4.14.126-stable review

[ Upstream commit fbc2a15e3433058582e5635aabe48a3011a644a8 ]

With holding queue's kobject refcount, it is safe for driver to schedule requeue. However, blk_mq_kick_requeue_list() may be called after blk_sync_queue() is done because of concurrent requeue activities, then requeue work may not be completed when freeing queue, and kernel oops is triggered.

So moving the cancel of requeue_work into blk_mq_release() for avoiding race between requeue and freeing queue.

---
 block/blk-core.c | 1 -
 block/blk-mq.c   | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

index 0b14aebfd1a8..4e04c79aa2c2 100644
@@ -339,7 +339,6 @@ void blk_sync_queue(struct request_queue *q)
 		struct blk_mq_hw_ctx *hctx;
 		int i;
 
-		cancel_delayed_work_sync(&q->requeue_work);
 		queue_for_each_hw_ctx(q, hctx, i)
 			cancel_delayed_work_sync(&hctx->run_work);
 	} else {

index eac444804736..55139d2fca3e 100644
@@ -2294,6 +2294,8 @@ void blk_mq_release(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 
+	cancel_delayed_work_sync(&q->requeue_work);
+
 	/* hctx kobj stays in hctx */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx)

2.20.1

[ Upstream commit 338aa10750ba24d04beeaf5dc5efc032e5cf343f ]

Fix the warning produced by gpiochip_set_irq_hooks() by allocating a dedicated IRQ chip per GPIO chip/port.

---
 drivers/gpio/gpio-vf610.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

index 1309b444720e..3210fba16a9b 100644
@@ -37,6 +37,7 @@ struct fsl_gpio_soc_data {
 
 struct vf610_gpio_port {
 	struct gpio_chip gc;
+	struct irq_chip ic;
 	void __iomem *base;
 	void __iomem *gpio_base;
 	const struct fsl_gpio_soc_data *sdata;

@@ -66,8 +67,6 @@ struct vf610_gpio_port {
 #define PORT_INT_EITHER_EDGE	0xb
 #define PORT_INT_LOGIC_ONE	0xc
 
-static struct irq_chip vf610_gpio_irq_chip;
-
 static const struct fsl_gpio_soc_data imx_data = {
 	.have_paddr = true,
 };

@@ -243,15 +242,6 @@ static int vf610_gpio_irq_set_wake(struct irq_data *d, u32 enable)
 	return 0;
 }
 
-static struct irq_chip vf610_gpio_irq_chip = {
-	.name		= "gpio-vf610",
-	.irq_ack	= vf610_gpio_irq_ack,
-	.irq_mask	= vf610_gpio_irq_mask,
-	.irq_unmask	= vf610_gpio_irq_unmask,
-	.irq_set_type	= vf610_gpio_irq_set_type,
-	.irq_set_wake	= vf610_gpio_irq_set_wake,
-};
-
 static int vf610_gpio_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id = of_match_device(vf610_gpio_dt_ids,

@@ -261,6 +251,7 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 	struct vf610_gpio_port *port;
 	struct resource *iores;
 	struct gpio_chip *gc;
+	struct irq_chip *ic;
 	int i;
 	int ret;
 

@@ -297,6 +288,14 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 	gc->direction_output = vf610_gpio_direction_output;
 	gc->set = vf610_gpio_set;
 
+	ic = &port->ic;
+	ic->name = "gpio-vf610";
+	ic->irq_ack = vf610_gpio_irq_ack;
+	ic->irq_mask = vf610_gpio_irq_mask;
+	ic->irq_unmask = vf610_gpio_irq_unmask;
+	ic->irq_set_type = vf610_gpio_irq_set_type;
+	ic->irq_set_wake = vf610_gpio_irq_set_wake;
+
 	ret = gpiochip_add_data(gc, port);
 	if (ret < 0)
 		return ret;

@@ -308,14 +307,13 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 	/* Clear the interrupt status register for all GPIO's */
 	vf610_gpio_writel(~0, port->base + PORT_ISFR);
 
-	ret = gpiochip_irqchip_add(gc, &vf610_gpio_irq_chip, 0,
-				   handle_edge_irq, IRQ_TYPE_NONE);
+	ret = gpiochip_irqchip_add(gc, ic, 0, handle_edge_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(dev, "failed to add irqchip\n");
 		gpiochip_remove(gc);
 		return ret;
 	}
-	gpiochip_set_chained_irqchip(gc, &vf610_gpio_irq_chip, port->irq,
+	gpiochip_set_chained_irqchip(gc, ic, port->irq,
 				     vf610_gpio_irq_handler);
 
 	return 0;

2.20.1

[ Upstream commit 689a58605b63173acb0a8cf954af6a8f60440c93 ]

Memory: 509108K/542612K available (3835K kernel code, 919K rwdata, 1028K rodata, 129K init, 211K bss, 33504K reserved, 0K cma-reserved)
NR_IRQS: 15
clocksource: timer: mask: 0xffffffffffffffff max_cycles: 0x1cd42e205, max_idle_ns: 881590404426 ns

------------[ cut here ]------------
WARNING: CPU: 0 PID: 0 at kernel/time/clockevents.c:458 clockevents_register_device+0x72/0x140
posix-timer cpumask == cpu_all_mask, using cpu_possible_mask instead
Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc4-00048-ged79cc87302b #4
Stack:
 604ebda0 603c5370 604ebe20 6046fd17
 00000000 6006fcbb 604ebdb0 603c53b5
 604ebe10 6003bfc4 604ebdd0 9000001ca
Call Trace:
 [<6006fcbb>] ? printk+0x0/0x94
 [<60083160>] ? clockevents_register_device+0x72/0x140
 [<6001f16e>] show_stack+0x13b/0x155
 [<603c5370>] ? dump_stack_print_info+0xe2/0xeb
 [<6006fcbb>] ? printk+0x0/0x94
 [<603c53b5>] dump_stack+0x2a/0x2c
 [<6003bfc4>] __warn+0x10e/0x13e
 [<60070320>] ? vprintk_func+0xc8/0xcf
 [<60030fd6>] ? block_signals+0x0/0x16
 [<6006fcbb>] ? printk+0x0/0x94
 [<6003c08b>] warn_slowpath_fmt+0x97/0x99
 [<600311a1>] ? set_signals+0x0/0x3f
 [<6003bff4>] ? warn_slowpath_fmt+0x0/0x99
 [<600842cb>] ? tick_oneshot_mode_active+0x44/0x4f
 [<60030fd6>] ? block_signals+0x0/0x16
 [<6006fcbb>] ? printk+0x0/0x94
 [<6007d2d5>] ? __clocksource_select+0x20/0x1b1
 [<60030fd6>] ? block_signals+0x0/0x16
 [<6006fcbb>] ? printk+0x0/0x94
 [<60083160>] clockevents_register_device+0x72/0x140
 [<60031192>] ? get_signals+0x0/0xf
 [<60030fd6>] ? block_signals+0x0/0x16
 [<6006fcbb>] ? printk+0x0/0x94
 [<60002eec>] um_timer_setup+0xc8/0xca
 [<60001b59>] start_kernel+0x47f/0x57e
 [<600035bc>] start_kernel_proc+0x49/0x4d
 [<6006c483>] ? kmsg_dump_register+0x82/0x8a
 [<6001de62>] new_thread_handler+0x81/0xb2
 [<60003571>] ? kmsg_dumper_stdout_init+0x1a/0x1c
 [<60020c75>] uml_finishsetup+0x54/0x59

random: get_random_bytes called from init_oops_id+0x27/0x34 with crng_init=0

---[ end trace 00173d0117a88acb ]---

Calibrating delay loop... 6941.90 BogoMIPS (lpj=34709504)

---
 arch/um/kernel/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 7f69d17de354..9b21ae892009 100644
@@ -56,7 +56,7 @@ static int itimer_one_shot(struct clock_event_device *evt)
 static struct clock_event_device timer_clockevent = {
 	.name			= "posix-timer",
 	.rating			= 250,
-	.cpumask		= cpu_all_mask,
+	.cpumask		= cpu_possible_mask,
 	.features		= CLOCK_EVT_FEAT_PERIODIC |
 				  CLOCK_EVT_FEAT_ONESHOT,
 	.set_state_shutdown	= itimer_shutdown,

2.20.1




_______________________________________________
linux-um mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-um

[ Upstream commit 918bbde8085ae147a43dcb491953e0dd8f3e9d6a ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX5_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX5_CLK_AHB as "ahb" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx51.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 1ee1d542d9ad..29c965126817 100644
@@ -476,7 +476,7 @@
 				reg = <0x83fb0000 0x4000>;
 				interrupts = <6>;
 				clocks = <&clks IMX5_CLK_SDMA_GATE>,
-					 <&clks IMX5_CLK_SDMA_GATE>;
+					 <&clks IMX5_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx51.bin";

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit 2b8358a951b1e2a534a54924cd8245e58a1c5fb8 ]

The mpc85xx EDAC driver can be configured as a module but then fails to build because it uses two unexported symbols:

ERROR: ".pci_find_hose_for_OF_device" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
ERROR: ".early_find_capability" [drivers/edac/mpc85xx_edac_mod.ko] undefined!

We don't want to export those symbols just for this driver, so make the driver only configurable as a built-in.

This seems to have been broken since at least

c92132f59806 ("edac/85xx: Add PCIe error interrupt edac support")

(Nov 2013).

[ bp: make it depend on EDAC=y so that the EDAC core doesn't get built
as a module. ]

---
 drivers/edac/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 96afb2aeed18..aaaa8ce8d3fd 100644
@@ -246,8 +246,8 @@ config EDAC_PND2
 	  micro-server but may appear on others in the future.
 
 config EDAC_MPC85XX
-	tristate "Freescale MPC83xx / MPC85xx"
-	depends on FSL_SOC
+	bool "Freescale MPC83xx / MPC85xx"
+	depends on FSL_SOC && EDAC=y
 	help
 	  Support for error detection and correction on the Freescale
 	  MPC8349, MPC8560, MPC8540, MPC8548, T4240

2.20.1

[ Upstream commit b7b4fda2636296471e29b78c2aa9535d7bedb7a0 ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX5_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX5_CLK_AHB as "ahb" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx50.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 3747d80104f4..63e1d2fe2e19 100644
@@ -441,7 +441,7 @@
 				reg = <0x63fb0000 0x4000>;
 				interrupts = <6>;
 				clocks = <&clks IMX5_CLK_SDMA_GATE>,
-					 <&clks IMX5_CLK_SDMA_GATE>;
+					 <&clks IMX5_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx50.bin";
 			};

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit 28c168018e0902c67eb9c60d0fc4c8aa166c4efe ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX5_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX5_CLK_AHB as "ahb" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx53.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 2e516f4985e4..ddc3ce67c29a 100644
@@ -676,7 +676,7 @@
 				reg = <0x63fb0000 0x4000>;
 				interrupts = <6>;
 				clocks = <&clks IMX5_CLK_SDMA_GATE>,
-					 <&clks IMX5_CLK_SDMA_GATE>;
+					 <&clks IMX5_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx53.bin";

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit cc839d0f8c284fcb7591780b568f13415bbb737c ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX6SL_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX6SL_CLK_AHB as "ahb" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx6sl.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 3f76f980947e..bd9308b222ba 100644
@@ -718,7 +718,7 @@
 				reg = <0x020ec000 0x4000>;
 				interrupts = <0 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6SL_CLK_SDMA>,
-					 <&clks IMX6SL_CLK_SDMA>;
+					 <&clks IMX6SL_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				/* imx6sl reuses imx6q sdma firmware */

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit 412b032a1dc72fc9d1c258800355efa6671b6315 ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX7D_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX7D_CLK_IPG as "ipg" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx7s.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 82ad26e766eb..bf15efbe8a71 100644
@@ -997,8 +997,8 @@
 				compatible = "fsl,imx7d-sdma", "fsl,imx35-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_SDMA_CORE_CLK>,
-					 <&clks IMX7D_AHB_CHANNEL_ROOT_CLK>;
+				clocks = <&clks IMX7D_IPG_ROOT_CLK>,
+					 <&clks IMX7D_SDMA_CORE_CLK>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit 7b3132ecefdd1fcdf6b86e62021d0e55ea8034db ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX6UL_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX6UL_CLK_IPG as "ipg" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx6ul.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f11a241a340d..036aeba4f02c 100644
@@ -680,7 +680,7 @@
 					     "fsl,imx35-sdma";
 				reg = <0x020ec000 0x4000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX6UL_CLK_SDMA>,
+				clocks = <&clks IMX6UL_CLK_IPG>,
 					 <&clks IMX6UL_CLK_SDMA>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit 8979117765c19edc3b01cc0ef853537bf93eea4b ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX6SX_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality. Fix the code to specify IMX6SX_CLK_IPG as "ipg" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx6sx.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index d64438bfa68b..61ad4e296257 100644
@@ -766,7 +766,7 @@
 				compatible = "fsl,imx6sx-sdma", "fsl,imx6q-sdma";
 				reg = <0x020ec000 0x4000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX6SX_CLK_SDMA>,
+				clocks = <&clks IMX6SX_CLK_IPG>,
 					 <&clks IMX6SX_CLK_SDMA>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[ Upstream commit b14c872eebc501b9640b04f4a152df51d6eaf2fc ]

Since 25aaa75df1e6 SDMA driver uses clock rates of "ipg" and "ahb" clock to determine if it needs to configure the IP block as operating at 1:1 or 1:2 clock ratio (ACR bit in SDMAARM_CONFIG). Specifying both clocks as IMX6QDL_CLK_SDMA results in driver incorrectly thinking that ratio is 1:1 which results in broken SDMA funtionality(this at least breaks RAVE SP serdev driver on RDU2). Fix the code to specify IMX6QDL_CLK_IPG as "ipg" clock for SDMA, to avoid detecting incorrect clock ratio.

---
 arch/arm/boot/dts/imx6qdl.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 8884b4a3cafb..0fedb0c24eca 100644
@@ -909,7 +909,7 @@
 				compatible = "fsl,imx6q-sdma", "fsl,imx35-sdma";
 				reg = <0x020ec000 0x4000>;
 				interrupts = <0 2 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX6QDL_CLK_SDMA>,
+				clocks = <&clks IMX6QDL_CLK_IPG>,
 					 <&clks IMX6QDL_CLK_SDMA>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;

2.20.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[early feedback]

Building mips:nlm_xlp_defconfig ... failed (and other mips builds)
--------------
Error log:
/opt/buildbot/slave/stable-queue-4.14/build/arch/mips/kernel/prom.c: In function 'early_init_dt_add_memory_arch':
/opt/buildbot/slave/stable-queue-4.14/build/arch/mips/kernel/prom.c:44:14: error: 'PHYS_ADDR_MAX' undeclared

The problem affects v4.14.y and all earlier branches. PHYS_ADDR_MAX is indeed undeclared in those branches. It was introduced with commit 1c4bc43ddfd52 ("mm/memblock: introduce PHYS_ADDR_MAX").

Guenter

Thanks, I've dropped the mips patch that caused this. I'll also drop it from the 4.4 and 4.9 trees.

Sasha, I thought you had builders set up for stuff like this?

greg k-h

I have that scripting in place, and I usually check it once before I send the initial reviews and then once Greg does the -rc release.

--
Thanks,
Sasha

OK, good to hear. So this time must be some exceptional error.

thanks,

Takashi

Thanks!

