diff options
Diffstat (limited to 'arch')
201 files changed, 2253 insertions, 904 deletions
diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4067f5169144..955b0362cdfb 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -132,7 +132,7 @@ AFLAGS_NOWARN :=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W) ifeq ($(CONFIG_THUMB2_KERNEL),y) CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN) -AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2 +AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb CFLAGS_ISA +=-mthumb else CFLAGS_ISA :=$(call cc-option,-marm,) $(AFLAGS_NOWARN) diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 12933eff419f..446861b6b17b 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -304,7 +304,7 @@ }; gpio0: gpio@18100 { - compatible = "marvell,armadaxp-gpio", + compatible = "marvell,armada-370-gpio", "marvell,orion-gpio"; reg = <0x18100 0x40>, <0x181c0 0x08>; reg-names = "gpio", "pwm"; @@ -323,7 +323,7 @@ }; gpio1: gpio@18140 { - compatible = "marvell,armadaxp-gpio", + compatible = "marvell,armada-370-gpio", "marvell,orion-gpio"; reg = <0x18140 0x40>, <0x181c8 0x08>; reg-names = "gpio", "pwm"; diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi index 1e05208d9f34..9d1cac49c022 100644 --- a/arch/arm/boot/dts/armada-39x.dtsi +++ b/arch/arm/boot/dts/armada-39x.dtsi @@ -213,7 +213,7 @@ }; gpio0: gpio@18100 { - compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio"; + compatible = "marvell,orion-gpio"; reg = <0x18100 0x40>; ngpios = <32>; gpio-controller; @@ -227,7 +227,7 @@ }; gpio1: gpio@18140 { - compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio"; + compatible = "marvell,orion-gpio"; reg = <0x18140 0x40>; ngpios = <28>; gpio-controller; diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts index d1971ddf06a5..7f755e5a4624 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts @@ -751,7 +751,7 @@ }; pca9849@75 { - compatible = "nxp,pca849"; + compatible = "nxp,pca9849"; reg = <0x75>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index 37d0cffea99c..70c4a4852256 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -488,7 +488,7 @@ scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; status = "okay"; - i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index 4bc4371e6bae..4b81a975c979 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -632,7 +632,6 @@ &uart1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; - uart-has-rtscts; rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts index 162dc259edc8..5a74c7f68eb6 100644 --- a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/imx7d-pico-dwarf.dts index 5162fe227d1e..fdc10563f147 100644 --- a/arch/arm/boot/dts/imx7d-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx7d-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -52,7 +52,7 @@ }; &i2c4 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-pico-nymph.dts b/arch/arm/boot/dts/imx7d-pico-nymph.dts index 104a85254adb..5afb1674e012 100644 --- a/arch/arm/boot/dts/imx7d-pico-nymph.dts +++ b/arch/arm/boot/dts/imx7d-pico-nymph.dts @@ -43,7 +43,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -64,7 +64,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-smegw01.dts b/arch/arm/boot/dts/imx7d-smegw01.dts index 546268b8d0b1..c0f00f5db11e 100644 --- a/arch/arm/boot/dts/imx7d-smegw01.dts +++ b/arch/arm/boot/dts/imx7d-smegw01.dts @@ -198,6 +198,7 @@ &usbotg2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usbotg2>; + over-current-active-low; dr_mode = "host"; status = "okay"; }; @@ -374,7 +375,7 @@ pinctrl_usbotg2: usbotg2grp { fsl,pins = < - MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x04 + MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x5c >; }; diff --git a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi index b637241316bb..fd671c7a1e5d 100644 --- a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi +++ b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi @@ -480,6 +480,7 @@ reg = <0xc8000000 0x1000>, <0xc0000000 0x4000000>; reg-names = "control", "memory"; clocks = <&clk 0>; + nuvoton,shm = <&shm>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts index 44cd72f1b1be..116e59a3b76d 100644 --- a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts +++ b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts @@ -19,16 +19,16 @@ serial@f995e000 { status = "okay"; }; + }; +}; - sdhci@f9824900 { - bus-width = <8>; - non-removable; - status = "okay"; - }; +&sdhc_1 { + bus-width = <8>; + non-removable; + status = "okay"; +}; - sdhci@f98a4900 { - cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>; - bus-width = <4>; - }; - }; +&sdhc_2 { + cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>; + bus-width = <4>; }; diff --git a/arch/arm/boot/dts/qcom-apq8084.dtsi b/arch/arm/boot/dts/qcom-apq8084.dtsi index fe30abfff90a..4b0d2b4f4b6a 100644 --- a/arch/arm/boot/dts/qcom-apq8084.dtsi +++ b/arch/arm/boot/dts/qcom-apq8084.dtsi @@ -421,7 +421,7 @@ status = "disabled"; }; - mmc@f9824900 { + sdhc_1: mmc@f9824900 { compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4"; reg = <0xf9824900 0x11c>, <0xf9824000 0x800>; reg-names = "hc", "core"; @@ -434,7 +434,7 @@ status = "disabled"; }; - mmc@f98a4900 { + sdhc_2: mmc@f98a4900 { compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4"; reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>; reg-names = "hc", "core"; diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index 8f5477e307dd..37a5d96aaf64 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -564,7 +564,7 @@ mpddrc: mpddrc@ffffe800 { compatible = "microchip,sam9x60-ddramc", "atmel,sama5d3-ddramc"; reg = <0xffffe800 0x200>; - clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_CORE PMC_MCK>; + clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_PERIPHERAL 49>; clock-names = "ddrck", "mpddr"; }; diff --git a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi index d865ab5d866b..dd23de85100c 100644 --- a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi +++ b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi @@ -101,8 +101,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index aef02e6421a3..7d11c50b9e40 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -391,8 +391,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index 002f221f1694..c06edd2eacb0 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -428,8 +428,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 134a798ad3f2..bb40fb46da81 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -247,8 +247,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x200000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index 42ed4a04a12e..6280c5e86a12 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -345,7 +345,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts index f892977da9e4..c00d39562a10 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts @@ -340,7 +340,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index 971e74546fb1..13e62c7c25dc 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -53,7 +53,12 @@ $(obj)/%-core.S: $(src)/%-armv4.pl clean-files += poly1305-core.S sha256-core.S sha512-core.S +aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 + +AFLAGS_sha256-core.o += $(aflags-thumb2-y) +AFLAGS_sha512-core.o += $(aflags-thumb2-y) + # massage the perlasm code a bit so we only get the NEON routine if we need it poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5 poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7 -AFLAGS_poly1305-core.o += $(poly1305-aflags-y) +AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y) diff --git a/arch/arm/mach-footbridge/isa-rtc.c b/arch/arm/mach-footbridge/isa-rtc.c index b8f741a3a37e..237b828dd2f1 100644 --- a/arch/arm/mach-footbridge/isa-rtc.c +++ b/arch/arm/mach-footbridge/isa-rtc.c @@ -20,7 +20,6 @@ #include <linux/init.h> #include <linux/mc146818rtc.h> -#include <linux/bcd.h> #include <linux/io.h> #include "common.h" diff --git a/arch/arm/mach-imx/cpu-imx25.c b/arch/arm/mach-imx/cpu-imx25.c index 3e63445cde06..cc86977d0a34 100644 --- a/arch/arm/mach-imx/cpu-imx25.c +++ b/arch/arm/mach-imx/cpu-imx25.c @@ -23,6 +23,7 @@ static int mx25_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx25-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = readl(iim_base + MXC_IIMSREV); iounmap(iim_base); diff --git a/arch/arm/mach-imx/cpu-imx27.c b/arch/arm/mach-imx/cpu-imx27.c index bf70e13bbe9e..1d2893908368 100644 --- a/arch/arm/mach-imx/cpu-imx27.c +++ b/arch/arm/mach-imx/cpu-imx27.c @@ -28,6 +28,7 @@ static int mx27_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm"); ccm_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!ccm_base); /* * now we have access to the IO registers. As we need diff --git a/arch/arm/mach-imx/cpu-imx31.c b/arch/arm/mach-imx/cpu-imx31.c index b9c24b851d1a..35c544924e50 100644 --- a/arch/arm/mach-imx/cpu-imx31.c +++ b/arch/arm/mach-imx/cpu-imx31.c @@ -39,6 +39,7 @@ static int mx31_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx31-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); /* read SREV register from IIM module */ diff --git a/arch/arm/mach-imx/cpu-imx35.c b/arch/arm/mach-imx/cpu-imx35.c index 80e7d8ab9f1b..1fe75b39c2d9 100644 --- a/arch/arm/mach-imx/cpu-imx35.c +++ b/arch/arm/mach-imx/cpu-imx35.c @@ -21,6 +21,7 @@ static int mx35_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = imx_readl(iim_base + MXC_IIMSREV); diff --git a/arch/arm/mach-imx/cpu-imx5.c b/arch/arm/mach-imx/cpu-imx5.c index ad56263778f9..a67c89bf155d 100644 --- a/arch/arm/mach-imx/cpu-imx5.c +++ b/arch/arm/mach-imx/cpu-imx5.c @@ -28,6 +28,7 @@ static u32 imx5_read_srev_reg(const char *compat) np = of_find_compatible_node(NULL, NULL, compat); iim_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!iim_base); srev = readl(iim_base + IIM_SREV) & 0xff; diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig index 538a960257cc..7ec7ada287e0 100644 --- a/arch/arm/mach-omap1/Kconfig +++ b/arch/arm/mach-omap1/Kconfig @@ -4,6 +4,7 @@ menuconfig ARCH_OMAP1 depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 depends on CPU_LITTLE_ENDIAN depends on ATAGS + select ARCH_OMAP select ARCH_HAS_HOLES_MEMORYMODEL select ARCH_OMAP select CLKSRC_MMIO @@ -45,10 +46,6 @@ config ARCH_OMAP16XX select CPU_ARM926T select OMAP_DM_TIMER -config ARCH_OMAP1_ANY - select ARCH_OMAP - def_bool ARCH_OMAP730 || ARCH_OMAP850 || ARCH_OMAP15XX || ARCH_OMAP16XX - config ARCH_OMAP bool diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile index 506074b86333..0615cb0ba580 100644 --- a/arch/arm/mach-omap1/Makefile +++ b/arch/arm/mach-omap1/Makefile @@ -3,8 +3,6 @@ # Makefile for the linux kernel. # -ifdef CONFIG_ARCH_OMAP1_ANY - # Common support obj-y := io.o id.o sram-init.o sram.o time.o irq.o mux.o flash.o \ serial.o devices.o dma.o omap-dma.o fb.o @@ -59,5 +57,3 @@ obj-$(CONFIG_ARCH_OMAP730) += gpio7xx.o obj-$(CONFIG_ARCH_OMAP850) += gpio7xx.o obj-$(CONFIG_ARCH_OMAP15XX) += gpio15xx.o obj-$(CONFIG_ARCH_OMAP16XX) += gpio16xx.o - -endif diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c index c675f11de99d..61fa26efd865 100644 --- a/arch/arm/mach-omap1/gpio15xx.c +++ b/arch/arm/mach-omap1/gpio15xx.c @@ -11,6 +11,7 @@ #include <linux/gpio.h> #include <linux/platform_data/gpio-omap.h> #include <linux/soc/ti/omap1-soc.h> +#include <asm/irq.h> #include "irqs.h" diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c index d2db9b8aed3f..0074b011a05a 100644 --- a/arch/arm/mach-omap1/io.c +++ b/arch/arm/mach-omap1/io.c @@ -22,17 +22,14 @@ * The machine specific code may provide the extra mapping besides the * default mapping provided here. */ -static struct map_desc omap_io_desc[] __initdata = { +#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) +static struct map_desc omap7xx_io_desc[] __initdata = { { .virtual = OMAP1_IO_VIRT, .pfn = __phys_to_pfn(OMAP1_IO_PHYS), .length = OMAP1_IO_SIZE, .type = MT_DEVICE - } -}; - -#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) -static struct map_desc omap7xx_io_desc[] __initdata = { + }, { .virtual = OMAP7XX_DSP_BASE, .pfn = __phys_to_pfn(OMAP7XX_DSP_START), @@ -50,6 +47,12 @@ static struct map_desc omap7xx_io_desc[] __initdata = { #ifdef CONFIG_ARCH_OMAP15XX static struct map_desc omap1510_io_desc[] __initdata = { { + .virtual = OMAP1_IO_VIRT, + .pfn = __phys_to_pfn(OMAP1_IO_PHYS), + .length = OMAP1_IO_SIZE, + .type = MT_DEVICE + }, + { .virtual = OMAP1510_DSP_BASE, .pfn = __phys_to_pfn(OMAP1510_DSP_START), .length = OMAP1510_DSP_SIZE, @@ -66,6 +69,12 @@ static struct map_desc omap1510_io_desc[] __initdata = { #if defined(CONFIG_ARCH_OMAP16XX) static struct map_desc omap16xx_io_desc[] __initdata = { { + .virtual = OMAP1_IO_VIRT, + .pfn = __phys_to_pfn(OMAP1_IO_PHYS), + .length = OMAP1_IO_SIZE, + .type = MT_DEVICE + }, + { .virtual = OMAP16XX_DSP_BASE, .pfn = __phys_to_pfn(OMAP16XX_DSP_START), .length = OMAP16XX_DSP_SIZE, @@ -79,18 +88,9 @@ static struct map_desc omap16xx_io_desc[] __initdata = { }; #endif -/* - * Maps common IO regions for omap1 - */ -static void __init omap1_map_common_io(void) -{ - iotable_init(omap_io_desc, ARRAY_SIZE(omap_io_desc)); -} - #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) void __init omap7xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap7xx_io_desc, ARRAY_SIZE(omap7xx_io_desc)); } #endif @@ -98,7 +98,6 @@ void __init omap7xx_map_io(void) #ifdef CONFIG_ARCH_OMAP15XX void __init omap15xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap1510_io_desc, ARRAY_SIZE(omap1510_io_desc)); } #endif @@ -106,7 +105,6 @@ void __init omap15xx_map_io(void) #if defined(CONFIG_ARCH_OMAP16XX) void __init omap16xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap16xx_io_desc, ARRAY_SIZE(omap16xx_io_desc)); } #endif diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index 05c25c432449..b1632cbe37e6 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -89,7 +89,6 @@ static struct omap_mcbsp_ops omap1_mcbsp_ops = { #define OMAP1610_MCBSP2_BASE 0xfffb1000 #define OMAP1610_MCBSP3_BASE 0xe1017000 -#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) struct resource omap7xx_mcbsp_res[][6] = { { { @@ -159,14 +158,7 @@ static struct omap_mcbsp_platform_data omap7xx_mcbsp_pdata[] = { }; #define OMAP7XX_MCBSP_RES_SZ ARRAY_SIZE(omap7xx_mcbsp_res[1]) #define OMAP7XX_MCBSP_COUNT ARRAY_SIZE(omap7xx_mcbsp_res) -#else -#define omap7xx_mcbsp_res_0 NULL -#define omap7xx_mcbsp_pdata NULL -#define OMAP7XX_MCBSP_RES_SZ 0 -#define OMAP7XX_MCBSP_COUNT 0 -#endif -#ifdef CONFIG_ARCH_OMAP15XX struct resource omap15xx_mcbsp_res[][6] = { { { @@ -266,14 +258,7 @@ static struct omap_mcbsp_platform_data omap15xx_mcbsp_pdata[] = { }; #define OMAP15XX_MCBSP_RES_SZ ARRAY_SIZE(omap15xx_mcbsp_res[1]) #define OMAP15XX_MCBSP_COUNT ARRAY_SIZE(omap15xx_mcbsp_res) -#else -#define omap15xx_mcbsp_res_0 NULL -#define omap15xx_mcbsp_pdata NULL -#define OMAP15XX_MCBSP_RES_SZ 0 -#define OMAP15XX_MCBSP_COUNT 0 -#endif -#ifdef CONFIG_ARCH_OMAP16XX struct resource omap16xx_mcbsp_res[][6] = { { { @@ -373,12 +358,6 @@ static struct omap_mcbsp_platform_data omap16xx_mcbsp_pdata[] = { }; #define OMAP16XX_MCBSP_RES_SZ ARRAY_SIZE(omap16xx_mcbsp_res[1]) #define OMAP16XX_MCBSP_COUNT ARRAY_SIZE(omap16xx_mcbsp_res) -#else -#define omap16xx_mcbsp_res_0 NULL -#define omap16xx_mcbsp_pdata NULL -#define OMAP16XX_MCBSP_RES_SZ 0 -#define OMAP16XX_MCBSP_COUNT 0 -#endif static void omap_mcbsp_register_board_cfg(struct resource *res, int res_count, struct omap_mcbsp_platform_data *config, int size) diff --git a/arch/arm/mach-omap1/pm.h b/arch/arm/mach-omap1/pm.h index d9165709c532..0d1f092821ff 100644 --- a/arch/arm/mach-omap1/pm.h +++ b/arch/arm/mach-omap1/pm.h @@ -106,13 +106,6 @@ #define OMAP7XX_IDLECT3 0xfffece24 #define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00 -#if !defined(CONFIG_ARCH_OMAP730) && \ - !defined(CONFIG_ARCH_OMAP850) && \ - !defined(CONFIG_ARCH_OMAP15XX) && \ - !defined(CONFIG_ARCH_OMAP16XX) -#warning "Power management for this processor not implemented yet" -#endif - #ifndef __ASSEMBLER__ #include <linux/clk.h> diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index b90d98bae68d..03e25af6f48c 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -45,6 +45,8 @@ config MACH_PXA27X_DT config MACH_PXA3XX_DT bool "Support PXA3xx platforms from device tree" select CPU_PXA300 + select CPU_PXA310 + select CPU_PXA320 select PINCTRL select POWER_SUPPLY select PXA3xx diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c1494a4dee25..53f2d8774fdb 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -161,7 +161,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup(); /* allocate the zero page. */ - zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index fa6999e24b07..e43f6d716b4b 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -6,6 +6,7 @@ * VM_EXEC */ #include <asm/asm-offsets.h> +#include <asm/pgtable.h> #include <asm/thread_info.h> #ifdef CONFIG_CPU_V7M diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 03934808b2ed..c5ccca26a408 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -184,8 +184,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_ERRATUM_2645198 + bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption" + default y + help + This option adds the workaround for ARM Cortex-A715 erratum 2645198. + + If a Cortex-A715 cpu sees a page mapping permissions change from executable + to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the + next instruction abort caused by permission fault. + + Only user-space does executable to non-executable permission transition via + mprotect() system call. Workaround the problem by doing a break-before-make + TLB invalidation, for all changes to executable user space mappings. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts index e3486f60645a..a1f0c38ccadd 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts @@ -131,10 +131,6 @@ }; &usb { - phys = <&usb2_phy1>; - phy-names = "usb2-phy1"; -}; - -&usb2_phy0 { - status = "disabled"; + phys = <&usb2_phy0>, <&usb2_phy1>; + phy-names = "usb2-phy0", "usb2-phy1"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts index 5a8d85a7d161..bbdf989058ff 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts @@ -110,7 +110,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts index 9b726c2a4842..dda27ed7aaf2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts @@ -89,7 +89,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts index b2fcbba60d3a..3b0ed9305f2b 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts @@ -88,7 +88,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts index 41d8b15f25a5..aa52ff73ff9e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts @@ -53,7 +53,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts index 1bfbce69cc8b..ee8e932628d1 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts @@ -136,7 +136,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts index ef6c8967533e..d4867d6cf47c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts @@ -245,7 +245,7 @@ &i2c3 { status = "okay"; - i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9540"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi index f598669e742f..52c5a43b30a0 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi @@ -103,7 +103,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi index 3d9647b3da14..537cecb13dd0 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi @@ -44,7 +44,7 @@ &i2c0 { status = "okay"; - pca9547@75 { + i2c-mux@75 { compatible = "nxp,pca9547"; reg = <0x75>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi index afb455210bd0..d32a52ab00a4 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi @@ -54,7 +54,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi index 0c64b9194621..214f21bd0cb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi @@ -164,7 +164,7 @@ sc_pwrkey: keys { compatible = "fsl,imx8qxp-sc-key", "fsl,imx-sc-key"; - linux,keycode = <KEY_POWER>; + linux,keycodes = <KEY_POWER>; wakeup-source; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi index 03266bd90a06..169f047fbca5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi @@ -120,7 +120,7 @@ &ecspi2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_espi2>; - cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; + cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>; status = "okay"; eeprom@0 { @@ -316,7 +316,7 @@ MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x82 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x82 MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x82 - MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x41 + MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x41 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts index 24f61db33eba..9889319d4f04 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts @@ -88,6 +88,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_watchdog_gpio>; compatible = "linux,wdt-gpio"; + always-running; gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; hw_algo = "level"; /* Reset triggers in 2..3 seconds */ @@ -275,7 +276,7 @@ compatible = "rohm,bd71847"; reg = <0x4b>; #clock-cells = <0>; - clocks = <&clk_xtal32k 0>; + clocks = <&clk_xtal32k>; clock-output-names = "clk-32k-out"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts index 74c09891600f..6357078185ed 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_i2c3>; status = "okay"; - i2cmux@70 { + i2c-mux@70 { compatible = "nxp,pca9540"; reg = <0x70>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index 83c8f715cd90..b1f11098d248 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -602,7 +602,7 @@ #define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0 #define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 -#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0 +#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 #define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 #define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso index 3ea73a6886ff..f6ad1a4b8b66 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso index 2fa635e1c1a8..1f8ea20dfafc 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 244ef8d6cc68..7761d5671cb1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -222,7 +222,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_bten>; cts-gpios = <&gpio5 8 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts index 750a1f07ecb7..64b366e83fa1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts @@ -733,7 +733,6 @@ dtr-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -749,7 +748,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -758,7 +756,6 @@ pinctrl-0 = <&pinctrl_uart4>, <&pinctrl_uart4_gpio>; cts-gpios = <&gpio5 11 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 12 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -771,6 +768,7 @@ &usbotg2 { dr_mode = "host"; vbus-supply = <®_usb2_vbus>; + over-current-active-low; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts index 32872b0b1aaf..e8bc1fccc47b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts @@ -664,7 +664,6 @@ pinctrl-0 = <&pinctrl_uart1>, <&pinctrl_uart1_gpio>; rts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio4 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -681,7 +680,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { @@ -699,7 +697,6 @@ dtr-gpios = <&gpio4 3 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio4 6 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 8ce562246a08..acc2ba8e00a8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -581,7 +581,6 @@ dtr-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi index c2a5c2f7b204..7c3f5c54f040 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi @@ -9,6 +9,7 @@ simple-audio-card,bitclock-master = <&dailink_master>; simple-audio-card,format = "i2s"; simple-audio-card,frame-master = <&dailink_master>; + simple-audio-card,mclk-fs = <256>; simple-audio-card,name = "imx8mm-wm8904"; simple-audio-card,routing = "Headphone Jack", "HPOUTL", diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi index 73cc3fafa018..b2bcd2282170 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi @@ -11,6 +11,7 @@ simple-audio-card,bitclock-master = <&dailink_master>; simple-audio-card,format = "i2s"; simple-audio-card,frame-master = <&dailink_master>; + simple-audio-card,mclk-fs = <256>; simple-audio-card,name = "imx8mm-nau8822"; simple-audio-card,routing = "Headphones", "LHP", diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 0d454e0e2f7c..702d87621bb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -98,6 +98,7 @@ off-on-delay = <500000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_eth>; + regulator-always-on; regulator-boot-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts index b9444e4a3d2d..7c12518dbc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts @@ -643,7 +643,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index d4c7ca16abd0..f2d93437084b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -36,8 +36,8 @@ pcie0_refclk: pcie0-refclk { compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <100000000>; + #clock-cells = <0>; + clock-frequency = <100000000>; }; reg_can1_stby: regulator-can1-stby { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi index 79b290a002c1..ecc4bce6db97 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi @@ -99,7 +99,6 @@ regulators { buck1: BUCK1 { - regulator-compatible = "BUCK1"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <2187500>; regulator-boot-on; @@ -108,7 +107,6 @@ }; buck2: BUCK2 { - regulator-compatible = "BUCK2"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <2187500>; regulator-boot-on; @@ -119,7 +117,6 @@ }; buck4: BUCK4 { - regulator-compatible = "BUCK4"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -127,7 +124,6 @@ }; buck5: BUCK5 { - regulator-compatible = "BUCK5"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -135,7 +131,6 @@ }; buck6: BUCK6 { - regulator-compatible = "BUCK6"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -143,7 +138,6 @@ }; ldo1: LDO1 { - regulator-compatible = "LDO1"; regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -151,7 +145,6 @@ }; ldo2: LDO2 { - regulator-compatible = "LDO2"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <1150000>; regulator-boot-on; @@ -159,7 +152,6 @@ }; ldo3: LDO3 { - regulator-compatible = "LDO3"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -167,13 +159,11 @@ }; ldo4: LDO4 { - regulator-compatible = "LDO4"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <3300000>; }; ldo5: LDO5 { - regulator-compatible = "LDO5"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index ceeca4966fc5..8eb7d5ee38da 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -623,7 +623,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 7a6e6221f421..03034b439c1f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -524,6 +524,7 @@ compatible = "fsl,imx8mp-gpc"; reg = <0x303a0000 0x1000>; interrupt-parent = <&gic>; + interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>; interrupt-controller; #interrupt-cells = <3>; @@ -590,7 +591,7 @@ reg = <IMX8MP_POWER_DOMAIN_MIPI_PHY2>; }; - pgc_hsiomix: power-domains@17 { + pgc_hsiomix: power-domain@17 { #power-domain-cells = <0>; reg = <IMX8MP_POWER_DOMAIN_HSIOMIX>; clocks = <&clk IMX8MP_CLK_HSIO_AXI>, @@ -1297,7 +1298,7 @@ reg = <0x32f10100 0x8>, <0x381f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "hsio", "suspend"; interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>; @@ -1310,9 +1311,9 @@ usb_dwc3_0: usb@38100000 { compatible = "snps,dwc3"; reg = <0x38100000 0x10000>; - clocks = <&clk IMX8MP_CLK_HSIO_AXI>, + clocks = <&clk IMX8MP_CLK_USB_ROOT>, <&clk IMX8MP_CLK_USB_CORE_REF>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "bus_early", "ref", "suspend"; interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>; phys = <&usb3_phy0>, <&usb3_phy0>; @@ -1339,7 +1340,7 @@ reg = <0x32f10108 0x8>, <0x382f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "hsio", "suspend"; interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>; @@ -1352,9 +1353,9 @@ usb_dwc3_1: usb@38200000 { compatible = "snps,dwc3"; reg = <0x38200000 0x10000>; - clocks = <&clk IMX8MP_CLK_HSIO_AXI>, + clocks = <&clk IMX8MP_CLK_USB_ROOT>, <&clk IMX8MP_CLK_USB_CORE_REF>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "bus_early", "ref", "suspend"; interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; phys = <&usb3_phy1>, <&usb3_phy1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts index 9dda2a1554c3..8614c18b5998 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts @@ -133,7 +133,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - i2cmux@70 { + i2c-mux@70 { compatible = "nxp,pca9546"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1_pca9546>; @@ -216,7 +216,7 @@ pinctrl-0 = <&pinctrl_i2c4>; status = "okay"; - pca9546: i2cmux@70 { + pca9546: i2c-mux@70 { compatible = "nxp,pca9546"; reg = <0x70>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts index 5d5aa6537225..6e6182709d22 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts @@ -339,7 +339,7 @@ bus-width = <4>; non-removable; no-sd; - no-emmc; + no-mmc; status = "okay"; brcmf: wifi@1 { @@ -359,7 +359,7 @@ cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; bus-width = <4>; no-sdio; - no-emmc; + no-mmc; disable-wp; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts index 07d8dd8160f6..afa883389456 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts @@ -61,7 +61,7 @@ pinctrl-0 = <&pinctrl_lpi2c1 &pinctrl_ioexp_rst>; status = "okay"; - i2c-switch@71 { + i2c-mux@71 { compatible = "nxp,pca9646", "nxp,pca9546"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index 69786c326db0..27f9a9f33134 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -74,7 +74,7 @@ pinctrl_usdhc1: usdhc1grp { fsl,pins = < - MX93_PAD_SD1_CLK__USDHC1_CLK 0x17fe + MX93_PAD_SD1_CLK__USDHC1_CLK 0x15fe MX93_PAD_SD1_CMD__USDHC1_CMD 0x13fe MX93_PAD_SD1_DATA0__USDHC1_DATA0 0x13fe MX93_PAD_SD1_DATA1__USDHC1_DATA1 0x13fe @@ -84,7 +84,7 @@ MX93_PAD_SD1_DATA5__USDHC1_DATA5 0x13fe MX93_PAD_SD1_DATA6__USDHC1_DATA6 0x13fe MX93_PAD_SD1_DATA7__USDHC1_DATA7 0x13fe - MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x17fe + MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x15fe >; }; @@ -102,7 +102,7 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX93_PAD_SD2_CLK__USDHC2_CLK 0x17fe + MX93_PAD_SD2_CLK__USDHC2_CLK 0x15fe MX93_PAD_SD2_CMD__USDHC2_CMD 0x13fe MX93_PAD_SD2_DATA0__USDHC2_DATA0 0x13fe MX93_PAD_SD2_DATA1__USDHC2_DATA1 0x13fe diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi index 7308f7b6b22c..8bce64069138 100644 --- a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi +++ b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi @@ -98,7 +98,7 @@ uart1: serial@12100 { compatible = "snps,dw-apb-uart"; - reg = <0x11000 0x100>; + reg = <0x12100 0x100>; reg-shift = <2>; interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; reg-io-width = <1>; diff --git a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi index 87c90e93667f..79de9cc395c4 100644 --- a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi @@ -3,6 +3,7 @@ * Copyright (c) 2015, LGE Inc. All rights reserved. * Copyright (c) 2016, The Linux Foundation. All rights reserved. * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com> + * Copyright (c) 2022, Dominik Kobinski <dominikkobinski314@gmail.com> */ /dts-v1/; @@ -51,6 +52,11 @@ reg = <0 0x03400000 0 0x1200000>; no-map; }; + + removed_region: reserved@5000000 { + reg = <0 0x05000000 0 0x2200000>; + no-map; + }; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts index b242c272d2af..fcca1ba94da6 100644 --- a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts +++ b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts @@ -11,6 +11,12 @@ #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/input/gpio-keys.h> +/delete-node/ &adsp_mem; +/delete-node/ &audio_mem; +/delete-node/ &mpss_mem; +/delete-node/ &peripheral_region; +/delete-node/ &rmtfs_mem; + / { model = "Xiaomi Mi 4C"; compatible = "xiaomi,libra", "qcom,msm8992"; @@ -70,25 +76,67 @@ #size-cells = <2>; ranges; - /* This is for getting crash logs using Android downstream kernels */ - ramoops@dfc00000 { - compatible = "ramoops"; - reg = <0x0 0xdfc00000 0x0 0x40000>; - console-size = <0x10000>; - record-size = <0x10000>; - ftrace-size = <0x10000>; - pmsg-size = <0x20000>; + memory_hole: hole@6400000 { + reg = <0 0x06400000 0 0x600000>; + no-map; + }; + + memory_hole2: hole2@6c00000 { + reg = <0 0x06c00000 0 0x2400000>; + no-map; + }; + + mpss_mem: mpss@9000000 { + reg = <0 0x09000000 0 0x5a00000>; + no-map; + }; + + tzapp: tzapp@ea00000 { + reg = <0 0x0ea00000 0 0x1900000>; + no-map; + }; + + mdm_rfsa_mem: mdm-rfsa@ca0b0000 { + reg = <0 0xca0b0000 0 0x10000>; + no-map; + }; + + rmtfs_mem: rmtfs@ca100000 { + compatible = "qcom,rmtfs-mem"; + reg = <0 0xca100000 0 0x180000>; + no-map; + + qcom,client-id = <1>; }; - modem_region: modem_region@9000000 { - reg = <0x0 0x9000000 0x0 0x5a00000>; + audio_mem: audio@cb400000 { + reg = <0 0xcb000000 0 0x400000>; + no-mem; + }; + + qseecom_mem: qseecom@cb400000 { + reg = <0 0xcb400000 0 0x1c00000>; + no-mem; + }; + + adsp_rfsa_mem: adsp-rfsa@cd000000 { + reg = <0 0xcd000000 0 0x10000>; no-map; }; - tzapp: modem_region@ea00000 { - reg = <0x0 0xea00000 0x0 0x1900000>; + sensor_rfsa_mem: sensor-rfsa@cd010000 { + reg = <0 0xcd010000 0 0x10000>; no-map; }; + + ramoops@dfc00000 { + compatible = "ramoops"; + reg = <0 0xdfc00000 0 0x40000>; + console-size = <0x10000>; + record-size = <0x10000>; + ftrace-size = <0x10000>; + pmsg-size = <0x20000>; + }; }; }; @@ -130,11 +178,6 @@ status = "okay"; }; -&peripheral_region { - reg = <0x0 0x7400000 0x0 0x1c00000>; - no-map; -}; - &pm8994_spmi_regulators { VDD_APC0: s8 { regulator-min-microvolt = <680000>; diff --git a/arch/arm64/boot/dts/qcom/msm8992.dtsi b/arch/arm64/boot/dts/qcom/msm8992.dtsi index 10adb4986ef1..02fc3795dbfd 100644 --- a/arch/arm64/boot/dts/qcom/msm8992.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8992.dtsi @@ -37,10 +37,6 @@ compatible = "qcom,rpmcc-msm8992", "qcom,rpmcc"; }; -&tcsr_mutex { - compatible = "qcom,sfpb-mutex"; -}; - &timer { interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, diff --git a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts index 85abff0e9b3f..7b0f62144c3e 100644 --- a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts +++ b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts @@ -9,9 +9,6 @@ #include "msm8994.dtsi" -/* Angler's firmware does not report where the memory is allocated */ -/delete-node/ &cont_splash_mem; - / { model = "Huawei Nexus 6P"; compatible = "huawei,angler", "qcom,msm8994"; @@ -28,6 +25,22 @@ chosen { stdout-path = "serial0:115200n8"; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + tzapp_mem: tzapp@4800000 { + reg = <0 0x04800000 0 0x1900000>; + no-map; + }; + + removed_region: reserved@6300000 { + reg = <0 0x06300000 0 0xD00000>; + no-map; + }; + }; }; &blsp1_uart2 { diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 109c9d2b684d..71cf81a8eb4d 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -10,6 +10,7 @@ #include <dt-bindings/interconnect/qcom,sc8280xp.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/mailbox/qcom-ipcc.h> +#include <dt-bindings/phy/phy-qcom-qmp.h> #include <dt-bindings/power/qcom-rpmpd.h> #include <dt-bindings/soc/qcom,rpmh-rsc.h> #include <dt-bindings/thermal/thermal.h> @@ -762,7 +763,7 @@ <0>, <0>, <0>, - <&usb_0_ssphy>, + <&usb_0_qmpphy QMP_USB43DP_USB3_PIPE_CLK>, <0>, <0>, <0>, @@ -770,7 +771,7 @@ <0>, <0>, <0>, - <&usb_1_ssphy>, + <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>, <0>, <0>, <0>, @@ -1673,42 +1674,26 @@ }; }; - usb_0_qmpphy: phy-wrapper@88ec000 { + usb_0_qmpphy: phy@88eb000 { compatible = "qcom,sc8280xp-qmp-usb43dp-phy"; - reg = <0 0x088ec000 0 0x1e4>, - <0 0x088eb000 0 0x40>, - <0 0x088ed000 0 0x1c8>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x088eb000 0 0x4000>; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB4_EUD_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", "ref", "com_aux", "usb3_pipe"; + + power-domains = <&gcc USB30_PRIM_GDSC>; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, - <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; + <&gcc GCC_USB4_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - power-domains = <&gcc USB30_PRIM_GDSC>; + #clock-cells = <1>; + #phy-cells = <1>; status = "disabled"; - - usb_0_ssphy: usb3-phy@88eb400 { - reg = <0 0x088eb400 0 0x100>, - <0 0x088eb600 0 0x3ec>, - <0 0x088ec400 0 0x364>, - <0 0x088eba00 0 0x100>, - <0 0x088ebc00 0 0x3ec>, - <0 0x088ec200 0 0x18>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb0_phy_pipe_clk_src"; - }; }; usb_1_hsphy: phy@8902000 { @@ -1725,42 +1710,26 @@ status = "disabled"; }; - usb_1_qmpphy: phy-wrapper@8904000 { + usb_1_qmpphy: phy@8903000 { compatible = "qcom,sc8280xp-qmp-usb43dp-phy"; - reg = <0 0x08904000 0 0x1e4>, - <0 0x08903000 0 0x40>, - <0 0x08905000 0 0x1c8>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x08903000 0 0x4000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB4_CLKREF_CLK>, - <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "ref", "com_aux"; + <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; + clock-names = "aux", "ref", "com_aux", "usb3_pipe"; + + power-domains = <&gcc USB30_SEC_GDSC>; resets = <&gcc GCC_USB3_PHY_SEC_BCR>, <&gcc GCC_USB4_1_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - power-domains = <&gcc USB30_SEC_GDSC>; + #clock-cells = <1>; + #phy-cells = <1>; status = "disabled"; - - usb_1_ssphy: usb3-phy@8903400 { - reg = <0 0x08903400 0 0x100>, - <0 0x08903600 0 0x3ec>, - <0 0x08904400 0 0x364>, - <0 0x08903a00 0 0x100>, - <0 0x08903c00 0 0x3ec>, - <0 0x08904200 0 0x18>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb1_phy_pipe_clk_src"; - }; }; pmu@9091000 { @@ -1910,7 +1879,7 @@ reg = <0 0x0a600000 0 0xcd00>; interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>; iommus = <&apps_smmu 0x820 0x0>; - phys = <&usb_0_hsphy>, <&usb_0_ssphy>; + phys = <&usb_0_hsphy>, <&usb_0_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -1964,7 +1933,7 @@ reg = <0 0x0a800000 0 0xcd00>; interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>; iommus = <&apps_smmu 0x860 0x0>; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index dab5579946f3..927032863e2f 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -334,7 +334,6 @@ exit-latency-us = <6562>; min-residency-us = <9987>; local-timer-stop; - status = "disabled"; }; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 245dce24ec59..fb3cd20a82b5 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -2382,8 +2382,8 @@ <&rpmhcc RPMH_CXO_CLK>; clock-names = "iface", "core", "xo"; resets = <&gcc GCC_SDCC2_BCR>; - interconnects = <&aggre2_noc MASTER_SDCC_2 0 &mc_virt SLAVE_EBI1 0>, - <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_SDCC_2 0>; + interconnects = <&aggre2_noc MASTER_SDCC_2 &mc_virt SLAVE_EBI1>, + <&gem_noc MASTER_APPSS_PROC &config_noc SLAVE_SDCC_2>; interconnect-names = "sdhc-ddr","cpu-sdhc"; iommus = <&apps_smmu 0x4a0 0x0>; power-domains = <&rpmhpd SM8350_CX>; diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 0890e4f568fb..cbb3d961123b 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ "2:" \ - : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ + : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 52075e93de6c..a94d6dacc029 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \ " eor %[old2], %[old2], %[oldval2]\n" \ " orr %[old1], %[old1], %[old2]" \ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ - [v] "+Q" (*(unsigned long *)ptr) \ + [v] "+Q" (*(__uint128_t *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ : cl); \ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 