6.17.9-rc1 review

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 8b93f8933d37591d17c59fd71b18fc61966d9515 ]

In test_record_concurrent, as stderr is sent to /dev/null, error messages are hidden. Change this to gather the error messages and dump them on failure.

Some minor sh->bash changes to add some more diagnostics in trap_cleanup.

Stable-dep-of: 3c723f449723 ("perf test: Fix lock contention test")

---
 tools/perf/tests/shell/lock_contention.sh | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

index d33d9e4392b06..7248a74ca2a32 100755
@@ -7,14 +7,17 @@ set -e
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 result=$(mktemp /tmp/__perf_test.result.XXXXX)
+errout=$(mktemp /tmp/__perf_test.errout.XXXXX)
 
 cleanup() {
 	rm -f ${perfdata}
 	rm -f ${result}
+	rm -f ${errout}
 	trap - EXIT TERM INT
 }
 
 trap_cleanup() {
+	echo "Unexpected signal in ${FUNCNAME[1]}"
 	cleanup
 	exit ${err}
 }

@@ -75,10 +78,12 @@ test_bpf()
 test_record_concurrent()
 {
 	echo "Testing perf lock record and perf lock contention at the same time"
-	perf lock record -o- -- perf bench sched messaging -p 2> /dev/null | \
+	perf lock record -o- -- perf bench sched messaging -p 2> ${errout} | \
 	perf lock contention -i- -E 1 -q 2> ${result}
 	if [ "$(cat "${result}" | wc -l)" != "1" ]; then
 		echo "[Fail] Recorded result count is not 1:" "$(cat "${result}" | wc -l)"
+		cat ${errout}
+		cat ${result}
 		err=1
 		exit
 	fi

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ravi Bangoria <[email protected]>

[ Upstream commit 3c723f449723db2dc2b75b7efe03c2a76e4c09f0 ]

Couple of independent fixes:

1. Wire in SIGSEGV handler that terminates the test with a failure code.

2. Use "--lock-cgroup" instead of "-g"; "-g" was proposed but never merged. See commit 4d1792d0a2564caf ("perf lock contention: Add --lock-cgroup option")

3. Call cleanup() on every normal exit so trap_cleanup() doesn't mistake it for an unexpected signal and emit a false-negative "Unexpected signal in main" message.

Before patch:

  # ./perf test -vv "lock contention"
   85: kernel lock contention analysis test:
  --- start ---
  test child forked, pid 610711
  Testing perf lock record and perf lock contention
  Testing perf lock contention --use-bpf
  Testing perf lock record and perf lock contention at the same time
  Testing perf lock contention --threads
  Testing perf lock contention --lock-addr
  Testing perf lock contention --lock-cgroup
  Unexpected signal in test_aggr_cgroup
  ---- end(0) ----
   85: kernel lock contention analysis test                            : Ok

After patch:

  # ./perf test -vv "lock contention"
   85: kernel lock contention analysis test:
  --- start ---
  test child forked, pid 602637
  Testing perf lock record and perf lock contention
  Testing perf lock contention --use-bpf
  Testing perf lock record and perf lock contention at the same time
  Testing perf lock contention --threads
  Testing perf lock contention --lock-addr
  Testing perf lock contention --lock-cgroup
  Testing perf lock contention --type-filter (w/ spinlock)
  Testing perf lock contention --lock-filter (w/ tasklist_lock)
  Testing perf lock contention --callstack-filter (w/ unix_stream)
  [Skip] Could not find 'unix_stream'
  Testing perf lock contention --callstack-filter with task aggregation
  [Skip] Could not find 'unix_stream'
  Testing perf lock contention --cgroup-filter
  Testing perf lock contention CSV output
  ---- end(0) ----
   85: kernel lock contention analysis test                            : Ok

---
 tools/perf/tests/shell/lock_contention.sh | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

index 7248a74ca2a32..6dd90519f45ce 100755
@@ -13,15 +13,18 @@ cleanup() {
 	rm -f ${perfdata}
 	rm -f ${result}
 	rm -f ${errout}
-	trap - EXIT TERM INT
+	trap - EXIT TERM INT ERR
 }
 
 trap_cleanup() {
+	if (( $? == 139 )); then #SIGSEGV
+		err=1
+	fi
 	echo "Unexpected signal in ${FUNCNAME[1]}"
 	cleanup
 	exit ${err}
 }
-trap trap_cleanup EXIT TERM INT
+trap trap_cleanup EXIT TERM INT ERR
 
 check() {
 	if [ "$(id -u)" != 0 ]; then

@@ -145,7 +148,7 @@ test_aggr_cgroup()
 	fi
 
 	# the perf lock contention output goes to the stderr
-	perf lock con -a -b -g -E 1 -q -- perf bench sched messaging -p > /dev/null 2> ${result}
+	perf lock con -a -b --lock-cgroup -E 1 -q -- perf bench sched messaging -p > /dev/null 2> ${result}
 	if [ "$(cat "${result}" | wc -l)" != "1" ]; then
 		echo "[Fail] BPF result count is not 1:" "$(cat "${result}" | wc -l)"
 		err=1

@@ -271,7 +274,7 @@ test_cgroup_filter()
 		return
 	fi
 
-	perf lock con -a -b -g -E 1 -F wait_total -q -- perf bench sched messaging -p > /dev/null 2> ${result}
+	perf lock con -a -b --lock-cgroup -E 1 -F wait_total -q -- perf bench sched messaging -p > /dev/null 2> ${result}
 	if [ "$(cat "${result}" | wc -l)" != "1" ]; then
 		echo "[Fail] BPF result should have a cgroup result:" "$(cat "${result}")"
 		err=1

@@ -279,7 +282,7 @@ test_cgroup_filter()
 	fi
 
 	cgroup=$(cat "${result}" | awk '{ print $3 }')
-	perf lock con -a -b -g -E 1 -G "${cgroup}" -q -- perf bench sched messaging -p > /dev/null 2> ${result}
+	perf lock con -a -b --lock-cgroup -E 1 -G "${cgroup}" -q -- perf bench sched messaging -p > /dev/null 2> ${result}
 	if [ "$(cat "${result}" | wc -l)" != "1" ]; then
 		echo "[Fail] BPF result should have a result with cgroup filter:" "$(cat "${cgroup}")"
 		err=1

@@ -338,4 +341,5 @@ test_aggr_task_stack_filter
 test_cgroup_filter
 test_csv_output
 
+cleanup
 exit ${err}

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Anand Moon <[email protected]>

[ Upstream commit d425aef66e62221fa6bb0ccb94296df29e4cc107 ]

Enable proper pin multiplexing for the I2S1 8-channel transmit interface by adding the default pinctrl configuration which esures correct signal routing and avoids pinmux conflicts during audio playback.

Changes fix the error

[  116.856643] [    T782] rockchip-pinctrl pinctrl: pin gpio1-10 already requested by affinity_hint; cannot claim for fe410000.i2s
[  116.857567] [    T782] rockchip-pinctrl pinctrl: error -EINVAL: pin-42 (fe410000.i2s)
[  116.857618] [    T782] rockchip-pinctrl pinctrl: error -EINVAL: could not request pin 42 (gpio1-10) from group i2s1m0-sdi1 on device rockchip-pinctrl
[  116.857659] [    T782] rockchip-i2s-tdm fe410000.i2s: Error applying setting, reverse things back

I2S1 on the M1 to the codec in the RK809 only uses the SCLK, LRCK, SDI0 and SDO0 signals, so limit the claimed pins to those.

With this change audio output works as expected:

$ aplay -l
**** List of PLAYBACK Hardware Devices ****
card 0: HDMI [HDMI], device 0: fe400000.i2s-i2s-hifi i2s-hifi-0 [fe400000.i2s-i2s-hifi i2s-hifi-0]
  Subdevices: 1/1
  Subdevice #0: subdevice #0
card 1: RK817 [Analog RK817], device 0: fe410000.i2s-rk817-hifi rk817-hifi-0 [fe410000.i2s-rk817-hifi rk817-hifi-0]
  Subdevices: 1/1
  Subdevice #0: subdevice #0

---
 arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 2 ++
 1 file changed, 2 insertions(+)

index 0f844806ec542..442a2bc43ba8e 100644
@@ -482,6 +482,8 @@
 };
 
 &i2s1_8ch {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2s1m0_sclktx &i2s1m0_lrcktx &i2s1m0_sdi0 &i2s1m0_sdo0>;
 	rockchip,trcm-sync-tx-only;
 	status = "okay";
 };

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrey Leonchikov <[email protected]>

[ Upstream commit e179de737d13ad99bd19ea0fafab759d4074a425 ]

Fix typo into regulator GPIO definition. With current definition, PCIe doesn't start up. Valid definition is already used in "pinctrl" section, "pcie_drv" (gpio4, RK_PB1).

---
 arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 7f578c50b4ad1..f74590af7e33f 100644
@@ -120,7 +120,7 @@
 		compatible = "regulator-fixed";
 		regulator-name = "vcc3v3_pcie";
 		enable-active-high;
-		gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_HIGH>;
+		gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pcie_drv>;
 		regulator-always-on;

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dragan Simic <[email protected]>

[ Upstream commit b3fd04e23f6e4496f5a2279466a33fbdc83500f0 ]

Unify the naming of the existing GPU OPP table nodes found in the RK3588 and RK3588J SoC dtsi files with the other SoC's GPU OPP nodes, following the more "modern" node naming scheme.

---
 arch/arm64/boot/dts/rockchip/rk3588-opp.dtsi | 2 +-
 arch/arm64/boot/dts/rockchip/rk3588j.dtsi    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

index 0f1a776973516..b5d630d2c879f 100644
@@ -115,7 +115,7 @@
 		};
 	};
 
-	gpu_opp_table: opp-table {
+	gpu_opp_table: opp-table-gpu {
 		compatible = "operating-points-v2";
 
 		opp-300000000 {

index 9884a5df47dfe..e1e0e3fc0ca70 100644
@@ -66,7 +66,7 @@
 		};
 	};
 
-	gpu_opp_table: opp-table {
+	gpu_opp_table: opp-table-gpu {
 		compatible = "operating-points-v2";
 
 		opp-300000000 {

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dario Binacchi <[email protected]>

[ Upstream commit 62bf7708fe80ec0db14b9179c25eeeda9f81e9d0 ]

The 'report-rate-hz' property for the edt-ft5x06 driver was added and handled in the Linux kernel by me with patches [1] and [2] for this specific board.

The v1 upstream version, which was the one applied to the customer's kernel, used the 'report-rate' property, which was written directly to the controller register. During review, the 'hz' suffix was added, changing its handling so that writing the value directly to the register was no longer possible for the M06 controller.

Once the patches were accepted in mainline, I did not reapply them to the customer's kernel, and when upstreaming the DTS for this board, I forgot to correct the 'report-rate-hz' property value.

The property must be set to 60 because this board uses the M06 controller, which expects the report rate in units of 10 Hz, meaning the actual value written to the register is 6.

[1] 625f829586ea ("dt-bindings: input: touchscreen: edt-ft5x06: add report-rate-hz")
[2] 5bcee83a406c ("Input: edt-ft5x06 - set report rate by dts property")

---
 arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-rmm.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 5d1cc8a1f5558..8d41f76ae270b 100644
@@ -136,7 +136,7 @@
 		interrupt-parent = <&gpio2>;
 		interrupts = <8 IRQ_TYPE_EDGE_FALLING>;
 		reset-gpios = <&gpio2 14 GPIO_ACTIVE_LOW>;
-		report-rate-hz = <6>;
+		report-rate-hz = <60>;
 		/* settings valid only for Hycon touchscreen */
 		touchscreen-size-x = <1280>;
 		touchscreen-size-y = <800>;

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jihed Chaibi <[email protected]>

[ Upstream commit f31e261712a0d107f09fb1d3dc8f094806149c83 ]

Rename the 'ssi2' and 'aud3' nodes to 'mux-ssi2' and 'mux-aud3' in the audmux configuration of imx51-zii-rdu1.dts to comply with the naming convention in imx-audmux.yaml.

This fixes the following dt-schema warning:

imx51-zii-rdu1.dtb: audmux@83fd0000 (fsl,imx51-audmux): 'aud3', 'ssi2' do not match any of the regexes: '^mux-[0-9a-z]*$', '^pinctrl-[0-9]+$'

---
 arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 06545a6052f71..43ff5eafb2bb8 100644
@@ -259,7 +259,7 @@
 	pinctrl-0 = <&pinctrl_audmux>;
 	status = "okay";
 
-	ssi2 {
+	mux-ssi2 {
 		fsl,audmux-port = <1>;
 		fsl,port-config = <
 			(IMX_AUDMUX_V2_PTCR_SYN |

@@ -271,7 +271,7 @@
 		>;
 	};
 
-	aud3 {
+	mux-aud3 {
 		fsl,audmux-port = <2>;
 		fsl,port-config = <
 			IMX_AUDMUX_V2_PTCR_SYN

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: João Paulo Gonçalves <[email protected]>

[ Upstream commit ec4daace64a44b53df76f0629e82684ef09ce869 ]

The gpio0_mipi_csi DT nodes are enabled by default, but they are dependent on the irqsteer_csi nodes, which are not enabled. This causes the gpio0_mipi_csi GPIOs to be probe deferred. Since these GPIOs can be used independently of the CSI controller, enable irqsteer_csi by default too to prevent them from being deferred and to ensure they work out of the box.