BTW, do we have a systematic check whether the selected stable commit is reverted in a later commit? At least, you can track it as long as Fixes tag is properly set.

Takashi

Now dropped everywhere, and I added 7c32ae35fbf9 ("ALSA: seq: Cover unsubscribe_port() in list_mutex") everywhere instead.

thanks,

greg k-h

This commit is reverted later by commit f0654ba94e33. So please drop this. The proper fix is done later by commit 7c32ae35fbf9 ("ALSA: seq: Cover unsubscribe_port() in list_mutex")

Ditto for 4.19.y and 5.1.y.

thanks,

Takashi

[ Upstream commit a223770bfa7b6647f3a70983257bd89f9cafce46 ]

CONFIG_WATCHDOG_PRETIMEOUT_GOV build symbol adds watchdog_pretimeout.o object to watchdog.o, the latter is compiled only if CONFIG_WATCHDOG_CORE is selected, so it rightfully makes sense to add it as a dependency.

The change fixes the next compilation errors, if CONFIG_WATCHDOG_CORE=n and CONFIG_WATCHDOG_PRETIMEOUT_GOV=y are selected:

drivers/watchdog/pretimeout_noop.o: In function `watchdog_gov_noop_register':
drivers/watchdog/pretimeout_noop.c:35: undefined reference to watchdog_register_governor' drivers/watchdog/pretimeout_noop.o: In function watchdog_gov_noop_unregister':
drivers/watchdog/pretimeout_noop.c:40: undefined reference to `watchdog_unregister_governor'

drivers/watchdog/pretimeout_panic.o: In function `watchdog_gov_panic_register':
drivers/watchdog/pretimeout_panic.c:35: undefined reference to watchdog_register_governor' drivers/watchdog/pretimeout_panic.o: In function watchdog_gov_panic_unregister':
drivers/watchdog/pretimeout_panic.c:40: undefined reference to `watchdog_unregister_governor'

---
 drivers/watchdog/Kconfig | 1 +
 1 file changed, 1 insertion(+)

index ddd4a06b2ab8..a2ac08f7be9c 100644
@@ -1941,6 +1941,7 @@ comment "Watchdog Pretimeout Governors"
 
 config WATCHDOG_PRETIMEOUT_GOV
 	bool "Enable watchdog pretimeout governors"
+	depends on WATCHDOG_CORE
 	help
 	  The option allows to select watchdog pretimeout governors.
 

2.20.1

[ Upstream commit f0d14edd2ba43b995bef4dd5da5ffe0ae19321a1 ]

In case __get_free_pages() fails and returns NULL, fix the return value to -ENOMEM and release resources to avoid dereferencing a NULL pointer.

---
 drivers/pci/host/pcie-rcar.c | 4 ++++
 1 file changed, 4 insertions(+)

index 41edce16a07c..fad57d068db3 100644
@@ -888,6 +888,10 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie)
 
 	/* setup MSI data target */
 	msi->pages = __get_free_pages(GFP_KERNEL, 0);
+	if (!msi->pages) {
+		err = -ENOMEM;
+		goto err;
+	}
 	base = virt_to_phys((void *)msi->pages);
 
 	rcar_pci_write_reg(pcie, base | MSIFE, PCIEMSIALR);

2.20.1

[ Upstream commit 5ab99cf7d5e96e3b727c30e7a8524c976bd3723d ]

The PVDD_APIO_1V8 (LDO2) and PVDD_ABB_1V8 (LDO8) regulators were turned off by Linux kernel as unused. However they supply critical parts of SoC so they should be always on:

1. PVDD_APIO_1V8 supplies SYS pins (gpx[0-3], PSHOLD), HDMI level shift, RTC, VDD1_12 (DRAM internal 1.8 V logic), pull-up for PMIC interrupt lines, TTL/UARTR level shift, reset pins and SW-TACT1 button. It also supplies unused blocks like VDDQ_SRAM (for SROM controller) and VDDQ_GPIO (gpm7, gpy7).
The LDO2 cannot be turned off (S2MPS11 keeps it on anyway) so marking it "always-on" only reflects its real status.

2. PVDD_ABB_1V8 supplies Adaptive Body Bias Generator for ARM cores, memory and Mali (G3D).

---
 arch/arm/boot/dts/exynos5420-arndale-octa.dts | 2 ++
 1 file changed, 2 insertions(+)

index ee1bb9b8b366..38538211a967 100644
@@ -109,6 +109,7 @@
 				regulator-name = "PVDD_APIO_1V8";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
 			};
 
 			ldo3_reg: LDO3 {

@@ -147,6 +148,7 @@
 				regulator-name = "PVDD_ABB_1V8";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
 			};
 
 			ldo9_reg: LDO9 {

2.20.1

[ Upstream commit b00ef53053191d3025c15e8041699f8c9d132daf ]

It must be made sure that immediate mode is not already set, when modifying shadow register value in ehrpwm_pwm_disable(). Otherwise modifications to the action-qualifier continuous S/W force register(AQSFRC) will be done in the active register.
This may happen when both channels are being disabled. In this case, only the first channel state will be recorded as disabled in the shadow register. Later, when enabling the first channel again, the second channel would be enabled as well. Setting RLDCSF to zero, first, ensures that the shadow register is updated as desired.

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

index f7b8a86fa5c5..ad4a40c0f27c 100644
@@ -382,6 +382,8 @@ static void ehrpwm_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	}
 
 	/* Update shadow register first before modifying active register */
+	ehrpwm_modify(pc->mmio_base, AQSFRC, AQSFRC_RLDCSF_MASK,
+		      AQSFRC_RLDCSF_ZRO);
 	ehrpwm_modify(pc->mmio_base, AQCSFRC, aqcsfrc_mask, aqcsfrc_val);
 	/*
 	 * Changes to immediate action on Action Qualifier. This puts

2.20.1

[ Upstream commit 5ba846b1ee0792f5a596b9b0b86d6e8cdebfab06 ]

Intel IOMMU, when enabled, tries to find the domain of the device, assuming it's a PCI one, during DMA operations, such as mapping or unmapping. Since we are splitting the actual PCI device to couple of children via MFD framework (see drivers/mfd/intel-lpss.c for details), the DMA device appears to be a platform one, and thus not an actual one that performs DMA. In a such situation IOMMU can't find or allocate a proper domain for its operations. As a result, all DMA operations are failed.

In order to fix this, supply parent of the platform device to the DMA engine framework and fix filter functions accordingly.

We may rely on the fact that parent is a real PCI device, because no other configuration is present in the wild.

---
 drivers/dma/idma64.c              | 6 ++++--
 drivers/dma/idma64.h              | 2 ++
 drivers/spi/spi-pxa2xx.c          | 7 +------
 drivers/tty/serial/8250/8250_dw.c | 4 ++--
 4 files changed, 9 insertions(+), 10 deletions(-)

index 1953e57505f4..f17a4c7a1781 100644
@@ -589,7 +589,7 @@ static int idma64_probe(struct idma64_chip *chip)
 	idma64->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	idma64->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
-	idma64->dma.dev = chip->dev;
+	idma64->dma.dev = chip->sysdev;
 
 	dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK);
 

@@ -629,6 +629,7 @@ static int idma64_platform_probe(struct platform_device *pdev)
 {
 	struct idma64_chip *chip;
 	struct device *dev = &pdev->dev;
+	struct device *sysdev = dev->parent;
 	struct resource *mem;
 	int ret;
 

@@ -645,11 +646,12 @@ static int idma64_platform_probe(struct platform_device *pdev)
 	if (IS_ERR(chip->regs))
 		return PTR_ERR(chip->regs);
 
-	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	ret = dma_coerce_mask_and_coherent(sysdev, DMA_BIT_MASK(64));
 	if (ret)
 		return ret;
 
 	chip->dev = dev;
+	chip->sysdev = sysdev;
 
 	ret = idma64_probe(chip);
 	if (ret)

index 6b816878e5e7..baa32e1425de 100644
@@ -216,12 +216,14 @@ static inline void idma64_writel(struct idma64 *idma64, int offset, u32 value)
 /**
  * struct idma64_chip - representation of iDMA 64-bit controller hardware
  * @dev:		struct device of the DMA controller
+ * @sysdev:		struct device of the physical device that does DMA
  * @irq:		irq line
  * @regs:		memory mapped I/O space
  * @idma64:		struct idma64 that is filed by idma64_probe()
  */
 struct idma64_chip {
 	struct device	*dev;
+	struct device	*sysdev;
 	int		irq;
 	void __iomem	*regs;
 	struct idma64	*idma64;

index efdae686a761..9bf3e5f945c7 100644
@@ -1505,12 +1505,7 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 
 static bool pxa2xx_spi_idma_filter(struct dma_chan *chan, void *param)
 {
-	struct device *dev = param;
-
-	if (dev != chan->device->dev->parent)
-		return false;
-
-	return true;
+	return param == chan->device->dev;
 }
 
 static struct pxa2xx_spi_master *

index 27c5b2b46b8d..4ca46aa64699 100644
@@ -315,7 +315,7 @@ static bool dw8250_fallback_dma_filter(struct dma_chan *chan, void *param)
 
 static bool dw8250_idma_filter(struct dma_chan *chan, void *param)
 {
-	return param == chan->device->dev->parent;
+	return param == chan->device->dev;
 }
 
 static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data)

@@ -356,7 +356,7 @@ static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data)
 		}
 	}
 
-	/* Platforms with iDMA */
+	/* Platforms with iDMA 64-bit */
 	if (platform_get_resource_byname(to_platform_device(p->dev),
 					 IORESOURCE_MEM, "lpss_priv")) {
 		data->dma.rx_param = p->dev->parent;

2.20.1

[ Upstream commit 699ca30162686bf305cdf94861be02eb0cf9bda2 ]

If __get_free_pages() fails, return -ENOMEM to avoid a NULL pointer dereference.

---
 drivers/pci/host/pcie-xilinx.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

index 29f024f0ed7f..a8a44afa81ec 100644
@@ -338,14 +338,19 @@ static const struct irq_domain_ops msi_domain_ops = {
  * xilinx_pcie_enable_msi - Enable MSI support
  * @port: PCIe port information
  */
-static void xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
+static int xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
 {
 	phys_addr_t msg_addr;
 
 	port->msi_pages = __get_free_pages(GFP_KERNEL, 0);
+	if (!port->msi_pages)
+		return -ENOMEM;
+
 	msg_addr = virt_to_phys((void *)port->msi_pages);
 	pcie_write(port, 0x0, XILINX_PCIE_REG_MSIBASE1);
 	pcie_write(port, msg_addr, XILINX_PCIE_REG_MSIBASE2);
+
+	return 0;
 }
 
 /* INTx Functions */

@@ -500,6 +505,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 	struct device *dev = port->dev;
 	struct device_node *node = dev->of_node;
 	struct device_node *pcie_intc_node;
+	int ret;
 
 	/* Setup INTx */
 	pcie_intc_node = of_get_next_child(node, NULL);

@@ -528,7 +534,9 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 			return -ENODEV;
 		}
 
-		xilinx_pcie_enable_msi(port);
+		ret = xilinx_pcie_enable_msi(port);
+		if (ret)
+			return ret;
 	}
 
 	return 0;

2.20.1

[ Upstream commit da38ef3ed10a09248e13ae16530c2c6d448dc47d ]

We are currently assuming all GPIOs are non-wakeup capable GPIOs as we not configuring the bank->non_wakeup_gpios like we used to earlier with platform_data.

Let's add omap_gpio_is_off_wakeup_capable() to make the handling clearer while considering that later patches may want to configure SoC specific bank->non_wakeup_gpios for the GPIOs in wakeup domain.

---
 drivers/gpio/gpio-omap.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

index 148e81eea35a..83c6843db50c 100644
@@ -296,6 +296,22 @@ static void omap_clear_gpio_debounce(struct gpio_bank *bank, unsigned offset)
 	}
 }
 
+/*
+ * Off mode wake-up capable GPIOs in bank(s) that are in the wakeup domain.
+ * See TRM section for GPIO for "Wake-Up Generation" for the list of GPIOs
+ * in wakeup domain. If bank->non_wakeup_gpios is not configured, assume none
+ * are capable waking up the system from off mode.
+ */
+static bool omap_gpio_is_off_wakeup_capable(struct gpio_bank *bank, u32 gpio_mask)
+{
+	u32 no_wake = bank->non_wakeup_gpios;
+
+	if (no_wake)
+		return !!(~no_wake & gpio_mask);
+
+	return false;
+}
+
 static inline void omap_set_gpio_trigger(struct gpio_bank *bank, int gpio,
 						unsigned trigger)
 {

@@ -327,13 +343,7 @@ static inline void omap_set_gpio_trigger(struct gpio_bank *bank, int gpio,
 	}
 
 	/* This part needs to be executed always for OMAP{34xx, 44xx} */
-	if (!bank->regs->irqctrl) {
-		/* On omap24xx proceed only when valid GPIO bit is set */
-		if (bank->non_wakeup_gpios) {
-			if (!(bank->non_wakeup_gpios & gpio_bit))
-				goto exit;
-		}
-
+	if (!bank->regs->irqctrl && !omap_gpio_is_off_wakeup_capable(bank, gpio)) {
 		/*
 		 * Log the edge gpio and manually trigger the IRQ
 		 * after resume if the input level changes

@@ -346,7 +356,6 @@ static inline void omap_set_gpio_trigger(struct gpio_bank *bank, int gpio,
 			bank->enabled_non_wakeup_gpios &= ~gpio_bit;
 	}
 
-exit:
 	bank->level_mask =
 		readl_relaxed(bank->base + bank->regs->leveldetect0) |
 		readl_relaxed(bank->base + bank->regs->leveldetect1);

2.20.1

[ Upstream commit 1d84353d205a953e2381044953b7fa31c8c9702d ]

In case ioremap fails, the fix releases resources and returns -ENOMEM to avoid NULL pointer dereferences.

---
 drivers/video/fbdev/imsttfb.c | 5 +++++
 1 file changed, 5 insertions(+)

index ecdcf358ad5e..ffcf553719a3 100644
@@ -1516,6 +1516,11 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	info->fix.smem_start = addr;
 	info->screen_base = (__u8 *)ioremap(addr, par->ramdac == IBM ?
 					    0x400000 : 0x800000);
+	if (!info->screen_base) {
+		release_mem_region(addr, size);
+		framebuffer_release(info);
+		return -ENOMEM;
+	}
 	info->fix.mmio_start = addr + 0x800000;
 	par->dc_regs = ioremap(addr + 0x800000, 0x1000);
 	par->cmap_regs_phys = addr + 0x840000;

2.20.1

[ Upstream commit 778c02a236a8728bb992de10ed1f12c0be5b7b0e ]

If a sync bfq_queue has a higher weight than some other queue, and remains temporarily empty while in service, then, to preserve the bandwidth share of the queue, it is necessary to plug I/O dispatching until a new request arrives for the queue. In addition, a timeout needs to be set, to avoid waiting for ever if the process associated with the queue has actually finished its I/O.

Even with the above timeout, the device is however not fed with new I/O for a while, if the process has finished its I/O. If this happens often, then throughput drops and latencies grow. For this reason, the timeout is kept rather low: 8 ms is the current default.

Unfortunately, such a low value may cause, on the opposite end, a violation of bandwidth guarantees for a process that happens to issue new I/O too late. The higher the system load, the higher the probability that this happens to some process. This is a problem in scenarios where service guarantees matter more than throughput. One important case are weight-raised queues, which need to be granted a very high fraction of the bandwidth.