31d13a6001df..de4ff90785b2 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -48,8 +48,17 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); }) extern spinlock_t efi_rt_lock; +extern u64 *efi_rt_stack_top; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); +/* + * efi_rt_stack_top[-1] contains the value the stack pointer had before + * switching to the EFI runtime stack. + */ +#define current_in_efi() \ + (!preemptible() && efi_rt_stack_top != NULL && \ + on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1)) + #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) /* diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index d20f5da2d76f..6a4a1ab8eb23 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep); void __init arm64_hugetlb_cma_reserve(void); +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); + #include <asm-generic/hugetlb.h> #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b4bbeed80fb6..65e78999c75d 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) - +#define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) { @@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #else #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) +#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL @@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte) static inline bool pmd_user_accessible_page(pmd_t pmd) { - return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); + return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { - return pud_leaf(pud) && pud_user(pud); + return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif @@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void) } +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +#define ptep_modify_prot_start ptep_modify_prot_start +extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define ptep_modify_prot_commit ptep_modify_prot_commit +extern void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 4e5354beafb0..66ec8caa6ac0 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -106,4 +106,19 @@ static inline struct stack_info stackinfo_get_sdei_critical(void) #define stackinfo_get_sdei_critical() stackinfo_get_unknown() #endif +#ifdef CONFIG_EFI +extern u64 *efi_rt_stack_top; + +static inline struct stack_info stackinfo_get_efi(void) +{ + unsigned long high = (u64)efi_rt_stack_top; + unsigned long low = high - THREAD_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; +} +#endif + #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index ba4bff5ca674..2b09495499c6 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -16,7 +16,7 @@ #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES -typedef u32 uprobe_opcode_t; +typedef __le32 uprobe_opcode_t; struct arch_uprobe_task { }; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 89ac00084f38..307faa2b4395 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2645198 + { + .desc = "ARM erratum 2645198", + .capability = ARM64_WORKAROUND_2645198, + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2077057 { .desc = "ARM erratum 2077057", diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index a00886410537..e8ae803662cf 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -4,6 +4,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> SYM_FUNC_START(__efi_rt_asm_wrapper) stp x29, x30, [sp, #-112]! @@ -45,7 +46,10 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x4, x6 blr x8 + mov x16, sp mov sp, x29 + str xzr, [x16, #8] // clear recorded task SP value + ldp x1, x2, [sp, #16] cmp x2, x18 ldp x29, x30, [sp], #112 @@ -70,6 +74,9 @@ SYM_FUNC_END(__efi_rt_asm_wrapper) SYM_CODE_START(__efi_rt_asm_recover) mov sp, x30 + ldr_l x16, efi_rt_stack_top // clear recorded task SP value + str xzr, [x16, #-8] + ldp x19, x20, [sp, #32] ldp x21, x22, [sp, #48] ldp x23, x24, [sp, #64] diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index fab05de2e12d..b273900f4566 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <asm/efi.h> +#include <asm/stacktrace.h> static bool region_is_misaligned(const efi_memory_desc_t *md) { @@ -154,7 +155,7 @@ asmlinkage efi_status_t __efi_rt_asm_recover(void); bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) { /* Check whether the exception occurred while running the firmware */ - if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64) + if (!current_in_efi() || regs->pc >= TASK_SIZE_64) return false; pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 353009d7f307..2e94d20c4ac7 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,28 +8,27 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(cprm, i, m) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ - if (vma->vm_flags & VM_MTE) + for (i = 0, m = cprm->vma_meta; \ + i < cprm->vma_count; \ + i++, m = cprm->vma_meta + i) \ + if (m->flags & VM_MTE) -static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) +static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m) { - if (vma->vm_flags & VM_DONTDUMP) - return 0; - - return vma_pages(vma) * MTE_PAGE_TAG_STORAGE; + return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE; } /* Derived from dump_user_range(); start/end must be page-aligned */ static int mte_dump_tag_range(struct coredump_params *cprm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long len) { int ret = 1; unsigned long addr; void *tags = NULL; - for (addr = start; addr < end; addr += PAGE_SIZE) { + for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page = get_dump_page(addr); /* @@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm, mte_save_page_tags(page_address(page), tags); put_page(page); if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { - mte_free_tag_storage(tags); ret = 0; break; } @@ -77,13 +75,13 @@ static int mte_dump_tag_range(struct coredump_params *cprm, return ret; } -Elf_Half elf_core_extra_phdrs(void) +Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(cprm, i, m) vma_count++; return vma_count; @@ -91,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); + int i; + struct core_vma_metadata *m; - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(cprm, i, m) { struct elf_phdr phdr; phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; - phdr.p_vaddr = vma->vm_start; + phdr.p_vaddr = m->start; phdr.p_paddr = 0; - phdr.p_filesz = mte_vma_tag_dump_size(vma); - phdr.p_memsz = vma->vm_end - vma->vm_start; + phdr.p_filesz = mte_vma_tag_dump_size(m); + phdr.p_memsz = m->end - m->start; offset += phdr.p_filesz; phdr.p_flags = 0; phdr.p_align = 0; @@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) - data_size += mte_vma_tag_dump_size(vma); + for_each_mte_vma(cprm, i, m) + data_size += mte_vma_tag_dump_size(m); return data_size; } int elf_core_write_extra_data(struct coredump_params *cprm) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - - for_each_mte_vma(vmi, vma) { - if (vma->vm_flags & VM_DONTDUMP) - continue; + int i; + struct core_vma_metadata *m; - if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end)) + for_each_mte_vma(cprm, i, m) { + if (!mte_dump_tag_range(cprm, m->start, m->dump_size)) return 0; } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index dcc81e7200d4..b6ef1af0122e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -385,7 +385,7 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 2686ab157601..0c321ad23cd3 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1357,7 +1357,7 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif -#ifdef CONFIG_ARM64_SVE +#ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, #endif diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e0d09bf5b01b..be279fd48248 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -281,7 +281,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) vl = task_get_sme_vl(current); } else { - if (!system_supports_sve()) + /* + * A SME only system use SVE for streaming mode so can + * have a SVE formatted context with a zero VL and no + * payload data. + */ + if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; vl = task_get_sve_vl(current); @@ -732,7 +737,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; if (add_all || test_thread_flag(TIF_SVE) || diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 117e2c180f3c..83154303e682 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> +#include <linux/efi.h> #include <linux/export.h> #include <linux/ftrace.h> #include <linux/sched.h> @@ -12,6 +13,7 @@ #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <asm/efi.h> #include <asm/irq.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -186,6 +188,13 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) : stackinfo_get_unknown(); \ }) +#define STACKINFO_EFI \ + ({ \ + ((task == current) && current_in_efi()) \ + ? stackinfo_get_efi() \ + : stackinfo_get_unknown(); \ + }) + noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) @@ -200,6 +209,9 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, STACKINFO_SDEI(normal), STACKINFO_SDEI(critical), #endif +#ifdef CONFIG_EFI + STACKINFO_EFI, +#endif }; struct unwind_state state = { .stacks = stacks, diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5626ddb540ce..cf4c495a4321 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -1079,7 +1079,7 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, /* uaccess failed, don't leave stale tags */ if (num_tags != MTE_GRANULES_PER_PAGE) - mte_clear_page_tags(page); + mte_clear_page_tags(maddr); set_page_mte_tagged(page); kvm_release_pfn_dirty(pfn); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 94a666dd1443..2642e9ce2819 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2187,7 +2187,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); + return vgic_write_guest_lock(kvm, gpa, &val, ite_esz); } /** @@ -2339,7 +2339,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); + return vgic_write_guest_lock(kvm, ptr, &val, dte_esz); } /** @@ -2526,7 +2526,7 @@ static int vgic_its_save_cte(struct vgic_its *its, ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); - return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); + return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz); } /* @@ -2607,7 +2607,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) */ val = 0; BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); + ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } @@ -2743,7 +2743,6 @@ static int vgic_its_has_attr(struct kvm_device *dev, static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); - struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ @@ -2763,9 +2762,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: - dist->save_its_tables_in_progress = true; ret = abi->save_tables(its); - dist->save_its_tables_in_progress = false; break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); @@ -2792,7 +2789,7 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - return dist->save_its_tables_in_progress; + return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 2074521d4a8c..684bdfaad4a9 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -339,7 +339,7 @@ retry: if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } @@ -350,26 +350,23 @@ retry: * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ -static void unmap_all_vpes(struct vgic_dist *dist) +static void unmap_all_vpes(struct kvm *kvm) { - struct irq_desc *desc; + struct vgic_dist *dist = &kvm->arch.vgic; int i; - for (i = 0; i < dist->its_vm.nr_vpes; i++) { - desc = irq_to_desc(dist->its_vm.vpes[i]->irq); - irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); - } + for (i = 0; i < dist->its_vm.nr_vpes; i++) + free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } -static void map_all_vpes(struct vgic_dist *dist) +static void map_all_vpes(struct kvm *kvm) { - struct irq_desc *desc; + struct vgic_dist *dist = &kvm->arch.vgic; int i; - for (i = 0; i < dist->its_vm.nr_vpes; i++) { - desc = irq_to_desc(dist->its_vm.vpes[i]->irq); - irq_domain_activate_irq(irq_desc_get_irq_data(desc), false); - } + for (i = 0; i < dist->its_vm.nr_vpes; i++) + WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), + dist->its_vm.vpes[i]->irq)); } /** @@ -394,7 +391,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { - unmap_all_vpes(dist); + unmap_all_vpes(kvm); vlpi_avail = true; } @@ -437,14 +434,14 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) else val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) - map_all_vpes(dist); + map_all_vpes(kvm); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index ad06ba6c9b00..a413718be92b 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -222,6 +222,11 @@ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) *val = !!(*ptr & mask); } +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) +{ + return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); +} + /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized @@ -283,8 +288,7 @@ int vgic_v4_init(struct kvm *kvm) irq_flags &= ~IRQ_NOAUTOEN; irq_set_status_flags(irq, irq_flags); - ret = request_irq(irq, vgic_v4_doorbell_handler, - 0, "vcpu", vcpu); + ret = vgic_v4_request_vpe_irq(vcpu, irq); if (ret) { kvm_err("failed to allocate vcpu IRQ%d\n", irq); /* diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 0c8da72953f0..7f7f3c5ed85a 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -6,6 +6,7 @@ #define __KVM_ARM_VGIC_NEW_H__ #include <linux/irqchip/arm-gic-common.h> +#include <asm/kvm_mmu.h> #define PRODUCT_ID_KVM 0x4b /* ASCII code K */ #define IMPLEMENTER_ARM 0x43b @@ -131,6 +132,19 @@ static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) return vgic_irq_get_lr_count(irq) > 1; } +static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret; + + dist->table_write_in_progress = true; + ret = kvm_write_guest_lock(kvm, gpa, data, len); + dist->table_write_in_progress = false; + + return ret; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC @@ -331,5 +345,6 @@ int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); #endif diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..95364e8bdc19 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return huge_ptep_clear_flush(vma, addr, ptep); + } + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 14c87e8d69d8..d77c9f56b7b4 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void) } early_initcall(prevent_bootmem_remove_init); #endif + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); + } + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index a86ee376920a..dfeb2c51e257 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,6 +71,7 @@ WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 +WORKAROUND_2645198 WORKAROUND_2658417 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c index 94680521fbf9..8895df121540 100644 --- a/arch/ia64/kernel/elfcore.c +++ b/arch/ia64/kernel/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf64_Half elf_core_extra_phdrs(void) +Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return GATE_EHDR->e_phnum; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { const struct elf_phdr *const gate_phdrs = (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index f6a502e8f02c..6e948d015332 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u asmlinkage long ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp) { + struct timespec64 rtn_tp; + s64 tick_ns; + /* * ia64's clock_gettime() syscall is implemented as a vdso call * fsys_clock_gettime(). Currently it handles only @@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user * switch (which_clock) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: - s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); - struct timespec64 rtn_tp = ns_to_timespec64(tick_ns); + tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); + rtn_tp = ns_to_timespec64(tick_ns); return put_timespec64(&rtn_tp, tp); } diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 90f9d3399b2a..3418d32d4fc7 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -10,8 +10,6 @@ #define FTRACE_REGS_PLT_IDX 1 #define NR_FTRACE_PLTS 2 -#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1])) - #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index c00e1512d4fa..7eedd83fd0d7 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -377,14 +377,6 @@ static inline bool unsigned_imm_check(unsigned long val, unsigned int bit) return val < (1UL << bit); } -static inline unsigned long sign_extend(unsigned long val, unsigned int idx) -{ - if (!is_imm_negative(val, idx + 1)) - return ((1UL << idx) - 1) & val; - else - return ~((1UL << idx) - 1) | val; -} - #define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ int offset) \ @@ -401,6 +393,7 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \ } DEF_EMIT_REG0I26_FORMAT(b, b_op) +DEF_EMIT_REG0I26_FORMAT(bl, bl_op) #define DEF_EMIT_REG1I20_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h index f2b52b9ea93d..b9dce87afd2e 100644 --- a/arch/loongarch/include/asm/unwind.h +++ b/arch/loongarch/include/asm/unwind.h @@ -8,7 +8,9 @@ #define _ASM_UNWIND_H #include <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> #include <asm/stacktrace.h> enum unwinder_type { @@ -20,11 +22,13 @@ struct unwind_state { char type; /* UNWINDER_XXX */ struct stack_info stack_info; struct task_struct *task; - bool first, error, is_ftrace; + bool first, error, reset; int graph_idx; unsigned long sp, pc, ra; }; +bool default_next_frame(struct unwind_state *state); + void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs); bool unwind_next_frame(struct unwind_state *state); @@ -40,4 +44,39 @@ static inline bool unwind_error(struct unwind_state *state) return state->error; } +#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1])) + +static inline unsigned long unwind_graph_addr(struct unwind_state *state, + unsigned long pc, unsigned long cfa) +{ + return ftrace_graph_ret_addr(state->task, &state->graph_idx, + pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET)); +} + +static __always_inline void __unwind_start(struct unwind_state *state, + struct task_struct *task, struct pt_regs *regs) +{ + memset(state, 0, sizeof(*state)); + if (regs) { + state->sp = regs->regs[3]; + state->pc = regs->csr_era; + state->ra = regs->regs[1]; + } else if (task && task != current) { + state->sp = thread_saved_fp(task); + state->pc = thread_saved_ra(task); + state->ra = 0; + } else { + state->sp = (unsigned long)__builtin_frame_address(0); + state->pc = (unsigned long)__builtin_return_address(0); + state->ra = 0; + } + state->task = task; + get_stack_info(state->sp, state->task, &state->stack_info); + state->pc = unwind_graph_addr(state, state->pc, state->sp); +} + +static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state) +{ + return unwind_done(state) ? 0 : state->pc; +} #endif /* _ASM_UNWIND_H */ diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index fcaa024a685e..c8cfbd562921 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -8,7 +8,7 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unaligned.o + alternative.o unaligned.