---
 arch/arm64/boot/dts/freescale/imx8-ss-img.dtsi | 2 --
 1 file changed, 2 deletions(-)

index 2cf0f7208350a..a72b2f1c4a1b2 100644
@@ -67,7 +67,6 @@ img_subsys: bus@58000000 {
 		power-domains = <&pd IMX_SC_R_CSI_0>;
 		fsl,channel = <0>;
 		fsl,num-irqs = <32>;
-		status = "disabled";
 	};
 
 	gpio0_mipi_csi0: gpio@58222000 {

@@ -144,7 +143,6 @@ img_subsys: bus@58000000 {
 		power-domains = <&pd IMX_SC_R_CSI_1>;
 		fsl,channel = <0>;
 		fsl,num-irqs = <32>;
-		status = "disabled";
 	};
 
 	gpio0_mipi_csi1: gpio@58242000 {

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Frieder Schrempf <[email protected]>

[ Upstream commit 6504297872c7a5d0d06247970d32940eba26b8b3 ]

The VBUS supply regulator is currently assigned to the PHY node. This causes the VBUS to be always on, even when the controller needs to be switched to peripheral mode.

Fix the OTG role switching by adding a connector node and moving the VBUS supply regulator to that node. This way the VBUS gets correctly switched according to the current role.

---
 .../dts/freescale/imx8mp-kontron-bl-osm-s.dts | 24 +++++++++++++++----
 1 file changed, 19 insertions(+), 5 deletions(-)

index 0eb9e726a9b81..6c63f0a5fa91b 100644
@@ -16,11 +16,20 @@
 		ethernet1 = &eqos;
 	};
 
-	extcon_usbc: usbc {
-		compatible = "linux,extcon-usb-gpio";
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+		label = "Type-C";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_usb1_id>;
-		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+		type = "micro";
+		vbus-supply = <&reg_usb1_vbus>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb3_dwc>;
+			};
+		};
 	};
 
 	leds {

@@ -230,9 +239,15 @@
 	hnp-disable;
 	srp-disable;
 	dr_mode = "otg";
-	extcon = <&extcon_usbc>;
 	usb-role-switch;
+	role-switch-default-mode = "peripheral";
 	status = "okay";
+
+	port {
+		usb3_dwc: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
+	};
 };
 
 &usb_dwc3_1 {

@@ -261,7 +276,6 @@
 };
 
 &usb3_phy0 {
-	vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
 };
 

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Ichikawa <[email protected]>

[ Upstream commit 53f731f5bba0cf03b751ccceb98b82fadc9ccd1e ]

Use a scope-based cleanup helper for the buffer allocated with kmalloc() in ntrig_report_version() to simplify the cleanup logic and prevent memory leaks (specifically the !hid_is_usb()-case one).

---
 drivers/hid/hid-ntrig.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

index 0f76e241e0afb..a7f10c45f62bd 100644
@@ -142,13 +142,13 @@ static void ntrig_report_version(struct hid_device *hdev)
 	int ret;
 	char buf[20];
 	struct usb_device *usb_dev = hid_to_usb_dev(hdev);
-	unsigned char *data = kmalloc(8, GFP_KERNEL);
+	unsigned char *data __free(kfree) = kmalloc(8, GFP_KERNEL);
 
 	if (!hid_is_usb(hdev))
 		return;
 
 	if (!data)
-		goto err_free;
+		return;
 
 	ret = usb_control_msg(usb_dev, usb_rcvctrlpipe(usb_dev, 0),
 			      USB_REQ_CLEAR_FEATURE,

@@ -163,9 +163,6 @@ static void ntrig_report_version(struct hid_device *hdev)
 		hid_info(hdev, "Firmware version: %s (%02x%02x %02x%02x)\n",
 			 buf, data[2], data[3], data[4], data[5]);
 	}
-
-err_free:
-	kfree(data);
 }
 
 static ssize_t show_phys_width(struct device *dev,

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rafał Miłecki <[email protected]>

[ Upstream commit 3d1c795bdef43363ed1ff71e3f476d86c22e059b ]

Luxul XAP-1440 has BCM54210E PHY at address 25.

---
 arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index ac44c745bdf8e..a39a021a39107 100644
@@ -55,8 +55,8 @@
 	mdio {
 		/delete-node/ switch@1e;
 
-		bcm54210e: ethernet-phy@0 {
-			reg = <0>;
+		bcm54210e: ethernet-phy@25 {
+			reg = <25>;
 		};
 	};
 };

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrey Leonchikov <[email protected]>

[ Upstream commit a59e927ff46a967f84ddf94e89cbb045810e8974 ]

Fix typo into regulator GPIO definition. With current
definition - USB powered off. Valid definition can be found on "pinctrl" section:
vcc5v0_usb2t_en: vcc5v0-usb2t-en {
rockchip,pins = <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_none>;
};

vcc5v0_usb2b_en: vcc5v0-usb2b-en {
rockchip,pins = <4 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
};

---
 arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index f74590af7e33f..b6cf03a7ba66b 100644
@@ -187,7 +187,7 @@
 	vcc5v0_usb2b: regulator-vcc5v0-usb2b {
 		compatible = "regulator-fixed";
 		enable-active-high;
-		gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio4 RK_PC4 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc5v0_usb2b_en>;
 		regulator-name = "vcc5v0_usb2b";

@@ -199,7 +199,7 @@
 	vcc5v0_usb2t: regulator-vcc5v0-usb2t {
 		compatible = "regulator-fixed";
 		enable-active-high;
-		gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>;
+		gpios = <&gpio3 RK_PD5 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc5v0_usb2t_en>;
 		regulator-name = "vcc5v0_usb2t";

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chukun Pan <[email protected]>

[ Upstream commit 264152a97edf9f1b7ed5372e4033e46108e41422 ]

The reset property is not part of the binding, so drop it. It is also not used by the driver, so it was likely copied from some vendor-kernel node.

---
 arch/arm64/boot/dts/rockchip/rk3576.dtsi | 2 --
 1 file changed, 2 deletions(-)

index c3cdae8a54941..f236edcac3767 100644
@@ -2311,8 +2311,6 @@
 			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2c9m0_xfer>;
-			resets = <&cru SRST_I2C9>, <&cru SRST_P_I2C9>;
-			reset-names = "i2c", "apb";
 			#address-cells = <1>;
 			#size-cells = <0>;
 			status = "disabled";

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Luke Wang <[email protected]>

[ Upstream commit f84fd5bec502447df145f31734793714690ce27f ]

The register addresses of ADP5585 and ADP5589 are swapped.

---
 drivers/pwm/pwm-adp5585.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index dc2860979e24e..806f8d79b0d7b 100644
@@ -190,13 +190,13 @@ static int adp5585_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct adp5585_pwm_chip adp5589_pwm_chip_info = {
+static const struct adp5585_pwm_chip adp5585_pwm_chip_info = {
 	.pwm_cfg = ADP5585_PWM_CFG,
 	.pwm_offt_low = ADP5585_PWM_OFFT_LOW,
 	.pwm_ont_low = ADP5585_PWM_ONT_LOW,
 };
 
-static const struct adp5585_pwm_chip adp5585_pwm_chip_info = {
+static const struct adp5585_pwm_chip adp5589_pwm_chip_info = {
 	.pwm_cfg = ADP5589_PWM_CFG,
 	.pwm_offt_low = ADP5589_PWM_OFFT_LOW,
 	.pwm_ont_low = ADP5589_PWM_ONT_LOW,

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Abdun Nihaal <[email protected]>

[ Upstream commit 8513c154f8ad7097653dd9bf43d6155e5aad4ab3 ]

The memory allocated for buf is not freed in the error paths when ps_get_report() fails. Free buf before jumping to transfer_failed label

---
 drivers/hid/hid-playstation.c | 2 ++
 1 file changed, 2 insertions(+)

index 1468fb11e39df..657e9ae1be1ee 100644
@@ -1807,6 +1807,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)
 
 				hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret);
 				ret = -EILSEQ;
+				kfree(buf);
 				goto transfer_failed;
 			} else {
 				break;

@@ -1824,6 +1825,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)
 
 		if (ret) {
 			hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret);
+			kfree(buf);
 			goto transfer_failed;
 		}
 	}

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Abdun Nihaal <[email protected]>

[ Upstream commit a78eb69d60ce893de48dd75f725ba21309131fc2 ]

In uclogic_params_ugee_v2_init_event_hooks(), the memory allocated for event_hook is not freed in the next error path. Fix that by freeing it.

---
 drivers/hid/hid-uclogic-params.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 4a17f7332c3f5..016d1f08bd1db 100644
@@ -1369,8 +1369,10 @@ static int uclogic_params_ugee_v2_init_event_hooks(struct hid_device *hdev,
 	event_hook->hdev = hdev;
 	event_hook->size = ARRAY_SIZE(reconnect_event);
 	event_hook->event = kmemdup(reconnect_event, event_hook->size, GFP_KERNEL);
-	if (!event_hook->event)
+	if (!event_hook->event) {
+		kfree(event_hook);
 		return -ENOMEM;
+	}
 
 	list_add_tail(&event_hook->list, &p->event_hooks->list);
 

2.51.0

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bibo Mao <[email protected]>

commit 5001bcf86edf2de02f025a0f789bcac37fa040e6 upstream.

On LoongArch system, guest PMU hardware is shared by guest and host but PMU interrupt is separated. PMU is pass-through to VM, and there is PMU context switch when exit to host and return to guest.

There is optimiation to check whether PMU is enabled by guest. If not, it is not necessary to return to guest. However, if it is enabled, PMU context for guest need switch on. Now KVM_REQ_PMU notification is set on vCPU context switch, but it is missing if there is no vCPU context switch while PMU is used by guest VM, so fix it.

---
 arch/loongarch/kvm/vcpu.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -133,6 +133,9 @@ static void kvm_lose_pmu(struct kvm_vcpu
 	 * Clear KVM_LARCH_PMU if the guest is not using PMU CSRs when
 	 * exiting the guest, so that the next time trap into the guest.
 	 * We don't need to deal with PMU CSRs contexts.
+	 *
+	 * Otherwise set the request bit KVM_REQ_PMU to restore guest PMU
+	 * before entering guest VM
 	 */
 	val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0);
 	val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1);

@@ -140,6 +143,8 @@ static void kvm_lose_pmu(struct kvm_vcpu
 	val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3);
 	if (!(val & KVM_PMU_EVENT_ENABLED))
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_PMU;
+	else
+		kvm_make_request(KVM_REQ_PMU, vcpu);
 
 	kvm_restore_host_pmu(vcpu);
 }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bibo Mao <[email protected]>

commit d3c9515e4f9d10ccb113adb4809db5cc31e7ef65 upstream.

When timer is fired in oneshot mode, CSR.TVAL will stop with value -1 rather than 0. However when the register CSR.TVAL is restored, it will continue to count down rather than stop there.

Now the method is to write 0 to CSR.TVAL, wait to count down for 1 cycle at least, which is 10ns with a timer freq 100MHz, and then retore timer interrupt status. Here add 2 cycles delay to assure that timer interrupt is injected.

With this patch, timer selftest case passes to run always.

---
 arch/loongarch/kvm/timer.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <asm/delay.h>
 #include <asm/kvm_csr.h>
 #include <asm/kvm_vcpu.h>
 

@@ -95,6 +96,7 @@ void kvm_restore_timer(struct kvm_vcpu *
 		 * and set CSR TVAL with -1
 		 */
 		write_gcsr_timertick(0);
+		__delay(2); /* Wait cycles until timer interrupt injected */
 
 		/*
 		 * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bibo Mao <[email protected]>

commit 237e74bfa261fb0cf75bd08c9be0c5094018ee20 upstream.

VM fails to boot with 256 vCPUs, the detailed command is

qemu-system-loongarch64 -smp 256

and there is an error reported as follows:

KVM_LOONGARCH_EXTIOI_INIT_NUM_CPU failed: Invalid argument

There is typo issue in function kvm_eiointc_ctrl_access() when set max supported vCPUs.

---
 arch/loongarch/kvm/intc/eiointc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -439,7 +439,7 @@ static int kvm_eiointc_ctrl_access(struc
 	spin_lock_irqsave(&s->lock, flags);
 	switch (type) {
 	case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU:
-		if (val >= EIOINTC_ROUTE_MAX_VCPUS)
+		if (val > EIOINTC_ROUTE_MAX_VCPUS)
 			ret = -EINVAL;
 		else
 			s->num_cpu = val;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

commit ae431059e75d36170a5ae6b44cc4d06d43613215 upstream.