To address this issue, this commit lower-bounds the plugging timeout for weight-raised queues to 20 ms. This simple change provides relevant benefits. For example, on a PLEXTOR PX-256M5S, with which gnome-terminal starts in 0.6 seconds if there is no other I/O in progress, the same applications starts in
- 0.8 seconds, instead of 1.2 seconds, if ten files are being read sequentially in parallel
- 1 second, instead of 2 seconds, if, in parallel, five files are being read sequentially, and five more files are being written sequentially

---
 block/bfq-iosched.c | 2 ++
 1 file changed, 2 insertions(+)

index 3b44bd28fc45..7d45ac451745 100644
@@ -2282,6 +2282,8 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
 	    bfq_symmetric_scenario(bfqd))
 		sl = min_t(u64, sl, BFQ_MIN_TT);
+	else if (bfqq->wr_coeff > 1)
+		sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
 
 	bfqd->last_idling_start = ktime_get();
 	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),

2.20.1

[ Upstream commit ec7f6aad57ad29e4e66cc2e18e1e1599ddb02542 ]

When ioremap fails, hga_vram should not be dereferenced. The fix check the failure to avoid NULL pointer dereference.

---
 drivers/video/fbdev/hgafb.c | 2 ++
 1 file changed, 2 insertions(+)

index 463028543173..59e1cae57948 100644
@@ -285,6 +285,8 @@ static int hga_card_detect(void)
 	hga_vram_len  = 0x08000;
 
 	hga_vram = ioremap(0xb0000, hga_vram_len);
+	if (!hga_vram)
+		goto error;
 
 	if (request_region(0x3b0, 12, "hgafb"))
 		release_io_ports = 1;

2.20.1

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 2fa7a155b25160696cd77cdd995536cf5e172e20 which is commit d5bb334a8e171b262e48f378bd2096c0ea458265 upstream.

Lots of people have reported issues with this patch, and as there does not seem to be a fix going into Linus's kernel tree any time soon, revert the commit in the stable trees so as to get people's machines working properly again.

---
 include/net/bluetooth/hci_core.h |    3 ---
 net/bluetooth/hci_conn.c         |    8 --------
 2 files changed, 11 deletions(-)

@@ -178,9 +178,6 @@ struct adv_info {
 
 #define HCI_MAX_SHORT_NAME_LENGTH	10
 
-/* Min encryption key size to match with SMP */
-#define HCI_MIN_ENC_KEY_SIZE		7
-
 /* Default LE RPA expiry time, 15 minutes */
 #define HCI_DEFAULT_RPA_TIMEOUT		(15 * 60)
 

@@ -1165,14 +1165,6 @@ int hci_conn_check_link_mode(struct hci_
 	    !test_bit(HCI_CONN_ENCRYPT, &conn->flags))
 		return 0;
 
-	/* The minimum encryption key size needs to be enforced by the
-	 * host stack before establishing any L2CAP connections. The
-	 * specification in theory allows a minimum of 1, but to align
-	 * BR/EDR and LE transports, a minimum of 7 is chosen.
-	 */
-	if (conn->enc_key_size < HCI_MIN_ENC_KEY_SIZE)
-		return 0;
-
 	return 1;
 }
 

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 140ae656e3b7476719a2b15b96527c73c5acf90b which is commit b30a43ac7132cdda833ac4b13dd1ebd35ace14b7 upstream.

Sven reports:
Commit 1e07d63749 ("drm/nouveau: add kconfig option to turn off nouveau legacy contexts. (v3)") has caused a build failure for me when I actually tried that option (CONFIG_NOUVEAU_LEGACY_CTX_SUPPORT=n):

,----
| Kernel: arch/x86/boot/bzImage is ready (#1)
| Building modules, stage 2.
| MODPOST 290 modules
| ERROR: "drm_legacy_mmap" [drivers/gpu/drm/nouveau/nouveau.ko] undefined! | scripts/Makefile.modpost:91: recipe for target '__modpost' failed `----

Upstream does not have that problem, as commit bed2dd8421 ("drm/ttm:
Quick-test mmap offset in ttm_bo_mmap()") has removed the use of drm_legacy_mmap from nouveau_ttm.c. Unfortunately that commit does not apply in 5.1.9.

The ensuing discussion proposed a number of one-off patches, but no solid agreement was made, so just revert the commit for now to get people's systems building again.

---
 drivers/gpu/drm/nouveau/Kconfig       |   13 +------------
 drivers/gpu/drm/nouveau/nouveau_drm.c |    7 ++-----
 2 files changed, 3 insertions(+), 17 deletions(-)

@@ -16,20 +16,9 @@ config DRM_NOUVEAU
 	select INPUT if ACPI && X86
 	select THERMAL if ACPI && X86
 	select ACPI_VIDEO if ACPI && X86
-	help
-	  Choose this option for open-source NVIDIA support.
-
-config NOUVEAU_LEGACY_CTX_SUPPORT
-	bool "Nouveau legacy context support"
-	depends on DRM_NOUVEAU
 	select DRM_VM
-	default y
 	help
-	  There was a version of the nouveau DDX that relied on legacy
-	  ctx ioctls not erroring out. But that was back in time a long
-	  ways, so offer a way to disable it now. For uapi compat with
-	  old nouveau ddx this should be on by default, but modern distros
-	  should consider turning it off.
+	  Choose this option for open-source NVIDIA support.
 
 config NOUVEAU_PLATFORM_DRIVER
 	bool "Nouveau (NVIDIA) SoC GPUs"

@@ -967,11 +967,8 @@ nouveau_driver_fops = {
 static struct drm_driver
 driver_stub = {
 	.driver_features =
-		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_RENDER
-#if defined(CONFIG_NOUVEAU_LEGACY_CTX_SUPPORT)
-		| DRIVER_KMS_LEGACY_CONTEXT
-#endif
-		,
+		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_RENDER |
+		DRIVER_KMS_LEGACY_CONTEXT,
 
 	.load = nouveau_drm_load,
 	.unload = nouveau_drm_unload,

From: Helen Koike <[email protected]>

commit 89a4aac0ab0e6f5eea10d7bf4869dd15c3de2cd4 upstream.

In the case of a normal sync update, the preparation of framebuffers (be it calling drm_atomic_helper_prepare_planes() or doing setups with drm_framebuffer_get()) are performed in the new_state and the respective cleanups are performed in the old_state.

In the case of async updates, the preparation is also done in the new_state but the cleanups are done in the new_state (because updates are performed in place, i.e. in the current state).

The current code blocks async udpates when the fb is changed, turning async updates into sync updates, slowing down cursor updates and introducing regressions in igt tests with errors of type:

"CRITICAL: completed 97 cursor updated in a period of 30 flips, we expect to complete approximately 15360 updates, with the threshold set at 7680"

Fb changes in async updates were prevented to avoid the following scenario:

- Async update, oldfb = NULL, newfb = fb1, prepare fb1, cleanup fb1
- Async update, oldfb = fb1, newfb = fb2, prepare fb2, cleanup fb2
- Non-async commit, oldfb = fb2, newfb = fb1, prepare fb1, cleanup fb2 (wrong) Where we have a single call to prepare fb2 but double cleanup call to fb2.

To solve the above problems, instead of blocking async fb changes, we place the old framebuffer in the new_state object, so when the code performs cleanups in the new_state it will cleanup the old_fb and we will have the following scenario instead:

- Async update, oldfb = NULL, newfb = fb1, prepare fb1, no cleanup
- Async update, oldfb = fb1, newfb = fb2, prepare fb2, cleanup fb1
- Non-async commit, oldfb = fb2, newfb = fb1, prepare fb1, cleanup fb2

Where calls to prepare/cleanup are balanced.

---
 drivers/gpu/drm/drm_atomic_helper.c      |   10 ++++++++++
 include/drm/drm_modeset_helper_vtables.h |    8 ++++++++
 2 files changed, 18 insertions(+)

@@ -1462,6 +1462,8 @@ EXPORT_SYMBOL(drm_atomic_helper_async_ch
  * drm_atomic_async_check() succeeds. Async commits are not supposed to swap
  * the states like normal sync commits, but just do in-place changes on the
  * current state.
+ *
+ * TODO: Implement full swap instead of doing in-place changes.
  */
 void drm_atomic_helper_async_commit(struct drm_device *dev,
 				    struct drm_atomic_state *state)

@@ -1472,8 +1474,16 @@ void drm_atomic_helper_async_commit(stru
 	int i;
 
 	for_each_new_plane_in_state(state, plane, plane_state, i) {
+		struct drm_framebuffer *old_fb = plane->state->fb;
+
 		funcs = plane->helper_private;
 		funcs->atomic_async_update(plane, plane_state);
+
+		/*
+		 * Make sure the FBs have been swapped so that cleanups in the
+		 * new_state performs a cleanup in the old FB.
+		 */
+		WARN_ON_ONCE(plane_state->fb != old_fb);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_async_commit);

@@ -1159,6 +1159,14 @@ struct drm_plane_helper_funcs {
 	 * current one with the new plane configurations in the new
 	 * plane_state.
 	 *
+	 * Drivers should also swap the framebuffers between current plane
+	 * state (&drm_plane.state) and new_state.
+	 * This is required since cleanup for async commits is performed on
+	 * the new state, rather than old state like for traditional commits.
+	 * Since we want to give up the reference on the current (old) fb
+	 * instead of our brand new one, swap them in the driver during the
+	 * async commit.
+	 *
 	 * FIXME:
 	 *  - It only works for single plane updates
 	 *  - Async Pageflips are not supported yet

[ Upstream commit 347ab9480313737c0f1aaa08e8f2e1a791235535 ]

This patch fixes deadlock warning if removing PWM device when CONFIG_PROVE_LOCKING is enabled.

This issue can be reproceduced by the following steps on the R-Car H3 Salvator-X board if the backlight is disabled:

 # cd /sys/class/pwm/pwmchip0
 # echo 0 > export
 # ls
 device  export  npwm  power  pwm0  subsystem  uevent  unexport
 # cd device/driver
 # ls
 bind  e6e31000.pwm  uevent  unbind
 # echo e6e31000.pwm > unbind

[   87.659974] ======================================================
[   87.666149] WARNING: possible circular locking dependency detected
[   87.672327] 5.0.0 #7 Not tainted
[   87.675549] ------------------------------------------------------
[   87.681723] bash/2986 is trying to acquire lock:
[   87.686337] 000000005ea0e178 (kn->count#58){++++}, at: kernfs_remove_by_name_ns+0x50/0xa0
[   87.694528]
[   87.694528] but task is already holding lock:
[   87.700353] 000000006313b17c (pwm_lock){+.+.}, at: pwmchip_remove+0x28/0x13c
[   87.707405]
[   87.707405] which lock already depends on the new lock.
[   87.707405]
[   87.715574]
[   87.715574] the existing dependency chain (in reverse order) is:
[   87.723048]
[   87.723048] -> #1 (pwm_lock){+.+.}:
[   87.728017]        __mutex_lock+0x70/0x7e4
[   87.732108]        mutex_lock_nested+0x1c/0x24
[   87.736547]        pwm_request_from_chip.part.6+0x34/0x74
[   87.741940]        pwm_request_from_chip+0x20/0x40
[   87.746725]        export_store+0x6c/0x1f4
[   87.750820]        dev_attr_store+0x18/0x28
[   87.754998]        sysfs_kf_write+0x54/0x64
[   87.759175]        kernfs_fop_write+0xe4/0x1e8
[   87.763615]        __vfs_write+0x40/0x184
[   87.767619]        vfs_write+0xa8/0x19c
[   87.771448]        ksys_write+0x58/0xbc
[   87.775278]        __arm64_sys_write+0x18/0x20
[   87.779721]        el0_svc_common+0xd0/0x124
[   87.783986]        el0_svc_compat_handler+0x1c/0x24
[   87.788858]        el0_svc_compat+0x8/0x18
[   87.792947]
[   87.792947] -> #0 (kn->count#58){++++}:
[   87.798260]        lock_acquire+0xc4/0x22c
[   87.802353]        __kernfs_remove+0x258/0x2c4
[   87.806790]        kernfs_remove_by_name_ns+0x50/0xa0
[   87.811836]        remove_files.isra.1+0x38/0x78
[   87.816447]        sysfs_remove_group+0x48/0x98
[   87.820971]        sysfs_remove_groups+0x34/0x4c
[   87.825583]        device_remove_attrs+0x6c/0x7c
[   87.830197]        device_del+0x11c/0x33c
[   87.834201]        device_unregister+0x14/0x2c
[   87.838638]        pwmchip_sysfs_unexport+0x40/0x4c
[   87.843509]        pwmchip_remove+0xf4/0x13c
[   87.847773]        rcar_pwm_remove+0x28/0x34
[   87.852039]        platform_drv_remove+0x24/0x64
[   87.856651]        device_release_driver_internal+0x18c/0x21c
[   87.862391]        device_release_driver+0x14/0x1c
[   87.867175]        unbind_store+0xe0/0x124
[   87.871265]        drv_attr_store+0x20/0x30
[   87.875442]        sysfs_kf_write+0x54/0x64
[   87.879618]        kernfs_fop_write+0xe4/0x1e8
[   87.884055]        __vfs_write+0x40/0x184
[   87.888057]        vfs_write+0xa8/0x19c
[   87.891887]        ksys_write+0x58/0xbc
[   87.895716]        __arm64_sys_write+0x18/0x20
[   87.900154]        el0_svc_common+0xd0/0x124
[   87.904417]        el0_svc_compat_handler+0x1c/0x24
[   87.909289]        el0_svc_compat+0x8/0x18
[   87.913378]
[   87.913378] other info that might help us debug this:
[   87.913378]
[   87.921374]  Possible unsafe locking scenario:
[   87.921374]
[   87.927286]        CPU0                    CPU1
[   87.931808]        ----                    ----
[   87.936331]   lock(pwm_lock);
[   87.939293]                                lock(kn->count#58);
[   87.945120]                                lock(pwm_lock);
[   87.950599]   lock(kn->count#58);
[   87.953908]
[   87.953908]  *** DEADLOCK ***
[   87.953908]
[   87.959821] 4 locks held by bash/2986:
[   87.963563]  #0: 00000000ace7bc30 (sb_writers#6){.+.+}, at: vfs_write+0x188/0x19c
[   87.971044]  #1: 00000000287991b2 (&of->mutex){+.+.}, at: kernfs_fop_write+0xb4/0x1e8
[   87.978872]  #2: 00000000f739d016 (&dev->mutex){....}, at: device_release_driver_internal+0x40/0x21c
[   87.988001]  #3: 000000006313b17c (pwm_lock){+.+.}, at: pwmchip_remove+0x28/0x13c
[   87.995481]
[   87.995481] stack backtrace:
[   87.999836] CPU: 0 PID: 2986 Comm: bash Not tainted 5.0.0 #7
[   88.005489] Hardware name: Renesas Salvator-X board based on r8a7795 ES1.x (DT)
[   88.012791] Call trace:
[   88.015235]  dump_backtrace+0x0/0x190
[   88.018891]  show_stack+0x14/0x1c
[   88.022204]  dump_stack+0xb0/0xec
[   88.025514]  print_circular_bug.isra.32+0x1d0/0x2e0
[   88.030385]  __lock_acquire+0x1318/0x1864
[   88.034388]  lock_acquire+0xc4/0x22c
[   88.037958]  __kernfs_remove+0x258/0x2c4
[   88.041874]  kernfs_remove_by_name_ns+0x50/0xa0
[   88.046398]  remove_files.isra.1+0x38/0x78
[   88.050487]  sysfs_remove_group+0x48/0x98
[   88.054490]  sysfs_remove_groups+0x34/0x4c
[   88.058580]  device_remove_attrs+0x6c/0x7c
[   88.062671]  device_del+0x11c/0x33c
[   88.066154]  device_unregister+0x14/0x2c
[   88.070070]  pwmchip_sysfs_unexport+0x40/0x4c
[   88.074421]  pwmchip_remove+0xf4/0x13c
[   88.078163]  rcar_pwm_remove+0x28/0x34
[   88.081906]  platform_drv_remove+0x24/0x64
[   88.085996]  device_release_driver_internal+0x18c/0x21c
[   88.091215]  device_release_driver+0x14/0x1c
[   88.095478]  unbind_store+0xe0/0x124
[   88.099048]  drv_attr_store+0x20/0x30
[   88.102704]  sysfs_kf_write+0x54/0x64
[   88.106359]  kernfs_fop_write+0xe4/0x1e8
[   88.110275]  __vfs_write+0x40/0x184
[   88.113757]  vfs_write+0xa8/0x19c
[   88.117065]  ksys_write+0x58/0xbc
[   88.120374]  __arm64_sys_write+0x18/0x20
[   88.124291]  el0_svc_common+0xd0/0x124
[   88.128034]  el0_svc_compat_handler+0x1c/0x24
[   88.132384]  el0_svc_compat+0x8/0x18

The sysfs unexport in pwmchip_remove() is completely asymmetric to what we do in pwmchip_add_with_polarity() and commit 0733424c9ba9 ("pwm: Unexport children before chip removal") is a strong indication that this was wrong to begin with. We should just move pwmchip_sysfs_unexport() where it belongs, which is right after pwmchip_sysfs_unexport_children(). In that case, we do not need separate functions anymore either.

