perf_events
 TARGETS += pidfd
 TARGETS += pid_namespace
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
new file mode 100644
index 000000000000..3e84e26341d1
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -0,0 +1,2 @@
+TEST_PROGS = set_pcie_cooling_state.sh
+include ../lib.mk
diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh
new file mode 100755
index 000000000000..9df606552af3
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh
@@ -0,0 +1,122 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+SYSFS=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+retval=0
+skipmsg="skip all tests:"
+
+PCIEPORTTYPE="PCIe_Port_Link_Speed"
+
+prerequisite()
+{
+	local ports
+
+	if [ $UID != 0 ]; then
+		echo $skipmsg must be run as root >&2
+		exit $ksft_skip
+	fi
+
+	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
+
+	if [ ! -d "$SYSFS" ]; then
+		echo $skipmsg sysfs is not mounted >&2
+		exit $ksft_skip
+	fi
+
+	if ! ls $SYSFS/class/thermal/cooling_device* > /dev/null 2>&1; then
+		echo $skipmsg thermal cooling devices missing >&2
+		exit $ksft_skip
+	fi
+
+	ports=`grep -e "^$PCIEPORTTYPE" $SYSFS/class/thermal/cooling_device*/type | wc -l`
+	if [ $ports -eq 0 ]; then
+		echo $skipmsg pcie cooling devices missing >&2
+		exit $ksft_skip
+	fi
+}
+
+testport=
+find_pcie_port()
+{
+	local patt="$1"
+	local pcieports
+	local max
+	local cur
+	local delta
+	local bestdelta=-1
+
+	pcieports=`grep -l -F -e "$patt" /sys/class/thermal/cooling_device*/type`
+	if [ -z "$pcieports" ]; then
+		return
+	fi
+	pcieports=${pcieports//\/type/}
+	# Find the port with the highest PCIe Link Speed
+	for port in $pcieports; do
+		max=`cat $port/max_state`
+		cur=`cat $port/cur_state`
+		delta=$((max-cur))
+		if [ $delta -gt $bestdelta ]; then
+			testport="$port"
+			bestdelta=$delta
+		fi
+	done
+}
+
+sysfspcidev=
+find_sysfs_pci_dev()
+{
+	local typefile="$1/type"
+	local pcidir
+
+	pcidir="$SYSFS/bus/pci/devices/`sed -e "s|^${PCIEPORTTYPE}_||g" $typefile`"
+
+	if [ -r "$pcidir/current_link_speed" ]; then
+		sysfspcidev="$pcidir/current_link_speed"
+	fi
+}
+
+usage()
+{
+	echo "Usage $0 [ -d dev ]"
+	echo -e "\t-d: PCIe port BDF string (e.g., 0000:00:04.0)"
+}
+
+pattern="$PCIEPORTTYPE"
+parse_arguments()
+{
+	while getopts d:h opt; do
+		case $opt in
+			h)
+				usage "$0"
+				exit 0
+				;;
+			d)
+				pattern="$PCIEPORTTYPE_$OPTARG"
+				;;
+			*)
+				usage "$0"
+				exit 0
+				;;
+		esac
+	done
+}
+
+parse_arguments "$@"
+prerequisite
+find_pcie_port "$pattern"
+if [ -z "$testport" ]; then
+	echo $skipmsg "pcie cooling device not found from sysfs" >&2
+	exit $ksft_skip
+fi
+find_sysfs_pci_dev "$testport"
+if [ -z "$sysfspcidev" ]; then
+	echo $skipmsg "PCIe port device not found from sysfs" >&2
+	exit $ksft_skip
+fi
+
+./set_pcie_speed.sh "$testport" "$sysfspcidev"
+retval=$?
+
+exit $retval
diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh
new file mode 100755
index 000000000000..584596949312
--- /dev/null
+++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+set -e
+
+TESTNAME=set_pcie_speed
+
+declare -a PCIELINKSPEED=(
+	"2.5 GT/s PCIe"
+	"5.0 GT/s PCIe"
+	"8.0 GT/s PCIe"
+	"16.0 GT/s PCIe"
+	"32.0 GT/s PCIe"
+	"64.0 GT/s PCIe"
+)
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+retval=0
+
+coolingdev="$1"
+statefile="$coolingdev/cur_state"
+maxfile="$coolingdev/max_state"
+linkspeedfile="$2"
+
+oldstate=`cat $statefile`
+maxstate=`cat $maxfile`
+
+set_state()
+{
+	local state=$1
+	local linkspeed
+	local expected_linkspeed
+
+	echo $state > $statefile
+
+	sleep 1
+
+	linkspeed="`cat $linkspeedfile`"
+	expected_linkspeed=$((maxstate-state))
+	expected_str="${PCIELINKSPEED[$expected_linkspeed]}"
+	if [ ! "${expected_str}" = "${linkspeed}" ]; then
+		echo "$TESTNAME failed: expected: ${expected_str}; got ${linkspeed}"
+		retval=1
+	fi
+}
+
+cleanup_skip ()
+{
+	set_state $oldstate
+	exit $ksft_skip
+}
+
+trap cleanup_skip EXIT
+
+echo "$TESTNAME: testing states $maxstate .. $oldstate with $coolingdev"
+for i in $(seq $maxstate -1 $oldstate); do
+	set_state "$i"
+done
+
+trap EXIT
+if [ $retval -eq 0 ]; then
+	echo "$TESTNAME [PASS]"
+else
+	echo "$TESTNAME [FAIL]"
+fi
+exit $retval