When unbinding a memslot from a guest_memfd instance, remove the bindings even if the guest_memfd file is dying, i.e. even if its file refcount has gone to zero. If the memslot is freed before the file is fully released, nullifying the memslot side of the binding in kvm_gmem_release() will write to freed memory, as detected by syzbot+KASAN:

==================================================================

  BUG: KASAN: slab-use-after-free in kvm_gmem_release+0x176/0x440 virt/kvm/guest_memfd.c:353
  Write of size 8 at addr ffff88807befa508 by task syz.0.17/6022

  CPU: 0 UID: 0 PID: 6022 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/02/2025
  Call Trace:
   <TASK>
   dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120
   print_address_description mm/kasan/report.c:378 [inline]
   print_report+0xca/0x240 mm/kasan/report.c:482
   kasan_report+0x118/0x150 mm/kasan/report.c:595
   kvm_gmem_release+0x176/0x440 virt/kvm/guest_memfd.c:353
   __fput+0x44c/0xa70 fs/file_table.c:468
   task_work_run+0x1d4/0x260 kernel/task_work.c:227
   resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
   exit_to_user_mode_loop+0xe9/0x130 kernel/entry/common.c:43
   exit_to_user_mode_prepare include/linux/irq-entry-common.h:225 [inline]
   syscall_exit_to_user_mode_work include/linux/entry-common.h:175 [inline]
   syscall_exit_to_user_mode include/linux/entry-common.h:210 [inline]
   do_syscall_64+0x2bd/0xfa0 arch/x86/entry/syscall_64.c:100
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7fbeeff8efc9
   </TASK>

  Allocated by task 6023:
   kasan_save_stack mm/kasan/common.c:56 [inline]
   kasan_save_track+0x3e/0x80 mm/kasan/common.c:77
   poison_kmalloc_redzone mm/kasan/common.c:397 [inline]
   __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:414
   kasan_kmalloc include/linux/kasan.h:262 [inline]
   __kmalloc_cache_noprof+0x3e2/0x700 mm/slub.c:5758
   kmalloc_noprof include/linux/slab.h:957 [inline]
   kzalloc_noprof include/linux/slab.h:1094 [inline]
   kvm_set_memory_region+0x747/0xb90 virt/kvm/kvm_main.c:2104
   kvm_vm_ioctl_set_memory_region+0x6f/0xd0 virt/kvm/kvm_main.c:2154
   kvm_vm_ioctl+0x957/0xc60 virt/kvm/kvm_main.c:5201
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:597 [inline]
   __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:583
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

  Freed by task 6023:
   kasan_save_stack mm/kasan/common.c:56 [inline]
   kasan_save_track+0x3e/0x80 mm/kasan/common.c:77
   kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584
   poison_slab_object mm/kasan/common.c:252 [inline]
   __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:284
   kasan_slab_free include/linux/kasan.h:234 [inline]
   slab_free_hook mm/slub.c:2533 [inline]
   slab_free mm/slub.c:6622 [inline]
   kfree+0x19a/0x6d0 mm/slub.c:6829
   kvm_set_memory_region+0x9c4/0xb90 virt/kvm/kvm_main.c:2130
   kvm_vm_ioctl_set_memory_region+0x6f/0xd0 virt/kvm/kvm_main.c:2154
   kvm_vm_ioctl+0x957/0xc60 virt/kvm/kvm_main.c:5201
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:597 [inline]
   __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:583
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

Deliberately don't acquire filemap invalid lock when the file is dying as the lifecycle of f_mapping is outside the purview of KVM. Dereferencing the mapping is *probably* fine, but there's no need to invalidate anything as memslot deletion is responsible for zapping SPTEs, and the only code that can access the dying file is kvm_gmem_release(), whose core code is mutually exclusive with unbinding.

Note, the mutual exclusivity is also what makes it safe to access the bindings on a dying gmem instance. Unbinding either runs with slots_lock held, or after the last reference to the owning "struct kvm" is put, and kvm_gmem_release() nullifies the slot pointer under slots_lock, and puts its reference to the VM after that is done.

---
 virt/kvm/guest_memfd.c |   45 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 13 deletions(-)

@@ -523,31 +523,50 @@ err:
 	return r;
 }
 
-void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gmem)
 {
 	unsigned long start = slot->gmem.pgoff;
 	unsigned long end = start + slot->npages;
-	struct kvm_gmem *gmem;
+
+	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+
+	/*
+	 * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn()
+	 * cannot see this memslot.
+	 */
+	WRITE_ONCE(slot->gmem.file, NULL);
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
 	struct file *file;
 
 	/*
-	 * Nothing to do if the underlying file was already closed (or is being
-	 * closed right now), kvm_gmem_release() invalidates all bindings.
+	 * Nothing to do if the underlying file was _already_ closed, as
+	 * kvm_gmem_release() invalidates and nullifies all bindings.
 	 */
-	file = kvm_gmem_get_file(slot);
-	if (!file)
+	if (!slot->gmem.file)
 		return;
 
-	gmem = file->private_data;
-
-	filemap_invalidate_lock(file->f_mapping);
-	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	file = kvm_gmem_get_file(slot);
 
 	/*
-	 * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn()
-	 * cannot see this memslot.
+	 * However, if the file is _being_ closed, then the bindings need to be
+	 * removed as kvm_gmem_release() might not run until after the memslot
+	 * is freed.  Note, modifying the bindings is safe even though the file
+	 * is dying as kvm_gmem_release() nullifies slot->gmem.file under
+	 * slots_lock, and only puts its reference to KVM after destroying all
+	 * bindings.  I.e. reaching this point means kvm_gmem_release() hasn't
+	 * yet destroyed the bindings or freed the gmem_file, and can't do so
+	 * until the caller drops slots_lock.
 	 */
-	WRITE_ONCE(slot->gmem.file, NULL);
+	if (!file) {
+		__kvm_gmem_unbind(slot, slot->gmem.file->private_data);
+		return;
+	}
+
+	filemap_invalidate_lock(file->f_mapping);
+	__kvm_gmem_unbind(slot, file->private_data);
 	filemap_invalidate_unlock(file->f_mapping);
 
 	fput(file);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

commit 3f9eacf4f0705876a5d6526d7d320ca91d7d7a16 upstream.

32bit ID registers aren't getting much love these days, and are often missed in updates. One of these updates broke restoring a GICv2 guest on a GICv3 machine.

Instead of performing a piecemeal fix, just bite the bullet and make all 32bit ID regs fully writable. KVM itself never relies on them for anything, and if the VMM wants to mess up the guest, so be it.

---
 arch/arm64/kvm/sys_regs.c |   59 ++++++++++++++++++++++++----------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

@@ -2515,19 +2515,23 @@ static bool bad_redir_trap(struct kvm_vc
 	.val = 0,				\
 }
 
-/* sys_reg_desc initialiser for known cpufeature ID registers */
-#define AA32_ID_SANITISED(name) {		\
-	ID_DESC(name),				\
-	.visibility = aa32_id_visibility,	\
-	.val = 0,				\
-}
-
 /* sys_reg_desc initialiser for writable ID registers */
 #define ID_WRITABLE(name, mask) {		\
 	ID_DESC(name),				\
 	.val = mask,				\
 }
 
+/*
+ * 32bit ID regs are fully writable when the guest is 32bit
+ * capable. Nothing in the KVM code should rely on 32bit features
+ * anyway, only 64bit, so let the VMM do its worse.
+ */
+#define AA32_ID_WRITABLE(name) {		\
+	ID_DESC(name),				\
+	.visibility = aa32_id_visibility,	\
+	.val = GENMASK(31, 0),			\
+}
+
 /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */
 #define ID_FILTERED(sysreg, name, mask) {	\
 	ID_DESC(sysreg),				\

@@ -3039,40 +3043,39 @@ static const struct sys_reg_desc sys_reg
 
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
-	AA32_ID_SANITISED(ID_PFR0_EL1),
-	AA32_ID_SANITISED(ID_PFR1_EL1),
+	AA32_ID_WRITABLE(ID_PFR0_EL1),
+	AA32_ID_WRITABLE(ID_PFR1_EL1),
 	{ SYS_DESC(SYS_ID_DFR0_EL1),
 	  .access = access_id_reg,
 	  .get_user = get_id_reg,
 	  .set_user = set_id_dfr0_el1,
 	  .visibility = aa32_id_visibility,
 	  .reset = read_sanitised_id_dfr0_el1,
-	  .val = ID_DFR0_EL1_PerfMon_MASK |
-		 ID_DFR0_EL1_CopDbg_MASK, },
+	  .val = GENMASK(31, 0) },
 	ID_HIDDEN(ID_AFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR2_EL1),
-	AA32_ID_SANITISED(ID_MMFR3_EL1),
+	AA32_ID_WRITABLE(ID_MMFR0_EL1),
+	AA32_ID_WRITABLE(ID_MMFR1_EL1),
+	AA32_ID_WRITABLE(ID_MMFR2_EL1),
+	AA32_ID_WRITABLE(ID_MMFR3_EL1),
 
 	/* CRm=2 */
-	AA32_ID_SANITISED(ID_ISAR0_EL1),
-	AA32_ID_SANITISED(ID_ISAR1_EL1),
-	AA32_ID_SANITISED(ID_ISAR2_EL1),
-	AA32_ID_SANITISED(ID_ISAR3_EL1),
-	AA32_ID_SANITISED(ID_ISAR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR5_EL1),
-	AA32_ID_SANITISED(ID_MMFR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR6_EL1),
+	AA32_ID_WRITABLE(ID_ISAR0_EL1),
+	AA32_ID_WRITABLE(ID_ISAR1_EL1),
+	AA32_ID_WRITABLE(ID_ISAR2_EL1),
+	AA32_ID_WRITABLE(ID_ISAR3_EL1),
+	AA32_ID_WRITABLE(ID_ISAR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR6_EL1),
 
 	/* CRm=3 */
-	AA32_ID_SANITISED(MVFR0_EL1),
-	AA32_ID_SANITISED(MVFR1_EL1),
-	AA32_ID_SANITISED(MVFR2_EL1),
+	AA32_ID_WRITABLE(MVFR0_EL1),
+	AA32_ID_WRITABLE(MVFR1_EL1),
+	AA32_ID_WRITABLE(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	AA32_ID_SANITISED(ID_PFR2_EL1),
+	AA32_ID_WRITABLE(ID_PFR2_EL1),
 	ID_HIDDEN(ID_DFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yosry Ahmed <[email protected]>

commit dc55b3c3f61246e483e50c85d8d5366f9567e188 upstream.

The APM lists the DbgCtlMsr field as being tracked by the VMCB_LBR clean bit. Always clear the bit when MSR_IA32_DEBUGCTLMSR is updated.

The history is complicated, it was correctly cleared for L1 before commit 1d5a1b5860ed ("KVM: x86: nSVM: correctly virtualize LBR msrs when L2 is running"). At that point svm_set_msr() started to rely on svm_update_lbrv() to clear the bit, but when nested virtualization is enabled the latter does not always clear it even if MSR_IA32_DEBUGCTLMSR changed. Go back to clearing it directly in svm_set_msr().

---
 arch/x86/kvm/svm/svm.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -3044,7 +3044,11 @@ static int svm_set_msr(struct kvm_vcpu *
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
+		if (svm_get_lbr_vmcb(svm)->save.dbgctl == data)
+			break;
+
 		svm_get_lbr_vmcb(svm)->save.dbgctl = data;
+		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
 		svm_update_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yosry Ahmed <[email protected]>

commit fbe5e5f030c22ae717ee422aaab0e00ea84fab5e upstream.

svm_update_lbrv() is called when MSR_IA32_DEBUGCTLMSR is updated, and on nested transitions where LBRV is used. It checks whether LBRV enablement needs to be changed in the current VMCB, and if it does, it also recalculate intercepts to LBR MSRs.

However, there are cases where intercepts need to be updated even when LBRV enablement doesn't. Example scenario:
- L1 has MSR_IA32_DEBUGCTLMSR cleared.
- L1 runs L2 without LBR_CTL_ENABLE (no LBRV).
- L2 sets DEBUGCTLMSR_LBR in MSR_IA32_DEBUGCTLMSR, svm_update_lbrv() sets LBR_CTL_ENABLE in VMCB02 and disables intercepts to LBR MSRs.
- L2 exits to L1, svm_update_lbrv() is not called on this transition.
- L1 clears MSR_IA32_DEBUGCTLMSR, svm_update_lbrv() finds that LBR_CTL_ENABLE is already cleared in VMCB01 and does nothing.
- Intercepts remain disabled, L1 reads to LBR MSRs read the host MSRs.

Fix it by always recalculating intercepts in svm_update_lbrv().

