diff options
| author | Paolo Bonzini <[email protected]> | 2024-07-12 11:24:12 -0400 |
|---|---|---|
| committer | Paolo Bonzini <[email protected]> | 2024-07-12 11:24:12 -0400 |
| commit | c8b8b8190a80b591aa73c27c70a668799f8db547 (patch) | |
| tree | 9d948c9aac89678abe64ac81f6c43348bf4b2091 /arch | |
| parent | f0a23883fad4ec8a63faddb9639a92be2e007624 (diff) | |
| parent | 492ac37fa38faf520b5beae44c930063265ee183 (diff) | |
Merge tag 'loongarch-kvm-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD
LoongArch KVM changes for v6.11
1. Add ParaVirt steal time support.
2. Add some VM migration enhancement.
3. Add perf kvm-stat support for loongarch.
Diffstat (limited to 'arch')
141 files changed, 1399 insertions, 815 deletions
diff --git a/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi index d80440446473..05d7a462ea25 100644 --- a/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi @@ -85,7 +85,7 @@ }; }; - panel { + panel_dpi: panel { compatible = "sii,43wvf1g"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_display_power>; diff --git a/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso index c84e9b052527..151e9cee3c87 100644 --- a/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso +++ b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso @@ -10,8 +10,6 @@ /plugin/; &{/} { - /delete-node/ panel; - hdmi: connector-hdmi { compatible = "hdmi-connector"; label = "hdmi"; @@ -82,6 +80,10 @@ }; }; +&panel_dpi { + status = "disabled"; +}; + &tve { status = "disabled"; }; diff --git a/arch/arm/boot/dts/rockchip/rk3066a.dtsi b/arch/arm/boot/dts/rockchip/rk3066a.dtsi index 30139f21de64..15cbd94d7ec0 100644 --- a/arch/arm/boot/dts/rockchip/rk3066a.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3066a.dtsi @@ -128,6 +128,7 @@ pinctrl-0 = <&hdmii2c_xfer>, <&hdmi_hpd>; power-domains = <&power RK3066_PD_VIO>; rockchip,grf = <&grf>; + #sound-dai-cells = <0>; status = "disabled"; ports { diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 78282ced5038..e408399d5f0e 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -14,6 +14,7 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> #include <asm/ptrace.h> +#include <asm/uaccess.h> #ifdef CONFIG_EFI void efi_init(void); @@ -25,6 +26,18 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, boo #define arch_efi_call_virt_setup() efi_virtmap_load() #define arch_efi_call_virt_teardown() efi_virtmap_unload() +#ifdef CONFIG_CPU_TTBR0_PAN +#undef arch_efi_call_virt +#define arch_efi_call_virt(p, f, args...) ({ \ + unsigned int flags = uaccess_save_and_enable(); \ + efi_status_t res = _Generic((p)->f(args), \ + efi_status_t: (p)->f(args), \ + default: ((p)->f(args), EFI_ABORTED)); \ + uaccess_restore(flags); \ + res; \ +}) +#endif + #define ARCH_EFI_IRQ_FLAGS_MASK \ (PSR_J_BIT | PSR_E_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | \ PSR_T_BIT | MODE_MASK) diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index a0b6d1e3812f..e61591f33a6c 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -232,11 +232,24 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long old; if (unlikely(atomic_read(¤t->tracing_graph_pause))) +err_out: return; if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) { - /* FP points one word below parent's top of stack */ - frame_pointer += 4; + /* + * Usually, the stack frames are contiguous in memory but cases + * have been observed where the next stack frame does not live + * at 'frame_pointer + 4' as this code used to assume. + * + * Instead, dereference the field in the stack frame that + * stores the SP of the calling frame: to avoid unbounded + * recursion, this cannot involve any ftrace instrumented + * functions, so use the __get_kernel_nofault() primitive + * directly. + */ + __get_kernel_nofault(&frame_pointer, + (unsigned long *)(frame_pointer - 8), + unsigned long, err_out); } else { struct stackframe frame = { .fp = frame_pointer, diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 4768b05fd765..98544741ce17 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -6,6 +6,7 @@ #include <dt-bindings/phy/phy-imx8-pcie.h> #include <dt-bindings/pwm/pwm.h> #include "imx8mm.dtsi" +#include "imx8mm-overdrive.dtsi" / { chosen { @@ -935,7 +936,7 @@ /* Verdin GPIO_9_DSI (pulled-up as active-low) */ pinctrl_gpio_9_dsi: gpio9dsigrp { fsl,pins = - <MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15 0x146>; /* SODIMM 17 */ + <MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15 0x1c6>; /* SODIMM 17 */ }; /* Verdin GPIO_10_DSI (pulled-up as active-low) */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 43f1d45ccc96..f5115f9e8c47 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -254,7 +254,7 @@ <&clk IMX8MP_CLK_CLKOUT2>, <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <13000000>, <13000000>, <156000000>; + assigned-clock-rates = <13000000>, <13000000>, <208000000>; reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index dec57fad6828..e2b5e7ac3e46 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -219,7 +219,7 @@ bluetooth { compatible = "brcm,bcm4330-bt"; - shutdown-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 5c6b39c6933f..6e05361c1ffb 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -36,7 +36,7 @@ regulator-name = "SD1_SPWR"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3000000>; - gpio = <&lsio_gpio4 19 GPIO_ACTIVE_HIGH>; + gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index d400d85f42a9..bd98eff4d685 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -296,7 +296,6 @@ vmmc-supply = <®_usdhc2_vmmc>; bus-width = <4>; status = "okay"; - no-sdio; no-mmc; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts index b47fe02c33fb..079101cddd65 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts @@ -5,6 +5,8 @@ */ /dts-v1/; + +#include <dt-bindings/leds/common.h> #include "rk3308.dtsi" / { @@ -24,17 +26,21 @@ leds { compatible = "gpio-leds"; pinctrl-names = "default"; - pinctrl-0 = <&green_led_gio>, <&heartbeat_led_gpio>; + pinctrl-0 = <&green_led>, <&heartbeat_led>; green-led { + color = <LED_COLOR_ID_GREEN>; default-state = "on"; + function = LED_FUNCTION_POWER; gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>; label = "rockpis:green:power"; linux,default-trigger = "default-on"; }; blue-led { + color = <LED_COLOR_ID_BLUE>; default-state = "on"; + function = LED_FUNCTION_HEARTBEAT; gpios = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>; label = "rockpis:blue:user"; linux,default-trigger = "heartbeat"; @@ -126,10 +132,12 @@ }; &emmc { - bus-width = <4>; cap-mmc-highspeed; - mmc-hs200-1_8v; + cap-sd-highspeed; + no-sdio; non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>; vmmc-supply = <&vcc_io>; status = "okay"; }; @@ -214,11 +222,11 @@ pinctrl-0 = <&rtc_32k>; leds { - green_led_gio: green-led-gpio { + green_led: green-led { rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>; }; - heartbeat_led_gpio: heartbeat-led-gpio { + heartbeat_led: heartbeat-led { rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi index 962ea893999b..c00da150a22f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi @@ -811,7 +811,7 @@ clocks = <&cru SCLK_I2S2_8CH_TX_OUT>, <&cru SCLK_I2S2_8CH_RX_OUT>, <&cru PCLK_ACODEC>; - reset-names = "codec-reset"; + reset-names = "codec"; resets = <&cru SRST_ACODEC_P>; #sound-dai-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts index f09d60bbe6c4..a608a219543e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts @@ -241,8 +241,8 @@ rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; - interrupt-parent = <&gpio2>; - interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&gpio0>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <1>; clock-output-names = "xin32k", "rk805-clkout2"; gpio-controller; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index 734f87db4d11..73618df7a889 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -793,6 +793,7 @@ dma-names = "tx"; pinctrl-names = "default"; pinctrl-0 = <&spdif_tx>; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -804,6 +805,7 @@ clocks = <&cru SCLK_I2S_2CH>, <&cru HCLK_I2S_2CH>; dmas = <&dmac_bus 6>, <&dmac_bus 7>; dma-names = "tx", "rx"; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -817,6 +819,7 @@ dma-names = "tx", "rx"; pinctrl-names = "default"; pinctrl-0 = <&i2s_8ch_bus>; + #sound-dai-cells = <0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 789fd0dcc88b..3cd63d1e8f15 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -450,7 +450,7 @@ ap_i2c_audio: &i2c8 { dlg,btn-cfg = <50>; dlg,mic-det-thr = <500>; dlg,jack-ins-deb = <20>; - dlg,jack-det-rate = "32ms_64ms"; + dlg,jack-det-rate = "32_64"; dlg,jack-rem-deb = <1>; dlg,a-d-btn-thr = <0xa>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts index 26322a358d91..b908ce006c26 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts @@ -289,7 +289,7 @@ regulator-name = "vdd_gpu"; regulator-always-on; regulator-boot-on; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <500000>; regulator-max-microvolt = <1350000>; regulator-ramp-delay = <6001>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index 1a604429fb26..e74871491ef5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -444,6 +444,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts index b4f22d95ac0e..e80caa36f8e4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts @@ -435,6 +435,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index b8e15b76a8a6..2e7512676b7e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -383,6 +383,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; sd-uhs-sdr104; vmmc-supply = <&vcc_3v3_s3>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi index aebe1fedd2d8..615094bb8ba3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi @@ -344,6 +344,11 @@ }; }; +&pwm0 { + pinctrl-0 = <&pwm0m1_pins>; + pinctrl-names = "default"; +}; + &saradc { vref-supply = <&vcc_1v8_s0>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts index 3b2ec1d0c542..074c316a9a69 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts @@ -288,9 +288,9 @@ pinctrl-0 = <&i2c7m0_xfer>; status = "okay"; - es8316: audio-codec@11 { + es8316: audio-codec@10 { compatible = "everest,es8316"; - reg = <0x11>; + reg = <0x10>; assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; assigned-clock-rates = <12288000>; clocks = <&cru I2S0_8CH_MCLKOUT>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts index 8e2a07612d17..3b9a349362db 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts @@ -366,6 +366,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; @@ -393,6 +394,7 @@ pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, <&rk806_dvs2_null>, <&rk806_dvs3_null>; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 4ff0ae3f6d66..41fd90895dfc 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -153,8 +153,9 @@ extern void __memset_io(volatile void __iomem *, int, size_t); * emit the large TLP from the CPU. */ -static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to, - const u32 *from, size_t count) +static __always_inline void +__const_memcpy_toio_aligned32(volatile u32 __iomem *to, const u32 *from, + size_t count) { switch (count) { case 8: @@ -196,24 +197,22 @@ static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to, void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count); -static inline void __const_iowrite32_copy(void __iomem *to, const void *from, - size_t count) +static __always_inline void +__iowrite32_copy(void __iomem *to, const void *from, size_t count) { - if (count == 8 || count == 4 || count == 2 || count == 1) { + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { __const_memcpy_toio_aligned32(to, from, count); dgh(); } else { __iowrite32_copy_full(to, from, count); } } +#define __iowrite32_copy __iowrite32_copy -#define __iowrite32_copy(to, from, count) \ - (__builtin_constant_p(count) ? \ - __const_iowrite32_copy(to, from, count) : \ - __iowrite32_copy_full(to, from, count)) - -static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to, - const u64 *from, size_t count) +static __always_inline void +__const_memcpy_toio_aligned64(volatile u64 __iomem *to, const u64 *from, + size_t count) { switch (count) { case 8: @@ -255,21 +254,18 @@ static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to, void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count); -static inline void __const_iowrite64_copy(void __iomem *to, const void *from, - size_t count) +static __always_inline void +__iowrite64_copy(void __iomem *to, const void *from, size_t count) { - if (count == 8 || count == 4 || count == 2 || count == 1) { + if (__builtin_constant_p(count) && + (count == 8 || count == 4 || count == 2 || count == 1)) { __const_memcpy_toio_aligned64(to, from, count); dgh(); } else { __iowrite64_copy_full(to, from, count); } } - -#define __iowrite64_copy(to, from, count) \ - (__builtin_constant_p(count) ? \ - __const_iowrite64_copy(to, from, count) : \ - __iowrite64_copy_full(to, from, count)) +#define __iowrite64_copy __iowrite64_copy /* * I/O memory mapping functions. diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 9943ff0af4c9..1f60aa1bc750 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -170,6 +170,7 @@ #define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ +#define PTE_SWBITS_MASK _AT(pteval_t, (BIT(63) | GENMASK(58, 55))) #define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) #ifdef CONFIG_ARM64_PA_BITS_52 diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 266b96acc014..1386e8e751f2 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -840,7 +840,7 @@ __SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SYSCALL(__NR_io_pgetevents_time64, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index dd6ce86d4332..b776e7424fe9 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -462,6 +462,9 @@ static int run_all_insn_set_hw_mode(unsigned int cpu) for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) { struct insn_emulation *insn = insn_emulations[i]; bool enable = READ_ONCE(insn->current_mode) == INSN_HW; + if (insn->status == INSN_UNAVAILABLE) + continue; + if (insn->set_hw_mode && insn->set_hw_mode(enable)) { pr_warn("CPU[%u] cannot support the emulation of %s", cpu, insn->name); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4a92096db34e..712718aed5dd 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/kmemleak.h> #include <linux/screen_info.h> #include <linux/vmalloc.h> @@ -213,6 +214,7 @@ l: if (!p) { return -ENOMEM; } + kmemleak_not_leak(p); efi_rt_stack_top = p + THREAD_SIZE; return 0; } diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index 5fa08e13e17e..f374a3e5a5fe 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -173,7 +173,7 @@ static void __init remap_idmap_for_lpa2(void) * Don't bother with the FDT, we no longer need it after this. */ memset(init_idmap_pg_dir, 0, - (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end); + (u64)init_idmap_pg_end - (u64)init_idmap_pg_dir); create_init_idmap(init_idmap_pg_dir, mask); dsb(ishst); diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index ad198262b981..7230f6e20ab8 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -53,17 +53,15 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, syscall_set_return_value(current, regs, 0, ret); /* - * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), - * but not enough for arm64 stack utilization comfort. To keep - * reasonable stack head room, reduce the maximum offset to 9 bits. + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints: the AAPCS mandates a + * 16-byte aligned SP at function boundaries, which will remove the + * 4 low bits from any entropy chosen here. * - * The actual entropy will be further reduced by the compiler when - * applying stack alignment constraints: the AAPCS mandates a - * 16-byte (i.e. 4-bit) aligned SP at function boundaries. - * - * The resulting 5 bits of entropy is seen in SP[8:4]. + * The resulting 6 bits of entropy is seen in SP[9:4]. */ - choose_random_kstack_offset(get_random_u16() & 0x1FF); + choose_random_kstack_offset(get_random_u16()); } static inline bool has_syscall_work(unsigned long flags) diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 02746f9d0980..efb053af331c 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -177,6 +177,14 @@ static void ffa_retrieve_req(struct arm_smccc_res *res, u32 len) res); } +static void ffa_rx_release(struct arm_smccc_res *res) +{ + arm_smccc_1_1_smc(FFA_RX_RELEASE, + 0, 0, + 0, 0, 0, 0, 0, + res); +} + static void do_ffa_rxtx_map(struct arm_smccc_res *res, struct kvm_cpu_context *ctxt) { @@ -543,16 +551,19 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res, if (WARN_ON(offset > len || fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) { ret = FFA_RET_ABORTED; + ffa_rx_release(res); goto out_unlock; } if (len > ffa_desc_buf.len) { ret = FFA_RET_NO_MEMORY; + ffa_rx_release(res); goto out_unlock; } buf = ffa_desc_buf.buf; memcpy(buf, hyp_buffers.rx, fraglen); + ffa_rx_release(res); for (fragoff = fraglen; fragoff < len; fragoff += fraglen) { ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff); @@ -563,6 +574,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res, fraglen = res->a3; memcpy((void *)buf + fragoff, hyp_buffers.rx, fraglen); + ffa_rx_release(res); } ffa_mem_reclaim(res, handle_lo, handle_hi, flags); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 8f5b7a3e7009..7f68cf58b978 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -391,7 +391,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index a3983a631b5a..9e50928f5d7d 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -919,8 +919,19 @@ free: return ret; } -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg) +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg) { + struct kvm_vcpu *vcpu; + unsigned long c; + + lockdep_assert_held(&kvm->arch.config_lock); + + /* Garbage collect the region */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (vcpu->arch.vgic_cpu.rdreg == rdreg) + vcpu->arch.vgic_cpu.rdreg = NULL; + } + list_del(&rdreg->list); kfree(rdreg); } @@ -945,7 +956,7 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 6106ebd5ba42..03d356a12377 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -316,7 +316,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg); +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 9f9486de0004..a3edced29ac1 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -376,7 +376,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, * clearing access/dirty for the whole block. */ unsigned long start = addr; - unsigned long end = start + nr; + unsigned long end = start + nr * PAGE_SIZE; if (pte_cont(__ptep_get(ptep + nr - 1))) end = ALIGN(end, CONT_PTE_SIZE); @@ -386,7 +386,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, ptep = contpte_align_down(ptep); } - __clear_young_dirty_ptes(vma, start, ptep, end - start, flags); + __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index c927e9312f10..353ea5dc32b8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -124,7 +124,8 @@ bool pgattr_change_is_safe(u64 old, u64 new) * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ - pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG; + pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG | + PTE_SWBITS_MASK; /* creating or taking down mappings is always safe */ if (!pte_valid(__pte(old)) || !pte_valid(__pte(new))) diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index 7ff6a2466af1..e0594b6370a6 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -6,6 +6,7 @@ #define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYNC_FILE_RANGE2 #include <asm-generic/unistd.h> #define __NR_set_thread_area (__NR_arch_specific_syscall + 0) diff --git a/arch/csky/kernel/syscall.c b/arch/csky/kernel/syscall.c index 3d30e58a45d2..4540a271ee39 100644 --- a/arch/csky/kernel/syscall.c +++ b/arch/csky/kernel/syscall.c @@ -20,7 +20,7 @@ SYSCALL_DEFINE6(mmap2, unsigned long, prot, unsigned long, flags, unsigned long, fd, - off_t, offset) + unsigned long, offset) { if (unlikely(offset & (~PAGE_MASK >> 12))) return -EINVAL; diff --git a/arch/hexagon/include/asm/syscalls.h b/arch/hexagon/include/asm/syscalls.h new file mode 100644 index 000000000000..40f2d08bec92 --- /dev/null +++ b/arch/hexagon/include/asm/syscalls.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <asm-generic/syscalls.h> + +asmlinkage long sys_hexagon_fadvise64_64(int fd, int advice, + u32 a2, u32 a3, u32 a4, u32 a5); diff --git a/arch/hexagon/include/uapi/asm/unistd.h b/arch/hexagon/include/uapi/asm/unistd.h index 432c4db1b623..21ae22306b5d 100644 --- a/arch/hexagon/include/uapi/asm/unistd.h +++ b/arch/hexagon/include/uapi/asm/unistd.h @@ -36,5 +36,6 @@ #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYNC_FILE_RANGE2 #include <asm-generic/unistd.h> diff --git a/arch/hexagon/kernel/syscalltab.c b/arch/hexagon/kernel/syscalltab.c index 0fadd582cfc7..5d98bdc494ec 100644 --- a/arch/hexagon/kernel/syscalltab.c +++ b/arch/hexagon/kernel/syscalltab.c @@ -14,6 +14,13 @@ #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +SYSCALL_DEFINE6(hexagon_fadvise64_64, int, fd, int, advice, + SC_ARG64(offset), SC_ARG64(len)) +{ + return ksys_fadvise64_64(fd, SC_VAL64(loff_t, offset), SC_VAL64(loff_t, len), advice); +} +#define sys_fadvise64_64 sys_hexagon_fadvise64_64 + void *sys_call_table[__NR_syscalls] = { #include <asm/unistd.h> }; diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e38139c576ee..b81d0eba5c7e 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -143,7 +143,7 @@ config LOONGARCH select HAVE_LIVEPATCH select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS + select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -261,6 +261,9 @@ config AS_HAS_EXPLICIT_RELOCS config AS_HAS_FCSR_CLASS def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0) +config AS_HAS_THIN_ADD_SUB + def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) + config AS_HAS_LSX_EXTENSION def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0) @@ -646,6 +649,17 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + depends on PARAVIRT + help + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + endmenu config ARCH_SELECT_MEMORY_MODEL diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug index 98d60630c3d4..8b2ce5b5d43e 100644 --- a/arch/loongarch/Kconfig.debug +++ b/arch/loongarch/Kconfig.debug @@ -28,6 +28,7 @@ config UNWINDER_PROLOGUE config UNWINDER_ORC bool "ORC unwinder" + depends on HAVE_OBJTOOL select OBJTOOL help This option enables the ORC (Oops Rewind Capability) unwinder for diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts index 8aefb0c12672..a34734a6c3ce 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts @@ -44,14 +44,14 @@ &gmac0 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; bus_id = <0x0>; }; &gmac1 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; bus_id = <0x1>; }; diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts index 8463fe035386..23cf26cc3e5f 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts @@ -43,7 +43,7 @@ &gmac0 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy0>; mdio { compatible = "snps,dwmac-mdio"; @@ -58,7 +58,7 @@ &gmac1 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy1>; mdio { compatible = "snps,dwmac-mdio"; diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts index 74b99bd234cc..ea9e6985d0e9 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts @@ -92,7 +92,7 @@ &gmac2 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy2>; mdio { compatible = "snps,dwmac-mdio"; diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 21447fb1efc7..d78330916bd1 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -75,6 +75,8 @@ do { \ #define CSR_MWPC_NUM 0x3f #define CTRL_PLV_ENABLE 0x1e +#define CTRL_PLV0_ENABLE 0x02 +#define CTRL_PLV3_ENABLE 0x10 #define MWPnCFG3_LoadEn 8 #define MWPnCFG3_StoreEn 9 @@ -101,7 +103,7 @@ struct perf_event; struct perf_event_attr; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset); + int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); extern int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index c87b6ea0ec47..fe38f98eeff8 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -30,12 +30,17 @@ #define KVM_PRIVATE_MEM_SLOTS 0 #define KVM_HALT_POLL_NS_DEFAULT 500000 +#define KVM_REQ_TLB_FLUSH_GPA KVM_ARCH_REQ(0) +#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(1) #define KVM_GUESTDBG_SW_BP_MASK \ (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP) #define KVM_GUESTDBG_VALID_MASK \ (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP | KVM_GUESTDBG_SINGLESTEP) +#define KVM_DIRTY_LOG_MANUAL_CAPS \ + (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | KVM_DIRTY_LOG_INITIALLY_SET) + struct kvm_vm_stat { struct kvm_vm_stat_generic generic; u64 pages; @@ -190,6 +195,7 @@ struct kvm_vcpu_arch { /* vcpu's vpid */ u64 vpid; + gpa_t flush_gpa; /* Frequency of stable timer in Hz */ u64 timer_mhz; @@ -201,6 +207,13 @@ struct kvm_vcpu_arch { struct kvm_mp_state mp_state; /* cpucfg */ u32 cpucfg[KVM_MAX_CPUCFG_REGS]; + + /* paravirt steal time */ + struct { + u64 guest_addr; + u64 last_steal; + struct gfn_to_hva_cache cache; + } st; }; static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg) diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h index 4ba2312e5f8c..335fb86778e2 100644 --- a/arch/loongarch/include/asm/kvm_para.h +++ b/arch/loongarch/include/asm/kvm_para.h @@ -14,6 +14,7 @@ #define KVM_HCALL_SERVICE HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SERVICE) #define KVM_HCALL_FUNC_IPI 1 +#define KVM_HCALL_FUNC_NOTIFY 2 #define KVM_HCALL_SWDBG HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SWDBG) @@ -24,6 +25,16 @@ #define KVM_HCALL_INVALID_CODE -1UL #define KVM_HCALL_INVALID_PARAMETER -2UL +#define KVM_STEAL_PHYS_VALID BIT_ULL(0) +#define KVM_STEAL_PHYS_MASK GENMASK_ULL(63, 6) + +struct kvm_steal_time { + __u64 steal; + __u32 version; + __u32 flags; + __u32 pad[12]; +}; + /* * Hypercall interface for KVM hypervisor * diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h index 590a92cb5416..c416cb7125c0 100644 --- a/arch/loongarch/include/asm/kvm_vcpu.h +++ b/arch/loongarch/include/asm/kvm_vcpu.h @@ -120,4 +120,9 @@ static inline void kvm_write_reg(struct kvm_vcpu *vcpu, int num, unsigned long v vcpu->arch.gprs[num] = val; } +static inline bool kvm_pvtime_supported(void) +{ + return !!sched_info_on(); +} + #endif /* __ASM_LOONGARCH_KVM_VCPU_H__ */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index eb09adda54b7..7a4633ef284b 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -169,6 +169,7 @@ #define KVM_SIGNATURE "KVM\0" #define CPUCFG_KVM_FEATURE (CPUCFG_KVM_BASE + 4) #define KVM_FEATURE_IPI BIT(1) +#define KVM_FEATURE_STEAL_TIME BIT(2) #ifndef __ASSEMBLY__ diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index 27f319b49862..b5f9de9f102e 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu); static inline void early_numa_add_cpu(int cpuid, s16 node) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void set_cpuid_to_node(int cpuid, s16 node) { } static inline int early_cpu_to_node(int cpu) { diff --git a/arch/loongarch/include/asm/paravirt.h b/arch/loongarch/include/asm/paravirt.h index 0965710f47f2..dddec49671ae 100644 --- a/arch/loongarch/include/asm/paravirt.h +++ b/arch/loongarch/include/asm/paravirt.h @@ -18,6 +18,7 @@ static inline u64 paravirt_steal_clock(int cpu) } int __init pv_ipi_init(void); +int __init pv_time_init(void); #else @@ -26,5 +27,9 @@ static inline int pv_ipi_init(void) return 0; } +static inline int pv_time_init(void) +{ + return 0; +} #endif // CONFIG_PARAVIRT #endif diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 45b507a7b06f..d9eafd3ee3d1 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -42,7 +42,7 @@ .macro JUMP_VIRT_ADDR temp1 temp2 li.d \temp1, CACHE_BASE pcaddi \temp2, 0 - or \temp1, \temp1, \temp2 + bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0 jirl zero, \temp1, 0xc .endm diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h index f9abef382317..ddc5cab0ffd0 100644 --- a/arch/loongarch/include/uapi/asm/kvm.h +++ b/arch/loongarch/include/uapi/asm/kvm.h @@ -81,7 +81,11 @@ struct kvm_fpu { #define LOONGARCH_REG_64(TYPE, REG) (TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT)) #define KVM_IOC_CSRID(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG) #define KVM_IOC_CPUCFG(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG) + +/* Device Control API on vcpu fd */ #define KVM_LOONGARCH_VCPU_CPUCFG 0 +#define KVM_LOONGARCH_VCPU_PVTIME_CTRL 1 +#define KVM_LOONGARCH_VCPU_PVTIME_GPA 0 struct kvm_debug_exit_arch { }; diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index c4f7de2e2805..4677ea8fa8e9 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -22,7 +22,7 @@ _head: .word MZ_MAGIC /* "MZ", MS-DOS header */ .org 0x8 - .dword kernel_entry /* Kernel entry point */ + .dword _kernel_entry /* Kernel entry point (physical address) */ .dword _kernel_asize /* Kernel image effective size */ .