We also really want to remove sysfs irrespective of whether or not the chip will be removed as a result of pwmchip_remove(). We can only assume that the driver will be gone after that, so we shouldn't leave any dangling sysfs files around.

This warning disappears if we move pwmchip_sysfs_unexport() to the top of pwmchip_remove(), pwmchip_sysfs_unexport_children(). That way it is also outside of the pwm_lock section, which indeed doesn't seem to be needed.

Moving the pwmchip_sysfs_export() call outside of that section also seems fine and it'd be perfectly symmetric with pwmchip_remove() again.

So, this patch fixes them.

---
 drivers/pwm/core.c  | 10 +++++-----
 drivers/pwm/sysfs.c | 14 +-------------
 include/linux/pwm.h |  5 -----
 3 files changed, 6 insertions(+), 23 deletions(-)

index 1581f6ab1b1f..c45e5719ba17 100644
@@ -311,10 +311,12 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
 	if (IS_ENABLED(CONFIG_OF))
 		of_pwmchip_add(chip);
 
-	pwmchip_sysfs_export(chip);
-
 out:
 	mutex_unlock(&pwm_lock);
+
+	if (!ret)
+		pwmchip_sysfs_export(chip);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pwmchip_add_with_polarity);

@@ -348,7 +350,7 @@ int pwmchip_remove(struct pwm_chip *chip)
 	unsigned int i;
 	int ret = 0;
 
-	pwmchip_sysfs_unexport_children(chip);
+	pwmchip_sysfs_unexport(chip);
 
 	mutex_lock(&pwm_lock);
 

@@ -368,8 +370,6 @@ int pwmchip_remove(struct pwm_chip *chip)
 
 	free_pwms(chip);
 
-	pwmchip_sysfs_unexport(chip);
-
 out:
 	mutex_unlock(&pwm_lock);
 	return ret;

index a813239300c3..0850b11dfd83 100644
@@ -397,19 +397,6 @@ void pwmchip_sysfs_export(struct pwm_chip *chip)
 }
 
 void pwmchip_sysfs_unexport(struct pwm_chip *chip)
-{
-	struct device *parent;
-
-	parent = class_find_device(&pwm_class, NULL, chip,
-				   pwmchip_sysfs_match);
-	if (parent) {
-		/* for class_find_device() */
-		put_device(parent);
-		device_unregister(parent);
-	}
-}
-
-void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
 {
 	struct device *parent;
 	unsigned int i;

@@ -427,6 +414,7 @@ void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
 	}
 
 	put_device(parent);
+	device_unregister(parent);
 }
 
 static int __init pwm_sysfs_init(void)

index 56518adc31dd..bd7d611d63e9 100644
@@ -639,7 +639,6 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num)
 #ifdef CONFIG_PWM_SYSFS
 void pwmchip_sysfs_export(struct pwm_chip *chip);
 void pwmchip_sysfs_unexport(struct pwm_chip *chip);
-void pwmchip_sysfs_unexport_children(struct pwm_chip *chip);
 #else
 static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
 {

@@ -648,10 +647,6 @@ static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
 static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip)
 {
 }
-
-static inline void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
-{
-}
 #endif /* CONFIG_PWM_SYSFS */
 
 #endif /* __LINUX_PWM_H */

2.20.1

[ Upstream commit 954b4b752a4c4e963b017ed8cef4c453c5ed308d ]

The MSI message address in the RC address space can be 64 bit. The R-Car PCIe RC supports such a 64bit MSI message address as well. The code currently uses virt_to_phys(__get_free_pages()) to obtain a reserved page for the MSI message address, and the return value of which can be a 64 bit physical address on 64 bit system.

However, the driver only programs PCIEMSIALR register with the bottom 32 bits of the virt_to_phys(__get_free_pages()) return value and does not program the top 32 bits into PCIEMSIAUR, but rather programs the PCIEMSIAUR register with 0x0. This worked fine on older 32 bit R-Car SoCs, however may fail on new 64 bit R-Car SoCs.

Since from a PCIe controller perspective, an inbound MSI is a memory write to a special address (in case of this controller, defined by the value in PCIEMSIAUR:PCIEMSIALR), which triggers an interrupt, but never hits the DRAM _and_ because allocation of an MSI by a PCIe card driver obtains the MSI message address by reading PCIEMSIAUR:PCIEMSIALR in rcar_msi_setup_irqs(), incorrectly programmed PCIEMSIAUR cannot cause memory corruption or other issues.

There is however the possibility that if virt_to_phys(__get_free_pages()) returned address above the 32bit boundary _and_ PCIEMSIAUR was programmed to 0x0 _and_ if the system had physical RAM at the address matching the value of PCIEMSIALR, a PCIe card driver could allocate a buffer with a physical address matching the value of PCIEMSIALR and a remote write to such a buffer by a PCIe card would trigger a spurious MSI.

---
 drivers/pci/host/pcie-rcar.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index fad57d068db3..2b0a1f3b8265 100644
@@ -849,7 +849,7 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
 	struct rcar_msi *msi = &pcie->msi;
-	unsigned long base;
+	phys_addr_t base;
 	int err, i;
 
 	mutex_init(&msi->lock);

@@ -894,8 +894,8 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie)
 	}
 	base = virt_to_phys((void *)msi->pages);
 
-	rcar_pci_write_reg(pcie, base | MSIFE, PCIEMSIALR);
-	rcar_pci_write_reg(pcie, 0, PCIEMSIAUR);
+	rcar_pci_write_reg(pcie, lower_32_bits(base) | MSIFE, PCIEMSIALR);
+	rcar_pci_write_reg(pcie, upper_32_bits(base), PCIEMSIAUR);
 
 	/* enable all MSI interrupts */
 	rcar_pci_write_reg(pcie, 0xffffffff, PCIEMSIIER);

2.20.1

[ Upstream commit 32a155b1a83d6659e2272e8e1eec199667b1897e ]

The datasheet says the vconn MUST be off when we start toggling. The tcpm.c state-machine is responsible to make sure vconn is off, but lets add a WARN to catch any cases where vconn is not off for some reason.

---
 drivers/staging/typec/fusb302/fusb302.c | 2 ++
 1 file changed, 2 insertions(+)

index 7d9f25db1add..794dbc34973f 100644
@@ -671,6 +671,8 @@ static int fusb302_set_toggling(struct fusb302_chip *chip,
 			return ret;
 		chip->intr_togdone = false;
 	} else {
+		/* Datasheet says vconn MUST be off when toggling */
+		WARN(chip->vconn_on, "Vconn is on during toggle start");
 		/* unmask TOGDONE interrupt */
 		ret = fusb302_i2c_clear_bits(chip, FUSB_REG_MASKA,
 					     FUSB_REG_MASKA_TOGDONE);

2.20.1

[ Upstream commit 4d8e3e951a856777720272ce27f2c738a3eeef8c ]

During early system resume on Exynos5422 with performance counters enabled the following kernel oops happens:

    Internal error: Oops - undefined instruction: 0 [#1] PREEMPT SMP ARM
    Modules linked in:
    CPU: 0 PID: 1433 Comm: bash Tainted: G        W         5.0.0-rc5-next-20190208-00023-gd5fb5a8a13e6-dirty #5480
    Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
    ...
    Flags: nZCv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment none
    Control: 10c5387d  Table: 4451006a  DAC: 00000051
    Process bash (pid: 1433, stack limit = 0xb7e0e22f)
    ...
    (reset_ctrl_regs) from [<c0112ad0>] (dbg_cpu_pm_notify+0x1c/0x24)
    (dbg_cpu_pm_notify) from [<c014c840>] (notifier_call_chain+0x44/0x84)
    (notifier_call_chain) from [<c014cbc0>] (__atomic_notifier_call_chain+0x7c/0x128)
    (__atomic_notifier_call_chain) from [<c01ffaac>] (cpu_pm_notify+0x30/0x54)
    (cpu_pm_notify) from [<c055116c>] (syscore_resume+0x98/0x3f4)
    (syscore_resume) from [<c0189350>] (suspend_devices_and_enter+0x97c/0xe74)
    (suspend_devices_and_enter) from [<c0189fb8>] (pm_suspend+0x770/0xc04)
    (pm_suspend) from [<c0187740>] (state_store+0x6c/0xcc)
    (state_store) from [<c09fa698>] (kobj_attr_store+0x14/0x20)
    (kobj_attr_store) from [<c030159c>] (sysfs_kf_write+0x4c/0x50)
    (sysfs_kf_write) from [<c0300620>] (kernfs_fop_write+0xfc/0x1e0)
    (kernfs_fop_write) from [<c0282be8>] (__vfs_write+0x2c/0x160)
    (__vfs_write) from [<c0282ea4>] (vfs_write+0xa4/0x16c)
    (vfs_write) from [<c0283080>] (ksys_write+0x40/0x8c)
    (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28)

Undefined instruction is triggered during CP14 reset, because bits: #16 (Secure privileged invasive debug disabled) and #17 (Secure privileged noninvasive debug disable) are set in DSCR. Those bits depend on SPNIDEN and SPIDEN lines, which are provided by Secure JTAG hardware block. That block in turn is powered from cluster 0 (big/Eagle), but the Exynos5422 boots on cluster 1 (LITTLE/KFC).

To fix this issue it is enough to turn on the power on the cluster 0 for a while. This lets the Secure JTAG block to propagate the needed signals to LITTLE/KFC cores and change their DSCR.

---
 arch/arm/mach-exynos/suspend.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

index 9be92073f847..1c17d991bcde 100644
@@ -441,8 +441,27 @@ early_wakeup:
 
 static void exynos5420_prepare_pm_resume(void)
 {
+	unsigned int mpidr, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
 	if (IS_ENABLED(CONFIG_EXYNOS5420_MCPM))
 		WARN_ON(mcpm_cpu_powered_up());
+
+	if (IS_ENABLED(CONFIG_HW_PERF_EVENTS) && cluster != 0) {
+		/*
+		 * When system is resumed on the LITTLE/KFC core (cluster 1),
+		 * the DSCR is not properly updated until the power is turned
+		 * on also for the cluster 0. Enable it for a while to
+		 * propagate the SPNIDEN and SPIDEN signals from Secure JTAG
+		 * block and avoid undefined instruction issue on CP14 reset.
+		 */
+		pmu_raw_writel(S5P_CORE_LOCAL_PWR_EN,
+				EXYNOS_COMMON_CONFIGURATION(0));
+		pmu_raw_writel(0,
+				EXYNOS_COMMON_CONFIGURATION(0));
+	}
 }
 
 static void exynos5420_pm_resume(void)

2.20.1

[ Upstream commit 8c43004af01635cc9fbb11031d070e5e0d327ef2 ]

pcpu_find_block_fit() guarantees that a fit is found within PCPU_BITMAP_BLOCK_BITS. Iteration is used to determine the first fit as it compares against the block's contig_hint. This can lead to incorrectly scanning past the end of the bitmap. The behavior was okay given the check after for bit_off >= end and the correctness of the hints from pcpu_find_block_fit().

This patch fixes this by bounding the end offset by the number of bits in a chunk.

---
 mm/percpu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index bc58bcbe4b60..9beb84800d8d 100644
@@ -984,7 +984,8 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
 	/*
 	 * Search to find a fit.
 	 */
-	end = start + alloc_bits + PCPU_BITMAP_BLOCK_BITS;
+	end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS,
+		    pcpu_chunk_map_bits(chunk));
 	bit_off = bitmap_find_next_zero_area(chunk->alloc_map, end, start,
 					     alloc_bits, align_mask);
 	if (bit_off >= end)

2.20.1

[ Upstream commit 41be3e2618174fdf3361e49e64f2bf530f40c6b0 ]

vfio_dev_present() which is the condition to wait_event_interruptible_timeout(), will call vfio_group_get_device and try to acquire the mutex group->device_lock.

wait_event_interruptible_timeout() will set the state of the current task to TASK_INTERRUPTIBLE, before doing the condition check. This means that we will try to acquire the mutex while already in a sleeping state. The scheduler warns us by giving the following warning:

[ 4050.264464] ------------[ cut here ]------------
[ 4050.264508] do not call blocking ops when !TASK_RUNNING; state=1 set at [<00000000b33c00e2>] prepare_to_wait_event+0x14a/0x188
[ 4050.264529] WARNING: CPU: 12 PID: 35924 at kernel/sched/core.c:6112 __might_sleep+0x76/0x90

....