---
 arch/x86/kvm/svm/svm.c |   29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

@@ -852,25 +852,29 @@ void svm_copy_lbrs(struct vmcb *to_vmcb,
 	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }
 
-void svm_enable_lbrv(struct kvm_vcpu *vcpu)
+static void __svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
-	svm_recalc_lbr_msr_intercepts(vcpu);
 
 	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
 	if (is_guest_mode(vcpu))
 		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
 }
 
-static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
+void svm_enable_lbrv(struct kvm_vcpu *vcpu)
+{
+	__svm_enable_lbrv(vcpu);
+	svm_recalc_lbr_msr_intercepts(vcpu);
+}
+
+static void __svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
-	svm_recalc_lbr_msr_intercepts(vcpu);
 
 	/*
 	 * Move the LBR msrs back to the vmcb01 to avoid copying them

@@ -899,13 +903,18 @@ void svm_update_lbrv(struct kvm_vcpu *vc
 			    (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
 			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
-	if (enable_lbrv == current_enable_lbrv)
-		return;
+	if (enable_lbrv && !current_enable_lbrv)
+		__svm_enable_lbrv(vcpu);
+	else if (!enable_lbrv && current_enable_lbrv)
+		__svm_disable_lbrv(vcpu);
 
-	if (enable_lbrv)
-		svm_enable_lbrv(vcpu);
-	else
-		svm_disable_lbrv(vcpu);
+	/*
+	 * During nested transitions, it is possible that the current VMCB has
+	 * LBR_CTL set, but the previous LBR_CTL had it cleared (or vice versa).
+	 * In this case, even though LBR_CTL does not need an update, intercepts
+	 * do, so always recalculate the intercepts here.
+	 */
+	svm_recalc_lbr_msr_intercepts(vcpu);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yosry Ahmed <[email protected]>

commit 8a4821412cf2c1429fffa07c012dd150f2edf78c upstream.

The current scheme for handling LBRV when nested is used is very complicated, especially when L1 does not enable LBRV (i.e. does not set LBR_CTL_ENABLE_MASK).

To avoid copying LBRs between VMCB01 and VMCB02 on every nested transition, the current implementation switches between using VMCB01 or VMCB02 as the source of truth for the LBRs while L2 is running. If L2 enables LBR, VMCB02 is used as the source of truth. When L2 disables LBR, the LBRs are copied to VMCB01 and VMCB01 is used as the source of truth. This introduces significant complexity, and incorrect behavior in some cases.

For example, on a nested #VMEXIT, the LBRs are only copied from VMCB02 to VMCB01 if LBRV is enabled in VMCB01. This is because L2's writes to MSR_IA32_DEBUGCTLMSR to enable LBR are intercepted and propagated to VMCB01 instead of VMCB02. However, LBRV is only enabled in VMCB02 when L2 is running.

This means that if L2 enables LBR and exits to L1, the LBRs will not be propagated from VMCB02 to VMCB01, because LBRV is disabled in VMCB01.

There is no meaningful difference in CPUID rate in L2 when copying LBRs on every nested transition vs. the current approach, so do the simple and correct thing and always copy LBRs between VMCB01 and VMCB02 on nested transitions (when LBRV is disabled by L1). Drop the conditional LBRs copying in __svm_{enable/disable}_lbrv() as it is now unnecessary.

VMCB02 becomes the only source of truth for LBRs when L2 is running, regardless of LBRV being enabled by L1, drop svm_get_lbr_vmcb() and use svm->vmcb directly in its place.

---
 arch/x86/kvm/svm/nested.c |   20 +++++++-------------
 arch/x86/kvm/svm/svm.c    |   46 ++++++++++------------------------------------
 2 files changed, 17 insertions(+), 49 deletions(-)

@@ -669,11 +669,10 @@ static void nested_vmcb02_prepare_save(s
 		 */
 		svm_copy_lbrs(vmcb02, vmcb12);
 		vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS;
-		svm_update_lbrv(&svm->vcpu);
-
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	} else {
 		svm_copy_lbrs(vmcb02, vmcb01);
 	}
+	svm_update_lbrv(&svm->vcpu);
 }
 
 static inline bool is_evtinj_soft(u32 evtinj)

@@ -825,11 +824,7 @@ static void nested_vmcb02_prepare_contro
 			svm->soft_int_next_rip = vmcb12_rip;
 	}
 
-	vmcb02->control.virt_ext            = vmcb01->control.virt_ext &
-					      LBR_CTL_ENABLE_MASK;
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV))
-		vmcb02->control.virt_ext  |=
-			(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK);
+	/* LBR_CTL_ENABLE_MASK is controlled by svm_update_lbrv() */
 
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;

@@ -1169,13 +1164,12 @@ int nested_svm_vmexit(struct vcpu_svm *s
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
 	if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
-		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)))
 		svm_copy_lbrs(vmcb12, vmcb02);
-		svm_update_lbrv(vcpu);
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	else
 		svm_copy_lbrs(vmcb01, vmcb02);
-		svm_update_lbrv(vcpu);
-	}
+
+	svm_update_lbrv(vcpu);
 
 	if (vnmi) {
 		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sukrit Bhatnagar <[email protected]>

commit d0164c161923ac303bd843e04ebe95cfd03c6e19 upstream.

On an EPT violation, bit 7 of the exit qualification is set if the guest linear-address is valid. The derived page fault error code should not be checked for this bit.

---
 arch/x86/kvm/vmx/common.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -98,7 +98,7 @@ static inline int __vmx_handle_ept_viola
 	error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
 		      ? PFERR_PRESENT_MASK : 0;
 
-	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+	if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID)
 		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
 			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

commit 8a7348a9ed70bda1c1f51d3f1815bcbdf9f3b38c upstream.

nfsd exports a "pseudo root filesystem" which is used by NFSv4 to find the various exported filesystems using LOOKUP requests from a known root filehandle. NFSv3 uses the MOUNT protocol to find those exported filesystems and so is not given access to the pseudo root filesystem.

If a v3 (or v2) client uses a filehandle from that filesystem, nfsd_set_fh_dentry() will report an error, but still stores the export in "struct svc_fh" even though it also drops the reference (exp_put()). This means that when fh_put() is called an extra reference will be dropped which can lead to use-after-free and possible denial of service.

Normal NFS usage will not provide a pseudo-root filehandle to a v3 client. This bug can only be triggered by the client synthesising an incorrect filehandle.

To fix this we move the assignments to the svc_fh later, after all possible error cases have been detected.

---
 fs/nfsd/nfsfh.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -269,9 +269,6 @@ static __be32 nfsd_set_fh_dentry(struct
 				dentry);
 	}
 
-	fhp->fh_dentry = dentry;
-	fhp->fh_export = exp;
-
 	switch (fhp->fh_maxsize) {
 	case NFS4_FHSIZE:
 		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)

@@ -293,6 +290,9 @@ static __be32 nfsd_set_fh_dentry(struct
 			goto out;
 	}
 
+	fhp->fh_dentry = dentry;
+	fhp->fh_export = exp;
+
 	return 0;
 out:
 	exp_put(exp);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Olga Kornievskaia <[email protected]>

commit 4d3dbc2386fe051e44efad663e0ec828b98ab53f upstream.

RFC 7862 Section 4.1.2 says that if the server supports CLONE it MUST support clone_blksize attribute.

---
 fs/nfsd/nfsd.h |    1 +
 1 file changed, 1 insertion(+)

@@ -455,6 +455,7 @@ enum {
 #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
 	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
 	FATTR4_WORD2_MODE_UMASK | \
+	FATTR4_WORD2_CLONE_BLKSIZE | \
 	NFSD4_2_SECURITY_ATTRS | \
 	FATTR4_WORD2_XATTR_SUPPORT | \
 	FATTR4_WORD2_TIME_DELEG_ACCESS | \

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Olga Kornievskaia <[email protected]>

commit 4aa17144d5abc3c756883e3a010246f0dba8b468 upstream.

Typically copynotify stateid is freed either when parent's stateid is being close/freed or in nfsd4_laundromat if the stateid hasn't been used in a lease period.

However, in case when the server got an OPEN (which created a parent stateid), followed by a COPY_NOTIFY using that stateid, followed by a client reboot. New client instance while doing CREATE_SESSION would force expire previous state of this client. It leads to the open state being freed thru release_openowner-> nfs4_free_ol_stateid() and it finds that it still has copynotify stateid associated with it. We currently print a warning and is triggerred

WARNING: CPU: 1 PID: 8858 at fs/nfsd/nfs4state.c:1550 nfs4_free_ol_stateid+0xb0/0x100 [nfsd]

This patch, instead, frees the associated copynotify stateid here.

If the parent stateid is freed (without freeing the copynotify stateids associated with it), it leads to the list corruption when laundromat ends up freeing the copynotify state later.

[ 1626.839430] Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
[ 1626.842828] Modules linked in: nfnetlink_queue nfnetlink_log bluetooth cfg80211 rpcrdma rdma_cm iw_cm ib_cm ib_core nfsd nfs_acl lockd grace nfs_localio ext4 crc16 mbcache jbd2 overlay uinput snd_seq_dummy snd_hrtimer qrtr rfkill vfat fat uvcvideo snd_hda_codec_generic videobuf2_vmalloc videobuf2_memops snd_hda_intel uvc snd_intel_dspcfg videobuf2_v4l2 videobuf2_common snd_hda_codec snd_hda_core videodev snd_hwdep snd_seq mc snd_seq_device snd_pcm snd_timer snd soundcore sg loop auth_rpcgss vsock_loopback vmw_vsock_virtio_transport_common vmw_vsock_vmci_transport vmw_vmci vsock xfs 8021q garp stp llc mrp nvme ghash_ce e1000e nvme_core sr_mod nvme_keyring nvme_auth cdrom vmwgfx drm_ttm_helper ttm sunrpc dm_mirror dm_region_hash dm_log iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi fuse dm_multipath dm_mod nfnetlink
[ 1626.855594] CPU: 2 UID: 0 PID: 199 Comm: kworker/u24:33 Kdump: loaded Tainted: G    B   W           6.17.0-rc7+ #22 PREEMPT(voluntary)
[ 1626.857075] Tainted: [B]=BAD_PAGE, [W]=WARN
[ 1626.857573] Hardware name: VMware, Inc. VMware20,1/VBSA, BIOS VMW201.00V.24006586.BA64.2406042154 06/04/2024
[ 1626.858724] Workqueue: nfsd4 laundromat_main [nfsd]
[ 1626.859304] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 1626.860010] pc : __list_del_entry_valid_or_report+0x148/0x200
[ 1626.860601] lr : __list_del_entry_valid_or_report+0x148/0x200
[ 1626.861182] sp : ffff8000881d7a40
[ 1626.861521] x29: ffff8000881d7a40 x28: 0000000000000018 x27: ffff0000c2a98200
[ 1626.862260] x26: 0000000000000600 x25: 0000000000000000 x24: ffff8000881d7b20
[ 1626.862986] x23: ffff0000c2a981e8 x22: 1fffe00012410e7d x21: ffff0000920873e8
[ 1626.863701] x20: ffff0000920873e8 x19: ffff000086f22998 x18: 0000000000000000
[ 1626.864421] x17: 20747562202c3839 x16: 3932326636383030 x15: 3030666666662065
[ 1626.865092] x14: 6220646c756f6873 x13: 0000000000000001 x12: ffff60004fd9e4a3
[ 1626.865713] x11: 1fffe0004fd9e4a2 x10: ffff60004fd9e4a2 x9 : dfff800000000000
[ 1626.866320] x8 : 00009fffb0261b5e x7 : ffff00027ecf2513 x6 : 0000000000000001
[ 1626.866938] x5 : ffff00027ecf2510 x4 : ffff60004fd9e4a3 x3 : 0000000000000000
[ 1626.867553] x2 : 0000000000000000 x1 : ffff000096069640 x0 : 000000000000006d
[ 1626.868167] Call trace:
[ 1626.868382]  __list_del_entry_valid_or_report+0x148/0x200 (P)
[ 1626.868876]  _free_cpntf_state_locked+0xd0/0x268 [nfsd]
[ 1626.869368]  nfs4_laundromat+0x6f8/0x1058 [nfsd]
[ 1626.869813]  laundromat_main+0x24/0x60 [nfsd]
[ 1626.870231]  process_one_work+0x584/0x1050
[ 1626.870595]  worker_thread+0x4c4/0xc60
[ 1626.870893]  kthread+0x2f8/0x398
[ 1626.871146]  ret_from_fork+0x10/0x20
[ 1626.871422] Code: aa1303e1 aa1403e3 910e8000 97bc55d7 (d4210000)
[ 1626.871892] SMP: stopping secondary CPUs

---
 fs/nfsd/nfs4state.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1505,7 +1505,8 @@ static void nfs4_free_ol_stateid(struct
 	release_all_access(stp);
 	if (stp->st_stateowner)
 		nfs4_put_stateowner(stp->st_stateowner);
-	WARN_ON(!list_empty(&stid->sc_cp_list));
+	if (!list_empty(&stid->sc_cp_list))
+		nfs4_free_cpntf_statelist(stid->sc_client->net, stid);
 	kmem_cache_free(stateid_slab, stid);
 }
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Oberparleiter <[email protected]>

commit ec4d11fc4b2dd4a2fa8c9d801ee9753b74623554 upstream.