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c index c5aebeac960b..4ad13847e962 100644 --- a/arch/loongarch/kernel/alternative.c +++ b/arch/loongarch/kernel/alternative.c @@ -74,7 +74,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, switch (src->reg0i26_format.opcode) { case b_op: case bl_op: - jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27); + jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 27); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; @@ -93,7 +93,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, fallthrough; case beqz_op: case bnez_op: - jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22); + jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 22); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; @@ -112,7 +112,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, case bge_op: case bltu_op: case bgeu_op: - jump_addr = cur_pc + sign_extend(si << 2, 17); + jump_addr = cur_pc + sign_extend64(si << 2, 17); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 255a09876ef2..3a3fce2d7846 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -94,7 +94,7 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; - elf_hwcap |= HWCAP_LOONGARCH_CRC32; + elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32; config = read_cpucfg(LOONGARCH_CPUCFG1); if (config & CPUCFG1_UAL) { diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 75e5be807a0d..7e5c293ed89f 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -67,14 +67,17 @@ SYM_FUNC_END(except_vec_cex) .macro BUILD_HANDLER exception handler prep .align 5 SYM_FUNC_START(handle_\exception) + 666: BACKUP_T0T1 SAVE_ALL build_prep_\prep move a0, sp la.abs t0, do_\handler jirl ra, t0, 0 + 668: RESTORE_ALL_AND_RET SYM_FUNC_END(handle_\exception) + SYM_DATA(unwind_hint_\exception, .word 668b - 666b) .endm BUILD_HANDLER ade ade badv diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 512579d79b22..badc59087042 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -58,7 +58,6 @@ u32 larch_insn_gen_nop(void) u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) { long offset = dest - pc; - unsigned int immediate_l, immediate_h; union loongarch_instruction insn; if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { @@ -66,15 +65,7 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) return INSN_BREAK; } - offset >>= 2; - - immediate_l = offset & 0xffff; - offset >>= 16; - immediate_h = offset & 0x3ff; - - insn.reg0i26_format.opcode = b_op; - insn.reg0i26_format.immediate_l = immediate_l; - insn.reg0i26_format.immediate_h = immediate_h; + emit_b(&insn, offset >> 2); return insn.word; } @@ -82,7 +73,6 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest) { long offset = dest - pc; - unsigned int immediate_l, immediate_h; union loongarch_instruction insn; if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { @@ -90,15 +80,7 @@ u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest) return INSN_BREAK; } - offset >>= 2; - - immediate_l = offset & 0xffff; - offset >>= 16; - immediate_h = offset & 0x3ff; - - insn.reg0i26_format.opcode = bl_op; - insn.reg0i26_format.immediate_l = immediate_l; - insn.reg0i26_format.immediate_h = immediate_h; + emit_bl(&insn, offset >> 2); return insn.word; } @@ -107,10 +89,7 @@ u32 larch_insn_gen_or(enum loongarch_gpr rd, enum loongarch_gpr rj, enum loongar { union loongarch_instruction insn; - insn.reg3_format.opcode = or_op; - insn.reg3_format.rd = rd; - insn.reg3_format.rj = rj; - insn.reg3_format.rk = rk; + emit_or(&insn, rd, rj, rk); return insn.word; } @@ -124,9 +103,7 @@ u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm) { union loongarch_instruction insn; - insn.reg1i20_format.opcode = lu12iw_op; - insn.reg1i20_format.rd = rd; - insn.reg1i20_format.immediate = imm; + emit_lu12iw(&insn, rd, imm); return insn.word; } @@ -135,9 +112,7 @@ u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm) { union loongarch_instruction insn; - insn.reg1i20_format.opcode = lu32id_op; - insn.reg1i20_format.rd = rd; - insn.reg1i20_format.immediate = imm; + emit_lu32id(&insn, rd, imm); return insn.word; } @@ -146,10 +121,7 @@ u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) { union loongarch_instruction insn; - insn.reg2i12_format.opcode = lu52id_op; - insn.reg2i12_format.rd = rd; - insn.reg2i12_format.rj = rj; - insn.reg2i12_format.immediate = imm; + emit_lu52id(&insn, rd, rj, imm); return insn.word; } @@ -158,10 +130,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, unsigned l { union loongarch_instruction insn; - insn.reg2i16_format.opcode = jirl_op; - insn.reg2i16_format.rd = rd; - insn.reg2i16_format.rj = rj; - insn.reg2i16_format.immediate = (dest - pc) >> 2; + emit_jirl(&insn, rj, rd, (dest - pc) >> 2); return insn.word; } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index c583b1ef1f44..edfd220a3737 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -191,20 +191,14 @@ out: unsigned long __get_wchan(struct task_struct *task) { - unsigned long pc; + unsigned long pc = 0; struct unwind_state state; if (!try_get_task_stack(task)) return 0; - unwind_start(&state, task, NULL); - state.sp = thread_saved_fp(task); - get_stack_info(state.sp, state.task, &state.stack_info); - state.pc = thread_saved_ra(task); -#ifdef CONFIG_UNWINDER_PROLOGUE - state.type = UNWINDER_PROLOGUE; -#endif - for (; !unwind_done(&state); unwind_next_frame(&state)) { + for (unwind_start(&state, task, NULL); + !unwind_done(&state); unwind_next_frame(&state)) { pc = unwind_get_return_address(&state); if (!pc) break; diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 7ea62faeeadb..c38a146a973b 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -72,9 +72,6 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs, if (!task) task = current; - if (user_mode(regs)) - state.type = UNWINDER_GUESS; - printk("%sCall Trace:", loglvl); for (unwind_start(&state, task, pregs); !unwind_done(&state); unwind_next_frame(&state)) { diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c new file mode 100644 index 000000000000..a463d6961344 --- /dev/null +++ b/arch/loongarch/kernel/unwind.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#include <linux/kernel.h> +#include <linux/ftrace.h> + +#include <asm/unwind.h> + +bool default_next_frame(struct unwind_state *state) +{ + struct stack_info *info = &state->stack_info; + unsigned long addr; + + if (unwind_done(state)) + return false; + + do { + for (state->sp += sizeof(unsigned long); + state->sp < info->end; state->sp += sizeof(unsigned long)) { + addr = *(unsigned long *)(state->sp); + state->pc = unwind_graph_addr(state, addr, state->sp + 8); + if (__kernel_text_address(state->pc)) + return true; + } + + state->sp = info->next_sp; + + } while (!get_stack_info(state->sp, state->task, info)); + + return false; +} diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c index e2d2e4f3001f..98379b7d4147 100644 --- a/arch/loongarch/kernel/unwind_guess.c +++ b/arch/loongarch/kernel/unwind_guess.c @@ -2,37 +2,18 @@ /* * Copyright (C) 2022 Loongson Technology Corporation Limited */ -#include <linux/kernel.h> -#include <linux/ftrace.h> - #include <asm/unwind.h> unsigned long unwind_get_return_address(struct unwind_state *state) { - if (unwind_done(state)) - return 0; - else if (state->first) - return state->pc; - - return *(unsigned long *)(state->sp); + return __unwind_get_return_address(state); } EXPORT_SYMBOL_GPL(unwind_get_return_address); void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs) { - memset(state, 0, sizeof(*state)); - - if (regs) { - state->sp = regs->regs[3]; - state->pc = regs->csr_era; - } - - state->task = task; - state->first = true; - - get_stack_info(state->sp, state->task, &state->stack_info); - + __unwind_start(state, task, regs); if (!unwind_done(state) && !__kernel_text_address(state->pc)) unwind_next_frame(state); } @@ -40,30 +21,6 @@ EXPORT_SYMBOL_GPL(unwind_start); bool unwind_next_frame(struct unwind_state *state) { - struct stack_info *info = &state->stack_info; - unsigned long addr; - - if (unwind_done(state)) - return false; - - if (state->first) - state->first = false; - - do { - for (state->sp += sizeof(unsigned long); - state->sp < info->end; - state->sp += sizeof(unsigned long)) { - addr = *(unsigned long *)(state->sp); - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - if (__kernel_text_address(addr)) - return true; - } - - state->sp = info->next_sp; - - } while (!get_stack_info(state->sp, state->task, info)); - - return false; + return default_next_frame(state); } EXPORT_SYMBOL_GPL(unwind_next_frame); diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 0f8d1451ebb8..9095fde8e55d 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -2,61 +2,116 @@ /* * Copyright (C) 2022 Loongson Technology Corporation Limited */ +#include <linux/cpumask.h> #include <linux/ftrace.h> #include <linux/kallsyms.h> #include <asm/inst.h> +#include <asm/loongson.h> #include <asm/ptrace.h> +#include <asm/setup.h> #include <asm/unwind.h> -static inline void unwind_state_fixup(struct unwind_state *state) -{ -#ifdef CONFIG_DYNAMIC_FTRACE - static unsigned long ftrace = (unsigned long)ftrace_call + 4; - - if (state->pc == ftrace) - state->is_ftrace = true; +extern const int unwind_hint_ade; +extern const int unwind_hint_ale; +extern const int unwind_hint_bp; +extern const int unwind_hint_fpe; +extern const int unwind_hint_fpu; +extern const int unwind_hint_lsx; +extern const int unwind_hint_lasx; +extern const int unwind_hint_lbt; +extern const int unwind_hint_ri; +extern const int unwind_hint_watch; +extern unsigned long eentry; +#ifdef CONFIG_NUMA +extern unsigned long pcpu_handlers[NR_CPUS]; #endif -} -unsigned long unwind_get_return_address(struct unwind_state *state) +static inline bool scan_handlers(unsigned long entry_offset) { + int idx, offset; - if (unwind_done(state)) - return 0; - else if (state->type) - return state->pc; - else if (state->first) - return state->pc; - - return *(unsigned long *)(state->sp); + if (entry_offset >= EXCCODE_INT_START * VECSIZE) + return false; + idx = entry_offset / VECSIZE; + offset = entry_offset % VECSIZE; + switch (idx) { + case EXCCODE_ADE: + return offset == unwind_hint_ade; + case EXCCODE_ALE: + return offset == unwind_hint_ale; + case EXCCODE_BP: + return offset == unwind_hint_bp; + case EXCCODE_FPE: + return offset == unwind_hint_fpe; + case EXCCODE_FPDIS: + return offset == unwind_hint_fpu; + case EXCCODE_LSXDIS: + return offset == unwind_hint_lsx; + case EXCCODE_LASXDIS: + return offset == unwind_hint_lasx; + case EXCCODE_BTDIS: + return offset == unwind_hint_lbt; + case EXCCODE_INE: + return offset == unwind_hint_ri; + case EXCCODE_WATCH: + return offset == unwind_hint_watch; + default: + return false; + } } -EXPORT_SYMBOL_GPL(unwind_get_return_address); -static bool unwind_by_guess(struct unwind_state *state) +static inline bool fix_exception(unsigned long pc) { - struct stack_info *info = &state->stack_info; - unsigned long addr; - - for (state->sp += sizeof(unsigned long); - state->sp < info->end; - state->sp += sizeof(unsigned long)) { - addr = *(unsigned long *)(state->sp); - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - if (__kernel_text_address(addr)) +#ifdef CONFIG_NUMA + int cpu; + + for_each_possible_cpu(cpu) { + if (!pcpu_handlers[cpu]) + continue; + if (scan_handlers(pc - pcpu_handlers[cpu])) return true; } +#endif + return scan_handlers(pc - eentry); +} +/* + * As we meet ftrace_regs_entry, reset first flag like first doing + * tracing. Prologue analysis will stop soon because PC is at entry. + */ +static inline bool fix_ftrace(unsigned long pc) +{ +#ifdef CONFIG_DYNAMIC_FTRACE + return pc == (unsigned long)ftrace_call + LOONGARCH_INSN_SIZE; +#else return false; +#endif } +static inline bool unwind_state_fixup(struct unwind_state *state) +{ + if (!fix_exception(state->pc) && !fix_ftrace(state->pc)) + return false; + + state->reset = true; + return true; +} + +/* + * LoongArch function prologue is like follows, + * [instructions not use stack var] + * addi.d sp, sp, -imm + * st.d xx, sp, offset <- save callee saved regs and + * st.d yy, sp, offset save ra if function is nest. + * [others instructions] + */ static bool unwind_by_prologue(struct unwind_state *state) { long frame_ra = -1; unsigned long frame_size = 0; - unsigned long size, offset, pc = state->pc; + unsigned long size, offset, pc; struct pt_regs *regs; struct stack_info *info = &state->stack_info; union loongarch_instruction *ip, *ip_end; @@ -64,20 +119,21 @@ static bool unwind_by_prologue(struct unwind_state *state) if (state->sp >= info->end || state->sp < info->begin) return false; - if (state->is_ftrace) { - /* - * As we meet ftrace_regs_entry, reset first flag like first doing - * tracing. Prologue analysis will stop soon because PC is at entry. - */ + if (state->reset) { regs = (struct pt_regs *)state->sp; state->first = true; - state->is_ftrace = false; + state->reset = false; state->pc = regs->csr_era; state->ra = regs->regs[1]; state->sp = regs->regs[3]; return true; } + /* + * When first is not set, the PC is a return address in the previous frame. + * We need to adjust its value in case overflow to the next symbol. + */ + pc = state->pc - (state->first ? 0 : LOONGARCH_INSN_SIZE); if (!kallsyms_lookup_size_offset(pc, &size, &offset)) return false; @@ -93,6 +149,10 @@ static bool unwind_by_prologue(struct unwind_state *state) ip++; } + /* + * Can't find stack alloc action, PC may be in a leaf function. Only the + * first being true is reasonable, otherwise indicate analysis is broken. + */ if (!frame_size) { if (state->first) goto first; @@ -110,6 +170,7 @@ static bool unwind_by_prologue(struct unwind_state *state) ip++; } + /* Can't find save $ra action, PC may be in a leaf function, too. */ if (frame_ra < 0) { if (state->first) { state->sp = state->sp + frame_size; @@ -118,88 +179,47 @@ static bool unwind_by_prologue(struct unwind_state *state) return false; } - if (state->first) - state->first = false; - state->pc = *(unsigned long *)(state->sp + frame_ra); state->sp = state->sp + frame_size; goto out; first: - state->first = false; - if (state->pc == state->ra) - return false; - state->pc = state->ra; out: - unwind_state_fixup(state); - return !!__kernel_text_address(state->pc); -} - -void unwind_start(struct unwind_state *state, struct task_struct *task, - struct pt_regs *regs) -{ - memset(state, 0, sizeof(*state)); - - if (regs && __kernel_text_address(regs->csr_era)) { - state->pc = regs->csr_era; - state->sp = regs->regs[3]; - state->ra = regs->regs[1]; - state->type = UNWINDER_PROLOGUE; - } - - state->task = task; - state->first = true; - - get_stack_info(state->sp, state->task, &state->stack_info); - - if (!unwind_done(state) && !__kernel_text_address(state->pc)) - unwind_next_frame(state); + state->first = false; + return unwind_state_fixup(state) || __kernel_text_address(state->pc); } -EXPORT_SYMBOL_GPL(unwind_start); -bool unwind_next_frame(struct unwind_state *state) +static bool next_frame(struct unwind_state *state) { - struct stack_info *info = &state->stack_info; - struct pt_regs *regs; unsigned long pc; + struct pt_regs *regs; + struct stack_info *info = &state->stack_info; if (unwind_done(state)) return false; do { - switch (state->type) { - case UNWINDER_GUESS: - state->first = false; - if (unwind_by_guess(state)) - return true; - break; + if (unwind_by_prologue(state)) { + state->pc = unwind_graph_addr(state, state->pc, state->sp); + return true; + } + + if (info->type == STACK_TYPE_IRQ && info->end == state->sp) { + regs = (struct pt_regs *)info->next_sp; + pc = regs->csr_era; + + if (user_mode(regs) || !__kernel_text_address(pc)) + return false; + + state->first = true; + state->pc = pc; + state->ra = regs->regs[1]; + state->sp = regs->regs[3]; + get_stack_info(state->sp, state->task, info); - case UNWINDER_PROLOGUE: - if (unwind_by_prologue(state)) { - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - return true; - } - - if (info->type == STACK_TYPE_IRQ && - info->end == state->sp) { - regs = (struct pt_regs *)info->next_sp; - pc = regs->csr_era; - - if (user_mode(regs) || !__kernel_text_address(pc)) - return false; - - state->first = true; - state->ra = regs->regs[1]; - state->sp = regs->regs[3]; - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - get_stack_info(state->sp, state->task, info); - - return true; - } + return true; } state->sp = info->next_sp; @@ -208,4 +228,36 @@ bool unwind_next_frame(struct unwind_state *state) return false; } + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + return __unwind_get_return_address(state); +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs) +{ + __unwind_start(state, task, regs); + state->type = UNWINDER_PROLOGUE; + state->first = true; + + /* + * The current PC is not kernel text address, we cannot find its + * relative symbol. Thus, prologue analysis will be broken. Luckily, + * we can use the default_next_frame(). + */ + if (!__kernel_text_address(state->pc)) { + state->type = UNWINDER_GUESS; + if (!unwind_done(state)) + unwind_next_frame(state); + } +} +EXPORT_SYMBOL_GPL(unwind_start); + +bool unwind_next_frame(struct unwind_state *state) +{ + return state->type == UNWINDER_PROLOGUE ? + next_frame(state) : default_next_frame(state); +} EXPORT_SYMBOL_GPL(unwind_next_frame); diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index da3681f131c8..8bad6b0cff59 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -251,7 +251,7 @@ static void output_pgtable_bits_defines(void) } #ifdef CONFIG_NUMA -static unsigned long pcpu_handlers[NR_CPUS]; +unsigned long pcpu_handlers[NR_CPUS]; #endif extern long exception_handlers[VECSIZE * 128 / sizeof(long)]; diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 4dfe1f49c5c8..6817892a2c58 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1303,7 +1303,7 @@ static char iodc_dbuf[4096] __page_aligned_bss; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; count = min_t(unsigned int, count, sizeof(iodc_dbuf)); @@ -1315,6 +1315,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1330,7 +1331,7 @@ print: __pa(pdc_result), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 69c62933e952..ceb45f51d52e 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -126,6 +126,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -166,7 +172,7 @@ long arch_ptrace(struct task_struct *child, long request, addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || @@ -181,14 +187,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -285,7 +291,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, if (addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ @@ -302,6 +308,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); @@ -484,7 +495,7 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val) case RI(iaoq[0]): case RI(iaoq[1]): /* set 2 lowest bits to ensure userspace privilege: */ - regs->iaoq[num - RI(iaoq[0])] = val | 3; + regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER; return; case RI(sar): regs->sar = val; return; diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index af04cea82b94..352d7de24018 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -210,6 +210,10 @@ ld_version() gsub(".*version ", ""); gsub("-.*", ""); split($1,a, "."); + if( length(a[3]) == "8" ) + # a[3] is probably a date of format yyyymmdd used for release snapshots. We + # can assume it to be zero as it does not signify a new version as such. + a[3] = 0; print a[1]*100000000 + a[2]*1000000 + a[3]*10000; exit }' diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dd39313242b4..d5cd16270c5d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -97,6 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) radix__tlb_flush(tlb); + + return hash__tlb_flush(tlb); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 77fa88c2aed0..eb6d094083fd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -173,6 +173,15 @@ static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) return flags; } +static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask) +{ + unsigned long flags = irq_soft_mask_return(); + + irq_soft_mask_set(flags & ~mask); + + return flags; +} + static inline unsigned long arch_local_save_flags(void) { return irq_soft_mask_return(); @@ -192,7 +201,7 @@ static inline void arch_local_irq_enable(void) static inline unsigned long arch_local_irq_save(void) { - return irq_soft_mask_set_return(IRQS_DISABLED); + return irq_soft_mask_or_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -331,10 +340,11 @@ bool power_pmu_wants_prompt_pmi(void); * is a different soft-masked interrupt pending that requires hard * masking. */ -static inline bool should_hard_irq_enable(void) +static inline bool should_hard_irq_enable(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS)); WARN_ON(mfmsr() & MSR_EE); } @@ -347,8 +357,17 @@ static inline bool should_hard_irq_enable(void) * * TODO: Add test for 64e */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi()) - return false; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (!power_pmu_wants_prompt_pmi()) + return false; + /* + * If PMIs are disabled then IRQs should be disabled as well, + * so we shouldn't see this condition, check for it just in + * case because we are about to enable PMIs. + */ + if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED)) + return false; + } if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK) return false; @@ -358,18 +377,16 @@ static inline bool should_hard_irq_enable(void) /* * Do the hard enabling, only call this if should_hard_irq_enable is true. + * This allows PMI interrupts to profile irq handlers. */ static inline void do_hard_irq_enable(void) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); - WARN_ON(mfmsr() & MSR_EE); - } /* - * This allows PMI interrupts (and watchdog soft-NMIs) through. - * There is no other reason to enable this way. + * Asynch interrupts come in with IRQS_ALL_DISABLED, + * PACA_IRQ_HARD_DIS, and MSR[EE]=0. */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + irq_soft_mask_andc_return(IRQS_PMI_DISABLED); get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; __hard_irq_enable(); } @@ -452,7 +469,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static __always_inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(struct pt_regs *regs) { return false; } diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4f897993b710..699a88584ae1 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -137,7 +137,7 @@ struct imc_pmu { * are inited. */ struct imc_pmu_ref { - struct mutex lock; + spinlock_t lock; unsigned int id; int refc; }; diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f55c6fb34a3a..5712dd846263 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) ppc_msgsync(); - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index d438ca74e96c..fdbee1093e2b 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -864,7 +864,7 @@ _GLOBAL(load_up_spe) * SPE unavailable trap from kernel - print a message, but let * the task use SPE in the kernel until it returns to user mode. */ -KernelSPE: +SYM_FUNC_START_LOCAL(KernelSPE) lwz r3,_MSR(r1) oris r3,r3,MSR_SPE@h stw r3,_MSR(r1) /* enable use of SPE after return */ @@ -881,6 +881,7 @@ KernelSPE: #endif .align 4,0 +SYM_FUNC_END(KernelSPE) #endif /* CONFIG_SPE */ /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c5b9ce887483..c9535f2760b5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -238,7 +238,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp) irq = static_call(ppc_get_irq)(); /* We can hard enable interrupts now to allow perf interrupts */ - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); /* And finally process it */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index d68de3618741..e26eb6618ae5 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -515,7 +515,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { + if (should_hard_irq_enable(regs)) { /* * Ensure a positive value is written to the decrementer, or * else some CPUs will continue to take decrementer exceptions. diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index af8854f9eae3..52085751f5f4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -989,10 +989,13 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) * linux,drconf-usable-memory properties. Get an approximate on the * number of usable memory entries and use for FDT size estimation. */ - usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) + - (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); - - extra_size = (unsigned int)(usm_entries * sizeof(u64)); + if (drmem_lmb_size()) { + usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) + + (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); + extra_size = (unsigned int)(usm_entries * sizeof(u64)); + } else { + extra_size = 0; + } /* * Get the number of CPU nodes in the current DT. This allows to diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 96a4803ba31c..01adffb24667 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -912,16 +912,15 @@ static int kvmppc_handle_debug(struct kvm_vcpu *vcpu) static void kvmppc_fill_pt_regs(struct pt_regs *regs) { - ulong r1, ip, msr, lr; + ulong r1, msr, lr; asm("mr %0, 1" : "=r"(r1)); asm("mflr %0" : "=r"(lr)); asm("mfmsr %0" : "=r"(msr)); - asm("bl 1f; 1: mflr %0" : "=r"(ip)); memset(regs, 0, sizeof(*regs)); regs->gpr[1] = r1; - regs->nip = ip; + regs->nip = _THIS_IP_; regs->msr = msr; regs->link = lr; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 80a148c57de8..44a35ed4f686 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1012,7 +1012,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, void hpt_clear_stress(void); static struct timer_list stress_hpt_timer; -void stress_hpt_timer_fn(struct timer_list *timer) +static void stress_hpt_timer_fn(struct timer_list *timer) { int next_cpu; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index cac727b01799..26245aaf12b8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -234,6 +234,14 @@ void radix__mark_rodata_ro(void) end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); + + for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) { + end = start + PAGE_SIZE; + if (overlaps_interrupt_vector_text(start, end)) + radix__change_memory_range(start, end, _PAGE_WRITE); + else + break; + } } void radix__mark_initmem_nx(void) @@ -262,6 +270,22 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX + unsigned long stext_phys; + + stext_phys = __pa_symbol(_stext); + + // Relocatable kernel running at non-zero real address + if (stext_phys != 0) { + // The end of interrupts code at zero is a rodata boundary + unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys; + if (addr < end_intr) + return end_intr; + + // Start of relocated kernel text is a rodata boundary + if (addr < stext_phys) + return stext_phys; + } + if (addr < __pa_symbol(__srwx_boundary)) return __pa_symbol(__srwx_boundary); #endif diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d517aba94d1b..9d229ef7f86e 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -14,6 +14,7 @@ #include <asm/cputhreads.h> #include <asm/smp.h> #include <linux/string.h> +#include <linux/spinlock.h> /* Nest IMC data structures and variables */ @@ -50,7 +51,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -400,7 +401,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) get_hard_smp_processor_id(cpu)); /* * If this is the last cpu in this chip then, skip the reference - * count mutex lock and make the reference count on this chip zero. + * count lock and make the reference count on this chip zero. */ ref = get_nest_pmu_ref(cpu); if (!ref) @@ -462,15 +463,15 @@ static void nest_imc_counters_release(struct perf_event *event) /* * See if we need to disable the nest PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the nest counters. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return; - /* Take the mutex lock for this node and then decrement the reference count */ - mutex_lock(&ref->lock); + /* Take the lock for this node and then decrement the reference count */ + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -482,7 +483,7 @@ static void nest_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that node. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -490,7 +491,7 @@ static void nest_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id); return; } @@ -498,7 +499,7 @@ static void nest_imc_counters_release(struct perf_event *event) WARN(1, "nest-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); } static int nest_imc_event_init(struct perf_event *event) @@ -557,26 +558,25 @@ static int nest_imc_event_init(struct perf_event *event) /* * Get the imc_pmu_ref struct for this node. - * Take the mutex lock and then increment the count of nest pmu events - * inited. + * Take the lock and then increment the count of nest pmu events inited. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to start the counters for node %d\n", node_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); event->destroy = nest_imc_counters_release; return 0; @@ -612,9 +612,8 @@ static int core_imc_mem_init(int cpu, int size) return -ENOMEM; mem_info->vbase = page_address(page); - /* Init the mutex */ core_imc_refc[core_id].id = core_id; - mutex_init(&core_imc_refc[core_id].lock); + spin_lock_init(&core_imc_refc[core_id].lock); rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE, __pa((void *)mem_info->vbase), @@ -703,9 +702,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu); } else { /* - * If this is the last cpu in this core then, skip taking refernce - * count mutex lock for this core and directly zero "refc" for - * this core. + * If this is the last cpu in this core then skip taking reference + * count lock for this core and directly zero "refc" for this core. */ opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(cpu)); @@ -720,11 +718,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) * last cpu in this core and core-imc event running * in this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_CORE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } return 0; } @@ -739,7 +737,7 @@ static int core_imc_pmu_cpumask_init(void) static void reset_global_refc(struct perf_event *event) { - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); imc_global_refc.refc--; /* @@ -751,7 +749,7 @@ static void reset_global_refc(struct perf_event *event) imc_global_refc.refc = 0; imc_global_refc.id = 0; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } static void core_imc_counters_release(struct perf_event *event) @@ -764,17 +762,17 @@ static void core_imc_counters_release(struct perf_event *event) /* * See if we need to disable the IMC PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the core counters. */ core_id = event->cpu / threads_per_core; - /* Take the mutex lock and decrement the refernce count for this core */ + /* Take the lock and decrement the refernce count for this core */ ref = &core_imc_refc[core_id]; if (!ref) return; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -786,7 +784,7 @@ static void core_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that core. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -794,7 +792,7 @@ static void core_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("IMC: Unable to stop the counters for core %d\n", core_id); return; } @@ -802,7 +800,7 @@ static void core_imc_counters_release(struct perf_event *event) WARN(1, "core-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); reset_global_refc(event); } @@ -840,7 +838,6 @@ static int core_imc_event_init(struct perf_event *event) if ((!pcmi->vbase)) return -ENODEV; - /* Get the core_imc mutex for this core */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; @@ -848,22 +845,22 @@ static int core_imc_event_init(struct perf_event *event) /* * Core pmu units are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the core counters. + * If yes, take the lock and enable the core counters. * If not, just increment the count in core_imc_refc struct. */ - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("core-imc: Unable to start the counters for core %d\n", core_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* * Since the system can run either in accumulation or trace-mode @@ -874,7 +871,7 @@ static int core_imc_event_init(struct perf_event *event) * to know whether any other trace/thread imc * events are running. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { /* * No other trace/thread imc events are running in @@ -883,10 +880,10 @@ static int core_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_CORE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; @@ -958,10 +955,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu) mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); /* Reduce the refc if thread-imc event running on this cpu */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_THREAD) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1001,7 +998,7 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); /* * Check if any other trace/core imc events are running in the * system, if not set the global id to thread-imc. @@ -1010,10 +1007,10 @@ static int thread_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_THREAD; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->pmu->task_ctx_nr = perf_sw_context; event->destroy = reset_global_refc; @@ -1135,25 +1132,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags) /* * imc pmus are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the counters. + * If yes, take the lock and enable the counters. * If not, just increment the count in ref count struct. */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to start the counter\ for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1170,12 +1167,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to stop the counters\ for core %d\n", core_id); return; @@ -1183,7 +1180,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags) } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); @@ -1224,9 +1221,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size) } } - /* Init the mutex, if not already */ trace_imc_refc[core_id].id = core_id; - mutex_init(&trace_imc_refc[core_id].lock); + spin_lock_init(&trace_imc_refc[core_id].lock); mtspr(SPRN_LDBAR, 0); return 0; @@ -1246,10 +1242,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu) * Reduce the refc if any trace-imc event running * on this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_TRACE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1371,17 +1367,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags) } mtspr(SPRN_LDBAR, ldbar_value); - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1414,19 +1410,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id); return; } } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); trace_imc_event_stop(event, flags); } @@ -1448,7 +1444,7 @@ static int trace_imc_event_init(struct perf_event *event) * no other thread is running any core/thread imc * events */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { /* * No core/thread imc events are running in the @@ -1457,10 +1453,10 @@ static int trace_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_TRACE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.idx = -1; @@ -1533,10 +1529,10 @@ static int init_nest_pmu_ref(void) i = 0; for_each_node(nid) { /* - * Mutex lock to avoid races while tracking the number of + * Take the lock to avoid races while tracking the number of * sessions using the chip's nest pmu units. */ - mutex_init(&nest_imc_refc[i].lock); + spin_lock_init(&nest_imc_refc[i].lock); /* * Loop to init the "id" with the node_id. Variable "i" initialized to diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index faf2c2177094..82153960ac00 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -80,6 +80,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index 43bed6c0a84f..5235fd1c9cb6 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -328,7 +328,7 @@ bus-range = <0x0 0xff>; ranges = <0x81000000 0x0 0x60080000 0x0 0x60080000 0x0 0x10000>, /* I/O */ <0x82000000 0x0 0x60090000 0x0 0x60090000 0x0 0xff70000>, /* mem */ - <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x1000000>, /* mem */ + <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x10000000>, /* mem */ <0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>; /* mem prefetchable */ num-lanes = <0x8>; interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>; diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 7226e2462584..2c0f4c887289 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -46,7 +46,7 @@ .macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \ new_c_2, vendor_id_2, errata_id_2, enable_2 - ALTERNATIVE_CFG \old_c, \new_c_1, \vendor_id_1, \errata_id_1, \enable_1 + ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1 ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2 .endm diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 86328e3acb02..64ad1937e714 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -70,7 +70,6 @@ static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX); */ enum riscv_isa_ext_key { RISCV_ISA_EXT_KEY_FPU, /* For 'F' and 'D' */ - RISCV_ISA_EXT_KEY_ZIHINTPAUSE, RISCV_ISA_EXT_KEY_SVINVAL, RISCV_ISA_EXT_KEY_MAX, }; @@ -91,8 +90,6 @@ static __always_inline int riscv_isa_ext2key(int num) return RISCV_ISA_EXT_KEY_FPU; case RISCV_ISA_EXT_d: return RISCV_ISA_EXT_KEY_FPU; - case RISCV_ISA_EXT_ZIHINTPAUSE: - return RISCV_ISA_EXT_KEY_ZIHINTPAUSE; case RISCV_ISA_EXT_SVINVAL: return RISCV_ISA_EXT_KEY_SVINVAL; default: diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index cf24da85b13c..cc7da66ee0c0 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -18,6 +18,7 @@ #include <asm/kvm_vcpu_insn.h> #include <asm/kvm_vcpu_sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #define KVM_MAX_VCPUS 1024 @@ -228,6 +229,9 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; + + /* Performance monitoring context */ + struct kvm_pmu pmu_context; }; static inline void kvm_arch_sync_events(struct kvm *kvm) {} diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h new file mode 100644 index 000000000000..395518a1664e --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#ifndef __KVM_VCPU_RISCV_PMU_H +#define __KVM_VCPU_RISCV_PMU_H + +#include <linux/perf/riscv_pmu.h> +#include <asm/sbi.h> + +#ifdef CONFIG_RISCV_PMU_SBI +#define RISCV_KVM_MAX_FW_CTRS 32 +#define RISCV_KVM_MAX_HW_CTRS 32 +#define RISCV_KVM_MAX_COUNTERS (RISCV_KVM_MAX_HW_CTRS + RISCV_KVM_MAX_FW_CTRS) +static_assert(RISCV_KVM_MAX_COUNTERS <= 64); + +struct kvm_fw_event { + /* Current value of the event */ + unsigned long value; + + /* Event monitoring status */ + bool started; +}; + +/* Per virtual pmu counter data */ +struct kvm_pmc { + u8 idx; + struct perf_event *perf_event; + u64 counter_val; + union sbi_pmu_ctr_info cinfo; + /* Event monitoring status */ + bool started; + /* Monitoring event ID */ + unsigned long event_idx; +}; + +/* PMU data structure per vcpu */ +struct kvm_pmu { + struct kvm_pmc pmc[RISCV_KVM_MAX_COUNTERS]; + struct kvm_fw_event fw_event[RISCV_KVM_MAX_FW_CTRS]; + /* Number of the virtual firmware counters available */ + int num_fw_ctrs; + /* Number of the virtual hardware counters available */ + int num_hw_ctrs; + /* A flag to indicate that pmu initialization is done */ + bool init_done; + /* Bit map of all the virtual counter used */ + DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS); +}; + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu_context)) + +#if defined(CONFIG_32BIT) +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#else +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#endif + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid); +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); + +#else +struct kvm_pmu { +}; + +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = 0, .count = 0, .func = NULL }, + +static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {} +static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) {} +static inline void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_RISCV_PMU_SBI */ +#endif /* !__KVM_VCPU_RISCV_PMU_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index f79478a85d2d..8425556af7d1 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -18,6 +18,13 @@ struct kvm_vcpu_sbi_context { int return_handled; }; +struct kvm_vcpu_sbi_return { + unsigned long out_val; + unsigned long err_val; + struct kvm_cpu_trap *utrap; + bool uexit; +}; + struct kvm_vcpu_sbi_extension { unsigned long extid_start; unsigned long extid_end; @@ -27,8 +34,10 @@ struct kvm_vcpu_sbi_extension { * specific error codes. */ int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, struct kvm_cpu_trap *utrap, - bool *exit); + struct kvm_vcpu_sbi_return *retdata); + + /* Extension specific probe function */ + unsigned long (*probe)(struct kvm_vcpu *vcpu); }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 4ca7fbacff42..945b7be249c1 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -169,9 +169,9 @@ enum sbi_pmu_fw_generic_events_t { SBI_PMU_FW_ILLEGAL_INSN = 4, SBI_PMU_FW_SET_TIMER = 5, SBI_PMU_FW_IPI_SENT = 6, - SBI_PMU_FW_IPI_RECVD = 7, + SBI_PMU_FW_IPI_RCVD = 7, SBI_PMU_FW_FENCE_I_SENT = 8, - SBI_PMU_FW_FENCE_I_RECVD = 9, + SBI_PMU_FW_FENCE_I_RCVD = 9, SBI_PMU_FW_SFENCE_VMA_SENT = 10, SBI_PMU_FW_SFENCE_VMA_RCVD = 11, SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, @@ -215,6 +215,9 @@ enum sbi_pmu_ctr_type { #define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06 #define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01 +#define SBI_PMU_EVENT_CACHE_ID_SHIFT 3 +#define SBI_PMU_EVENT_CACHE_OP_SHIFT 1 + #define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF /* Flags defined for config matching function */ diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index fa70cfe507aa..14f5d27783b8 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,30 +4,26 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> #include <asm/barrier.h> -#include <asm/hwcap.h> static inline void cpu_relax(void) { - if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) { #ifdef __riscv_muldiv - int dummy; - /* In lieu of a halt instruction, induce a long-latency stall. */ - __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); + int dummy; + /* In lieu of a halt instruction, induce a long-latency stall. */ + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif - } else { - /* - * Reduce instruction retirement. - * This assumes the PC changes. - */ -#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE - __asm__ __volatile__ ("pause"); + +#ifdef __riscv_zihintpause + /* + * Reduce instruction retirement. + * This assumes the PC changes. + */ + __asm__ __volatile__ ("pause"); #else - /* Encoding of the pause instruction */ - __asm__ __volatile__ (".4byte 0x100000F"); + /* Encoding of the pause instruction */ + __asm__ __volatile__ (".4byte 0x100000F"); #endif - } barrier(); } diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index b865046e4dbb..4bf6c449d78b 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -326,7 +326,7 @@ clear_bss_done: call soc_early_init tail start_kernel -#if CONFIG_RISCV_BOOT_SPINWAIT +#ifdef CONFIG_RISCV_BOOT_SPINWAIT .Lsecondary_start: /* Set trap vector to spin forever to help debug */ la a3, .Lsecondary_park diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index f21592d20306..41c7481afde3 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -48,6 +48,21 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) post_kprobe_handler(p, kcb, regs); } +static bool __kprobes arch_check_kprobe(struct kprobe *p) +{ + unsigned long tmp = (unsigned long)p->addr - p->offset; + unsigned long addr = (unsigned long)p->addr; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long probe_addr = (unsigned long)p->addr; @@ -55,6 +70,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (probe_addr & 0x1) return -EILSEQ; + if (!arch_check_kprobe(p)) + return -EILSEQ; + /* copy instruction */ p->opcode = *p->addr; diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index d73e96f6ed7c..a20568bd1f1a 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -71,11 +71,11 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *reg u32 rd_index = (opcode >> 7) & 0x1f; u32 rs1_index = (opcode >> 15) & 0x1f; - ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); if (!ret) return ret; - ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); if (!ret) return ret; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 3373df413c88..ddb2afba6d25 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -39,7 +39,6 @@ static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { - init_cpu_topology(); } void __init smp_prepare_cpus(unsigned int max_cpus) @@ -48,6 +47,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int ret; unsigned int curr_cpuid; + init_cpu_topology(); + curr_cpuid = smp_processor_id(); store_cpu_topology(curr_cpuid); numa_store_cpu_info(curr_cpuid); diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 019df9208bdd..278e97c06e0a 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -25,3 +25,4 @@ kvm-y += vcpu_sbi_base.o kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index e2da56ed9069..41ad7639a17b 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -39,7 +39,8 @@ int kvm_arch_hardware_enable(void) hideleg |= (1UL << IRQ_VS_EXT); csr_write(CSR_HIDELEG, hideleg); - csr_write(CSR_HCOUNTEREN, -1UL); + /* VS should access only the time counter directly. Everything else should trap */ + csr_write(CSR_HCOUNTEREN, 0x02); csr_write(CSR_HVIP, 0); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 66ef19676fe4..78211aed36fa 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -585,7 +585,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -645,12 +645,12 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, if (logging || (vma->vm_flags & VM_PFNMAP)) vma_pagesize = PAGE_SIZE; - if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE) + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; mmap_read_unlock(current->mm); - if (vma_pagesize != PGDIR_SIZE && + if (vma_pagesize != PUD_SIZE && vma_pagesize != PMD_SIZE && vma_pagesize != PAGE_SIZE) { kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize); diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index 309d79b3e5cd..b797f7cc0824 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -181,6 +181,7 @@ void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) { + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_RCVD); local_flush_icache_all(); } @@ -264,15 +265,18 @@ void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_gva( READ_ONCE(v->vmid), d.asid, d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_all( READ_ONCE(v->vmid), d.asid); break; case KVM_RISCV_HFENCE_VVMA_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); kvm_riscv_local_hfence_vvma_gva( READ_ONCE(v->vmid), d.addr, d.size, d.order); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7c08567097f0..7d010b0be54e 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -138,6 +138,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) WRITE_ONCE(vcpu->arch.irqs_pending, 0); WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + kvm_riscv_vcpu_pmu_reset(vcpu); + vcpu->arch.hfence_head = 0; vcpu->arch.hfence_tail = 0; memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); @@ -194,6 +196,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); + /* setup performance monitoring */ + kvm_riscv_vcpu_pmu_init(vcpu); + /* Reset VCPU */ kvm_riscv_reset_vcpu(vcpu); @@ -216,6 +221,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Cleanup VCPU timer */ kvm_riscv_vcpu_timer_deinit(vcpu); + kvm_riscv_vcpu_pmu_deinit(vcpu); + /* Free unused pages pre-allocated for G-stage page table mappings */ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index c9f741ab26f5..4ea101a73d8b 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -160,6 +160,9 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, /* Set Guest PC to Guest exception vector */ vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC); + + /* Set Guest privilege mode to supervisor */ + vcpu->arch.guest_context.sstatus |= SR_SPP; } /* @@ -179,6 +182,12 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = -EFAULT; run->exit_reason = KVM_EXIT_UNKNOWN; switch (trap->scause) { + case EXC_INST_ILLEGAL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + break; case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap); diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 0bb52761a3f7..f689337b78ff 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -213,7 +213,9 @@ struct csr_func { unsigned long wr_mask); }; -static const struct csr_func csr_funcs[] = { }; +static const struct csr_func csr_funcs[] = { + KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS +}; /** * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c new file mode 100644 index 000000000000..86391a5061dd --- /dev/null +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#define pr_fmt(fmt) "riscv-kvm-pmu: " fmt +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <linux/perf/riscv_pmu.h> +#include <asm/csr.h> +#include <asm/kvm_vcpu_sbi.h> +#include <asm/kvm_vcpu_pmu.h> +#include <linux/bitops.h> + +#define kvm_pmu_num_counters(pmu) ((pmu)->num_hw_ctrs + (pmu)->num_fw_ctrs) +#define get_event_type(x) (((x) & SBI_PMU_EVENT_IDX_TYPE_MASK) >> 16) +#define get_event_code(x) ((x) & SBI_PMU_EVENT_IDX_CODE_MASK) + +static enum perf_hw_id hw_event_perf_map[SBI_PMU_HW_GENERAL_MAX] = { + [SBI_PMU_HW_CPU_CYCLES] = PERF_COUNT_HW_CPU_CYCLES, + [SBI_PMU_HW_INSTRUCTIONS] = PERF_COUNT_HW_INSTRUCTIONS, + [SBI_PMU_HW_CACHE_REFERENCES] = PERF_COUNT_HW_CACHE_REFERENCES, + [SBI_PMU_HW_CACHE_MISSES] = PERF_COUNT_HW_CACHE_MISSES, + [SBI_PMU_HW_BRANCH_INSTRUCTIONS] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [SBI_PMU_HW_BRANCH_MISSES] = PERF_COUNT_HW_BRANCH_MISSES, + [SBI_PMU_HW_BUS_CYCLES] = PERF_COUNT_HW_BUS_CYCLES, + [SBI_PMU_HW_STALLED_CYCLES_FRONTEND] = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + [SBI_PMU_HW_STALLED_CYCLES_BACKEND] = PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + [SBI_PMU_HW_REF_CPU_CYCLES] = PERF_COUNT_HW_REF_CPU_CYCLES, +}; + +static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) +{ + u64 counter_val_mask = GENMASK(pmc->cinfo.width, 0); + u64 sample_period; + + if (!pmc->counter_val) + sample_period = counter_val_mask + 1; + else + sample_period = (-pmc->counter_val) & counter_val_mask; + + return sample_period; +} + +static u32 kvm_pmu_get_perf_event_type(unsigned long eidx) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 type = PERF_TYPE_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + type = PERF_TYPE_HARDWARE; + break; + case SBI_PMU_EVENT_TYPE_CACHE: + type = PERF_TYPE_HW_CACHE; + break; + case SBI_PMU_EVENT_TYPE_RAW: + case SBI_PMU_EVENT_TYPE_FW: + type = PERF_TYPE_RAW; + break; + default: + break; + } + + return type; +} + +static bool kvm_pmu_is_fw_event(unsigned long eidx) +{ + return get_event_type(eidx) == SBI_PMU_EVENT_TYPE_FW; +} + +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_disable(pmc->perf_event); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) +{ + return hw_event_perf_map[sbi_event_code]; +} + +static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) +{ + u64 config = U64_MAX; + unsigned int cache_type, cache_op, cache_result; + + /* All the cache event masks lie within 0xFF. No separate masking is necessary */ + cache_type = (sbi_event_code & SBI_PMU_EVENT_CACHE_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_ID_SHIFT; + cache_op = (sbi_event_code & SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_OP_SHIFT; + cache_result = sbi_event_code & SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK; + + if (cache_type >= PERF_COUNT_HW_CACHE_MAX || + cache_op >= PERF_COUNT_HW_CACHE_OP_MAX || + cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return config; + + config = cache_type | (cache_op << 8) | (cache_result << 16); + + return config; +} + +static u64 kvm_pmu_get_perf_event_config(unsigned long eidx, uint64_t evt_data) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 ecode = get_event_code(eidx); + u64 config = U64_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + if (ecode < SBI_PMU_HW_GENERAL_MAX) + config = kvm_pmu_get_perf_event_hw_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_CACHE: + config = kvm_pmu_get_perf_event_cache_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_RAW: + config = evt_data & RISCV_PMU_RAW_EVENT_MASK; + break; + case SBI_PMU_EVENT_TYPE_FW: + if (ecode < SBI_PMU_FW_MAX) + config = (1ULL << 63) | ecode; + break; + default: + break; + } + + return config; +} + +static int kvm_pmu_get_fixed_pmc_index(unsigned long eidx) +{ + u32 etype = kvm_pmu_get_perf_event_type(eidx); + u32 ecode = get_event_code(eidx); + + if (etype != SBI_PMU_EVENT_TYPE_HW) + return -EINVAL; + + if (ecode == SBI_PMU_HW_CPU_CYCLES) + return 0; + else if (ecode == SBI_PMU_HW_INSTRUCTIONS) + return 2; + else + return -EINVAL; +} + +static int kvm_pmu_get_programmable_pmc_index(struct kvm_pmu *kvpmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ctr_idx = -1; + int i, pmc_idx; + int min, max; + + if (kvm_pmu_is_fw_event(eidx)) { + /* Firmware counters are mapped 1:1 starting from num_hw_ctrs for simplicity */ + min = kvpmu->num_hw_ctrs; + max = min + kvpmu->num_fw_ctrs; + } else { + /* First 3 counters are reserved for fixed counters */ + min = 3; + max = kvpmu->num_hw_ctrs; + } + + for_each_set_bit(i, &cmask, BITS_PER_LONG) { + pmc_idx = i + cbase; + if ((pmc_idx >= min && pmc_idx < max) && + !test_bit(pmc_idx, kvpmu->pmc_in_use)) { + ctr_idx = pmc_idx; + break; + } + } + + return ctr_idx; +} + +static int pmu_get_pmc_index(struct kvm_pmu *pmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ret; + + /* Fixed counters need to be have fixed mapping as they have different width */ + ret = kvm_pmu_get_fixed_pmc_index(eidx); + if (ret >= 0) + return ret; + + return kvm_pmu_get_programmable_pmc_index(pmu, eidx, cbase, cmask); +} + +static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u64 enabled, running; + int fevent_code; + + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + } else if (pmc->perf_event) { + pmc->counter_val += perf_event_read_value(pmc->perf_event, &enabled, &running); + } else { + return -EINVAL; + } + *out_val = pmc->counter_val; + + return 0; +} + +static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ctr_base, + unsigned long ctr_mask) +{ + /* Make sure the we have a valid counter mask requested from the caller */ + if (!ctr_mask || (ctr_base + __fls(ctr_mask) >= kvm_pmu_num_counters(kvpmu))) + return -EINVAL; + + return 0; +} + +static int kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, + unsigned long flags, unsigned long eidx, unsigned long evtdata) +{ + struct perf_event *event; + + kvm_pmu_release_perf_event(pmc); + attr->config = kvm_pmu_get_perf_event_config(eidx, evtdata); + if (flags & SBI_PMU_CFG_FLAG_CLEAR_VALUE) { + //TODO: Do we really want to clear the value in hardware counter + pmc->counter_val = 0; + } + + /* + * Set the default sample_period for now. The guest specified value + * will be updated in the start call. + */ + attr->sample_period = kvm_pmu_get_sample_period(pmc); + + event = perf_event_create_kernel_counter(attr, -1, current, NULL, pmc); + if (IS_ERR(event)) { + pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); + return PTR_ERR(event); + } + + pmc->perf_event = event; + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + perf_event_enable(pmc->perf_event); + + return 0; +} + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_fw_event *fevent; + + if (!kvpmu || fid >= SBI_PMU_FW_MAX) + return -EINVAL; + + fevent = &kvpmu->fw_event[fid]; + if (fevent->started) + fevent->value++; + + return 0; +} + +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int cidx, ret = KVM_INSN_CONTINUE_NEXT_SEPC; + + if (!kvpmu || !kvpmu->init_done) { + /* + * In absence of sscofpmf in the platform, the guest OS may use + * the legacy PMU driver to read cycle/instret. In that case, + * just return 0 to avoid any illegal trap. However, any other + * hpmcounter access should result in illegal trap as they must + * be access through SBI PMU only. + */ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return ret; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } + } + + /* The counter CSR are read only. Thus, any write should result in illegal traps */ + if (wr_mask) + return KVM_INSN_ILLEGAL_TRAP; + + cidx = csr_num - CSR_CYCLE; + + if (pmu_ctr_read(vcpu, cidx, val) < 0) + return KVM_INSN_ILLEGAL_TRAP; + + return ret; +} + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + retdata->out_val = kvm_pmu_num_counters(kvpmu); + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + retdata->out_val = kvpmu->pmc[cidx].cinfo.value; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Start the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) + pmc->counter_val = ival; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Check if the counter was already started for some reason */ + if (kvpmu->fw_event[fevent_code].started) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + + kvpmu->fw_event[fevent_code].started = true; + kvpmu->fw_event[fevent_code].value = pmc->counter_val; + } else if (pmc->perf_event) { + if (unlikely(pmc->started)) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + perf_event_period(pmc->perf_event, kvm_pmu_get_sample_period(pmc)); + perf_event_enable(pmc->perf_event); + pmc->started = true; + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + u64 enabled, running; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Stop the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (!kvpmu->fw_event[fevent_code].started) + sbiret = SBI_ERR_ALREADY_STOPPED; + + kvpmu->fw_event[fevent_code].started = false; + } else if (pmc->perf_event) { + if (pmc->started) { + /* Stop counting the counter */ + perf_event_disable(pmc->perf_event); + pmc->started = false; + } else { + sbiret = SBI_ERR_ALREADY_STOPPED; + } + + if (flags & SBI_PMU_STOP_FLAG_RESET) { + /* Relase the counter if this is a reset request */ + pmc->counter_val += perf_event_read_value(pmc->perf_event, + &enabled, &running); + kvm_pmu_release_perf_event(pmc); + } + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + if (flags & SBI_PMU_STOP_FLAG_RESET) { + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + clear_bit(pmc_index, kvpmu->pmc_in_use); + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata) +{ + int ctr_idx, ret, sbiret = 0; + bool is_fevent; + unsigned long event_code; + u32 etype = kvm_pmu_get_perf_event_type(eidx); + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + struct perf_event_attr attr = { + .type = etype, + .size = sizeof(struct perf_event_attr), + .pinned = true, + /* + * It should never reach here if the platform doesn't support the sscofpmf + * extension as mode filtering won't work without it. + */ + .exclude_host = true, + .exclude_hv = true, + .exclude_user = !!(flags & SBI_PMU_CFG_FLAG_SET_UINH), + .exclude_kernel = !!(flags & SBI_PMU_CFG_FLAG_SET_SINH), + .config1 = RISCV_PMU_CONFIG1_GUEST_EVENTS, + }; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + event_code = get_event_code(eidx); + is_fevent = kvm_pmu_is_fw_event(eidx); + if (is_fevent && event_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + + /* + * SKIP_MATCH flag indicates the caller is aware of the assigned counter + * for this event. Just do a sanity check if it already marked used. + */ + if (flags & SBI_PMU_CFG_FLAG_SKIP_MATCH) { + if (!test_bit(ctr_base + __ffs(ctr_mask), kvpmu->pmc_in_use)) { + sbiret = SBI_ERR_FAILURE; + goto out; + } + ctr_idx = ctr_base + __ffs(ctr_mask); + } else { + ctr_idx = pmu_get_pmc_index(kvpmu, eidx, ctr_base, ctr_mask); + if (ctr_idx < 0) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + } + + pmc = &kvpmu->pmc[ctr_idx]; + pmc->idx = ctr_idx; + + if (is_fevent) { + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + kvpmu->fw_event[event_code].started = true; + } else { + ret = kvm_pmu_create_perf_event(pmc, &attr, flags, eidx, evtdata); + if (ret) + return ret; + } + + set_bit(ctr_idx, kvpmu->pmc_in_use); + pmc->event_idx = eidx; + retdata->out_val = ctr_idx; +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_ctr_read(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) +{ + int i = 0, ret, num_hw_ctrs = 0, hpm_width = 0; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* + * PMU functionality should be only available to guests if privilege mode + * filtering is available in the host. Otherwise, guest will always count + * events while the execution is in hypervisor mode. + */ + if (!riscv_isa_extension_available(NULL, SSCOFPMF)) + return; + + ret = riscv_pmu_get_hpm_info(&hpm_width, &num_hw_ctrs); + if (ret < 0 || !hpm_width || !num_hw_ctrs) + return; + + /* + * Increase the number of hardware counters to offset the time counter. + */ + kvpmu->num_hw_ctrs = num_hw_ctrs + 1; + kvpmu->num_fw_ctrs = SBI_PMU_FW_MAX; + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + + if (kvpmu->num_hw_ctrs > RISCV_KVM_MAX_HW_CTRS) { + pr_warn_once("Limiting the hardware counters to 32 as specified by the ISA"); + kvpmu->num_hw_ctrs = RISCV_KVM_MAX_HW_CTRS; + } + + /* + * There is no correlation between the logical hardware counter and virtual counters. + * However, we need to encode a hpmcounter CSR in the counter info field so that + * KVM can trap n emulate the read. This works well in the migration use case as + * KVM doesn't care if the actual hpmcounter is available in the hardware or not. + */ + for (i = 0; i < kvm_pmu_num_counters(kvpmu); i++) { + /* TIME CSR shouldn't be read from perf interface */ + if (i == 1) + continue; + pmc = &kvpmu->pmc[i]; + pmc->idx = i; + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + if (i < kvpmu->num_hw_ctrs) { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW; + if (i < 3) + /* CY, IR counters */ + pmc->cinfo.width = 63; + else + pmc->cinfo.width = hpm_width; + /* + * The CSR number doesn't have any relation with the logical + * hardware counters. The CSR numbers are encoded sequentially + * to avoid maintaining a map between the virtual counter + * and CSR number. + */ + pmc->cinfo.csr = CSR_CYCLE + i; + } else { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_FW; + pmc->cinfo.width = BITS_PER_LONG - 1; + } + } + + kvpmu->init_done = true; +} + +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + if (!kvpmu) + return; + + for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_MAX_COUNTERS) { + pmc = &kvpmu->pmc[i]; + pmc->counter_val = 0; + kvm_pmu_release_perf_event(pmc); + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + } + bitmap_zero(kvpmu->pmc_in_use, RISCV_MAX_COUNTERS); + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); +} + +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_pmu_deinit(vcpu); +} diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index f96991d230bf..15fde15f9fb8 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -12,26 +12,6 @@ #include <asm/sbi.h> #include <asm/kvm_vcpu_sbi.h> -static int kvm_linux_err_map_sbi(int err) -{ - switch (err) { - case 0: - return SBI_SUCCESS; - case -EPERM: - return SBI_ERR_DENIED; - case -EINVAL: - return SBI_ERR_INVALID_PARAM; - case -EFAULT: - return SBI_ERR_INVALID_ADDRESS; - case -EOPNOTSUPP: - return SBI_ERR_NOT_SUPPORTED; - case -EALREADY: - return SBI_ERR_ALREADY_AVAILABLE; - default: - return SBI_ERR_FAILURE; - }; -} - #ifndef CONFIG_RISCV_SBI_V01 static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { .extid_start = -1UL, @@ -40,6 +20,16 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { }; #endif +#ifdef CONFIG_RISCV_PMU_SBI +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu; +#else +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, &vcpu_sbi_ext_base, @@ -48,6 +38,7 @@ static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_rfence, &vcpu_sbi_ext_srst, &vcpu_sbi_ext_hsm, + &vcpu_sbi_ext_pmu, &vcpu_sbi_ext_experimental, &vcpu_sbi_ext_vendor, }; @@ -125,11 +116,14 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret = 1; bool next_sepc = true; - bool userspace_exit = false; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; const struct kvm_vcpu_sbi_extension *sbi_ext; - struct kvm_cpu_trap utrap = { 0 }; - unsigned long out_val = 0; + struct kvm_cpu_trap utrap = {0}; + struct kvm_vcpu_sbi_return sbi_ret = { + .out_val = 0, + .err_val = 0, + .utrap = &utrap, + }; bool ext_is_v01 = false; sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); @@ -139,42 +133,46 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) cp->a7 <= SBI_EXT_0_1_SHUTDOWN) ext_is_v01 = true; #endif - ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit); + ret = sbi_ext->handler(vcpu, run, &sbi_ret); } else { /* Return error for unsupported SBI calls */ cp->a0 = SBI_ERR_NOT_SUPPORTED; goto ecall_done; } + /* + * When the SBI extension returns a Linux error code, it exits the ioctl + * loop and forwards the error to userspace. + */ + if (ret < 0) { + next_sepc = false; + goto ecall_done; + } + /* Handle special error cases i.e trap, exit or userspace forward */ - if (utrap.scause) { + if (sbi_ret.utrap->scause) { /* No need to increment sepc or exit ioctl loop */ ret = 1; - utrap.sepc = cp->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + sbi_ret.utrap->sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, sbi_ret.utrap); next_sepc = false; goto ecall_done; } /* Exit ioctl loop or Propagate the error code the guest */ - if (userspace_exit) { + if (sbi_ret.uexit) { next_sepc = false; ret = 0; } else { - /** - * SBI extension handler always returns an Linux error code. Convert - * it to the SBI specific error code that can be propagated the SBI - * caller. - */ - ret = kvm_linux_err_map_sbi(ret); - cp->a0 = ret; + cp->a0 = sbi_ret.err_val; ret = 1; } ecall_done: if (next_sepc) cp->sepc += 4; - if (!ext_is_v01) - cp->a1 = out_val; + /* a1 should only be updated when we continue the ioctl loop */ + if (!ext_is_v01 && ret == 1) + cp->a1 = sbi_ret.out_val; return ret; } diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 5d65c634d301..9945aff34c14 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -14,11 +14,11 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *trap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + unsigned long *out_val = &retdata->out_val; switch (cp->a6) { case SBI_EXT_BASE_GET_SPEC_VERSION: @@ -42,9 +42,12 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * forward it to the userspace */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; - } else - *out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0; + retdata->uexit = true; + } else { + sbi_ext = kvm_vcpu_sbi_find_ext(cp->a0); + *out_val = sbi_ext && sbi_ext->probe ? + sbi_ext->probe(vcpu) : !!sbi_ext; + } break; case SBI_EXT_BASE_GET_MVENDORID: *out_val = vcpu->arch.mvendorid; @@ -56,11 +59,11 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, *out_val = vcpu->arch.mimpid; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { @@ -70,17 +73,15 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { }; static int kvm_sbi_ext_forward_handler(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) { /* * Both SBI experimental and vendor extensions are * unconditionally forwarded to userspace. */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; return 0; } diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index 2e915cafd551..7dca0e9381d9 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -21,9 +21,9 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) - return -EALREADY; + return SBI_ERR_ALREADY_AVAILABLE; reset_cntx = &target_vcpu->arch.guest_reset_context; /* start address */ @@ -42,7 +42,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) { if (vcpu->arch.power_off) - return -EINVAL; + return SBI_ERR_FAILURE; kvm_riscv_vcpu_power_off(vcpu); @@ -57,7 +57,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) return SBI_HSM_STATE_STARTED; else if (vcpu->stat.generic.blocking) @@ -67,9 +67,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) } static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -88,27 +86,29 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_HSM_HART_STATUS: ret = kvm_sbi_hsm_vcpu_get_status(vcpu); if (ret >= 0) { - *out_val = ret; - ret = 0; + retdata->out_val = ret; + retdata->err_val = 0; } - break; + return 0; case SBI_EXT_HSM_HART_SUSPEND: switch (cp->a0) { case SBI_HSM_SUSPEND_RET_DEFAULT: kvm_riscv_vcpu_wfi(vcpu); break; case SBI_HSM_SUSPEND_NON_RET_DEFAULT: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; break; default: - ret = -EINVAL; + ret = SBI_ERR_INVALID_PARAM; } break; default: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; } - return ret; + retdata->err_val = ret; + + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = { diff --git a/arch/riscv/kvm/vcpu_sbi_pmu.c b/arch/riscv/kvm/vcpu_sbi_pmu.c new file mode 100644 index 000000000000..7eca72df2cbd --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_pmu.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/kvm_vcpu_sbi.h> + +static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + unsigned long funcid = cp->a6; + u64 temp; + + if (!kvpmu->init_done) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + switch (funcid) { + case SBI_EXT_PMU_NUM_COUNTERS: + ret = kvm_riscv_vcpu_pmu_num_ctrs(vcpu, retdata); + break; + case SBI_EXT_PMU_COUNTER_GET_INFO: + ret = kvm_riscv_vcpu_pmu_ctr_info(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_CFG_MATCH: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a5 << 32) | cp->a4; +#else + temp = cp->a4; +#endif + /* + * This can fail if perf core framework fails to create an event. + * Forward the error to userspace because it's an error which + * happened within the host kernel. The other option would be + * to convert to an SBI error and forward to the guest. + */ + ret = kvm_riscv_vcpu_pmu_ctr_cfg_match(vcpu, cp->a0, cp->a1, + cp->a2, cp->a3, temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_START: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a4 << 32) | cp->a3; +#else + temp = cp->a3; +#endif + ret = kvm_riscv_vcpu_pmu_ctr_start(vcpu, cp->a0, cp->a1, cp->a2, + temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_STOP: + ret = kvm_riscv_vcpu_pmu_ctr_stop(vcpu, cp->a0, cp->a1, cp->a2, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ: + ret = kvm_riscv_vcpu_pmu_ctr_read(vcpu, cp->a0, retdata); + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return ret; +} + +static unsigned long kvm_sbi_ext_pmu_probe(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + return kvpmu->init_done; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = SBI_EXT_PMU, + .extid_end = SBI_EXT_PMU, + .handler = kvm_sbi_ext_pmu_handler, + .probe = kvm_sbi_ext_pmu_probe, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 03a0198389f0..7c4d5d38a339 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -11,19 +11,21 @@ #include <linux/kvm_host.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; u64 next_cycle; - if (cp->a6 != SBI_EXT_TIME_SET_TIMER) - return -EINVAL; + if (cp->a6 != SBI_EXT_TIME_SET_TIMER) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_SET_TIMER); #if __riscv_xlen == 32 next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; #else @@ -31,7 +33,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, #endif kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { @@ -41,8 +43,7 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { }; static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; unsigned long i; @@ -51,9 +52,12 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; - if (cp->a6 != SBI_EXT_IPI_SEND_IPI) - return -EINVAL; + if (cp->a6 != SBI_EXT_IPI_SEND_IPI) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_IPI_SENT); kvm_for_each_vcpu(i, tmp, vcpu->kvm) { if (hbase != -1UL) { if (tmp->vcpu_id < hbase) @@ -64,6 +68,7 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); if (ret < 0) break; + kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD); } return ret; @@ -76,10 +81,8 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = { }; static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; @@ -88,6 +91,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run switch (funcid) { case SBI_EXT_RFENCE_REMOTE_FENCE_I: kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: if (cp->a2 == 0 && cp->a3 == 0) @@ -95,6 +99,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: if (cp->a2 == 0 && cp->a3 == 0) @@ -105,6 +110,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT, cp->a4); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_SENT); break; case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: @@ -116,10 +122,10 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run */ break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { @@ -130,14 +136,12 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long funcid = cp->a6; u32 reason = cp->a1; u32 type = cp->a0; - int ret = 0; switch (funcid) { case SBI_EXT_SRST_RESET: @@ -146,24 +150,24 @@ static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, reason); - *exit = true; + retdata->uexit = true; break; case SBI_SRST_RESET_TYPE_COLD_REBOOT: case SBI_SRST_RESET_TYPE_WARM_REBOOT: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_RESET, reason); - *exit = true; + retdata->uexit = true; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = { diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c index 489f225ee66d..8f4c4fa16227 100644 --- a/arch/riscv/kvm/vcpu_sbi_v01.c +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -14,9 +14,7 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { ulong hmask; int i, ret = 0; @@ -24,6 +22,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_vcpu *rvcpu; struct kvm *kvm = vcpu->kvm; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_cpu_trap *utrap = retdata->utrap; switch (cp->a7) { case SBI_EXT_0_1_CONSOLE_GETCHAR: @@ -33,7 +32,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * handled in kernel so we forward these to user-space */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_SET_TIMER: #if __riscv_xlen == 32 @@ -48,8 +47,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, break; case SBI_EXT_0_1_SEND_IPI: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -65,14 +63,13 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_0_1_SHUTDOWN: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, 0); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_REMOTE_FENCE_I: case SBI_EXT_0_1_REMOTE_SFENCE_VMA: case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -103,7 +100,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, } break; default: - ret = -EINVAL; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index e27c2140d620..b519a1f045d8 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -23,9 +23,9 @@ #define memmove memmove #define memzero(s, n) memset((s), 0, (n)) -#ifdef CONFIG_KERNEL_BZIP2 +#if defined(CONFIG_KERNEL_BZIP2) #define BOOT_HEAP_SIZE 0x400000 -#elif CONFIG_KERNEL_ZSTD +#elif defined(CONFIG_KERNEL_ZSTD) #define BOOT_HEAP_SIZE 0x30000 #else #define BOOT_HEAP_SIZE 0x10000 @@ -80,6 +80,6 @@ void *decompress_kernel(void) void *output = (void *)decompress_offset; __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, 0, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, error); return output; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a7b4e1d82758..74b35ec2ad28 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -190,7 +190,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_CRYPTO_LIB_CURVE25519=m CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m @@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set @@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y -CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 2bc2d0fe5774..cec71268e3bc 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -181,7 +181,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRYPTO_LIB_CURVE25519=m @@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index ae14ab0b864d..a9c0c81d1de9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y -# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y @@ -50,6 +49,7 @@ CONFIG_ZFCP=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set +# CONFIG_LEGACY_TIOCSTI is not set # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set # CONFIG_HMC_DRV is not set diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index feaba12dbecb..efa103b52a1a 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -131,19 +131,21 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; -struct hws_trailer_entry { - union { - struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ - }; - unsigned long long flags; /* 0 - 63: All indicators */ +union hws_trailer_header { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + unsigned long long overflow; /* 64 - Overflow Count */ }; - unsigned long long overflow; /* 64 - sample Overflow count */ + __uint128_t val; +}; + +struct hws_trailer_entry { + union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ @@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi, return USEC_PER_SEC * qsi->cpu_speed / rate; } -#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL -#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL - /* Return TOD timestamp contained in an trailer entry */ static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te) { /* TOD in STCKE format */ - if (te->t) + if (te->header.t) return *((unsigned long long *) &te->timestamp[1]); /* TOD in STCK format */ diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 77f24262c25c..ac665b9670c5 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 1999, 2020 */ -#ifndef DEBUG_H -#define DEBUG_H +#ifndef _ASM_S390_DEBUG_H +#define _ASM_S390_DEBUG_H #include <linux/string.h> #include <linux/spinlock.h> @@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas); #endif /* MODULE */ -#endif /* DEBUG_H */ +#endif /* _ASM_S390_DEBUG_H */ diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index cb5fc0690435..081837b391e3 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -31,7 +31,7 @@ pcp_op_T__ *ptr__; \ preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ - prev__ = *ptr__; \ + prev__ = READ_ONCE(*ptr__); \ do { \ old__ = prev__; \ new__ = old__ op (val); \ diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index fc6d5f58debe..2df94d32140c 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - if (image->type == KEXEC_TYPE_CRASH) - buf.mem += crashk_res.start; ptr = (void *)ipl_cert_list_addr; end = ptr + ipl_cert_list_size; @@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + ret = kexec_add_buffer(&buf); out: return ret; diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 332a49965130..ce886a03545a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb) static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) { - unsigned long sdb, *trailer; + struct hws_trailer_entry *te; + unsigned long sdb; /* Allocate and initialize sample-data-block */ sdb = get_zeroed_page(gfp_flags); if (!sdb) return -ENOMEM; - trailer = trailer_entry_ptr(sdb); - *trailer = SDB_TE_ALERT_REQ_MASK; + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + te->header.a = 1; /* Link SDB into the sample-data-block-table */ *sdbt = sdb; @@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, "%s: Found unknown" " sampling data entry: te->f %i" " basic.def %#4x (%p)\n", __func__, - te->f, sample->def, sample); + te->header.f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, * that are not full. Stop processing if the first * invalid format was detected. */ - if (!te->f) + if (!te->header.f) break; } @@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, } } +static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new) +{ + asm volatile( + " cdsg %[old],%[new],%[ptr]\n" + : [old] "+d" (old), [ptr] "+QS" (*ptr) + : [new] "d" (new) + : "memory", "cc"); + return old; +} + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; + union hws_trailer_header old, prev, new; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); /* Leave loop if no more work to do (block full indicator) */ - if (!te->f) { + if (!te->header.f) { done = 1; if (!flush_all) break; } /* Check the sample overflow count */ - if (te->overflow) + if (te->header.overflow) /* Account sample overflows and, if a particular limit * is reached, extend the sampling buffer. * For details, see sfb_account_overflows(). */ - sampl_overflow += te->overflow; + sampl_overflow += te->header.overflow; /* Timestamps are valid for full sample-data-blocks only */ debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " "overflow %llu timestamp %#llx\n", - __func__, (unsigned long)sdbt, te->overflow, - (te->f) ? trailer_timestamp(te) : 0ULL); + __func__, (unsigned long)sdbt, te->header.overflow, + (te->header.f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and * flag if an (perf) event overflow happened. If so, the PMU @@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + old.val = prev.val; + new.val = prev.val; + new.f = 0; + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); /* Advance to next sample-data-block */ sdbt++; @@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle) range_scan = AUX_SDB_NUM_ALERT(aux); for (i = 0, idx = aux->head; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - if (!(te->flags & SDB_TE_BUFFER_FULL_MASK)) + if (!te->header.f) break; } /* i is num of SDBs which are full */ @@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle) /* Remove alert indicators in the buffer */ te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags &= ~SDB_TE_ALERT_REQ_MASK; + te->header.a = 0; debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", __func__, i, range_scan, aux->head); @@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | - SDB_TE_ALERT_REQ_MASK); - te->overflow = 0; + te->header.f = 0; + te->header.a = 0; + te->header.overflow = 0; } /* Save the position of empty SDBs */ aux->empty_mark = aux->head + range - 1; @@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle, /* Set alert indicator */ aux->alert_mark = aux->head + range/2 - 1; te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags = te->flags | SDB_TE_ALERT_REQ_MASK; + te->header.a = 1; /* Reset hardware buffer head */ head = AUX_SDB_INDEX(aux, aux->head); @@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle, static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; + union hws_trailer_header old, prev, new; struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + old.val = prev.val; + new.val = prev.val; + *overflow = old.overflow; + if (old.f) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); return true; } @@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + union hws_trailer_header old, prev, new; + unsigned long long orig_overflow; struct hws_trailer_entry *te; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " @@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + old.val = prev.val; + new.val = prev.val; + orig_overflow = old.overflow; + new.f = 0; + new.overflow = 0; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new.a = 1; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); *overflow += orig_overflow; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 2b6091349daa..696c9e007a36 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -508,6 +508,7 @@ static void __init setup_lowcore_dat_on(void) { struct lowcore *abs_lc; unsigned long flags; + int i; __ctl_clear_bit(0, 28); S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT; @@ -523,8 +524,8 @@ static void __init setup_lowcore_dat_on(void) abs_lc = get_abs_lowcore(&flags); abs_lc->restart_flags = RESTART_FLAG_CTLREGS; abs_lc->program_new_psw = S390_lowcore.program_new_psw; - memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area, - sizeof(abs_lc->cregs_save_area)); + for (i = 0; i < 16; i++) + abs_lc->cregs_save_area[i] = S390_lowcore.cregs_save_area[i]; put_abs_lowcore(abs_lc, flags); } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 5ea3830af0cc..cbf9c1b0beda 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -17,6 +17,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define RUNTIME_DISCARD_EXIT + #define EMITS_PT_NOTE #include <asm-generic/vmlinux.lds.h> @@ -79,6 +81,7 @@ SECTIONS _end_amode31_refs = .; } + . = ALIGN(PAGE_SIZE); _edata = .; /* End of data section */ /* will be freed after init */ @@ -193,6 +196,7 @@ SECTIONS BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE) + . = ALIGN(PAGE_SIZE); _end = . ; /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 3754d7937530..8edb3bee74b6 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index a889a3a938ba..d1ce73f3bd85 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -28,7 +28,7 @@ #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) -typedef struct { +typedef union { struct { unsigned long pmd_low; unsigned long pmd_high; diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 3161b9ccd2a5..b6276a3521d7 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ * Written by Niibe Yutaka and Paul Mundt */ OUTPUT_ARCH(sh) +#define RUNTIME_DISCARD_EXIT #include <asm/thread_info.h> #include <asm/cache.h> #include <asm/vmlinux.lds.h> diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9cf07322875a..73ed982d4100 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -14,13 +14,13 @@ endif ifdef CONFIG_CC_IS_GCC RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) -RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register) endif ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif +RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S index 5521ea12f44e..aa9b96457584 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -32,7 +32,7 @@ intcall: movw %dx, %si movw %sp, %di movw $11, %cx - rep; movsd + rep; movsl /* Pop full state from the stack */ popal @@ -67,7 +67,7 @@ intcall: jz 4f movw %sp, %si movw $11, %cx - rep; movsd + rep; movsl 4: addw $44, %sp /* Restore state and return */ diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d4a314cc50d6..321a5011042d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode) /* Load the new page-table. */ write_cr3(top_level_pgt); + + /* + * Now that the required page table mappings are established and a + * GHCB can be used, check for SNP guest/HV feature compatibility. + */ + snp_check_features(); } static pte_t *split_large_pmd(struct x86_mapping_info *info, diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 62208ec04ca4..20118fb7c53b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -126,6 +126,7 @@ static inline void console_init(void) #ifdef CONFIG_AMD_MEM_ENCRYPT void sev_enable(struct boot_params *bp); +void snp_check_features(void); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); void snp_set_page_private(unsigned long paddr); @@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp) if (bp) bp->cc_blob_address = 0; } +static inline void snp_check_features(void) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c93930d5ccbd..d63ad8f99f83 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void) error("Can't unmap GHCB page"); } +static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set, + unsigned int reason, u64 exit_info_2) +{ + u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + bool sev_es_check_ghcb_fault(unsigned long address) { /* Check whether the fault was on the GHCB page */ @@ -270,6 +287,59 @@ static void enforce_vmpl0(void) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } +/* + * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need + * guest side implementation for proper functioning of the guest. If any + * of these features are enabled in the hypervisor but are lacking guest + * side implementation, the behavior of the guest will be undefined. The + * guest could fail in non-obvious way making it difficult to debug. + * + * As the behavior of reserved feature bits is unknown to be on the + * safe side add them to the required features mask. + */ +#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \ + MSR_AMD64_SNP_REFLECT_VC | \ + MSR_AMD64_SNP_RESTRICTED_INJ | \ + MSR_AMD64_SNP_ALT_INJ | \ + MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_VMPL_SSS | \ + MSR_AMD64_SNP_SECURE_TSC | \ + MSR_AMD64_SNP_VMGEXIT_PARAM | \ + MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_RESERVED_BIT13 | \ + MSR_AMD64_SNP_RESERVED_BIT15 | \ + MSR_AMD64_SNP_RESERVED_MASK) + +/* + * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented + * by the guest kernel. As and when a new feature is implemented in the + * guest kernel, a corresponding bit should be added to the mask. + */ +#define SNP_FEATURES_PRESENT (0) + +void snp_check_features(void) +{ + u64 unsupported; + + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + return; + + /* + * Terminate the boot if hypervisor has enabled any feature lacking + * guest side implementation. Pass on the unsupported features mask through + * EXIT_INFO_2 of the GHCB protocol so that those features can be reported + * as part of the guest boot failure. + */ + unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + if (unsupported) { + if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN, + GHCB_SNP_UNSUPPORTED, unsupported); + } +} + void sev_enable(struct boot_params *bp) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index aa53d042b943..73bd0d70817e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6339,6 +6339,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: pmem = true; x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index a2834bc93149..551741e79e03 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -41,6 +41,7 @@ * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL + * MTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,50 +52,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL,RPL + * ICL,TGL,RKL,ADL,RPL,MTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, - * RPL,SPR + * RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL + * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL,RPL + * TNT,RKL,ADL,RPL,MTL * Scope: Package (physical package) * */ @@ -676,6 +677,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), @@ -686,6 +688,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6f1ccc57a692..459b1aafd4d4 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ecced3a52668..c65d8906cbcf 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: @@ -107,6 +108,8 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 65064d9f7fa6..8eb74cf386db 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -14,6 +14,7 @@ #include <asm/mmu.h> #include <asm/mpspec.h> #include <asm/x86_init.h> +#include <asm/cpufeature.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ unsigned long acpi_get_wakeup_address(void); +static inline bool acpi_skip_set_wakeup_address(void) +{ + return cpu_feature_enabled(X86_FEATURE_XENPV); +} + +#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address + /* * Check if the CPU can handle C2 and deeper */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b049d950612f..ca97442e8d49 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 37ff47552bcb..d3fe82c5d6b6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -566,6 +566,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 1f60a2b27936..fdbb5f07448f 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void) static void disable_freq_invariance_workfn(struct work_struct *work) { + int cpu; + static_branch_disable(&arch_scale_freq_key); + + /* + * Set arch_freq_scale to a default value on all cpus + * This negates the effect of scaling + */ + for_each_possible_cpu(cpu) + per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index efe0c30d3a12..77538abeb72a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid) return entry; } +static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) +{ + u64 msr_val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, msr_val); + + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; + + *val = msr_val; + return 0; +} + static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) @@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, struct arch_mbm_state *am; am = get_arch_mbm_state(hw_dom, rmid, eventid); - if (am) + if (am) { memset(am, 0, sizeof(*am)); + + /* Record any initial, non-zero count value. */ + __rmid_read(rmid, eventid, &am->prev_msr); + } } static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) @@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; u64 msr_val, chunks; + int ret; if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; - /* - * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured - * with a valid event code for supported resource type and the bits - * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, - * IA32_QM_CTR.data (bits 61:0) reports the monitored data. - * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) - * are error bits. - */ - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, msr_val); - - if (msr_val & RMID_VAL_ERROR) - return -EIO; - if (msr_val & RMID_VAL_UNAVAIL) - return -EINVAL; + ret = __rmid_read(rmid, eventid, &msr_val); + if (ret) + return ret; am = get_arch_mbm_state(hw_dom, rmid, eventid); if (am) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e5a48f05e787..5993da21d822 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk, /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. */ - barrier(); + smp_mb(); /* * By now, the task's closid and rmid are set. If the task is current @@ -2402,6 +2404,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, WRITE_ONCE(t->rmid, to->mon.rmid); /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + + /* * If the task is on a CPU, set the CPU in the mask. * The detection is inaccurate as tasks might move or * schedule before the smp function call takes place. diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 3aa5304200c5..4d8aff05a509 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index beb1bada1b0a..c683666876f1 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -65,8 +65,10 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); - for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } } void __init init_IRQ(void) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0f82c247e1fd..7896acf05117 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3539,18 +3539,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d3987359d441..cb258f58fdc8 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -26,6 +26,7 @@ #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> +#include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -804,6 +805,9 @@ void __init poking_init(void) poking_mm = mm_alloc(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 46de9cf5c91d..fb4b1b5e0dea 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, u8 mtrr_type, uniform; mtrr_type = mtrr_type_lookup(start, end, &uniform); - if (mtrr_type != MTRR_TYPE_WRBACK) + if (mtrr_type != MTRR_TYPE_WRBACK && + mtrr_type != MTRR_TYPE_INVALID) return _PAGE_CACHE_MODE_UC_MINUS; return _PAGE_CACHE_MODE_WB; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 758cbfe55daa..4b3efaa82ab7 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -12,6 +12,7 @@ */ #include <linux/acpi.h> +#include <linux/efi.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/bitmap.h> @@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } +static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +{ +#ifdef CONFIG_EFI + efi_memory_desc_t *md; + u64 size, mmio_start, mmio_end; + + for_each_efi_memory_desc(md) { + if (md->type == EFI_MEMORY_MAPPED_IO) { + size = md->num_pages << EFI_PAGE_SHIFT; + mmio_start = md->phys_addr; + mmio_end = mmio_start + size; + + /* + * N.B. Caller supplies (start, start + size), + * so to match, mmio_end is the first address + * *past* the EFI_MEMORY_MAPPED_IO area. + */ + if (mmio_start <= start && end <= mmio_end) + return true; + } + } +#endif + + return false; +} + typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type); static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) + struct device *dev, const char *method) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); u64 old_size = size; int num_buses; - char *method = with_e820 ? "E820" : "ACPI motherboard resources"; while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; @@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved in %s\n", + dev_info(dev, "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n", + pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { @@ -500,7 +526,8 @@ static bool __ref pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { - if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) + if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, + "ACPI motherboard resource")) return true; if (dev) @@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e "MMCONFIG at %pR not reserved in " "ACPI motherboard resources\n", &cfg->res); + + if (is_mmconf_reserved(is_efi_mmio, cfg, dev, + "EfiMemoryMappedIO")) + return true; } /* @@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); return false; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index b94f727251b6..8babce71915f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) { for (i = 0; i < msidesc->nvec_used; i++) xen_destroy_irq(msidesc->irq + i); + msidesc->irq = 0; } } @@ -433,6 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = { }; static struct msi_domain_info xen_pci_msi_domain_info = { + .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS, .ops = &xen_pci_msi_domain_ops, }; diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 48a3eb09d951..650cdbbdaf45 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf32_Half elf_core_extra_phdrs(void) +Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..9bdc3b656b2c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn) return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; } -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 228e4dff5fb2..a6d09fe04831 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -154,11 +154,6 @@ struct thread_struct { unsigned long ra; /* kernel's a0: return address and window call size */ unsigned long sp; /* kernel's a1: stack pointer */ - /* struct xtensa_cpuinfo info; */ - - unsigned long bad_vaddr; /* last user fault */ - unsigned long bad_uaddr; /* last kernel fault accessing user space */ - unsigned long error_code; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK]; struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK]; @@ -176,10 +171,6 @@ struct thread_struct { { \ ra: 0, \ sp: sizeof(init_stack) + (long) &init_stack, \ - /*info: {0}, */ \ - bad_vaddr: 0, \ - bad_uaddr: 0, \ - error_code: 0, \ } diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 0c25e035ff10..cd98366a9b23 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs) __die_if_kernel("Unhandled unaligned exception in kernel", regs, SIGKILL); - current->thread.bad_vaddr = regs->excvaddr; - current->thread.error_code = -3; pr_info_ratelimited("Unaligned memory access to %08lx in '%s' " "(pid = %d, pc = %#010lx)\n", regs->excvaddr, current->comm, diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 8c781b05c0bd..faf7cf35a0ee 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -206,8 +206,6 @@ good_area: bad_area: mmap_read_unlock(mm); if (user_mode(regs)) { - current->thread.bad_vaddr = address; - current->thread.error_code = is_write; force_sig_fault(SIGSEGV, code, (void *) address); return; } @@ -232,7 +230,6 @@ do_sigbus: /* Send a sigbus, regardless of whether we were in kernel * or user mode. */ - current->thread.bad_vaddr = address; force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address); /* Kernel mode? Handle exceptions or die */ @@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) if ((entry = search_exception_tables(regs->pc)) != NULL) { pr_debug("%s: Exception at pc=%#010lx (%lx)\n", current->comm, regs->pc, entry->fixup); - current->thread.bad_uaddr = address; regs->pc = entry->fixup; return; } |