4050.264756] Call Trace:

[ 4050.264765] ([<000000000017bbaa>] __might_sleep+0x72/0x90)
[ 4050.264774]  [<0000000000b97edc>] __mutex_lock+0x44/0x8c0
[ 4050.264782]  [<0000000000b9878a>] mutex_lock_nested+0x32/0x40
[ 4050.264793]  [<000003ff800d7abe>] vfio_group_get_device+0x36/0xa8 [vfio]
[ 4050.264803]  [<000003ff800d87c0>] vfio_del_group_dev+0x238/0x378 [vfio]
[ 4050.264813]  [<000003ff8015f67c>] mdev_remove+0x3c/0x68 [mdev]
[ 4050.264825]  [<00000000008e01b0>] device_release_driver_internal+0x168/0x268
[ 4050.264834]  [<00000000008de692>] bus_remove_device+0x162/0x190
[ 4050.264843]  [<00000000008daf42>] device_del+0x1e2/0x368
[ 4050.264851]  [<00000000008db12c>] device_unregister+0x64/0x88
[ 4050.264862]  [<000003ff8015ed84>] mdev_device_remove+0xec/0x130 [mdev]
[ 4050.264872]  [<000003ff8015f074>] remove_store+0x6c/0xa8 [mdev]
[ 4050.264881]  [<000000000046f494>] kernfs_fop_write+0x14c/0x1f8
[ 4050.264890]  [<00000000003c1530>] __vfs_write+0x38/0x1a8
[ 4050.264899]  [<00000000003c187c>] vfs_write+0xb4/0x198
[ 4050.264908]  [<00000000003c1af2>] ksys_write+0x5a/0xb0
[ 4050.264916]  [<0000000000b9e270>] system_call+0xdc/0x2d8
[ 4050.264925] 4 locks held by sh/35924:
[ 4050.264933]  #0: 000000001ef90325 (sb_writers#4){.+.+}, at: vfs_write+0x9e/0x198
[ 4050.264948]  #1: 000000005c1ab0b3 (&of->mutex){+.+.}, at: kernfs_fop_write+0x1cc/0x1f8
[ 4050.264963]  #2: 0000000034831ab8 (kn->count#297){++++}, at: kernfs_remove_self+0x12e/0x150
[ 4050.264979]  #3: 00000000e152484f (&dev->mutex){....}, at: device_release_driver_internal+0x5c/0x268
[ 4050.264993] Last Breaking-Event-Address:
[ 4050.265002]  [<000000000017bbaa>] __might_sleep+0x72/0x90
[ 4050.265010] irq event stamp: 7039
[ 4050.265020] hardirqs last  enabled at (7047): [<00000000001cee7a>] console_unlock+0x6d2/0x740
[ 4050.265029] hardirqs last disabled at (7054): [<00000000001ce87e>] console_unlock+0xd6/0x740
[ 4050.265040] softirqs last  enabled at (6416): [<0000000000b8fe26>] __udelay+0xb6/0x100
[ 4050.265049] softirqs last disabled at (6415): [<0000000000b8fe06>] __udelay+0x96/0x100
[ 4050.265057] ---[ end trace d04a07d39d99a9f9 ]---

Let's fix this as described in the article
https://lwn.net/Articles/628628/.

---
 drivers/vfio/vfio.c | 30 ++++++++++--------------------
 1 file changed, 10 insertions(+), 20 deletions(-)

index f5a86f651f38..0d73d913c18b 100644
@@ -34,6 +34,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 
 #define DRIVER_VERSION	"0.3"
 #define DRIVER_AUTHOR	"Alex Williamson <[email protected]>"

@@ -909,30 +910,17 @@ void *vfio_device_data(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_device_data);
 
-/* Given a referenced group, check if it contains the device */
-static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	device = vfio_group_get_device(group, dev);
-	if (!device)
-		return false;
-
-	vfio_device_put(device);
-	return true;
-}
-
 /*
  * Decrement the device reference count and wait for the device to be
  * removed.  Open file descriptors for the device... */
 void *vfio_del_group_dev(struct device *dev)
 {
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct vfio_device *device = dev_get_drvdata(dev);
 	struct vfio_group *group = device->group;
 	void *device_data = device->device_data;
 	struct vfio_unbound_dev *unbound;
 	unsigned int i = 0;
-	long ret;
 	bool interrupted = false;
 
 	/*

@@ -969,6 +957,8 @@ void *vfio_del_group_dev(struct device *dev)
 	 * interval with counter to allow the driver to take escalating
 	 * measures to release the device if it has the ability to do so.
 	 */
+	add_wait_queue(&vfio.release_q, &wait);
+
 	do {
 		device = vfio_group_get_device(group, dev);
 		if (!device)

@@ -980,12 +970,10 @@ void *vfio_del_group_dev(struct device *dev)
 		vfio_device_put(device);
 
 		if (interrupted) {
-			ret = wait_event_timeout(vfio.release_q,
-					!vfio_dev_present(group, dev), HZ * 10);
+			wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
 		} else {
-			ret = wait_event_interruptible_timeout(vfio.release_q,
-					!vfio_dev_present(group, dev), HZ * 10);
-			if (ret == -ERESTARTSYS) {
+			wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
+			if (signal_pending(current)) {
 				interrupted = true;
 				dev_warn(dev,
 					 "Device is currently in use, task"

@@ -994,8 +982,10 @@ void *vfio_del_group_dev(struct device *dev)
 					 current->comm, task_pid_nr(current));
 			}
 		}
-	} while (ret <= 0);
 
+	} while (1);
+
+	remove_wait_queue(&vfio.release_q, &wait);
 	/*
 	 * In order to support multiple devices per group, devices can be
 	 * plucked from the group while other devices in the group are still

2.20.1

[ Upstream commit 7640682e67b33cab8628729afec8ca92b851394f ]

FUSE filesystem server and kernel client negotiate during initialization phase, what should be the maximum write size the client will ever issue. Correspondingly the filesystem server then queues sys_read calls to read requests with buffer capacity large enough to carry request header + that max_write bytes. A filesystem server is free to set its max_write in anywhere in the range between [1*page, fc->max_pages*page]. In particular go-fuse[2] sets max_write by default as 64K, wheres default fc->max_pages corresponds to 128K. Libfuse also allows users to configure max_write, but by default presets it to possible maximum.

If max_write is < fc->max_pages*page, and in NOTIFY_RETRIEVE handler we allow to retrieve more than max_write bytes, corresponding prepared NOTIFY_REPLY will be thrown away by fuse_dev_do_read, because the filesystem server, in full correspondence with server/client contract, will be only queuing sys_read with ~max_write buffer capacity, and fuse_dev_do_read throws away requests that cannot fit into server request buffer. In turn the filesystem server could get stuck waiting indefinitely for NOTIFY_REPLY since NOTIFY_RETRIEVE handler returned OK which is understood by clients as that NOTIFY_REPLY was queued and will be sent back.

Cap requested size to negotiate max_write to avoid the problem. This aligns with the way NOTIFY_RETRIEVE handler works, which already unconditionally caps requested retrieve size to fuse_conn->max_pages. This way it should not hurt NOTIFY_RETRIEVE semantic if we return less data than was originally requested.

Please see [1] for context where the problem of stuck filesystem was hit for real, how the situation was traced and for more involving patch that did not make it into the tree.

[1] https://marc.info/?l=linux-fsdevel&m=155057023600853&w=2
[2] https://github.com/hanwen/go-fuse

---
 fs/fuse/dev.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1678,7 +1678,7 @@ static int fuse_retrieve(struct fuse_con
 	offset = outarg->offset & ~PAGE_MASK;
 	file_size = i_size_read(inode);
 
-	num = outarg->size;
+	num = min(outarg->size, fc->max_write);
 	if (outarg->offset > file_size)
 		num = 0;
 	else if (outarg->offset + num > file_size)

[ Upstream commit 2fe518fecb3a4727393be286db9804cd82ee2d91 ]

When the bit_offset in the cell is zero, the pointer to the msb will not be properly initialized (ie, will still be pointing to the first byte in the buffer).

This being the case, if there are bits to clear in the msb, those will be left untouched while the mask will incorrectly clear bit positions on the first byte.

This commit also makes sure that any byte unused in the cell is cleared.

---
 drivers/nvmem/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

index 635886e4835c..dba3f4d0a63d 100644
@@ -954,7 +954,7 @@ static inline void nvmem_shift_read_buffer_in_place(struct nvmem_cell *cell,
 						    void *buf)
 {
 	u8 *p, *b;
-	int i, bit_offset = cell->bit_offset;
+	int i, extra, bit_offset = cell->bit_offset;
 
 	p = b = buf;
 	if (bit_offset) {

@@ -969,11 +969,16 @@ static inline void nvmem_shift_read_buffer_in_place(struct nvmem_cell *cell,
 			p = b;
 			*b++ >>= bit_offset;
 		}
-
-		/* result fits in less bytes */
-		if (cell->bytes != DIV_ROUND_UP(cell->nbits, BITS_PER_BYTE))
-			*p-- = 0;
+	} else {
+		/* point to the msb */
+		p += cell->bytes - 1;
 	}
+
+	/* result fits in less bytes */
+	extra = cell->bytes - DIV_ROUND_UP(cell->nbits, BITS_PER_BYTE);
+	while (--extra >= 0)
+		*p-- = 0;
+
 	/* clear msb bits if any leftover in the last byte */
 	*p &= GENMASK((cell->nbits%BITS_PER_BYTE) - 1, 0);
 }

2.20.1

[ Upstream commit 0b8f62625dc309651d0efcb6a6247c933acd8b45 ]

A fuzzer recently triggered lockdep warnings about potential sb_writers deadlocks caused by fh_want_write().

Looks like we aren't careful to pair each fh_want_write() with an fh_drop_write().

It's not normally a problem since fh_put() will call fh_drop_write() for us. And was OK for NFSv3 where we'd do one operation that might call fh_want_write(), and then put the filehandle.

But an NFSv4 protocol fuzzer can do weird things like call unlink twice in a compound, and then we get into trouble.

I'm a little worried about this approach of just leaving everything to fh_put(). But I think there are probably a lot of fh_want_write()/fh_drop_write() imbalances so for now I think we need it to be more forgiving.

---
 fs/nfsd/vfs.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index be6d8e00453f..85f544007311 100644
@@ -117,8 +117,11 @@ void		nfsd_put_raparams(struct file *file, struct raparms *ra);
 
 static inline int fh_want_write(struct svc_fh *fh)
 {
-	int ret = mnt_want_write(fh->fh_export->ex_path.mnt);
+	int ret;
 
+	if (fh->fh_want_write)
+		return 0;
+	ret = mnt_want_write(fh->fh_export->ex_path.mnt);
 	if (!ret)
 		fh->fh_want_write = true;
 	return ret;

2.20.1

[ Upstream commit f495222e28275222ab6fd93813bd3d462e16d340 ]

Currently the IRQ handler in HD-audio controller driver is registered before the chip initialization. That is, we have some window opened between the azx_acquire_irq() call and the CORB/RIRB setup. If an interrupt is triggered in this small window, the IRQ handler may access to the uninitialized RIRB buffer, which leads to a NULL dereference Oops.

This is usually no big problem since most of Intel chips do register the IRQ via MSI, and we've already fixed the order of the IRQ enablement and the CORB/RIRB setup in the former commit b61749a89f82 ("sound: enable interrupt after dma buffer initialization"), hence the IRQ won't be triggered in that room. However, some platforms use a shared IRQ, and this may allow the IRQ trigger by another source.

Another possibility is the kdump environment: a stale interrupt might be present in there, the IRQ handler can be falsely triggered as well.

For covering this small race, let's move the azx_acquire_irq() call after hda_intel_init_chip() call. Although this is a bit radical change, it can cover more widely than checking the CORB/RIRB setup locally in the callee side.

---
 sound/pci/hda/hda_intel.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index afa591cf840a..65fb1e7edb9c 100644
@@ -1839,9 +1839,6 @@ static int azx_first_init(struct azx *chip)
 			chip->msi = 0;
 	}
 
-	if (azx_acquire_irq(chip, 0) < 0)
-		return -EBUSY;
-
 	pci_set_master(pci);
 	synchronize_irq(bus->irq);
 

@@ -1956,6 +1953,9 @@ static int azx_first_init(struct azx *chip)
 		return -ENODEV;
 	}
 
+	if (azx_acquire_irq(chip, 0) < 0)
+		return -EBUSY;
+
 	strcpy(card->driver, "HDA-Intel");
 	strlcpy(card->shortname, driver_short_names[chip->driver_type],
 		sizeof(card->shortname));

2.20.1

[ Upstream commit 8f220664570e755946db1282f48e07f26e1f2cb4 ]

commit 834b90519925 ("misc: pci_endpoint_test: Add support for PCI_ENDPOINT_TEST regs to be mapped to any BAR") while adding test_reg_bar in order to map PCI_ENDPOINT_TEST regs to be mapped to any BAR failed to update test_reg_bar in pci_endpoint_test, resulting in test_reg_bar having invalid value when used outside probe.

Fix it.

---
 drivers/misc/pci_endpoint_test.c | 1 +
 1 file changed, 1 insertion(+)

index e089bb6dde3a..9849bf183299 100644
@@ -479,6 +479,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
 		test_reg_bar = data->test_reg_bar;
+		test->test_reg_bar = test_reg_bar;
 		test->alignment = data->alignment;
 		no_msi = data->no_msi;
 	}

2.20.1

[ Upstream commit c8e9e9b7646ebe1c5066ddc420d7630876277eb4 ]

Just like IO queues, the admin queue also will not be restarted after a controller shutdown. Unquiesce this queue so that we do not block request dispatch on a permanently disabled controller.

---
 drivers/nvme/host/pci.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 06355ca832db..cd11cced3678 100644
@@ -2105,8 +2105,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	 * must flush all entered requests to their failed completion to avoid
 	 * deadlocking blk-mq hot-cpu notifier.
 	 */
-	if (shutdown)
+	if (shutdown) {
 		nvme_start_queues(&dev->ctrl);
+		if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
+			blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+	}
 	mutex_unlock(&dev->shutdown_lock);
 }
 

2.20.1

[ Upstream commit 0cd0e49711556d2331a06b1117b68dd786cb54d2 ]

Call order on probe():
- max14656_hw_init() enables interrupts on the chip
- devm_request_irq() starts processing interrupts, isr could be called immediately
- isr: schedules delayed work (irq_work)
- irq_work: calls power_supply_changed()
- devm_power_supply_register() registers the power supply

Depending on timing, it's possible that power_supply_changed() is called on an unregistered power supply structure.

Fix by registering the power supply before requesting the irq.

---
 drivers/power/supply/max14656_charger_detector.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

index b91b1d2999dc..d19307f791c6 100644
@@ -280,6 +280,13 @@ static int max14656_probe(struct i2c_client *client,
 
 	INIT_DELAYED_WORK(&chip->irq_work, max14656_irq_worker);
 
+	chip->detect_psy = devm_power_supply_register(dev,
+		       &chip->psy_desc, &psy_cfg);
+	if (IS_ERR(chip->detect_psy)) {
+		dev_err(dev, "power_supply_register failed\n");
+		return -EINVAL;
+	}
+
 	ret = devm_request_irq(dev, chip->irq, max14656_irq,
 			       IRQF_TRIGGER_FALLING,
 			       MAX14656_NAME, chip);

@@ -289,13 +296,6 @@ static int max14656_probe(struct i2c_client *client,
 	}
 	enable_irq_wake(chip->irq);
 
-	chip->detect_psy = devm_power_supply_register(dev,
-		       &chip->psy_desc, &psy_cfg);
-	if (IS_ERR(chip->detect_psy)) {
-		dev_err(dev, "power_supply_register failed\n");
-		return -EINVAL;
-	}
-
 	schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(2000));
 
 	return 0;

2.20.1

[ Upstream commit e61985d0550df8c2078310202aaad9b41049c36c ]

If punit or telemetry device initialization fails, pmc driver should unregister and return failure.

This change is to fix a kernel panic when removing kernel module intel_pmc_ipc.