Using gcov on kernels compiled with GCC 15 results in truncated 16-byte long .gcda files with no usable data. To fix this, update GCOV_COUNTERS to match the value defined by GCC 15.

Tested with GCC 14.3.0 and GCC 15.2.0.

---
 kernel/gcov/gcc_4_7.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -18,7 +18,9 @@
 #include <linux/mm.h>
 #include "gcov.h"
 
-#if (__GNUC__ >= 14)
+#if (__GNUC__ >= 15)
+#define GCOV_COUNTERS			10
+#elif (__GNUC__ >= 14)
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ >= 10)
 #define GCOV_COUNTERS			8

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joshua Rogers <[email protected]>

commit 98a5fd31cbf72d46bf18e50b3ab0ce86d5f319a9 upstream.

When the per-IP connection limit is exceeded in ksmbd_kthread_fn(), the code sets ret = -EAGAIN and continues the accept loop without closing the just-accepted socket. That leaks one socket per rejected attempt from a single IP and enables a trivial remote DoS.

Release client_sk before continuing.

This bug was found with ZeroPath.

---
 fs/smb/server/transport_tcp.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -284,8 +284,11 @@ static int ksmbd_kthread_fn(void *p)
 			}
 		}
 		up_read(&conn_list_lock);
-		if (ret == -EAGAIN)
+		if (ret == -EAGAIN) {
+			/* Per-IP limit hit: release the just-accepted socket. */
+			sock_release(client_sk);
 			continue;
+		}
 
 skip_max_ip_conns_limit:
 		if (server_conf.max_connections &&

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pedro Demarchi Gomes <[email protected]>

commit f5548c318d6520d4fa3c5ed6003eeb710763cbc5 upstream.

Currently, scan_get_next_rmap_item() walks every page address in a VMA to locate mergeable pages. This becomes highly inefficient when scanning large virtual memory areas that contain mostly unmapped regions, causing ksmd to use large amount of cpu without deduplicating much pages.

This patch replaces the per-address lookup with a range walk using walk_page_range(). The range walker allows KSM to skip over entire unmapped holes in a VMA, avoiding unnecessary lookups. This problem was previously discussed in [1].

Consider the following test program which creates a 32 TiB mapping in the virtual address space but only populates a single page:

#include <unistd.h>
#include <stdio.h>
#include <sys/mman.h>

/* 32 TiB */
const size_t size = 32ul * 1024 * 1024 * 1024 * 1024;

int main() {
        char *area = mmap(NULL, size, PROT_READ | PROT_WRITE,
                          MAP_NORESERVE | MAP_PRIVATE | MAP_ANON, -1, 0);

        if (area == MAP_FAILED) {
                perror("mmap() failed\n");
                return -1;
        }

        /* Populate a single page such that we get an anon_vma. */
        *area = 0;

        /* Enable KSM. */
        madvise(area, size, MADV_MERGEABLE);
        pause();
        return 0;
}

$ ./ksm-sparse  &
$ echo 1 > /sys/kernel/mm/ksm/run

Without this patch ksmd uses 100% of the cpu for a long time (more then 1 hour in my test machine) scanning all the 32 TiB virtual address space that contain only one mapped page. This makes ksmd essentially deadlocked not able to deduplicate anything of value. With this patch ksmd walks only the one mapped page and skips the rest of the 32 TiB virtual address space, making the scan fast using little cpu.

---
 mm/ksm.c |  113 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 104 insertions(+), 9 deletions(-)

@@ -2458,6 +2458,95 @@ static bool should_skip_rmap_item(struct
 	return true;
 }
 
+struct ksm_next_page_arg {
+	struct folio *folio;
+	struct page *page;
+	unsigned long addr;
+};
+
+static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end,
+		struct mm_walk *walk)
+{
+	struct ksm_next_page_arg *private = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	pte_t *start_ptep = NULL, *ptep, pte;
+	struct mm_struct *mm = walk->mm;
+	struct folio *folio;
+	struct page *page;
+	spinlock_t *ptl;
+	pmd_t pmd;
+
+	if (ksm_test_exit(mm))
+		return 0;
+
+	cond_resched();
+
+	pmd = pmdp_get_lockless(pmdp);
+	if (!pmd_present(pmd))
+		return 0;
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && pmd_leaf(pmd)) {
+		ptl = pmd_lock(mm, pmdp);
+		pmd = pmdp_get(pmdp);
+
+		if (!pmd_present(pmd)) {
+			goto not_found_unlock;
+		} else if (pmd_leaf(pmd)) {
+			page = vm_normal_page_pmd(vma, addr, pmd);
+			if (!page)
+				goto not_found_unlock;
+			folio = page_folio(page);
+
+			if (folio_is_zone_device(folio) || !folio_test_anon(folio))
+				goto not_found_unlock;
+
+			page += ((addr & (PMD_SIZE - 1)) >> PAGE_SHIFT);
+			goto found_unlock;
+		}
+		spin_unlock(ptl);
+	}
+
+	start_ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!start_ptep)
+		return 0;
+
+	for (ptep = start_ptep; addr < end; ptep++, addr += PAGE_SIZE) {
+		pte = ptep_get(ptep);
+
+		if (!pte_present(pte))
+			continue;
+
+		page = vm_normal_page(vma, addr, pte);
+		if (!page)
+			continue;
+		folio = page_folio(page);
+
+		if (folio_is_zone_device(folio) || !folio_test_anon(folio))
+			continue;
+		goto found_unlock;
+	}
+
+not_found_unlock:
+	spin_unlock(ptl);
+	if (start_ptep)
+		pte_unmap(start_ptep);
+	return 0;
+found_unlock:
+	folio_get(folio);
+	spin_unlock(ptl);
+	if (start_ptep)
+		pte_unmap(start_ptep);
+	private->page = page;
+	private->folio = folio;
+	private->addr = addr;
+	return 1;
+}
+
+static struct mm_walk_ops ksm_next_page_ops = {
+	.pmd_entry = ksm_next_page_pmd_entry,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
 static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 {
 	struct mm_struct *mm;

@@ -2545,21 +2634,27 @@ next_mm:
 			ksm_scan.address = vma->vm_end;
 
 		while (ksm_scan.address < vma->vm_end) {
+			struct ksm_next_page_arg ksm_next_page_arg;
 			struct page *tmp_page = NULL;
-			struct folio_walk fw;
 			struct folio *folio;
 
 			if (ksm_test_exit(mm))
 				break;
 
-			folio = folio_walk_start(&fw, vma, ksm_scan.address, 0);
-			if (folio) {
-				if (!folio_is_zone_device(folio) &&
-				     folio_test_anon(folio)) {
-					folio_get(folio);
-					tmp_page = fw.page;
-				}
-				folio_walk_end(&fw, vma);
+			int found;
+
+			found = walk_page_range_vma(vma, ksm_scan.address,
+						    vma->vm_end,
+						    &ksm_next_page_ops,
+						    &ksm_next_page_arg);
+
+			if (found > 0) {
+				folio = ksm_next_page_arg.folio;
+				tmp_page = ksm_next_page_arg.page;
+				ksm_scan.address = ksm_next_page_arg.addr;
+			} else {
+				VM_WARN_ON_ONCE(found < 0);
+				ksm_scan.address = vma->vm_end - PAGE_SIZE;
 			}
 
 			if (tmp_page) {

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pasha Tatashin <[email protected]>

commit e38f65d317df1fd2dcafe614d9c537475ecf9992 upstream.

Patch series "KHO: kfence + KHO memory corruption fix", v3.

This series fixes a memory corruption bug in KHO that occurs when KFENCE is enabled.

The root cause is that KHO metadata, allocated via kzalloc(), can be randomly serviced by kfence_alloc(). When a kernel boots via KHO, the early memblock allocator is restricted to a "scratch area". This forces the KFENCE pool to be allocated within this scratch area, creating a conflict. If KHO metadata is subsequently placed in this pool, it gets corrupted during the next kexec operation.

Google is using KHO and have had obscure crashes due to this memory corruption, with stacks all over the place. I would prefer this fix to be properly backported to stable so we can also automatically consume it once we switch to the upstream KHO.

Patch 1/3 introduces a debug-only feature (CONFIG_KEXEC_HANDOVER_DEBUG) that adds checks to detect and fail any operation that attempts to place KHO metadata or preserved memory within the scratch area. This serves as a validation and diagnostic tool to confirm the problem without affecting production builds.

Patch 2/3 Increases bitmap to PAGE_SIZE, so buddy allocator can be used.

Patch 3/3 Provides the fix by modifying KHO to allocate its metadata directly from the buddy allocator instead of slab. This bypasses the KFENCE interception entirely.

This patch (of 3):

It is invalid for KHO metadata or preserved memory regions to be located within the KHO scratch area, as this area is overwritten when the next kernel is loaded, and used early in boot by the next kernel. This can lead to memory corruption.

Add checks to kho_preserve_* and KHO's internal metadata allocators (xa_load_or_alloc, new_chunk) to verify that the physical address of the memory does not overlap with any defined scratch region. If an overlap is detected, the operation will fail and a WARN_ON is triggered. To avoid performance overhead in production kernels, these checks are enabled only when CONFIG_KEXEC_HANDOVER_DEBUG is selected.

---
 kernel/Kconfig.kexec             |    9 ++++++
 kernel/Makefile                  |    1 
 kernel/kexec_handover.c          |   57 ++++++++++++++++++++++++++-------------
 kernel/kexec_handover_debug.c    |   25 +++++++++++++++++
 kernel/kexec_handover_internal.h |   20 +++++++++++++
 5 files changed, 93 insertions(+), 19 deletions(-)
 create mode 100644 kernel/kexec_handover_debug.c
 create mode 100644 kernel/kexec_handover_internal.h

@@ -109,6 +109,15 @@ config KEXEC_HANDOVER
 	  to keep data or state alive across the kexec. For this to work,
 	  both source and target kernels need to have this option enabled.
 
+config KEXEC_HANDOVER_DEBUG
+	bool "Enable Kexec Handover debug checks"
+	depends on KEXEC_HANDOVER
+	help
+	  This option enables extra sanity checks for the Kexec Handover
+	  subsystem. Since, KHO performance is crucial in live update
+	  scenarios and the extra code might be adding overhead it is
+	  only optionally enabled.
+
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	default ARCH_DEFAULT_CRASH_DUMP

@@ -82,6 +82,7 @@ obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
 obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o
 obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
+obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup/

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_handover_debug.c - kexec handover optional debug functionality
+ * Copyright (C) 2025 Google LLC, Pasha Tatashin <[email protected]>
+ */
+
+#define pr_fmt(fmt) "KHO: " fmt
+
+#include "kexec_handover_internal.h"
+
+bool kho_scratch_overlap(phys_addr_t phys, size_t size)
+{
+	phys_addr_t scratch_start, scratch_end;
+	unsigned int i;
+
+	for (i = 0; i < kho_scratch_cnt; i++) {
+		scratch_start = kho_scratch[i].addr;
+		scratch_end = kho_scratch[i].addr + kho_scratch[i].size;
+
+		if (phys < scratch_end && (phys + size) > scratch_start)
+			return true;
+	}
+
+	return false;
+}

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H
+#define LINUX_KEXEC_HANDOVER_INTERNAL_H
+
+#include <linux/kexec_handover.h>
+#include <linux/types.h>
+
+extern struct kho_scratch *kho_scratch;
+extern unsigned int kho_scratch_cnt;
+
+#ifdef CONFIG_KEXEC_HANDOVER_DEBUG
+bool kho_scratch_overlap(phys_addr_t phys, size_t size);
+#else
+static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size)
+{
+	return false;
+}
+#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */
+
+#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */

I ran into a build problem that afaics is caused by this change:

"""
In file included from ./arch/x86/include/asm/bug.h:103,

                 from ./arch/x86/include/asm/alternative.h:9,
                 from ./arch/x86/include/asm/barrier.h:5,
                 from ./include/asm-generic/bitops/generic-non-atomic.h:7,
                 from ./include/linux/bitops.h:28,
                 from ./include/linux/bitmap.h:8,
                 from ./include/linux/nodemask.h:91,
                 from ./include/linux/numa.h:6,
                 from ./include/linux/cma.h:7,
                 from kernel/kexec_handover.c:12:
kernel/kexec_handover.c: In function ‘kho_preserve_phys’:
kernel/kexec_handover.c:732:41: error: ‘nr_pages’ undeclared (first use in this function); did you mean ‘dir_pages’?
  732 |                                         nr_pages << PAGE_SHIFT))) {
      |                                         ^~~~~~~~

./include/asm-generic/bug.h:123:32: note: in definition of macro ‘WARN_ON’
123 | int __ret_warn_on = !!(condition); \
| ^~~~~~~~~
kernel/kexec_handover.c:732:41: note: each undeclared identifier is reported only once for each function it appears in

  732 |                                         nr_pages << PAGE_SHIFT))) {
      |                                         ^~~~~~~~

./include/asm-generic/bug.h:123:32: note: in definition of macro ‘WARN_ON’
123 | int __ret_warn_on = !!(condition); \
| ^~~~~~~~~
make[3]: *** [scripts/Makefile.build:287: kernel/kexec_handover.o] Error 1
make[3]: *** Waiting for unfinished jobs....
make[2]: *** [scripts/Makefile.build:556: kernel] Error 2
make[2]: *** Waiting for unfinished jobs....
make[1]: *** [/builddir/build/BUILD/kernel-6.17.9-build/kernel-6.17.9-rc1/linux-6.17.9-0.rc1.300.vanilla.fc43.x86_64/Makefile:2019: .] Error 2
make: *** [Makefile:256: __sub-make] Error 2
"""

Ciao, Thorsten

8375b76517cb5 ("kho: replace kho_preserve_phys() with kho_preserve_pages()") refactored this function to work on page granularity (nr_pages) instead of bytes (size). Since that commit wasn't backported, nr_pages does not exist.