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index fc55c4de2a11..621ad7634df7 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) static int hw_breakpoint_control(struct perf_event *bp, enum hw_breakpoint_ops ops) { - u32 ctrl; + u32 ctrl, privilege; int i, max_slots, enable; + struct pt_regs *regs; struct perf_event **slots; struct arch_hw_breakpoint *info = counter_arch_bp(bp); + if (arch_check_bp_in_kernelspace(info)) + privilege = CTRL_PLV0_ENABLE; + else + privilege = CTRL_PLV3_ENABLE; + + /* Whether bp belongs to a task. */ + if (bp->hw.target) + regs = task_pt_regs(bp->hw.target); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { /* Breakpoint */ slots = this_cpu_ptr(bp_on_reg); @@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp, switch (ops) { case HW_BREAKPOINT_INSTALL: /* Set the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); - write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); - write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); - write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { - write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, privilege); } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + if (bp->hw.target) + regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, 0); - write_wb_reg(CSR_CFG_ADDR, i, 1, 0); - write_wb_reg(CSR_CFG_MASK, i, 0, 0); - write_wb_reg(CSR_CFG_MASK, i, 1, 0); - write_wb_reg(CSR_CFG_CTRL, i, 0, 0); - write_wb_reg(CSR_CFG_CTRL, i, 1, 0); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + } + if (bp->hw.target) + regs->csr_prmd &= ~CSR_PRMD_PWE; break; } @@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset) + int *gen_len, int *gen_type) { /* Type */ switch (ctrl.type) { @@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } - if (!ctrl.len) - return -EINVAL; - - *offset = __ffs(ctrl.len); - /* Len */ switch (ctrl.len) { case LOONGARCH_BREAKPOINT_LEN_1: @@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, struct arch_hw_breakpoint *hw) { int ret; - u64 alignment_mask, offset; + u64 alignment_mask; /* Build the arch_hw_breakpoint. */ ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) - alignment_mask = 0x7; - else + if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { alignment_mask = 0x3; - offset = hw->address & alignment_mask; - - hw->address &= ~alignment_mask; - hw->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + } return 0; } @@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(bp_on_reg); for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { - bp = slots[i]; - if (bp == NULL) - continue; - perf_bp_event(bp, regs); + if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_FWPS); + update_bp_registers(regs, 0, 0); + } } - update_bp_registers(regs, 0, 0); } NOKPROBE_SYMBOL(breakpoint_handler); @@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { - wp = slots[i]; - if (wp == NULL) - continue; - perf_bp_event(wp, regs); + if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_MWPS); + update_bp_registers(regs, 0, 1); + } } - update_bp_registers(regs, 0, 1); } NOKPROBE_SYMBOL(watchpoint_handler); diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index 1633ed4f692f..9abe8b71aa48 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -4,11 +4,14 @@ #include <linux/interrupt.h> #include <linux/jump_label.h> #include <linux/kvm_para.h> +#include <linux/reboot.h> #include <linux/static_call.h> #include <asm/paravirt.h> +static int has_steal_clock; struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; +static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); static u64 native_steal_clock(int cpu) { @@ -17,6 +20,34 @@ static u64 native_steal_clock(int cpu) DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); +static bool steal_acc = true; + +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} +early_param("no-steal-acc", parse_no_stealacc); + +static u64 paravt_steal_clock(int cpu) +{ + int version; + u64 steal; + struct kvm_steal_time *src; + + src = &per_cpu(steal_time, cpu); + do { + + version = src->version; + virt_rmb(); /* Make sure that the version is read before the steal */ + steal = src->steal; + virt_rmb(); /* Make sure that the steal is read before the next version */ + + } while ((version & 1) || (version != src->version)); + + return steal; +} + #ifdef CONFIG_SMP static void pv_send_ipi_single(int cpu, unsigned int action) { @@ -149,3 +180,117 @@ int __init pv_ipi_init(void) return 0; } + +static int pv_enable_steal_time(void) +{ + int cpu = smp_processor_id(); + unsigned long addr; + struct kvm_steal_time *st; + + if (!has_steal_clock) + return -EPERM; + + st = &per_cpu(steal_time, cpu); + addr = per_cpu_ptr_to_phys(st); + + /* The whole structure kvm_steal_time should be in one page */ + if (PFN_DOWN(addr) != PFN_DOWN(addr + sizeof(*st))) { + pr_warn("Illegal PV steal time addr %lx\n", addr); + return -EFAULT; + } + + addr |= KVM_STEAL_PHYS_VALID; + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, addr); + + return 0; +} + +static void pv_disable_steal_time(void) +{ + if (has_steal_clock) + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, 0); +} + +#ifdef CONFIG_SMP +static int pv_time_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_enable_steal_time(); + local_irq_restore(flags); + + return 0; +} + +static int pv_time_cpu_down_prepare(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_disable_steal_time(); + local_irq_restore(flags); + + return 0; +} +#endif + +static void pv_cpu_reboot(void *unused) +{ + pv_disable_steal_time(); +} + +static int pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) +{ + on_each_cpu(pv_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block pv_reboot_nb = { + .notifier_call = pv_reboot_notify, +}; + +int __init pv_time_init(void) +{ + int r, feature; + + if (!cpu_has_hypervisor) + return 0; + if (!kvm_para_available()) + return 0; + + feature = read_cpucfg(CPUCFG_KVM_FEATURE); + if (!(feature & KVM_FEATURE_STEAL_TIME)) + return 0; + + has_steal_clock = 1; + r = pv_enable_steal_time(); + if (r < 0) { + has_steal_clock = 0; + return 0; + } + register_reboot_notifier(&pv_reboot_nb); + +#ifdef CONFIG_SMP + r = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "loongarch/pv_time:online", + pv_time_cpu_online, pv_time_cpu_down_prepare); + if (r < 0) { + has_steal_clock = 0; + pr_err("Failed to install cpu hotplug callbacks\n"); + return r; + } +#endif + + static_call_update(pv_steal_clock, paravt_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); +#endif + + pr_info("Using paravirt steal-time\n"); + + return 0; +} diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index c114c5ef1332..200109de1971 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, offset; + int err, len, type; - err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + err = arch_bp_generic_fields(ctrl, &len, &type); if (err) return err; - switch (note_type) { - case NT_LOONGARCH_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_LOONGARCH_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: - return -EINVAL; - } - attr->bp_len = len; attr->bp_type = type; - attr->bp_addr += offset; return 0; } @@ -609,10 +595,27 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, return PTR_ERR(bp); attr = bp->attr; - decode_ctrl_reg(uctrl, &ctrl); - err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); - if (err) - return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case NT_LOONGARCH_HW_WATCH: + decode_ctrl_reg(uctrl, &ctrl); + break; + default: + return -EINVAL; + } + + if (uctrl & CTRL_PLV_ENABLE) { + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + attr.disabled = 0; + } else { + attr.disabled = 1; + } return modify_user_hw_breakpoint(bp, &attr); } @@ -643,6 +646,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; + /* Kernel-space address cannot be monitored by user-space */ + if ((unsigned long)addr >= XKPRANGE) + return -EINVAL; + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 60e0fe97f61a..3d048f1be143 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -282,7 +282,7 @@ static void __init fdt_setup(void) return; /* Prefer to use built-in dtb, checking its legality first. */ - if (!fdt_check_header(__dtb_start)) + if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start)) fdt_pointer = __dtb_start; else fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */ @@ -351,10 +351,8 @@ void __init platform_init(void) arch_reserve_vmcore(); arch_reserve_crashkernel(); -#ifdef CONFIG_ACPI_TABLE_UPGRADE - acpi_table_upgrade(); -#endif #ifdef CONFIG_ACPI + acpi_table_upgrade(); acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 0dfe2388ef41..1436d2465939 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -273,7 +273,6 @@ static void __init fdt_smp_setup(void) if (cpuid == loongson_sysconf.boot_cpu_id) { cpu = 0; - numa_add_cpu(cpu); } else { cpu = cpumask_next_zero(-1, cpu_present_mask); } @@ -283,6 +282,9 @@ static void __init fdt_smp_setup(void) set_cpu_present(cpu, true); __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; + + early_numa_add_cpu(cpu, 0); + set_cpuid_to_node(cpuid, 0); } loongson_sysconf.nr_cpus = num_processors; @@ -468,6 +470,7 @@ void smp_prepare_boot_cpu(void) set_cpu_possible(0, true); set_cpu_online(0, true); set_my_cpu_offset(per_cpu_offset(0)); + numa_add_cpu(0); rr_node = first_node(node_online_map); for_each_possible_cpu(cpu) { diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index b4c5acd7aa3b..8801611143ab 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -22,7 +22,7 @@ #define __SYSCALL(nr, call) [nr] = (call), SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, - prot, unsigned long, flags, unsigned long, fd, off_t, offset) + prot, unsigned long, flags, unsigned long, fd, unsigned long, offset) { if (offset & ~PAGE_MASK) return -EINVAL; diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index fd5354f9be7c..46d7d40c87e3 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -15,6 +15,7 @@ #include <asm/cpu-features.h> #include <asm/loongarch.h> +#include <asm/paravirt.h> #include <asm/time.h> u64 cpu_clock_freq; @@ -214,4 +215,5 @@ void __init time_init(void) constant_clockevent_init(); constant_clocksource_init(); + pv_time_init(); } diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index e8e97dbf9ca4..3c7595342730 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -6,6 +6,7 @@ #define PAGE_SIZE _PAGE_SIZE #define RO_EXCEPTION_TABLE_ALIGN 4 +#define PHYSADDR_MASK 0xffffffffffff /* 48-bit */ /* * Put .bss..swapper_pg_dir as the first thing in .bss. This will @@ -142,10 +143,11 @@ SECTIONS #ifdef CONFIG_EFI_STUB /* header symbols */ - _kernel_asize = _end - _text; - _kernel_fsize = _edata - _text; - _kernel_vsize = _end - __initdata_begin; - _kernel_rsize = _edata - __initdata_begin; + _kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK); + _kernel_asize = ABSOLUTE(_end - _text); + _kernel_fsize = ABSOLUTE(_edata - _text); + _kernel_vsize = ABSOLUTE(_end - __initdata_begin); + _kernel_rsize = ABSOLUTE(_edata - __initdata_begin); #endif .gptab.sdata : { diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig index c4ef2b4d9797..248744b4d086 100644 --- a/arch/loongarch/kvm/Kconfig +++ b/arch/loongarch/kvm/Kconfig @@ -29,6 +29,7 @@ config KVM select KVM_MMIO select HAVE_KVM_READONLY_MEM select KVM_XFER_TO_GUEST_WORK + select SCHED_INFO help Support hosting virtualized guest machines using hardware virtualization extensions. You will need diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index c86e099af5ca..ea73f9dc2cc6 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -24,7 +24,7 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst) { int rd, rj; - unsigned int index; + unsigned int index, ret; if (inst.reg2_format.opcode != cpucfg_op) return EMULATE_FAIL; @@ -50,7 +50,10 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst) vcpu->arch.gprs[rd] = *(unsigned int *)KVM_SIGNATURE; break; case CPUCFG_KVM_FEATURE: - vcpu->arch.gprs[rd] = KVM_FEATURE_IPI; + ret = KVM_FEATURE_IPI; + if (kvm_pvtime_supported()) + ret |= KVM_FEATURE_STEAL_TIME; + vcpu->arch.gprs[rd] = ret; break; default: vcpu->arch.gprs[rd] = 0; @@ -687,6 +690,34 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +static long kvm_save_notify(struct kvm_vcpu *vcpu) +{ + unsigned long id, data; + + id = kvm_read_reg(vcpu, LOONGARCH_GPR_A1); + data = kvm_read_reg(vcpu, LOONGARCH_GPR_A2); + switch (id) { + case KVM_FEATURE_STEAL_TIME: + if (!kvm_pvtime_supported()) + return KVM_HCALL_INVALID_CODE; + + if (data & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID)) + return KVM_HCALL_INVALID_PARAMETER; + + vcpu->arch.st.guest_addr = data; + if (!(data & KVM_STEAL_PHYS_VALID)) + break; + + vcpu->arch.st.last_steal = current->sched_info.run_delay; + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + break; + default: + break; + }; + + return 0; +}; + /* * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root. * @vcpu: Virtual CPU context. @@ -758,10 +789,13 @@ static void kvm_handle_service(struct kvm_vcpu *vcpu) kvm_send_pv_ipi(vcpu); ret = KVM_HCALL_SUCCESS; break; + case KVM_HCALL_FUNC_NOTIFY: + ret = kvm_save_notify(vcpu); + break; default: ret = KVM_HCALL_INVALID_CODE; break; - }; + } kvm_write_reg(vcpu, LOONGARCH_GPR_A0, ret); } diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 86a2f2d0cb27..844736b99d38 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -242,6 +242,7 @@ void kvm_check_vpid(struct kvm_vcpu *vcpu) kvm_update_vpid(vcpu, cpu); trace_kvm_vpid_change(vcpu, vcpu->arch.vpid); vcpu->cpu = cpu; + kvm_clear_request(KVM_REQ_TLB_FLUSH_GPA, vcpu); } /* Restore GSTAT(0x50).vpid */ diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 98883aa23ab8..2634a9e8d82c 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -163,6 +163,7 @@ static kvm_pte_t *kvm_populate_gpa(struct kvm *kvm, child = kvm_mmu_memory_cache_alloc(cache); _kvm_pte_init(child, ctx.invalid_ptes[ctx.level - 1]); + smp_wmb(); /* Make pte visible before pmd */ kvm_set_pte(entry, __pa(child)); } else if (kvm_pte_huge(*entry)) { return entry; @@ -444,6 +445,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, enum kvm_mr_change change) { int needs_flush; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; + + /* Only track memslot flags changed */ + if (change != KVM_MR_FLAGS_ONLY) + return; + + /* Discard dirty page tracking on readonly memslot */ + if ((old_flags & new_flags) & KVM_MEM_READONLY) + return; /* * If dirty page logging is enabled, write protect all pages in the slot @@ -454,9 +466,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot() */ - if (change == KVM_MR_FLAGS_ONLY && - (!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) && - new->flags & KVM_MEM_LOG_DIRTY_PAGES)) { + if (!(old_flags & KVM_MEM_LOG_DIRTY_PAGES) && log_dirty_pages) { + /* + * Initially-all-set does not require write protecting any page + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; + spin_lock(&kvm->mmu_lock); /* Write protect GPA page table entries */ needs_flush = kvm_mkclean_gpa_pt(kvm, new->base_gfn, @@ -540,6 +557,7 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; struct kvm_memory_slot *slot; + struct page *page; spin_lock(&kvm->mmu_lock); @@ -551,10 +569,8 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ } /* Track access to pages marked old */ - new = *ptep; - if (!kvm_pte_young(new)) - new = kvm_pte_mkyoung(new); - /* call kvm_set_pfn_accessed() after unlock */ + new = kvm_pte_mkyoung(*ptep); + /* call kvm_set_pfn_accessed() after unlock */ if (write && !kvm_pte_dirty(new)) { if (!kvm_pte_write(new)) { @@ -582,19 +598,22 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ if (changed) { kvm_set_pte(ptep, new); pfn = kvm_pte_pfn(new); + page = kvm_pfn_to_refcounted_page(pfn); + if (page) + get_page(page); } spin_unlock(&kvm->mmu_lock); - /* - * Fixme: pfn may be freed after mmu_lock - * kvm_try_get_pfn(pfn)/kvm_release_pfn pair to prevent this? - */ - if (kvm_pte_young(changed)) - kvm_set_pfn_accessed(pfn); + if (changed) { + if (kvm_pte_young(changed)) + kvm_set_pfn_accessed(pfn); - if (kvm_pte_dirty(changed)) { - mark_page_dirty(kvm, gfn); - kvm_set_pfn_dirty(pfn); + if (kvm_pte_dirty(changed)) { + mark_page_dirty(kvm, gfn); + kvm_set_pfn_dirty(pfn); + } + if (page) + put_page(page); } return ret; out: @@ -737,6 +756,7 @@ static kvm_pte_t *kvm_split_huge(struct kvm_vcpu *vcpu, kvm_pte_t *ptep, gfn_t g val += PAGE_SIZE; } + smp_wmb(); /* Make pte visible before pmd */ /* The later kvm_flush_tlb_gpa() will flush hugepage tlb */ kvm_set_pte(ptep, __pa(child)); @@ -858,11 +878,21 @@ retry: /* Disable dirty logging on HugePages */ level = 0; - if (!fault_supports_huge_mapping(memslot, hva, write)) { - level = 0; - } else { + if (fault_supports_huge_mapping(memslot, hva, write)) { + /* Check page level about host mmu*/ level = host_pfn_mapping_level(kvm, gfn, memslot); if (level == 1) { + /* + * Check page level about secondary mmu + * Disable hugepage if it is normal page on + * secondary mmu already + */ + ptep = kvm_populate_gpa(kvm, NULL, gpa, 0); + if (ptep && !kvm_pte_huge(*ptep)) + level = 0; + } + + if (level == 1) { gfn = gfn & ~(PTRS_PER_PTE - 1); pfn = pfn & ~(PTRS_PER_PTE - 1); } @@ -892,7 +922,6 @@ retry: kvm_set_pfn_dirty(pfn); } - kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); out: srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -908,7 +937,8 @@ int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) return ret; /* Invalidate this entry in the TLB */ - kvm_flush_tlb_gpa(vcpu, gpa); + vcpu->arch.flush_gpa = gpa; + kvm_make_request(KVM_REQ_TLB_FLUSH_GPA, vcpu); return 0; } diff --git a/arch/loongarch/kvm/tlb.c b/arch/loongarch/kvm/tlb.c index 02535df6b51f..ebdbe9264e9c 100644 --- a/arch/loongarch/kvm/tlb.c +++ b/arch/loongarch/kvm/tlb.c @@ -23,10 +23,7 @@ void kvm_flush_tlb_all(void) void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa) { - unsigned long flags; - - local_irq_save(flags); + lockdep_assert_irqs_disabled(); gpa &= (PAGE_MASK << 1); invtlb(INVTLB_GID_ADDR, read_csr_gstat() & CSR_GSTAT_GID, gpa); - local_irq_restore(flags); } diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 9e8030d45129..bdfb1a910e27 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -31,6 +31,50 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; +static void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ + u32 version; + u64 steal; + gpa_t gpa; + struct kvm_memslots *slots; + struct kvm_steal_time __user *st; + struct gfn_to_hva_cache *ghc; + + ghc = &vcpu->arch.st.cache; + gpa = vcpu->arch.st.guest_addr; + if (!(gpa & KVM_STEAL_PHYS_VALID)) + return; + + gpa &= KVM_STEAL_PHYS_MASK; + slots = kvm_memslots(vcpu->kvm); + if (slots->generation != ghc->generation || gpa != ghc->gpa) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st))) { + ghc->gpa = INVALID_GPA; + return; + } + } + + st = (struct kvm_steal_time __user *)ghc->hva; + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ + + version += 1; + unsafe_put_user(version, &st->version, out); + smp_wmb(); + + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); + + smp_wmb(); + version += 1; + unsafe_put_user(version, &st->version, out); +out: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); +} + /* * kvm_check_requests - check and handle pending vCPU requests * @@ -48,9 +92,22 @@ static int kvm_check_requests(struct kvm_vcpu *vcpu) if (kvm_dirty_ring_check_request(vcpu)) return RESUME_HOST; + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + kvm_update_stolen_time(vcpu); + return RESUME_GUEST; } +static void kvm_late_check_requests(struct kvm_vcpu *vcpu) +{ + lockdep_assert_irqs_disabled(); + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GPA, vcpu)) + if (vcpu->arch.flush_gpa != INVALID_GPA) { + kvm_flush_tlb_gpa(vcpu, vcpu->arch.flush_gpa); + vcpu->arch.flush_gpa = INVALID_GPA; + } +} + /* * Check and handle pending signal and vCPU requests etc * Run with irq enabled and preempt enabled @@ -101,6 +158,13 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu) /* Make sure the vcpu mode has been written */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); kvm_check_vpid(vcpu); + + /* + * Called after function kvm_check_vpid() + * Since it updates CSR.GSTAT used by kvm_flush_tlb_gpa(), + * and it may also clear KVM_REQ_TLB_FLUSH_GPA pending bit + */ + kvm_late_check_requests(vcpu); vcpu->arch.host_eentry = csr_read64(LOONGARCH_CSR_EENTRY); /* Clear KVM_LARCH_SWCSR_LATEST as CSR will change when enter guest */ vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; @@ -354,6 +418,17 @@ static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val) return -EINVAL; if (id == LOONGARCH_CSR_ESTAT) { + preempt_disable(); + vcpu_load(vcpu); + /* + * Sync pending interrupts into ESTAT so that interrupt + * remains during VM migration stage + */ + kvm_deliver_intr(vcpu); + vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; + vcpu_put(vcpu); + preempt_enable(); + /* ESTAT IP0~IP7 get from GINTC */ gintc = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_GINTC) & 0xff; *val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT) | (gintc << 2); @@ -662,6 +737,16 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu, return -ENXIO; } +static int kvm_loongarch_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + if (!kvm_pvtime_supported() || + attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + return 0; +} + static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -671,6 +756,9 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, case KVM_LOONGARCH_VCPU_CPUCFG: ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr); break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_has_attr(vcpu, attr); + break; default: break; } @@ -678,7 +766,7 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, return ret; } -static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu, +static int kvm_loongarch_cpucfg_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = 0; @@ -694,6 +782,23 @@ static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu, return ret; } +static int kvm_loongarch_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 gpa; + u64 __user *user = (u64 __user *)attr->addr; + + if (!kvm_pvtime_supported() || + attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + gpa = vcpu->arch.st.guest_addr; + if (put_user(gpa, user)) + return -EFAULT; + + return 0; +} + static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -701,7 +806,10 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu, switch (attr->group) { case KVM_LOONGARCH_VCPU_CPUCFG: - ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr); + ret = kvm_loongarch_cpucfg_get_attr(vcpu, attr); + break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_get_attr(vcpu, attr); break; default: break; @@ -716,6 +824,43 @@ static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu, return -ENXIO; } +static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int idx, ret = 0; + u64 gpa, __user *user = (u64 __user *)attr->addr; + struct kvm *kvm = vcpu->kvm; + + if (!kvm_pvtime_supported() || + attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + if (get_user(gpa, user)) + return -EFAULT; + + if (gpa & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID)) + return -EINVAL; + + if (!(gpa & KVM_STEAL_PHYS_VALID)) { + vcpu->arch.st.guest_addr = gpa; + return 0; + } + + /* Check the address is in a valid memslot */ + idx = srcu_read_lock(&kvm->srcu); + if (kvm_is_error_hva(gfn_to_hva(kvm, gpa >> PAGE_SHIFT))) + ret = -EINVAL; + srcu_read_unlock(&kvm->srcu, idx); + + if (!ret) { + vcpu->arch.st.guest_addr = gpa; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + } + + return ret; +} + static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -725,6 +870,9 @@ static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu, case KVM_LOONGARCH_VCPU_CPUCFG: ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr); break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_set_attr(vcpu, attr); + break; default: break; } @@ -994,6 +1142,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct loongarch_csrs *csr; vcpu->arch.vpid = 0; + vcpu->arch.flush_gpa = INVALID_GPA; hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); vcpu->arch.swtimer.function = kvm_swtimer_wakeup; @@ -1084,6 +1233,7 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Control guest page CCA attribute */ change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT); + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); /* Don't bother restoring registers multiple times unless necessary */ if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE) diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index ed9f34da1a2a..0850b099f300 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -35,7 +35,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, - off_t, pgoff) + unsigned long, pgoff) { if (pgoff & ~PAGE_MASK) return -EINVAL; diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index ec180ab92eaa..66a8ba19c287 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -110,7 +110,8 @@ static void bcm6358_quirks(void) * RAC flush causes kernel panics on BCM6358 when booting from TP1 * because the bootloader is not initializing it properly. */ - bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) || + !!BMIPS_GET_CBR(); } static void bcm6368_quirks(void) diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h index 30e86861c206..b1ee3c48e84b 100644 --- a/arch/mips/include/asm/mipsmtregs.h +++ b/arch/mips/include/asm/mipsmtregs.h @@ -322,7 +322,7 @@ static inline void ehb(void) " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ _ASM_SET_MFTC0 \ - " mftc0 $1, " #rt ", " #sel " \n" \ + " mftc0 %0, " #rt ", " #sel " \n" \ _ASM_UNSET_MFTC0 \ " .set pop \n" \ : "=r" (__res)); \ diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index cc869f5d5693..953f5b7dc723 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -354,7 +354,7 @@ 412 n32 utimensat_time64 sys_utimensat 413 n32 pselect6_time64 compat_sys_pselect6_time64 414 n32 ppoll_time64 compat_sys_ppoll_time64 -416 n32 io_pgetevents_time64 sys_io_pgetevents +416 n32 