---
 drivers/platform/x86/intel_pmc_ipc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index e03fa31446ca..c9b3ef333743 100644
@@ -747,13 +747,17 @@ static int ipc_create_pmc_devices(void)
 	if (ret) {
 		dev_err(ipcdev.dev, "Failed to add punit platform device\n");
 		platform_device_unregister(ipcdev.tco_dev);
+		return ret;
 	}
 
 	if (!ipcdev.telem_res_inval) {
 		ret = ipc_create_telemetry_device();
-		if (ret)
+		if (ret) {
 			dev_warn(ipcdev.dev,
 				"Failed to add telemetry platform device\n");
+			platform_device_unregister(ipcdev.punit_dev);
+			platform_device_unregister(ipcdev.tco_dev);
+		}
 	}
 
 	return ret;

2.20.1

[ Upstream commit feb689025fbb6f0aa6297d3ddf97de945ea4ad32 ]

ALSA OSS sequencer calls the ioctl function indirectly via snd_seq_kernel_client_ctl(). While we already applied the protection against races between the normal ioctls and writes via the client's ioctl_mutex, this code path was left untouched. And this seems to be the cause of still remaining some rare UAF as spontaneously triggered by syzkaller.

For the sake of robustness, wrap the ioctl_mutex also for the call via snd_seq_kernel_client_ctl(), too.

---
 sound/core/seq/seq_clientmgr.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

index 3bcd7a2f0394..692631bd4a35 100644
@@ -2348,14 +2348,19 @@ int snd_seq_kernel_client_ctl(int clientid, unsigned int cmd, void *arg)
 {
 	const struct ioctl_handler *handler;
 	struct snd_seq_client *client;
+	int err;
 
 	client = clientptr(clientid);
 	if (client == NULL)
 		return -ENXIO;
 
 	for (handler = ioctl_handlers; handler->cmd > 0; ++handler) {
-		if (handler->cmd == cmd)
-			return handler->func(client, arg);
+		if (handler->cmd == cmd) {
+			mutex_lock(&client->ioctl_mutex);
+			err = handler->func(client, arg);
+			mutex_unlock(&client->ioctl_mutex);
+			return err;
+		}
 	}
 
 	pr_debug("ALSA: seq unknown ioctl() 0x%x (type='%c', number=0x%02x)\n",

2.20.1

[ Upstream commit fb26228bfc4ce3951544848555c0278e2832e618 ]

The find_dlpar_node() helper returns a device node with its reference incremented. Both the add and remove paths use this helper for find the appropriate node, but fail to release the reference when done.

Annotate the find_dlpar_node() helper with a comment about the incremented reference count and call of_node_put() on the obtained device_node in the add and remove paths. Also, fixup a reference leak in the find_vio_slot() helper where we fail to call of_node_put() on the vdevice node after we iterate over its children.

---
 drivers/pci/hotplug/rpadlpar_core.c | 4 ++++
 1 file changed, 4 insertions(+)

index a3449d717a99..f8f26684c67d 100644
@@ -55,6 +55,7 @@ static struct device_node *find_vio_slot_node(char *drc_name)
 		if ((rc == 0) && (!strcmp(drc_name, name)))
 			break;
 	}
+	of_node_put(parent);
 
 	return dn;
 }

@@ -78,6 +79,7 @@ static struct device_node *find_php_slot_pci_node(char *drc_name,
 	return np;
 }
 
+/* Returns a device_node with its reference count incremented */
 static struct device_node *find_dlpar_node(char *drc_name, int *node_type)
 {
 	struct device_node *dn;

@@ -313,6 +315,7 @@ int dlpar_add_slot(char *drc_name)
 			rc = dlpar_add_phb(drc_name, dn);
 			break;
 	}
+	of_node_put(dn);
 
 	printk(KERN_INFO "%s: slot %s added\n", DLPAR_MODULE_NAME, drc_name);
 exit:

@@ -446,6 +449,7 @@ int dlpar_remove_slot(char *drc_name)
 			rc = dlpar_remove_pci_slot(drc_name, dn);
 			break;
 	}
+	of_node_put(dn);
 	vm_unmap_aliases();
 
 	printk(KERN_INFO "%s: slot %s removed\n", DLPAR_MODULE_NAME, drc_name);

2.20.1

[ Upstream commit cf1ec4539a50bdfe688caad4615ca47646884316 ]

The intel_iommu_gfx_mapped flag is exported by the Intel IOMMU driver to indicate whether an IOMMU is used for the graphic device. In a virtualized IOMMU environment (e.g. QEMU), an include-all IOMMU is used for graphic device. This flag is found to be clear even the IOMMU is used.

---
 drivers/iommu/intel-iommu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

index fe935293fa7b..baa4c58e2736 100644
@@ -4019,9 +4019,7 @@ static void __init init_no_remapping_devices(void)
 
 		/* This IOMMU has *only* gfx devices. Either bypass it or
 		   set the gfx_mapped flag, as appropriate */
-		if (dmar_map_gfx) {
-			intel_iommu_gfx_mapped = 1;
-		} else {
+		if (!dmar_map_gfx) {
 			drhd->ignored = 1;
 			for_each_active_dev_scope(drhd->devices,
 						  drhd->devices_cnt, i, dev)

@@ -4807,6 +4805,9 @@ int __init intel_iommu_init(void)
 		goto out_free_reserved_range;
 	}
 
+	if (dmar_map_gfx)
+		intel_iommu_gfx_mapped = 1;
+
 	init_no_remapping_devices();
 
 	ret = init_dmars();

2.20.1

[ Upstream commit bbdc00a7de24cc90315b1775fb74841373fe12f7 ]

The rk3288 SoC has two PWM implementations available, the "old" implementation and the "new" one. You can switch between the two of them by flipping a bit in the grf.

The "old" implementation is the default at chip power up but isn't the one that's officially supposed to be used. ...and, in fact, the driver that gets selected in Linux using the rk3288 device tree only supports the "new" implementation.

Long ago I tried to get a switch to the right IP block landed in the PWM driver (search for "rk3288: Switch to use the proper PWM IP") but that got rejected. In the mean time the grf has grown a full-fledged driver that already sets other random bits like this. That means we can now get the fix landed.

For those wondering how things could have possibly worked for the last 4.5 years, folks have mostly been relying on the bootloader to set this bit. ...but occasionally folks have pointed back to my old patch series [1] in downstream kernels.

[1] https://www.mail-archive.com/[email protected]/msg1391597.html

---
 drivers/soc/rockchip/grf.c | 2 ++
 1 file changed, 2 insertions(+)

index 15e71fd6c513..0931ddb0b384 100644
@@ -44,9 +44,11 @@ static const struct rockchip_grf_info rk3036_grf __initconst = {
 };
 
 #define RK3288_GRF_SOC_CON0		0x244
+#define RK3288_GRF_SOC_CON2		0x24c
 
 static const struct rockchip_grf_value rk3288_defaults[] __initconst = {
 	{ "jtag switching", RK3288_GRF_SOC_CON0, HIWORD_UPDATE(0, 1, 12) },
+	{ "pwm select", RK3288_GRF_SOC_CON2, HIWORD_UPDATE(1, 1, 0) },
 };
 
 static const struct rockchip_grf_info rk3288_grf __initconst = {

2.20.1

[ Upstream commit 57a20248ef3e429dc822f0774bc4e00136c46c83 ]

Experimentally it can be seen that going into deep sleep (specifically setting PMU_CLR_DMA and PMU_CLR_BUS in RK3288_PMU_PWRMODE_CON1) appears to fail unless "aclk_dmac1" is on. The failure is that the system never signals that it made it into suspend on the GLOBAL_PWROFF pin and it just hangs.

NOTE that it's confirmed that it's the actual suspend that fails, not one of the earlier calls to read/write registers. Specifically if you comment out the "PMU_GLOBAL_INT_DISABLE" setting in rk3288_slp_mode_set() and then comment out the "cpu_do_idle()" call in rockchip_lpmode_enter() then you can exercise the whole suspend path without any crashing.

This is currently not a problem with suspend upstream because there is no current way to exercise the deep suspend code. However, anyone trying to make it work will run into this issue.

This was not a problem on shipping rk3288-based Chromebooks because those devices all ran on an old kernel based on 3.14. On that kernel "aclk_dmac1" appears to be left on all the time.

There are several ways to skin this problem.

A) We could add "aclk_dmac1" to the list of critical clocks and that apperas to work, but presumably that wastes power.

B) We could keep a list of "struct clk" objects to enable at suspend time in clk-rk3288.c and use the standard clock APIs.

C) We could make the rk3288-pmu driver keep a list of clocks to enable at suspend time. Presumably this would require a dts and bindings change.

D) We could just whack the clock on in the existing syscore suspend function where we whack a bunch of other clocks. This is particularly easy because we know for sure that the clock's only parent ("aclk_cpu") is a critical clock so we don't need to do anything more than ungate it.

In this case I have chosen D) because it seemed like the least work, but any of the other options would presumably also work fine.

---
 drivers/clk/rockchip/clk-rk3288.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

index 64191694ff6e..9cfdbea493bb 100644
@@ -835,6 +835,9 @@ static const int rk3288_saved_cru_reg_ids[] = {
 	RK3288_CLKSEL_CON(10),
 	RK3288_CLKSEL_CON(33),
 	RK3288_CLKSEL_CON(37),
+
+	/* We turn aclk_dmac1 on for suspend; this will restore it */
+	RK3288_CLKGATE_CON(10),
 };
 
 static u32 rk3288_saved_cru_regs[ARRAY_SIZE(rk3288_saved_cru_reg_ids)];

@@ -850,6 +853,14 @@ static int rk3288_clk_suspend(void)
 				readl_relaxed(rk3288_cru_base + reg_id);
 	}
 
+	/*
+	 * Going into deep sleep (specifically setting PMU_CLR_DMA in
+	 * RK3288_PMU_PWRMODE_CON1) appears to fail unless
+	 * "aclk_dmac1" is on.
+	 */
+	writel_relaxed(1 << (12 + 16),
+		       rk3288_cru_base + RK3288_CLKGATE_CON(10));
+
 	/*
 	 * Switch PLLs other than DPLL (for SDRAM) to slow mode to
 	 * avoid crashes on resume. The Mask ROM on the system will

2.20.1

[ Upstream commit 89e28da82836530f1ac7a3a32fecc31f22d79b3e ]

When building with -Wsometimes-uninitialized, Clang warns:

drivers/soc/mediatek/mtk-pmic-wrap.c:1358:6: error: variable 'rdata' is used uninitialized whenever '||' condition is true [-Werror,-Wsometimes-uninitialized]

If pwrap_write returns non-zero, pwrap_read will not be called to initialize rdata, meaning that we will use some random uninitialized stack value in our print statement. Zero initialize rdata in case this happens.

---
 drivers/soc/mediatek/mtk-pmic-wrap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e3df1e96b141..d7a31bf3c9d6 100644
@@ -778,7 +778,7 @@ static bool pwrap_is_pmic_cipher_ready(struct pmic_wrapper *wrp)
 static int pwrap_init_cipher(struct pmic_wrapper *wrp)
 {
 	int ret;
-	u32 rdata;
+	u32 rdata = 0;
 
 	pwrap_writel(wrp, 0x1, PWRAP_CIPHER_SWRST);
 	pwrap_writel(wrp, 0x0, PWRAP_CIPHER_SWRST);

2.20.1

[ Upstream commit f316a2b53cd7f37963ae20ec7072eb27a349a4ce ]

hook_fault_code() is an ARM32 specific API for hooking into data abort.

AM65X platforms (that integrate ARM v8 cores and select CONFIG_ARM64 as arch) rely on pci-keystone.c but on them the enumeration of a non-present BDF does not trigger a bus error, so the fixup exception provided by calling hook_fault_code() is not needed and can be guarded with CONFIG_ARM.

---
 drivers/pci/dwc/pci-keystone.c | 4 ++++
 1 file changed, 4 insertions(+)

index 39405598b22d..9bc52e4cf52a 100644
@@ -240,6 +240,7 @@ static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
 		ks_dw_pcie_enable_error_irq(ks_pcie);
 }
 
+#ifdef CONFIG_ARM
 /*
  * When a PCI device does not exist during config cycles, keystone host gets a
  * bus error instead of returning 0xffffffff. This handler always returns 0

@@ -259,6 +260,7 @@ static int keystone_pcie_fault(unsigned long addr, unsigned int fsr,
 
 	return 0;
 }
+#endif
 
 static int __init ks_pcie_host_init(struct pcie_port *pp)
 {

@@ -282,12 +284,14 @@ static int __init ks_pcie_host_init(struct pcie_port *pp)
 	val |= BIT(12);
 	writel(val, pci->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
 
+#ifdef CONFIG_ARM
 	/*
 	 * PCIe access errors that result into OCP errors are caught by ARM as
 	 * "External aborts"
 	 */
 	hook_fault_code(17, keystone_pcie_fault, SIGBUS, 0,
 			"Asynchronous external abort");
+#endif
 
 	return 0;
 }

2.20.1

[ Upstream commit ea094d53580f40c2124cef3d072b73b2425e7bfd ]

In pcibios_irq_init(), the PCI IRQ routing table 'pirq_table' is first found through pirq_find_routing_table(). If the table is not found and CONFIG_PCI_BIOS is defined, the table is then allocated in pcibios_get_irq_routing_table() using kmalloc(). Later, if the I/O APIC is used, this table is actually not used. In that case, the allocated table is not freed, which is a memory leak.

Free the allocated table if it is not used.

[bhelgaas: added Ingo's reviewed-by, since the only change since v1 was to use the irq_routing_table local variable name he suggested]

---
 arch/x86/pci/irq.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

index 0452629148be..c77f565a04f2 100644
@@ -1118,6 +1118,8 @@ static const struct dmi_system_id pciirq_dmi_table[] __initconst = {
 
 void __init pcibios_irq_init(void)
 {
+	struct irq_routing_table *rtable = NULL;
+
 	DBG(KERN_DEBUG "PCI: IRQ init\n");
 
 	if (raw_pci_ops == NULL)

@@ -1128,8 +1130,10 @@ void __init pcibios_irq_init(void)
 	pirq_table = pirq_find_routing_table();
 
 #ifdef CONFIG_PCI_BIOS
-	if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN))
+	if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) {
 		pirq_table = pcibios_get_irq_routing_table();
+		rtable = pirq_table;
+	}
 #endif
 	if (pirq_table) {
 		pirq_peer_trick();

@@ -1144,8 +1148,10 @@ void __init pcibios_irq_init(void)
 		 * If we're using the I/O APIC, avoid using the PCI IRQ
 		 * routing table
 		 */
-		if (io_apic_assign_pci_irqs)
+		if (io_apic_assign_pci_irqs) {
+			kfree(rtable);
 			pirq_table = NULL;
+		}
 	}
 
 	x86_init.pci.fixup_irqs();

2.20.1

[ Upstream commit 94d4e7af14a1170e34cf082d92e4c02de9e9fb88 ]

As new transfer mechanisms are added to the EC codebase, they may not support v2 of the EC protocol.

If the v3 initial handshake transfer fails, the kernel will try and call cmd_xfer as a fallback. If v2 is not supported, cmd_xfer will be NULL, and the code will end up causing a kernel panic.

Add a check for NULL before calling the transfer function, along with a helpful comment explaining how one might end up in this situation.

---
 drivers/platform/chrome/cros_ec_proto.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

index 2ac4a7178470..dbad14716da4 100644
@@ -67,6 +67,17 @@ static int send_command(struct cros_ec_device *ec_dev,
 	else
 		xfer_fxn = ec_dev->cmd_xfer;
 
+	if (!xfer_fxn) {
+		/*
+		 * This error can happen if a communication error happened and
+		 * the EC is trying to use protocol v2, on an underlying
+		 * communication mechanism that does not support v2.
+		 */
+		dev_err_once(ec_dev->dev,
+			     "missing EC transfer API, cannot send command\n");
+		return -EIO;
+	}
+
 	ret = (*xfer_fxn)(ec_dev, msg);
 	if (msg->result == EC_RES_IN_PROGRESS) {
 		int i;

2.20.1

[ Upstream commit 2b59e01a3aa665f751d1410b99fae9336bd424e1 ]

Currently one bit in cma bitmap represents number of pages rather than one page, cma->count means cma size in pages. So to find available pages via find_next_zero_bit()/find_next_bit() we should use cma size not in pages but in bits although current free pages number is correct due to zero value of order_per_bit. Once order_per_bit is changed the bitmap status will be incorrect.