Simple fix should be to replace "nr_pages << PAGE_SHIFT" with "size".

[...]

Regards,
Pratyush Yadav

Great, can you provide a working version? I'll go drop this patch from the queue for now and push out a -rc2

thanks,

greg k-h

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pasha Tatashin <[email protected]>

commit a2fff99f92dae9c0eaf0d75de3def70ec68dad92 upstream.

KHO memory preservation metadata is preserved in 512 byte chunks which requires their allocation from slab allocator. Slabs are not safe to be used with KHO because of kfence, and because partial slabs may lead leaks to the next kernel. Change the size to be PAGE_SIZE.

The kfence specifically may cause memory corruption, where it randomly provides slab objects that can be within the scratch area. The reason for that is that kfence allocates its objects prior to KHO scratch is marked as CMA region.

While this change could potentially increase metadata overhead on systems with sparsely preserved memory, this is being mitigated by ongoing work to reduce sparseness during preservation via 1G guest pages. Furthermore, this change aligns with future work on a stateless KHO, which will also use page-sized bitmaps for its radix tree metadata.

---
 kernel/kexec_handover.c |   21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

@@ -52,10 +52,10 @@ early_param("kho", kho_parse_enable);
  * Keep track of memory that is to be preserved across KHO.
  *
  * The serializing side uses two levels of xarrays to manage chunks of per-order
- * 512 byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order of a
- * 1TB system would fit inside a single 512 byte bitmap. For order 0 allocations
- * each bitmap will cover 16M of address space. Thus, for 16G of memory at most
- * 512K of bitmap memory will be needed for order 0.
+ * PAGE_SIZE byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order
+ * of a 8TB system would fit inside a single 4096 byte bitmap. For order 0
+ * allocations each bitmap will cover 128M of address space. Thus, for 16G of
+ * memory at most 512K of bitmap memory will be needed for order 0.
  *
  * This approach is fully incremental, as the serialization progresses folios
  * can continue be aggregated to the tracker. The final step, immediately prior

@@ -63,12 +63,14 @@ early_param("kho", kho_parse_enable);
  * successor kernel to parse.
  */
 
-#define PRESERVE_BITS (512 * 8)
+#define PRESERVE_BITS (PAGE_SIZE * 8)
 
 struct kho_mem_phys_bits {
 	DECLARE_BITMAP(preserve, PRESERVE_BITS);
 };
 
+static_assert(sizeof(struct kho_mem_phys_bits) == PAGE_SIZE);
+
 struct kho_mem_phys {
 	/*
 	 * Points to kho_mem_phys_bits, a sparse bitmap array. Each bit is sized

@@ -93,19 +95,19 @@ struct kho_serialization {
 	struct khoser_mem_chunk *preserved_mem_map;
 };
 
-static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
+static void *xa_load_or_alloc(struct xarray *xa, unsigned long index)
 {
 	void *res = xa_load(xa, index);
 
 	if (res)
 		return res;
 
-	void *elm __free(kfree) = kzalloc(sz, GFP_KERNEL);
+	void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
 	if (!elm)
 		return ERR_PTR(-ENOMEM);
 
-	if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), sz)))
+	if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), PAGE_SIZE)))
 		return ERR_PTR(-EINVAL);
 
 	res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL);

@@ -175,8 +177,7 @@ static int __kho_preserve_order(struct k
 		}
 	}
 
-	bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
-				sizeof(*bits));
+	bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
 	if (IS_ERR(bits))
 		return PTR_ERR(bits);
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pasha Tatashin <[email protected]>

commit fa759cd75bce5489eed34596daa53f721849a86f upstream.

KHO allocates metadata for its preserved memory map using the slab allocator via kzalloc(). This metadata is temporary and is used by the next kernel during early boot to find preserved memory.

A problem arises when KFENCE is enabled. kzalloc() calls can be randomly intercepted by kfence_alloc(), which services the allocation from a dedicated KFENCE memory pool. This pool is allocated early in boot via memblock.

When booting via KHO, the memblock allocator is restricted to a "scratch area", forcing the KFENCE pool to be allocated within it. This creates a conflict, as the scratch area is expected to be ephemeral and overwriteable by a subsequent kexec. If KHO metadata is placed in this KFENCE pool, it leads to memory corruption when the next kernel is loaded.

To fix this, modify KHO to allocate its metadata directly from the buddy allocator instead of slab.

---
 include/linux/gfp.h     |    3 +++
 kernel/kexec_handover.c |    6 +++---
 2 files changed, 6 insertions(+), 3 deletions(-)

@@ -7,6 +7,7 @@
 #include <linux/mmzone.h>
 #include <linux/topology.h>
 #include <linux/alloc_tag.h>
+#include <linux/cleanup.h>
 #include <linux/sched.h>
 
 struct vm_area_struct;

@@ -463,4 +464,6 @@ static inline struct folio *folio_alloc_
 /* This should be paired with folio_put() rather than free_contig_range(). */
 #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__))
 
+DEFINE_FREE(free_page, void *, free_page((unsigned long)_T))
+
 #endif /* __LINUX_GFP_H */

@@ -102,7 +102,7 @@ static void *xa_load_or_alloc(struct xar
 	if (res)
 		return res;
 
-	void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	void *elm __free(free_page) = (void *)get_zeroed_page(GFP_KERNEL);
 
 	if (!elm)
 		return ERR_PTR(-ENOMEM);

@@ -266,9 +266,9 @@ static_assert(sizeof(struct khoser_mem_c
 static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk,
 					  unsigned long order)
 {
-	struct khoser_mem_chunk *chunk __free(kfree) = NULL;
+	struct khoser_mem_chunk *chunk __free(free_page) = NULL;
 
-	chunk = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	chunk = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!chunk)
 		return ERR_PTR(-ENOMEM);
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pratyush Yadav <[email protected]>

commit b05addf6f0596edb1f82ab4059438c7ef2d2686d upstream.

Calling __kho_unpreserve() on a pair of (pfn, end_pfn) that wasn't preserved is a bug. Currently, if that is done, the physxa or bits can be NULL. This results in a soft lockup since a NULL physxa or bits results in redoing the loop without ever making any progress.

Return when physxa or bits are not found, but WARN first to loudly indicate invalid behaviour.

---
 kernel/kexec_handover.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -131,12 +131,12 @@ static void __kho_unpreserve(struct kho_
 		const unsigned long pfn_high = pfn >> order;
 
 		physxa = xa_load(&track->orders, order);
-		if (!physxa)
-			continue;
+		if (WARN_ON_ONCE(!physxa))
+			return;
 
 		bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
-		if (!bits)
-			continue;
+		if (WARN_ON_ONCE(!bits))
+			return;
 
 		clear_bit(pfn_high % PRESERVE_BITS, bits->preserve);
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nate Karstens <[email protected]>

commit 4da4e4bde1c453ac5cc2dce5def81d504ae257ee upstream.

The len member of the sk_buff is an unsigned int. This is cast to ssize_t (a signed type) for the first sk_buff in the comparison, but not the second sk_buff. On 32-bit systems, this can result in an integer underflow for certain values because unsigned arithmetic is being used.

This appears to be an oversight: if the intention was to use unsigned arithmetic, then the first cast would have been omitted. The change ensures both len values are cast to ssize_t.

The underflow causes an issue with ktls when multiple TLS PDUs are included in a single TCP segment. The mainline kernel does not use strparser for ktls anymore, but this is still useful for other features that still use strparser, and for backporting.

---
 net/strparser/strparser.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -238,7 +238,7 @@ static int __strp_recv(read_descriptor_t
 				strp_parser_err(strp, -EMSGSIZE, desc);
 				break;
 			} else if (len <= (ssize_t)head->len -
-					  skb->len - stm->strp.offset) {
+					  (ssize_t)skb->len - stm->strp.offset) {
 				/* Length must be into new skb (and also
 				 * greater than zero)
 				 */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Qinxin Xia <[email protected]>

commit 23ee8a2563a0f24cf4964685ced23c32be444ab8 upstream.

The padding field in the structure was previously reserved to maintain a stable interface for potential new fields, ensuring compatibility with user-space shared data structures. However,it was accidentally removed by tiantao in a prior commit, which may lead to incompatibility between user space and the kernel.

This patch reinstates the padding to restore the original structure layout and preserve compatibility.

---
 include/linux/map_benchmark.h |    1 +
 1 file changed, 1 insertion(+)

@@ -27,5 +27,6 @@ struct map_benchmark {
 	__u32 dma_dir; /* DMA data direction */
 	__u32 dma_trans_ns; /* time for DMA transmission in ns */
 	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
+	__u8 expansion[76]; /* For future use */
 };
 #endif /* _KERNEL_DMA_BENCHMARK_H */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Kaiser <[email protected]>

commit 91a54090026f84ceffaa12ac53c99b9f162946f6 upstream.

maple_tree tracepoints contain pointers to function names. Such a pointer is saved when a tracepoint logs an event. There's no guarantee that it's still valid when the event is parsed later and the pointer is dereferenced.

The kernel warns about these unsafe pointers.

	event 'ma_read' has unsafe pointer field 'fn'
	WARNING: kernel/trace/trace.c:3779 at ignore_event+0x1da/0x1e4

Mark the function names as tracepoint_string() to fix the events.

One case that doesn't work without my patch would be trace-cmd record to save the binary ringbuffer and trace-cmd report to parse it in userspace. The address of __func__ can't be dereferenced from userspace but tracepoint_string will add an entry to /sys/kernel/tracing/printk_formats

---
 lib/maple_tree.c |   30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

@@ -64,6 +64,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/maple_tree.h>
 
+#define TP_FCT tracepoint_string(__func__)
+
 /*
  * Kernel pointer hashing renders much of the maple tree dump useless as tagged
  * pointers get hashed to arbitrary values.

@@ -2976,7 +2978,7 @@ static inline void mas_rebalance(struct
 	MA_STATE(l_mas, mas->tree, mas->index, mas->last);
 	MA_STATE(r_mas, mas->tree, mas->index, mas->last);
 
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 
 	/*
 	 * Rebalancing occurs if a node is insufficient.  Data is rebalanced

@@ -3337,7 +3339,7 @@ static void mas_split(struct ma_state *m
 	MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last);
 	MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last);
 
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 
 	mast.l = &l_mas;
 	mast.r = &r_mas;

@@ -3512,7 +3514,7 @@ static bool mas_is_span_wr(struct ma_wr_
 			return false;
 	}
 
-	trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry);
+	trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry);
 	return true;
 }
 

@@ -3756,7 +3758,7 @@ static noinline void mas_wr_spanning_sto
 	 * of data may happen.
 	 */
 	mas = wr_mas->mas;
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 
 	if (unlikely(!mas->index && mas->last == ULONG_MAX))
 		return mas_new_root(mas, wr_mas->entry);

@@ -3894,7 +3896,7 @@ done:
 	} else {
 		memcpy(wr_mas->node, newnode, sizeof(struct maple_node));
 	}
-	trace_ma_write(__func__, mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
 	mas_update_gap(mas);
 	mas->end = new_end;
 	return;

@@ -3938,7 +3940,7 @@ static inline void mas_wr_slot_store(str
 		mas->offset++; /* Keep mas accurate. */
 	}
 
-	trace_ma_write(__func__, mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
 	/*
 	 * Only update gap when the new entry is empty or there is an empty
 	 * entry in the original two ranges.

@@ -4059,7 +4061,7 @@ static inline void mas_wr_append(struct
 		mas_update_gap(mas);
 
 	mas->end = new_end;
-	trace_ma_write(__func__, mas, new_end, wr_mas->entry);
+	trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry);
 	return;
 }
 

@@ -4073,7 +4075,7 @@ static void mas_wr_bnode(struct ma_wr_st
 {
 	struct maple_big_node b_node;
 
-	trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry);
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
 	mas_commit_b_node(wr_mas, &b_node);

@@ -5405,7 +5407,7 @@ void *mas_store(struct ma_state *mas, vo
 	int request;
 	MA_WR_STATE(wr_mas, mas, entry);
 
-	trace_ma_write(__func__, mas, 0, entry);
+	trace_ma_write(TP_FCT, mas, 0, entry);
 #ifdef CONFIG_DEBUG_MAPLE_TREE
 	if (MAS_WARN_ON(mas, mas->index > mas->last))
 		pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last,

@@ -5506,7 +5508,7 @@ void mas_store_prealloc(struct ma_state
 	}
 
 store:
-	trace_ma_write(__func__, mas, 0, entry);
+	trace_ma_write(TP_FCT, mas, 0, entry);
 	mas_wr_store_entry(&wr_mas);
 	MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas));
 	mas_destroy(mas);

@@ -6319,7 +6321,7 @@ void *mtree_load(struct maple_tree *mt,
 	MA_STATE(mas, mt, index, index);
 	void *entry;
 
-	trace_ma_read(__func__, &mas);
+	trace_ma_read(TP_FCT, &mas);
 	rcu_read_lock();
 retry:
 	entry = mas_start(&mas);

@@ -6362,7 +6364,7 @@ int mtree_store_range(struct maple_tree
 	MA_STATE(mas, mt, index, last);
 	int ret = 0;
 
-	trace_ma_write(__func__, &mas, 0, entry);
+	trace_ma_write(TP_FCT, &mas, 0, entry);
 	if (WARN_ON_ONCE(xa_is_advanced(entry)))
 		return -EINVAL;
 

@@ -6585,7 +6587,7 @@ void *mtree_erase(struct maple_tree *mt,
 	void *entry = NULL;
 
 	MA_STATE(mas, mt, index, index);
-	trace_ma_op(__func__, &mas);
+	trace_ma_op(TP_FCT, &mas);
 
 	mtree_lock(mt);
 	entry = mas_erase(&mas);

@@ -6923,7 +6925,7 @@ void *mt_find(struct maple_tree *mt, uns
 	unsigned long copy = *index;
 #endif
 
-	trace_ma_read(__func__, &mas);
+	trace_ma_read(TP_FCT, &mas);
 
 	if ((*index) > max)
 		return NULL;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Huacai Chen <[email protected]>

commit 43a9e6a10bdde32445ad2725f568e08a94e51dc9 upstream.

1. Use phys_addr_t instead of u64, which can work for both 32/64 bits.
2. Check whether the input physical address is above TO_PHYS_MASK (and return NULL if yes) for the DMW version.

Note: In theory early_ioremap() also need the TO_PHYS_MASK checking, but the UEFI BIOS pass some DMW virtual addresses.

---
 arch/loongarch/include/asm/io.h |    5 ++++-
 arch/loongarch/mm/ioremap.c     |    2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

@@ -14,7 +14,7 @@
 #include <asm/pgtable-bits.h>
 #include <asm/string.h>
 
-extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size);
+extern void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size);
 extern void __init early_iounmap(void __iomem *addr, unsigned long size);
 
 #define early_memremap early_ioremap

@@ -25,6 +25,9 @@ extern void __init early_iounmap(void __
 static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 					 pgprot_t prot)
 {
+	if (offset > TO_PHYS_MASK)
+		return NULL;
+
 	switch (pgprot_val(prot) & _CACHE_MASK) {
 	case _CACHE_CC:
 		return (void __iomem *)(unsigned long)(CACHE_BASE + offset);

@@ -6,7 +6,7 @@
 #include <asm/io.h>
 #include <asm-generic/early_ioremap.h>
 
-void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size)
+void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size)
 {
 	return ((void __iomem *)TO_CACHE(phys_addr));
 }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Huacai Chen <[email protected]>

commit eeeeaafa62ea0cd4b86390f657dc0aea73bff4f5 upstream.

CSR.FWPC and CSR.MWPC are 32bit registers, so use csr_read32() rather than csr_read64() to read the values of FWPC/MWPC.

---
 arch/loongarch/include/asm/hw_breakpoint.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -134,13 +134,13 @@ static inline void hw_breakpoint_thread_
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
-	return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM;
+	return csr_read32(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM;
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
-	return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM;
+	return csr_read32(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM;
 }
 
 #endif	/* __KERNEL__ */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tianyang Zhang <[email protected]>

commit a073d637c8cfbfbab39b7272226a3fbf3b887580 upstream.

Now if the PTE/PMD is dirty with _PAGE_DIRTY but without _PAGE_MODIFIED, after {pte,pmd}_modify() we lose _PAGE_DIRTY, then {pte,pmd}_dirty() return false and lead to data loss. This can happen in certain scenarios such as HW PTW doesn't set _PAGE_MODIFIED automatically, so here we need _PAGE_MODIFIED to record the dirty status (_PAGE_DIRTY).

The new modification involves checking whether the original PTE/PMD has the _PAGE_DIRTY flag. If it exists, the _PAGE_MODIFIED bit is also set, ensuring that the {pte,pmd}_dirty() interface can always return accurate information.

---
 arch/loongarch/include/asm/pgtable.h |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -424,6 +424,9 @@ static inline unsigned long pte_accessib
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
+	if (pte_val(pte) & _PAGE_DIRTY)
+		pte_val(pte) |= _PAGE_MODIFIED;
+
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
 		     (pgprot_val(newprot) & ~_PAGE_CHG_MASK));
 }

@@ -547,9 +550,11 @@ static inline struct page *pmd_page(pmd_
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmd_val(pmd) = (pmd_val(pmd) & _HPAGE_CHG_MASK) |
-				(pgprot_val(newprot) & ~_HPAGE_CHG_MASK);
-	return pmd;
+	if (pmd_val(pmd) & _PAGE_DIRTY)
+		pmd_val(pmd) |= _PAGE_MODIFIED;
+
+	return __pmd((pmd_val(pmd) & _HPAGE_CHG_MASK) |
+		     (pgprot_val(newprot) & ~_HPAGE_CHG_MASK));
 }
 
 static inline pmd_t pmd_mkinvalid(pmd_t pmd)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chuang Wang <[email protected]>

commit ac1499fcd40fe06479e9b933347b837ccabc2a40 upstream.

The sit driver's packet transmission path calls: sit_tunnel_xmit() -> update_or_create_fnhe(), which lead to fnhe_remove_oldest() being called to delete entries exceeding FNHE_RECLAIM_DEPTH+random.

The race window is between fnhe_remove_oldest() selecting fnheX for deletion and the subsequent kfree_rcu(). During this time, the concurrent path's __mkroute_output() -> find_exception() can fetch the soon-to-be-deleted fnheX, and rt_bind_exception() then binds it with a new dst using a dst_hold(). When the original fnheX is freed via RCU, the dst reference remains permanently leaked.

CPU 0 CPU 1
__mkroute_output()
find_exception() [fnheX]
update_or_create_fnhe()
fnhe_remove_oldest() [fnheX]
rt_bind_exception() [bind dst]
RCU callback [fnheX freed, dst leak]

This issue manifests as a device reference count leak and a warning in dmesg when unregistering the net device:

unregister_netdevice: waiting for sitX to become free. Usage count = N

Ido Schimmel provided the simple test validation method [1].

The fix clears 'oldest->fnhe_daddr' before calling fnhe_flush_routes(). Since rt_bind_exception() checks this field, setting it to zero prevents the stale fnhe from being reused and bound to a new dst just before it is freed.

[1]
ip netns add ns1
ip -n ns1 link set dev lo up
ip -n ns1 address add 192.0.2.1/32 dev lo
ip -n ns1 link add name dummy1 up type dummy
ip -n ns1 route add 192.0.2.2/32 dev dummy1
ip -n ns1 link add name gretap1 up arp off type gretap \

    local 192.0.2.1 remote 192.0.2.2
ip -n ns1 route add 198.51.0.0/16 dev gretap1
taskset -c 0 ip netns exec ns1 mausezahn gretap1 \
    -A 198.51.100.1 -B 198.51.0.0/16 -t udp -p 1000 -c 0 -q &
taskset -c 2 ip netns exec ns1 mausezahn gretap1 \
    -A 198.51.100.1 -B 198.51.0.0/16 -t udp -p 1000 -c 0 -q &

sleep 10
ip netns pids ns1 | xargs kill
ip netns del ns1

---
 net/ipv4/route.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -606,6 +606,11 @@ static void fnhe_remove_oldest(struct fn
 			oldest_p = fnhe_p;
 		}
 	}
+
+	/* Clear oldest->fnhe_daddr to prevent this fnhe from being
+	 * rebound with new dsts in rt_bind_exception().
+	 */
+	oldest->fnhe_daddr = 0;
 	fnhe_flush_routes(oldest);
 	*oldest_p = oldest->fnhe_next;
 	kfree_rcu(oldest, rcu);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quanmin Yan <[email protected]>

commit 9fd7bb5083d1e1027b8ac1e365c29921ab88b177 upstream.

In DAMON's damon_sysfs_repeat_call_fn(), time_before() is used to compare the current jiffies with next_update_jiffies to determine whether to update the sysfs files at this moment.

On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this causes time_before() in damon_sysfs_repeat_call_fn() to unexpectedly return true during the first 5 minutes after boot on 32-bit systems (see [1] for more explanation, which fixes another jiffies-related issue before). As a result, DAMON does not update sysfs files during that period.

There is also an issue unrelated to the system's word size[2]: if the user stops DAMON just after next_update_jiffies is updated and restarts it after 'refresh_ms' or a longer delay, next_update_jiffies will retain an older value, causing time_before() to return false and the update to happen earlier than expected.

Fix these issues by making next_update_jiffies a global variable and initializing it each time DAMON is started.

---
 mm/damon/sysfs.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

@@ -1514,16 +1514,17 @@ static struct damon_ctx *damon_sysfs_bui
 	return ctx;
 }
 
+static unsigned long damon_sysfs_next_update_jiffies;
+
 static int damon_sysfs_repeat_call_fn(void *data)
 {
 	struct damon_sysfs_kdamond *sysfs_kdamond = data;
-	static unsigned long next_update_jiffies;
 
 	if (!sysfs_kdamond->refresh_ms)
 		return 0;
-	if (time_before(jiffies, next_update_jiffies))
+	if (time_before(jiffies, damon_sysfs_next_update_jiffies))
 		return 0;
-	next_update_jiffies = jiffies +
+	damon_sysfs_next_update_jiffies = jiffies +
 		msecs_to_jiffies(sysfs_kdamond->refresh_ms);
 
 	if (!mutex_trylock(&damon_sysfs_lock))

@@ -1569,6 +1570,9 @@ static int damon_sysfs_turn_damon_on(str
 	}
 	kdamond->damon_ctx = ctx;
 
+	damon_sysfs_next_update_jiffies =
+		jiffies + msecs_to_jiffies(kdamond->refresh_ms);
+
 	repeat_call_control->fn = damon_sysfs_repeat_call_fn;
 	repeat_call_control->data = kdamond;
 	repeat_call_control->repeat = true;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Edward Adam Davis <[email protected]>

commit 9a6b60cb147d53968753a34805211d2e5e08c027 upstream.

Because kthread_stop did not stop sc_task properly and returned -EINTR, the sc_timer was not properly closed, ultimately causing the problem [1] reported by syzbot when freeing sci due to the sc_timer not being closed.

Because the thread sc_task main function nilfs_segctor_thread() returns 0 when it succeeds, when the return value of kthread_stop() is not 0 in nilfs_segctor_destroy(), we believe that it has not properly closed sc_timer.

We use timer_shutdown_sync() to sync wait for sc_timer to shutdown, and set the value of sc_task to NULL under the protection of lock sc_state_lock, so as to avoid the issue caused by sc_timer not being properly shutdowned.

[1]
ODEBUG: free active (active state 0) object: 00000000dacb411a object type: timer_list hint: nilfs_construction_timeout

Call trace:
 nilfs_segctor_destroy fs/nilfs2/segment.c:2811 [inline]
 nilfs_detach_log_writer+0x668/0x8cc fs/nilfs2/segment.c:2877
 nilfs_put_super+0x4c/0x12c fs/nilfs2/super.c:509

---
 fs/nilfs2/segment.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct
 
 	if (sci->sc_task) {
 		wake_up(&sci->sc_wait_daemon);
-		kthread_stop(sci->sc_task);
+		if (kthread_stop(sci->sc_task)) {
+			spin_lock(&sci->sc_state_lock);
+			sci->sc_task = NULL;
+			timer_shutdown_sync(&sci->sc_timer);
+			spin_unlock(&sci->sc_state_lock);
+		}
 	}
 
 	spin_lock(&sci->sc_state_lock);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Breno Leitao <[email protected]>

commit 49c8d2c1f94cc2f4d1a108530d7ba52614b874c2 upstream.

commit efa95b01da18 ("netpoll: fix use after free") incorrectly ignored the refcount and prematurely set dev->npinfo to NULL during netpoll cleanup, leading to improper behavior and memory leaks.

Scenario causing lack of proper cleanup:

1) A netpoll is associated with a NIC (e.g., eth0) and netdev->npinfo is allocated, and refcnt = 1
- Keep in mind that npinfo is shared among all netpoll instances. In this case, there is just one.

2) Another netpoll is also associated with the same NIC and npinfo->refcnt += 1.
- Now dev->npinfo->refcnt = 2;
- There is just one npinfo associated to the netdev.

3) When the first netpolls goes to clean up:
- The first cleanup succeeds and clears np->dev->npinfo, ignoring refcnt.
- It basically calls RCU_INIT_POINTER(np->dev->npinfo, NULL);
- Set dev->npinfo = NULL, without proper cleanup
- No ->ndo_netpoll_cleanup() is either called

4) Now the second target tries to clean up
- The second cleanup fails because np->dev->npinfo is already NULL.
* In this case, ops->ndo_netpoll_cleanup() was never called, and the skb pool is not cleaned as well (for the second netpoll instance)
- This leaks npinfo and skbpool skbs, which is clearly reported by kmemleak.

Revert commit efa95b01da18 ("netpoll: fix use after free") and adds clarifying comments emphasizing that npinfo cleanup should only happen once the refcount reaches zero, ensuring stable and correct netpoll behavior.

---
 net/core/netpoll.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -812,6 +812,10 @@ static void __netpoll_cleanup(struct net
 	if (!npinfo)
 		return;
 
+	/* At this point, there is a single npinfo instance per netdevice, and
+	 * its refcnt tracks how many netpoll structures are linked to it. We
+	 * only perform npinfo cleanup when the refcnt decrements to zero.
+	 */
 	if (refcount_dec_and_test(&npinfo->refcnt)) {
 		const struct net_device_ops *ops;
 

@@ -821,8 +825,7 @@ static void __netpoll_cleanup(struct net
 
 		RCU_INIT_POINTER(np->dev->npinfo, NULL);
 		call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info);
-	} else
-		RCU_INIT_POINTER(np->dev->npinfo, NULL);
+	}
 
 	skb_pool_flush(np);
 }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lance Yang <[email protected]>

commit 6f86d0534fddfbd08687fa0f01479d4226bc3c3d upstream.

When a page fault occurs in a secret memory file created with memfd_secret(2), the kernel will allocate a new folio for it, mark the underlying page as not-present in the direct map, and add it to the file mapping.

If two tasks cause a fault in the same page concurrently, both could end up allocating a folio and removing the page from the direct map, but only one would succeed in adding the folio to the file mapping. The task that failed undoes the effects of its attempt by (a) freeing the folio again and (b) putting the page back into the direct map. However, by doing these two operations in this order, the page becomes available to the allocator again before it is placed back in the direct mapping.

If another task attempts to allocate the page between (a) and (b), and the kernel tries to access it via the direct map, it would result in a supervisor not-present page fault.

Fix the ordering to restore the direct map before the folio is freed.

---
 mm/secretmem.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -82,13 +82,13 @@ retry:
 		__folio_mark_uptodate(folio);
 		err = filemap_add_folio(mapping, folio, offset, gfp);
 		if (unlikely(err)) {
-			folio_put(folio);
 			/*
 			 * If a split of large page was required, it
 			 * already happened when we marked the page invalid
 			 * which guarantees that this call won't fail
 			 */
 			set_direct_map_default_noflush(folio_page(folio, 0));
+			folio_put(folio);
 			if (err == -EEXIST)
 				goto retry;
 

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt <[email protected]>

commit dd4adb986a86727ed8f56c48b6d0695f1e211e65 upstream.

The tracing selftest "event-filter-function.tc" was failing because it first runs the "sample_events" function that triggers the kmem_cache_free event and it looks at what function was used during a call to "ls".

But the first time it calls this, it could trigger events that are used to pull pages into the page cache.

The rest of the test uses the function it finds during that call to see if it will be called in subsequent "sample_events" calls. But if there's no need to pull pages into the page cache, it will not trigger that function and the test will fail.

Call the "sample_events" twice to trigger all the page cache work before it calls it to find a function to use in subsequent checks.

---
 tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc |    4 ++++
 1 file changed, 4 insertions(+)

@@ -20,6 +20,10 @@ sample_events() {
 echo 0 > tracing_on
 echo 0 > events/enable
 
+# Clear functions caused by page cache; run sample_events twice
+sample_events
+sample_events
+
 echo "Get the most frequently calling function"
 echo > trace
 sample_events

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg <[email protected]>

commit a9da90e618cd0669a22bcc06a96209db5dd96e9b upstream.

While connecting, the MAC address can already no longer be changed. The change is already rejected if netif_carrier_ok(), but of course that's not true yet while connecting. Check for auth_data or assoc_data, so the MAC address cannot be changed.

Also more comprehensively check that there are no stations on the interface being changed - if any peer station is added it will know about our address already, so we cannot change it.

---
 net/mac80211/iface.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

@@ -223,6 +223,10 @@ static int ieee80211_can_powered_addr_ch
 	if (netif_carrier_ok(sdata->dev))
 		return -EBUSY;
 
+	/* if any stations are set known (so they know this vif too), reject */
+	if (sta_info_get_by_idx(sdata, 0))
+		return -EBUSY;
+
 	/* First check no ROC work is happening on this iface */
 	list_for_each_entry(roc, &local->roc_list, list) {
 		if (roc->sdata != sdata)

@@ -242,12 +246,16 @@ static int ieee80211_can_powered_addr_ch
 			ret = -EBUSY;
 	}
 
+	/*
+	 * More interface types could be added here but changing the
+	 * address while powered makes the most sense in client modes.
+	 */
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
-		/* More interface types could be added here but changing the
-		 * address while powered makes the most sense in client modes.
-		 */
+		/* refuse while connecting */
+		if (sdata->u.mgd.auth_data || sdata->u.mgd.assoc_data)
+			return -EBUSY;
 		break;
 	default:
 		ret = -EOPNOTSUPP;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zi Yan <[email protected]>

commit fa5a061700364bc28ee1cb1095372f8033645dcb upstream.

folio split clears PG_has_hwpoisoned, but the flag should be preserved in after-split folios containing pages with PG_hwpoisoned flag if the folio is split to >0 order folios. Scan all pages in a to-be-split folio to determine which after-split folios need the flag.

An alternatives is to change PG_has_hwpoisoned to PG_maybe_hwpoisoned to avoid the scan and set it on all after-split folios, but resulting false positive has undesirable negative impact. To remove false positive, caller of folio_test_has_hwpoisoned() and folio_contain_hwpoisoned_page() needs to do the scan. That might be causing a hassle for current and future callers and more costly than doing the scan in the split code. More details are discussed in [1].

This issue can be exposed via:
1. splitting a has_hwpoisoned folio to >0 order from debugfs interface;
2. truncating part of a has_hwpoisoned folio in truncate_inode_partial_folio().

And later accesses to a hwpoisoned page could be possible due to the missing has_hwpoisoned folio flag. This will lead to MCE errors.

---
 mm/huge_memory.c |   23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

@@ -3271,6 +3271,14 @@ bool can_split_folio(struct folio *folio
 					caller_pins;
 }
 
+static bool page_range_has_hwpoisoned(struct page *page, long nr_pages)
+{
+	for (; nr_pages; page++, nr_pages--)
+		if (PageHWPoison(page))
+			return true;
+	return false;
+}
+
 /*
  * It splits @folio into @new_order folios and copies the @folio metadata to
  * all the resulting folios.

@@ -3278,17 +3286,24 @@ bool can_split_folio(struct folio *folio
 static void __split_folio_to_order(struct folio *folio, int old_order,
 		int new_order)
 {
+	/* Scan poisoned pages when split a poisoned folio to large folios */
+	const bool handle_hwpoison = folio_test_has_hwpoisoned(folio) && new_order;
 	long new_nr_pages = 1 << new_order;
 	long nr_pages = 1 << old_order;
 	long i;
 
+	folio_clear_has_hwpoisoned(folio);
+
+	/* Check first new_nr_pages since the loop below skips them */
+	if (handle_hwpoison &&
+	    page_range_has_hwpoisoned(folio_page(folio, 0), new_nr_pages))
+		folio_set_has_hwpoisoned(folio);
 	/*
 	 * Skip the first new_nr_pages, since the new folio from them have all
 	 * the flags from the original folio.
 	 */
 	for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) {
 		struct page *new_head = &folio->page + i;
-
 		/*
 		 * Careful: new_folio is not a "real" folio before we cleared PageTail.
 		 * Don't pass it around before clear_compound_head().

@@ -3330,6 +3345,10 @@ static void __split_folio_to_order(struc
 				 (1L << PG_dirty) |
 				 LRU_GEN_MASK | LRU_REFS_MASK));
 
+		if (handle_hwpoison &&
+		    page_range_has_hwpoisoned(new_head, new_nr_pages))
+			folio_set_has_hwpoisoned(new_folio);
+
 		new_folio->mapping = folio->mapping;
 		new_folio->index = folio->index + i;
 

@@ -3430,8 +3449,6 @@ static int __split_unmapped_folio(struct
 	if (folio_test_anon(folio))
 		mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
 
-	folio_clear_has_hwpoisoned(folio);
-
 	/*
 	 * split to new_order one order at a time. For uniform split,
 	 * folio is split to new_order directly.

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Yang <[email protected]>

commit 895b4c0c79b092d732544011c3cecaf7322c36a1 upstream.

Pde is erased from subdir rbtree through rb_erase(), but not set the node to EMPTY, which may result in uaf access. We should use RB_CLEAR_NODE() set the erased node to EMPTY, then pde_subdir_next() will return NULL to avoid uaf access.

We found an uaf issue while using stress-ng testing, need to run testcase getdent and tun in the same time. The steps of the issue is as follows:

1) use getdent to traverse dir /proc/pid/net/dev_snmp6/, and current pde is tun3;

2) in the [time windows] unregister netdevice tun3 and tun2, and erase them from rbtree. erase tun3 first, and then erase tun2. the pde(tun2) will be released to slab;

3) continue to getdent process, then pde_subdir_next() will return pde(tun2) which is released, it will case uaf access.

CPU 0 | CPU 1
-------------------------------------------------------------------------

traverse dir /proc/pid/net/dev_snmp6/      |   unregister_netdevice(tun->dev)   //tun3 tun2
sys_getdents64()                           |
  iterate_dir()                            |
    proc_readdir()                         |
      proc_readdir_de()                    |     snmp6_unregister_dev()
        pde_get(de);                       |       proc_remove()
        read_unlock(&proc_subdir_lock);    |         remove_proc_subtree()
                                           |           write_lock(&proc_subdir_lock);
        [time window]                      |           rb_erase(&root->subdir_node, &parent->subdir);
                                           |           write_unlock(&proc_subdir_lock);
        read_lock(&proc_subdir_lock);      |
        next = pde_subdir_next(de);        |
        pde_put(de);                       |
        de = next;    //UAF                |

rbtree of dev_snmp6

                        |
                    pde(tun3)
                     /    \
                  NULL  pde(tun2)

---
 fs/proc/generic.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

@@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde)
 	}
 }
 
+static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent)
+{
+	rb_erase(&pde->subdir_node, &parent->subdir);
+	RB_CLEAR_NODE(&pde->subdir_node);
+}
+
 /*
  * Remove a /proc entry and free it if it's not currently in use.
  */

@@ -720,7 +726,7 @@ void remove_proc_entry(const char *name,
 			WARN(1, "removing permanent /proc entry '%s'", de->name);
 			de = NULL;
 		} else {
-			rb_erase(&de->subdir_node, &parent->subdir);
+			pde_erase(de, parent);
 			if (S_ISDIR(de->mode))
 				parent->nlink--;
 		}

@@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name
 			root->parent->name, root->name);
 		return -EINVAL;
 	}
-	rb_erase(&root->subdir_node, &parent->subdir);
+	pde_erase(root, parent);
 
 	de = root;
 	while (1) {

@@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name
 					next->parent->name, next->name);
 				return -EINVAL;
 			}
-			rb_erase(&next->subdir_node, &de->subdir);
+			pde_erase(next, de);
 			de = next;
 			continue;
 		}

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Isaac J. Manjarres <[email protected]>

commit 0d6c356dd6547adac2b06b461528e3573f52d953 upstream.

When emitting the order of the allocation for a hash table, alloc_large_system_hash() unconditionally subtracts PAGE_SHIFT from log base 2 of the allocation size. This is not correct if the allocation size is smaller than a page, and yields a negative value for the order as seen below:

TCP established hash table entries: 32 (order: -4, 256 bytes, linear) TCP bind hash table entries: 32 (order: -2, 1024 bytes, linear)

Use get_order() to compute the order when emitting the hash table information to correctly handle cases where the allocation size is smaller than a page:

TCP established hash table entries: 32 (order: 0, 256 bytes, linear) TCP bind hash table entries: 32 (order: 0, 1024 bytes, linear)

---
 mm/mm_init.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2537,7 +2537,7 @@ void *__init alloc_large_system_hash(con
 		panic("Failed to allocate %s hash table\n", tablename);
 
 	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
-		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
+		tablename, 1UL << log2qty, get_order(size), size,
 		virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
 
 	if (_hash_shift)