io_pgetevents_time64 compat_sys_io_pgetevents_time64 417 n32 recvmmsg_time64 compat_sys_recvmmsg_time64 418 n32 mq_timedsend_time64 sys_mq_timedsend 419 n32 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 008ebe60263e..2439a2491cff 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -27,7 +27,7 @@ 17 o32 break sys_ni_syscall # 18 was sys_stat 18 o32 unused18 sys_ni_syscall -19 o32 lseek sys_lseek +19 o32 lseek sys_lseek compat_sys_lseek 20 o32 getpid sys_getpid 21 o32 mount sys_mount 22 o32 umount sys_oldumount @@ -403,7 +403,7 @@ 412 o32 utimensat_time64 sys_utimensat sys_utimensat 413 o32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 o32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 o32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 o32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 o32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 o32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 o32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/mips/pci/ops-rc32434.c b/arch/mips/pci/ops-rc32434.c index 874ed6df9768..34b9323bdabb 100644 --- a/arch/mips/pci/ops-rc32434.c +++ b/arch/mips/pci/ops-rc32434.c @@ -112,8 +112,8 @@ retry: * gives them time to settle */ if (where == PCI_VENDOR_ID) { - if (ret == 0xffffffff || ret == 0x00000000 || - ret == 0x0000ffff || ret == 0xffff0000) { + if (*val == 0xffffffff || *val == 0x00000000 || + *val == 0x0000ffff || *val == 0xffff0000) { if (delay > 4) return 0; delay *= 2; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index daafeb20f993..dc9b902de8ea 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -16,6 +16,7 @@ config PARISC select ARCH_HAS_UBSAN select ARCH_HAS_PTE_SPECIAL select ARCH_NO_SG_CHAIN + select ARCH_SPLIT_ARG64 if !64BIT select ARCH_SUPPORTS_HUGETLBFS if PA20 select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_STACKWALK diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index ba4c05bc24d6..8394718870e1 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,18 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); #define flush_cache_vmap_early(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd..babf65751e81 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 422f3e1e6d9c..483bfafd930c 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/syscalls.h> +#include <linux/vmalloc.h> #include <asm/pdc.h> #include <asm/cache.h> #include <asm/cacheflush.h> @@ -31,20 +32,31 @@ #include <asm/mmu_context.h> #include <asm/cachectl.h> +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 2a12a547b447..826c8e51b585 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -23,12 +23,3 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, current->comm, current->pid, r20); return -ENOSYS; } - -asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags, - compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd, - const char __user * pathname) -{ - return sys_fanotify_mark(fanotify_fd, flags, - ((__u64)mask1 << 32) | mask0, - dfd, pathname); -} diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index b13c21373974..66dc406b12e4 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -108,7 +108,7 @@ 95 common fchown sys_fchown 96 common getpriority sys_getpriority 97 common setpriority sys_setpriority -98 common recv sys_recv +98 common recv sys_recv compat_sys_recv 99 common statfs sys_statfs compat_sys_statfs 100 common fstatfs sys_fstatfs compat_sys_fstatfs 101 common stat64 sys_stat64 @@ -135,7 +135,7 @@ 120 common clone sys_clone_wrapper 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile -123 common recvfrom sys_recvfrom +123 common recvfrom sys_recvfrom compat_sys_recvfrom 124 32 adjtimex sys_adjtimex_time32 124 64 adjtimex sys_adjtimex 125 common mprotect sys_mprotect @@ -364,7 +364,7 @@ 320 common accept4 sys_accept4 321 common prlimit64 sys_prlimit64 322 common fanotify_init sys_fanotify_init -323 common fanotify_mark sys_fanotify_mark sys32_fanotify_mark +323 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 324 32 clock_adjtime sys_clock_adjtime32 324 64 clock_adjtime sys_clock_adjtime 325 common name_to_handle_at sys_name_to_handle_at diff --git a/arch/powerpc/crypto/.gitignore b/arch/powerpc/crypto/.gitignore index e1094f08f713..e9fe73aac8b6 100644 --- a/arch/powerpc/crypto/.gitignore +++ b/arch/powerpc/crypto/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only aesp10-ppc.S +aesp8-ppc.S ghashp10-ppc.S +ghashp8-ppc.S diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d1030bc52564..d283d281d28e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -849,6 +849,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) { struct eeh_dev *edev; struct pci_dev *pdev; + struct pci_bus *bus = NULL; if (pe->type & EEH_PE_PHB) return pe->phb->bus; @@ -859,9 +860,11 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) /* Retrieve the parent PCI bus of first (top) PCI device */ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); + pci_lock_rescan_remove(); pdev = eeh_dev_to_pci_dev(edev); if (pdev) - return pdev->bus; + bus = pdev->bus; + pci_unlock_rescan_remove(); - return NULL; + return bus; } diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4690c219bfa4..63432a33ec49 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -647,8 +647,9 @@ __after_prom_start: * Note: This process overwrites the OF exception vectors. */ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET) - mr. r4,r26 /* In some cases the loader may */ - beq 9f /* have already put us at zero */ + mr r4,r26 /* Load the virtual source address into r4 */ + cmpld r3,r4 /* Check if source == dest */ + beq 9f /* If so skip the copy */ li r6,0x100 /* Start offset, the first 0x100 */ /* bytes were copied earlier. */ diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 3656f1ca7a21..ebae8415dfbb 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -230,8 +230,10 @@ 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -246,6 +248,7 @@ 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead 191 64 readahead sys_readahead +191 spu readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 @@ -293,6 +296,7 @@ 232 nospu set_tid_address sys_set_tid_address 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create @@ -502,7 +506,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 85050be08a23..72b12bc10f90 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -27,6 +27,7 @@ #include <asm/paca.h> #include <asm/mmu.h> #include <asm/sections.h> /* _end */ +#include <asm/setup.h> #include <asm/smp.h> #include <asm/hw_breakpoint.h> #include <asm/svm.h> @@ -317,6 +318,16 @@ void default_machine_kexec(struct kimage *image) if (!kdump_in_progress()) kexec_prepare_cpus(); +#ifdef CONFIG_PPC_PSERIES + /* + * This must be done after other CPUs have shut down, otherwise they + * could execute the 'scv' instruction, which is not supported with + * reloc disabled (see configure_exceptions()). + */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) + pseries_disable_reloc_on_exc(); +#endif + printk("kexec: Starting switchover sequence.\n"); /* switch to a staticly allocated stack. Based on irq stack code. diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index b569ebaa590e..3ff3de9a52ac 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -130,14 +130,16 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, } rcu_read_unlock(); - fdput(f); - - if (!found) + if (!found) { + fdput(f); return -EINVAL; + } table_group = iommu_group_get_iommudata(grp); - if (WARN_ON(!table_group)) + if (WARN_ON(!table_group)) { + fdput(f); return -EFAULT; + } for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { struct iommu_table *tbltmp = table_group->tables[i]; @@ -158,8 +160,10 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, break; } } - if (!tbl) + if (!tbl) { + fdput(f); return -EINVAL; + } rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { @@ -170,6 +174,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, /* stit is being destroyed */ iommu_tce_table_put(tbl); rcu_read_unlock(); + fdput(f); return -ENOTTY; } /* @@ -177,6 +182,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, * its KVM reference counter and can return. */ rcu_read_unlock(); + fdput(f); return 0; } rcu_read_unlock(); @@ -184,6 +190,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { iommu_tce_table_put(tbl); + fdput(f); return -ENOMEM; } @@ -192,6 +199,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, list_add_rcu(&stit->next, &stt->iommu_tables); + fdput(f); return 0; } diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 096d09ed89f6..431be156ca9b 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -61,11 +61,3 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary) } else xics_kexec_teardown_cpu(secondary); } - -void pseries_machine_kexec(struct kimage *image) -{ - if (firmware_has_feature(FW_FEATURE_SET_MODE)) - pseries_disable_reloc_on_exc(); - - default_machine_kexec(image); -} diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index bba4ad192b0f..3968a6970fa8 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -38,7 +38,6 @@ static inline void smp_init_pseries(void) { } #endif extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary); -void pseries_machine_kexec(struct kimage *image); extern void pSeries_final_fixup(void); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 284a6fa04b0c..b10a25325238 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -343,8 +343,8 @@ static int alloc_dispatch_log_kmem_cache(void) { void (*ctor)(void *) = get_dtl_cache_ctor(); - dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, ctor); + dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor); if (!dtl_cache) { pr_warn("Failed to create dispatch trace log buffer cache\n"); pr_warn("Stolen time statistics will be unreliable\n"); @@ -1159,7 +1159,6 @@ define_machine(pseries) { .machine_check_exception = pSeries_machine_check_exception, .machine_check_log_err = pSeries_machine_check_log_err, #ifdef CONFIG_KEXEC_CORE - .machine_kexec = pseries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts index 8df4cf3656f2..a7d753b6fdfd 100644 --- a/arch/riscv/boot/dts/canaan/canaan_kd233.dts +++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts @@ -15,6 +15,10 @@ model = "Kendryte KD233"; compatible = "canaan,kendryte-kd233", "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -46,7 +50,6 @@ &fpioa { pinctrl-0 = <&jtag_pinctrl>; pinctrl-names = "default"; - status = "okay"; jtag_pinctrl: jtag-pinmux { pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>, @@ -118,6 +121,7 @@ #sound-dai-cells = <1>; pinctrl-0 = <&i2s0_pinctrl>; pinctrl-names = "default"; + status = "okay"; }; &spi0 { @@ -125,6 +129,7 @@ pinctrl-names = "default"; num-cs = <1>; cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; panel@0 { compatible = "canaan,kd233-tft", "ilitek,ili9341"; diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi index f87c5164d9cf..4f5d40fa1e77 100644 --- a/arch/riscv/boot/dts/canaan/k210.dtsi +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -16,13 +16,6 @@ #size-cells = <1>; compatible = "canaan,kendryte-k210"; - aliases { - serial0 = &uarths0; - serial1 = &uart1; - serial2 = &uart2; - serial3 = &uart3; - }; - /* * The K210 has an sv39 MMU following the privileged specification v1.9. * Since this is a non-ratified draft specification, the kernel does not @@ -137,6 +130,7 @@ reg = <0x38000000 0x1000>; interrupts = <33>; clocks = <&sysclk K210_CLK_CPU>; + status = "disabled"; }; gpio0: gpio-controller@38001000 { @@ -152,6 +146,7 @@ <62>, <63>, <64>, <65>; gpio-controller; ngpios = <32>; + status = "disabled"; }; dmac0: dma-controller@50000000 { @@ -187,6 +182,7 @@ <&sysclk K210_CLK_GPIO>; clock-names = "bus", "db"; resets = <&sysrst K210_RST_GPIO>; + status = "disabled"; gpio1_0: gpio-port@0 { #gpio-cells = <2>; @@ -214,6 +210,7 @@ dsr-override; cts-override; ri-override; + status = "disabled"; }; uart2: serial@50220000 { @@ -230,6 +227,7 @@ dsr-override; cts-override; ri-override; + status = "disabled"; }; uart3: serial@50230000 { @@ -246,6 +244,7 @@ dsr-override; cts-override; ri-override; + status = "disabled"; }; spi2: spi@50240000 { @@ -259,6 +258,7 @@ <&sysclk K210_CLK_APB0>; clock-names = "ssi_clk", "pclk"; resets = <&sysrst K210_RST_SPI2>; + status = "disabled"; }; i2s0: i2s@50250000 { @@ -268,6 +268,7 @@ clocks = <&sysclk K210_CLK_I2S0>; clock-names = "i2sclk"; resets = <&sysrst K210_RST_I2S0>; + status = "disabled"; }; i2s1: i2s@50260000 { @@ -277,6 +278,7 @@ clocks = <&sysclk K210_CLK_I2S1>; clock-names = "i2sclk"; resets = <&sysrst K210_RST_I2S1>; + status = "disabled"; }; i2s2: i2s@50270000 { @@ -286,6 +288,7 @@ clocks = <&sysclk K210_CLK_I2S2>; clock-names = "i2sclk"; resets = <&sysrst K210_RST_I2S2>; + status = "disabled"; }; i2c0: i2c@50280000 { @@ -296,6 +299,7 @@ <&sysclk K210_CLK_APB0>; clock-names = "ref", "pclk"; resets = <&sysrst K210_RST_I2C0>; + status = "disabled"; }; i2c1: i2c@50290000 { @@ -306,6 +310,7 @@ <&sysclk K210_CLK_APB0>; clock-names = "ref", "pclk"; resets = <&sysrst K210_RST_I2C1>; + status = "disabled"; }; i2c2: i2c@502a0000 { @@ -316,6 +321,7 @@ <&sysclk K210_CLK_APB0>; clock-names = "ref", "pclk"; resets = <&sysrst K210_RST_I2C2>; + status = "disabled"; }; fpioa: pinmux@502b0000 { @@ -464,6 +470,7 @@ reset-names = "spi"; num-cs = <4>; reg-io-width = <4>; + status = "disabled"; }; spi1: spi@53000000 { @@ -479,6 +486,7 @@ reset-names = "spi"; num-cs = <4>; reg-io-width = <4>; + status = "disabled"; }; spi3: spi@54000000 { @@ -495,6 +503,7 @@ num-cs = <4>; reg-io-width = <4>; + status = "disabled"; }; }; }; diff --git a/arch/riscv/boot/dts/canaan/k210_generic.dts b/arch/riscv/boot/dts/canaan/k210_generic.dts index 396c8ca4d24d..5734cc03753b 100644 --- a/arch/riscv/boot/dts/canaan/k210_generic.dts +++ b/arch/riscv/boot/dts/canaan/k210_generic.dts @@ -15,6 +15,10 @@ model = "Kendryte K210 generic"; compatible = "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -24,7 +28,6 @@ &fpioa { pinctrl-0 = <&jtag_pins>; pinctrl-names = "default"; - status = "okay"; jtag_pins: jtag-pinmux { pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>, diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts index 6d25bf07481a..2ab376d609d2 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts @@ -17,6 +17,10 @@ compatible = "sipeed,maix-bit", "sipeed,maix-bitm", "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -58,7 +62,6 @@ &fpioa { pinctrl-names = "default"; pinctrl-0 = <&jtag_pinctrl>; - status = "okay"; jtag_pinctrl: jtag-pinmux { pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>, @@ -156,6 +159,7 @@ #sound-dai-cells = <1>; pinctrl-0 = <&i2s0_pinctrl>; pinctrl-names = "default"; + status = "okay"; }; &i2c1 { @@ -170,6 +174,7 @@ pinctrl-names = "default"; num-cs = <1>; cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; panel@0 { compatible = "sitronix,st7789v"; @@ -199,6 +204,8 @@ }; &spi3 { + status = "okay"; + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts index f4f4d8d5e8b8..d98e20775c07 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts @@ -17,6 +17,10 @@ compatible = "sipeed,maix-dock-m1", "sipeed,maix-dock-m1w", "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -63,7 +67,6 @@ &fpioa { pinctrl-0 = <&jtag_pinctrl>; pinctrl-names = "default"; - status = "okay"; jtag_pinctrl: jtag-pinmux { pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>, @@ -159,6 +162,7 @@ #sound-dai-cells = <1>; pinctrl-0 = <&i2s0_pinctrl>; pinctrl-names = "default"; + status = "okay"; }; &i2c1 { @@ -173,6 +177,7 @@ pinctrl-names = "default"; num-cs = <1>; cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; panel@0 { compatible = "sitronix,st7789v"; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts index 0d86df47e1ed..79ecd549700a 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts @@ -16,6 +16,10 @@ model = "SiPeed MAIX GO"; compatible = "sipeed,maix-go", "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -69,7 +73,6 @@ &fpioa { pinctrl-0 = <&jtag_pinctrl>; pinctrl-names = "default"; - status = "okay"; jtag_pinctrl: jtag-pinmux { pinmux = <K210_FPIOA(0, K210_PCF_JTAG_TCLK)>, @@ -167,6 +170,7 @@ #sound-dai-cells = <1>; pinctrl-0 = <&i2s0_pinctrl>; pinctrl-names = "default"; + status = "okay"; }; &i2c1 { @@ -181,6 +185,7 @@ pinctrl-names = "default"; num-cs = <1>; cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; panel@0 { compatible = "sitronix,st7789v"; @@ -209,6 +214,8 @@ }; &spi3 { + status = "okay"; + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts index 5c05c498e2b8..019c03ae51f6 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts @@ -15,6 +15,10 @@ model = "SiPeed MAIXDUINO"; compatible = "sipeed,maixduino", "canaan,kendryte-k210"; + aliases { + serial0 = &uarths0; + }; + chosen { bootargs = "earlycon console=ttySIF0"; stdout-path = "serial0:115200n8"; @@ -39,8 +43,6 @@ }; &fpioa { - status = "okay"; - uarths_pinctrl: uarths-pinmux { pinmux = <K210_FPIOA(4, K210_PCF_UARTHS_RX)>, /* Header "0" */ <K210_FPIOA(5, K210_PCF_UARTHS_TX)>; /* Header "1" */ @@ -132,6 +134,7 @@ #sound-dai-cells = <1>; pinctrl-0 = <&i2s0_pinctrl>; pinctrl-names = "default"; + status = "okay"; }; &i2c1 { @@ -146,6 +149,7 @@ pinctrl-names = "default"; num-cs = <1>; cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; panel@0 { compatible = "sitronix,st7789v"; @@ -174,6 +178,8 @@ }; &spi3 { + status = "okay"; + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; diff --git a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts index cd013588adc0..375ff2661b6e 100644 --- a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts +++ b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts @@ -45,6 +45,7 @@ no-1-8-v; no-mmc; no-sdio; + disable-wp; }; &uart0 { diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi index 8ff6ea64f048..68d16717db8c 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi @@ -244,7 +244,7 @@ regulator-boot-on; regulator-always-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; regulator-name = "emmc_vdd"; }; }; diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h index 06e439eeef9a..09fde95a5e8f 100644 --- a/arch/riscv/include/asm/insn.h +++ b/arch/riscv/include/asm/insn.h @@ -145,7 +145,7 @@ /* parts of opcode for RVF, RVD and RVQ */ #define RVFDQ_FL_FS_WIDTH_OFF 12 -#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(3, 0) +#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(2, 0) #define RVFDQ_FL_FS_WIDTH_W 2 #define RVFDQ_FL_FS_WIDTH_D 3 #define RVFDQ_LS_FS_WIDTH_Q 4 diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 87cbd86576b2..4b95c574fd04 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -120,9 +120,6 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); mutex_unlock(&text_mutex); - if (!mod) - local_flush_icache_range(rec->ip, rec->ip + MCOUNT_INSN_SIZE); - return out; } @@ -156,9 +153,9 @@ static int __ftrace_modify_code(void *data) } else { while (atomic_read(¶m->cpu_count) <= num_online_cpus()) cpu_relax(); - } - local_flush_icache_all(); + local_flush_icache_all(); + } return 0; } diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index ed9cad20c039..3c830a6f7ef4 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -121,20 +121,12 @@ static void machine_kexec_mask_interrupts(void) for_each_irq_desc(i, desc) { struct irq_chip *chip; - int ret; chip = irq_desc_get_chip(desc); if (!chip) continue; - /* - * First try to remove the active state. If this - * fails, try to EOI the interrupt. - */ - ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); - - if (ret && irqd_irq_inprogress(&desc->irq_data) && - chip->irq_eoi) + if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) chip->irq_eoi(&desc->irq_data); if (chip->irq_mask) diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 4007563fb607..ab03732d06c4 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -89,6 +89,14 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) memset(waddr, c, len); + /* + * We could have just patched a function that is about to be + * called so make sure we don't execute partially patched + * instructions by flushing the icache as soon as possible. + */ + local_flush_icache_range((unsigned long)waddr, + (unsigned long)waddr + len); + patch_unmap(FIX_TEXT_POKE0); if (across_pages) @@ -135,6 +143,14 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) ret = copy_to_kernel_nofault(waddr, insn, len); + /* + * We could have just patched a function that is about to be + * called so make sure we don't execute partially patched + * instructions by flushing the icache as soon as possible. + */ + local_flush_icache_range((unsigned long)waddr, + (unsigned long)waddr + len); + patch_unmap(FIX_TEXT_POKE0); if (across_pages) @@ -189,9 +205,6 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len) ret = patch_insn_set(tp, c, len); - if (!ret) - flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len); - return ret; } NOKPROBE_SYMBOL(patch_text_set_nosync); @@ -224,9 +237,6 @@ int patch_text_nosync(void *addr, const void *insns, size_t len) ret = patch_insn_write(tp, insns, len); - if (!ret) - flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len); - return ret; } NOKPROBE_SYMBOL(patch_text_nosync); @@ -253,9 +263,9 @@ static int patch_text_cb(void *data) } else { while (atomic_read(&patch->cpu_count) <= num_online_cpus()) cpu_relax(); - } - local_flush_icache_all(); + local_flush_icache_all(); + } return ret; } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 528ec7cc9a62..10e311b2759d 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -32,6 +32,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; + int graph_idx = 0; int level = 0; if (regs) { @@ -68,7 +69,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, pc = regs->ra; } else { fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); if (pc == (unsigned long)ret_from_exception) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) @@ -156,7 +157,7 @@ unsigned long __get_wchan(struct task_struct *task) return pc; } -noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { walk_stackframe(task, regs, consume_entry, cookie); diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 64155323cc92..d77afe05578f 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -23,7 +23,7 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, #ifdef CONFIG_64BIT SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, - unsigned long, fd, off_t, offset) + unsigned long, fd, unsigned long, offset) { return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); } @@ -32,7 +32,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, - unsigned long, fd, off_t, offset) + unsigned long, fd, unsigned long, offset) { /* * Note that the shift for mmap2 is constant (12), diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 04db1f993c47..bcf41d6e0df0 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -327,7 +327,7 @@ static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_att event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc); if (IS_ERR(event)) { - pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); + pr_debug("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); return PTR_ERR(event); } diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index b3fcf7d67efb..5224f3733802 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -293,8 +293,8 @@ void handle_page_fault(struct pt_regs *regs) if (unlikely(access_error(cause, vma))) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_SUCCESS); - tsk->thread.bad_cause = SEGV_ACCERR; - bad_area_nosemaphore(regs, code, addr); + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, SEGV_ACCERR, addr); return; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index e3218d65f21d..e3405e4b99af 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -250,18 +250,19 @@ static void __init setup_bootmem(void) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; /* - * memblock allocator is not aware of the fact that last 4K bytes of - * the addressable memory can not be mapped because of IS_ERR_VALUE - * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. For 64-bit - * kernel, this problem can't happen here as the end of the virtual - * address space is occupied by the kernel mapping then this check must - * be done as soon as the kernel mapping base address is determined. + * Reserve physical address space that would be mapped to virtual + * addresses greater than (void *)(-PAGE_SIZE) because: + * - This memory would overlap with ERR_PTR + * - This memory belongs to high memory, which is not supported + * + * This is not applicable to 64-bit kernel, because virtual addresses + * after (void *)(-PAGE_SIZE) are not linearly mapped: they are + * occupied by kernel mapping. Also it is unrealistic for high memory + * to exist on 64-bit platforms. */ if (!IS_ENABLED(CONFIG_64BIT)) { - max_mapped_addr = __pa(~(ulong)0); - if (max_mapped_addr == (phys_ram_end - 1)) - memblock_set_current_limit(max_mapped_addr - 4096); + max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE); + memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); } min_low_pfn = PFN_UP(phys_ram_base); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 182aac6a0f77..5a36d5538dae 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -170,11 +170,14 @@ static void kaslr_adjust_got(unsigned long offset) u64 *entry; /* - * Even without -fPIE, Clang still uses a global offset table for some - * reason. Adjust the GOT entries. + * Adjust GOT entries, except for ones for undefined weak symbols + * that resolved to zero. This also skips the first three reserved + * entries on s390x that are zero. */ - for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) - *entry += offset - __START_KERNEL; + for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) { + if (*entry) + *entry += offset - __START_KERNEL; + } } /* @@ -384,7 +387,7 @@ static void fixup_vmlinux_info(void) void startup_kernel(void) { unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long nokaslr_offset_phys = mem_safe_offset(); + unsigned long nokaslr_offset_phys, kaslr_large_page_offset; unsigned long amode31_lma = 0; unsigned long max_physmem_end; unsigned long asce_limit; @@ -393,6 +396,12 @@ void startup_kernel(void) fixup_vmlinux_info(); setup_lpp(); + + /* + * Non-randomized kernel physical start address must be _SEGMENT_SIZE + * aligned (see blow). + */ + nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size); /* @@ -425,10 +434,25 @@ void startup_kernel(void) save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); - if (kaslr_enabled()) - __kaslr_offset_phys = randomize_within_range(kernel_size, THREAD_SIZE, 0, ident_map_size); + /* + * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower + * 20 bits (the offset within a large page) are zero. Copy the last + * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to + * __kaslr_offset_phys. + * + * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset + * are identical, which is required to allow for large mappings of the + * kernel image. + */ + kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; + if (kaslr_enabled()) { + unsigned long end = ident_map_size - kaslr_large_page_offset; + + __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end); + } if (!