The size input in cma_debug_show_areas() is not correct. It will affect the available pages at some position to debug the failure issue.

This is an example with order_per_bit = 1

Before this change:

[    4.120060] cma: number of available pages: 1@93+4@108+7@121+7@137+7@153+7@169+7@185+7@201+3@213+3@221+3@229+3@237+3@245+3@253+3@261+3@269+3@277+3@285+3@293+3@301+3@309+3@317+3@325+19@333+15@369+512@512=> 638 free of 1024 total pages

After this change:

[    4.143234] cma: number of available pages: 2@93+8@108+14@121+14@137+14@153+14@169+14@185+14@201+6@213+6@221+6@229+6@237+6@245+6@253+6@261+6@269+6@277+6@285+6@293+6@301+6@309+6@317+6@325+38@333+30@369=> 252 free of 1024 total pages

Obviously the bitmap status before is incorrect.

---
 mm/cma.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

index cba4fe1b284c..56761e40d191 100644
@@ -366,23 +366,26 @@ err:
 #ifdef CONFIG_CMA_DEBUG
 static void cma_debug_show_areas(struct cma *cma)
 {
-	unsigned long next_zero_bit, next_set_bit;
+	unsigned long next_zero_bit, next_set_bit, nr_zero;
 	unsigned long start = 0;
-	unsigned int nr_zero, nr_total = 0;
+	unsigned long nr_part, nr_total = 0;
+	unsigned long nbits = cma_bitmap_maxno(cma);
 
 	mutex_lock(&cma->lock);
 	pr_info("number of available pages: ");
 	for (;;) {
-		next_zero_bit = find_next_zero_bit(cma->bitmap, cma->count, start);
-		if (next_zero_bit >= cma->count)
+		next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start);
+		if (next_zero_bit >= nbits)
 			break;
-		next_set_bit = find_next_bit(cma->bitmap, cma->count, next_zero_bit);
+		next_set_bit = find_next_bit(cma->bitmap, nbits, next_zero_bit);
 		nr_zero = next_set_bit - next_zero_bit;
-		pr_cont("%s%u@%lu", nr_total ? "+" : "", nr_zero, next_zero_bit);
-		nr_total += nr_zero;
+		nr_part = nr_zero << cma->order_per_bit;
+		pr_cont("%s%lu@%lu", nr_total ? "+" : "", nr_part,
+			next_zero_bit);
+		nr_total += nr_part;
 		start = next_zero_bit + nr_zero;
 	}
-	pr_cont("=> %u free of %lu total pages\n", nr_total, cma->count);
+	pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count);
 	mutex_unlock(&cma->lock);
 }
 #else

2.20.1

[ Upstream commit dad06532292d77f37fbe831a02948a593500f682 ]

In virtualized setup, when system reboots due to warm reset interrupt storm is seen.

Call Trace:
<IRQ>
dump_stack+0x70/0xa5
__report_bad_irq+0x2e/0xc0
note_interrupt+0x248/0x290
? add_interrupt_randomness+0x30/0x220
handle_irq_event_percpu+0x54/0x80
handle_irq_event+0x39/0x60
handle_fasteoi_irq+0x91/0x150
handle_irq+0x108/0x180
do_IRQ+0x52/0xf0
common_interrupt+0xf/0xf
</IRQ>
RIP: 0033:0x76fc2cfabc1d
Code: 24 28 bf 03 00 00 00 31 c0 48 8d 35 63 77 0e 00 48 8d 15 2e

94 0e 00 4c 89 f9 49 89 d9 4c 89 d3 e8 b8 e2 01 00 48 8b 54 24 18 <48> 89 ef 48 89 de 4c 89 e1 e8 d5 97 01 00 84 c0 74 2d 48 8b 04 24
RSP: 002b:00007ffd247c1fc0 EFLAGS: 00000293 ORIG_RAX: ffffffffffffffda
RAX: 0000000000000000 RBX: 00007ffd247c1ff0 RCX: 000000000003d3ce
RDX: 0000000000000000 RSI: 00007ffd247c1ff0 RDI: 000076fc2cbb6010
RBP: 000076fc2cded010 R08: 00007ffd247c2210 R09: 00007ffd247c22a0
R10: 000076fc29465470 R11: 0000000000000000 R12: 00007ffd247c1fc0
R13: 000076fc2ce8e470 R14: 000076fc27ec9960 R15: 0000000000000414 handlers:
[<000000000d3fa913>] idma64_irq
Disabling IRQ #27

To avoid interrupt storm, set the device in reset state before bringing out the device from reset state.

Changelog v2:
- correct the subject line by adding "mfd: "

---
 drivers/mfd/intel-lpss.c | 3 +++
 1 file changed, 3 insertions(+)

index 40e8d9b59d07..b5c4f8f974aa 100644
@@ -273,6 +273,9 @@ static void intel_lpss_init_dev(const struct intel_lpss *lpss)
 {
 	u32 value = LPSS_PRIV_SSP_REG_DIS_DMA_FIN;
 
+	/* Set the device in reset state */
+	writel(0, lpss->priv + LPSS_PRIV_RESETS);
+
 	intel_lpss_deassert_reset(lpss);
 
 	intel_lpss_set_remap_addr(lpss);

2.20.1

[ Upstream commit fc7d18cf6a923cde7f5e7ba2c1105bb106d3e29a ]

We print a calibration failure message on -EPROBE_DEFER from nvmem/qfprom as follows:

[    3.003090] qcom-tsens 4a9000.thermal-sensor: version: 1.4
[    3.005376] qcom-tsens 4a9000.thermal-sensor: tsens calibration failed
[    3.113248] qcom-tsens 4a9000.thermal-sensor: version: 1.4

This confuses people when, in fact, calibration succeeds later when nvmem/qfprom device is available. Don't print this message on a -EPROBE_DEFER.

---
 drivers/thermal/qcom/tsens.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 3f9fe6aa51cc..ebbe1ec7b9e8 100644
@@ -162,7 +162,8 @@ static int tsens_probe(struct platform_device *pdev)
 	if (tmdev->ops->calibrate) {
 		ret = tmdev->ops->calibrate(tmdev);
 		if (ret < 0) {
-			dev_err(dev, "tsens calibration failed\n");
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "tsens calibration failed\n");
 			return ret;
 		}
 	}

2.20.1

[ Upstream commit 48171d0ea7caccf21c9ee3ae75eb370f2a756062 ]

I noticed that we can get a -EREMOTEIO errors on at least omap4 duovero:

twl6040 0-004b: Failed to write 2d = 19: -121

And then any following register access will produce errors.

There 2d offset above is register ACCCTL that gets written on twl6040 powerup. With error checking added to the related regcache_sync() call, the -EREMOTEIO error is reproducable on twl6040 powerup at least duovero.

To fix the error, we need to wait until twl6040 is accessible after the powerup. Based on tests on omap4 duovero, we need to wait over 8ms after powerup before register write will complete without failures. Let's also make sure we warn about possible errors too.

Note that we have twl6040_patch[] reg_sequence with the ACCCTL register configuration and regcache_sync() will write the new value to ACCCTL.

---
 drivers/mfd/twl6040.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

index dd19f17a1b63..2b8c479dbfa6 100644
@@ -322,8 +322,19 @@ int twl6040_power(struct twl6040 *twl6040, int on)
 			}
 		}
 
+		/*
+		 * Register access can produce errors after power-up unless we
+		 * wait at least 8ms based on measurements on duovero.
+		 */
+		usleep_range(10000, 12000);
+
 		/* Sync with the HW */
-		regcache_sync(twl6040->regmap);
+		ret = regcache_sync(twl6040->regmap);
+		if (ret) {
+			dev_err(twl6040->dev, "Failed to sync with the HW: %i\n",
+				ret);
+			goto out;
+		}
 
 		/* Default PLL configuration after power up */
 		twl6040->pll = TWL6040_SYSCLK_SEL_LPPLL;

2.20.1

[ Upstream commit 9e364e87ad7f2c636276c773d718cda29d62b741 ]

MODULE_DEVICE_TABLE(of, <of_match_table> should be called to complete DT OF mathing mechanism and register it.

Before this patch:
modinfo drivers/mfd/tps65912-spi.ko | grep alias
alias: spi:tps65912

After this patch:
modinfo drivers/mfd/tps65912-spi.ko | grep alias

alias:          of:N*T*Cti,tps65912C*
alias:          of:N*T*Cti,tps65912
alias:          spi:tps65912

---
 drivers/mfd/tps65912-spi.c | 1 +
 1 file changed, 1 insertion(+)

index 3bd75061f777..f78be039e463 100644
@@ -27,6 +27,7 @@ static const struct of_device_id tps65912_spi_of_match_table[] = {
 	{ .compatible = "ti,tps65912", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, tps65912_spi_of_match_table);
 
 static int tps65912_spi_probe(struct spi_device *spi)
 {

2.20.1

[ Upstream commit 63f55fcea50c25ae5ad45af92d08dae3b84534c2 ]

Currently IRQ remains enabled after .remove, later if device is probed, IRQ is requested before .thermal_init, this may cause IRQ function be called before device is initialized.

this patch disables interrupt in .remove, to ensure irq function only be called after device is fully initialized.

---
 drivers/thermal/rcar_gen3_thermal.c | 3 +++
 1 file changed, 3 insertions(+)

index 203aca44a2bb..0afdda2db3a0 100644
@@ -342,6 +342,9 @@ MODULE_DEVICE_TABLE(of, rcar_gen3_thermal_dt_ids);
 static int rcar_gen3_thermal_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct rcar_gen3_thermal_priv *priv = dev_get_drvdata(dev);
+
+	rcar_thermal_irq_set(priv, false);
 
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);

2.20.1

[ Upstream commit 13d03e9daf70dab032c03dc172e75bb98ad899c4 ]

Where possible, we want the failsafe link configuration (one which won't hang the OR during modeset because of not enough bandwidth for the mode) to also be supported by the sink.

This prevents "link rate unsupported by sink" messages when link training fails.

---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

index 6160a6158cf2..5e51a5c1eb01 100644
@@ -364,8 +364,15 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps)
 	 * and it's better to have a failed modeset than that.
 	 */
 	for (cfg = nvkm_dp_rates; cfg->rate; cfg++) {
-		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw)
-			failsafe = cfg;
+		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw) {
+			/* Try to respect sink limits too when selecting
+			 * lowest link configuration.
+			 */
+			if (!failsafe ||
+			    (cfg->nr <= sink_nr && cfg->bw <= sink_bw))
+				failsafe = cfg;
+		}
+
 		if (failsafe && cfg[1].rate < dataKBps)
 			break;
 	}

2.20.1

[ Upstream commit a9e73998f9d705c94a8dca9687633adc0f24a19a ]

While validating new map we require the @start_data to be strictly less than @end_data, which is fine for regular applications (this is why this nit didn't trigger for that long). These members are set from executable loaders such as elf handers, still it is pretty valid to have a loadable data section with zero size in file, in such case the start_data is equal to end_data once kernel loader finishes.

As a result when we're trying to restore such programs the procedure fails and the kernel returns -EINVAL. From the image dump of a program:

 | "mm_start_code": "0x400000",
 | "mm_end_code": "0x8f5fb4",
 | "mm_start_data": "0xf1bfb0",
 | "mm_end_data": "0xf1bfb0",

Thus we need to change validate_prctl_map from strictly less to less or equal operator use.

---
 kernel/sys.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e25ec93aea22..ab96b9882347 100644
@@ -1861,7 +1861,7 @@ static int validate_prctl_map(struct prctl_mm_map *prctl_map)
 	((unsigned long)prctl_map->__m1 __op				\
 	 (unsigned long)prctl_map->__m2) ? 0 : -EINVAL
 	error  = __prctl_check_order(start_code, <, end_code);
-	error |= __prctl_check_order(start_data, <, end_data);
+	error |= __prctl_check_order(start_data,<=, end_data);
 	error |= __prctl_check_order(start_brk, <=, brk);
 	error |= __prctl_check_order(arg_start, <=, arg_end);
 	error |= __prctl_check_order(env_start, <=, env_end);

2.20.1

[ Upstream commit b07e228eee69601addba98b47b1a3850569e5013 ]

The documentated behavior is: if max_hw_heartbeat_ms is implemented, the minimum of the set_timeout argument and max_hw_heartbeat_ms should be used. This patch implements this behavior.
Previously only the first 7bits were used and the input argument was returned.

---
 drivers/watchdog/imx2_wdt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 518dfa1047cb..5098982e1a58 100644
@@ -181,8 +181,10 @@ static void __imx2_wdt_set_timeout(struct watchdog_device *wdog,
 static int imx2_wdt_set_timeout(struct watchdog_device *wdog,
 				unsigned int new_timeout)
 {
-	__imx2_wdt_set_timeout(wdog, new_timeout);
+	unsigned int actual;
 
+	actual = min(new_timeout, wdog->max_hw_heartbeat_ms * 1000);
+	__imx2_wdt_set_timeout(wdog, actual);
 	wdog->timeout = new_timeout;
 	return 0;
 }

2.20.1

[ Upstream commit 93fa5b280761a4dbb14c5330f260380385ab2b49 ]

There are situations when memory regions coming from dts may be too big for the platform physical address space. This especially concerns XPA-capable systems. Bootloader may determine more than 4GB memory available and pass it to the kernel over dts memory node, while kernel is built without XPA/64BIT support. In this case the region may either simply be truncated by add_memory_region() method or by u64->phys_addr_t type casting. But in worst case the method can even drop the memory region if it exceeds PHYS_ADDR_MAX size. So lets make sure the retrieved from dts memory regions are valid, and if some of them aren't, just manually truncate them with a warning printed out.

---
 arch/mips/kernel/prom.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

index 0dbcd152a1a9..90f332f0625f 100644
@@ -41,7 +41,19 @@ char *mips_get_machine_name(void)
 #ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
-	return add_memory_region(base, size, BOOT_MEM_RAM);
+	if (base >= PHYS_ADDR_MAX) {
+		pr_warn("Trying to add an invalid memory region, skipped\n");
+		return;
+	}
+
+	/* Truncate the passed memory region instead of type casting */
+	if (base + size - 1 >= PHYS_ADDR_MAX || base + size < base) {
+		pr_warn("Truncate memory region %llx @ %llx to size %llx\n",
+			size, base, PHYS_ADDR_MAX - base);
+		size = PHYS_ADDR_MAX - base;
+	}
+
+	add_memory_region(base, size, BOOT_MEM_RAM);
 }
 
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)

2.20.1

I still run these manually (I guess it's time to automate that too), so it happens sometimes that folks notice these faster :)

--
Thanks,
Sasha

[ Upstream commit 198790d9a3aeaef5792d33a560020861126edc22 ]

In free_percpu() we sometimes call pcpu_schedule_balance_work() to queue a work item (which does a wakeup) while holding pcpu_lock. This creates an unnecessary lock dependency between pcpu_lock and the scheduler's pi_lock. There are other places where we call pcpu_schedule_balance_work() without hold pcpu_lock, and this case doesn't need to be different.