__kaslr_offset_phys) __kaslr_offset_phys = nokaslr_offset_phys; + __kaslr_offset_phys |= kaslr_large_page_offset; kaslr_adjust_vmlinux_info(__kaslr_offset_phys); physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size); deploy_kernel((void *)__kaslr_offset_phys); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 96d48b7112d4..40cfce2687c4 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -261,21 +261,27 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m static bool large_allowed(enum populate_mode mode) { - return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY); + return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL); } static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat2 && large_allowed(mode) && - IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE; + IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE); } static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat1 && large_allowed(mode) && - IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE; + IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE); } static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 1fe5a1d3ff60..a750711d44c8 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS #ifdef CONFIG_KERNEL_UNCOMPRESSED . = ALIGN(PAGE_SIZE); . += AMODE31_SIZE; /* .amode31 section */ + . = ALIGN(1 << 20); /* _SEGMENT_SIZE */ #else . = ALIGN(8); #endif diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 145342e46ea8..f3602414a961 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -43,7 +43,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -51,6 +50,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 @@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -574,18 +601,16 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -# CONFIG_DRM_DEBUG_MODESET_LOCK is not set +CONFIG_DRM=m +CONFIG_DRM_VIRTIO_GPU=m CONFIG_FB=y # CONFIG_FB_DEVICE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m -CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_MLX5_VFIO_PCI=m @@ -645,7 +670,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -663,6 +687,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -879,6 +904,5 @@ CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y -CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index dc237896f99d..d0d8925fdf09 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -41,7 +41,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -49,6 +48,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -564,17 +592,16 @@ CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +CONFIG_DRM=m +CONFIG_DRM_VIRTIO_GPU=m CONFIG_FB=y # CONFIG_FB_DEVICE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m -CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_MLX5_VFIO_PCI=m @@ -630,7 +657,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -649,6 +675,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c51f3ec4eb28..8c2b61363bab 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KEXEC=y -CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set +# CONFIG_AP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set -# CONFIG_GCC_PLUGINS is not set # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SWAP is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_COMPACTION is not set -# CONFIG_MIGRATION is not set CONFIG_NET=y # CONFIG_IUCV is not set # CONFIG_PCPU_DEV_REFCNT is not set diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index 7f5004065e8a..35555c944630 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -54,7 +54,7 @@ static __always_inline void arch_exit_to_user_mode(void) static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) { - choose_random_kstack_offset(get_tod_clock_fast() & 0xff); + choose_random_kstack_offset(get_tod_clock_fast()); } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 736cc88f497d..d8bbcac89ac3 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -426,6 +426,7 @@ struct kvm_vcpu_stat { u64 instruction_io_other; u64 instruction_lpsw; u64 instruction_lpswe; + u64 instruction_lpswey; u64 instruction_pfmf; u64 instruction_ptff; u64 instruction_sck; diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 9863ebe75019..edae13416196 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -451,7 +451,7 @@ static void *nt_final(void *ptr) /* * Initialize ELF header (new kernel) */ -static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) +static void *ehdr_init(Elf64_Ehdr *ehdr, int phdr_count) { memset(ehdr, 0, sizeof(*ehdr)); memcpy(ehdr->e_ident, ELFMAG, SELFMAG); @@ -465,11 +465,8 @@ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) ehdr->e_phoff = sizeof(Elf64_Ehdr); ehdr->e_ehsize = sizeof(Elf64_Ehdr); ehdr->e_phentsize = sizeof(Elf64_Phdr); - /* - * Number of memory chunk PT_LOAD program headers plus one kernel - * image PT_LOAD program header plus one PT_NOTE program header. - */ - ehdr->e_phnum = mem_chunk_cnt + 1 + 1; + /* Number of PT_LOAD program headers plus PT_NOTE program header */ + ehdr->e_phnum = phdr_count + 1; return ehdr + 1; } @@ -503,12 +500,14 @@ static int get_mem_chunk_cnt(void) /* * Initialize ELF loads (new kernel) */ -static void loads_init(Elf64_Phdr *phdr) +static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm) { - unsigned long old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); + unsigned long old_identity_base = 0; phys_addr_t start, end; u64 idx; + if (os_info_has_vm) + old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE); for_each_physmem_range(idx, &oldmem_type, &start, &end) { phdr->p_type = PT_LOAD; phdr->p_vaddr = old_identity_base + start; @@ -522,6 +521,11 @@ static void loads_init(Elf64_Phdr *phdr) } } +static bool os_info_has_vm(void) +{ + return os_info_old_value(OS_INFO_KASLR_OFFSET); +} + /* * Prepare PT_LOAD type program header for kernel image region */ @@ -566,7 +570,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) return ptr; } -static size_t get_elfcorehdr_size(int mem_chunk_cnt) +static size_t get_elfcorehdr_size(int phdr_count) { size_t size; @@ -581,10 +585,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt) size += nt_vmcoreinfo_size(); /* nt_final */ size += sizeof(Elf64_Nhdr); - /* PT_LOAD type program header for kernel text region */ - size += sizeof(Elf64_Phdr); /* PT_LOADS */ - size += mem_chunk_cnt * sizeof(Elf64_Phdr); + size += phdr_count * sizeof(Elf64_Phdr); return size; } @@ -595,8 +597,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt) int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads, *phdr_text; + int mem_chunk_cnt, phdr_text_cnt; size_t alloc_size; - int mem_chunk_cnt; void *ptr, *hdr; u64 hdr_off; @@ -615,12 +617,14 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) } mem_chunk_cnt = get_mem_chunk_cnt(); + phdr_text_cnt = os_info_has_vm() ? 1 : 0; - alloc_size = get_elfcorehdr_size(mem_chunk_cnt); + alloc_size = get_elfcorehdr_size(mem_chunk_cnt + phdr_text_cnt); hdr = kzalloc(alloc_size, GFP_KERNEL); - /* Without elfcorehdr /proc/vmcore cannot be created. Thus creating + /* + * Without elfcorehdr /proc/vmcore cannot be created. Thus creating * a dump with this crash kernel will fail. Panic now to allow other * dump mechanisms to take over. */ @@ -628,21 +632,23 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) panic("s390 kdump allocating elfcorehdr failed"); /* Init elf header */ - ptr = ehdr_init(hdr, mem_chunk_cnt); + phdr_notes = ehdr_init(hdr, mem_chunk_cnt + phdr_text_cnt); /* Init program headers */ - phdr_notes = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); - phdr_text = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); - phdr_loads = ptr; - ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt); + if (phdr_text_cnt) { + phdr_text = phdr_notes + 1; + phdr_loads = phdr_text + 1; + } else { + phdr_loads = phdr_notes + 1; + } + ptr = PTR_ADD(phdr_loads, sizeof(Elf64_Phdr) * mem_chunk_cnt); /* Init notes */ hdr_off = PTR_DIFF(ptr, hdr); ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); /* Init kernel text program header */ - text_init(phdr_text); + if (phdr_text_cnt) + text_init(phdr_text); /* Init loads */ - loads_init(phdr_loads); + loads_init(phdr_loads, phdr_text_cnt); /* Finalize program headers */ hdr_off = PTR_DIFF(ptr, hdr); *addr = (unsigned long long) hdr; diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c index dc2355c623d6..50cbcbbaa03d 100644 --- a/arch/s390/kernel/syscall.c +++ b/arch/s390/kernel/syscall.c @@ -38,33 +38,6 @@ #include "entry.h" -/* - * Perform the mmap() system call. Linux for S/390 isn't able to handle more - * than 5 system call parameters, so this system call uses a memory block - * for parameter passing. - */ - -struct s390_mmap_arg_struct { - unsigned long addr; - unsigned long len; - unsigned long prot; - unsigned long flags; - unsigned long fd; - unsigned long offset; -}; - -SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg) -{ - struct s390_mmap_arg_struct a; - int error = -EFAULT; - - if (copy_from_user(&a, arg, sizeof(a))) - goto out; - error = ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); -out: - return error; -} - #ifdef CONFIG_SYSVIPC /* * sys_ipc() is the de-multiplexer for the SysV IPC calls. diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index bd0fee24ad10..01071182763e 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 854d0d1410be..4a74effe6870 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -132,6 +132,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_io_other), STATS_DESC_COUNTER(VCPU, instruction_lpsw), STATS_DESC_COUNTER(VCPU, instruction_lpswe), + STATS_DESC_COUNTER(VCPU, instruction_lpswey), STATS_DESC_COUNTER(VCPU, instruction_pfmf), STATS_DESC_COUNTER(VCPU, instruction_ptff), STATS_DESC_COUNTER(VCPU, instruction_sck), diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 111eb5c74784..bf8534218af3 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -138,6 +138,21 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar) +{ + u32 base1 = vcpu->arch.sie_block->ipb >> 28; + s64 disp1; + + /* The displacement is a 20bit _SIGNED_ value */ + disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19); + + if (ar) + *ar = base1; + + return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; +} + static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, u64 *address1, u64 *address2, u8 *ar_b1, u8 *ar_b2) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 1be19cc9d73c..1a49b89706f8 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -797,6 +797,36 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) return 0; } +static int handle_lpswey(struct kvm_vcpu *vcpu) +{ + psw_t new_psw; + u64 addr; + int rc; + u8 ar; + + vcpu->stat.instruction_lpswey++; + + if (!test_kvm_facility(vcpu->kvm, 193)) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_siy(vcpu, &ar); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + vcpu->arch.sie_block->gpsw = new_psw; + if (!is_valid_psw(&vcpu->arch.sie_block->gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + return 0; +} + static int handle_stidp(struct kvm_vcpu *vcpu) { u64 stidp_data = vcpu->kvm->arch.model.cpuid; @@ -1462,6 +1492,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) case 0x61: case 0x62: return handle_ri(vcpu); + case 0x71: + return handle_lpswey(vcpu); default: return -EOPNOTSUPP; } diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index ff8f24854c64..0ef83b6ac0db 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -410,7 +410,7 @@ static void __init cpu_enable_directed_irq(void *unused) union zpci_sic_iib iib = {{0}}; union zpci_sic_iib ziib = {{0}}; - iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector; + iib.cdiib.dibv_addr = virt_to_phys(zpci_ibv[smp_processor_id()]->vector); zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib); zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib); diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 9dca568509a5..d6f4afcb0e87 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -59,3 +59,14 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, (u64)len0 << 32 | len1, advice); #endif } + +/* + * swap the arguments the way that libc wants them instead of + * moving flags ahead of the 64-bit nbytes argument + */ +SYSCALL_DEFINE6(sh_sync_file_range6, int, fd, SC_ARG64(offset), + SC_ARG64(nbytes), unsigned int, flags) +{ + return ksys_sync_file_range(fd, SC_VAL64(loff_t, offset), + SC_VAL64(loff_t, nbytes), flags); +} diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index bbf83a2db986..c55fd7696d40 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -321,7 +321,7 @@ 311 common set_robust_list sys_set_robust_list 312 common get_robust_list sys_get_robust_list 313 common splice sys_splice -314 common sync_file_range sys_sync_file_range +314 common sync_file_range sys_sh_sync_file_range6 315 common tee sys_tee 316 common vmsplice sys_vmsplice 317 common move_pages sys_move_pages @@ -395,6 +395,7 @@ 385 common pkey_alloc sys_pkey_alloc 386 common pkey_free sys_pkey_free 387 common rseq sys_rseq +388 common sync_file_range2 sys_sync_file_range2 # room for arch specific syscalls 393 common semget sys_semget 394 common semctl sys_semctl diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index a45f0f31fe51..a3d308f2043e 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -18,224 +18,3 @@ sys32_mmap2: sethi %hi(sys_mmap), %g1 jmpl %g1 + %lo(sys_mmap), %g0 sllx %o5, 12, %o5 - - .align 32 - .globl sys32_socketcall -sys32_socketcall: /* %o0=call, %o1=args */ - cmp %o0, 1 - bl,pn %xcc, do_einval - cmp %o0, 18 - bg,pn %xcc, do_einval - sub %o0, 1, %o0 - sllx %o0, 5, %o0 - sethi %hi(__socketcall_table_begin), %g2 - or %g2, %lo(__socketcall_table_begin), %g2 - jmpl %g2 + %o0, %g0 - nop -do_einval: - retl - mov -EINVAL, %o0 - - .align 32 -__socketcall_table_begin: - - /* Each entry is exactly 32 bytes. */ -do_sys_socket: /* sys_socket(int, int, int) */ -1: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_socket), %g1 -2: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_socket), %g0 -3: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_bind: /* sys_bind(int fd, struct sockaddr *, int) */ -4: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_bind), %g1 -5: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_bind), %g0 -6: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_connect: /* sys_connect(int, struct sockaddr *, int) */ -7: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_connect), %g1 -8: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_connect), %g0 -9: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_listen: /* sys_listen(int, int) */ -10: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_listen), %g1 - jmpl %g1 + %lo(sys_listen), %g0 -11: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop - nop -do_sys_accept: /* sys_accept(int, struct sockaddr *, int *) */ -12: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_accept), %g1 -13: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_accept), %g0 -14: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_getsockname: /* sys_getsockname(int, struct sockaddr *, int *) */ -15: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getsockname), %g1 -16: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_getsockname), %g0 -17: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_getpeername: /* sys_getpeername(int, struct sockaddr *, int *) */ -18: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getpeername), %g1 -19: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_getpeername), %g0 -20: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_socketpair: /* sys_socketpair(int, int, int, int *) */ -21: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_socketpair), %g1 -22: ldswa [%o1 + 0x8] %asi, %o2 -23: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_socketpair), %g0 -24: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_send: /* sys_send(int, void *, size_t, unsigned int) */ -25: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_send), %g1 -26: lduwa [%o1 + 0x8] %asi, %o2 -27: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_send), %g0 -28: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_recv: /* sys_recv(int, void *, size_t, unsigned int) */ -29: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_recv), %g1 -30: lduwa [%o1 + 0x8] %asi, %o2 -31: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_recv), %g0 -32: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_sendto: /* sys_sendto(int, u32, compat_size_t, unsigned int, u32, int) */ -33: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_sendto), %g1 -34: lduwa [%o1 + 0x8] %asi, %o2 -35: lduwa [%o1 + 0xc] %asi, %o3 -36: lduwa [%o1 + 0x10] %asi, %o4 -37: ldswa [%o1 + 0x14] %asi, %o5 - jmpl %g1 + %lo(sys_sendto), %g0 -38: lduwa [%o1 + 0x4] %asi, %o1 -do_sys_recvfrom: /* sys_recvfrom(int, u32, compat_size_t, unsigned int, u32, u32) */ -39: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_recvfrom), %g1 -40: lduwa [%o1 + 0x8] %asi, %o2 -41: lduwa [%o1 + 0xc] %asi, %o3 -42: lduwa [%o1 + 0x10] %asi, %o4 -43: lduwa [%o1 + 0x14] %asi, %o5 - jmpl %g1 + %lo(sys_recvfrom), %g0 -44: lduwa [%o1 + 0x4] %asi, %o1 -do_sys_shutdown: /* sys_shutdown(int, int) */ -45: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_shutdown), %g1 - jmpl %g1 + %lo(sys_shutdown), %g0 -46: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop - nop -do_sys_setsockopt: /* sys_setsockopt(int, int, int, char *, int) */ -47: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_setsockopt), %g1 -48: ldswa [%o1 + 0x8] %asi, %o2 -49: lduwa [%o1 + 0xc] %asi, %o3 -50: ldswa [%o1 + 0x10] %asi, %o4 - jmpl %g1 + %lo(sys_setsockopt), %g0 -51: ldswa [%o1 + 0x4] %asi, %o1 - nop -do_sys_getsockopt: /* sys_getsockopt(int, int, int, u32, u32) */ -52: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getsockopt), %g1 -53: ldswa [%o1 + 0x8] %asi, %o2 -54: lduwa [%o1 + 0xc] %asi, %o3 -55: lduwa [%o1 + 0x10] %asi, %o4 - jmpl %g1 + %lo(sys_getsockopt), %g0 -56: ldswa [%o1 + 0x4] %asi, %o1 - nop -do_sys_sendmsg: /* compat_sys_sendmsg(int, struct compat_msghdr *, unsigned int) */ -57: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(compat_sys_sendmsg), %g1 -58: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(compat_sys_sendmsg), %g0 -59: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_recvmsg: /* compat_sys_recvmsg(int, struct compat_msghdr *, unsigned int) */ -60: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(compat_sys_recvmsg), %g1 -61: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(compat_sys_recvmsg), %g0 -62: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_accept4: /* sys_accept4(int, struct sockaddr *, int *, int) */ -63: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_accept4), %g1 -64: lduwa [%o1 + 0x8] %asi, %o2 -65: ldswa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_accept4), %g0 -66: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - - .section __ex_table,"a" - .align 4 - .word 1b, __retl_efault, 2b, __retl_efault - .word 3b, __retl_efault, 4b, __retl_efault - .word 5b, __retl_efault, 6b, __retl_efault - .word 7b, __retl_efault, 8b, __retl_efault - .word 9b, __retl_efault, 10b, __retl_efault - .word 11b, __retl_efault, 12b, __retl_efault - .word 13b, __retl_efault, 14b, __retl_efault - .word 15b, __retl_efault, 16b, __retl_efault - .word 17b, __retl_efault, 18b, __retl_efault - .word 19b, __retl_efault, 20b, __retl_efault - .word 21b, __retl_efault, 22b, __retl_efault - .word 23b, __retl_efault, 24b, __retl_efault - .word 25b, __retl_efault, 26b, __retl_efault - .word 27b, __retl_efault, 28b, __retl_efault - .word 29b, __retl_efault, 30b, __retl_efault - .word 31b, __retl_efault, 32b, __retl_efault - .word 33b, __retl_efault, 34b, __retl_efault - .word 35b, __retl_efault, 36b, __retl_efault - .word 37b, __retl_efault, 38b, __retl_efault - .word 39b, __retl_efault, 40b, __retl_efault - .word 41b, __retl_efault, 42b, __retl_efault - .word 43b, __retl_efault, 44b, __retl_efault - .word 45b, __retl_efault, 46b, __retl_efault - .word 47b, __retl_efault, 48b, __retl_efault - .word 49b, __retl_efault, 50b, __retl_efault - .word 51b, __retl_efault, 52b, __retl_efault - .word 53b, __retl_efault, 54b, __retl_efault - .word 55b, __retl_efault, 56b, __retl_efault - .word 57b, __retl_efault, 58b, __retl_efault - .word 59b, __retl_efault, 60b, __retl_efault - .word 61b, __retl_efault, 62b, __retl_efault - .word 63b, __retl_efault, 64b, __retl_efault - .word 65b, __retl_efault, 66b, __retl_efault - .previous diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index ac6c281ccfe0..cfdfb3707c16 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -117,7 +117,7 @@ 90 common dup2 sys_dup2 91 32 setfsuid32 sys_setfsuid 92 common fcntl sys_fcntl compat_sys_fcntl -93 common select sys_select +93 common select sys_select compat_sys_select 94 32 setfsgid32 sys_setfsgid 95 common fsync sys_fsync 96 common setpriority sys_setpriority @@ -155,7 +155,7 @@ 123 32 fchown sys_fchown16 123 64 fchown sys_fchown 124 common fchmod sys_fchmod -125 common recvfrom sys_recvfrom +125 common recvfrom sys_recvfrom compat_sys_recvfrom 126 32 setreuid sys_setreuid16 126 64 setreuid sys_setreuid 127 32 setregid sys_setregid16 @@ -247,7 +247,7 @@ 204 32 readdir sys_old_readdir compat_sys_old_readdir 204 64 readdir sys_nis_syscall 205 common readahead sys_readahead compat_sys_readahead -206 common socketcall sys_socketcall sys32_socketcall +206 common socketcall sys_socketcall compat_sys_socketcall 207 common syslog sys_syslog 208 common lookup_dcookie sys_ni_syscall 209 common fadvise64 sys_fadvise64 compat_sys_fadvise64 @@ -461,7 +461,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 243ee86cb1b1..f2051644de94 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -105,9 +105,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7fd1f57ad3d3..d6ebcab1d8b2 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -420,7 +420,7 @@ 412 i386 utimensat_time64 sys_utimensat 413 i386 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 i386 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 i386 io_pgetevents_time64 sys_io_pgetevents +416 i386 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 i386 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 i386 mq_timedsend_time64 sys_mq_timedsend 419 i386 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index ed2797f132ce..62cef2113ca7 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -93,10 +93,9 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, \ asm volatile(ALTERNATIVE(_lock_loc \ "call cmpxchg8b_emu", \ - _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \ - : [ptr] "+m" (*(_ptr)), \ - "+a" (o.low), "+d" (o.high) \ - : "b" (n.low), "c" (n.high), "S" (_ptr) \ + _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \ + : "+a" (o.low), "+d" (o.high) \ + : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \ : "memory"); \ \ o.full; \ @@ -122,12 +121,11 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 \ asm volatile(ALTERNATIVE(_lock_loc \ "call cmpxchg8b_emu", \ - _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \ + _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \ CC_SET(e) \ : CC_OUT(e) (ret), \ - [ptr] "+m" (*(_ptr)), \ "+a" (o.low), "+d" (o.high) \ - : "b" (n.low), "c" (n.high), "S" (_ptr) \ + : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \ : "memory"); \ \ if (unlikely(!ret)) \ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 1dc600fa3ba5..481096177500 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -401,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); extern void __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags); -#define __efi_memmap_free __efi_memmap_free extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 7e523bb3d2d3..fb2809b20b0a 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -73,19 +73,16 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, #endif /* - * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), - * but not enough for x86 stack utilization comfort. To keep - * reasonable stack head room, reduce the maximum offset to 8 bits. - * - * The actual entropy will be further reduced by the compiler when - * applying stack alignment constraints (see cc_stack_align4/8 in + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints (see cc_stack_align4/8 in * arch/x86/Makefile), which will remove the 3 (x86_64) or 2 (ia32) * low bits from any entropy chosen here. * - * Therefore, final stack offset entropy will be 5 (x86_64) or - * 6 (ia32) bits. + * Therefore, final stack offset entropy will be 7 (x86_64) or + * 8 (ia32) bits. */ - choose_random_kstack_offset(rdtsc() & 0xFF); + choose_random_kstack_offset(rdtsc()); } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 0f9bab92a43d..3a7755c1a441 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%c4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3cf156f70859..027a8c7a2c9e 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -215,7 +215,14 @@ out: int amd_smn_read(u16 node, u32 address, u32 *value) { - return __amd_smn_rw(node, address, value, false); + int err = __amd_smn_rw(node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; } EXPORT_SYMBOL_GPL(amd_smn_read); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 2345e6836593..366f496ca3ce 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -519,7 +519,8 @@ void free_rmid(u32 closid, u32 rmid) * allows architectures that ignore the closid parameter to avoid an * unnecessary check. */ - if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + if (!resctrl_arch_mon_capable() || + idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID)) return; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index b180d8e497c3..cc0f7f70b17b 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image) void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e42faa792c07..52e1f3f0b361 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -27,25 +27,7 @@ unsigned long profile_pc(struct pt_regs *regs) { - unsigned long pc = instruction_pointer(regs); - - if (!user_mode(regs) && in_lock_functions(pc)) { -#ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + sizeof(long)); -#else - unsigned long *sp = (unsigned long *)regs->sp; - /* - * Return address is either directly at stack pointer - * or above a saved flags. Eflags has bits 22-31 zero, - * kernel addresses don't. - */ - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; -#endif - } - return pc; + return instruction_pointer(regs); } EXPORT_SYMBOL(profile_pc); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b252a2732b6f..c58da281f14f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2855,7 +2855,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (sev_es_prevent_msr_access(vcpu, msr_info)) { msr_info->data = 0; - return -EINVAL; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; } switch (msr_info->index) { @@ -3010,7 +3010,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; if (sev_es_prevent_msr_access(vcpu, msr)) - return -EINVAL; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; switch (ecx) { case MSR_AMD64_TSC_RATIO: diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 10d5ed8b5990..a1cb3a4e6742 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index ce84ba86e69e..6ce10e3c6228 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,7 +493,7 @@ static void __init numa_clear_kernel_node_hotplug(void) for_each_reserved_mem_region(mb_region) { int nid = memblock_get_region_node(mb_region); - if (nid != MAX_NUMNODES) + if (nid != NUMA_NO_NODE) node_set(nid, reserved_nodemask); } @@ -614,9 +614,9 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - MAX_NUMNODES)); + NUMA_NO_NODE)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - MAX_NUMNODES)); + NUMA_NO_NODE)); /* In case that parsing SRAT failed. */ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb5e..6ed1935504b9 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** |