Moving the call outside the lock prevents the following lockdep splat when running tools/testing/selftests/bpf/{test_maps,test_progs} in sequence with lockdep enabled:

======================================================
WARNING: possible circular locking dependency detected 5.1.0-dbg-DEV #1 Not tainted
------------------------------------------------------
kworker/23:255/18872 is trying to acquire lock:
000000000bc79290 (&(&pool->lock)->rlock){-.-.}, at: __queue_work+0xb2/0x520

but task is already holding lock:
00000000e3e7a6aa (pcpu_lock){..-.}, at: free_percpu+0x36/0x260

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #4 (pcpu_lock){..-.}:

       lock_acquire+0x9e/0x180
       _raw_spin_lock_irqsave+0x3a/0x50
       pcpu_alloc+0xfa/0x780
       __alloc_percpu_gfp+0x12/0x20
       alloc_htab_elem+0x184/0x2b0
       __htab_percpu_map_update_elem+0x252/0x290
       bpf_percpu_hash_update+0x7c/0x130
       __do_sys_bpf+0x1912/0x1be0
       __x64_sys_bpf+0x1a/0x20
       do_syscall_64+0x59/0x400
       entry_SYSCALL_64_after_hwframe+0x49/0xbe

-> #3 (&htab->buckets[i].lock){....}:

       lock_acquire+0x9e/0x180
       _raw_spin_lock_irqsave+0x3a/0x50
       htab_map_update_elem+0x1af/0x3a0

-> #2 (&rq->lock){-.-.}:

       lock_acquire+0x9e/0x180
       _raw_spin_lock+0x2f/0x40
       task_fork_fair+0x37/0x160
       sched_fork+0x211/0x310
       copy_process.part.43+0x7b1/0x2160
       _do_fork+0xda/0x6b0
       kernel_thread+0x29/0x30
       rest_init+0x22/0x260
       arch_call_rest_init+0xe/0x10
       start_kernel+0x4fd/0x520
       x86_64_start_reservations+0x24/0x26
       x86_64_start_kernel+0x6f/0x72
       secondary_startup_64+0xa4/0xb0

-> #1 (&p->pi_lock){-.-.}:

       lock_acquire+0x9e/0x180
       _raw_spin_lock_irqsave+0x3a/0x50
       try_to_wake_up+0x41/0x600
       wake_up_process+0x15/0x20
       create_worker+0x16b/0x1e0
       workqueue_init+0x279/0x2ee
       kernel_init_freeable+0xf7/0x288
       kernel_init+0xf/0x180
       ret_from_fork+0x24/0x30

-> #0 (&(&pool->lock)->rlock){-.-.}:

       __lock_acquire+0x101f/0x12a0
       lock_acquire+0x9e/0x180
       _raw_spin_lock+0x2f/0x40
       __queue_work+0xb2/0x520
       queue_work_on+0x38/0x80
       free_percpu+0x221/0x260
       pcpu_freelist_destroy+0x11/0x20
       stack_map_free+0x2a/0x40
       bpf_map_free_deferred+0x3c/0x50
       process_one_work+0x1f7/0x580
       worker_thread+0x54/0x410
       kthread+0x10f/0x150
       ret_from_fork+0x24/0x30

other info that might help us debug this:

Chain exists of:
  &(&pool->lock)->rlock --> &htab->buckets[i].lock --> pcpu_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(pcpu_lock);
                               lock(&htab->buckets[i].lock);
                               lock(pcpu_lock);

lock(&(&pool->lock)->rlock);

*** DEADLOCK ***

3 locks held by kworker/23:255/18872:
#0: 00000000b36a6e16 ((wq_completion)events){+.+.},

     at: process_one_work+0x17a/0x580
 #1: 00000000dfd966f0 ((work_completion)(&map->work)){+.+.},
     at: process_one_work+0x17a/0x580
 #2: 00000000e3e7a6aa (pcpu_lock){..-.},
     at: free_percpu+0x36/0x260

stack backtrace:
CPU: 23 PID: 18872 Comm: kworker/23:255 Not tainted 5.1.0-dbg-DEV #1
Hardware name: ...
Workqueue: events bpf_map_free_deferred
Call Trace:
 dump_stack+0x67/0x95
 print_circular_bug.isra.38+0x1c6/0x220
 check_prev_add.constprop.50+0x9f6/0xd20
 __lock_acquire+0x101f/0x12a0
 lock_acquire+0x9e/0x180
 _raw_spin_lock+0x2f/0x40
 __queue_work+0xb2/0x520
 queue_work_on+0x38/0x80
 free_percpu+0x221/0x260
 pcpu_freelist_destroy+0x11/0x20
 stack_map_free+0x2a/0x40
 bpf_map_free_deferred+0x3c/0x50
 process_one_work+0x1f7/0x580
 worker_thread+0x54/0x410
 kthread+0x10f/0x150
 ret_from_fork+0x24/0x30

---
 mm/percpu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 0c06e2f549a7..bc58bcbe4b60 100644
@@ -1702,6 +1702,7 @@ void free_percpu(void __percpu *ptr)
 	struct pcpu_chunk *chunk;
 	unsigned long flags;
 	int off;
+	bool need_balance = false;
 
 	if (!ptr)
 		return;

@@ -1723,7 +1724,7 @@ void free_percpu(void __percpu *ptr)
 
 		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
 			if (pos != chunk) {
-				pcpu_schedule_balance_work();
+				need_balance = true;
 				break;
 			}
 	}

@@ -1731,6 +1732,9 @@ void free_percpu(void __percpu *ptr)
 	trace_percpu_free_percpu(chunk->base_addr, off, ptr);
 
 	spin_unlock_irqrestore(&pcpu_lock, flags);
+
+	if (need_balance)
+		pcpu_schedule_balance_work();
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 

2.20.1

[ Upstream commit 745e10146c31b1c6ed3326286704ae251b17f663 ]

"cat /proc/slab_allocators" could hang forever on SMP machines with kmemleak or object debugging enabled due to other CPUs running do_drain() will keep making kmemleak_object or debug_objects_cache dirty and unable to escape the first loop in leaks_show(),

do {
	set_store_user_clean(cachep);
	drain_cpu_caches(cachep);
	...

} while (!is_store_user_clean(cachep));

For example,

do_drain
slabs_destroy

    slab_destroy
      kmem_cache_free
        __cache_free
          ___cache_free
            kmemleak_free_recursive
              delete_object_full
                __delete_object
                  put_object
                    free_object_rcu
                      kmem_cache_free
                        cache_free_debugcheck --> dirty kmemleak_object

One approach is to check cachep->name and skip both kmemleak_object and debug_objects_cache in leaks_show(). The other is to set store_user_clean after drain_cpu_caches() which leaves a small window between drain_cpu_caches() and set_store_user_clean() where per-CPU caches could be dirty again lead to slightly wrong information has been stored but could also speed up things significantly which sounds like a good compromise. For example,

 # cat /proc/slab_allocators
 0m42.778s # 1st approach
 0m0.737s  # 2nd approach

---
 mm/slab.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 843ecea9e336..a04aeae42306 100644
@@ -4320,8 +4320,12 @@ static int leaks_show(struct seq_file *m, void *p)
 	 * whole processing.
 	 */
 	do {
-		set_store_user_clean(cachep);
 		drain_cpu_caches(cachep);
+		/*
+		 * drain_cpu_caches() could make kmemleak_object and
+		 * debug_objects_cache dirty, so reset afterwards.
+		 */
+		set_store_user_clean(cachep);
 
 		x[1] = 0;
 

2.20.1

[ Upstream commit 35399f87e271f7cf3048eab00a421a6519ac8441 ]

In configfs_register_group(), if create_default_group() failed, we forget to unlink the group. It will left a invalid item in the parent list, which may trigger the use-after-free issue seen below:

BUG: KASAN: use-after-free in __list_add_valid+0xd4/0xe0 lib/list_debug.c:26
Read of size 8 at addr ffff8881ef61ae20 by task syz-executor.0/5996

CPU: 1 PID: 5996 Comm: syz-executor.0 Tainted: G         C        5.0.0+ #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xa9/0x10e lib/dump_stack.c:113
 print_address_description+0x65/0x270 mm/kasan/report.c:187
 kasan_report+0x149/0x18d mm/kasan/report.c:317
 __list_add_valid+0xd4/0xe0 lib/list_debug.c:26
 __list_add include/linux/list.h:60 [inline]
 list_add_tail include/linux/list.h:93 [inline]
 link_obj+0xb0/0x190 fs/configfs/dir.c:759
 link_group+0x1c/0x130 fs/configfs/dir.c:784
 configfs_register_group+0x56/0x1e0 fs/configfs/dir.c:1751
 configfs_register_default_group+0x72/0xc0 fs/configfs/dir.c:1834
 ? 0xffffffffc1be0000
 iio_sw_trigger_init+0x23/0x1000 [industrialio_sw_trigger]
 do_one_initcall+0xbc/0x47d init/main.c:887
 do_init_module+0x1b5/0x547 kernel/module.c:3456
 load_module+0x6405/0x8c10 kernel/module.c:3804
 __do_sys_finit_module+0x162/0x190 kernel/module.c:3898
 do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x462e99
Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f494ecbcc58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99
RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003
RBP: 00007f494ecbcc70 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f494ecbd6bc
R13: 00000000004bcefa R14: 00000000006f6fb0 R15: 0000000000000004

Allocated by task 5987:
 set_track mm/kasan/common.c:87 [inline]
 __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:497
 kmalloc include/linux/slab.h:545 [inline]
 kzalloc include/linux/slab.h:740 [inline]
 configfs_register_default_group+0x4c/0xc0 fs/configfs/dir.c:1829
 0xffffffffc1bd0023
 do_one_initcall+0xbc/0x47d init/main.c:887
 do_init_module+0x1b5/0x547 kernel/module.c:3456
 load_module+0x6405/0x8c10 kernel/module.c:3804
 __do_sys_finit_module+0x162/0x190 kernel/module.c:3898
 do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 5987:
 set_track mm/kasan/common.c:87 [inline]
 __kasan_slab_free+0x130/0x180 mm/kasan/common.c:459
 slab_free_hook mm/slub.c:1429 [inline]
 slab_free_freelist_hook mm/slub.c:1456 [inline]
 slab_free mm/slub.c:3003 [inline]
 kfree+0xe1/0x270 mm/slub.c:3955
 configfs_register_default_group+0x9a/0xc0 fs/configfs/dir.c:1836
 0xffffffffc1bd0023
 do_one_initcall+0xbc/0x47d init/main.c:887
 do_init_module+0x1b5/0x547 kernel/module.c:3456
 load_module+0x6405/0x8c10 kernel/module.c:3804
 __do_sys_finit_module+0x162/0x190 kernel/module.c:3898
 do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8881ef61ae00
 which belongs to the cache kmalloc-192 of size 192
The buggy address is located 32 bytes inside of
 192-byte region [ffff8881ef61ae00, ffff8881ef61aec0)
The buggy address belongs to the page:
page:ffffea0007bd8680 count:1 mapcount:0 mapping:ffff8881f6c03000 index:0xffff8881ef61a700
flags: 0x2fffc0000000200(slab)
raw: 02fffc0000000200 ffffea0007ca4740 0000000500000005 ffff8881f6c03000
raw: ffff8881ef61a700 000000008010000c 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8881ef61ad00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff8881ef61ad80: 00 00 00 00 00 00 00 00 fc fc fc fc fc fc fc fc
>ffff8881ef61ae00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                               ^
 ffff8881ef61ae80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
 ffff8881ef61af00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

---
 fs/configfs/dir.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

index d2a1a79fa324..d7955dc56737 100644
@@ -1755,12 +1755,19 @@ int configfs_register_group(struct config_group *parent_group,
 
 	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
 	ret = create_default_group(parent_group, group);
-	if (!ret) {
-		spin_lock(&configfs_dirent_lock);
-		configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
-		spin_unlock(&configfs_dirent_lock);
-	}
+	if (ret)
+		goto err_out;
+
+	spin_lock(&configfs_dirent_lock);
+	configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
+	spin_unlock(&configfs_dirent_lock);
+	inode_unlock(d_inode(parent));
+	return 0;
+err_out:
 	inode_unlock(d_inode(parent));
+	mutex_lock(&subsys->su_mutex);
+	unlink_group(group);
+	mutex_unlock(&subsys->su_mutex);
 	return ret;
 }
 EXPORT_SYMBOL(configfs_register_group);

2.20.1

[ Upstream commit 8520ce1e17799b220ff421d4f39438c9c572ade3 ]

The IRQ handler, mmci_irq(), loops until all status bits have been cleared. However, the status bit signaling busy in variant->busy_detect_flag, may be set even if busy detection isn't monitored for the current request.

This may be the case for the CMD11 when switching the I/O voltage, which leads to that mmci_irq() busy loops in IRQ context. Fix this problem, by clearing the status bit for busy, before continuing to validate the condition for the loop. This is safe, because the busy status detection has already been taken care of by mmci_cmd_irq().

---
 drivers/mmc/host/mmci.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index f1f54a818489..77f18729ee96 100644
@@ -1320,9 +1320,10 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 		}
 
 		/*
-		 * Don't poll for busy completion in irq context.
+		 * Busy detection has been handled by mmci_cmd_irq() above.
+		 * Clear the status bit to prevent polling in IRQ context.
 		 */
-		if (host->variant->busy_detect && host->busy_status)
+		if (host->variant->busy_detect_flag)
 			status &= ~host->variant->busy_detect_flag;
 
 		ret = 1;

2.20.1

[ Upstream commit 5e159cd349bf3a31fb7e35c23a93308eb30f4f71 ]

As Jungyeon reported in bugzilla:

https://bugzilla.kernel.org/show_bug.cgi?id=203209

- Overview
When mounting the attached crafted image and running program, I got this error. Additionally, it hangs on sync after the this script.

The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on.

- Reproduces
cc poc_01.c
./run.sh f2fs
sync

kernel BUG at fs/f2fs/f2fs.h:1788!

 RIP: 0010:f2fs_truncate_data_blocks_range+0x342/0x350
 Call Trace:
  f2fs_truncate_blocks+0x36d/0x3c0
  f2fs_truncate+0x88/0x110
  f2fs_setattr+0x3e1/0x460
  notify_change+0x2da/0x400
  do_truncate+0x6d/0xb0
  do_sys_ftruncate+0xf1/0x160
  do_syscall_64+0x43/0xf0
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

The reason is dec_valid_block_count() will trigger kernel panic due to inconsistent count in between inode.i_blocks and actual block.

To avoid panic, let's just print debug message and set SBI_NEED_FSCK to give a hint to fsck for latter repairing.

---
 fs/f2fs/f2fs.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

index 406d93b51a0b..6caae471c1a4 100644
@@ -1550,6 +1550,7 @@ enospc:
 	return -ENOSPC;
 }
 
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 						struct inode *inode,
 						block_t count)

@@ -1558,9 +1559,17 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
+	if (unlikely(inode->i_blocks < sectors)) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu",
+			inode->i_ino,
+			(unsigned long long)inode->i_blocks,
+			(unsigned long long)sectors);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return;
+	}
 	f2fs_i_blocks_write(inode, count, false, true);
 }
 

@@ -2382,7 +2391,6 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
 
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type);
-void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {