diff options
Diffstat (limited to 'arch')
454 files changed, 5537 insertions, 2167 deletions
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 8f627c200d60..57d81c6aa379 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -163,12 +163,16 @@ interrupt-names = "macirq"; phy-mode = "rgmii"; snps,pbl = <32>; + snps,multicast-filter-bins = <256>; clocks = <&gmacclk>; clock-names = "stmmaceth"; phy-handle = <&phy0>; resets = <&cgu_rst HSDK_ETH_RESET>; reset-names = "stmmaceth"; + tx-fifo-depth = <4096>; + rx-fifo-depth = <4096>; + mdio { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index d819de1c5d10..3ea4112c8302 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -92,8 +92,11 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new) #endif /* CONFIG_ARC_HAS_LLSC */ -#define cmpxchg(ptr, o, n) ((typeof(*(ptr)))__cmpxchg((ptr), \ - (unsigned long)(o), (unsigned long)(n))) +#define cmpxchg(ptr, o, n) ({ \ + (typeof(*(ptr)))__cmpxchg((ptr), \ + (unsigned long)(o), \ + (unsigned long)(n)); \ +}) /* * atomic_cmpxchg is same as cmpxchg @@ -198,8 +201,11 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, return __xchg_bad_pointer(); } -#define xchg(ptr, with) ((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), \ - sizeof(*(ptr)))) +#define xchg(ptr, with) ({ \ + (typeof(*(ptr)))__xchg((unsigned long)(with), \ + (ptr), \ + sizeof(*(ptr))); \ +}) #endif /* CONFIG_ARC_PLAT_EZNPS */ diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 2ce24e74f879..a509b77ef80d 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -488,8 +488,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev) /* loop thru all available h/w condition indexes */ for (j = 0; j < cc_bcr.c; j++) { write_aux_reg(ARC_REG_CC_INDEX, j); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); /* See if it has been mapped to a perf event_id */ for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index bcd7c9fc5d0f..869ac2d421c8 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -155,3 +155,11 @@ void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs) insterror_is_error(address, regs); } + +/* + * abort() call generated by older gcc for __builtin_trap() + */ +void abort(void) +{ + __asm__ __volatile__("trap_s 5\n"); +} diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 333daab7def0..93453fa48193 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -185,11 +185,6 @@ static void *__init unw_hdr_alloc_early(unsigned long sz) MAX_DMA_ADDRESS); } -static void *unw_hdr_alloc(unsigned long sz) -{ - return kmalloc(sz, GFP_KERNEL); -} - static void init_unwind_table(struct unwind_table *table, const char *name, const void *core_start, unsigned long core_size, const void *init_start, unsigned long init_size, @@ -370,6 +365,10 @@ ret_err: } #ifdef CONFIG_MODULES +static void *unw_hdr_alloc(unsigned long sz) +{ + return kmalloc(sz, GFP_KERNEL); +} static struct unwind_table *last_table; diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 8ceefbf72fb0..e5817b9b2c3f 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -902,9 +902,11 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) { struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; - unsigned int pd0[mmu->ways]; unsigned long flags; - int set; + int set, n_ways = mmu->ways; + + n_ways = min(n_ways, 4); + BUG_ON(mmu->ways > 4); local_irq_save(flags); @@ -912,9 +914,10 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, for (set = 0; set < mmu->sets; set++) { int is_valid, way; + unsigned int pd0[4]; /* read out all the ways of current set */ - for (way = 0, is_valid = 0; way < mmu->ways; way++) { + for (way = 0, is_valid = 0; way < n_ways; way++) { write_aux_reg(ARC_REG_TLBINDEX, SET_WAY_TO_IDX(mmu, set, way)); write_aux_reg(ARC_REG_TLBCOMMAND, TLBRead); @@ -928,14 +931,14 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, continue; /* Scan the set for duplicate ways: needs a nested loop */ - for (way = 0; way < mmu->ways - 1; way++) { + for (way = 0; way < n_ways - 1; way++) { int n; if (!pd0[way]) continue; - for (n = way + 1; n < mmu->ways; n++) { + for (n = way + 1; n < n_ways; n++) { if (pd0[way] != pd0[n]) continue; diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 49b954a2fa9b..b7dac0b03b37 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1030,14 +1030,21 @@ choice Say Y here if you want kernel low-level debugging support on SOCFPGA(Cyclone 5 and Arria 5) based platforms. - config DEBUG_SOCFPGA_UART1 + config DEBUG_SOCFPGA_ARRIA10_UART1 depends on ARCH_SOCFPGA - bool "Use SOCFPGA UART1 for low-level debug" + bool "Use SOCFPGA Arria10 UART1 for low-level debug" select DEBUG_UART_8250 help Say Y here if you want kernel low-level debugging support on SOCFPGA(Arria 10) based platforms. + config DEBUG_SOCFPGA_CYCLONE5_UART1 + depends on ARCH_SOCFPGA + bool "Use SOCFPGA Cyclone 5 UART1 for low-level debug" + select DEBUG_UART_8250 + help + Say Y here if you want kernel low-level debugging support + on SOCFPGA(Cyclone 5 and Arria 5) based platforms. config DEBUG_SUN9I_UART0 bool "Kernel low-level debugging messages via sun9i UART0" @@ -1383,22 +1390,21 @@ config DEBUG_OMAP2PLUS_UART depends on ARCH_OMAP2PLUS config DEBUG_IMX_UART_PORT - int "i.MX Debug UART Port Selection" if DEBUG_IMX1_UART || \ - DEBUG_IMX25_UART || \ - DEBUG_IMX21_IMX27_UART || \ - DEBUG_IMX31_UART || \ - DEBUG_IMX35_UART || \ - DEBUG_IMX50_UART || \ - DEBUG_IMX51_UART || \ - DEBUG_IMX53_UART || \ - DEBUG_IMX6Q_UART || \ - DEBUG_IMX6SL_UART || \ - DEBUG_IMX6SLL_UART || \ - DEBUG_IMX6SX_UART || \ - DEBUG_IMX6UL_UART || \ - DEBUG_IMX7D_UART + int "i.MX Debug UART Port Selection" + depends on DEBUG_IMX1_UART || \ + DEBUG_IMX25_UART || \ + DEBUG_IMX21_IMX27_UART || \ + DEBUG_IMX31_UART || \ + DEBUG_IMX35_UART || \ + DEBUG_IMX50_UART || \ + DEBUG_IMX51_UART || \ + DEBUG_IMX53_UART || \ + DEBUG_IMX6Q_UART || \ + DEBUG_IMX6SL_UART || \ + DEBUG_IMX6SX_UART || \ + DEBUG_IMX6UL_UART || \ + DEBUG_IMX7D_UART default 1 - depends on ARCH_MXC help Choose UART port on which kernel low-level debug messages should be output. @@ -1594,7 +1600,8 @@ config DEBUG_UART_PHYS default 0xfe800000 if ARCH_IOP32X default 0xff690000 if DEBUG_RK32_UART2 default 0xffc02000 if DEBUG_SOCFPGA_UART0 - default 0xffc02100 if DEBUG_SOCFPGA_UART1 + default 0xffc02100 if DEBUG_SOCFPGA_ARRIA10_UART1 + default 0xffc03000 if DEBUG_SOCFPGA_CYCLONE5_UART1 default 0xffd82340 if ARCH_IOP13XX default 0xffe40000 if DEBUG_RCAR_GEN1_SCIF0 default 0xffe42000 if DEBUG_RCAR_GEN1_SCIF2 @@ -1698,7 +1705,8 @@ config DEBUG_UART_VIRT default 0xfeb30c00 if DEBUG_KEYSTONE_UART0 default 0xfeb31000 if DEBUG_KEYSTONE_UART1 default 0xfec02000 if DEBUG_SOCFPGA_UART0 - default 0xfec02100 if DEBUG_SOCFPGA_UART1 + default 0xfec02100 if DEBUG_SOCFPGA_ARRIA10_UART1 + default 0xfec03000 if DEBUG_SOCFPGA_CYCLONE5_UART1 default 0xfec12000 if (DEBUG_MVEBU_UART0 || DEBUG_MVEBU_UART0_ALTERNATE) && ARCH_MVEBU default 0xfec12100 if DEBUG_MVEBU_UART1_ALTERNATE default 0xfec10000 if DEBUG_SIRFATLAS7_UART0 @@ -1746,9 +1754,9 @@ config DEBUG_UART_8250_WORD depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250 depends on DEBUG_UART_8250_SHIFT >= 2 default y if DEBUG_PICOXCELL_UART || \ - DEBUG_SOCFPGA_UART0 || DEBUG_SOCFPGA_UART1 || \ - DEBUG_KEYSTONE_UART0 || DEBUG_KEYSTONE_UART1 || \ - DEBUG_ALPINE_UART0 || \ + DEBUG_SOCFPGA_UART0 || DEBUG_SOCFPGA_ARRIA10_UART1 || \ + DEBUG_SOCFPGA_CYCLONE5_UART1 || DEBUG_KEYSTONE_UART0 || \ + DEBUG_KEYSTONE_UART1 || DEBUG_ALPINE_UART0 || \ DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \ DEBUG_DAVINCI_DA8XX_UART2 || \ DEBUG_BCM_KONA_UART || DEBUG_RK32_UART2 diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h index 07437816e098..b36c0289a308 100644 --- a/arch/arm/boot/compressed/libfdt_env.h +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -6,6 +6,8 @@ #include <linux/string.h> #include <asm/byteorder.h> +#define INT_MAX ((int)(~0U>>1)) + typedef __be16 fdt16_t; typedef __be32 fdt32_t; typedef __be64 fdt64_t; diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 478434ebff92..27ff3e689e96 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -724,6 +724,7 @@ pinctrl-0 = <&cpsw_default>; pinctrl-1 = <&cpsw_sleep>; status = "okay"; + slaves = <1>; }; &davinci_mdio { @@ -731,15 +732,14 @@ pinctrl-0 = <&davinci_mdio_default>; pinctrl-1 = <&davinci_mdio_sleep>; status = "okay"; -}; -&cpsw_emac0 { - phy_id = <&davinci_mdio>, <0>; - phy-mode = "rgmii-txid"; + ethphy0: ethernet-phy@0 { + reg = <0>; + }; }; -&cpsw_emac1 { - phy_id = <&davinci_mdio>, <1>; +&cpsw_emac0 { + phy-handle = <ðphy0>; phy-mode = "rgmii-txid"; }; diff --git a/arch/arm/boot/dts/am335x-pcm-953.dtsi b/arch/arm/boot/dts/am335x-pcm-953.dtsi index 1ec8e0d80191..572fbd254690 100644 --- a/arch/arm/boot/dts/am335x-pcm-953.dtsi +++ b/arch/arm/boot/dts/am335x-pcm-953.dtsi @@ -197,7 +197,7 @@ bus-width = <4>; pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-wega.dtsi b/arch/arm/boot/dts/am335x-wega.dtsi index 8ce541739b24..83e4fe595e37 100644 --- a/arch/arm/boot/dts/am335x-wega.dtsi +++ b/arch/arm/boot/dts/am335x-wega.dtsi @@ -157,7 +157,7 @@ bus-width = <4>; pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 4714a59fd86d..345c117bd5ef 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -1118,6 +1118,8 @@ ti,hwmods = "dss_dispc"; clocks = <&disp_clk>; clock-names = "fck"; + + max-memory-bandwidth = <230000000>; }; rfbi: rfbi@4832a800 { diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi index 97aa8e6a56da..9afebbfc4422 100644 --- a/arch/arm/boot/dts/am57xx-idk-common.dtsi +++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi @@ -405,6 +405,7 @@ vqmmc-supply = <&ldo1_reg>; bus-width = <4>; cd-gpios = <&gpio6 27 GPIO_ACTIVE_LOW>; /* gpio 219 */ + no-1-8-v; }; &mmc2 { diff --git a/arch/arm/boot/dts/arm-realview-eb.dtsi b/arch/arm/boot/dts/arm-realview-eb.dtsi index e2e9599596e2..05379b6c1c13 100644 --- a/arch/arm/boot/dts/arm-realview-eb.dtsi +++ b/arch/arm/boot/dts/arm-realview-eb.dtsi @@ -334,7 +334,7 @@ clock-names = "uartclk", "apb_pclk"; }; - ssp: ssp@1000d000 { + ssp: spi@1000d000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x1000d000 0x1000>; clocks = <&sspclk>, <&pclk>; diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts index c789564f2803..939c108c24a6 100644 --- a/arch/arm/boot/dts/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm-realview-pb1176.dts @@ -45,7 +45,7 @@ }; /* The voltage to the MMC card is hardwired at 3.3V */ - vmmc: fixedregulator@0 { + vmmc: regulator-vmmc { compatible = "regulator-fixed"; regulator-name = "vmmc"; regulator-min-microvolt = <3300000>; @@ -53,7 +53,7 @@ regulator-boot-on; }; - veth: fixedregulator@0 { + veth: regulator-veth { compatible = "regulator-fixed"; regulator-name = "veth"; regulator-min-microvolt = <3300000>; @@ -343,7 +343,7 @@ clock-names = "apb_pclk"; }; - pb1176_ssp: ssp@1010b000 { + pb1176_ssp: spi@1010b000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x1010b000 0x1000>; interrupt-parent = <&intc_dc1176>; diff --git a/arch/arm/boot/dts/arm-realview-pb11mp.dts b/arch/arm/boot/dts/arm-realview-pb11mp.dts index 3944765ac4b0..95037c48182d 100644 --- a/arch/arm/boot/dts/arm-realview-pb11mp.dts +++ b/arch/arm/boot/dts/arm-realview-pb11mp.dts @@ -145,7 +145,7 @@ }; /* The voltage to the MMC card is hardwired at 3.3V */ - vmmc: fixedregulator@0 { + vmmc: regulator-vmmc { compatible = "regulator-fixed"; regulator-name = "vmmc"; regulator-min-microvolt = <3300000>; @@ -153,7 +153,7 @@ regulator-boot-on; }; - veth: fixedregulator@0 { + veth: regulator-veth { compatible = "regulator-fixed"; regulator-name = "veth"; regulator-min-microvolt = <3300000>; @@ -480,7 +480,7 @@ clock-names = "uartclk", "apb_pclk"; }; - ssp@1000d000 { + spi@1000d000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x1000d000 0x1000>; interrupt-parent = <&intc_pb11mp>; diff --git a/arch/arm/boot/dts/arm-realview-pbx.dtsi b/arch/arm/boot/dts/arm-realview-pbx.dtsi index aeb49c4bd773..068293254fbb 100644 --- a/arch/arm/boot/dts/arm-realview-pbx.dtsi +++ b/arch/arm/boot/dts/arm-realview-pbx.dtsi @@ -43,7 +43,7 @@ }; /* The voltage to the MMC card is hardwired at 3.3V */ - vmmc: fixedregulator@0 { + vmmc: regulator-vmmc { compatible = "regulator-fixed"; regulator-name = "vmmc"; regulator-min-microvolt = <3300000>; @@ -51,7 +51,7 @@ regulator-boot-on; }; - veth: fixedregulator@0 { + veth: regulator-veth { compatible = "regulator-fixed"; regulator-name = "veth"; regulator-min-microvolt = <3300000>; @@ -318,7 +318,7 @@ clock-names = "uartclk", "apb_pclk"; }; - ssp: ssp@1000d000 { + ssp: spi@1000d000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x1000d000 0x1000>; clocks = <&sspclk>, <&pclk>; @@ -539,4 +539,3 @@ }; }; }; - diff --git a/arch/arm/boot/dts/armada-388-clearfog.dtsi b/arch/arm/boot/dts/armada-388-clearfog.dtsi index 68acfc968706..8a3bbb7d6cc1 100644 --- a/arch/arm/boot/dts/armada-388-clearfog.dtsi +++ b/arch/arm/boot/dts/armada-388-clearfog.dtsi @@ -89,7 +89,7 @@ &clearfog_sdhci_cd_pins>; pinctrl-names = "default"; status = "okay"; - vmmc = <®_3p3v>; + vmmc-supply = <®_3p3v>; wp-inverted; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index cf712444b2c2..10f2fb9e0ea6 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -240,7 +240,7 @@ rootfs@800000 { label = "rootfs"; - reg = <0x800000 0x0f800000>; + reg = <0x800000 0x1f800000>; }; }; }; diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index 64fa3f9a39d3..db0921e7a613 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -566,7 +566,7 @@ }; }; - uart1 { + usart1 { pinctrl_usart1: usart1-0 { atmel,pins = <AT91_PIOB 4 AT91_PERIPH_A AT91_PINCTRL_PULL_UP /* PB4 periph A with pullup */ diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi index bdeaa0b64a5b..0a673a7082be 100644 --- a/arch/arm/boot/dts/at91sam9x5cm.dtsi +++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi @@ -88,7 +88,7 @@ rootfs@800000 { label = "rootfs"; - reg = <0x800000 0x1f800000>; + reg = <0x800000 0x0f800000>; }; }; }; diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts index 580e3cbcfbf7..3e1584e787ae 100644 --- a/arch/arm/boot/dts/dove-cubox.dts +++ b/arch/arm/boot/dts/dove-cubox.dts @@ -87,7 +87,7 @@ status = "okay"; clock-frequency = <100000>; - si5351: clock-generator { + si5351: clock-generator@60 { compatible = "silabs,si5351a-msop"; reg = <0x60>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index f4a07bb7c3a2..c78471b05ab4 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -155,7 +155,7 @@ 0xffffe000 MBUS_ID(0x03, 0x01) 0 0x0000800 /* CESA SRAM 2k */ 0xfffff000 MBUS_ID(0x0d, 0x00) 0 0x0000800>; /* PMU SRAM 2k */ - spi0: spi-ctrl@10600 { + spi0: spi@10600 { compatible = "marvell,orion-spi"; #address-cells = <1>; #size-cells = <0>; @@ -168,7 +168,7 @@ status = "disabled"; }; - i2c: i2c-ctrl@11000 { + i2c: i2c@11000 { compatible = "marvell,mv64xxx-i2c"; reg = <0x11000 0x20>; #address-cells = <1>; @@ -218,7 +218,7 @@ status = "disabled"; }; - spi1: spi-ctrl@14600 { + spi1: spi@14600 { compatible = "marvell,orion-spi"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 0bf354024ef5..fec965009b9f 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -314,6 +314,7 @@ <0 0 0 2 &pcie1_intc 2>, <0 0 0 3 &pcie1_intc 3>, <0 0 0 4 &pcie1_intc 4>; + ti,syscon-unaligned-access = <&scm_conf1 0x14 1>; status = "disabled"; pcie1_intc: interrupt-controller { interrupt-controller; @@ -367,6 +368,7 @@ <0 0 0 2 &pcie2_intc 2>, <0 0 0 3 &pcie2_intc 3>, <0 0 0 4 &pcie2_intc 4>; + ti,syscon-unaligned-access = <&scm_conf1 0x14 2>; pcie2_intc: interrupt-controller { interrupt-controller; #address-cells = <0>; @@ -1540,6 +1542,7 @@ dr_mode = "otg"; snps,dis_u3_susphy_quirk; snps,dis_u2_susphy_quirk; + snps,dis_metastability_quirk; }; }; diff --git a/arch/arm/boot/dts/dra74x-mmc-iodelay.dtsi b/arch/arm/boot/dts/dra74x-mmc-iodelay.dtsi index 28ebb4eb884a..214b9e6de2c3 100644 --- a/arch/arm/boot/dts/dra74x-mmc-iodelay.dtsi +++ b/arch/arm/boot/dts/dra74x-mmc-iodelay.dtsi @@ -32,7 +32,7 @@ * * Datamanual Revisions: * - * AM572x Silicon Revision 2.0: SPRS953B, Revised November 2016 + * AM572x Silicon Revision 2.0: SPRS953F, Revised May 2019 * AM572x Silicon Revision 1.1: SPRS915R, Revised November 2016 * */ @@ -229,45 +229,45 @@ mmc3_pins_default: mmc3_pins_default { pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ - DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ - DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ - DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ - DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ - DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ >; }; mmc3_pins_hs: mmc3_pins_hs { pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ - DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ - DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ - DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ - DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ - DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ >; }; mmc3_pins_sdr12: mmc3_pins_sdr12 { pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ - DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ - DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ - DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ - DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ - DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ >; }; mmc3_pins_sdr25: mmc3_pins_sdr25 { pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ - DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ - DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ - DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ - DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ - DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ >; }; diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi index aa06a02c3ff5..5ba662254909 100644 --- a/arch/arm/boot/dts/exynos3250.dtsi +++ b/arch/arm/boot/dts/exynos3250.dtsi @@ -359,7 +359,7 @@ }; hsotg: hsotg@12480000 { - compatible = "snps,dwc2"; + compatible = "samsung,s3c6400-hsotg", "snps,dwc2"; reg = <0x12480000 0x20000>; interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cmu CLK_USBOTG>; diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts index 18a7f396ac5f..abd1705635f9 100644 --- a/arch/arm/boot/dts/exynos5250-arndale.dts +++ b/arch/arm/boot/dts/exynos5250-arndale.dts @@ -169,6 +169,8 @@ reg = <0x66>; interrupt-parent = <&gpx3>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&s5m8767_irq>; vinb1-supply = <&main_dc_reg>; vinb2-supply = <&main_dc_reg>; @@ -544,6 +546,13 @@ cap-sd-highspeed; }; +&pinctrl_0 { + s5m8767_irq: s5m8767-irq { + samsung,pins = "gpx3-2"; + samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>; + }; +}; + &rtc { status = "okay"; }; diff --git a/arch/arm/boot/dts/exynos5250-snow-rev5.dts b/arch/arm/boot/dts/exynos5250-snow-rev5.dts index 90560c316f64..cb986175b69b 100644 --- a/arch/arm/boot/dts/exynos5250-snow-rev5.dts +++ b/arch/arm/boot/dts/exynos5250-snow-rev5.dts @@ -23,6 +23,14 @@ samsung,model = "Snow-I2S-MAX98090"; samsung,audio-codec = <&max98090>; + + cpu { + sound-dai = <&i2s0 0>; + }; + + codec { + sound-dai = <&max98090 0>, <&hdmi>; + }; }; }; @@ -34,6 +42,9 @@ interrupt-parent = <&gpx0>; pinctrl-names = "default"; pinctrl-0 = <&max98090_irq>; + clocks = <&pmu_system_controller 0>; + clock-names = "mclk"; + #sound-dai-cells = <1>; }; }; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index c91eff8475a8..442161d2acd5 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -301,6 +301,7 @@ regulator-name = "vdd_1v35"; regulator-min-microvolt = <1350000>; regulator-max-microvolt = <1350000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -322,6 +323,7 @@ regulator-name = "vdd_2v"; regulator-min-microvolt = <2000000>; regulator-max-microvolt = <2000000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -332,6 +334,7 @@ regulator-name = "vdd_1v8"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -426,6 +429,7 @@ regulator-name = "vdd_ldo10"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-state-mem { regulator-off-in-suspend; }; diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts index daad5d425cf5..58af2254e521 100644 --- a/arch/arm/boot/dts/exynos5800-peach-pi.dts +++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts @@ -301,6 +301,7 @@ regulator-name = "vdd_1v35"; regulator-min-microvolt = <1350000>; regulator-max-microvolt = <1350000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -322,6 +323,7 @@ regulator-name = "vdd_2v"; regulator-min-microvolt = <2000000>; regulator-max-microvolt = <2000000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -332,6 +334,7 @@ regulator-name = "vdd_1v8"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-boot-on; regulator-state-mem { regulator-on-in-suspend; @@ -426,6 +429,7 @@ regulator-name = "vdd_ldo10"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-state-mem { regulator-off-in-suspend; }; diff --git a/arch/arm/boot/dts/gemini-sq201.dts b/arch/arm/boot/dts/gemini-sq201.dts index 63c02ca9513c..e9e2f6ff0c58 100644 --- a/arch/arm/boot/dts/gemini-sq201.dts +++ b/arch/arm/boot/dts/gemini-sq201.dts @@ -20,7 +20,7 @@ }; chosen { - bootargs = "console=ttyS0,115200n8"; + bootargs = "console=ttyS0,115200n8 root=/dev/mtdblock2 rw rootfstype=squashfs,jffs2 rootwait"; stdout-path = &uart0; }; @@ -71,37 +71,10 @@ /* 16MB of flash */ reg = <0x30000000 0x01000000>; - partition@0 { - label = "RedBoot"; - reg = <0x00000000 0x00120000>; - read-only; - }; - partition@120000 { - label = "Kernel"; - reg = <0x00120000 0x00200000>; - }; - partition@320000 { - label = "Ramdisk"; - reg = <0x00320000 0x00600000>; - }; - partition@920000 { - label = "Application"; - reg = <0x00920000 0x00600000>; - }; - partition@f20000 { - label = "VCTL"; - reg = <0x00f20000 0x00020000>; - read-only; - }; - partition@f40000 { - label = "CurConf"; - reg = <0x00f40000 0x000a0000>; - read-only; - }; - partition@fe0000 { - label = "FIS directory"; - reg = <0x00fe0000 0x00020000>; - read-only; + partitions { + compatible = "redboot-fis"; + /* Eraseblock at 0xfe0000 */ + fis-index-block = <0x1fc>; }; }; diff --git a/arch/arm/boot/dts/imx53-voipac-dmm-668.dtsi b/arch/arm/boot/dts/imx53-voipac-dmm-668.dtsi index df8dafe2564d..2297ed90ee89 100644 --- a/arch/arm/boot/dts/imx53-voipac-dmm-668.dtsi +++ b/arch/arm/boot/dts/imx53-voipac-dmm-668.dtsi @@ -17,12 +17,8 @@ memory@70000000 { device_type = "memory"; - reg = <0x70000000 0x20000000>; - }; - - memory@b0000000 { - device_type = "memory"; - reg = <0xb0000000 0x20000000>; + reg = <0x70000000 0x20000000>, + <0xb0000000 0x20000000>; }; regulators { diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index 9835a043d4e8..5a9ad916f952 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -464,7 +464,7 @@ pwm1: pwm@02080000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02080000 0x4000>; - interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM1>, <&clks IMX6UL_CLK_PWM1>; clock-names = "ipg", "per"; @@ -475,7 +475,7 @@ pwm2: pwm@02084000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02084000 0x4000>; - interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM2>, <&clks IMX6UL_CLK_PWM2>; clock-names = "ipg", "per"; @@ -486,7 +486,7 @@ pwm3: pwm@02088000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02088000 0x4000>; - interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM3>, <&clks IMX6UL_CLK_PWM3>; clock-names = "ipg", "per"; @@ -497,7 +497,7 @@ pwm4: pwm@0208c000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x0208c000 0x4000>; - interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM4>, <&clks IMX6UL_CLK_PWM4>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/imx7d-cl-som-imx7.dts b/arch/arm/boot/dts/imx7d-cl-som-imx7.dts index 3cc1fb9ce441..60a28281d3d1 100644 --- a/arch/arm/boot/dts/imx7d-cl-som-imx7.dts +++ b/arch/arm/boot/dts/imx7d-cl-som-imx7.dts @@ -43,7 +43,7 @@ <&clks IMX7D_ENET1_TIME_ROOT_CLK>; assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>; assigned-clock-rates = <0>, <100000000>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy0>; fsl,magic-packet; status = "okay"; @@ -69,7 +69,7 @@ <&clks IMX7D_ENET2_TIME_ROOT_CLK>; assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>; assigned-clock-rates = <0>, <100000000>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy1>; fsl,magic-packet; status = "okay"; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index f1470e1292b8..11ed757b5d19 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -453,8 +453,8 @@ reg = <0x302d0000 0x10000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_GPT1_ROOT_CLK>, - <&clks IMX7D_GPT1_ROOT_CLK>, - <&clks IMX7D_GPT_3M_CLK>; + <&clks IMX7D_GPT1_ROOT_CLK>, + <&clks IMX7D_GPT_3M_CLK>; clock-names = "ipg", "per", "osc_per"; }; @@ -462,7 +462,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302e0000 0x10000>; interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT2_ROOT_CLK>, <&clks IMX7D_GPT2_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -472,7 +472,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302f0000 0x10000>; interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT3_ROOT_CLK>, <&clks IMX7D_GPT3_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -482,7 +482,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x30300000 0x10000>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT4_ROOT_CLK>, <&clks IMX7D_GPT4_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index a7883676f675..b144a6a5d352 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -115,10 +115,14 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; }; @@ -241,6 +245,18 @@ OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */ >; }; + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT | MUX_MODE0) /* i2c2_sda */ + >; + }; + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT | MUX_MODE0) /* i2c3_sda */ + >; + }; }; &omap3_pmx_core2 { diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index cf22b35f0a28..7265d7072b5c 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -121,10 +121,14 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; at24@50 { compatible = "atmel,24c64"; @@ -219,6 +223,18 @@ OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ >; }; + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT | MUX_MODE0) /* i2c2_sda */ + >; + }; + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT | MUX_MODE0) /* i2c3_sda */ + >; + }; }; &uart2 { @@ -254,3 +270,7 @@ &twl_gpio { ti,use-leds; }; + +&twl_keypad { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/lpc32xx.dtsi b/arch/arm/boot/dts/lpc32xx.dtsi index f22a33a01819..d077bd2b9583 100644 --- a/arch/arm/boot/dts/lpc32xx.dtsi +++ b/arch/arm/boot/dts/lpc32xx.dtsi @@ -179,7 +179,7 @@ * ssp0 and spi1 are shared pins; * enable one in your board dts, as needed. */ - ssp0: ssp@20084000 { + ssp0: spi@20084000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x20084000 0x1000>; interrupts = <20 IRQ_TYPE_LEVEL_HIGH>; @@ -199,7 +199,7 @@ * ssp1 and spi2 are shared pins; * enable one in your board dts, as needed. */ - ssp1: ssp@2008c000 { + ssp1: spi@2008c000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x2008c000 0x1000>; interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index b98d44fde6b6..e3ae85d65b39 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -170,7 +170,7 @@ #clock-cells = <1>; #reset-cells = <1>; compatible = "amlogic,meson8-clkc"; - reg = <0x8000 0x4>, <0x4000 0x460>; + reg = <0x8000 0x4>, <0x4000 0x400>; }; pwm_ef: pwm@86c0 { diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi index bc278da7df0d..0f76da280ee7 100644 --- a/arch/arm/boot/dts/meson8b.dtsi +++ b/arch/arm/boot/dts/meson8b.dtsi @@ -121,7 +121,7 @@ #clock-cells = <1>; #reset-cells = <1>; compatible = "amlogic,meson8b-clkc"; - reg = <0x8000 0x4>, <0x4000 0x460>; + reg = <0x8000 0x4>, <0x4000 0x400>; }; reset: reset-controller@4404 { diff --git a/arch/arm/boot/dts/mmp2.dtsi b/arch/arm/boot/dts/mmp2.dtsi index 47e5b63339d1..e95deed6a797 100644 --- a/arch/arm/boot/dts/mmp2.dtsi +++ b/arch/arm/boot/dts/mmp2.dtsi @@ -180,7 +180,7 @@ clocks = <&soc_clocks MMP2_CLK_GPIO>; resets = <&soc_clocks MMP2_CLK_GPIO>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; ranges; gcb0: gpio@d4019000 { diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 4504908c23fe..e83d0619b3b7 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -28,6 +28,7 @@ aliases { display0 = &lcd; + display1 = &tv0; }; gpio-keys { @@ -71,7 +72,7 @@ #sound-dai-cells = <0>; }; - spi_lcd { + spi_lcd: spi_lcd { compatible = "spi-gpio"; #address-cells = <0x1>; #size-cells = <0x0>; @@ -123,7 +124,7 @@ }; tv0: connector { - compatible = "svideo-connector"; + compatible = "composite-video-connector"; label = "tv"; port { @@ -135,7 +136,7 @@ tv_amp: opa362 { compatible = "ti,opa362"; - enable-gpios = <&gpio1 23 GPIO_ACTIVE_HIGH>; + enable-gpios = <&gpio1 23 GPIO_ACTIVE_HIGH>; /* GPIO_23 to enable video out amplifier */ ports { #address-cells = <1>; @@ -274,6 +275,13 @@ OMAP3_CORE1_IOPAD(0x2134, PIN_INPUT_PULLUP | MUX_MODE4) /* gpio112 */ >; }; + + penirq_pins: pinmux_penirq_pins { + pinctrl-single,pins = < + /* here we could enable to wakeup the cpu from suspend by a pen touch */ + OMAP3_CORE1_IOPAD(0x2194, PIN_INPUT_PULLUP | MUX_MODE4) /* gpio160 */ + >; + }; }; &omap3_pmx_core2 { @@ -411,10 +419,19 @@ tsc2007@48 { compatible = "ti,tsc2007"; reg = <0x48>; + pinctrl-names = "default"; + pinctrl-0 = <&penirq_pins>; interrupt-parent = <&gpio6>; interrupts = <0 IRQ_TYPE_EDGE_FALLING>; /* GPIO_160 */ - gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; + gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* GPIO_160 */ ti,x-plate-ohms = <600>; + touchscreen-size-x = <480>; + touchscreen-size-y = <640>; + touchscreen-max-pressure = <1000>; + touchscreen-fuzz-x = <3>; + touchscreen-fuzz-y = <8>; + touchscreen-fuzz-pressure = <10>; + touchscreen-inverted-y; }; /* RFID EEPROM */ @@ -520,6 +537,12 @@ regulator-max-microvolt = <3150000>; }; +/* Needed to power the DPI pins */ + +&vpll2 { + regulator-always-on; +}; + &dss { pinctrl-names = "default"; pinctrl-0 = < &dss_dpi_pins >; @@ -540,10 +563,14 @@ vdda-supply = <&vdac>; + #address-cells = <1>; + #size-cells = <0>; + port { + reg = <0>; venc_out: endpoint { remote-endpoint = <&opa_in>; - ti,channels = <2>; + ti,channels = <1>; ti,invert-polarity; }; }; @@ -587,22 +614,22 @@ bootloaders@80000 { label = "U-Boot"; - reg = <0x80000 0x1e0000>; + reg = <0x80000 0x1c0000>; }; - bootloaders_env@260000 { + bootloaders_env@240000 { label = "U-Boot Env"; - reg = <0x260000 0x20000>; + reg = <0x240000 0x40000>; }; kernel@280000 { label = "Kernel"; - reg = <0x280000 0x400000>; + reg = <0x280000 0x600000>; }; - filesystem@680000 { + filesystem@880000 { label = "File System"; - reg = <0x680000 0xf980000>; + reg = <0x880000 0>; /* 0 = MTDPART_SIZ_FULL */ }; }; }; diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi index 53e007abdc71..964240a0f4a9 100644 --- a/arch/arm/boot/dts/omap3-pandora-common.dtsi +++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi @@ -221,6 +221,17 @@ gpio = <&gpio6 4 GPIO_ACTIVE_HIGH>; /* GPIO_164 */ }; + /* wl1251 wifi+bt module */ + wlan_en: fixed-regulator-wg7210_en { + compatible = "regulator-fixed"; + regulator-name = "vwlan"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + startup-delay-us = <50000>; + enable-active-high; + gpio = <&gpio1 23 GPIO_ACTIVE_HIGH>; + }; + /* wg7210 (wifi+bt module) 32k clock buffer */ wg7210_32k: fixed-regulator-wg7210_32k { compatible = "regulator-fixed"; @@ -514,9 +525,30 @@ /*wp-gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>;*/ /* GPIO_127 */ }; -/* mmc3 is probed using pdata-quirks to pass wl1251 card data */ &mmc3 { - status = "disabled"; + vmmc-supply = <&wlan_en>; + + bus-width = <4>; + non-removable; + ti,non-removable; + cap-power-off-card; + + pinctrl-names = "default"; + pinctrl-0 = <&mmc3_pins>; + + #address-cells = <1>; + #size-cells = <0>; + + wlan: wifi@1 { + compatible = "ti,wl1251"; + + reg = <1>; + + interrupt-parent = <&gpio1>; + interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* GPIO_21 */ + + ti,wl1251-has-eeprom; + }; }; /* bluetooth*/ diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi index 9a601d15247b..5b7bda74752b 100644 --- a/arch/arm/boot/dts/omap3-tao3530.dtsi +++ b/arch/arm/boot/dts/omap3-tao3530.dtsi @@ -224,7 +224,7 @@ pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; vqmmc-supply = <&vsim>; - cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_HIGH>; + cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>; bus-width = <8>; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 7824b2631cb6..c58f14de0145 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -694,6 +694,11 @@ vbus-supply = <&smps10_out1_reg>; }; +&dwc3 { + extcon = <&extcon_usb3>; + dr_mode = "otg"; +}; + &mcspi1 { }; diff --git a/arch/arm/boot/dts/orion5x-linkstation.dtsi b/arch/arm/boot/dts/orion5x-linkstation.dtsi index e9991c83d7b7..117d71546ed0 100644 --- a/arch/arm/boot/dts/orion5x-linkstation.dtsi +++ b/arch/arm/boot/dts/orion5x-linkstation.dtsi @@ -156,7 +156,7 @@ &i2c { status = "okay"; - rtc { + rtc@32 { compatible = "ricoh,rs5c372a"; reg = <0x32>; }; diff --git a/arch/arm/boot/dts/pxa25x.dtsi b/arch/arm/boot/dts/pxa25x.dtsi index 95d59be97213..8494b5787170 100644 --- a/arch/arm/boot/dts/pxa25x.dtsi +++ b/arch/arm/boot/dts/pxa25x.dtsi @@ -80,6 +80,10 @@ #pwm-cells = <1>; clocks = <&clks CLK_PWM1>; }; + + rtc@40900000 { + clocks = <&clks CLK_OSC32k768>; + }; }; timer@40a00000 { diff --git a/arch/arm/boot/dts/pxa27x.dtsi b/arch/arm/boot/dts/pxa27x.dtsi index 747f750f675d..ccbecad9c5c7 100644 --- a/arch/arm/boot/dts/pxa27x.dtsi +++ b/arch/arm/boot/dts/pxa27x.dtsi @@ -35,7 +35,7 @@ clocks = <&clks CLK_NONE>; }; - pxa27x_ohci: usb@4c000000 { + usb0: usb@4c000000 { compatible = "marvell,pxa-ohci"; reg = <0x4c000000 0x10000>; interrupts = <3>; @@ -71,7 +71,7 @@ clocks = <&clks CLK_PWM1>; }; - pwri2c: i2c@40f000180 { + pwri2c: i2c@40f00180 { compatible = "mrvl,pxa-i2c"; reg = <0x40f00180 0x24>; interrupts = <6>; @@ -113,6 +113,10 @@ status = "disabled"; }; + + rtc@40900000 { + clocks = <&clks CLK_OSC32k768>; + }; }; clocks { diff --git a/arch/arm/boot/dts/pxa2xx.dtsi b/arch/arm/boot/dts/pxa2xx.dtsi index e4ebcde17837..a03bca81ae8a 100644 --- a/arch/arm/boot/dts/pxa2xx.dtsi +++ b/arch/arm/boot/dts/pxa2xx.dtsi @@ -117,13 +117,6 @@ status = "disabled"; }; - usb0: ohci@4c000000 { - compatible = "marvell,pxa-ohci"; - reg = <0x4c000000 0x10000>; - interrupts = <3>; - status = "disabled"; - }; - mmc0: mmc@41100000 { compatible = "marvell,pxa-mmc"; reg = <0x41100000 0x1000>; diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi index 55c75b67351c..affa5b6f6da1 100644 --- a/arch/arm/boot/dts/pxa3xx.dtsi +++ b/arch/arm/boot/dts/pxa3xx.dtsi @@ -189,7 +189,7 @@ status = "disabled"; }; - pxa3xx_ohci: usb@4c000000 { + usb0: usb@4c000000 { compatible = "marvell,pxa-ohci"; reg = <0x4c000000 0x10000>; interrupts = <3>; diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi index 10d112a4078e..19156cbb6003 100644 --- a/arch/arm/boot/dts/qcom-ipq4019.dtsi +++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi @@ -234,7 +234,7 @@ saw0: regulator@b089000 { compatible = "qcom,saw2"; - reg = <0x02089000 0x1000>, <0x0b009000 0x1000>; + reg = <0x0b089000 0x1000>, <0x0b009000 0x1000>; regulator; }; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 5c0a76493d22..03cf0c84ac0a 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -750,7 +750,7 @@ /* no rts / cts for uart2 */ }; - spi { + spi-pins { spi_txd:spi-txd { rockchip,pins = <1 29 RK_FUNC_3 &pcfg_pull_default>; }; diff --git a/arch/arm/boot/dts/rk3188-radxarock.dts b/arch/arm/boot/dts/rk3188-radxarock.dts index 53d6fc2fdbce..541a798d3d20 100644 --- a/arch/arm/boot/dts/rk3188-radxarock.dts +++ b/arch/arm/boot/dts/rk3188-radxarock.dts @@ -130,6 +130,8 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; gpio = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc_pwr>; startup-delay-us = <100000>; vin-supply = <&vcc_io>; }; @@ -348,6 +350,12 @@ }; }; + sd0 { + sdmmc_pwr: sdmmc-pwr { + rockchip,pins = <RK_GPIO3 1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + usb { host_vbus_drv: host-vbus-drv { rockchip,pins = <0 3 RK_FUNC_GPIO &pcfg_pull_none>; diff --git a/arch/arm/boot/dts/rk3288-rock2-som.dtsi b/arch/arm/boot/dts/rk3288-rock2-som.dtsi index b9c471fcbd42..862c2248fcb6 100644 --- a/arch/arm/boot/dts/rk3288-rock2-som.dtsi +++ b/arch/arm/boot/dts/rk3288-rock2-som.dtsi @@ -63,7 +63,7 @@ vcc_flash: flash-regulator { compatible = "regulator-fixed"; - regulator-name = "vcc_sys"; + regulator-name = "vcc_flash"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; startup-delay-us = <150>; diff --git a/arch/arm/boot/dts/rk3288-veyron-mickey.dts b/arch/arm/boot/dts/rk3288-veyron-mickey.dts index f0994f0e5774..d6ca67866bc0 100644 --- a/arch/arm/boot/dts/rk3288-veyron-mickey.dts +++ b/arch/arm/boot/dts/rk3288-veyron-mickey.dts @@ -161,10 +161,6 @@ }; }; -&emmc { - /delete-property/mmc-hs200-1_8v; -}; - &i2c2 { status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts index 544de6027aaa..6000dca1cf05 100644 --- a/arch/arm/boot/dts/rk3288-veyron-minnie.dts +++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts @@ -125,10 +125,6 @@ power-supply = <&backlight_regulator>; }; -&emmc { - /delete-property/mmc-hs200-1_8v; -}; - &gpio_keys { pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 5a7888581eea..23907d9ce89a 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -213,6 +213,7 @@ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>, <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>; clock-frequency = <24000000>; + arm,no-tick-in-suspend; }; timer: timer@ff810000 { diff --git a/arch/arm/boot/dts/rv1108.dtsi b/arch/arm/boot/dts/rv1108.dtsi index e7cd1315db1b..aa4119eaea98 100644 --- a/arch/arm/boot/dts/rv1108.dtsi +++ b/arch/arm/boot/dts/rv1108.dtsi @@ -101,7 +101,7 @@ arm-pmu { compatible = "arm,cortex-a7-pmu"; - interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>; }; timer { @@ -522,7 +522,7 @@ compatible = "rockchip,gpio-bank"; reg = <0x20030000 0x100>; interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&xin24m>; + clocks = <&cru PCLK_GPIO0_PMU>; gpio-controller; #gpio-cells = <2>; @@ -535,7 +535,7 @@ compatible = "rockchip,gpio-bank"; reg = <0x10310000 0x100>; interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&xin24m>; + clocks = <&cru PCLK_GPIO1>; gpio-controller; #gpio-cells = <2>; @@ -548,7 +548,7 @@ compatible = "rockchip,gpio-bank"; reg = <0x10320000 0x100>; interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&xin24m>; + clocks = <&cru PCLK_GPIO2>; gpio-controller; #gpio-cells = <2>; @@ -561,7 +561,7 @@ compatible = "rockchip,gpio-bank"; reg = <0x10330000 0x100>; interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&xin24m>; + clocks = <&cru PCLK_GPIO3>; gpio-controller; #gpio-cells = <2>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts index b280e6494193..31b01a998b2e 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_de0_sockit.dts @@ -88,7 +88,7 @@ status = "okay"; clock-frequency = <100000>; - adxl345: adxl345@0 { + adxl345: adxl345@53 { compatible = "adi,adxl345"; reg = <0x53>; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index 2310a4e97768..986767735e24 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -197,7 +197,7 @@ <0xa0410100 0x100>; }; - scu@a04100000 { + scu@a0410000 { compatible = "arm,cortex-a9-scu"; reg = <0xa0410000 0x100>; }; @@ -878,7 +878,7 @@ power-domains = <&pm_domains DOMAIN_VAPE>; }; - ssp@80002000 { + spi@80002000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x80002000 0x1000>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; @@ -892,7 +892,7 @@ power-domains = <&pm_domains DOMAIN_VAPE>; }; - ssp@80003000 { + spi@80003000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x80003000 0x1000>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/ste-href-family-pinctrl.dtsi b/arch/arm/boot/dts/ste-href-family-pinctrl.dtsi index 5c5cea232743..1ec193b0c506 100644 --- a/arch/arm/boot/dts/ste-href-family-pinctrl.dtsi +++ b/arch/arm/boot/dts/ste-href-family-pinctrl.dtsi @@ -607,16 +607,20 @@ mcde { lcd_default_mode: lcd_default { - default_mux { + default_mux1 { /* Mux in VSI0 and all the data lines */ function = "lcd"; groups = "lcdvsi0_a_1", /* VSI0 for LCD */ "lcd_d0_d7_a_1", /* Data lines */ "lcd_d8_d11_a_1", /* TV-out */ - "lcdaclk_b_1", /* Clock line for TV-out */ "lcdvsi1_a_1"; /* VSI1 for HDMI */ }; + default_mux2 { + function = "lcda"; + groups = + "lcdaclk_b_1"; /* Clock line for TV-out */ + }; default_cfg1 { pins = "GPIO68_E1", /* VSI0 */ diff --git a/arch/arm/boot/dts/ste-hrefprev60.dtsi b/arch/arm/boot/dts/ste-hrefprev60.dtsi index 3f14b4df69b4..94eeb7f1c947 100644 --- a/arch/arm/boot/dts/ste-hrefprev60.dtsi +++ b/arch/arm/boot/dts/ste-hrefprev60.dtsi @@ -57,7 +57,7 @@ }; }; - ssp@80002000 { + spi@80002000 { /* * On the first generation boards, this SSP/SPI port was connected * to the AB8500. diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index ade1d0d4e5f4..1bf4358f8fa7 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -376,7 +376,7 @@ pinctrl-1 = <&i2c3_sleep_mode>; }; - ssp@80002000 { + spi@80002000 { pinctrl-names = "default"; pinctrl-0 = <&ssp0_snowball_mode>; }; diff --git a/arch/arm/boot/dts/ste-u300.dts b/arch/arm/boot/dts/ste-u300.dts index 62ecb6a2fa39..1bd1aba3322f 100644 --- a/arch/arm/boot/dts/ste-u300.dts +++ b/arch/arm/boot/dts/ste-u300.dts @@ -442,7 +442,7 @@ dma-names = "rx"; }; - spi: ssp@c0006000 { + spi: spi@c0006000 { compatible = "arm,pl022", "arm,primecell"; reg = <0xc0006000 0x1000>; interrupt-parent = <&vica>; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index 18f25c5e75ae..396fb6632bf0 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -104,8 +104,6 @@ }; hdmi_out: port@1 { - #address-cells = <1>; - #size-cells = <0>; reg = <1>; }; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index eef072a21acc..0bb82d0442a5 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -173,7 +173,7 @@ }; pmu { - compatible = "arm,cortex-a7-pmu", "arm,cortex-a15-pmu"; + compatible = "arm,cortex-a7-pmu"; interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 96bee776e145..77f04dbdf996 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -171,7 +171,7 @@ }; pmu { - compatible = "arm,cortex-a7-pmu", "arm,cortex-a15-pmu"; + compatible = "arm,cortex-a7-pmu"; interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero.dts b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero.dts index 387fc2aa546d..333df90e8037 100644 --- a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero.dts +++ b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero.dts @@ -78,7 +78,7 @@ }; &mmc0 { - pinctrl-0 = <&mmc0_pins_a>; + pinctrl-0 = <&mmc0_pins>; pinctrl-names = "default"; broken-cd; bus-width = <4>; @@ -87,7 +87,7 @@ }; &uart0 { - pinctrl-0 = <&uart0_pins_a>; + pinctrl-0 = <&uart0_pb_pins>; pinctrl-names = "default"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index 3a06dc5b3746..da5823c6fa3e 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -292,17 +292,17 @@ interrupt-controller; #interrupt-cells = <3>; - i2c0_pins: i2c0 { + i2c0_pins: i2c0-pins { pins = "PB6", "PB7"; function = "i2c0"; }; - uart0_pins_a: uart0@0 { + uart0_pb_pins: uart0-pb-pins { pins = "PB8", "PB9"; function = "uart0"; }; - mmc0_pins_a: mmc0@0 { + mmc0_pins: mmc0-pins { pins = "PF0", "PF1", "PF2", "PF3", "PF4", "PF5"; function = "mmc0"; @@ -310,7 +310,7 @@ bias-pull-up; }; - mmc1_pins: mmc1 { + mmc1_pins: mmc1-pins { pins = "PG0", "PG1", "PG2", "PG3", "PG4", "PG5"; function = "mmc1"; @@ -318,7 +318,7 @@ bias-pull-up; }; - spi0_pins: spi0 { + spi0_pins: spi0-pins { pins = "PC0", "PC1", "PC2", "PC3"; function = "spi0"; }; diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi index 11240a8313c2..03f37081fc64 100644 --- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi +++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi @@ -594,7 +594,7 @@ clock-names = "apb", "ir"; resets = <&r_ccu RST_APB0_IR>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x01f02000 0x40>; + reg = <0x01f02000 0x400>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts index 30436969adc0..1b8db91277b1 100644 --- a/arch/arm/boot/dts/tegra20-paz00.dts +++ b/arch/arm/boot/dts/tegra20-paz00.dts @@ -524,10 +524,10 @@ gpio-keys { compatible = "gpio-keys"; - power { - label = "Power"; + wakeup { + label = "Wakeup"; gpios = <&gpio TEGRA_GPIO(J, 7) GPIO_ACTIVE_LOW>; - linux,code = <KEY_POWER>; + linux,code = <KEY_WAKEUP>; wakeup-source; }; }; diff --git a/arch/arm/boot/dts/tegra30-apalis.dtsi b/arch/arm/boot/dts/tegra30-apalis.dtsi index faa8cd2914e8..b9368d40bc6f 100644 --- a/arch/arm/boot/dts/tegra30-apalis.dtsi +++ b/arch/arm/boot/dts/tegra30-apalis.dtsi @@ -166,14 +166,14 @@ /* Apalis MMC1 */ sdmmc3_clk_pa6 { - nvidia,pins = "sdmmc3_clk_pa6", - "sdmmc3_cmd_pa7"; + nvidia,pins = "sdmmc3_clk_pa6"; nvidia,function = "sdmmc3"; nvidia,pull = <TEGRA_PIN_PULL_NONE>; nvidia,tristate = <TEGRA_PIN_DISABLE>; }; sdmmc3_dat0_pb7 { - nvidia,pins = "sdmmc3_dat0_pb7", + nvidia,pins = "sdmmc3_cmd_pa7", + "sdmmc3_dat0_pb7", "sdmmc3_dat1_pb6", "sdmmc3_dat2_pb5", "sdmmc3_dat3_pb4", diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi index c3e9f1e847db..cb5b76e95813 100644 --- a/arch/arm/boot/dts/tegra30.dtsi +++ b/arch/arm/boot/dts/tegra30.dtsi @@ -840,7 +840,7 @@ nvidia,elastic-limit = <16>; nvidia,term-range-adj = <6>; nvidia,xcvr-setup = <51>; - nvidia.xcvr-setup-use-fuses; + nvidia,xcvr-setup-use-fuses; nvidia,xcvr-lsfslew = <1>; nvidia,xcvr-lsrslew = <1>; nvidia,xcvr-hsslew = <32>; @@ -877,7 +877,7 @@ nvidia,elastic-limit = <16>; nvidia,term-range-adj = <6>; nvidia,xcvr-setup = <51>; - nvidia.xcvr-setup-use-fuses; + nvidia,xcvr-setup-use-fuses; nvidia,xcvr-lsfslew = <2>; nvidia,xcvr-lsrslew = <2>; nvidia,xcvr-hsslew = <32>; @@ -913,7 +913,7 @@ nvidia,elastic-limit = <16>; nvidia,term-range-adj = <6>; nvidia,xcvr-setup = <51>; - nvidia.xcvr-setup-use-fuses; + nvidia,xcvr-setup-use-fuses; nvidia,xcvr-lsfslew = <2>; nvidia,xcvr-lsrslew = <2>; nvidia,xcvr-hsslew = <32>; diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 4a51612996bc..a9000d22b2c0 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -304,7 +304,7 @@ clock-names = "apb_pclk"; }; - ssp@101f4000 { + spi@101f4000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x101f4000 0x1000>; interrupts = <11>; diff --git a/arch/arm/configs/badge4_defconfig b/arch/arm/configs/badge4_defconfig index 5ae5b5228467..ef484c4cfd1a 100644 --- a/arch/arm/configs/badge4_defconfig +++ b/arch/arm/configs/badge4_defconfig @@ -91,7 +91,6 @@ CONFIG_USB_SERIAL_PL2303=m CONFIG_USB_SERIAL_CYBERJACK=m CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_RIO500=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m CONFIG_MSDOS_FS=y diff --git a/arch/arm/configs/corgi_defconfig b/arch/arm/configs/corgi_defconfig index 09e1672777c9..0ba8df0d48b9 100644 --- a/arch/arm/configs/corgi_defconfig +++ b/arch/arm/configs/corgi_defconfig @@ -197,7 +197,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index d5e1370ec303..38a5680c8236 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -588,7 +588,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index 2afb359f3168..bd71d5bf98c9 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -334,7 +334,6 @@ CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m CONFIG_USB_ADUTUX=m CONFIG_USB_SEVSEG=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYPRESS_CY7C63=m diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig index 9ea82c118661..3aff4ca2a94e 100644 --- a/arch/arm/configs/spitz_defconfig +++ b/arch/arm/configs/spitz_defconfig @@ -191,7 +191,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c index 96e62ec105d0..cd9e93b46c2d 100644 --- a/arch/arm/crypto/crc32-ce-glue.c +++ b/arch/arm/crypto/crc32-ce-glue.c @@ -236,7 +236,7 @@ static void __exit crc32_pmull_mod_exit(void) ARRAY_SIZE(crc32_pmull_algs)); } -static const struct cpu_feature crc32_cpu_feature[] = { +static const struct cpu_feature __maybe_unused crc32_cpu_feature[] = { { cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { } }; MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature); diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index a5807b67ca8a..fe47d24955ea 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -349,6 +349,13 @@ do { \ #define __get_user_asm_byte(x, addr, err) \ __get_user_asm(x, addr, err, ldrb) +#if __LINUX_ARM_ARCH__ >= 6 + +#define __get_user_asm_half(x, addr, err) \ + __get_user_asm(x, addr, err, ldrh) + +#else + #ifndef __ARMEB__ #define __get_user_asm_half(x, __gu_addr, err) \ ({ \ @@ -367,6 +374,8 @@ do { \ }) #endif +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + #define __get_user_asm_word(x, addr, err) \ __get_user_asm(x, addr, err, ldr) #endif @@ -442,6 +451,13 @@ do { \ #define __put_user_asm_byte(x, __pu_addr, err) \ __put_user_asm(x, __pu_addr, err, strb) +#if __LINUX_ARM_ARCH__ >= 6 + +#define __put_user_asm_half(x, __pu_addr, err) \ + __put_user_asm(x, __pu_addr, err, strh) + +#else + #ifndef __ARMEB__ #define __put_user_asm_half(x, __pu_addr, err) \ ({ \ @@ -458,6 +474,8 @@ do { \ }) #endif +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + #define __put_user_asm_word(x, __pu_addr, err) \ __put_user_asm(x, __pu_addr, err, str) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index d7dc808a3d15..08a7132f5600 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -282,16 +282,15 @@ __sys_trace: cmp scno, #-1 @ skip the syscall? bne 2b add sp, sp, #S_OFF @ restore stack - b ret_slow_syscall -__sys_trace_return: - str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 +__sys_trace_return_nosave: + enable_irq_notrace mov r0, sp bl syscall_trace_exit b ret_slow_syscall -__sys_trace_return_nosave: - enable_irq_notrace +__sys_trace_return: + str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 mov r0, sp bl syscall_trace_exit b ret_slow_syscall diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 746e7801dcdf..b2e4bc3a635e 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -42,6 +42,12 @@ _ASM_NOKPROBE(__get_user_1) ENTRY(__get_user_2) check_uaccess r0, 2, r1, r2, __get_user_bad +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(ldrh) r2, [r0] + +#else + #ifdef CONFIG_CPU_USE_DOMAINS rb .req ip 2: ldrbt r2, [r0], #1 @@ -56,6 +62,9 @@ rb .req r0 #else orr r2, rb, r2, lsl #8 #endif + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + mov r0, #0 ret lr ENDPROC(__get_user_2) @@ -145,7 +154,9 @@ _ASM_NOKPROBE(__get_user_bad8) .pushsection __ex_table, "a" .long 1b, __get_user_bad .long 2b, __get_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __get_user_bad +#endif .long 4b, __get_user_bad .long 5b, __get_user_bad8 .long 6b, __get_user_bad8 diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S index 38d660d3705f..515eeaa9975c 100644 --- a/arch/arm/lib/putuser.S +++ b/arch/arm/lib/putuser.S @@ -41,16 +41,13 @@ ENDPROC(__put_user_1) ENTRY(__put_user_2) check_uaccess r0, 2, r1, ip, __put_user_bad - mov ip, r2, lsr #8 -#ifdef CONFIG_THUMB2_KERNEL -#ifndef __ARMEB__ -2: TUSER(strb) r2, [r0] -3: TUSER(strb) ip, [r0, #1] +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(strh) r2, [r0] + #else -2: TUSER(strb) ip, [r0] -3: TUSER(strb) r2, [r0, #1] -#endif -#else /* !CONFIG_THUMB2_KERNEL */ + + mov ip, r2, lsr #8 #ifndef __ARMEB__ 2: TUSER(strb) r2, [r0], #1 3: TUSER(strb) ip, [r0] @@ -58,7 +55,8 @@ ENTRY(__put_user_2) 2: TUSER(strb) ip, [r0], #1 3: TUSER(strb) r2, [r0] #endif -#endif /* CONFIG_THUMB2_KERNEL */ + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ mov r0, #0 ret lr ENDPROC(__put_user_2) @@ -91,7 +89,9 @@ ENDPROC(__put_user_bad) .pushsection __ex_table, "a" .long 1b, __put_user_bad .long 2b, __put_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __put_user_bad +#endif .long 4b, __put_user_bad .long 5b, __put_user_bad .long 6b, __put_user_bad diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 2f6ac1afa804..686e7e6f2eb3 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1464,6 +1464,8 @@ static __init void da850_evm_init(void) if (ret) pr_warn("%s: dsp/rproc registration failed: %d\n", __func__, ret); + + regulator_has_full_constraints(); } #ifdef CONFIG_SERIAL_8250_CONSOLE diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c index 22440c05d66a..7120f93eab0b 100644 --- a/arch/arm/mach-davinci/devices-da8xx.c +++ b/arch/arm/mach-davinci/devices-da8xx.c @@ -699,6 +699,9 @@ static struct platform_device da8xx_lcdc_device = { .id = 0, .num_resources = ARRAY_SIZE(da8xx_lcdc_resources), .resource = da8xx_lcdc_resources, + .dev = { + .coherent_dma_mask = DMA_BIT_MASK(32), + } }; int __init da8xx_register_lcdc(struct da8xx_lcdc_platform_data *pdata) diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index 8be04ec95adf..d80b2290ac2e 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -856,8 +856,8 @@ static s8 dm365_queue_priority_mapping[][2] = { }; static const struct dma_slave_map dm365_edma_map[] = { - { "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) }, - { "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) }, + { "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) }, + { "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) }, { "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) }, { "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) }, { "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) }, diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S index cd350dee4df3..efcd400b2abb 100644 --- a/arch/arm/mach-davinci/sleep.S +++ b/arch/arm/mach-davinci/sleep.S @@ -37,6 +37,7 @@ #define DEEPSLEEP_SLEEPENABLE_BIT BIT(31) .text + .arch armv5te /* * Move DaVinci into deep sleep state * diff --git a/arch/arm/mach-imx/cpuidle-imx6sx.c b/arch/arm/mach-imx/cpuidle-imx6sx.c index b16bee20fa14..534e47ff037b 100644 --- a/arch/arm/mach-imx/cpuidle-imx6sx.c +++ b/arch/arm/mach-imx/cpuidle-imx6sx.c @@ -233,6 +233,15 @@ int __init imx6sx_cpuidle_init(void) #endif imx6_set_int_mem_clk_lpm(true); + imx6_enable_rbc(false); + /* + * set ARM power up/down timing to the fastest, + * sw2iso and sw can be set to one 32K cycle = 31us + * except for power up sw2iso which need to be + * larger than LDO ramp up time. + */ + imx_gpc_set_arm_power_up_timing(0xf, 1); + imx_gpc_set_arm_power_down_timing(1, 1); if (imx_get_soc_revision() >= IMX_CHIP_REVISION_1_2) { /* diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index 5d0a7c3f6114..e58cfa195794 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -1272,6 +1272,28 @@ static void __init imx6_pm_common_init(const struct imx6_pm_socdata IMX6Q_GPR1_GINT); } +static void imx6_pm_stby_poweroff(void) +{ + imx6_set_lpm(STOP_POWER_OFF); + imx6q_suspend_finish(0); + + mdelay(1000); + + pr_emerg("Unable to poweroff system\n"); +} + +static int imx6_pm_stby_poweroff_probe(void) +{ + if (pm_power_off) { + pr_warn("%s: pm_power_off already claimed %p %pf!\n", + __func__, pm_power_off, pm_power_off); + return -EBUSY; + } + + pm_power_off = imx6_pm_stby_poweroff; + return 0; +} + void __init imx6_pm_ccm_init(const char *ccm_compat) { struct device_node *np; @@ -1288,6 +1310,9 @@ void __init imx6_pm_ccm_init(const char *ccm_compat) val = readl_relaxed(ccm_base + CLPCR); val &= ~BM_CLPCR_LPM; writel_relaxed(val, ccm_base + CLPCR); + + if (of_property_read_bool(np, "fsl,pmic-stby-poweroff")) + imx6_pm_stby_poweroff_probe(); } void __init imx6q_pm_init(void) diff --git a/arch/arm/mach-ks8695/board-acs5k.c b/arch/arm/mach-ks8695/board-acs5k.c index e4d709c8ed32..76d3083f1f63 100644 --- a/arch/arm/mach-ks8695/board-acs5k.c +++ b/arch/arm/mach-ks8695/board-acs5k.c @@ -92,7 +92,7 @@ static struct i2c_board_info acs5k_i2c_devs[] __initdata = { }, }; -static void acs5k_i2c_init(void) +static void __init acs5k_i2c_init(void) { /* The gpio interface */ platform_device_register(&acs5k_i2c_device); diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile index e8ccf51c6f29..ec0235899de2 100644 --- a/arch/arm/mach-omap1/Makefile +++ b/arch/arm/mach-omap1/Makefile @@ -25,7 +25,7 @@ obj-y += $(i2c-omap-m) $(i2c-omap-y) led-y := leds.o -usb-fs-$(CONFIG_USB) := usb.o +usb-fs-$(CONFIG_USB_SUPPORT) := usb.o obj-y += $(usb-fs-m) $(usb-fs-y) # Specific board support diff --git a/arch/arm/mach-omap1/id.c b/arch/arm/mach-omap1/id.c index 52de382fc804..7e49dfda3d2f 100644 --- a/arch/arm/mach-omap1/id.c +++ b/arch/arm/mach-omap1/id.c @@ -200,10 +200,10 @@ void __init omap_check_revision(void) printk(KERN_INFO "Unknown OMAP cpu type: 0x%02x\n", cpu_type); } - printk(KERN_INFO "OMAP%04x", omap_revision >> 16); + pr_info("OMAP%04x", omap_revision >> 16); if ((omap_revision >> 8) & 0xff) - printk(KERN_INFO "%x", (omap_revision >> 8) & 0xff); - printk(KERN_INFO " revision %i handled as %02xxx id: %08x%08x\n", + pr_cont("%x", (omap_revision >> 8) & 0xff); + pr_cont(" revision %i handled as %02xxx id: %08x%08x\n", die_rev, omap_revision & 0xff, system_serial_low, system_serial_high); } diff --git a/arch/arm/mach-omap1/include/mach/usb.h b/arch/arm/mach-omap1/include/mach/usb.h index 77867778d4ec..5429d86c7190 100644 --- a/arch/arm/mach-omap1/include/mach/usb.h +++ b/arch/arm/mach-omap1/include/mach/usb.h @@ -11,7 +11,7 @@ #include <linux/platform_data/usb-omap1.h> -#if IS_ENABLED(CONFIG_USB) +#if IS_ENABLED(CONFIG_USB_SUPPORT) void omap1_usb_init(struct omap_usb_config *pdata); #else static inline void omap1_usb_init(struct omap_usb_config *pdata) diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 16cb1c195fd8..79d71b1eae59 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -199,8 +199,8 @@ void __init omap2xxx_check_revision(void) pr_info("%s", soc_name); if ((omap_rev() >> 8) & 0x0f) - pr_info("%s", soc_rev); - pr_info("\n"); + pr_cont("%s", soc_rev); + pr_cont("\n"); } #define OMAP3_SHOW_FEATURE(feat) \ diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index cf65ab8bb004..e5dcbda20129 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -131,6 +131,9 @@ static int __init omap4_sram_init(void) struct device_node *np; struct gen_pool *sram_pool; + if (!soc_is_omap44xx() && !soc_is_omap54xx()) + return 0; + np = of_find_compatible_node(NULL, NULL, "ti,omap4-mpu"); if (!np) pr_warn("%s:Unable to allocate sram needed to handle errata I688\n", diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c index de06a1d5ffab..e61c14f59063 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c @@ -966,7 +966,8 @@ static struct omap_hwmod_class_sysconfig am33xx_timer_sysc = { .rev_offs = 0x0000, .sysc_offs = 0x0010, .syss_offs = 0x0014, - .sysc_flags = (SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET), + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | + SYSC_HAS_RESET_STATUS, .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | SIDLE_SMART_WKUP), .sysc_fields = &omap_hwmod_sysc_type2, diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 2f4f7002f38d..87b0c38b7ca5 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -389,7 +389,8 @@ static struct omap_hwmod dra7xx_dcan2_hwmod = { static struct omap_hwmod_class_sysconfig dra7xx_epwmss_sysc = { .rev_offs = 0x0, .sysc_offs = 0x4, - .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET, + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | + SYSC_HAS_RESET_STATUS, .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), .sysc_fields = &omap_hwmod_sysc_type2, }; diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 6b433fce65a5..2477f6086de4 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -307,108 +307,15 @@ static void __init omap3_logicpd_torpedo_init(void) } /* omap3pandora legacy devices */ -#define PANDORA_WIFI_IRQ_GPIO 21 -#define PANDORA_WIFI_NRESET_GPIO 23 static struct platform_device pandora_backlight = { .name = "pandora-backlight", .id = -1, }; -static struct regulator_consumer_supply pandora_vmmc3_supply[] = { - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.2"), -}; - -static struct regulator_init_data pandora_vmmc3 = { - .constraints = { - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(pandora_vmmc3_supply), - .consumer_supplies = pandora_vmmc3_supply, -}; - -static struct fixed_voltage_config pandora_vwlan = { - .supply_name = "vwlan", - .microvolts = 1800000, /* 1.8V */ - .gpio = PANDORA_WIFI_NRESET_GPIO, - .startup_delay = 50000, /* 50ms */ - .enable_high = 1, - .init_data = &pandora_vmmc3, -}; - -static struct platform_device pandora_vwlan_device = { - .name = "reg-fixed-voltage", - .id = 1, - .dev = { - .platform_data = &pandora_vwlan, - }, -}; - -static void pandora_wl1251_init_card(struct mmc_card *card) -{ - /* - * We have TI wl1251 attached to MMC3. Pass this information to - * SDIO core because it can't be probed by normal methods. - */ - if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) { - card->quirks |= MMC_QUIRK_NONSTD_SDIO; - card->cccr.wide_bus = 1; - card->cis.vendor = 0x104c; - card->cis.device = 0x9066; - card->cis.blksize = 512; - card->cis.max_dtr = 24000000; - card->ocr = 0x80; - } -} - -static struct omap2_hsmmc_info pandora_mmc3[] = { - { - .mmc = 3, - .caps = MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD, - .gpio_cd = -EINVAL, - .gpio_wp = -EINVAL, - .init_card = pandora_wl1251_init_card, - }, - {} /* Terminator */ -}; - -static void __init pandora_wl1251_init(void) -{ - struct wl1251_platform_data pandora_wl1251_pdata; - int ret; - - memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata)); - - pandora_wl1251_pdata.power_gpio = -1; - - ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq"); - if (ret < 0) - goto fail; - - pandora_wl1251_pdata.irq = gpio_to_irq(PANDORA_WIFI_IRQ_GPIO); - if (pandora_wl1251_pdata.irq < 0) - goto fail_irq; - - pandora_wl1251_pdata.use_eeprom = true; - ret = wl1251_set_platform_data(&pandora_wl1251_pdata); - if (ret < 0) - goto fail_irq; - - return; - -fail_irq: - gpio_free(PANDORA_WIFI_IRQ_GPIO); -fail: - pr_err("wl1251 board initialisation failed\n"); -} - static void __init omap3_pandora_legacy_init(void) { platform_device_register(&pandora_backlight); - platform_device_register(&pandora_vwlan_device); - omap_hsmmc_init(pandora_mmc3); - omap_hsmmc_late_init(pandora_mmc3); - pandora_wl1251_init(); } #endif /* CONFIG_ARCH_OMAP3 */ diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c index a2dd13217c89..2819c43fe754 100644 --- a/arch/arm/mach-omap2/prm3xxx.c +++ b/arch/arm/mach-omap2/prm3xxx.c @@ -433,7 +433,7 @@ static void omap3_prm_reconfigure_io_chain(void) * registers, and omap3xxx_prm_reconfigure_io_chain() must be called. * No return value. */ -static void __init omap3xxx_prm_enable_io_wakeup(void) +static void omap3xxx_prm_enable_io_wakeup(void) { if (prm_features & PRM_HAS_IO_WAKEUP) omap2_prm_set_mod_reg_bits(OMAP3430_EN_IO_MASK, WKUP_MOD, diff --git a/arch/arm/mach-rpc/dma.c b/arch/arm/mach-rpc/dma.c index fb48f3141fb4..c4c96661eb89 100644 --- a/arch/arm/mach-rpc/dma.c +++ b/arch/arm/mach-rpc/dma.c @@ -131,7 +131,7 @@ static irqreturn_t iomd_dma_handle(int irq, void *dev_id) } while (1); idma->state = ~DMA_ST_AB; - disable_irq(irq); + disable_irq_nosync(irq); return IRQ_HANDLED; } @@ -174,6 +174,9 @@ static void iomd_enable_dma(unsigned int chan, dma_t *dma) DMA_FROM_DEVICE : DMA_TO_DEVICE); } + idma->dma_addr = idma->dma.sg->dma_address; + idma->dma_len = idma->dma.sg->length; + iomd_writeb(DMA_CR_C, dma_base + CR); idma->state = DMA_ST_AB; } diff --git a/arch/arm/mach-zynq/platsmp.c b/arch/arm/mach-zynq/platsmp.c index caa6d5fe9078..b296ada97409 100644 --- a/arch/arm/mach-zynq/platsmp.c +++ b/arch/arm/mach-zynq/platsmp.c @@ -65,7 +65,7 @@ int zynq_cpun_start(u32 address, int cpu) * 0x4: Jump by mov instruction * 0x8: Jumping address */ - memcpy((__force void *)zero, &zynq_secondary_trampoline, + memcpy_toio(zero, &zynq_secondary_trampoline, trampoline_size); writel(address, zero + trampoline_size); diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 2c96190e018b..96b17a870b91 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -768,6 +768,36 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, return NULL; } +static int alignment_get_arm(struct pt_regs *regs, u32 *ip, unsigned long *inst) +{ + u32 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_arm(instr); + + return fault; +} + +static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) +{ + u16 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_thumb16(instr); + + return fault; +} + static int do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { @@ -775,10 +805,10 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) unsigned long instr = 0, instrptr; int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs); unsigned int type; - unsigned int fault; u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; + int fault; if (interrupts_enabled(regs)) local_irq_enable(); @@ -787,15 +817,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); - fault = probe_kernel_address(ptr, tinstr); - tinstr = __mem_to_opcode_thumb16(tinstr); + + fault = alignment_get_thumb(regs, ptr, &tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ - u16 tinst2 = 0; - fault = probe_kernel_address(ptr + 1, tinst2); - tinst2 = __mem_to_opcode_thumb16(tinst2); + u16 tinst2; + fault = alignment_get_thumb(regs, ptr + 1, &tinst2); instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { @@ -804,8 +833,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } } } else { - fault = probe_kernel_address((void *)instrptr, instr); - instr = __mem_to_opcode_arm(instr); + fault = alignment_get_arm(regs, (void *)instrptr, &instr); } if (fault) { diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 49b1b8048635..9bb446cc135d 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -215,7 +215,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) { unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; - if (fsr & FSR_WRITE) + if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) mask = VM_WRITE; if (fsr & FSR_LNX_PF) mask = VM_EXEC; @@ -285,7 +285,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; - if (fsr & FSR_WRITE) + if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) flags |= FAULT_FLAG_WRITE; /* diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index c063708fa503..9ecc2097a87a 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -6,6 +6,7 @@ * Fault status register encodings. We steal bit 31 for our own purposes. */ #define FSR_LNX_PF (1 << 31) +#define FSR_CM (1 << 13) #define FSR_WRITE (1 << 11) #define FSR_FS4 (1 << 10) #define FSR_FS3_0 (15) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index defb7fc26428..27a40101dd3a 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -195,6 +195,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low, #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { + phys_addr_t addr = __pfn_to_phys(pfn); + + if (__phys_to_pfn(addr) != pfn) + return 0; + return memblock_is_map_memory(__pfn_to_phys(pfn)); } EXPORT_SYMBOL(pfn_valid); @@ -722,7 +727,8 @@ static void update_sections_early(struct section_perm perms[], int n) if (t->flags & PF_KTHREAD) continue; for_each_thread(t, s) - set_section_perms(perms, n, true, s->mm); + if (s->mm) + set_section_perms(perms, n, true, s->mm); } set_section_perms(perms, n, true, current->active_mm); set_section_perms(perms, n, true, &init_mm); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e46a6a446cdd..d8cbe772f690 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1175,10 +1175,29 @@ void __init adjust_lowmem_bounds(void) */ vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET; + /* + * The first usable region must be PMD aligned. Mark its start + * as MEMBLOCK_NOMAP if it isn't + */ + for_each_memblock(memory, reg) { + if (!memblock_is_nomap(reg)) { + if (!IS_ALIGNED(reg->base, PMD_SIZE)) { + phys_addr_t len; + + len = round_up(reg->base, PMD_SIZE) - reg->base; + memblock_mark_nomap(reg->base, len); + } + break; + } + } + for_each_memblock(memory, reg) { phys_addr_t block_start = reg->base; phys_addr_t block_end = reg->base + reg->size; + if (memblock_is_nomap(reg)) + continue; + if (reg->base < vmalloc_limit) { if (block_end > lowmem_limit) /* diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 92e84181933a..c68408d51c4b 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -135,7 +135,6 @@ __v7m_setup_cont: dsb mov r6, lr @ save LR ldr sp, =init_thread_union + THREAD_START_SP - stmia sp, {r0-r3, r12} cpsie i svc #0 1: cpsid i diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index dafeb5f81353..b18fb70c5dcf 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -25,8 +25,6 @@ #include "bpf_jit_32.h" -int bpf_jit_enable __read_mostly; - /* * eBPF prog stack layout: * diff --git a/arch/arm/plat-samsung/watchdog-reset.c b/arch/arm/plat-samsung/watchdog-reset.c index 307d8ad96a78..be2ed95da0ec 100644 --- a/arch/arm/plat-samsung/watchdog-reset.c +++ b/arch/arm/plat-samsung/watchdog-reset.c @@ -67,6 +67,7 @@ void samsung_wdt_reset(void) #ifdef CONFIG_OF static const struct of_device_id s3c2410_wdt_match[] = { { .compatible = "samsung,s3c2410-wdt" }, + { .compatible = "samsung,s3c6410-wdt" }, {}, }; diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c index b4d78959cadf..bc9a37b3cecd 100644 --- a/arch/arm/xen/efi.c +++ b/arch/arm/xen/efi.c @@ -31,7 +31,9 @@ void __init xen_efi_runtime_setup(void) efi.get_variable = xen_efi_get_variable; efi.get_next_variable = xen_efi_get_next_variable; efi.set_variable = xen_efi_set_variable; + efi.set_variable_nonblocking = xen_efi_set_variable; efi.query_variable_info = xen_efi_query_variable_info; + efi.query_variable_info_nonblocking = xen_efi_query_variable_info; efi.update_capsule = xen_efi_update_capsule; efi.query_capsule_caps = xen_efi_query_capsule_caps; efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e0e5a86b8d96..5b0dbfcf317b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -49,6 +49,7 @@ config ARM64 select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_PROBE diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 0c5f70e6d5cf..8c4bc5a2c61f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -149,6 +149,7 @@ archclean: $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=$(boot)/dts +ifeq ($(KBUILD_EXTMOD),) # We need to generate vdso-offsets.h before compiling certain files in kernel/. # In order to do that, we should use the archprepare target, but we can't since # asm-offsets.h is included in some files used to generate vdso-offsets.h, and @@ -158,6 +159,7 @@ archclean: prepare: vdso_prepare vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h +endif define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-nanopi-a64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-nanopi-a64.dts index 2beef9e6cb88..aa0b3844ad63 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-nanopi-a64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-nanopi-a64.dts @@ -126,9 +126,9 @@ ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts index 338e786155b1..2ef779b02757 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts @@ -120,10 +120,14 @@ /* DCDC3 is polyphased with DCDC2 */ +/* + * The board uses DDR3L DRAM chips. 1.36V is the closest to the nominal + * 1.35V that the PMIC can drive. + */ ®_dcdc5 { regulator-always-on; - regulator-min-microvolt = <1500000>; - regulator-max-microvolt = <1500000>; + regulator-min-microvolt = <1360000>; + regulator-max-microvolt = <1360000>; regulator-name = "vcc-ddr3"; }; diff --git a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi index 125f4deb52fe..b664e7af74eb 100644 --- a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi +++ b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi @@ -107,7 +107,7 @@ clock-names = "uartclk", "apb_pclk"; }; - spi0: ssp@e1020000 { + spi0: spi@e1020000 { status = "disabled"; compatible = "arm,pl022", "arm,primecell"; reg = <0 0xe1020000 0 0x1000>; @@ -117,7 +117,7 @@ clock-names = "apb_pclk"; }; - spi1: ssp@e1030000 { + spi1: spi@e1030000 { status = "disabled"; compatible = "arm,pl022", "arm,primecell"; reg = <0 0xe1030000 0 0x1000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 4b17a76959b2..c83c028e95af 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -178,7 +178,7 @@ pinctrl-names = "default"; }; -&pinctrl_aobus { +&gpio_ao { gpio-line-names = "UART TX", "UART RX", "Power Control", "Power Key In", "VCCK En", "CON1 Header Pin31", "I2S Header Pin6", "IR In", "I2S Header Pin7", @@ -186,7 +186,7 @@ "I2S Header Pin5", "HDMI CEC", "SYS LED"; }; -&pinctrl_periphs { +&gpio { gpio-line-names = /* Bank GPIOZ */ "Eth MDIO", "Eth MDC", "Eth RGMII RX Clk", "Eth RX DV", "Eth RX D0", "Eth RX D1", "Eth RX D2", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index c3c65b06ba76..4ea23df81f21 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -189,7 +189,7 @@ pinctrl-names = "default"; }; -&pinctrl_aobus { +&gpio_ao { gpio-line-names = "UART TX", "UART RX", "VCCK En", "TF 3V3/1V8 En", "USB HUB nRESET", "USB OTG Power En", "J7 Header Pin2", "IR In", "J7 Header Pin4", @@ -197,7 +197,7 @@ "HDMI CEC", "SYS LED"; }; -&pinctrl_periphs { +&gpio { gpio-line-names = /* Bank GPIOZ */ "Eth MDIO", "Eth MDC", "Eth RGMII RX Clk", "Eth RX DV", "Eth RX D0", "Eth RX D1", "Eth RX D2", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index af834cdbba79..250b5c11c0e2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -413,7 +413,7 @@ }; }; - spi_pins: spi { + spi_pins: spi-pins { mux { groups = "spi_miso", "spi_mosi", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts index edc512ad0bac..fb5db5f33e8c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts @@ -112,7 +112,7 @@ linux,rc-map-name = "rc-geekbox"; }; -&pinctrl_aobus { +&gpio_ao { gpio-line-names = "UART TX", "UART RX", "Power Key In", @@ -125,7 +125,7 @@ "SYS LED"; }; -&pinctrl_periphs { +&gpio { gpio-line-names = /* Bank GPIOZ */ "", "", "", "", "", "", "", "", "", "", "", "", "", "", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index d71cbf596d1f..e2c71753e327 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -14,7 +14,7 @@ / { compatible = "libretech,cc", "amlogic,s905x", "amlogic,meson-gxl"; - model = "Libre Technology CC"; + model = "Libre Computer Board AML-S905X-CC"; aliases { serial0 = &uart_AO; @@ -139,7 +139,7 @@ }; }; -&pinctrl_aobus { +&gpio_ao { gpio-line-names = "UART TX", "UART RX", "Blue LED", @@ -152,7 +152,7 @@ "7J1 Header Pin13"; }; -&pinctrl_periphs { +&gpio { gpio-line-names = /* Bank GPIOZ */ "", "", "", "", "", "", "", "", "", "", "", "", "", "", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index fb8d76a17bc5..3c3057944960 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -310,7 +310,7 @@ }; }; - spi_pins: spi { + spi_pins: spi-pins { mux { groups = "spi_miso", "spi_mosi", diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi index 15214d05fec1..8c20d4a0cb4e 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi @@ -42,13 +42,14 @@ pinmux: pinmux@0014029c { compatible = "pinctrl-single"; - reg = <0x0014029c 0x250>; + reg = <0x0014029c 0x26c>; #address-cells = <1>; #size-cells = <1>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0xf>; pinctrl-single,gpio-range = < - &range 0 154 MODE_GPIO + &range 0 91 MODE_GPIO + &range 95 60 MODE_GPIO >; range: gpio-range { #pinctrl-single,gpio-range-cells = <3>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index 2b76293b51c8..3d2921ef2935 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -444,8 +444,7 @@ <&pinmux 108 16 27>, <&pinmux 135 77 6>, <&pinmux 141 67 4>, - <&pinmux 145 149 6>, - <&pinmux 151 91 4>; + <&pinmux 145 149 6>; }; i2c1: i2c@000e0000 { diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 860c8fb10795..4bde7b6f2b11 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -168,14 +168,14 @@ clock-names = "apb_pclk"; status="disabled"; }; - spi0: ssp@fe800000 { + spi0: spi@fe800000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x0 0xfe800000 0x1000>; interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk_bus>; clock-names = "apb_pclk"; }; - spi1: ssp@fe900000 { + spi1: spi@fe900000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x0 0xfe900000 0x1000>; interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi index 1887af654a7d..16ced1ff1ad3 100644 --- a/arch/arm64/boot/dts/lg/lg1313.dtsi +++ b/arch/arm64/boot/dts/lg/lg1313.dtsi @@ -168,14 +168,14 @@ clock-names = "apb_pclk"; status="disabled"; }; - spi0: ssp@fe800000 { + spi0: spi@fe800000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x0 0xfe800000 0x1000>; interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk_bus>; clock-names = "apb_pclk"; }; - spi1: ssp@fe900000 { + spi1: spi@fe900000 { compatible = "arm,pl022", "arm,primecell"; reg = <0x0 0xfe900000 0x1000>; interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 8c0cf7efac65..b554cdaf5e53 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -134,7 +134,7 @@ uart0: serial@12000 { compatible = "marvell,armada-3700-uart"; - reg = <0x12000 0x400>; + reg = <0x12000 0x200>; interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi index d10d4430537a..be91873c0878 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi @@ -282,6 +282,7 @@ status = "okay"; bus-width = <8>; non-removable; + vqmmc-supply = <&vdd_1v8>; }; clocks { @@ -307,7 +308,8 @@ regulator-max-microvolt = <1320000>; enable-gpios = <&pmic 6 GPIO_ACTIVE_HIGH>; regulator-ramp-delay = <80>; - regulator-enable-ramp-delay = <1000>; + regulator-enable-ramp-delay = <2000>; + regulator-settling-time-us = <160>; }; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index d67ef4319f3b..97f31bc4fa1e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1584,7 +1584,7 @@ regulator-name = "VDD_HDMI_5V0"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; - gpio = <&exp1 12 GPIO_ACTIVE_LOW>; + gpio = <&exp1 12 GPIO_ACTIVE_HIGH>; enable-active-high; vin-supply = <&vdd_5v0_sys>; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 9bdf19f2cca7..466199766848 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -1103,7 +1103,7 @@ compatible = "nvidia,tegra210-agic"; #interrupt-cells = <3>; interrupt-controller; - reg = <0x702f9000 0x2000>, + reg = <0x702f9000 0x1000>, <0x702fa000 0x2000>; interrupts = <GIC_SPI 102 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>; clocks = <&tegra_car TEGRA210_CLK_APE>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index e720f40bbd5d..3f8f528099a8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -77,6 +77,7 @@ pinctrl-0 = <&usb30_host_drv>; regulator-name = "vcc_host_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; @@ -87,6 +88,7 @@ pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index f6b4b8f0260f..c34daae3c37c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -685,6 +685,7 @@ <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; + max-frequency = <150000000>; status = "disabled"; }; @@ -696,6 +697,7 @@ <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; + max-frequency = <150000000>; status = "disabled"; }; @@ -707,6 +709,7 @@ <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; + max-frequency = <150000000>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index ce592a4c0c4c..075659847791 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -113,6 +113,19 @@ vin-supply = <&vcc_1v8>; }; + vcc3v0_sd: vcc3v0-sd { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio0 RK_PA1 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc0_pwr_h>; + regulator-always-on; + regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3000000>; + regulator-name = "vcc3v0_sd"; + vin-supply = <&vcc3v3_sys>; + }; + vcc3v3_sys: vcc3v3-sys { compatible = "regulator-fixed"; regulator-name = "vcc3v3_sys"; @@ -136,7 +149,7 @@ vcc5v0_host: vcc5v0-host-regulator { compatible = "regulator-fixed"; enable-active-high; - gpio = <&gpio1 RK_PD1 GPIO_ACTIVE_HIGH>; + gpio = <&gpio4 RK_PD1 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_host_en>; regulator-name = "vcc5v0_host"; @@ -315,7 +328,7 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; regulator-state-mem { regulator-on-in-suspend; regulator-suspend-microvolt = <3000000>; @@ -490,6 +503,13 @@ }; }; + sd { + sdmmc0_pwr_h: sdmmc0-pwr-h { + rockchip,pins = + <RK_GPIO0 RK_PA1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + usb2 { vcc5v0_host_en: vcc5v0-host-en { rockchip,pins = @@ -537,6 +557,7 @@ }; &sdmmc { + broken-cd; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; @@ -545,6 +566,7 @@ max-frequency = <150000000>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>; + vmmc-supply = <&vcc3v0_sd>; vqmmc-supply = <&vcc_sdio>; status = "okay"; }; diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index efbeb3e0dcfb..70568e6db77b 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -54,7 +54,7 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct sha1_ce_state *sctx = shash_desc_ctx(desc); - bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE); + bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len; if (!may_use_simd()) return crypto_sha1_finup(desc, data, len, out); diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index fd1ff2b13dfa..af8472aded42 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -59,7 +59,7 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct sha256_ce_state *sctx = shash_desc_ctx(desc); - bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE); + bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len; if (!may_use_simd()) { if (len) diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 0f2e1ab5e166..9b2e2e2e728a 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -73,7 +73,7 @@ __XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE #define __XCHG_GEN(sfx) \ -static inline unsigned long __xchg##sfx(unsigned long x, \ +static __always_inline unsigned long __xchg##sfx(unsigned long x, \ volatile void *ptr, \ int size) \ { \ @@ -115,7 +115,7 @@ __XCHG_GEN(_mb) #define xchg(...) __xchg_wrapper( _mb, __VA_ARGS__) #define __CMPXCHG_GEN(sfx) \ -static inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ +static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ unsigned long old, \ unsigned long new, \ int size) \ @@ -248,7 +248,7 @@ __CMPWAIT_CASE( , , 8); #undef __CMPWAIT_CASE #define __CMPWAIT_GEN(sfx) \ -static inline void __cmpwait##sfx(volatile void *ptr, \ +static __always_inline void __cmpwait##sfx(volatile void *ptr, \ unsigned long val, \ int size) \ { \ diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index a3c7f271ad4c..9ed290a9811c 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -234,6 +234,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) } #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) +#define COMPAT_MINSIGSTKSZ 2048 static inline void __user *arch_compat_alloc_user_space(long len) { diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 7d6425d426ac..2f8bd0388905 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -42,9 +42,9 @@ #define ARM64_HAS_DCPOP 21 #define ARM64_UNMAP_KERNEL_AT_EL0 23 #define ARM64_HARDEN_BRANCH_PREDICTOR 24 -#define ARM64_HARDEN_BP_POST_GUEST_EXIT 25 -#define ARM64_SSBD 26 -#define ARM64_MISMATCHED_CACHE_TYPE 27 +#define ARM64_SSBD 25 +#define ARM64_MISMATCHED_CACHE_TYPE 26 +#define ARM64_SSBS 27 #define ARM64_NCAPS 28 diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c5bc80a03515..166f81b7afee 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -10,6 +10,7 @@ #define __ASM_CPUFEATURE_H #include <asm/cpucaps.h> +#include <asm/cputype.h> #include <asm/hwcap.h> #include <asm/sysreg.h> @@ -44,9 +45,10 @@ */ enum ftr_type { - FTR_EXACT, /* Use a predefined safe value */ - FTR_LOWER_SAFE, /* Smaller value is safe */ - FTR_HIGHER_SAFE,/* Bigger value is safe */ + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE, /* Bigger value is safe */ + FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ @@ -84,24 +86,227 @@ struct arm64_ftr_reg { extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; -/* scope of capability check */ -enum { - SCOPE_SYSTEM, - SCOPE_LOCAL_CPU, -}; +/* + * CPU capabilities: + * + * We use arm64_cpu_capabilities to represent system features, errata work + * arounds (both used internally by kernel and tracked in cpu_hwcaps) and + * ELF HWCAPs (which are exposed to user). + * + * To support systems with heterogeneous CPUs, we need to make sure that we + * detect the capabilities correctly on the system and take appropriate + * measures to ensure there are no incompatibilities. + * + * This comment tries to explain how we treat the capabilities. + * Each capability has the following list of attributes : + * + * 1) Scope of Detection : The system detects a given capability by + * performing some checks at runtime. This could be, e.g, checking the + * value of a field in CPU ID feature register or checking the cpu + * model. The capability provides a call back ( @matches() ) to + * perform the check. Scope defines how the checks should be performed. + * There are three cases: + * + * a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one + * matches. This implies, we have to run the check on all the + * booting CPUs, until the system decides that state of the + * capability is finalised. (See section 2 below) + * Or + * b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs + * matches. This implies, we run the check only once, when the + * system decides to finalise the state of the capability. If the + * capability relies on a field in one of the CPU ID feature + * registers, we use the sanitised value of the register from the + * CPU feature infrastructure to make the decision. + * Or + * c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the + * feature. This category is for features that are "finalised" + * (or used) by the kernel very early even before the SMP cpus + * are brought up. + * + * The process of detection is usually denoted by "update" capability + * state in the code. + * + * 2) Finalise the state : The kernel should finalise the state of a + * capability at some point during its execution and take necessary + * actions if any. Usually, this is done, after all the boot-time + * enabled CPUs are brought up by the kernel, so that it can make + * better decision based on the available set of CPUs. However, there + * are some special cases, where the action is taken during the early + * boot by the primary boot CPU. (e.g, running the kernel at EL2 with + * Virtualisation Host Extensions). The kernel usually disallows any + * changes to the state of a capability once it finalises the capability + * and takes any action, as it may be impossible to execute the actions + * safely. A CPU brought up after a capability is "finalised" is + * referred to as "Late CPU" w.r.t the capability. e.g, all secondary + * CPUs are treated "late CPUs" for capabilities determined by the boot + * CPU. + * + * At the moment there are two passes of finalising the capabilities. + * a) Boot CPU scope capabilities - Finalised by primary boot CPU via + * setup_boot_cpu_capabilities(). + * b) Everything except (a) - Run via setup_system_capabilities(). + * + * 3) Verification: When a CPU is brought online (e.g, by user or by the + * kernel), the kernel should make sure that it is safe to use the CPU, + * by verifying that the CPU is compliant with the state of the + * capabilities finalised already. This happens via : + * + * secondary_start_kernel()-> check_local_cpu_capabilities() + * + * As explained in (2) above, capabilities could be finalised at + * different points in the execution. Each newly booted CPU is verified + * against the capabilities that have been finalised by the time it + * boots. + * + * a) SCOPE_BOOT_CPU : All CPUs are verified against the capability + * except for the primary boot CPU. + * + * b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the + * user after the kernel boot are verified against the capability. + * + * If there is a conflict, the kernel takes an action, based on the + * severity (e.g, a CPU could be prevented from booting or cause a + * kernel panic). The CPU is allowed to "affect" the state of the + * capability, if it has not been finalised already. See section 5 + * for more details on conflicts. + * + * 4) Action: As mentioned in (2), the kernel can take an action for each + * detected capability, on all CPUs on the system. Appropriate actions + * include, turning on an architectural feature, modifying the control + * registers (e.g, SCTLR, TCR etc.) or patching the kernel via + * alternatives. The kernel patching is batched and performed at later + * point. The actions are always initiated only after the capability + * is finalised. This is usally denoted by "enabling" the capability. + * The actions are initiated as follows : + * a) Action is triggered on all online CPUs, after the capability is + * finalised, invoked within the stop_machine() context from + * enable_cpu_capabilitie(). + * + * b) Any late CPU, brought up after (1), the action is triggered via: + * + * check_local_cpu_capabilities() -> verify_local_cpu_capabilities() + * + * 5) Conflicts: Based on the state of the capability on a late CPU vs. + * the system state, we could have the following combinations : + * + * x-----------------------------x + * | Type | System | Late CPU | + * |-----------------------------| + * | a | y | n | + * |-----------------------------| + * | b | n | y | + * x-----------------------------x + * + * Two separate flag bits are defined to indicate whether each kind of + * conflict can be allowed: + * ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed + * ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed + * + * Case (a) is not permitted for a capability that the system requires + * all CPUs to have in order for the capability to be enabled. This is + * typical for capabilities that represent enhanced functionality. + * + * Case (b) is not permitted for a capability that must be enabled + * during boot if any CPU in the system requires it in order to run + * safely. This is typical for erratum work arounds that cannot be + * enabled after the corresponding capability is finalised. + * + * In some non-typical cases either both (a) and (b), or neither, + * should be permitted. This can be described by including neither + * or both flags in the capability's type field. + */ + + +/* + * Decide how the capability is detected. + * On any local CPU vs System wide vs the primary boot CPU + */ +#define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0)) +#define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1)) +/* + * The capabilitiy is detected on the Boot CPU and is used by kernel + * during early boot. i.e, the capability should be "detected" and + * "enabled" as early as possibly on all booting CPUs. + */ +#define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2)) +#define ARM64_CPUCAP_SCOPE_MASK \ + (ARM64_CPUCAP_SCOPE_SYSTEM | \ + ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_SCOPE_BOOT_CPU) + +#define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM +#define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU +#define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU +#define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK + +/* + * Is it permitted for a late CPU to have this capability when system + * hasn't already enabled it ? + */ +#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) +/* Is it safe for a late CPU to miss this capability when system has it */ +#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) + +/* + * CPU errata workarounds that need to be enabled at boot time if one or + * more CPUs in the system requires it. When one of these capabilities + * has been enabled, it is safe to allow any CPU to boot that doesn't + * require the workaround. However, it is not safe if a "late" CPU + * requires a workaround and the system hasn't enabled it already. + */ +#define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) +/* + * CPU feature detected at boot time based on system-wide value of a + * feature. It is safe for a late CPU to have this feature even though + * the system hasn't enabled it, although the featuer will not be used + * by Linux in this case. If the system has enabled this feature already, + * then every late CPU must have it. + */ +#define ARM64_CPUCAP_SYSTEM_FEATURE \ + (ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) +/* + * CPU feature detected at boot time based on feature of one or more CPUs. + * All possible conflicts for a late CPU are ignored. + */ +#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \ + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) + +/* + * CPU feature detected at boot time, on one or more CPUs. A late CPU + * is not allowed to have the capability when the system doesn't have it. + * It is Ok for a late CPU to miss the feature. + */ +#define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) + +/* + * CPU feature used early in the boot based on the boot CPU. All secondary + * CPUs must match the state of the capability as detected by the boot CPU. + */ +#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU struct arm64_cpu_capabilities { const char *desc; u16 capability; - int def_scope; /* default scope */ + u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); - int (*enable)(void *); /* Called on all active CPUs */ + /* + * Take the appropriate actions to enable this capability for this CPU. + * For each successfully booted CPU, this method is called for each + * globally detected capability. + */ + void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { struct { /* To be used for erratum handling only */ - u32 midr_model; - u32 midr_range_min, midr_range_max; + struct midr_range midr_range; }; + const struct midr_range *midr_range_list; struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; @@ -113,6 +318,23 @@ struct arm64_cpu_capabilities { }; }; +static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) +{ + return cap->type & ARM64_CPUCAP_SCOPE_MASK; +} + +static inline bool +cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); +} + +static inline bool +cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); +} + extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; @@ -224,15 +446,8 @@ static inline bool id_aa64pfr0_32bit_el0(u64 pfr0) } void __init setup_cpu_features(void); - -void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, - const char *info); -void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps); void check_local_cpu_capabilities(void); -void update_cpu_errata_workarounds(void); -void __init enable_errata_workarounds(void); -void verify_local_cpu_errata_workarounds(void); u64 read_sanitised_ftr_reg(u32 id); @@ -278,11 +493,7 @@ static inline int arm64_get_ssbd_state(void) #endif } -#ifdef CONFIG_ARM64_SSBD void arm64_set_ssbd_mitigation(bool state); -#else -static inline void arm64_set_ssbd_mitigation(bool state) {} -#endif #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 04569aa267fd..b23456035eac 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,8 @@ #define ARM_CPU_PART_CORTEX_A53 0xD03 #define ARM_CPU_PART_CORTEX_A73 0xD09 #define ARM_CPU_PART_CORTEX_A75 0xD0A +#define ARM_CPU_PART_CORTEX_A35 0xD04 +#define ARM_CPU_PART_CORTEX_A55 0xD05 #define APM_CPU_PART_POTENZA 0x000 @@ -108,6 +110,8 @@ #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) #define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75) +#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) @@ -126,6 +130,45 @@ #define read_cpuid(reg) read_sysreg_s(SYS_ ## reg) /* + * Represent a range of MIDR values for a given CPU model and a + * range of variant/revision values. + * + * @model - CPU model as defined by MIDR_CPU_MODEL + * @rv_min - Minimum value for the revision/variant as defined by + * MIDR_CPU_VAR_REV + * @rv_max - Maximum value for the variant/revision for the range. + */ +struct midr_range { + u32 model; + u32 rv_min; + u32 rv_max; +}; + +#define MIDR_RANGE(m, v_min, r_min, v_max, r_max) \ + { \ + .model = m, \ + .rv_min = MIDR_CPU_VAR_REV(v_min, r_min), \ + .rv_max = MIDR_CPU_VAR_REV(v_max, r_max), \ + } + +#define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf) + +static inline bool is_midr_in_range(u32 midr, struct midr_range const *range) +{ + return MIDR_IS_CPU_MODEL_RANGE(midr, range->model, + range->rv_min, range->rv_max); +} + +static inline bool +is_midr_in_range_list(u32 midr, struct midr_range const *ranges) +{ + while (ranges->model) + if (is_midr_in_range(midr, ranges++)) + return true; + return false; +} + +/* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID * rather than directly reading processor_id or read_cpuid() directly. diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 8389050328bb..558542086069 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -89,7 +89,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) #define alloc_screen_info(x...) &screen_info -#define free_screen_info(x...) + +static inline void free_screen_info(efi_system_table_t *sys_table_arg, + struct screen_info *si) +{ +} /* redeclare as 'hidden' so the compiler will generate relative references */ extern struct screen_info screen_info __attribute__((__visibility__("hidden"))); diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index c7e30a6ed56e..232917e9c1d9 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -134,7 +134,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, : "memory"); uaccess_disable(); - *uval = val; + if (!ret) + *uval = val; + return ret; } diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 4214c38d016b..e3193fd39d8d 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -271,6 +271,7 @@ __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) +__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) @@ -383,6 +384,13 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 1a6d02350fc6..c59e81b65132 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -70,8 +70,6 @@ extern u32 __kvm_get_mdcr_el2(void); extern u32 __init_stage2_translation(void); -extern void __qcom_hyp_sanitize_btac_predictors(void); - /* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */ #define __hyp_this_cpu_ptr(sym) \ ({ \ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b01ad3489bd8..f982c9d1d10b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -356,6 +356,8 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); void __kvm_set_tpidr_el2(u64 tpidr_el2); DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state); +void __kvm_enable_ssbs(void); + static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, unsigned long hyp_stack_ptr, unsigned long vector_ptr) @@ -380,6 +382,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, - (u64)kvm_ksym_ref(kvm_host_cpu_state); kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2); + + /* + * Disabling SSBD on a non-VHE system requires us to enable SSBS + * at EL2. + */ + if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) && + arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { + kvm_call_hyp(__kvm_enable_ssbs); + } } static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 2db84df5eb42..20e45733afa4 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -43,11 +43,11 @@ #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -71,8 +71,9 @@ #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ee77556b0124..aa3b8dd8fc35 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -258,23 +258,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } -#define __HAVE_ARCH_PTE_SAME -static inline int pte_same(pte_t pte_a, pte_t pte_b) -{ - pteval_t lhs, rhs; - - lhs = pte_val(pte_a); - rhs = pte_val(pte_b); - - if (pte_present(pte_a)) - lhs &= ~PTE_RDONLY; - - if (pte_present(pte_b)) - rhs &= ~PTE_RDONLY; - - return (lhs == rhs); -} - /* * Huge pte definitions. */ @@ -394,8 +377,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_SECT) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 -#define pud_sect(pud) (0) -#define pud_table(pud) (1) +static inline bool pud_sect(pud_t pud) { return false; } +static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 91bb97d8bdbf..9eb95ab19924 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -37,6 +37,7 @@ #include <linux/string.h> #include <asm/alternative.h> +#include <asm/cpufeature.h> #include <asm/fpsimd.h> #include <asm/hw_breakpoint.h> #include <asm/lse.h> @@ -147,11 +148,25 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) regs->pc = pc; } +static inline void set_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_SSBS_BIT; +} + +static inline void set_compat_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_AA32_SSBS_BIT; +} + static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); regs->pstate = PSR_MODE_EL0t; + + if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) + set_ssbs_bit(regs); + regs->sp = sp; } @@ -168,6 +183,9 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, regs->pstate |= COMPAT_PSR_E_BIT; #endif + if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) + set_compat_ssbs_bit(regs); + regs->compat_sp = sp; } #endif @@ -222,8 +240,8 @@ static inline void spin_lock_prefetch(const void *ptr) #endif -int cpu_enable_pan(void *__unused); -int cpu_enable_cache_maint_trap(void *__unused); +void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused); +void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 6069d66e0bc2..b466d763a90d 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -35,7 +35,38 @@ #define COMPAT_PTRACE_GETHBPREGS 29 #define COMPAT_PTRACE_SETHBPREGS 30 -/* AArch32 CPSR bits */ +/* SPSR_ELx bits for exceptions taken from AArch32 */ +#define PSR_AA32_MODE_MASK 0x0000001f +#define PSR_AA32_MODE_USR 0x00000010 +#define PSR_AA32_MODE_FIQ 0x00000011 +#define PSR_AA32_MODE_IRQ 0x00000012 +#define PSR_AA32_MODE_SVC 0x00000013 +#define PSR_AA32_MODE_ABT 0x00000017 +#define PSR_AA32_MODE_HYP 0x0000001a +#define PSR_AA32_MODE_UND 0x0000001b +#define PSR_AA32_MODE_SYS 0x0000001f +#define PSR_AA32_T_BIT 0x00000020 +#define PSR_AA32_F_BIT 0x00000040 +#define PSR_AA32_I_BIT 0x00000080 +#define PSR_AA32_A_BIT 0x00000100 +#define PSR_AA32_E_BIT 0x00000200 +#define PSR_AA32_SSBS_BIT 0x00800000 +#define PSR_AA32_DIT_BIT 0x01000000 +#define PSR_AA32_Q_BIT 0x08000000 +#define PSR_AA32_V_BIT 0x10000000 +#define PSR_AA32_C_BIT 0x20000000 +#define PSR_AA32_Z_BIT 0x40000000 +#define PSR_AA32_N_BIT 0x80000000 +#define PSR_AA32_IT_MASK 0x0600fc00 /* If-Then execution state mask */ +#define PSR_AA32_GE_MASK 0x000f0000 + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define PSR_AA32_ENDSTATE PSR_AA32_E_BIT +#else +#define PSR_AA32_ENDSTATE 0 +#endif + +/* AArch32 CPSR bits, as seen in AArch32 */ #define COMPAT_PSR_MODE_MASK 0x0000001f #define COMPAT_PSR_MODE_USR 0x00000010 #define COMPAT_PSR_MODE_FIQ 0x00000011 @@ -50,6 +81,7 @@ #define COMPAT_PSR_I_BIT 0x00000080 #define COMPAT_PSR_A_BIT 0x00000100 #define COMPAT_PSR_E_BIT 0x00000200 +#define COMPAT_PSR_DIT_BIT 0x00200000 #define COMPAT_PSR_J_BIT 0x01000000 #define COMPAT_PSR_Q_BIT 0x08000000 #define COMPAT_PSR_V_BIT 0x10000000 @@ -111,6 +143,30 @@ #define compat_sp_fiq regs[29] #define compat_lr_fiq regs[30] +static inline unsigned long compat_psr_to_pstate(const unsigned long psr) +{ + unsigned long pstate; + + pstate = psr & ~COMPAT_PSR_DIT_BIT; + + if (psr & COMPAT_PSR_DIT_BIT) + pstate |= PSR_AA32_DIT_BIT; + + return pstate; +} + +static inline unsigned long pstate_to_compat_psr(const unsigned long pstate) +{ + unsigned long psr; + + psr = pstate & ~PSR_AA32_DIT_BIT; + + if (pstate & PSR_AA32_DIT_BIT) + psr |= COMPAT_PSR_DIT_BIT; + + return psr; +} + /* * This struct defines the way the registers are stored on the stack during an * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index dd95d33a5bd5..03a6c256b7ec 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -16,6 +16,7 @@ #ifndef __ASM_STRING_H #define __ASM_STRING_H +#ifndef CONFIG_KASAN #define __HAVE_ARCH_STRRCHR extern char *strrchr(const char *, int c); @@ -34,6 +35,13 @@ extern __kernel_size_t strlen(const char *); #define __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *, __kernel_size_t); +#define __HAVE_ARCH_MEMCMP +extern int memcmp(const void *, const void *, size_t); + +#define __HAVE_ARCH_MEMCHR +extern void *memchr(const void *, int, __kernel_size_t); +#endif + #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *, const void *, __kernel_size_t); extern void *__memcpy(void *, const void *, __kernel_size_t); @@ -42,16 +50,10 @@ extern void *__memcpy(void *, const void *, __kernel_size_t); extern void *memmove(void *, const void *, __kernel_size_t); extern void *__memmove(void *, const void *, __kernel_size_t); -#define __HAVE_ARCH_MEMCHR -extern void *memchr(const void *, int, __kernel_size_t); - #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); extern void *__memset(void *, int, __kernel_size_t); -#define __HAVE_ARCH_MEMCMP -extern int memcmp(const void *, const void *, size_t); - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE void memcpy_flushcache(void *dst, const void *src, size_t cnt); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index ede80d47d0ef..50a89bcf9072 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -20,6 +20,7 @@ #ifndef __ASM_SYSREG_H #define __ASM_SYSREG_H +#include <asm/compiler.h> #include <linux/stringify.h> /* @@ -85,11 +86,14 @@ #define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4) #define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3) +#define REG_PSTATE_SSBS_IMM sys_reg(0, 3, 4, 0, 1) #define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM | \ (!!x)<<8 | 0x1f) #define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM | \ (!!x)<<8 | 0x1f) +#define SET_PSTATE_SSBS(x) __emit_inst(0xd5000000 | REG_PSTATE_SSBS_IMM | \ + (!!x)<<8 | 0x1f) #define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2) #define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2) @@ -296,28 +300,94 @@ #define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7) /* Common SCTLR_ELx flags. */ +#define SCTLR_ELx_DSSBS (1UL << 44) #define SCTLR_ELx_EE (1 << 25) +#define SCTLR_ELx_WXN (1 << 19) #define SCTLR_ELx_I (1 << 12) #define SCTLR_ELx_SA (1 << 3) #define SCTLR_ELx_C (1 << 2) #define SCTLR_ELx_A (1 << 1) #define SCTLR_ELx_M 1 +#define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ + SCTLR_ELx_SA | SCTLR_ELx_I) + +/* SCTLR_EL2 specific flags. */ #define SCTLR_EL2_RES1 ((1 << 4) | (1 << 5) | (1 << 11) | (1 << 16) | \ (1 << 18) | (1 << 22) | (1 << 23) | (1 << 28) | \ (1 << 29)) +#define SCTLR_EL2_RES0 ((1 << 6) | (1 << 7) | (1 << 8) | (1 << 9) | \ + (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \ + (1 << 17) | (1 << 20) | (1 << 21) | (1 << 24) | \ + (1 << 26) | (1 << 27) | (1 << 30) | (1 << 31) | \ + (0xffffefffUL << 32)) + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define ENDIAN_SET_EL2 SCTLR_ELx_EE +#define ENDIAN_CLEAR_EL2 0 +#else +#define ENDIAN_SET_EL2 0 +#define ENDIAN_CLEAR_EL2 SCTLR_ELx_EE +#endif -#define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ - SCTLR_ELx_SA | SCTLR_ELx_I) +/* SCTLR_EL2 value used for the hyp-stub */ +#define SCTLR_EL2_SET (ENDIAN_SET_EL2 | SCTLR_EL2_RES1) +#define SCTLR_EL2_CLEAR (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ + SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \ + SCTLR_ELx_DSSBS | ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0) + +#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff +#error "Inconsistent SCTLR_EL2 set/clear bits" +#endif /* SCTLR_EL1 specific flags. */ #define SCTLR_EL1_UCI (1 << 26) +#define SCTLR_EL1_E0E (1 << 24) #define SCTLR_EL1_SPAN (1 << 23) +#define SCTLR_EL1_NTWE (1 << 18) +#define SCTLR_EL1_NTWI (1 << 16) #define SCTLR_EL1_UCT (1 << 15) +#define SCTLR_EL1_DZE (1 << 14) +#define SCTLR_EL1_UMA (1 << 9) #define SCTLR_EL1_SED (1 << 8) +#define SCTLR_EL1_ITD (1 << 7) #define SCTLR_EL1_CP15BEN (1 << 5) +#define SCTLR_EL1_SA0 (1 << 4) + +#define SCTLR_EL1_RES1 ((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \ + (1 << 29)) +#define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \ + (1 << 21) | (1 << 27) | (1 << 30) | (1 << 31) | \ + (0xffffefffUL << 32)) + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) +#define ENDIAN_CLEAR_EL1 0 +#else +#define ENDIAN_SET_EL1 0 +#define ENDIAN_CLEAR_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) +#endif + +#define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\ + SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I |\ + SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_NTWI |\ + SCTLR_EL1_NTWE | SCTLR_EL1_SPAN | ENDIAN_SET_EL1 |\ + SCTLR_EL1_UCI | SCTLR_EL1_RES1) +#define SCTLR_EL1_CLEAR (SCTLR_ELx_A | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD |\ + SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\ + SCTLR_ELx_DSSBS | SCTLR_EL1_RES0) + +#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff +#error "Inconsistent SCTLR_EL1 set/clear bits" +#endif /* id_aa64isar0 */ +#define ID_AA64ISAR0_TS_SHIFT 52 +#define ID_AA64ISAR0_FHM_SHIFT 48 +#define ID_AA64ISAR0_DP_SHIFT 44 +#define ID_AA64ISAR0_SM4_SHIFT 40 +#define ID_AA64ISAR0_SM3_SHIFT 36 +#define ID_AA64ISAR0_SHA3_SHIFT 32 #define ID_AA64ISAR0_RDM_SHIFT 28 #define ID_AA64ISAR0_ATOMICS_SHIFT 20 #define ID_AA64ISAR0_CRC32_SHIFT 16 @@ -334,6 +404,7 @@ /* id_aa64pfr0 */ #define ID_AA64PFR0_CSV3_SHIFT 60 #define ID_AA64PFR0_CSV2_SHIFT 56 +#define ID_AA64PFR0_DIT_SHIFT 48 #define ID_AA64PFR0_GIC_SHIFT 24 #define ID_AA64PFR0_ASIMD_SHIFT 20 #define ID_AA64PFR0_FP_SHIFT 16 @@ -350,6 +421,13 @@ #define ID_AA64PFR0_EL0_64BIT_ONLY 0x1 #define ID_AA64PFR0_EL0_32BIT_64BIT 0x2 +/* id_aa64pfr1 */ +#define ID_AA64PFR1_SSBS_SHIFT 4 + +#define ID_AA64PFR1_SSBS_PSTATE_NI 0 +#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 +#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 + /* id_aa64mmfr0 */ #define ID_AA64MMFR0_TGRAN4_SHIFT 28 #define ID_AA64MMFR0_TGRAN64_SHIFT 24 @@ -379,6 +457,7 @@ #define ID_AA64MMFR1_VMIDBITS_16 2 /* id_aa64mmfr2 */ +#define ID_AA64MMFR2_AT_SHIFT 32 #define ID_AA64MMFR2_LVA_SHIFT 16 #define ID_AA64MMFR2_IESB_SHIFT 12 #define ID_AA64MMFR2_LSM_SHIFT 8 @@ -463,6 +542,7 @@ #else +#include <linux/build_bug.h> #include <linux/types.h> asm( @@ -515,6 +595,17 @@ asm( asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \ } while (0) +/* + * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the + * set mask are set. Other bits are left as-is. + */ +#define sysreg_clear_set(sysreg, clear, set) do { \ + u64 __scs_val = read_sysreg(sysreg); \ + u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \ + if (__scs_new != __scs_val) \ + write_sysreg(__scs_new, sysreg); \ +} while (0) + static inline void config_sctlr_el1(u32 clear, u32 set) { u32 val; diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index c5f89442785c..9d1e24e030b3 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -102,12 +102,6 @@ static inline bool has_vhe(void) return false; } -#ifdef CONFIG_ARM64_VHE -extern void verify_cpu_run_el(void); -#else -static inline void verify_cpu_run_el(void) {} -#endif - #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_H */ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index b3fdeee739ea..2bcd6e4f3474 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -37,5 +37,17 @@ #define HWCAP_FCMA (1 << 14) #define HWCAP_LRCPC (1 << 15) #define HWCAP_DCPOP (1 << 16) +#define HWCAP_SHA3 (1 << 17) +#define HWCAP_SM3 (1 << 18) +#define HWCAP_SM4 (1 << 19) +#define HWCAP_ASIMDDP (1 << 20) +#define HWCAP_SHA512 (1 << 21) +#define HWCAP_SVE (1 << 22) +#define HWCAP_ASIMDFHM (1 << 23) +#define HWCAP_DIT (1 << 24) +#define HWCAP_USCAT (1 << 25) +#define HWCAP_ILRCPC (1 << 26) +#define HWCAP_FLAGM (1 << 27) +#define HWCAP_SSBS (1 << 28) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 67d4c33974e8..eea58f8ec355 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -45,6 +45,7 @@ #define PSR_I_BIT 0x00000080 #define PSR_A_BIT 0x00000100 #define PSR_D_BIT 0x00000200 +#define PSR_SSBS_BIT 0x00001000 #define PSR_PAN_BIT 0x00400000 #define PSR_UAO_BIT 0x00800000 #define PSR_Q_BIT 0x08000000 diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index b3162715ed78..285f0b4851fc 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -157,10 +157,14 @@ static int __init acpi_fadt_sanity_check(void) */ if (table->revision < 5 || (table->revision == 5 && fadt->minor_revision < 1)) { - pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n", + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n", table->revision, fadt->minor_revision); - ret = -EINVAL; - goto out; + + if (!fadt->arm_boot_flags) { + ret = -EINVAL; + goto out; + } + pr_err("FADT has ARM boot flags set, assuming 5.1\n"); } if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 66be504edb6c..9eedf839e739 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -44,20 +44,23 @@ EXPORT_SYMBOL(__arch_copy_in_user); EXPORT_SYMBOL(memstart_addr); /* string / mem functions */ +#ifndef CONFIG_KASAN EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strcmp); EXPORT_SYMBOL(strncmp); EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strnlen); +EXPORT_SYMBOL(memcmp); +EXPORT_SYMBOL(memchr); +#endif + EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memset); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(__memmove); -EXPORT_SYMBOL(memchr); -EXPORT_SYMBOL(memcmp); /* atomic bitops */ EXPORT_SYMBOL(set_bit); diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S index e5de33513b5d..4cae34e5a24e 100644 --- a/arch/arm64/kernel/bpi.S +++ b/arch/arm64/kernel/bpi.S @@ -55,29 +55,14 @@ ENTRY(__bp_harden_hyp_vecs_start) .endr ENTRY(__bp_harden_hyp_vecs_end) -ENTRY(__qcom_hyp_sanitize_link_stack_start) - stp x29, x30, [sp, #-16]! - .rept 16 - bl . + 4 - .endr - ldp x29, x30, [sp], #16 -ENTRY(__qcom_hyp_sanitize_link_stack_end) -.macro smccc_workaround_1 inst +ENTRY(__smccc_workaround_1_smc_start) sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] stp x0, x1, [sp, #(8 * 2)] mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 - \inst #0 + smc #0 ldp x2, x3, [sp, #(8 * 0)] ldp x0, x1, [sp, #(8 * 2)] add sp, sp, #(8 * 4) -.endm - -ENTRY(__smccc_workaround_1_smc_start) - smccc_workaround_1 smc ENTRY(__smccc_workaround_1_smc_end) - -ENTRY(__smccc_workaround_1_hvc_start) - smccc_workaround_1 hvc -ENTRY(__smccc_workaround_1_hvc_end) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 3d6d7fae45de..7d15f4cb6393 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -19,6 +19,7 @@ #include <linux/arm-smccc.h> #include <linux/psci.h> #include <linux/types.h> +#include <linux/cpu.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> @@ -26,10 +27,18 @@ static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) { + u32 midr = read_cpuid_id(); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &entry->midr_range); +} + +static bool __maybe_unused +is_affected_midr_range_list(const struct arm64_cpu_capabilities *entry, + int scope) +{ WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); - return MIDR_IS_CPU_MODEL_RANGE(read_cpuid_id(), entry->midr_model, - entry->midr_range_min, - entry->midr_range_max); + return is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list); } static bool __maybe_unused @@ -43,7 +52,7 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope) model &= MIDR_IMPLEMENTOR_MASK | (0xf00 << MIDR_PARTNUM_SHIFT) | MIDR_ARCHITECTURE_MASK; - return model == entry->midr_model; + return model == entry->midr_range.model; } static bool @@ -61,26 +70,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, (arm64_ftr_reg_ctrel0.sys_val & mask); } -static int cpu_enable_trap_ctr_access(void *__unused) +static void +cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) { /* Clear SCTLR_EL1.UCT */ config_sctlr_el1(SCTLR_EL1_UCT, 0); - return 0; } -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR #include <asm/mmu_context.h> #include <asm/cacheflush.h> DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); #ifdef CONFIG_KVM -extern char __qcom_hyp_sanitize_link_stack_start[]; -extern char __qcom_hyp_sanitize_link_stack_end[]; extern char __smccc_workaround_1_smc_start[]; extern char __smccc_workaround_1_smc_end[]; -extern char __smccc_workaround_1_hvc_start[]; -extern char __smccc_workaround_1_hvc_end[]; static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, const char *hyp_vecs_end) @@ -94,9 +98,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K); } -static void __install_bp_hardening_cb(bp_hardening_cb_t fn, - const char *hyp_vecs_start, - const char *hyp_vecs_end) +static void install_bp_hardening_cb(bp_hardening_cb_t fn, + const char *hyp_vecs_start, + const char *hyp_vecs_end) { static int last_slot = -1; static DEFINE_SPINLOCK(bp_lock); @@ -123,14 +127,10 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, spin_unlock(&bp_lock); } #else -#define __qcom_hyp_sanitize_link_stack_start NULL -#define __qcom_hyp_sanitize_link_stack_end NULL #define __smccc_workaround_1_smc_start NULL #define __smccc_workaround_1_smc_end NULL -#define __smccc_workaround_1_hvc_start NULL -#define __smccc_workaround_1_hvc_end NULL -static void __install_bp_hardening_cb(bp_hardening_cb_t fn, +static void install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, const char *hyp_vecs_end) { @@ -138,23 +138,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM */ -static void install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry, - bp_hardening_cb_t fn, - const char *hyp_vecs_start, - const char *hyp_vecs_end) -{ - u64 pfr0; - - if (!entry->matches(entry, SCOPE_LOCAL_CPU)) - return; - - pfr0 = read_cpuid(ID_AA64PFR0_EL1); - if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT)) - return; - - __install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end); -} - #include <uapi/linux/psci.h> #include <linux/arm-smccc.h> #include <linux/psci.h> @@ -169,77 +152,95 @@ static void call_hvc_arch_workaround_1(void) arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } -static int enable_smccc_arch_workaround_1(void *data) +static void qcom_link_stack_sanitization(void) +{ + u64 tmp; + + asm volatile("mov %0, x30 \n" + ".rept 16 \n" + "bl . + 4 \n" + ".endr \n" + "mov x30, %0 \n" + : "=&r" (tmp)); +} + +static bool __nospectre_v2; +static int __init parse_nospectre_v2(char *str) +{ + __nospectre_v2 = true; + return 0; +} +early_param("nospectre_v2", parse_nospectre_v2); + +/* + * -1: No workaround + * 0: No workaround required + * 1: Workaround installed + */ +static int detect_harden_bp_fw(void) { - const struct arm64_cpu_capabilities *entry = data; bp_hardening_cb_t cb; void *smccc_start, *smccc_end; struct arm_smccc_res res; - - if (!entry->matches(entry, SCOPE_LOCAL_CPU)) - return 0; + u32 midr = read_cpuid_id(); if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - return 0; + return -1; switch (psci_ops.conduit) { case PSCI_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 < 0) + switch ((int)res.a0) { + case 1: + /* Firmware says we're just fine */ return 0; - cb = call_hvc_arch_workaround_1; - smccc_start = __smccc_workaround_1_hvc_start; - smccc_end = __smccc_workaround_1_hvc_end; + case 0: + cb = call_hvc_arch_workaround_1; + /* This is a guest, no need to patch KVM vectors */ + smccc_start = NULL; + smccc_end = NULL; + break; + default: + return -1; + } break; case PSCI_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 < 0) + switch ((int)res.a0) { + case 1: + /* Firmware says we're just fine */ return 0; - cb = call_smc_arch_workaround_1; - smccc_start = __smccc_workaround_1_smc_start; - smccc_end = __smccc_workaround_1_smc_end; + case 0: + cb = call_smc_arch_workaround_1; + smccc_start = __smccc_workaround_1_smc_start; + smccc_end = __smccc_workaround_1_smc_end; + break; + default: + return -1; + } break; default: - return 0; + return -1; } - install_bp_hardening_cb(entry, cb, smccc_start, smccc_end); + if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || + ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) + cb = qcom_link_stack_sanitization; - return 0; -} + if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) + install_bp_hardening_cb(cb, smccc_start, smccc_end); -static void qcom_link_stack_sanitization(void) -{ - u64 tmp; - - asm volatile("mov %0, x30 \n" - ".rept 16 \n" - "bl . + 4 \n" - ".endr \n" - "mov x30, %0 \n" - : "=&r" (tmp)); -} - -static int qcom_enable_link_stack_sanitization(void *data) -{ - const struct arm64_cpu_capabilities *entry = data; - - install_bp_hardening_cb(entry, qcom_link_stack_sanitization, - __qcom_hyp_sanitize_link_stack_start, - __qcom_hyp_sanitize_link_stack_end); - - return 0; + return 1; } -#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */ -#ifdef CONFIG_ARM64_SSBD DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); int ssbd_state __read_mostly = ARM64_SSBD_KERNEL; +static bool __ssb_safe = true; static const struct ssbd_options { const char *str; @@ -309,6 +310,19 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt, void arm64_set_ssbd_mitigation(bool state) { + if (!IS_ENABLED(CONFIG_ARM64_SSBD)) { + pr_info_once("SSBD disabled by kernel configuration\n"); + return; + } + + if (this_cpu_has_cap(ARM64_SSBS)) { + if (state) + asm volatile(SET_PSTATE_SSBS(0)); + else + asm volatile(SET_PSTATE_SSBS(1)); + return; + } + switch (psci_ops.conduit) { case PSCI_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); @@ -330,11 +344,28 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, struct arm_smccc_res res; bool required = true; s32 val; + bool this_cpu_safe = false; WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + if (cpu_mitigations_off()) + ssbd_state = ARM64_SSBD_FORCE_DISABLE; + + /* delay setting __ssb_safe until we get a firmware response */ + if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list)) + this_cpu_safe = true; + + if (this_cpu_has_cap(ARM64_SSBS)) { + if (!this_cpu_safe) + __ssb_safe = false; + required = false; + goto out_printmsg; + } + if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { ssbd_state = ARM64_SSBD_UNKNOWN; + if (!this_cpu_safe) + __ssb_safe = false; return false; } @@ -351,6 +382,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, default: ssbd_state = ARM64_SSBD_UNKNOWN; + if (!this_cpu_safe) + __ssb_safe = false; return false; } @@ -359,14 +392,18 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, switch (val) { case SMCCC_RET_NOT_SUPPORTED: ssbd_state = ARM64_SSBD_UNKNOWN; + if (!this_cpu_safe) + __ssb_safe = false; return false; + /* machines with mixed mitigation requirements must not return this */ case SMCCC_RET_NOT_REQUIRED: pr_info_once("%s mitigation not required\n", entry->desc); ssbd_state = ARM64_SSBD_MITIGATED; return false; case SMCCC_RET_SUCCESS: + __ssb_safe = false; required = true; break; @@ -376,12 +413,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, default: WARN_ON(1); + if (!this_cpu_safe) + __ssb_safe = false; return false; } switch (ssbd_state) { case ARM64_SSBD_FORCE_DISABLE: - pr_info_once("%s disabled from command-line\n", entry->desc); arm64_set_ssbd_mitigation(false); required = false; break; @@ -394,7 +432,6 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, break; case ARM64_SSBD_FORCE_ENABLE: - pr_info_once("%s forced from command-line\n", entry->desc); arm64_set_ssbd_mitigation(true); required = true; break; @@ -404,23 +441,126 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, break; } +out_printmsg: + switch (ssbd_state) { + case ARM64_SSBD_FORCE_DISABLE: + pr_info_once("%s disabled from command-line\n", entry->desc); + break; + + case ARM64_SSBD_FORCE_ENABLE: + pr_info_once("%s forced from command-line\n", entry->desc); + break; + } + return required; } -#endif /* CONFIG_ARM64_SSBD */ - -#define MIDR_RANGE(model, min, max) \ - .def_scope = SCOPE_LOCAL_CPU, \ - .matches = is_affected_midr_range, \ - .midr_model = model, \ - .midr_range_min = min, \ - .midr_range_max = max - -#define MIDR_ALL_VERSIONS(model) \ - .def_scope = SCOPE_LOCAL_CPU, \ - .matches = is_affected_midr_range, \ - .midr_model = model, \ - .midr_range_min = 0, \ - .midr_range_max = (MIDR_VARIANT_MASK | MIDR_REVISION_MASK) + +/* known invulnerable cores */ +static const struct midr_range arm64_ssb_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + {}, +}; + +#define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ + .matches = is_affected_midr_range, \ + .midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max) + +#define CAP_MIDR_ALL_VERSIONS(model) \ + .matches = is_affected_midr_range, \ + .midr_range = MIDR_ALL_VERSIONS(model) + +#define MIDR_FIXED(rev, revidr_mask) \ + .fixed_revs = (struct arm64_midr_revidr[]){{ (rev), (revidr_mask) }, {}} + +#define ERRATA_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, \ + CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) + +#define CAP_MIDR_RANGE_LIST(list) \ + .matches = is_affected_midr_range_list, \ + .midr_range_list = list + +/* Errata affecting a range of revisions of given model variant */ +#define ERRATA_MIDR_REV_RANGE(m, var, r_min, r_max) \ + ERRATA_MIDR_RANGE(m, var, r_min, var, r_max) + +/* Errata affecting a single variant/revision of a model */ +#define ERRATA_MIDR_REV(model, var, rev) \ + ERRATA_MIDR_RANGE(model, var, rev, var, rev) + +/* Errata affecting all variants/revisions of a given a model */ +#define ERRATA_MIDR_ALL_VERSIONS(model) \ + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, \ + CAP_MIDR_ALL_VERSIONS(model) + +/* Errata affecting a list of midr ranges, with same work around */ +#define ERRATA_MIDR_RANGE_LIST(midr_list) \ + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, \ + CAP_MIDR_RANGE_LIST(midr_list) + +/* Track overall mitigation state. We are only mitigated if all cores are ok */ +static bool __hardenbp_enab = true; +static bool __spectrev2_safe = true; + +/* + * List of CPUs that do not need any Spectre-v2 mitigation at all. + */ +static const struct midr_range spectre_v2_safe_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + { /* sentinel */ } +}; + +/* + * Track overall bp hardening for all heterogeneous cores in the machine. + * We are only considered "safe" if all booted cores are known safe. + */ +static bool __maybe_unused +check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) +{ + int need_wa; + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + + /* If the CPU has CSV2 set, we're safe */ + if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1), + ID_AA64PFR0_CSV2_SHIFT)) + return false; + + /* Alternatively, we have a list of unaffected CPUs */ + if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list)) + return false; + + /* Fallback to firmware detection */ + need_wa = detect_harden_bp_fw(); + if (!need_wa) + return false; + + __spectrev2_safe = false; + + if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) { + pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n"); + __hardenbp_enab = false; + return false; + } + + /* forced off */ + if (__nospectre_v2 || cpu_mitigations_off()) { + pr_info_once("spectrev2 mitigation disabled by command line option\n"); + __hardenbp_enab = false; + return false; + } + + if (need_wa < 0) { + pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n"); + __hardenbp_enab = false; + } + + return (need_wa > 0); +} const struct arm64_cpu_capabilities arm64_errata[] = { #if defined(CONFIG_ARM64_ERRATUM_826319) || \ @@ -430,8 +570,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A53 r0p[012] */ .desc = "ARM errata 826319, 827319, 824069", .capability = ARM64_WORKAROUND_CLEAN_CACHE, - MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02), - .enable = cpu_enable_cache_maint_trap, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 2), + .cpu_enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_819472 @@ -439,8 +579,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A53 r0p[01] */ .desc = "ARM errata 819472", .capability = ARM64_WORKAROUND_CLEAN_CACHE, - MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01), - .enable = cpu_enable_cache_maint_trap, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 1), + .cpu_enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_832075 @@ -448,9 +588,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A57 r0p0 - r1p2 */ .desc = "ARM erratum 832075", .capability = ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE, - MIDR_RANGE(MIDR_CORTEX_A57, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(1, 2)), + ERRATA_MIDR_RANGE(MIDR_CORTEX_A57, + 0, 0, + 1, 2), }, #endif #ifdef CONFIG_ARM64_ERRATUM_834220 @@ -458,9 +598,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A57 r0p0 - r1p2 */ .desc = "ARM erratum 834220", .capability = ARM64_WORKAROUND_834220, - MIDR_RANGE(MIDR_CORTEX_A57, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(1, 2)), + ERRATA_MIDR_RANGE(MIDR_CORTEX_A57, + 0, 0, + 1, 2), }, #endif #ifdef CONFIG_ARM64_ERRATUM_845719 @@ -468,7 +608,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A53 r0p[01234] */ .desc = "ARM erratum 845719", .capability = ARM64_WORKAROUND_845719, - MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04), + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_23154 @@ -476,7 +616,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cavium ThunderX, pass 1.x */ .desc = "Cavium erratum 23154", .capability = ARM64_WORKAROUND_CAVIUM_23154, - MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01), + ERRATA_MIDR_REV_RANGE(MIDR_THUNDERX, 0, 0, 1), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_27456 @@ -484,15 +624,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cavium ThunderX, T88 pass 1.x - 2.1 */ .desc = "Cavium erratum 27456", .capability = ARM64_WORKAROUND_CAVIUM_27456, - MIDR_RANGE(MIDR_THUNDERX, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(1, 1)), + ERRATA_MIDR_RANGE(MIDR_THUNDERX, + 0, 0, + 1, 1), }, { /* Cavium ThunderX, T81 pass 1.0 */ .desc = "Cavium erratum 27456", .capability = ARM64_WORKAROUND_CAVIUM_27456, - MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00), + ERRATA_MIDR_REV(MIDR_THUNDERX_81XX, 0, 0), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_30115 @@ -500,49 +640,48 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cavium ThunderX, T88 pass 1.x - 2.2 */ .desc = "Cavium erratum 30115", .capability = ARM64_WORKAROUND_CAVIUM_30115, - MIDR_RANGE(MIDR_THUNDERX, 0x00, - (1 << MIDR_VARIANT_SHIFT) | 2), + ERRATA_MIDR_RANGE(MIDR_THUNDERX, + 0, 0, + 1, 2), }, { /* Cavium ThunderX, T81 pass 1.0 - 1.2 */ .desc = "Cavium erratum 30115", .capability = ARM64_WORKAROUND_CAVIUM_30115, - MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x02), + ERRATA_MIDR_REV_RANGE(MIDR_THUNDERX_81XX, 0, 0, 2), }, { /* Cavium ThunderX, T83 pass 1.0 */ .desc = "Cavium erratum 30115", .capability = ARM64_WORKAROUND_CAVIUM_30115, - MIDR_RANGE(MIDR_THUNDERX_83XX, 0x00, 0x00), + ERRATA_MIDR_REV(MIDR_THUNDERX_83XX, 0, 0), }, #endif { .desc = "Mismatched cache line size", .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE, .matches = has_mismatched_cache_type, - .def_scope = SCOPE_LOCAL_CPU, - .enable = cpu_enable_trap_ctr_access, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .cpu_enable = cpu_enable_trap_ctr_access, }, { .desc = "Mismatched cache type", .capability = ARM64_MISMATCHED_CACHE_TYPE, .matches = has_mismatched_cache_type, - .def_scope = SCOPE_LOCAL_CPU, - .enable = cpu_enable_trap_ctr_access, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .cpu_enable = cpu_enable_trap_ctr_access, }, #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, - MIDR_RANGE(MIDR_QCOM_FALKOR_V1, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(0, 0)), + ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0), }, { .desc = "Qualcomm Technologies Kryo erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, - .def_scope = SCOPE_LOCAL_CPU, - .midr_model = MIDR_QCOM_KRYO, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .midr_range.model = MIDR_QCOM_KRYO, .matches = is_kryo_midr, }, #endif @@ -550,9 +689,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm Technologies Falkor erratum 1009", .capability = ARM64_WORKAROUND_REPEAT_TLBI, - MIDR_RANGE(MIDR_QCOM_FALKOR_V1, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(0, 0)), + ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0), }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 @@ -560,100 +697,56 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A73 all versions */ .desc = "ARM erratum 858921", .capability = ARM64_WORKAROUND_858921, - MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), }, #endif -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), - .enable = enable_smccc_arch_workaround_1, - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), - .enable = enable_smccc_arch_workaround_1, - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), - .enable = enable_smccc_arch_workaround_1, - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), - .enable = enable_smccc_arch_workaround_1, - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1), - .enable = qcom_enable_link_stack_sanitization, - }, - { - .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, - MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1), - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), - .enable = qcom_enable_link_stack_sanitization, - }, - { - .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, - MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), - }, - { - .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), - .enable = enable_smccc_arch_workaround_1, - }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), - .enable = enable_smccc_arch_workaround_1, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = check_branch_predictor, }, -#endif -#ifdef CONFIG_ARM64_SSBD { .desc = "Speculative Store Bypass Disable", - .def_scope = SCOPE_LOCAL_CPU, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .capability = ARM64_SSBD, .matches = has_ssbd_mitigation, + .midr_range_list = arm64_ssb_cpus, }, -#endif { } }; -/* - * The CPU Errata work arounds are detected and applied at boot time - * and the related information is freed soon after. If the new CPU requires - * an errata not detected at boot, fail this CPU. - */ -void verify_local_cpu_errata_workarounds(void) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, + char *buf) { - const struct arm64_cpu_capabilities *caps = arm64_errata; - - for (; caps->matches; caps++) { - if (cpus_have_cap(caps->capability)) { - if (caps->enable) - caps->enable((void *)caps); - } else if (caps->matches(caps, SCOPE_LOCAL_CPU)) { - pr_crit("CPU%d: Requires work around for %s, not detected" - " at boot time\n", - smp_processor_id(), - caps->desc ? : "an erratum"); - cpu_die_early(); - } - } + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -void update_cpu_errata_workarounds(void) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, + char *buf) { - update_cpu_capabilities(arm64_errata, "enabling workaround for"); + if (__spectrev2_safe) + return sprintf(buf, "Not affected\n"); + + if (__hardenbp_enab) + return sprintf(buf, "Mitigation: Branch predictor hardening\n"); + + return sprintf(buf, "Vulnerable\n"); } -void __init enable_errata_workarounds(void) +ssize_t cpu_show_spec_store_bypass(struct device *dev, + struct device_attribute *attr, char *buf) { - enable_cpu_capabilities(arm64_errata); + if (__ssb_safe) + return sprintf(buf, "Not affected\n"); + + switch (ssbd_state) { + case ARM64_SSBD_KERNEL: + case ARM64_SSBD_FORCE_ENABLE: + if (IS_ENABLED(CONFIG_ARM64_SSBD)) + return sprintf(buf, + "Mitigation: Speculative Store Bypass disabled via prctl\n"); + } + + return sprintf(buf, "Vulnerable\n"); } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 29b5b72b7877..15ce2c8b9ee2 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -24,6 +24,7 @@ #include <linux/stop_machine.h> #include <linux/types.h> #include <linux/mm.h> +#include <linux/cpu.h> #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> @@ -107,7 +108,13 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SM3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0), @@ -117,36 +124,42 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_FCMA_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_DPB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), /* Linux doesn't care about the EL3 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ASID_SHIFT, 4, 0), /* * Differing PARange is fine as long as all peripherals and memory are mapped * within the minimum PARange of all CPUs @@ -157,20 +170,21 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VHE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -178,8 +192,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1), /* DIC */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1), /* IDC */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, 24, 4, 0), /* CWG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, 20, 4, 0), /* ERG */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will @@ -197,14 +211,14 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = { }; static const struct arm64_ftr_bits ftr_id_mmfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0xf), /* InnerShr */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), /* FCSE */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 16, 4, 0), /* TCM */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0), /* ShareLvl */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0xf), /* OuterShr */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* PMSA */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* VMSA */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), /* TCM */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* ShareLvl */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0xf), /* OuterShr */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* PMSA */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* VMSA */ ARM64_FTR_END, }; @@ -225,8 +239,8 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { }; static const struct arm64_ftr_bits ftr_mvfr2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* FPMisc */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* SIMDMisc */ ARM64_FTR_END, }; @@ -238,25 +252,25 @@ static const struct arm64_ftr_bits ftr_dczid[] = { static const struct arm64_ftr_bits ftr_id_isar5[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_mmfr4[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* ac2 */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_pfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* State1 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* State0 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* State3 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), /* State2 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* State1 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* State0 */ ARM64_FTR_END, }; @@ -337,7 +351,7 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 0, CRm = 4 */ ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0), - ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz), + ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -411,6 +425,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_LOWER_SAFE: ret = new < cur ? new : cur; break; + case FTR_HIGHER_OR_ZERO_SAFE: + if (!cur || !new) + break; + /* Fallthrough */ case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; @@ -472,6 +490,9 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) reg->user_mask = user_mask; } +extern const struct arm64_cpu_capabilities arm64_errata[]; +static void __init setup_boot_cpu_capabilities(void); + void __init init_cpu_features(struct cpuinfo_arm64 *info) { /* Before we start using the tables, make sure it is sorted */ @@ -509,6 +530,11 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2); } + /* + * Detect and enable early CPU capabilities based on the boot CPU, + * after we have initialised the CPU feature infrastructure. + */ + setup_boot_cpu_capabilities(); } static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new) @@ -605,7 +631,6 @@ void update_cpu_features(int cpu, /* * EL3 is not our concern. - * ID_AA64PFR1 is currently RES0. */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); @@ -800,14 +825,34 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus ID_AA64PFR0_FP_SHIFT) < 0; } -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, - int __unused) + int scope) { - char const *str = "command line option"; - u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + /* List of CPUs that are not vulnerable and don't need KPTI */ + static const struct midr_range kpti_safe_list[] = { + MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), + MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), + }; + char const *str = "kpti command line option"; + bool meltdown_safe; + + meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list); + + /* Defer to CPU feature registers */ + if (has_cpuid_feature(entry, scope)) + meltdown_safe = true; + + if (!meltdown_safe) + __meltdown_safe = false; /* * For reasons that aren't entirely clear, enabling KPTI on Cavium @@ -819,6 +864,24 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, __kpti_forced = -1; } + /* Useful for KASLR robustness */ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) { + if (!__kpti_forced) { + str = "KASLR"; + __kpti_forced = 1; + } + } + + if (cpu_mitigations_off() && !__kpti_forced) { + str = "mitigations=off"; + __kpti_forced = -1; + } + + if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) { + pr_info_once("kernel page table isolation disabled by kernel configuration\n"); + return false; + } + /* Forced? */ if (__kpti_forced) { pr_info_once("kernel page table isolation forced %s by %s\n", @@ -826,23 +889,12 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, return __kpti_forced > 0; } - /* Useful for KASLR robustness */ - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return true; - - /* Don't force KPTI for CPUs that are not vulnerable */ - switch (read_cpuid_id() & MIDR_CPU_MODEL_MASK) { - case MIDR_CAVIUM_THUNDERX2: - case MIDR_BRCM_VULCAN: - return false; - } - - /* Defer to CPU feature registers */ - return !cpuid_feature_extract_unsigned_field(pfr0, - ID_AA64PFR0_CSV3_SHIFT); + return !meltdown_safe; } -static int kpti_install_ng_mappings(void *__unused) +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +static void +kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) { typedef void (kpti_remap_fn)(int, int, phys_addr_t); extern kpti_remap_fn idmap_kpti_install_ng_mappings; @@ -852,7 +904,7 @@ static int kpti_install_ng_mappings(void *__unused) int cpu = smp_processor_id(); if (kpti_applied) - return 0; + return; remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); @@ -863,8 +915,14 @@ static int kpti_install_ng_mappings(void *__unused) if (!cpu) kpti_applied = true; - return 0; + return; } +#else +static void +kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) +{ +} +#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ static int __init parse_kpti(char *str) { @@ -878,9 +936,8 @@ static int __init parse_kpti(char *str) return 0; } early_param("kpti", parse_kpti); -#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ -static int cpu_copy_el2regs(void *__unused) +static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused) { /* * Copy register values that aren't redirected by hardware. @@ -892,15 +949,55 @@ static int cpu_copy_el2regs(void *__unused) */ if (!alternatives_applied) write_sysreg(read_sysreg(tpidr_el1), tpidr_el2); +} + +#ifdef CONFIG_ARM64_SSBD +static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr) +{ + if (user_mode(regs)) + return 1; + if (instr & BIT(CRm_shift)) + regs->pstate |= PSR_SSBS_BIT; + else + regs->pstate &= ~PSR_SSBS_BIT; + + arm64_skip_faulting_instruction(regs, 4); return 0; } +static struct undef_hook ssbs_emulation_hook = { + .instr_mask = ~(1U << CRm_shift), + .instr_val = 0xd500001f | REG_PSTATE_SSBS_IMM, + .fn = ssbs_emulation_handler, +}; + +static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused) +{ + static bool undef_hook_registered = false; + static DEFINE_SPINLOCK(hook_lock); + + spin_lock(&hook_lock); + if (!undef_hook_registered) { + register_undef_hook(&ssbs_emulation_hook); + undef_hook_registered = true; + } + spin_unlock(&hook_lock); + + if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { + sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS); + arm64_set_ssbd_mitigation(false); + } else { + arm64_set_ssbd_mitigation(true); + } +} +#endif /* CONFIG_ARM64_SSBD */ + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", .capability = ARM64_HAS_SYSREG_GIC_CPUIF, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_useable_gicv3_cpuif, .sys_reg = SYS_ID_AA64PFR0_EL1, .field_pos = ID_AA64PFR0_GIC_SHIFT, @@ -911,20 +1008,20 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Privileged Access Never", .capability = ARM64_HAS_PAN, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, .field_pos = ID_AA64MMFR1_PAN_SHIFT, .sign = FTR_UNSIGNED, .min_field_value = 1, - .enable = cpu_enable_pan, + .cpu_enable = cpu_enable_pan, }, #endif /* CONFIG_ARM64_PAN */ #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) { .desc = "LSE atomic instructions", .capability = ARM64_HAS_LSE_ATOMICS, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR0_EL1, .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT, @@ -935,14 +1032,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Software prefetching using PRFM", .capability = ARM64_HAS_NO_HW_PREFETCH, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .matches = has_no_hw_prefetch, }, #ifdef CONFIG_ARM64_UAO { .desc = "User Access Override", .capability = ARM64_HAS_UAO, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR2_EL1, .field_pos = ID_AA64MMFR2_UAO_SHIFT, @@ -956,21 +1053,23 @@ static const struct arm64_cpu_capabilities arm64_features[] = { #ifdef CONFIG_ARM64_PAN { .capability = ARM64_ALT_PAN_NOT_UAO, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = cpufeature_pan_not_uao, }, #endif /* CONFIG_ARM64_PAN */ +#ifdef CONFIG_ARM64_VHE { .desc = "Virtualization Host Extensions", .capability = ARM64_HAS_VIRT_HOST_EXTN, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = runs_at_el2, - .enable = cpu_copy_el2regs, + .cpu_enable = cpu_copy_el2regs, }, +#endif /* CONFIG_ARM64_VHE */ { .desc = "32-bit EL0 Support", .capability = ARM64_HAS_32BIT_EL0, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, @@ -980,22 +1079,28 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Reduced HYP mapping offset", .capability = ARM64_HYP_OFFSET_LOW, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = hyp_offset_low, }, -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 { .desc = "Kernel page table isolation (KPTI)", .capability = ARM64_UNMAP_KERNEL_AT_EL0, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, + /* + * The ID feature fields below are used to indicate that + * the CPU doesn't need KPTI. See unmap_kernel_at_el0 for + * more details. + */ + .sys_reg = SYS_ID_AA64PFR0_EL1, + .field_pos = ID_AA64PFR0_CSV3_SHIFT, + .min_field_value = 1, .matches = unmap_kernel_at_el0, - .enable = kpti_install_ng_mappings, + .cpu_enable = kpti_install_ng_mappings, }, -#endif { /* FP/SIMD is not implemented */ .capability = ARM64_HAS_NO_FPSIMD, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .min_field_value = 0, .matches = has_no_fpsimd, }, @@ -1003,26 +1108,39 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Data cache clean to Point of Persistence", .capability = ARM64_HAS_DCPOP, - .def_scope = SCOPE_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64ISAR1_EL1, .field_pos = ID_AA64ISAR1_DPB_SHIFT, .min_field_value = 1, }, #endif +#ifdef CONFIG_ARM64_SSBD + { + .desc = "Speculative Store Bypassing Safe (SSBS)", + .capability = ARM64_SSBS, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .field_pos = ID_AA64PFR1_SSBS_SHIFT, + .sign = FTR_UNSIGNED, + .min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY, + .cpu_enable = cpu_enable_ssbs, + }, +#endif {}, }; -#define HWCAP_CAP(reg, field, s, min_value, type, cap) \ +#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ { \ .desc = #cap, \ - .def_scope = SCOPE_SYSTEM, \ + .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ .matches = has_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ .sign = s, \ .min_field_value = min_value, \ - .hwcap_type = type, \ + .hwcap_type = cap_type, \ .hwcap = cap, \ } @@ -1031,17 +1149,28 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC), + HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS), {}, }; @@ -1106,7 +1235,7 @@ static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps) /* We support emulation of accesses to CPU ID feature registers */ elf_hwcap |= HWCAP_CPUID; for (; hwcaps->matches; hwcaps++) - if (hwcaps->matches(hwcaps, hwcaps->def_scope)) + if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps))) cap_set_elf_hwcap(hwcaps); } @@ -1129,11 +1258,13 @@ static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array, return false; } -void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, - const char *info) +static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, + u16 scope_mask, const char *info) { + scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (; caps->matches; caps++) { - if (!caps->matches(caps, caps->def_scope)) + if (!(caps->type & scope_mask) || + !caps->matches(caps, cpucap_default_scope(caps))) continue; if (!cpus_have_cap(caps->capability) && caps->desc) @@ -1142,33 +1273,69 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, } } +static void update_cpu_capabilities(u16 scope_mask) +{ + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); + __update_cpu_capabilities(arm64_errata, scope_mask, + "enabling workaround for"); +} + +static int __enable_cpu_capability(void *arg) +{ + const struct arm64_cpu_capabilities *cap = arg; + + cap->cpu_enable(cap); + return 0; +} + /* * Run through the enabled capabilities and enable() it on all active * CPUs */ -void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +static void __init +__enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, + u16 scope_mask) { + scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (; caps->matches; caps++) { unsigned int num = caps->capability; - if (!cpus_have_cap(num)) + if (!(caps->type & scope_mask) || !cpus_have_cap(num)) continue; /* Ensure cpus_have_const_cap(num) works */ static_branch_enable(&cpu_hwcap_keys[num]); - if (caps->enable) { + if (caps->cpu_enable) { /* - * Use stop_machine() as it schedules the work allowing - * us to modify PSTATE, instead of on_each_cpu() which - * uses an IPI, giving us a PSTATE that disappears when - * we return. + * Capabilities with SCOPE_BOOT_CPU scope are finalised + * before any secondary CPU boots. Thus, each secondary + * will enable the capability as appropriate via + * check_local_cpu_capabilities(). The only exception is + * the boot CPU, for which the capability must be + * enabled here. This approach avoids costly + * stop_machine() calls for this case. + * + * Otherwise, use stop_machine() as it schedules the + * work allowing us to modify PSTATE, instead of + * on_each_cpu() which uses an IPI, giving us a PSTATE + * that disappears when we return. */ - stop_machine(caps->enable, (void *)caps, cpu_online_mask); + if (scope_mask & SCOPE_BOOT_CPU) + caps->cpu_enable(caps); + else + stop_machine(__enable_cpu_capability, + (void *)caps, cpu_online_mask); } } } +static void __init enable_cpu_capabilities(u16 scope_mask) +{ + __enable_cpu_capabilities(arm64_features, scope_mask); + __enable_cpu_capabilities(arm64_errata, scope_mask); +} + /* * Flag to indicate if we have computed the system wide * capabilities based on the boot time active CPUs. This @@ -1185,13 +1352,82 @@ static inline void set_sys_caps_initialised(void) } /* + * Run through the list of capabilities to check for conflicts. + * If the system has already detected a capability, take necessary + * action on this CPU. + * + * Returns "false" on conflicts. + */ +static bool +__verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps_list, + u16 scope_mask) +{ + bool cpu_has_cap, system_has_cap; + const struct arm64_cpu_capabilities *caps; + + scope_mask &= ARM64_CPUCAP_SCOPE_MASK; + + for (caps = caps_list; caps->matches; caps++) { + if (!(caps->type & scope_mask)) + continue; + + cpu_has_cap = __this_cpu_has_cap(caps_list, caps->capability); + system_has_cap = cpus_have_cap(caps->capability); + + if (system_has_cap) { + /* + * Check if the new CPU misses an advertised feature, + * which is not safe to miss. + */ + if (!cpu_has_cap && !cpucap_late_cpu_optional(caps)) + break; + /* + * We have to issue cpu_enable() irrespective of + * whether the CPU has it or not, as it is enabeld + * system wide. It is upto the call back to take + * appropriate action on this CPU. + */ + if (caps->cpu_enable) + caps->cpu_enable(caps); + } else { + /* + * Check if the CPU has this capability if it isn't + * safe to have when the system doesn't. + */ + if (cpu_has_cap && !cpucap_late_cpu_permitted(caps)) + break; + } + } + + if (caps->matches) { + pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n", + smp_processor_id(), caps->capability, + caps->desc, system_has_cap, cpu_has_cap); + return false; + } + + return true; +} + +static bool verify_local_cpu_caps(u16 scope_mask) +{ + return __verify_local_cpu_caps(arm64_errata, scope_mask) && + __verify_local_cpu_caps(arm64_features, scope_mask); +} + +/* * Check for CPU features that are used in early boot * based on the Boot CPU value. */ static void check_early_cpu_features(void) { - verify_cpu_run_el(); verify_cpu_asid_bits(); + /* + * Early features are used by the kernel already. If there + * is a conflict, we cannot proceed further. + */ + if (!verify_local_cpu_caps(SCOPE_BOOT_CPU)) + cpu_panic_kernel(); } static void @@ -1206,26 +1442,6 @@ verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps) } } -static void -verify_local_cpu_features(const struct arm64_cpu_capabilities *caps_list) -{ - const struct arm64_cpu_capabilities *caps = caps_list; - for (; caps->matches; caps++) { - if (!cpus_have_cap(caps->capability)) - continue; - /* - * If the new CPU misses an advertised feature, we cannot proceed - * further, park the cpu. - */ - if (!__this_cpu_has_cap(caps_list, caps->capability)) { - pr_crit("CPU%d: missing feature: %s\n", - smp_processor_id(), caps->desc); - cpu_die_early(); - } - if (caps->enable) - caps->enable((void *)caps); - } -} /* * Run through the enabled system capabilities and enable() it on this CPU. @@ -1237,8 +1453,14 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps_list) */ static void verify_local_cpu_capabilities(void) { - verify_local_cpu_errata_workarounds(); - verify_local_cpu_features(arm64_features); + /* + * The capabilities with SCOPE_BOOT_CPU are checked from + * check_early_cpu_features(), as they need to be verified + * on all secondary CPUs. + */ + if (!verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU)) + cpu_die_early(); + verify_local_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) verify_local_elf_hwcaps(compat_elf_hwcaps); @@ -1254,20 +1476,22 @@ void check_local_cpu_capabilities(void) /* * If we haven't finalised the system capabilities, this CPU gets - * a chance to update the errata work arounds. + * a chance to update the errata work arounds and local features. * Otherwise, this CPU should verify that it has all the system * advertised capabilities. */ if (!sys_caps_initialised) - update_cpu_errata_workarounds(); + update_cpu_capabilities(SCOPE_LOCAL_CPU); else verify_local_cpu_capabilities(); } -static void __init setup_feature_capabilities(void) +static void __init setup_boot_cpu_capabilities(void) { - update_cpu_capabilities(arm64_features, "detected feature:"); - enable_cpu_capabilities(arm64_features); + /* Detect capabilities with either SCOPE_BOOT_CPU or SCOPE_LOCAL_CPU */ + update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU); + /* Enable the SCOPE_BOOT_CPU capabilities alone right away */ + enable_cpu_capabilities(SCOPE_BOOT_CPU); } DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); @@ -1286,14 +1510,24 @@ bool this_cpu_has_cap(unsigned int cap) __this_cpu_has_cap(arm64_errata, cap)); } +static void __init setup_system_capabilities(void) +{ + /* + * We have finalised the system-wide safe feature + * registers, finalise the capabilities that depend + * on it. Also enable all the available capabilities, + * that are not enabled already. + */ + update_cpu_capabilities(SCOPE_SYSTEM); + enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU); +} + void __init setup_cpu_features(void) { u32 cwg; int cls; - /* Set the CPU feature capabilies */ - setup_feature_capabilities(); - enable_errata_workarounds(); + setup_system_capabilities(); mark_const_caps_ready(); setup_elf_hwcaps(arm64_elf_hwcaps); @@ -1419,3 +1653,15 @@ static int __init enable_mrs_emulation(void) } core_initcall(enable_mrs_emulation); + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, + char *buf) +{ + if (__meltdown_safe) + return sprintf(buf, "Not affected\n"); + + if (arm64_kernel_unmapped_at_el0()) + return sprintf(buf, "Mitigation: PTI\n"); + + return sprintf(buf, "Vulnerable\n"); +} diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 311885962830..9ff64e04e63d 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -69,6 +69,18 @@ static const char *const hwcap_str[] = { "fcma", "lrcpc", "dcpop", + "sha3", + "sm3", + "sm4", + "asimddp", + "sha512", + "sve", + "asimdfhm", + "dit", + "uscat", + "ilrcpc", + "flagm", + "ssbs", NULL }; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 5d547deb6996..f4fdf6420ac5 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -28,6 +28,7 @@ #include <linux/signal.h> #include <asm/fpsimd.h> +#include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/simd.h> diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 50986e388d2b..6eefd5873aef 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -76,7 +76,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (offset < -SZ_128M || offset >= SZ_128M) { #ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline; + struct plt_entry trampoline, *dst; struct module *mod; /* @@ -104,24 +104,33 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * is added in the future, but for now, the pr_err() below * deals with a theoretical issue only. */ + dst = mod->arch.ftrace_trampoline; trampoline = get_plt_entry(addr); - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &trampoline)) { - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &(struct plt_entry){})) { + if (!plt_entries_equal(dst, &trampoline)) { + if (!plt_entries_equal(dst, &(struct plt_entry){})) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; } /* point the trampoline to our ftrace entry point */ module_disable_ro(mod); - *mod->arch.ftrace_trampoline = trampoline; + *dst = trampoline; module_enable_ro(mod, true); - /* update trampoline before patching in the branch */ - smp_wmb(); + /* + * Ensure updated trampoline is visible to instruction + * fetch before we patch in the branch. Although the + * architecture doesn't require an IPI in this case, + * Neoverse-N1 erratum #1542419 does require one + * if the TLB maintenance in module_enable_ro() is + * skipped due to rodata_enabled. It doesn't seem worth + * it to make it conditional given that this is + * certainly not a fast-path. + */ + flush_icache_range((unsigned long)&dst[0], + (unsigned long)&dst[1]); } - addr = (unsigned long)(void *)mod->arch.ftrace_trampoline; + addr = (unsigned long)dst; #else /* CONFIG_ARM64_MODULE_PLTS */ return -EINVAL; #endif /* CONFIG_ARM64_MODULE_PLTS */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 1371542de0d3..9c00fd2acc2a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -388,17 +388,13 @@ ENTRY(el2_setup) mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 b.eq 1f - mrs x0, sctlr_el1 -CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1 -CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 + mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1) msr sctlr_el1, x0 mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 isb ret -1: mrs x0, sctlr_el2 -CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2 -CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2 +1: mov_q x0, (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) msr sctlr_el2, x0 #ifdef CONFIG_ARM64_VHE @@ -505,10 +501,7 @@ install_el2_stub: * requires no configuration, and all non-hyp-specific EL2 setup * will be done via the _EL1 system register aliases in __cpu_setup. */ - /* sctlr_el1 */ - mov x0, #0x0800 // Set/clear RES{1,0} bits -CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems -CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems + mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1) msr sctlr_el1, x0 /* Coprocessor traps. */ @@ -601,6 +594,7 @@ secondary_startup: /* * Common entry point for secondary CPUs. */ + bl __cpu_secondary_check52bitva bl __cpu_setup // initialise processor bl __enable_mmu ldr x8, =__secondary_switched @@ -675,6 +669,31 @@ ENTRY(__enable_mmu) ret ENDPROC(__enable_mmu) +ENTRY(__cpu_secondary_check52bitva) +#ifdef CONFIG_ARM64_52BIT_VA + ldr_l x0, vabits_user + cmp x0, #52 + b.ne 2f + + mrs_s x0, SYS_ID_AA64MMFR2_EL1 + and x0, x0, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + cbnz x0, 2f + + adr_l x0, va52mismatch + mov w1, #1 + strb w1, [x0] + dmb sy + dc ivac, x0 // Invalidate potentially stale cache line + + update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x0, x1 +1: wfe + wfi + b 1b + +#endif +2: ret +ENDPROC(__cpu_secondary_check52bitva) + __no_granule_support: /* Indicate that this CPU can't boot and is stuck in the kernel */ update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2 diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 749f81779420..95697a9c1245 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -548,13 +548,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) /* Aligned */ break; case 1: - /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) - break; case 2: /* Allow halfword watchpoints and breakpoints. */ if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + case 3: + /* Allow single byte watchpoint. */ + if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; default: return -EINVAL; } diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index 40f9f0b078a4..12af2ba8d558 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -73,7 +73,11 @@ #ifdef CONFIG_EFI -__efistub_stext_offset = stext - _text; +/* + * Use ABSOLUTE() to avoid ld.lld treating this as a relative symbol: + * https://github.com/ClangBuiltLinux/linux/issues/561 + */ +__efistub_stext_offset = ABSOLUTE(stext - _text); /* * The EFI stub has its own symbol namespace prefixed by __efistub_, to diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 2718a77da165..4381aa7b071d 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -793,6 +793,46 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, state); } +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + u32 insn = aarch64_insn_get_ldadd_value(); + + switch (size) { + case AARCH64_INSN_SIZE_32: + case AARCH64_INSN_SIZE_64: + break; + default: + pr_err("%s: unimplemented size encoding %d\n", __func__, size); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_encode_ldst_size(size, insn); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, + result); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, + address); + + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, + value); +} + +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + /* + * STADD is simply encoded as an alias for LDADD with XZR as + * the destination register. + */ + return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address, + value, size); +} + static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, enum aarch64_insn_prfm_policy policy, diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f469e0435903..73ecccc514e1 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -32,6 +32,7 @@ void *module_alloc(unsigned long size) { + u64 module_alloc_end = module_alloc_base + MODULES_VSIZE; gfp_t gfp_mask = GFP_KERNEL; void *p; @@ -39,9 +40,12 @@ void *module_alloc(unsigned long size) if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) gfp_mask |= __GFP_NOWARN; + if (IS_ENABLED(CONFIG_KASAN)) + /* don't exceed the static module region - see below */ + module_alloc_end = MODULES_END; + p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_base + MODULES_VSIZE, - gfp_mask, PAGE_KERNEL_EXEC, 0, + module_alloc_end, gfp_mask, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 9e773732520c..243fd247d04e 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -296,6 +296,10 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, if (IS_ENABLED(CONFIG_ARM64_UAO) && cpus_have_const_cap(ARM64_HAS_UAO)) childregs->pstate |= PSR_UAO_BIT; + + if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) + set_ssbs_bit(childregs); + p->thread.cpu_context.x19 = stack_start; p->thread.cpu_context.x20 = stk_sz; } @@ -336,6 +340,32 @@ void uao_thread_switch(struct task_struct *next) } /* + * Force SSBS state on context-switch, since it may be lost after migrating + * from a CPU which treats the bit as RES0 in a heterogeneous system. + */ +static void ssbs_thread_switch(struct task_struct *next) +{ + struct pt_regs *regs = task_pt_regs(next); + + /* + * Nothing to do for kernel threads, but 'regs' may be junk + * (e.g. idle task) so check the flags and bail early. + */ + if (unlikely(next->flags & PF_KTHREAD)) + return; + + /* If the mitigation is enabled, then we leave SSBS clear. */ + if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || + test_tsk_thread_flag(next, TIF_SSBD)) + return; + + if (compat_user_mode(regs)) + set_compat_ssbs_bit(regs); + else if (user_mode(regs)) + set_ssbs_bit(regs); +} + +/* * We store our current task in sp_el0, which is clobbered by userspace. Keep a * shadow copy so that we can restore this upon entry from userspace. * @@ -363,6 +393,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, contextidr_thread_switch(next); entry_task_switch(next); uao_thread_switch(next); + ssbs_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 34d915b6974b..242527f29c41 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1402,15 +1402,20 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) } /* - * Bits which are always architecturally RES0 per ARM DDI 0487A.h + * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. + * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is + * not described in ARM DDI 0487D.a. + * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may + * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. + * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \ - GENMASK_ULL(5, 5)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ + GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 933adbc0f654..0311fe52c8ff 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -32,6 +33,7 @@ static int save_return_addr(struct stackframe *frame, void *d) return 0; } } +NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { @@ -55,3 +57,4 @@ void *return_address(unsigned int level) return NULL; } EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b7ad41d7b6ee..909bf3926fd2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -83,43 +83,6 @@ enum ipi_msg_type { IPI_WAKEUP }; -#ifdef CONFIG_ARM64_VHE - -/* Whether the boot CPU is running in HYP mode or not*/ -static bool boot_cpu_hyp_mode; - -static inline void save_boot_cpu_run_el(void) -{ - boot_cpu_hyp_mode = is_kernel_in_hyp_mode(); -} - -static inline bool is_boot_cpu_in_hyp_mode(void) -{ - return boot_cpu_hyp_mode; -} - -/* - * Verify that a secondary CPU is running the kernel at the same - * EL as that of the boot CPU. - */ -void verify_cpu_run_el(void) -{ - bool in_el2 = is_kernel_in_hyp_mode(); - bool boot_cpu_el2 = is_boot_cpu_in_hyp_mode(); - - if (in_el2 ^ boot_cpu_el2) { - pr_crit("CPU%d: mismatched Exception Level(EL%d) with boot CPU(EL%d)\n", - smp_processor_id(), - in_el2 ? 2 : 1, - boot_cpu_el2 ? 2 : 1); - cpu_panic_kernel(); - } -} - -#else -static inline void save_boot_cpu_run_el(void) {} -#endif - #ifdef CONFIG_HOTPLUG_CPU static int op_cpu_kill(unsigned int cpu); #else @@ -143,6 +106,7 @@ static int boot_secondary(unsigned int cpu, struct task_struct *idle) } static DECLARE_COMPLETION(cpu_running); +bool va52mismatch __ro_after_init; int __cpu_up(unsigned int cpu, struct task_struct *idle) { @@ -172,10 +136,15 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) if (!cpu_online(cpu)) { pr_crit("CPU%u: failed to come online\n", cpu); + + if (IS_ENABLED(CONFIG_ARM64_52BIT_VA) && va52mismatch) + pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); + ret = -EIO; } } else { pr_err("CPU%u: failed to boot: %d\n", cpu, ret); + return ret; } secondary_data.task = NULL; @@ -448,13 +417,6 @@ void __init smp_prepare_boot_cpu(void) */ jump_label_init(); cpuinfo_store_boot_cpu(); - save_boot_cpu_run_el(); - /* - * Run the errata work around checks on the boot CPU, once we have - * initialised the cpu feature infrastructure from - * cpuinfo_store_boot_cpu() above. - */ - update_cpu_errata_workarounds(); } static u64 __init of_get_cpu_mpidr(struct device_node *dn) diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c index 0560738c1d5c..58de005cd756 100644 --- a/arch/arm64/kernel/ssbd.c +++ b/arch/arm64/kernel/ssbd.c @@ -3,13 +3,32 @@ * Copyright (C) 2018 ARM Ltd, All Rights Reserved. */ +#include <linux/compat.h> #include <linux/errno.h> #include <linux/prctl.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/thread_info.h> +#include <asm/compat.h> #include <asm/cpufeature.h> +static void ssbd_ssbs_enable(struct task_struct *task) +{ + u64 val = is_compat_thread(task_thread_info(task)) ? + PSR_AA32_SSBS_BIT : PSR_SSBS_BIT; + + task_pt_regs(task)->pstate |= val; +} + +static void ssbd_ssbs_disable(struct task_struct *task) +{ + u64 val = is_compat_thread(task_thread_info(task)) ? + PSR_AA32_SSBS_BIT : PSR_SSBS_BIT; + + task_pt_regs(task)->pstate &= ~val; +} + /* * prctl interface for SSBD */ @@ -45,12 +64,14 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) return -EPERM; task_clear_spec_ssb_disable(task); clear_tsk_thread_flag(task, TIF_SSBD); + ssbd_ssbs_enable(task); break; case PR_SPEC_DISABLE: if (state == ARM64_SSBD_FORCE_DISABLE) return -EPERM; task_set_spec_ssb_disable(task); set_tsk_thread_flag(task, TIF_SSBD); + ssbd_ssbs_disable(task); break; case PR_SPEC_FORCE_DISABLE: if (state == ARM64_SSBD_FORCE_DISABLE) @@ -58,6 +79,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); set_tsk_thread_flag(task, TIF_SSBD); + ssbd_ssbs_disable(task); break; default: return -ERANGE; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d5718a060672..2ae7630d685b 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -18,6 +18,7 @@ #include <linux/kernel.h> #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> @@ -85,6 +86,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) return 0; } +NOKPROBE_SYMBOL(unwind_frame); void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) @@ -99,6 +101,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, break; } } +NOKPROBE_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 74259ae9c7f2..5ae9c86c30d1 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -38,6 +38,7 @@ #include <asm/atomic.h> #include <asm/bug.h> +#include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/insn.h> @@ -436,10 +437,9 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); } -int cpu_enable_cache_maint_trap(void *__unused) +void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) { config_sctlr_el1(SCTLR_EL1_UCI, 0); - return 0; } #define __user_cache_maint(insn, address, res) \ @@ -648,7 +648,6 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) handler[reason], smp_processor_id(), esr, esr_get_class_string(esr)); - die("Oops - bad mode", regs, 0); local_irq_disable(); panic("bad mode"); } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index a7b3c198d4de..a360ac6e89e9 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -196,15 +196,3 @@ alternative_endif eret ENDPROC(__fpsimd_guest_restore) - -ENTRY(__qcom_hyp_sanitize_btac_predictors) - /** - * Call SMC64 with Silicon provider serviceID 23<<8 (0xc2001700) - * 0xC2000000-0xC200FFFF: assigned to SiP Service Calls - * b15-b0: contains SiP functionID - */ - movz x0, #0x1700 - movk x0, #0xc200, lsl #16 - smc #0 - ret -ENDPROC(__qcom_hyp_sanitize_btac_predictors) diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 44845996b554..4a8fdbb29286 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -405,16 +405,6 @@ again: __set_host_arch_workaround_state(vcpu); - if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) { - u32 midr = read_cpuid_id(); - - /* Apply BTAC predictors mitigation to all Falkor chips */ - if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || - ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) { - __qcom_hyp_sanitize_btac_predictors(); - } - } - fp_enabled = __fpsimd_enabled(); __sysreg_save_guest_state(guest_ctxt); diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index e19d89cabf2a..3773311ffcd0 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -188,3 +188,14 @@ void __hyp_text __kvm_set_tpidr_el2(u64 tpidr_el2) { asm("msr tpidr_el2, %0": : "r" (tpidr_el2)); } + +void __hyp_text __kvm_enable_ssbs(void) +{ + u64 tmp; + + asm volatile( + "mrs %0, sctlr_el2\n" + "orr %0, %0, %1\n" + "msr sctlr_el2, %0" + : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS)); +} diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 21ba0b29621b..4374020c824a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -57,5 +57,6 @@ ENDPROC(__arch_clear_user) .section .fixup,"ax" .align 2 9: mov x0, x2 // return the original size + uaccess_disable_not_uao x2, x3 ret .previous diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 20305d485046..96b22c0fa343 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -75,5 +75,6 @@ ENDPROC(__arch_copy_from_user) .section .fixup,"ax" .align 2 9998: sub x0, end, dst // bytes not copied + uaccess_disable_not_uao x3, x4 ret .previous diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 54b75deb1d16..e56c705f1f23 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -77,5 +77,6 @@ ENDPROC(__arch_copy_in_user) .section .fixup,"ax" .align 2 9998: sub x0, end, dst // bytes not copied + uaccess_disable_not_uao x3, x4 ret .previous diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index fda6172d6b88..6b99b939c50f 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -74,5 +74,6 @@ ENDPROC(__arch_copy_to_user) .section .fixup,"ax" .align 2 9998: sub x0, end, dst // bytes not copied + uaccess_disable_not_uao x3, x4 ret .previous diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S index 4444c1d25f4b..0f164a4baf52 100644 --- a/arch/arm64/lib/memchr.S +++ b/arch/arm64/lib/memchr.S @@ -30,7 +30,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -ENTRY(memchr) +WEAK(memchr) and w1, w1, #0xff 1: subs x2, x2, #1 b.mi 2f diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index 2a4e239bd17a..fb295f52e9f8 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -58,7 +58,7 @@ pos .req x11 limit_wd .req x12 mask .req x13 -ENTRY(memcmp) +WEAK(memcmp) cbz limit, .Lret0 eor tmp1, src1, src2 tst tmp1, #7 diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S index dae0cf5591f9..7c83091d1bcd 100644 --- a/arch/arm64/lib/strchr.S +++ b/arch/arm64/lib/strchr.S @@ -29,7 +29,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -ENTRY(strchr) +WEAK(strchr) and w1, w1, #0xff 1: ldrb w2, [x0], #1 cmp w2, w1 diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index 471fe61760ef..7d5d15398bfb 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -60,7 +60,7 @@ tmp3 .req x9 zeroones .req x10 pos .req x11 -ENTRY(strcmp) +WEAK(strcmp) eor tmp1, src1, src2 mov zeroones, #REP8_01 tst tmp1, #7 diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 55ccc8e24c08..8e0b14205dcb 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -56,7 +56,7 @@ pos .req x12 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -ENTRY(strlen) +WEAK(strlen) mov zeroones, #REP8_01 bic src, srcin, #15 ands tmp1, srcin, #15 diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index e267044761c6..66bd145935d9 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -64,7 +64,7 @@ limit_wd .req x13 mask .req x14 endloop .req x15 -ENTRY(strncmp) +WEAK(strncmp) cbz limit, .Lret0 eor tmp1, src1, src2 mov zeroones, #REP8_01 diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index eae38da6e0bb..355be04441fe 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -59,7 +59,7 @@ limit_wd .req x14 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -ENTRY(strnlen) +WEAK(strnlen) cbz limit, .Lhit_limit mov zeroones, #REP8_01 bic src, srcin, #15 diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S index 61eabd9a289a..f3b9f8e2917c 100644 --- a/arch/arm64/lib/strrchr.S +++ b/arch/arm64/lib/strrchr.S @@ -29,7 +29,7 @@ * Returns: * x0 - address of last occurrence of 'c' or 0 */ -ENTRY(strrchr) +WEAK(strrchr) mov x3, #0 and w1, w1, #0xff 1: ldrb w2, [x0], #1 diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 465b90d7abf2..bf7c285d0c82 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -875,7 +875,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint, NOKPROBE_SYMBOL(do_debug_exception); #ifdef CONFIG_ARM64_PAN -int cpu_enable_pan(void *__unused) +void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused) { /* * We modify PSTATE. This won't work from irq context as the PSTATE @@ -885,6 +885,5 @@ int cpu_enable_pan(void *__unused) config_sctlr_el1(SCTLR_EL1_SPAN, 0); asm(SET_PSTATE_PAN(1)); - return 0; } #endif /* CONFIG_ARM64_PAN */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6ac0d32d60a5..abb9d2ecc675 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -899,13 +899,18 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) int __init arch_ioremap_pud_supported(void) { - /* only 4k granule supports level 1 block mappings */ - return IS_ENABLED(CONFIG_ARM64_4K_PAGES); + /* + * Only 4k granule supports level 1 block mappings. + * SW table walks can't handle removal of intermediate entries. + */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && + !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int __init arch_ioremap_pmd_supported(void) { - return 1; + /* See arch_ioremap_pud_supported() */ + return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index dad128ba98bf..e9c843e0c172 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -419,7 +419,7 @@ static int __init dummy_numa_init(void) if (numa_off) pr_info("NUMA disabled\n"); /* Forced off on command line. */ pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", - 0LLU, PFN_PHYS(max_pfn) - 1); + memblock_start_of_DRAM(), memblock_end_of_DRAM() - 1); for_each_memblock(memory, mblk) { ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 034a3a2a38ee..ecbc060807d2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -280,6 +280,15 @@ skip_pgd: msr sctlr_el1, x18 isb + /* + * Invalidate the local I-cache so that any instructions fetched + * speculatively from the PoC are discarded, since they may have + * been dynamically patched at the PoU. + */ + ic iallu + dsb nsh + isb + /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] ret @@ -421,11 +430,7 @@ ENTRY(__cpu_setup) /* * Prepare SCTLR */ - adr x5, crval - ldp w5, w6, [x5] - mrs x0, sctlr_el1 - bic x0, x0, x5 // clear bits - orr x0, x0, x6 // set bits + mov_q x0, SCTLR_EL1_SET /* * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for * both user and kernel. @@ -461,21 +466,3 @@ ENTRY(__cpu_setup) msr tcr_el1, x10 ret // return to head.S ENDPROC(__cpu_setup) - - /* - * We set the desired value explicitly, including those of the - * reserved bits. The values of bits EE & E0E were set early in - * el2_setup, which are left untouched below. - * - * n n T - * U E WT T UD US IHBS - * CE0 XWHW CZ ME TEEA S - * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM - * 0011 0... 1101 ..0. ..0. 10.. .0.. .... < hardware reserved - * .... .1.. .... 01.1 11.1 ..01 0.01 1101 < software settings - */ - .type crval, #object -crval: - .word 0xfcffffff // clear - .word 0x34d5d91d // set - .popsection diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 6c881659ee8a..76606e87233f 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -100,6 +100,10 @@ #define A64_STXR(sf, Rt, Rn, Rs) \ A64_LSX(sf, Rt, Rn, Rs, STORE_EX) +/* LSE atomics */ +#define A64_STADD(sf, Rn, Rs) \ + aarch64_insn_gen_stadd(Rn, Rs, A64_SIZE(sf)) + /* Add/subtract (immediate) */ #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \ aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 6110fe344368..1bbb457c293f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -31,8 +31,6 @@ #include "bpf_jit.h" -int bpf_jit_enable __read_mostly; - #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) #define TCALL_CNT (MAX_BPF_JIT_REG + 2) @@ -330,7 +328,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const int i = insn - ctx->prog->insnsi; const bool is64 = BPF_CLASS(code) == BPF_ALU64; const bool isdw = BPF_SIZE(code) == BPF_DW; - u8 jmp_cond; + u8 jmp_cond, reg; s32 jmp_offset; #define check_imm(bits, imm) do { \ @@ -706,18 +704,28 @@ emit_cond_jmp: break; } break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_W: /* STX XADD: lock *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - emit(A64_LDXR(isdw, tmp2, tmp), ctx); - emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); - emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx); - jmp_offset = -3; - check_imm19(jmp_offset); - emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + if (!off) { + reg = dst; + } else { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) { + emit(A64_STADD(isdw, reg, src), ctx); + } else { + emit(A64_LDXR(isdw, tmp2, reg), ctx); + emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); + emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -3; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + } break; /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 853b5611a894..95e8d130e123 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -913,8 +913,12 @@ module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mo void module_arch_cleanup (struct module *mod) { - if (mod->arch.init_unw_table) + if (mod->arch.init_unw_table) { unw_remove_unwind_table(mod->arch.init_unw_table); - if (mod->arch.core_unw_table) + mod->arch.init_unw_table = NULL; + } + if (mod->arch.core_unw_table) { unw_remove_unwind_table(mod->arch.core_unw_table); + mod->arch.core_unw_table = NULL; + } } diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index aa19b7ac8222..476c7b4be378 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -49,6 +49,7 @@ paddr_to_nid(unsigned long paddr) return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0); } +EXPORT_SYMBOL(paddr_to_nid); #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA) /* diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c index b29c3b241e1b..107082877064 100644 --- a/arch/m68k/kernel/uboot.c +++ b/arch/m68k/kernel/uboot.c @@ -102,5 +102,5 @@ __init void process_uboot_commandline(char *commandp, int size) } parse_uboot_commandline(commandp, len); - commandp[size - 1] = 0; + commandp[len - 1] = 0; } diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile index d269dd4b8279..fe5e48184c3c 100644 --- a/arch/microblaze/Makefile +++ b/arch/microblaze/Makefile @@ -83,19 +83,21 @@ archclean: linux.bin linux.bin.gz linux.bin.ub: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' simpleImage.%: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' define archhelp echo '* linux.bin - Create raw binary' echo ' linux.bin.gz - Create compressed raw binary' echo ' linux.bin.ub - Create U-Boot wrapped raw binary' - echo ' simpleImage.<dt> - ELF image with $(arch)/boot/dts/<dt>.dts linked in' - echo ' - stripped elf with fdt blob' - echo ' simpleImage.<dt>.unstrip - full ELF image with fdt blob' - echo ' *_defconfig - Select default config from arch/microblaze/configs' - echo '' + echo ' simpleImage.<dt> - Create the following images with <dt>.dtb linked in' + echo ' simpleImage.<dt> : raw image' + echo ' simpleImage.<dt>.ub : raw image with U-Boot header' + echo ' simpleImage.<dt>.unstrip: ELF (identical to vmlinux)' + echo ' simpleImage.<dt>.strip : stripped ELF' echo ' Targets with <dt> embed a device tree blob inside the image' echo ' These targets support board with firmware that does not' echo ' support passing a device tree directly. Replace <dt> with the' diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile index 7c2f52d4a0e4..49dbd1063d71 100644 --- a/arch/microblaze/boot/Makefile +++ b/arch/microblaze/boot/Makefile @@ -9,15 +9,12 @@ OBJCOPYFLAGS := -R .note -R .comment -R .note.gnu.build-id -O binary $(obj)/linux.bin: vmlinux FORCE $(call if_changed,objcopy) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' $(obj)/linux.bin.ub: $(obj)/linux.bin FORCE $(call if_changed,uimage) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' $(obj)/linux.bin.gz: $(obj)/linux.bin FORCE $(call if_changed,gzip) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' quiet_cmd_cp = CP $< $@$2 cmd_cp = cat $< >$@$2 || (rm -f $@ && echo false) @@ -35,6 +32,5 @@ $(obj)/simpleImage.%: vmlinux FORCE $(call if_changed,objcopy) $(call if_changed,uimage) $(call if_changed,strip,.strip) - @echo 'Kernel: $(UIMAGE_OUT) is ready' ' (#'`cat .version`')' clean-files += simpleImage.*.unstrip linux.bin.ub dts/*.dtb diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8d4470f44b74..7e267d657c56 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -800,7 +800,6 @@ config SIBYTE_SWARM select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT - select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI config SIBYTE_LITTLESUR bool "Sibyte BCM91250C2-LittleSur" @@ -813,6 +812,7 @@ config SIBYTE_LITTLESUR select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN + select ZONE_DMA32 if 64BIT config SIBYTE_SENTOSA bool "Sibyte BCM91250E-Sentosa" @@ -823,7 +823,6 @@ config SIBYTE_SENTOSA select SYS_HAS_CPU_SB1 select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_LITTLE_ENDIAN - select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI config SIBYTE_BIGSUR bool "Sibyte BCM91480B-BigSur" @@ -837,7 +836,6 @@ config SIBYTE_BIGSUR select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT - select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI config SNI_RM bool "SNI RM200/300/400" diff --git a/arch/mips/bcm47xx/workarounds.c b/arch/mips/bcm47xx/workarounds.c index 1a8a07e7a563..46eddbec8d9f 100644 --- a/arch/mips/bcm47xx/workarounds.c +++ b/arch/mips/bcm47xx/workarounds.c @@ -5,9 +5,8 @@ #include <bcm47xx_board.h> #include <bcm47xx.h> -static void __init bcm47xx_workarounds_netgear_wnr3500l(void) +static void __init bcm47xx_workarounds_enable_usb_power(int usb_power) { - const int usb_power = 12; int err; err = gpio_request_one(usb_power, GPIOF_OUT_INIT_HIGH, "usb_power"); @@ -23,7 +22,10 @@ void __init bcm47xx_workarounds(void) switch (board) { case BCM47XX_BOARD_NETGEAR_WNR3500L: - bcm47xx_workarounds_netgear_wnr3500l(); + bcm47xx_workarounds_enable_usb_power(12); + break; + case BCM47XX_BOARD_NETGEAR_WNDR3400_V3: + bcm47xx_workarounds_enable_usb_power(21); break; default: /* No workaround(s) needed */ diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index 7019e2967009..bbbf8057565b 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -84,7 +84,7 @@ void __init prom_init(void) * Here we will start up CPU1 in the background and ask it to * reconfigure itself then go back to sleep. */ - memcpy((void *)0xa0000200, &bmips_smp_movevec, 0x20); + memcpy((void *)0xa0000200, bmips_smp_movevec, 0x20); __sync(); set_c0_cause(C_SW0); cpumask_set_cpu(1, &bmips_booted_mask); diff --git a/arch/mips/bcm63xx/reset.c b/arch/mips/bcm63xx/reset.c index a2af38cf28a7..64574e74cb23 100644 --- a/arch/mips/bcm63xx/reset.c +++ b/arch/mips/bcm63xx/reset.c @@ -120,7 +120,7 @@ #define BCM6368_RESET_DSL 0 #define BCM6368_RESET_SAR SOFTRESET_6368_SAR_MASK #define BCM6368_RESET_EPHY SOFTRESET_6368_EPHY_MASK -#define BCM6368_RESET_ENETSW 0 +#define BCM6368_RESET_ENETSW SOFTRESET_6368_ENETSW_MASK #define BCM6368_RESET_PCM SOFTRESET_6368_PCM_MASK #define BCM6368_RESET_MPI SOFTRESET_6368_MPI_MASK #define BCM6368_RESET_PCIE 0 diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index adce180f3ee4..331b9e0a8072 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -75,6 +75,8 @@ OBJCOPYFLAGS_piggy.o := --add-section=.image=$(obj)/vmlinux.bin.z \ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE $(call if_changed,objcopy) +HOSTCFLAGS_calc_vmlinuz_load_addr.o += $(LINUXINCLUDE) + # Calculate the load address of the compressed kernel image hostprogs-y := calc_vmlinuz_load_addr diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c index 542c3ede9722..d14f75ec8273 100644 --- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c +++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c @@ -13,7 +13,7 @@ #include <stdint.h> #include <stdio.h> #include <stdlib.h> -#include "../../../../include/linux/sizes.h" +#include <linux/sizes.h> int main(int argc, char *argv[]) { diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi index efd5f0722206..39b6269610d4 100644 --- a/arch/mips/boot/dts/qca/ar9331.dtsi +++ b/arch/mips/boot/dts/qca/ar9331.dtsi @@ -99,7 +99,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar7240-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c index 8241fc6aa17d..3839feba68f2 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c +++ b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c @@ -266,7 +266,7 @@ int cvmx_cmd_queue_length(cvmx_cmd_queue_id_t queue_id) } else { union cvmx_pko_mem_debug8 debug8; debug8.u64 = cvmx_read_csr(CVMX_PKO_MEM_DEBUG8); - return debug8.cn58xx.doorbell; + return debug8.cn50xx.doorbell; } case CVMX_CMD_QUEUE_ZIP: case CVMX_CMD_QUEUE_DFA: diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c index 1d92efb82c37..e1e24118c169 100644 --- a/arch/mips/cavium-octeon/octeon-platform.c +++ b/arch/mips/cavium-octeon/octeon-platform.c @@ -501,7 +501,7 @@ static void __init octeon_fdt_set_phy(int eth, int phy_addr) if (phy_addr >= 256 && alt_phy > 0) { const struct fdt_property *phy_prop; struct fdt_property *alt_prop; - u32 phy_handle_name; + fdt32_t phy_handle_name; /* Use the alt phy node instead.*/ phy_prop = fdt_get_property(initial_boot_params, eth, "phy-handle", NULL); diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index c3d0d0a6e044..6895430b5b2c 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -623,7 +623,6 @@ CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m CONFIG_USB_ADUTUX=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYPRESS_CY7C63=m diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 99679e514042..d67a39219fff 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -344,7 +344,6 @@ CONFIG_USB_SERIAL_SAFE_PADDED=y CONFIG_USB_SERIAL_CYBERJACK=m CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c index 6aa264b9856a..7c6151d412bd 100644 --- a/arch/mips/fw/sni/sniprom.c +++ b/arch/mips/fw/sni/sniprom.c @@ -42,7 +42,7 @@ /* O32 stack has to be 8-byte aligned. */ static u64 o32_stk[4096]; -#define O32_STK &o32_stk[sizeof(o32_stk)] +#define O32_STK (&o32_stk[ARRAY_SIZE(o32_stk)]) #define __PROM_O32(fun, arg) fun arg __asm__(#fun); \ __asm__(#fun " = call_o32") diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h index b3e2975f83d3..a564915fddc4 100644 --- a/arch/mips/include/asm/bmips.h +++ b/arch/mips/include/asm/bmips.h @@ -75,11 +75,11 @@ static inline int register_bmips_smp_ops(void) #endif } -extern char bmips_reset_nmi_vec; -extern char bmips_reset_nmi_vec_end; -extern char bmips_smp_movevec; -extern char bmips_smp_int_vec; -extern char bmips_smp_int_vec_end; +extern char bmips_reset_nmi_vec[]; +extern char bmips_reset_nmi_vec_end[]; +extern char bmips_smp_movevec[]; +extern char bmips_smp_int_vec[]; +extern char bmips_smp_int_vec_end[]; extern int bmips_smp_enabled; extern int bmips_cpu_offset; diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 89e9fb7976fe..520ca166cbed 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -73,8 +73,8 @@ extern unsigned long __xchg_called_with_bad_pointer(void) extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size); -static inline unsigned long __xchg(volatile void *ptr, unsigned long x, - int size) +static __always_inline +unsigned long __xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { case 1: @@ -146,8 +146,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size); -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, unsigned int size) +static __always_inline +unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) { switch (size) { case 1: diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h index 493a3cc7c39a..cfdbe66575f4 100644 --- a/arch/mips/include/asm/kexec.h +++ b/arch/mips/include/asm/kexec.h @@ -12,11 +12,11 @@ #include <asm/stacktrace.h> /* Maximum physical address we can use pages from */ -#define KEXEC_SOURCE_MEMORY_LIMIT (0x20000000) +#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) /* Maximum address we can reach in physical address mode */ -#define KEXEC_DESTINATION_MEMORY_LIMIT (0x20000000) +#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL) /* Maximum address we can use for the control code buffer */ -#define KEXEC_CONTROL_MEMORY_LIMIT (0x20000000) +#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL) /* Reserve 3*4096 bytes for board-specific info */ #define KEXEC_CONTROL_PAGE_SIZE (4096 + 3*4096) diff --git a/arch/mips/include/asm/mach-ath79/ar933x_uart.h b/arch/mips/include/asm/mach-ath79/ar933x_uart.h index c2917b39966b..bba2c8837951 100644 --- a/arch/mips/include/asm/mach-ath79/ar933x_uart.h +++ b/arch/mips/include/asm/mach-ath79/ar933x_uart.h @@ -27,8 +27,8 @@ #define AR933X_UART_CS_PARITY_S 0 #define AR933X_UART_CS_PARITY_M 0x3 #define AR933X_UART_CS_PARITY_NONE 0 -#define AR933X_UART_CS_PARITY_ODD 1 -#define AR933X_UART_CS_PARITY_EVEN 2 +#define AR933X_UART_CS_PARITY_ODD 2 +#define AR933X_UART_CS_PARITY_EVEN 3 #define AR933X_UART_CS_IF_MODE_S 2 #define AR933X_UART_CS_IF_MODE_M 0x3 #define AR933X_UART_CS_IF_MODE_NONE 0 diff --git a/arch/mips/include/asm/netlogic/xlr/fmn.h b/arch/mips/include/asm/netlogic/xlr/fmn.h index 5604db3d1836..d79c68fa78d9 100644 --- a/arch/mips/include/asm/netlogic/xlr/fmn.h +++ b/arch/mips/include/asm/netlogic/xlr/fmn.h @@ -301,8 +301,6 @@ static inline int nlm_fmn_send(unsigned int size, unsigned int code, for (i = 0; i < 8; i++) { nlm_msgsnd(dest); status = nlm_read_c2_status0(); - if ((status & 0x2) == 1) - pr_info("Send pending fail!\n"); if ((status & 0x4) == 0) return 0; } diff --git a/arch/mips/include/asm/octeon/cvmx-pko.h b/arch/mips/include/asm/octeon/cvmx-pko.h index 5f47f76ed510..20eb9c46a75a 100644 --- a/arch/mips/include/asm/octeon/cvmx-pko.h +++ b/arch/mips/include/asm/octeon/cvmx-pko.h @@ -611,7 +611,7 @@ static inline void cvmx_pko_get_port_status(uint64_t port_num, uint64_t clear, pko_reg_read_idx.s.index = cvmx_pko_get_base_queue(port_num); cvmx_write_csr(CVMX_PKO_REG_READ_IDX, pko_reg_read_idx.u64); debug8.u64 = cvmx_read_csr(CVMX_PKO_MEM_DEBUG8); - status->doorbell = debug8.cn58xx.doorbell; + status->doorbell = debug8.cn50xx.doorbell; } } diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 9e494f8d9c03..af19d1300a4c 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -25,7 +25,17 @@ extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; extern cpumask_t cpu_foreign_map[]; -#define raw_smp_processor_id() (current_thread_info()->cpu) +static inline int raw_smp_processor_id(void) +{ +#if defined(__VDSO__) + extern int vdso_smp_processor_id(void) + __compiletime_error("VDSO should not call smp_processor_id()"); + return vdso_smp_processor_id(); +#else + return current_thread_info()->cpu; +#endif +} +#define raw_smp_processor_id raw_smp_processor_id /* Map from cpu id to sequential logical cpu number. This will only not be idempotent when cpus failed to come on-line. */ diff --git a/arch/mips/include/uapi/asm/sgidefs.h b/arch/mips/include/uapi/asm/sgidefs.h index 26143e3b7c26..69c3de90c536 100644 --- a/arch/mips/include/uapi/asm/sgidefs.h +++ b/arch/mips/include/uapi/asm/sgidefs.h @@ -12,14 +12,6 @@ #define __ASM_SGIDEFS_H /* - * Using a Linux compiler for building Linux seems logic but not to - * everybody. - */ -#ifndef __linux__ -#error Use a Linux compiler or give up. -#endif - -/* * Definitions for the ISA levels * * With the introduction of MIPS32 / MIPS64 instruction sets definitions diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 6d7f97552200..e1a905515283 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -456,27 +456,27 @@ static unsigned long pin_cfg_bias_disable[] = { static struct pinctrl_map pin_map[] __initdata = { /* NAND pin configuration */ PIN_MAP_MUX_GROUP_DEFAULT("jz4740-nand", - "10010000.jz4740-pinctrl", "nand", "nand-cs1"), + "10010000.pin-controller", "nand-cs1", "nand"), /* fbdev pin configuration */ PIN_MAP_MUX_GROUP("jz4740-fb", PINCTRL_STATE_DEFAULT, - "10010000.jz4740-pinctrl", "lcd", "lcd-8bit"), + "10010000.pin-controller", "lcd-8bit", "lcd"), PIN_MAP_MUX_GROUP("jz4740-fb", PINCTRL_STATE_SLEEP, - "10010000.jz4740-pinctrl", "lcd", "lcd-no-pins"), + "10010000.pin-controller", "lcd-no-pins", "lcd"), /* MMC pin configuration */ PIN_MAP_MUX_GROUP_DEFAULT("jz4740-mmc.0", - "10010000.jz4740-pinctrl", "mmc", "mmc-1bit"), + "10010000.pin-controller", "mmc-1bit", "mmc"), PIN_MAP_MUX_GROUP_DEFAULT("jz4740-mmc.0", - "10010000.jz4740-pinctrl", "mmc", "mmc-4bit"), + "10010000.pin-controller", "mmc-4bit", "mmc"), PIN_MAP_CONFIGS_PIN_DEFAULT("jz4740-mmc.0", - "10010000.jz4740-pinctrl", "PD0", pin_cfg_bias_disable), + "10010000.pin-controller", "PD0", pin_cfg_bias_disable), PIN_MAP_CONFIGS_PIN_DEFAULT("jz4740-mmc.0", - "10010000.jz4740-pinctrl", "PD2", pin_cfg_bias_disable), + "10010000.pin-controller", "PD2", pin_cfg_bias_disable), /* PWM pin configuration */ PIN_MAP_MUX_GROUP_DEFAULT("jz4740-pwm", - "10010000.jz4740-pinctrl", "pwm4", "pwm4"), + "10010000.pin-controller", "pwm4", "pwm4"), }; diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index 97d5239ca47b..428ef2189203 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -80,6 +80,8 @@ static int __populate_cache_leaves(unsigned int cpu) if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED); + this_cpu_ci->cpu_map_populated = true; + return 0; } diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 5f209f111e59..df7ddd246eaa 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -32,7 +32,8 @@ void __init setup_pit_timer(void) static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 1) /* PIT does not scale! */ + if (num_possible_cpus() > 1 || /* PIT does not scale! */ + !clockevent_state_periodic(&i8253_clockevent)) return 0; return clocksource_i8253_init(); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 382d12eb88f0..45fbcbbf2504 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -457,10 +457,10 @@ static void bmips_wr_vec(unsigned long dst, char *start, char *end) static inline void bmips_nmi_handler_setup(void) { - bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec, - &bmips_reset_nmi_vec_end); - bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec, - &bmips_smp_int_vec_end); + bmips_wr_vec(BMIPS_NMI_RESET_VEC, bmips_reset_nmi_vec, + bmips_reset_nmi_vec_end); + bmips_wr_vec(BMIPS_WARM_RESTART_VEC, bmips_smp_int_vec, + bmips_smp_int_vec_end); } struct reset_vec_info { diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c index f7a0645ccb82..6305e91ffc44 100644 --- a/arch/mips/kernel/uprobes.c +++ b/arch/mips/kernel/uprobes.c @@ -112,9 +112,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs) */ aup->resume_epc = regs->cp0_epc + 4; if (insn_has_delay_slot((union mips_instruction) aup->insn[0])) { - unsigned long epc; - - epc = regs->cp0_epc; __compute_return_epc_for_insn(regs, (union mips_instruction) aup->insn[0]); aup->resume_epc = regs->cp0_epc; diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index c4ef1c31e0c4..37caeadb2964 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -156,8 +156,9 @@ static int ltq_eiu_settype(struct irq_data *d, unsigned int type) if (edge) irq_set_handler(d->hwirq, handle_edge_irq); - ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_C) | - (val << (i * 4)), LTQ_EIU_EXIN_C); + ltq_eiu_w32((ltq_eiu_r32(LTQ_EIU_EXIN_C) & + (~(7 << (i * 4)))) | (val << (i * 4)), + LTQ_EIU_EXIN_C); } } diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 0fce4608aa88..12abf14aed4a 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -43,6 +43,10 @@ else $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) endif +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-y += $(call cc-option,-mno-loongson-mmi) + # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c index ffefc1cb2612..98c3a7feb10f 100644 --- a/arch/mips/loongson64/common/serial.c +++ b/arch/mips/loongson64/common/serial.c @@ -110,7 +110,7 @@ static int __init serial_init(void) } module_init(serial_init); -static void __init serial_exit(void) +static void __exit serial_exit(void) { platform_device_unregister(&uart8250_device); } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 91ad023ead8c..60c58005fd20 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -203,7 +203,7 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) int __virt_addr_valid(const volatile void *kaddr) { - unsigned long vaddr = (unsigned long)vaddr; + unsigned long vaddr = (unsigned long)kaddr; if ((vaddr < PAGE_OFFSET) || (vaddr >= MAP_BASE)) return 0; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 79b9f2ad3ff5..b55c74a7f7a4 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -388,6 +388,7 @@ static struct work_registers build_get_work_registers(u32 **p) static void build_restore_work_registers(u32 **p) { if (scratch_reg >= 0) { + uasm_i_ehb(p); UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); return; } @@ -633,7 +634,7 @@ static __maybe_unused void build_convert_pte_to_entrylo(u32 **p, return; } - if (cpu_has_rixi && _PAGE_NO_EXEC) { + if (cpu_has_rixi && !!_PAGE_NO_EXEC) { if (fill_includes_sw_bits) { UASM_i_ROTR(p, reg, reg, ilog2(_PAGE_GLOBAL)); } else { @@ -657,6 +658,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, int restore_scratch) { if (restore_scratch) { + /* + * Ensure the MFC0 below observes the value written to the + * KScratch register by the prior MTC0. + */ + if (scratch_reg >= 0) + uasm_i_ehb(p); + /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16); @@ -923,6 +931,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } if (mode != not_refill && check_for_high_segbits) { uasm_l_large_segbits_fault(l, *p); + + if (mode == refill_scratch && scratch_reg >= 0) + uasm_i_ehb(p); + /* * We get here if we are an xsseg address, or if we are * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary. @@ -1259,6 +1271,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l, UASM_i_MTC0(p, odd, C0_ENTRYLO1); /* load it */ if (c0_scratch_reg >= 0) { + uasm_i_ehb(p); UASM_i_MFC0(p, scratch, c0_kscratch(), c0_scratch_reg); build_tlb_write_entry(p, l, r, tlb_random); uasm_l_leave(l, *p); @@ -1615,15 +1628,17 @@ static void build_setup_pgd(void) uasm_i_dinsm(&p, a0, 0, 29, 64 - 29); uasm_l_tlbl_goaround1(&l, p); UASM_i_SLL(&p, a0, a0, 11); - uasm_i_jr(&p, 31); UASM_i_MTC0(&p, a0, C0_CONTEXT); + uasm_i_jr(&p, 31); + uasm_i_ehb(&p); } else { /* PGD in c0_KScratch */ - uasm_i_jr(&p, 31); if (cpu_has_ldpte) UASM_i_MTC0(&p, a0, C0_PWBASE); else UASM_i_MTC0(&p, a0, c0_kscratch(), pgd_reg); + uasm_i_jr(&p, 31); + uasm_i_ehb(&p); } #else #ifdef CONFIG_SMP @@ -1637,13 +1652,16 @@ static void build_setup_pgd(void) UASM_i_LA_mostly(&p, a2, pgdc); UASM_i_SW(&p, a0, uasm_rel_lo(pgdc), a2); #endif /* SMP */ - uasm_i_jr(&p, 31); /* if pgd_reg is allocated, save PGD also to scratch register */ - if (pgd_reg != -1) + if (pgd_reg != -1) { UASM_i_MTC0(&p, a0, c0_kscratch(), pgd_reg); - else + uasm_i_jr(&p, 31); + uasm_i_ehb(&p); + } else { + uasm_i_jr(&p, 31); uasm_i_nop(&p); + } #endif if (p >= tlbmiss_handler_setup_pgd_end) panic("tlbmiss_handler_setup_pgd space exceeded"); diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 44b925005dd3..4d8cb9bb8365 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1207,8 +1207,6 @@ jmp_cmp: return 0; } -int bpf_jit_enable __read_mostly; - void bpf_jit_compile(struct bpf_prog *fp) { struct jit_ctx ctx; diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 8004bfcfb033..42faa95ce664 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -177,8 +177,6 @@ static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx) (ctx->idx * 4) - 4; } -int bpf_jit_enable __read_mostly; - enum which_ebpf_reg { src_reg, src_reg_no_fp, diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile index 3ef3fb658136..b3d6bf23a662 100644 --- a/arch/mips/sibyte/common/Makefile +++ b/arch/mips/sibyte/common/Makefile @@ -1,5 +1,4 @@ obj-y := cfe.o -obj-$(CONFIG_SWIOTLB) += dma.o obj-$(CONFIG_SIBYTE_BUS_WATCHER) += bus_watcher.o obj-$(CONFIG_SIBYTE_CFE_CONSOLE) += cfe_console.o obj-$(CONFIG_SIBYTE_TBPROF) += sb_tbprof.o diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c deleted file mode 100644 index eb47a94f3583..000000000000 --- a/arch/mips/sibyte/common/dma.c +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * DMA support for Broadcom SiByte platforms. - * - * Copyright (c) 2018 Maciej W. Rozycki - */ - -#include <linux/swiotlb.h> -#include <asm/bootinfo.h> - -void __init plat_swiotlb_setup(void) -{ - swiotlb_init(1); -} diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 1791a44ee570..20aaf77166e8 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -959,12 +959,11 @@ void __init txx9_sramc_init(struct resource *r) goto exit_put; err = sysfs_create_bin_file(&dev->dev.kobj, &dev->bindata_attr); if (err) { - device_unregister(&dev->dev); iounmap(dev->base); - kfree(dev); + device_unregister(&dev->dev); } return; exit_put: + iounmap(dev->base); put_device(&dev->dev); - return; } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index d1a60690e690..24f5f6baf2c0 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -7,7 +7,10 @@ ccflags-vdso := \ $(filter -I%,$(KBUILD_CFLAGS)) \ $(filter -E%,$(KBUILD_CFLAGS)) \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ - $(filter -march=%,$(KBUILD_CFLAGS)) + $(filter -march=%,$(KBUILD_CFLAGS)) \ + $(filter -m%-float,$(KBUILD_CFLAGS)) \ + $(filter -mno-loongson-%,$(KBUILD_CFLAGS)) \ + -D__VDSO__ cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index b16e95a4e875..1107d34e45bf 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -184,7 +184,7 @@ handler: ;\ * occured. in fact they never do. if you need them use * values saved on stack (for SPR_EPC, SPR_ESR) or content * of r4 (for SPR_EEAR). for details look at EXCEPTION_HANDLE() - * in 'arch/or32/kernel/head.S' + * in 'arch/openrisc/kernel/head.S' */ /* =====================================================[ exceptions] === */ diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 90979acdf165..4d878d13b860 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -1551,7 +1551,7 @@ _string_nl: /* * .data section should be page aligned - * (look into arch/or32/kernel/vmlinux.lds) + * (look into arch/openrisc/kernel/vmlinux.lds.S) */ .section .data,"aw" .align 8192 diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S index a4ce3314e78e..b658f77d6369 100644 --- a/arch/parisc/boot/compressed/vmlinux.lds.S +++ b/arch/parisc/boot/compressed/vmlinux.lds.S @@ -40,8 +40,8 @@ SECTIONS #endif _startcode_end = .; - /* bootloader code and data starts behind area of extracted kernel */ - . = (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START); + /* bootloader code and data starts at least behind area of extracted kernel */ + . = MAX(ABSOLUTE(.), (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START)); /* align on next page boundary */ . = ALIGN(4096); diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index eca5b2a1c7e1..f468a5b44508 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -171,6 +171,9 @@ long arch_ptrace(struct task_struct *child, long request, if ((addr & (sizeof(unsigned long)-1)) || addr >= sizeof(struct pt_regs)) break; + if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { + data |= 3; /* ensure userspace privilege */ + } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || (addr >= PT_FR0 && addr <= PT_FR31 + 4) || @@ -232,16 +235,18 @@ long arch_ptrace(struct task_struct *child, long request, static compat_ulong_t translate_usr_offset(compat_ulong_t offset) { - if (offset < 0) - return sizeof(struct pt_regs); - else if (offset <= 32*4) /* gr[0..31] */ - return offset * 2 + 4; - else if (offset <= 32*4+32*8) /* gr[0..31] + fr[0..31] */ - return offset + 32*4; - else if (offset < sizeof(struct pt_regs)/2 + 32*4) - return offset * 2 + 4 - 32*8; + compat_ulong_t pos; + + if (offset < 32*4) /* gr[0..31] */ + pos = offset * 2 + 4; + else if (offset < 32*4+32*8) /* fr[0] ... fr[31] */ + pos = (offset - 32*4) + PT_FR0; + else if (offset < sizeof(struct pt_regs)/2 + 32*4) /* sr[0] ... ipsw */ + pos = (offset - 32*4 - 32*8) * 2 + PT_SR0 + 4; else - return sizeof(struct pt_regs); + pos = sizeof(struct pt_regs); + + return pos; } long compat_arch_ptrace(struct task_struct *child, compat_long_t request, @@ -285,9 +290,12 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, addr = translate_usr_offset(addr); if (addr >= sizeof(struct pt_regs)) break; + if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { + data |= 3; /* ensure userspace privilege */ + } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ - *(__u64 *) ((char *) task_regs(child) + addr) = data; + *(__u32 *) ((char *) task_regs(child) + addr) = data; ret = 0; } else if ((addr >= PT_GR1+4 && addr <= PT_GR31+4) || @@ -500,7 +508,8 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val) return; case RI(iaoq[0]): case RI(iaoq[1]): - regs->iaoq[num - RI(iaoq[0])] = val; + /* set 2 lowest bits to ensure userspace privilege: */ + regs->iaoq[num - RI(iaoq[0])] = val | 3; return; case RI(sar): regs->sar = val; return; diff --git a/arch/parisc/math-emu/cnv_float.h b/arch/parisc/math-emu/cnv_float.h index 933423fa5144..b0db61188a61 100644 --- a/arch/parisc/math-emu/cnv_float.h +++ b/arch/parisc/math-emu/cnv_float.h @@ -60,19 +60,19 @@ ((exponent < (SGL_P - 1)) ? \ (Sall(sgl_value) << (SGL_EXP_LENGTH + 1 + exponent)) : FALSE) -#define Int_isinexact_to_sgl(int_value) (int_value << 33 - SGL_EXP_LENGTH) +#define Int_isinexact_to_sgl(int_value) ((int_value << 33 - SGL_EXP_LENGTH) != 0) #define Sgl_roundnearest_from_int(int_value,sgl_value) \ if (int_value & 1<<(SGL_EXP_LENGTH - 2)) /* round bit */ \ - if ((int_value << 34 - SGL_EXP_LENGTH) || Slow(sgl_value)) \ + if (((int_value << 34 - SGL_EXP_LENGTH) != 0) || Slow(sgl_value)) \ Sall(sgl_value)++ #define Dint_isinexact_to_sgl(dint_valueA,dint_valueB) \ - ((Dintp1(dint_valueA) << 33 - SGL_EXP_LENGTH) || Dintp2(dint_valueB)) + (((Dintp1(dint_valueA) << 33 - SGL_EXP_LENGTH) != 0) || Dintp2(dint_valueB)) #define Sgl_roundnearest_from_dint(dint_valueA,dint_valueB,sgl_value) \ if (Dintp1(dint_valueA) & 1<<(SGL_EXP_LENGTH - 2)) \ - if ((Dintp1(dint_valueA) << 34 - SGL_EXP_LENGTH) || \ + if (((Dintp1(dint_valueA) << 34 - SGL_EXP_LENGTH) != 0) || \ Dintp2(dint_valueB) || Slow(sgl_value)) Sall(sgl_value)++ #define Dint_isinexact_to_dbl(dint_value) \ diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 92a9b5f12f98..f29f682352f0 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -3,7 +3,7 @@ * arch/parisc/mm/ioremap.c * * (C) Copyright 1995 1996 Linus Torvalds - * (C) Copyright 2001-2006 Helge Deller <deller@gmx.de> + * (C) Copyright 2001-2019 Helge Deller <deller@gmx.de> * (C) Copyright 2005 Kyle McMartin <kyle@parisc-linux.org> */ @@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l addr = (void __iomem *) area->addr; if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, phys_addr, pgprot)) { - vfree(addr); + vunmap(addr); return NULL; } @@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l } EXPORT_SYMBOL(__ioremap); -void iounmap(const volatile void __iomem *addr) +void iounmap(const volatile void __iomem *io_addr) { - if (addr > high_memory) - return vfree((void *) (PAGE_MASK & (unsigned long __force) addr)); + unsigned long addr = (unsigned long)io_addr & PAGE_MASK; + + if (is_vmalloc_addr((void *)addr)) + vunmap((void *)addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index e2a5a932c24a..5807c9d8e56d 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -24,8 +24,8 @@ compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ - -fno-strict-aliasing -Os -msoft-float -pipe \ - -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ + -fno-strict-aliasing -Os -msoft-float -mno-altivec -mno-vsx \ + -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ -D$(compress-y) BOOTCC := $(CC) diff --git a/arch/powerpc/boot/dts/bamboo.dts b/arch/powerpc/boot/dts/bamboo.dts index aa68911f6560..084b82ba7493 100644 --- a/arch/powerpc/boot/dts/bamboo.dts +++ b/arch/powerpc/boot/dts/bamboo.dts @@ -268,8 +268,10 @@ /* Outbound ranges, one memory and one IO, * later cannot be changed. Chip supports a second * IO range but we don't use it for now + * The chip also supports a larger memory range but + * it's not naturally aligned, so our code will break */ - ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x40000000 + ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x20000000 0x02000000 0x00000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00100000 0x01000000 0x00000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>; diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index f52c31b1f48f..39155d3b2cef 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -5,6 +5,8 @@ #include <types.h> #include <string.h> +#define INT_MAX ((int)(~0U>>1)) + #include "of.h" typedef u32 uint32_t; diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h index e22e5b3770dd..ebfadd39e192 100644 --- a/arch/powerpc/boot/xz_config.h +++ b/arch/powerpc/boot/xz_config.h @@ -20,10 +20,30 @@ static inline uint32_t swab32p(void *p) #ifdef __LITTLE_ENDIAN__ #define get_le32(p) (*((uint32_t *) (p))) +#define cpu_to_be32(x) swab32(x) +static inline u32 be32_to_cpup(const u32 *p) +{ + return swab32p((u32 *)p); +} #else #define get_le32(p) swab32p(p) +#define cpu_to_be32(x) (x) +static inline u32 be32_to_cpup(const u32 *p) +{ + return *p; +} #endif +static inline uint32_t get_unaligned_be32(const void *p) +{ + return be32_to_cpup(p); +} + +static inline void put_unaligned_be32(u32 val, void *p) +{ + *((u32 *)p) = cpu_to_be32(val); +} + #define memeq(a, b, size) (memcmp(a, b, size) == 0) #define memzero(buf, size) memset(buf, 0, size) diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index ba4c75062d49..2d4444981c2c 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -129,7 +129,10 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); /* Patch sites */ extern s32 patch__call_flush_count_cache; extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; extern long flush_count_cache; +extern long kvm_flush_link_stack; #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 53b31c2bcdf4..e4451b30d7e3 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -45,6 +45,7 @@ extern int machine_check_e500(struct pt_regs *regs); extern int machine_check_e200(struct pt_regs *regs); extern int machine_check_47x(struct pt_regs *regs); int machine_check_8xx(struct pt_regs *regs); +int machine_check_83xx(struct pt_regs *regs); extern void cpu_down_flush_e500v2(void); extern void cpu_down_flush_e500mc(void); @@ -215,7 +216,9 @@ enum { #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) +#define CPU_FTR_P9_TLBIE_STQ_BUG LONG_ASM_CONST(0x0000400000000000) #define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) +#define CPU_FTR_P9_TLBIE_ERAT_BUG LONG_ASM_CONST(0x0001000000000000) #ifndef __ASSEMBLY__ @@ -475,7 +478,8 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \ + CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG) #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \ (~CPU_FTR_SAO)) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 1a944c18c539..3c7d85945229 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -59,8 +59,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, pagefault_enable(); - if (!ret) - *oval = oldval; + *oval = oldval; return ret; } diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 7f74c282710f..fad0e6ff460f 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -21,11 +21,6 @@ #include <asm/opal.h> /* - * For static allocation of some of the structures. - */ -#define IMC_MAX_PMUS 32 - -/* * Compatibility macros for IMC devices */ #define IMC_DTB_COMPAT "ibm,opal-in-memory-counters" @@ -125,4 +120,5 @@ enum { extern int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id); extern void thread_imc_disable(void); +extern int get_max_nest_dev(void); #endif /* __ASM_POWERPC_IMC_PMU_H */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e3ba58f64c3d..5070b34b12fd 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -296,6 +296,7 @@ struct kvm_arch { #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; struct list_head rtas_tokens; + struct mutex rtas_token_lock; DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); #endif #ifdef CONFIG_KVM_MPIC diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 8eb3ebca02df..163970c56e2f 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -266,7 +266,7 @@ int64_t opal_xive_get_vp_info(uint64_t vp, int64_t opal_xive_set_vp_info(uint64_t vp, uint64_t flags, uint64_t report_cl_pair); -int64_t opal_xive_allocate_irq(uint32_t chip_id); +int64_t opal_xive_allocate_irq_raw(uint32_t chip_id); int64_t opal_xive_free_irq(uint32_t girq); int64_t opal_xive_sync(uint32_t type, uint32_t id); int64_t opal_xive_dump(uint32_t type, uint32_t id); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index b991bd31b383..031fc1bb23ac 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -324,6 +324,7 @@ #define PPC_INST_MULLI 0x1c000000 #define PPC_INST_DIVWU 0x7c000396 #define PPC_INST_DIVD 0x7c0003d2 +#define PPC_INST_DIVDU 0x7c000392 #define PPC_INST_RLWINM 0x54000000 #define PPC_INST_RLWIMI 0x50000000 #define PPC_INST_RLDICL 0x78000000 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index b779f3ccd412..05f3c2b3aa0e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -733,6 +733,8 @@ #define SRR1_PROGTRAP 0x00020000 /* Trap */ #define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */ +#define SRR1_MCE_MCP 0x00080000 /* Machine check signal caused interrupt */ + #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ #define HSRR1_DENORM 0x00100000 /* Denorm exception */ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 759597bf0fd8..ccf44c135389 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Software required to flush count cache on context switch #define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull +// Software required to flush link stack on context switch +#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index d89beaba26ff..8b957aabb826 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -213,30 +213,18 @@ * respectively. The result is placed in HIGH_SUM and LOW_SUM. Overflow * (i.e. carry out) is not stored anywhere, and is lost. */ -#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ else \ - __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3" \ + : "=r" (sh), "=&r" (sl) \ + : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl)); \ } while (0) /* sub_ddmmss is used in op-2.h and udivmodti4.c and should be equivalent to @@ -248,44 +236,24 @@ * and LOW_DIFFERENCE. Overflow (i.e. carry out) is not stored anywhere, * and is lost. */ -#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (ah) && (ah) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (ah) && (ah) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ else if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ else \ - __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2" \ + : "=r" (sh), "=&r" (sl) \ + : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \ } while (0) /* asm fragments for mul and div */ @@ -294,13 +262,10 @@ * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype * word product in HIGH_PROD and LOW_PROD. */ -#define umul_ppmm(ph, pl, m0, m1) \ +#define umul_ppmm(ph, pl, m0, m1) \ do { \ USItype __m0 = (m0), __m1 = (m1); \ - __asm__ ("mulhwu %0,%1,%2" \ - : "=r" ((USItype)(ph)) \ - : "%r" (__m0), \ - "r" (__m1)); \ + __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ (pl) = __m0 * __m1; \ } while (0) @@ -312,9 +277,10 @@ * significant bit of DENOMINATOR must be 1, then the pre-processor symbol * UDIV_NEEDS_NORMALIZATION is defined to 1. */ -#define udiv_qrnnd(q, r, n1, n0, d) \ +#define udiv_qrnnd(q, r, n1, n0, d) \ do { \ - UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m; \ + UWtype __d1, __d0, __q1, __q0; \ + UWtype __r1, __r0, __m; \ __d1 = __ll_highpart (d); \ __d0 = __ll_lowpart (d); \ \ @@ -325,7 +291,7 @@ if (__r1 < __m) \ { \ __q1--, __r1 += (d); \ - if (__r1 >= (d)) /* we didn't get carry when adding to __r1 */ \ + if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\ if (__r1 < __m) \ __q1--, __r1 += (d); \ } \ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index bd6d0fb5be9f..3865d1d23597 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -234,7 +234,7 @@ do { \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ @@ -248,7 +248,7 @@ do { \ ({ \ long __gu_err = -EFAULT; \ __long_type(*(ptr)) __gu_val = 0; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ barrier_nospec(); \ @@ -262,7 +262,7 @@ do { \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ @@ -280,6 +280,7 @@ extern unsigned long __copy_tofrom_user(void __user *to, static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { + barrier_nospec(); return __copy_tofrom_user(to, from, n); } #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index 1afe90ade595..674c03350cd1 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -86,6 +86,7 @@ struct vdso_data { __s32 wtom_clock_nsec; struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -107,6 +108,7 @@ struct vdso_data { __s32 wtom_clock_nsec; struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 142b08d40642..5607ce67d178 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -5,8 +5,8 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' -# Disable clang warning for using setjmp without setjmp.h header -CFLAGS_crash.o += $(call cc-disable-warning, builtin-requires-header) +# Avoid clang warnings around longjmp/setjmp declarations +CFLAGS_crash.o += -ffreestanding subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 2e5ea300258a..1bc761e537a9 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -373,6 +373,7 @@ int main(void) OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec); OFFSET(STAMP_XTIME, vdso_data, stamp_xtime); OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction); + OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res); OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size); OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size); OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size); @@ -401,7 +402,6 @@ int main(void) DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 760872916013..da4b0e379238 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1185,6 +1185,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "ppc603", }, +#ifdef CONFIG_PPC_83xx { /* e300c1 (a 603e core, plus some) on 83xx */ .pvr_mask = 0x7fff0000, .pvr_value = 0x00830000, @@ -1195,7 +1196,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .platform = "ppc603", }, { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ @@ -1209,7 +1210,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .platform = "ppc603", }, { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ @@ -1223,7 +1224,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e300", .oprofile_type = PPC_OPROFILE_FSL_EMB, @@ -1240,12 +1241,13 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, + .machine_check = machine_check_83xx, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e300", .oprofile_type = PPC_OPROFILE_FSL_EMB, .platform = "ppc603", }, +#endif { /* default match, we assume split I/D cache & TB (non-601)... */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 2dba206b065a..2357df60de95 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -733,15 +733,45 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) return true; } +/* + * Handle POWER9 broadcast tlbie invalidation issue using + * cpu feature flag. + */ +static __init void update_tlbie_feature_flag(unsigned long pvr) +{ + if (PVR_VER(pvr) == PVR_POWER9) { + /* + * Set the tlbie feature flag for anything below + * Nimbus DD 2.3 and Cumulus DD 1.3 + */ + if ((pvr & 0xe000) == 0) { + /* Nimbus */ + if ((pvr & 0xfff) < 0x203) + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } else if ((pvr & 0xc000) == 0) { + /* Cumulus */ + if ((pvr & 0xfff) < 0x103) + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } else { + WARN_ONCE(1, "Unknown PVR"); + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } + + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_ERAT_BUG; + } +} + static __init void cpufeatures_cpu_quirks(void) { - int version = mfspr(SPRN_PVR); + unsigned long version = mfspr(SPRN_PVR); /* * Not all quirks can be derived from the cpufeatures device tree. */ if ((version & 0xffffff00) == 0x004e0100) cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1; + + update_tlbie_feature_flag(version); } static void __init cpufeatures_setup_finished(void) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 45322b37669a..d2ba7936d0d3 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -361,10 +361,19 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) ptep = find_init_mm_pte(token, &hugepage_shift); if (!ptep) return token; - WARN_ON(hugepage_shift); - pa = pte_pfn(*ptep) << PAGE_SHIFT; - return pa | (token & (PAGE_SIZE-1)); + pa = pte_pfn(*ptep); + + /* On radix we can do hugepage mappings for io, so handle that */ + if (hugepage_shift) { + pa <<= hugepage_shift; + pa |= token & ((1ul << hugepage_shift) - 1); + } else { + pa <<= PAGE_SHIFT; + pa |= token & (PAGE_SIZE - 1); + } + + return pa; } /* diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8545a9523b9b..7339ca4fdc19 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -381,7 +381,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) while (parent) { if (!(parent->type & EEH_PE_INVALID)) break; - parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP); + parent->type &= ~EEH_PE_INVALID; parent = parent->parent; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 12395895b9aa..02a0bf52aec0 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -524,6 +524,7 @@ flush_count_cache: /* Save LR into r9 */ mflr r9 + // Flush the link stack .rept 64 bl .+4 .endr @@ -533,6 +534,11 @@ flush_count_cache: .balign 32 /* Restore LR */ 1: mtlr r9 + + // If we're just flushing the link stack, return here +3: nop + patch_site 3b patch__flush_link_stack_return + li r9,0x7fff mtctr r9 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f65bb53df43b..cdc53fd90597 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -464,6 +464,10 @@ EXC_COMMON_BEGIN(machine_check_handle_early) RFI_TO_USER_OR_KERNEL 9: /* Deliver the machine check to host kernel in V mode. */ +BEGIN_FTR_SECTION + ld r10,ORIG_GPR3(r1) + mtspr SPRN_CFAR,r10 +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) MACHINE_CHECK_HANDLER_WINDUP b machine_check_pSeries @@ -1675,7 +1679,7 @@ handle_page_fault: addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault cmpdi r3,0 - beq+ 12f + beq+ ret_from_except_lite bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD @@ -1690,7 +1694,12 @@ handle_dabr_fault: ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_break -12: b ret_from_except_lite + /* + * do_break() may have changed the NV GPRS while handling a breakpoint. + * If so, we need to restore them with their updated values. Don't use + * ret_from_except_lite here. + */ + b ret_from_except #ifdef CONFIG_PPC_STD_MMU_64 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4f2e18266e34..8c04c51a6e14 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -897,6 +897,7 @@ p_toc: .8byte __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ +__REF start_here_multiplatform: /* set up the TOC */ bl relative_toc @@ -972,6 +973,7 @@ start_here_multiplatform: RFI b . /* prevent speculative execution */ + .previous /* This is where all platforms converge execution */ start_here_common: diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index af7a20dc6e09..80b6caaa9b92 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -785,9 +785,9 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl)); if (tbl) { + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl)); align = 0; if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 3280953a82cf..afe086f48e7c 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -86,7 +86,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 1: dcbst 0,r6 @@ -102,7 +102,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 2: icbi 0,r6 @@ -134,7 +134,7 @@ _GLOBAL_TOC(flush_dcache_range) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 0: dcbst 0,r6 @@ -190,7 +190,7 @@ _GLOBAL(flush_inval_dcache_range) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ sync isync diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 0d790f8432d2..6ca1b3a1e196 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -45,6 +45,8 @@ static unsigned int pci_parse_of_flags(u32 addr0, int bridge) if (addr0 & 0x02000000) { flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) + flags |= IORESOURCE_MEM_64; flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; if (addr0 & 0x40000000) flags |= IORESOURCE_PREFETCH diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b10531372d7f..ba0d4f9a99ba 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -475,13 +475,14 @@ void giveup_all(struct task_struct *tsk) if (!tsk->thread.regs) return; + check_if_tm_restore_required(tsk); + usermsr = tsk->thread.regs->msr; if ((usermsr & msr_all_available) == 0) return; msr_check_and_set(msr_all_available); - check_if_tm_restore_required(tsk); WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); @@ -566,12 +567,11 @@ void flush_all_to_thread(struct task_struct *tsk) if (tsk->thread.regs) { preempt_disable(); BUG_ON(tsk != current); - save_all(tsk); - #ifdef CONFIG_SPE if (tsk->thread.regs->msr & MSR_SPE) tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); #endif + save_all(tsk); preempt_enable(); } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f83056297441..d96b28415090 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -128,7 +128,7 @@ static void __init move_device_tree(void) p = __va(memblock_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = p; - DBG("Moved device tree to 0x%p\n", p); + DBG("Moved device tree to 0x%px\n", p); } DBG("<- move_device_tree\n"); @@ -662,7 +662,7 @@ void __init early_init_devtree(void *params) { phys_addr_t limit; - DBG(" -> early_init_devtree(%p)\n", params); + DBG(" -> early_init_devtree(%px)\n", params); /* Too early to BUG_ON(), do it by hand */ if (!early_init_dt_verify(params)) @@ -722,7 +722,7 @@ void __init early_init_devtree(void *params) memblock_allow_resize(); memblock_dump_all(); - DBG("Phys. mem: %llx\n", memblock_phys_mem_size()); + DBG("Phys. mem: %llx\n", (unsigned long long)memblock_phys_mem_size()); /* We may need to relocate the flat tree, do it now. * FIXME .. and the initrd too? */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 1643e9e53655..a01f83ba739e 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -874,15 +874,17 @@ static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, return 0; for_each_cpu(cpu, cpus) { + struct device *dev = get_cpu_device(cpu); + switch (state) { case DOWN: - cpuret = cpu_down(cpu); + cpuret = device_offline(dev); break; case UP: - cpuret = cpu_up(cpu); + cpuret = device_online(dev); break; } - if (cpuret) { + if (cpuret < 0) { pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", __func__, ((state == UP) ? "up" : "down"), @@ -971,6 +973,8 @@ int rtas_ibm_suspend_me(u64 handle) data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + lock_device_hotplug(); + /* All present CPUs must be online */ cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); cpuret = rtas_online_cpus_mask(offline_mask); @@ -980,6 +984,7 @@ int rtas_ibm_suspend_me(u64 handle) goto out; } + cpu_hotplug_disable(); stop_topology_update(); /* Call function on all CPUs. One of us will make the @@ -994,6 +999,7 @@ int rtas_ibm_suspend_me(u64 handle) printk(KERN_ERR "Error doing global join\n"); start_topology_update(); + cpu_hotplug_enable(); /* Take down CPUs not online prior to suspend */ cpuret = rtas_offline_cpus_mask(offline_mask); @@ -1002,6 +1008,7 @@ int rtas_ibm_suspend_me(u64 handle) __func__); out: + unlock_device_hotplug(); free_cpumask_var(offline_mask); return atomic_read(&data.error); } diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 68d4ec373cfc..f5d6541bf8c2 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -24,11 +24,12 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_HW = 0x4, }; static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; +static bool link_stack_flush_enabled; bool barrier_nospec_enabled; static bool no_nospec; static bool btb_flush_enabled; -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static bool no_spectrev2; #endif @@ -106,7 +107,7 @@ static __init int barrier_nospec_debugfs_init(void) device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static int __init handle_nospectre_v2(char *p) { no_spectrev2 = true; @@ -114,6 +115,9 @@ static int __init handle_nospectre_v2(char *p) return 0; } early_param("nospectre_v2", handle_nospectre_v2); +#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_FSL_BOOK3E void setup_spectre_v2(void) { if (no_spectrev2 || cpu_mitigations_off()) @@ -201,11 +205,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { seq_buf_printf(&s, "Mitigation: Software count cache flush"); if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) seq_buf_printf(&s, " (hardware accelerated)"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else { @@ -366,18 +378,49 @@ static __init int stf_barrier_debugfs_init(void) device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +static void no_count_cache_flush(void) +{ + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); +} + static void toggle_count_cache_flush(bool enable) { - if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) && + !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) + enable = false; + + if (!enable) { patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); - count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; - pr_info("count-cache-flush: software flush disabled.\n"); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP); +#endif + pr_info("link-stack-flush: software flush disabled.\n"); + link_stack_flush_enabled = false; + no_count_cache_flush(); return; } + // This enables the branch from _switch to flush_count_cache patch_branch_site(&patch__call_flush_count_cache, (u64)&flush_count_cache, BRANCH_SET_LINK); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + // This enables the branch from guest_exit_cont to kvm_flush_link_stack + patch_branch_site(&patch__call_kvm_flush_link_stack, + (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); +#endif + + pr_info("link-stack-flush: software flush enabled.\n"); + link_stack_flush_enabled = true; + + // If we just need to flush the link stack, patch an early return + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR); + no_count_cache_flush(); + return; + } + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { count_cache_flush_type = COUNT_CACHE_FLUSH_SW; pr_info("count-cache-flush: full software flush sequence enabled.\n"); @@ -391,7 +434,26 @@ static void toggle_count_cache_flush(bool enable) void setup_count_cache_flush(void) { - toggle_count_cache_flush(true); + bool enable = true; + + if (no_spectrev2 || cpu_mitigations_off()) { + if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || + security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) + pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n"); + + enable = false; + } + + /* + * There's no firmware feature flag/hypervisor bit to tell us we need to + * flush the link stack on context switch. So we set it here if we see + * either of the Spectre v2 mitigations that aim to protect userspace. + */ + if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) || + security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + + toggle_count_cache_flush(enable); } #ifdef CONFIG_DEBUG_FS diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 636ea854808e..a03fc3109fa5 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1279,6 +1279,9 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 927384d85faf..b75bf6e74209 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -741,6 +741,11 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 34b73a262709..5307cb7e12de 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -24,11 +24,19 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_LR 0x70 -#define SL_R12 0x74 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_LR 0xb0 +#define SL_R12 0xb4 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .data @@ -113,6 +121,41 @@ _GLOBAL(swsusp_arch_suspend) mfibatl r4,3 stw r4,SL_IBAT3+4(r11) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r11) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r11) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r11) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r11) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r11) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r11) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r11) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r11) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r11) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r11) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r11) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r11) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r11) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r11) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r11) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + #if 0 /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -278,27 +321,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatu 3,r4 lwz r4,SL_IBAT3+4(r11) mtibatl 3,r4 -#endif - BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r11) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r11) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r11) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r11) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r11) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r11) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r11) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r11) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r11) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r11) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r11) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r11) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r11) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r11) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r11) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r11) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) +#endif /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index fe6f3a285455..14f3f28a089e 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -920,6 +920,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec; vdso_data->stamp_xtime = xt; vdso_data->stamp_sec_fraction = frac_sec; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++(vdso_data->tb_update_count); } @@ -984,10 +985,14 @@ static void register_decrementer_clockevent(int cpu) *dec = decrementer_clockevent; dec->cpumask = cpumask_of(cpu); + clockevents_config_and_register(dec, ppc_tb_freq, 2, decrementer_max); + printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n", dec->name, dec->mult, dec->shift, cpu); - clockevents_register_device(dec); + /* Set values for KVM, see kvm_emulate_dec() */ + decrementer_clockevent.mult = dec->mult; + decrementer_clockevent.shift = dec->shift; } static void enable_large_decrementer(void) @@ -1035,18 +1040,7 @@ static void __init set_decrementer_max(void) static void __init init_decrementer_clockevent(void) { - int cpu = smp_processor_id(); - - clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4); - - decrementer_clockevent.max_delta_ns = - clockevent_delta2ns(decrementer_max, &decrementer_clockevent); - decrementer_clockevent.max_delta_ticks = decrementer_max; - decrementer_clockevent.min_delta_ns = - clockevent_delta2ns(2, &decrementer_clockevent); - decrementer_clockevent.min_delta_ticks = 2; - - register_decrementer_clockevent(cpu); + register_decrementer_clockevent(smp_processor_id()); } void secondary_cpu_time_init(void) diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 3745113fcc65..2a7eb5452aba 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -37,6 +37,7 @@ data_page_branch: mtlr r0 addi r3, r3, __kernel_datapage_offset-data_page_branch lwz r0,0(r3) + .cfi_restore lr add r3,r0,r3 blr .cfi_endproc diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 769c2624e0a6..03a65fee8020 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -139,6 +139,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) */ 99: li r0,__NR_clock_gettime + .cfi_restore lr sc blr .cfi_endproc @@ -159,12 +160,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl __get_datapage@local /* get data page */ + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpli cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l stw r3,TSPC32_TV_SEC(r4) stw r5,TSPC32_TV_NSEC(r4) blr diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 69c5af2b3c96..228a4a2383d6 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -39,7 +39,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 @@ -56,7 +56,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index abf17feffe40..bf9668691511 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -37,6 +37,7 @@ data_page_branch: mtlr r0 addi r3, r3, __kernel_datapage_offset-data_page_branch lwz r0,0(r3) + .cfi_restore lr add r3,r0,r3 blr .cfi_endproc diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 382021324883..c973378e1f2b 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -124,6 +124,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) */ 99: li r0,__NR_clock_gettime + .cfi_restore lr sc blr .cfi_endproc @@ -144,12 +145,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl V_LOCAL_FUNC(__get_datapage) + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpldi cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l std r3,TSPC64_TV_SEC(r4) std r5,TSPC64_TV_NSEC(r4) blr diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 72d977e30952..1eda81249937 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -79,8 +79,11 @@ void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) { if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { ulong pc = kvmppc_get_pc(vcpu); + ulong lr = kvmppc_get_lr(vcpu); if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK); + if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) + kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK); vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK; } } @@ -836,6 +839,7 @@ int kvmppc_core_init_vm(struct kvm *kvm) #ifdef CONFIG_PPC64 INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables); INIT_LIST_HEAD(&kvm->arch.rtas_tokens); + mutex_init(&kvm->arch.rtas_token_lock); #endif return kvm->arch.kvm_ops->init_vm(kvm); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 27a41695fcfd..7f8f2a0189df 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -160,6 +160,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, asm volatile("ptesync": : :"memory"); asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1) : : "r" (addr), "r" (kvm->arch.lpid) : "memory"); + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) + asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1) + : : "r" (addr), "r" (kvm->arch.lpid) : "memory"); asm volatile("ptesync": : :"memory"); } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index e14cec6bc339..5e4446296021 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -404,7 +404,7 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, long ret; if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir))) - return H_HARDWARE; + return H_TOO_HARD; if (dir == DMA_NONE) return H_SUCCESS; @@ -434,15 +434,15 @@ long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl, return H_TOO_HARD; if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa))) - return H_HARDWARE; + return H_TOO_HARD; if (mm_iommu_mapped_inc(mem)) - return H_CLOSED; + return H_TOO_HARD; ret = iommu_tce_xchg(tbl, entry, &hpa, &dir); if (WARN_ON_ONCE(ret)) { mm_iommu_mapped_dec(mem); - return H_HARDWARE; + return H_TOO_HARD; } if (dir != DMA_NONE) @@ -566,8 +566,10 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (kvmppc_gpa_to_ua(vcpu->kvm, tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), - &ua, NULL)) - return H_PARAMETER; + &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { ret = kvmppc_tce_iommu_map(vcpu->kvm, diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 648cf6c01348..c75e5664fe3d 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -264,14 +264,14 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, &hpa))) - return H_HARDWARE; + return H_TOO_HARD; pua = (void *) vmalloc_to_phys(pua); if (WARN_ON_ONCE_RM(!pua)) return H_HARDWARE; if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) - return H_CLOSED; + return H_TOO_HARD; ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); if (ret) { @@ -448,7 +448,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, rmap = (void *) vmalloc_to_phys(rmap); if (WARN_ON_ONCE_RM(!rmap)) - return H_HARDWARE; + return H_TOO_HARD; /* * Synchronize with the MMU notifier callbacks in @@ -475,8 +475,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_gpa_to_ua(vcpu->kvm, tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), - &ua, NULL)) - return H_PARAMETER; + &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 58746328b9bd..7de26809340a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -392,12 +392,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu) static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) { - struct kvm_vcpu *ret; - - mutex_lock(&kvm->lock); - ret = kvm_get_vcpu_by_id(kvm, id); - mutex_unlock(&kvm->lock); - return ret; + return kvm_get_vcpu_by_id(kvm, id); } static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa) @@ -1258,7 +1253,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, struct kvmppc_vcore *vc = vcpu->arch.vcore; u64 mask; - mutex_lock(&kvm->lock); spin_lock(&vc->lock); /* * If ILE (interrupt little-endian) has changed, update the @@ -1298,7 +1292,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, mask &= 0xFFFFFFFF; vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); - mutex_unlock(&kvm->lock); } static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, @@ -1363,7 +1356,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.pspb); break; case KVM_REG_PPC_DPDES: - *val = get_reg_val(id, vcpu->arch.vcore->dpdes); + /* + * On POWER9, where we are emulating msgsndp etc., + * we return 1 bit for each vcpu, which can come from + * either vcore->dpdes or doorbell_request. + * On POWER8, doorbell_request is 0. + */ + *val = get_reg_val(id, vcpu->arch.vcore->dpdes | + vcpu->arch.doorbell_request); break; case KVM_REG_PPC_VTB: *val = get_reg_val(id, vcpu->arch.vcore->vtb); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 4962d537c186..669b547385f3 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -429,6 +429,37 @@ static inline int try_lock_tlbie(unsigned int *lock) return old == 0; } +static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid) +{ + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + /* Radix flush for a hash guest */ + + unsigned long rb,rs,prs,r,ric; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = 0; /* lpid = 0 */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + ric = 0; /* RIC_FLSUH_TLB */ + + /* + * Need the extra ptesync to make sure we don't + * re-order the tlbie + */ + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), + "i"(ric), "r"(rs) : "memory"); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : : + "r" (rb_value), "r" (lpid)); + } +} + static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, long npages, int global, bool need_sync) { @@ -448,6 +479,8 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : : "r" (rbvalues[i]), "r" (kvm->arch.lpid)); } + + fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); kvm->arch.tlbie_lock = 0; } else { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 663a398449b7..46ea42f40334 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -18,6 +18,7 @@ */ #include <asm/ppc_asm.h> +#include <asm/code-patching-asm.h> #include <asm/kvm_asm.h> #include <asm/reg.h> #include <asm/mmu.h> @@ -1445,6 +1446,10 @@ mc_cont: 1: #endif /* CONFIG_KVM_XICS */ + /* Possibly flush the link stack here. */ +1: nop + patch_site 1b patch__call_kvm_flush_link_stack + stw r12, STACK_SLOT_TRAP(r1) mr r3, r12 /* Increment exit count, poke other threads to exit */ @@ -1957,6 +1962,28 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) mtlr r0 blr +.balign 32 +.global kvm_flush_link_stack +kvm_flush_link_stack: + /* Save LR into r0 */ + mflr r0 + + /* Flush the link stack. On Power8 it's up to 32 entries in size. */ + .rept 32 + bl .+4 + .endr + + /* And on Power9 it's up to 64. */ +BEGIN_FTR_SECTION + .rept 32 + bl .+4 + .endr +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + /* Restore LR */ + mtlr r0 + blr + /* * Check whether an HDSI is an HPTE not found fault or something else. * If it is an HPTE not found fault that is due to the guest accessing diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 2d3b2b1cc272..8f2355138f80 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -146,7 +146,7 @@ static int rtas_token_undefine(struct kvm *kvm, char *name) { struct rtas_token_definition *d, *tmp; - lockdep_assert_held(&kvm->lock); + lockdep_assert_held(&kvm->arch.rtas_token_lock); list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) { if (rtas_name_matches(d->handler->name, name)) { @@ -167,7 +167,7 @@ static int rtas_token_define(struct kvm *kvm, char *name, u64 token) bool found; int i; - lockdep_assert_held(&kvm->lock); + lockdep_assert_held(&kvm->arch.rtas_token_lock); list_for_each_entry(d, &kvm->arch.rtas_tokens, list) { if (d->token == token) @@ -206,14 +206,14 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp) if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.rtas_token_lock); if (args.token) rc = rtas_token_define(kvm, args.name, args.token); else rc = rtas_token_undefine(kvm, args.name); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.rtas_token_lock); return rc; } @@ -245,7 +245,7 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) orig_rets = args.rets; args.rets = &args.args[be32_to_cpu(args.nargs)]; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.rtas_token_lock); rc = -ENOENT; list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) { @@ -256,7 +256,7 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) } } - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.rtas_token_lock); if (rc == 0) { args.rets = orig_rets; @@ -282,8 +282,6 @@ void kvmppc_rtas_tokens_free(struct kvm *kvm) { struct rtas_token_definition *d, *tmp; - lockdep_assert_held(&kvm->lock); - list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) { list_del(&d->list); kfree(d); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 3c75eee45edf..46f99fc1901c 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1001,20 +1001,22 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) /* Mask the VP IPI */ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01); - /* Disable the VP */ - xive_native_disable_vp(xc->vp_id); - - /* Free the queues & associated interrupts */ + /* Free escalations */ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { - struct xive_q *q = &xc->queues[i]; - - /* Free the escalation irq */ if (xc->esc_virq[i]) { free_irq(xc->esc_virq[i], vcpu); irq_dispose_mapping(xc->esc_virq[i]); kfree(xc->esc_virq_names[i]); } - /* Free the queue */ + } + + /* Disable the VP */ + xive_native_disable_vp(xc->vp_id); + + /* Free the queues */ + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { + struct xive_q *q = &xc->queues[i]; + xive_native_disable_queue(xc->vp_id, q, i); if (q->qpage) { free_pages((unsigned long)q->qpage, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 47d45733a346..af1f065dc9f3 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -58,6 +58,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions) || kvm_request_pending(v); } +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return false; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 52863deed65d..5fc8a010fdf0 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -581,21 +581,22 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) switch (regs->trap) { case 0x300: case 0x380: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "data at address 0x%08lx\n", regs->dar); + pr_alert("BUG: %s at 0x%08lx\n", + regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" : + "Unable to handle kernel data access", regs->dar); break; case 0x400: case 0x480: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "instruction fetch\n"); + pr_alert("BUG: Unable to handle kernel instruction fetch%s", + regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n"); break; case 0x600: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "unaligned access at address 0x%08lx\n", regs->dar); + pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n", + regs->dar); break; default: - printk(KERN_ALERT "Unable to handle kernel paging request for " - "unknown fault\n"); + pr_alert("BUG: Unable to handle unknown paging fault at 0x%08lx\n", + regs->dar); break; } printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n", diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 640cf566e986..a4b6efbf667b 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -104,6 +104,37 @@ static inline unsigned long ___tlbie(unsigned long vpn, int psize, return va; } +static inline void fixup_tlbie_vpn(unsigned long vpn, int psize, + int apsize, int ssize) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + /* Radix flush for a hash guest */ + + unsigned long rb,rs,prs,r,ric; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = 0; /* lpid = 0 */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + ric = 0; /* RIC_FLSUH_TLB */ + + /* + * Need the extra ptesync to make sure we don't + * re-order the tlbie + */ + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), + "i"(ric), "r"(rs) : "memory"); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + /* Need the extra ptesync to ensure we don't reorder tlbie*/ + asm volatile("ptesync": : :"memory"); + ___tlbie(vpn, psize, apsize, ssize); + } +} + static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) { unsigned long rb; @@ -181,6 +212,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, asm volatile("ptesync": : :"memory"); } else { __tlbie(vpn, psize, apsize, ssize); + fixup_tlbie_vpn(vpn, psize, apsize, ssize); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } if (lock_tlbie && !use_local) @@ -674,7 +706,7 @@ static void native_hpte_clear(void) */ static void native_flush_hash_range(unsigned long number, int local) { - unsigned long vpn; + unsigned long vpn = 0; unsigned long hash, index, hidx, shift, slot; struct hash_pte *hptep; unsigned long hpte_v; @@ -746,6 +778,10 @@ static void native_flush_hash_range(unsigned long number, int local) __tlbie(vpn, psize, psize, ssize); } pte_iterate_hashed_end(); } + /* + * Just do one more with the last used values. + */ + fixup_tlbie_vpn(vpn, psize, psize, ssize); asm volatile("eieio; tlbsync; ptesync":::"memory"); if (lock_tlbie) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 87687e46b48b..58c14749bb0c 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -35,6 +35,7 @@ #include <linux/memblock.h> #include <linux/context_tracking.h> #include <linux/libfdt.h> +#include <linux/cpu.h> #include <asm/debugfs.h> #include <asm/processor.h> @@ -1852,10 +1853,16 @@ static int hpt_order_get(void *data, u64 *val) static int hpt_order_set(void *data, u64 val) { + int ret; + if (!mmu_hash_ops.resize_hpt) return -ENODEV; - return mmu_hash_ops.resize_hpt(val); + cpus_read_lock(); + ret = mmu_hash_ops.resize_hpt(val); + cpus_read_unlock(); + + return ret; } DEFINE_SIMPLE_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 17ae5c15a9e0..ba02305f121e 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -442,14 +442,6 @@ void __init radix__early_init_devtree(void) mmu_psize_defs[MMU_PAGE_64K].shift = 16; mmu_psize_defs[MMU_PAGE_64K].ap = 0x5; found: -#ifdef CONFIG_SPARSEMEM_VMEMMAP - if (mmu_psize_defs[MMU_PAGE_2M].shift) { - /* - * map vmemmap using 2M if available - */ - mmu_vmemmap_psize = MMU_PAGE_2M; - } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ return; } @@ -527,7 +519,13 @@ void __init radix__early_init_mmu(void) #ifdef CONFIG_SPARSEMEM_VMEMMAP /* vmemmap mapping */ - mmu_vmemmap_psize = mmu_virtual_psize; + if (mmu_psize_defs[MMU_PAGE_2M].shift) { + /* + * map vmemmap using 2M if available + */ + mmu_vmemmap_psize = MMU_PAGE_2M; + } else + mmu_vmemmap_psize = mmu_virtual_psize; #endif /* * initialize page table size diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 12f95b1f7d07..48ed34d52ffd 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -491,6 +491,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0); } + /* do we need fixup here ?*/ asm volatile("eieio; tlbsync; ptesync" : : : "memory"); } EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 2a049fb8523d..96c52271e9c2 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -52,7 +52,7 @@ struct batrange { /* stores address ranges mapped by BATs */ phys_addr_t v_block_mapped(unsigned long va) { int b; - for (b = 0; b < 4; ++b) + for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b) if (va >= bat_addrs[b].start && va < bat_addrs[b].limit) return bat_addrs[b].phys + (va - bat_addrs[b].start); return 0; @@ -64,7 +64,7 @@ phys_addr_t v_block_mapped(unsigned long va) unsigned long p_block_mapped(phys_addr_t pa) { int b; - for (b = 0; b < 4; ++b) + for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b) if (pa >= bat_addrs[b].phys && pa < (bat_addrs[b].limit-bat_addrs[b].start) +bat_addrs[b].phys) diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 6d9bf014b3e7..2502fe3bfb54 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -315,7 +315,7 @@ void slb_initialize(void) #endif } - get_paca()->stab_rr = SLB_NUM_BOLTED; + get_paca()->stab_rr = SLB_NUM_BOLTED - 1; lflags = SLB_VSID_KERNEL | linear_llp; vflags = SLB_VSID_KERNEL | vmalloc_llp; diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 4b295cfd5f7e..41e782f126d6 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -23,6 +23,37 @@ #define RIC_FLUSH_PWC 1 #define RIC_FLUSH_ALL 2 +static inline void __tlbie_va(unsigned long va, unsigned long pid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = pid << PPC_BITLSHIFT(31); + prs = 1; /* process scoped */ + r = 1; /* raidx format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + + +static inline void fixup_tlbie_va(unsigned long va, unsigned long pid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, 0, ap, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, pid, ap, RIC_FLUSH_TLB); + } +} + static inline void __tlbiel_pid(unsigned long pid, int set, unsigned long ric) { @@ -68,22 +99,64 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); } -static inline void _tlbie_pid(unsigned long pid, unsigned long ric) +static inline void __tlbie_pid(unsigned long pid, unsigned long ric) { unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ - r = 1; /* raidx format */ + r = 1; /* radix format */ - asm volatile("ptesync": : :"memory"); asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - asm volatile("eieio; tlbsync; ptesync": : :"memory"); trace_tlbie(0, 0, rb, rs, ric, prs, r); } +static inline void fixup_tlbie_pid(unsigned long pid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_pid(0, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB); + } +} + +static inline void _tlbie_pid(unsigned long pid, unsigned long ric) +{ + asm volatile("ptesync": : :"memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid(pid, RIC_FLUSH_TLB); + fixup_tlbie_pid(pid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid(pid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid(pid, RIC_FLUSH_ALL); + fixup_tlbie_pid(pid); + } + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} + static inline void _tlbiel_va(unsigned long va, unsigned long pid, unsigned long ap, unsigned long ric) { @@ -105,19 +178,10 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, static inline void _tlbie_va(unsigned long va, unsigned long pid, unsigned long ap, unsigned long ric) { - unsigned long rb,rs,prs,r; - - rb = va & ~(PPC_BITMASK(52, 63)); - rb |= ap << PPC_BITLSHIFT(58); - rs = pid << PPC_BITLSHIFT(31); - prs = 1; /* process scoped */ - r = 1; /* raidx format */ - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + __tlbie_va(va, pid, ap, ric); + fixup_tlbie_va(va, pid, ap); asm volatile("eieio; tlbsync; ptesync": : :"memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); } /* diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 68dece206048..e5c1d30ee968 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -116,7 +116,7 @@ ___PPC_RA(a) | IMM_L(i)) #define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | ___PPC_RT(d) | \ ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_DIVD(d, a, b) EMIT(PPC_INST_DIVD | ___PPC_RT(d) | \ +#define PPC_DIVDU(d, a, b) EMIT(PPC_INST_DIVDU | ___PPC_RT(d) | \ ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_AND(d, a, b) EMIT(PPC_INST_AND | ___PPC_RA(d) | \ ___PPC_RS(a) | ___PPC_RB(b)) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index f760494ecd66..a9636d8cba15 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -18,8 +18,6 @@ #include "bpf_jit32.h" -int bpf_jit_enable __read_mostly; - static inline void bpf_flush_icache(void *start, void *end) { smp_wmb(); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 3a21d3956ad4..28434040cfb6 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -21,8 +21,6 @@ #include "bpf_jit64.h" -int bpf_jit_enable __read_mostly; - static void bpf_jit_fill_ill_insns(void *area, unsigned int size) { memset32(area, BREAKPOINT_INSTRUCTION, size/4); @@ -415,12 +413,12 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, PPC_LI(b2p[BPF_REG_0], 0); PPC_JMP(exit_addr); if (BPF_OP(code) == BPF_MOD) { - PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg); + PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg); PPC_MULD(b2p[TMP_REG_1], src_reg, b2p[TMP_REG_1]); PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]); } else - PPC_DIVD(dst_reg, dst_reg, src_reg); + PPC_DIVDU(dst_reg, dst_reg, src_reg); break; case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */ case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */ @@ -448,7 +446,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, break; case BPF_ALU64: if (BPF_OP(code) == BPF_MOD) { - PPC_DIVD(b2p[TMP_REG_2], dst_reg, + PPC_DIVDU(b2p[TMP_REG_2], dst_reg, b2p[TMP_REG_1]); PPC_MULD(b2p[TMP_REG_1], b2p[TMP_REG_1], @@ -456,7 +454,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]); } else - PPC_DIVD(dst_reg, dst_reg, + PPC_DIVDU(dst_reg, dst_reg, b2p[TMP_REG_1]); break; } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 994e4392cac5..a0b4c22d963a 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -26,7 +26,7 @@ */ static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); -static struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS]; +static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; struct imc_pmu_ref *nest_imc_refc; static int nest_pmus; @@ -286,13 +286,14 @@ static struct imc_pmu_ref *get_nest_pmu_ref(int cpu) static void nest_change_cpu_context(int old_cpu, int new_cpu) { struct imc_pmu **pn = per_nest_pmu_arr; - int i; if (old_cpu < 0 || new_cpu < 0) return; - for (i = 0; *pn && i < IMC_MAX_PMUS; i++, pn++) + while (*pn) { perf_pmu_migrate_context(&(*pn)->pmu, old_cpu, new_cpu); + pn++; + } } static int ppc_nest_imc_cpu_offline(unsigned int cpu) @@ -1188,6 +1189,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); + kfree(per_nest_pmu_arr); } if (nest_pmus > 0) @@ -1236,6 +1238,13 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent, return -ENOMEM; /* Needed for hotplug/migration */ + if (!per_nest_pmu_arr) { + per_nest_pmu_arr = kcalloc(get_max_nest_dev() + 1, + sizeof(struct imc_pmu *), + GFP_KERNEL); + if (!per_nest_pmu_arr) + return -ENOMEM; + } per_nest_pmu_arr[pmu_index] = pmu_ptr; break; case IMC_DOMAIN_CORE: @@ -1318,6 +1327,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id ret = nest_pmu_cpumask_init(); if (ret) { mutex_unlock(&nest_init_lock); + kfree(nest_imc_refc); + kfree(per_nest_pmu_arr); goto err_free; } } diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index cf9c35aa0cf4..7ecea7143e58 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -150,6 +150,14 @@ static bool is_thresh_cmp_valid(u64 event) return true; } +static unsigned int dc_ic_rld_quad_l1_sel(u64 event) +{ + unsigned int cache; + + cache = (event >> EVENT_CACHE_SEL_SHIFT) & MMCR1_DC_IC_QUAL_MASK; + return cache; +} + static inline u64 isa207_find_source(u64 idx, u32 sub_idx) { u64 ret = PERF_MEM_NA; @@ -290,10 +298,10 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) * have a cache selector of zero. The bank selector (bit 3) is * irrelevant, as long as the rest of the value is 0. */ - if (cache & 0x7) + if (!cpu_has_feature(CPU_FTR_ARCH_300) && (cache & 0x7)) return -1; - } else if (event & EVENT_IS_L1) { + } else if (cpu_has_feature(CPU_FTR_ARCH_300) || (event & EVENT_IS_L1)) { mask |= CNST_L1_QUAL_MASK; value |= CNST_L1_QUAL_VAL(cache); } @@ -396,11 +404,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev, /* In continuous sampling mode, update SDAR on TLB miss */ mmcra_sdar_mode(event[i], &mmcra); - if (event[i] & EVENT_IS_L1) { - cache = event[i] >> EVENT_CACHE_SEL_SHIFT; - mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT; - cache >>= 1; - mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT; + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + cache = dc_ic_rld_quad_l1_sel(event[i]); + mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT; + } else { + if (event[i] & EVENT_IS_L1) { + cache = dc_ic_rld_quad_l1_sel(event[i]); + mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT; + } } if (is_event_marked(event[i])) { diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 6c737d675792..493e5cc5fa8a 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -232,8 +232,8 @@ #define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) #define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8) #define MMCR1_FAB_SHIFT 36 -#define MMCR1_DC_QUAL_SHIFT 47 -#define MMCR1_IC_QUAL_SHIFT 46 +#define MMCR1_DC_IC_QUAL_MASK 0x3 +#define MMCR1_DC_IC_QUAL_SHIFT 46 /* MMCR1 Combine bits macro for power9 */ #define p9_MMCR1_COMBINE_SHIFT(pmc) (38 - ((pmc - 1) * 2)) diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/4xx/uic.c index 8b4dd0da0839..9e27cfe27026 100644 --- a/arch/powerpc/platforms/4xx/uic.c +++ b/arch/powerpc/platforms/4xx/uic.c @@ -158,6 +158,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) mtdcr(uic->dcrbase + UIC_PR, pr); mtdcr(uic->dcrbase + UIC_TR, tr); + mtdcr(uic->dcrbase + UIC_SR, ~mask); raw_spin_unlock_irqrestore(&uic->lock, flags); diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index d75c9816a5c9..2b6589fe812d 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -14,6 +14,7 @@ #include <linux/of_platform.h> #include <linux/pci.h> +#include <asm/debug.h> #include <asm/io.h> #include <asm/hw_irq.h> #include <asm/ipic.h> @@ -150,3 +151,19 @@ void __init mpc83xx_setup_arch(void) mpc83xx_setup_pci(); } + +int machine_check_83xx(struct pt_regs *regs) +{ + u32 mask = 1 << (31 - IPIC_MCP_WDT); + + if (!(regs->msr & SRR1_MCE_MCP) || !(ipic_get_mcp_status() & mask)) + return machine_check_generic(regs); + ipic_clear_mcp_status(mask); + + if (debugger_fault_handler(regs)) + return 1; + + die("Watchdog NMI Reset", regs, 0); + + return 1; +} diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index 1c2802fabd57..c856cd7fcdc4 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -37,10 +37,18 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_R12 0x70 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_R12 0xb0 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .text @@ -125,6 +133,41 @@ _GLOBAL(low_sleep_handler) mfibatl r4,3 stw r4,SL_IBAT3+4(r1) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r1) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r1) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r1) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r1) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r1) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r1) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r1) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r1) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r1) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r1) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r1) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r1) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r1) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r1) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r1) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r1) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -325,22 +368,37 @@ grackle_wake_up: mtibatl 3,r4 BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r1) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r1) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r1) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r1) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r1) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r1) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r1) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r1) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r1) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r1) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r1) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r1) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r1) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r1) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r1) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r1) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 8864065eba22..fa2965c96155 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -548,8 +548,8 @@ static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) static int pnv_eeh_get_phb_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result = 0; @@ -587,8 +587,8 @@ static int pnv_eeh_get_phb_state(struct eeh_pe *pe) static int pnv_eeh_get_pe_state(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; s64 rc; int result; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index c9a6d4f3403c..cfbd242c3e01 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -99,6 +99,7 @@ static int change_memblock_state(struct memory_block *mem, void *arg) return 0; } +/* called with device_hotplug_lock held */ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) { u64 end_pfn = start_pfn + nr_pages - 1; @@ -139,6 +140,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) /* Trace memory needs to be aligned to the size */ end_pfn = round_down(end_pfn - nr_pages, nr_pages); + lock_device_hotplug(); for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) { if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) { /* @@ -147,7 +149,6 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) * we never try to remove memory that spans two iomem * resources. */ - lock_device_hotplug(); end_pfn = base_pfn + nr_pages; for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) { remove_memory(nid, pfn << PAGE_SHIFT, bytes); @@ -156,6 +157,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) return base_pfn << PAGE_SHIFT; } } + unlock_device_hotplug(); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 6914b289c86b..dad23cd8a1de 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -87,6 +87,10 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) struct imc_pmu *pmu_ptr; u32 offset; + /* Return for unknown domain */ + if (domain < 0) + return -EINVAL; + /* memory for pmu */ pmu_ptr = kzalloc(sizeof(struct imc_pmu), GFP_KERNEL); if (!pmu_ptr) @@ -155,6 +159,22 @@ static void disable_core_pmu_counters(void) put_online_cpus(); } +int get_max_nest_dev(void) +{ + struct device_node *node; + u32 pmu_units = 0, type; + + for_each_compatible_node(node, NULL, IMC_DTB_UNIT_COMPAT) { + if (of_property_read_u32(node, "type", &type)) + continue; + + if (type == IMC_TYPE_CHIP) + pmu_units++; + } + + return pmu_units; +} + static int opal_imc_counters_probe(struct platform_device *pdev) { struct device_node *imc_dev = pdev->dev.of_node; diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 8c1ede2d3f7e..b12a75a0ee8b 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,7 +301,7 @@ OPAL_CALL(opal_xive_set_queue_info, OPAL_XIVE_SET_QUEUE_INFO); OPAL_CALL(opal_xive_donate_page, OPAL_XIVE_DONATE_PAGE); OPAL_CALL(opal_xive_alloc_vp_block, OPAL_XIVE_ALLOCATE_VP_BLOCK); OPAL_CALL(opal_xive_free_vp_block, OPAL_XIVE_FREE_VP_BLOCK); -OPAL_CALL(opal_xive_allocate_irq, OPAL_XIVE_ALLOCATE_IRQ); +OPAL_CALL(opal_xive_allocate_irq_raw, OPAL_XIVE_ALLOCATE_IRQ); OPAL_CALL(opal_xive_free_irq, OPAL_XIVE_FREE_IRQ); OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO); OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index c8a743af6bf5..597fcbf7a39e 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -617,7 +617,10 @@ static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj, bin_attr->size); } -static BIN_ATTR_RO(symbol_map, 0); +static struct bin_attribute symbol_map_attr = { + .attr = {.name = "symbol_map", .mode = 0400}, + .read = symbol_map_read +}; static void opal_export_symmap(void) { @@ -634,10 +637,10 @@ static void opal_export_symmap(void) return; /* Setup attributes */ - bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0])); - bin_attr_symbol_map.size = be64_to_cpu(syms[1]); + symbol_map_attr.private = __va(be64_to_cpu(syms[0])); + symbol_map_attr.size = be64_to_cpu(syms[1]); - rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map); + rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr); if (rc) pr_warn("Error %d creating OPAL symbols file\n", rc); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index ddef22e00ddd..d3d5796f7df6 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -598,8 +598,8 @@ static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt) static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no) { struct pnv_ioda_pe *slave, *pe; - u8 fstate, state; - __be16 pcierr; + u8 fstate = 0, state; + __be16 pcierr = 0; s64 rc; /* Sanity check on PE number */ diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 5422f4a6317c..e2d031a3ec15 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -600,8 +600,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { struct pnv_phb *phb = pdn->phb->private_data; - u8 fstate; - __be16 pcierr; + u8 fstate = 0; + __be16 pcierr = 0; unsigned int pe_no; s64 rc; diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index 3db53e8aff92..9b2ef76578f0 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -664,7 +664,7 @@ static int update_flash_db(void) db_set_64(db, &os_area_db_id_rtc_diff, saved_params.rtc_diff); count = os_area_flash_write(db, sizeof(struct os_area_db), pos); - if (count < sizeof(struct os_area_db)) { + if (count < 0 || count < sizeof(struct os_area_db)) { pr_debug("%s: os_area_flash_write failed %zd\n", __func__, count); error = count < 0 ? count : -EIO; diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index f4e6565dd7a9..fb2876a84fbe 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -63,6 +63,10 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) name = (char *)ccwa + be32_to_cpu(ccwa->name_offset); prop->name = kstrdup(name, GFP_KERNEL); + if (!prop->name) { + dlpar_free_cc_property(prop); + return NULL; + } prop->length = be32_to_cpu(ccwa->prop_length); value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset); diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 18014cdeb590..ef6595153642 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -149,7 +149,7 @@ static int dtl_start(struct dtl *dtl) /* Register our dtl buffer with the hypervisor. The HV expects the * buffer size to be passed in the second word of the buffer */ - ((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES; + ((u32 *)dtl->buf)[1] = cpu_to_be32(DISPATCH_LOG_BYTES); hwcpu = get_hard_smp_processor_id(dtl->cpu); addr = __pa(dtl->buf); @@ -184,7 +184,7 @@ static void dtl_stop(struct dtl *dtl) static u64 dtl_current_index(struct dtl *dtl) { - return lppaca_of(dtl->cpu).dtl_idx; + return be64_to_cpu(lppaca_of(dtl->cpu).dtl_idx); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 93e09f108ca1..fdfce7a46d73 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -295,6 +295,7 @@ static u32 lookup_lmb_associativity_index(struct of_drconf_cell *lmb) aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc); + of_node_put(dr_node); dlpar_free_cc_nodes(lmb_node); return aa_index; } @@ -787,7 +788,7 @@ static int dlpar_add_lmb(struct of_drconf_cell *lmb) nid = memory_add_physaddr_to_nid(lmb->base_addr); /* Add the memory */ - rc = add_memory(nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { dlpar_remove_device_tree_lmb(lmb); return rc; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 55e97565ed2d..c0ae3847b8db 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -48,6 +48,7 @@ #include <asm/kexec.h> #include <asm/fadump.h> #include <asm/asm-prototypes.h> +#include <asm/debugfs.h> #include "pseries.h" @@ -643,7 +644,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) return 0; } -/* Must be called in user context */ +/* + * Must be called in process context. The caller must hold the + * cpus_lock. + */ static int pseries_lpar_resize_hpt(unsigned long shift) { struct hpt_resize_state state = { @@ -699,7 +703,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) t1 = ktime_get(); - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, + &state, NULL); t2 = ktime_get(); @@ -1032,3 +1037,56 @@ static int __init reserve_vrma_context_id(void) return 0; } machine_device_initcall(pseries, reserve_vrma_context_id); + +#ifdef CONFIG_DEBUG_FS +/* debugfs file interface for vpa data */ +static ssize_t vpa_file_read(struct file *filp, char __user *buf, size_t len, + loff_t *pos) +{ + int cpu = (long)filp->private_data; + struct lppaca *lppaca = &lppaca_of(cpu); + + return simple_read_from_buffer(buf, len, pos, lppaca, + sizeof(struct lppaca)); +} + +static const struct file_operations vpa_fops = { + .open = simple_open, + .read = vpa_file_read, + .llseek = default_llseek, +}; + +static int __init vpa_debugfs_init(void) +{ + char name[16]; + long i; + static struct dentry *vpa_dir; + + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root); + if (!vpa_dir) { + pr_warn("%s: can't create vpa root dir\n", __func__); + return -ENOMEM; + } + + /* set up the per-cpu vpa file*/ + for_each_possible_cpu(i) { + struct dentry *d; + + sprintf(name, "cpu-%ld", i); + + d = debugfs_create_file(name, 0400, vpa_dir, (void *)i, + &vpa_fops); + if (!d) { + pr_warn("%s: can't create per-cpu vpa file\n", + __func__); + return -ENOMEM; + } + } + + return 0; +} +machine_arch_initcall(pseries, vpa_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index fbea7db043fa..9739a055e5f7 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -9,8 +9,10 @@ * 2 as published by the Free Software Foundation. */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/kobject.h> +#include <linux/sched.h> #include <linux/smp.h> #include <linux/stat.h> #include <linux/completion.h> @@ -207,7 +209,11 @@ static int update_dt_node(__be32 phandle, s32 scope) prop_data += vd; } + + cond_resched(); } + + cond_resched(); } while (rtas_rc == 1); of_node_put(dn); @@ -316,8 +322,12 @@ int pseries_devicetree_update(s32 scope) add_dt_node(phandle, drc_index); break; } + + cond_resched(); } } + + cond_resched(); } while (rc == 1); kfree(rtas_buf); @@ -343,11 +353,19 @@ void post_mobility_fixup(void) if (rc) printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc); + /* + * We don't want CPUs to go online/offline while the device + * tree is being updated. + */ + cpus_read_lock(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) printk(KERN_ERR "Post-mobility device tree update " "failed: %d\n", rc); + cpus_read_unlock(); + /* Possibly switch to a new RFI flush type */ pseries_setup_rfi_flush(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6a0ad56e89b9..7a9945b35053 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -307,6 +307,9 @@ static void pseries_lpar_idle(void) * low power mode by ceding processor to hypervisor */ + if (!prep_irq_for_idle()) + return; + /* Indicate to hypervisor that we are idle. */ get_lppaca()->idle = 1; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index a3b8d7d1316e..a820370883d9 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -482,7 +482,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, * Now go through the entire mask until we find a valid * target. */ - for (;;) { + do { /* * We re-check online as the fallback case passes us * an untested affinity mask @@ -490,12 +490,11 @@ static int xive_find_target_in_mask(const struct cpumask *mask, if (cpu_online(cpu) && xive_try_pick_target(cpu)) return cpu; cpu = cpumask_next(cpu, mask); - if (cpu == first) - break; /* Wrap around */ if (cpu >= nr_cpu_ids) cpu = cpumask_first(mask); - } + } while (cpu != first); + return -1; } @@ -968,6 +967,15 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw) xd->target = XIVE_INVALID_TARGET; irq_set_handler_data(virq, xd); + /* + * Turn OFF by default the interrupt being mapped. A side + * effect of this check is the mapping the ESB page of the + * interrupt in the Linux address space. This prevents page + * fault issues in the crash handler which masks all + * interrupts. + */ + xive_esb_read(xd, XIVE_ESB_SET_PQ_01); + return 0; } @@ -1009,12 +1017,13 @@ static void xive_ipi_eoi(struct irq_data *d) { struct xive_cpu *xc = __this_cpu_read(xive_cpu); - DBG_VERBOSE("IPI eoi: irq=%d [0x%lx] (HW IRQ 0x%x) pending=%02x\n", - d->irq, irqd_to_hwirq(d), xc->hw_ipi, xc->pending_prio); - /* Handle possible race with unplug and drop stale IPIs */ if (!xc) return; + + DBG_VERBOSE("IPI eoi: irq=%d [0x%lx] (HW IRQ 0x%x) pending=%02x\n", + d->irq, irqd_to_hwirq(d), xc->hw_ipi, xc->pending_prio); + xive_do_source_eoi(xc->hw_ipi, &xc->ipi_data); xive_do_queue_eoi(xc); } diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 0f89ee557b04..aac61374afeb 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -234,6 +234,17 @@ static bool xive_native_match(struct device_node *node) return of_device_is_compatible(node, "ibm,opal-xive-vc"); } +static s64 opal_xive_allocate_irq(u32 chip_id) +{ + s64 irq = opal_xive_allocate_irq_raw(chip_id); + + /* + * Old versions of skiboot can incorrectly return 0xffffffff to + * indicate no space, fix it up here. + */ + return irq == 0xffffffff ? OPAL_RESOURCE : irq; +} + #ifdef CONFIG_SMP static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc) { diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 091f1d0d0af1..7fc41bf30fd5 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -293,20 +293,28 @@ static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) data->esb_shift = esb_shift; data->trig_page = trig_page; + data->hw_irq = hw_irq; + /* * No chip-id for the sPAPR backend. This has an impact how we * pick a target. See xive_pick_irq_target(). */ data->src_chip = XIVE_INVALID_CHIP_ID; + /* + * When the H_INT_ESB flag is set, the H_INT_ESB hcall should + * be used for interrupt management. Skip the remapping of the + * ESB pages which are not available. + */ + if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB) + return 0; + data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift); if (!data->eoi_mmio) { pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq); return -ENOMEM; } - data->hw_irq = hw_irq; - /* Full function page supports trigger */ if (flags & XIVE_SRC_TRIGGER) { data->trig_mmio = data->eoi_mmio; diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 549e99e71112..a60c44b4a3e5 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -# Disable clang warning for using setjmp without setjmp.h header -subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header) +# Avoid clang warnings around longjmp/setjmp declarations +subdir-ccflags-y := -ffreestanding subdir-ccflags-$(CONFIG_PPC_WERROR) += -Werror @@ -13,6 +13,12 @@ UBSAN_SANITIZE := n ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -mno-sched-epilog,,$(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))) +ifdef CONFIG_CC_IS_CLANG +# clang stores addresses on the stack causing the frame size to blow +# out. See https://github.com/ClangBuiltLinux/linux/issues/252 +KBUILD_CFLAGS += -Wframe-larger-than=4096 +endif + ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += xmon.o nonstdio.o spr_access.o diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index f752f771f29d..51a53fd51722 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -465,8 +465,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) local_irq_save(flags); hard_irq_disable(); - tracing_enabled = tracing_is_on(); - tracing_off(); + if (!fromipi) { + tracing_enabled = tracing_is_on(); + tracing_off(); + } bp = in_breakpoint_table(regs->nip, &offset); if (bp != NULL) { @@ -2436,13 +2438,16 @@ static void dump_pacas(void) static void dump_one_xive(int cpu) { unsigned int hwid = get_hard_smp_processor_id(cpu); + bool hv = cpu_has_feature(CPU_FTR_HVMODE); - opal_xive_dump(XIVE_DUMP_TM_HYP, hwid); - opal_xive_dump(XIVE_DUMP_TM_POOL, hwid); - opal_xive_dump(XIVE_DUMP_TM_OS, hwid); - opal_xive_dump(XIVE_DUMP_TM_USER, hwid); - opal_xive_dump(XIVE_DUMP_VP, hwid); - opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid); + if (hv) { + opal_xive_dump(XIVE_DUMP_TM_HYP, hwid); + opal_xive_dump(XIVE_DUMP_TM_POOL, hwid); + opal_xive_dump(XIVE_DUMP_TM_OS, hwid); + opal_xive_dump(XIVE_DUMP_TM_USER, hwid); + opal_xive_dump(XIVE_DUMP_VP, hwid); + opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid); + } if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; @@ -3288,7 +3293,7 @@ void dump_segments(void) printf("sr0-15 ="); for (i = 0; i < 16; ++i) - printf(" %x", mfsrin(i)); + printf(" %x", mfsrin(i << 28)); printf("\n"); } #endif diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 591cbdf615af..1a906dd7ca7d 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -572,6 +572,9 @@ static int xts_aes_encrypt(struct blkcipher_desc *desc, struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; + if (!nbytes) + return -EINVAL; + if (unlikely(!xts_ctx->fc)) return xts_fallback_encrypt(desc, dst, src, nbytes); @@ -586,6 +589,9 @@ static int xts_aes_decrypt(struct blkcipher_desc *desc, struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; + if (!nbytes) + return -EINVAL; + if (unlikely(!xts_ctx->fc)) return xts_fallback_decrypt(desc, dst, src, nbytes); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 45eb5999110b..32f5b3fb069f 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -269,7 +269,7 @@ static int hypfs_show_options(struct seq_file *s, struct dentry *root) static int hypfs_fill_super(struct super_block *sb, void *data, int silent) { struct inode *root_inode; - struct dentry *root_dentry; + struct dentry *root_dentry, *update_file; int rc = 0; struct hypfs_sb_info *sbi; @@ -300,9 +300,10 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) rc = hypfs_diag_create_files(root_dentry); if (rc) return rc; - sbi->update_file = hypfs_create_update_file(root_dentry); - if (IS_ERR(sbi->update_file)) - return PTR_ERR(sbi->update_file); + update_file = hypfs_create_update_file(root_dentry); + if (IS_ERR(update_file)) + return PTR_ERR(update_file); + sbi->update_file = update_file; hypfs_update_update(sb); pr_info("Hypervisor filesystem mounted\n"); return 0; diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 2d58478c2745..9fee469d7130 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -59,6 +59,18 @@ static inline int test_facility(unsigned long nr) return __test_facility(nr, &S390_lowcore.stfle_fac_list); } +static inline unsigned long __stfle_asm(u64 *stfle_fac_list, int size) +{ + register unsigned long reg0 asm("0") = size - 1; + + asm volatile( + ".insn s,0xb2b00000,0(%1)" /* stfle */ + : "+d" (reg0) + : "a" (stfle_fac_list) + : "memory", "cc"); + return reg0; +} + /** * stfle - Store facility list extended * @stfle_fac_list: array where facility list can be stored @@ -76,13 +88,8 @@ static inline void stfle(u64 *stfle_fac_list, int size) memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4); if (S390_lowcore.stfl_fac_list & 0x01000000) { /* More facility bits available with stfle */ - register unsigned long reg0 asm("0") = size - 1; - - asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */ - : "+d" (reg0) - : "a" (stfle_fac_list) - : "memory", "cc"); - nr = (reg0 + 1) * 8; /* # bytes stored by stfle */ + nr = __stfle_asm(stfle_fac_list, size); + nr = min_t(unsigned long, (nr + 1) * 8, size * 8); } memset((char *) stfle_fac_list + nr, 0, size * 8 - nr); preempt_enable(); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index d7fe9838084d..328710b386e3 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1126,8 +1126,6 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_NX) - pte_val(entry) &= ~_PAGE_NOEXEC; if (pte_present(entry)) pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) @@ -1144,6 +1142,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); + if (!MACHINE_HAS_NX) + pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); } diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index cdd0f0d999e2..bd7a19a0aecf 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -67,8 +67,10 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n); unsigned long __must_check raw_copy_to_user(void __user *to, const void *from, unsigned long n); +#ifndef CONFIG_KASAN #define INLINE_COPY_FROM_USER #define INLINE_COPY_TO_USER +#endif #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES @@ -93,7 +95,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); __rc; \ }) -static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) +static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) { unsigned long spec = 0x810000UL; int rc; @@ -123,7 +125,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) return rc; } -static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) +static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) { unsigned long spec = 0x81UL; int rc; diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index b9d8fe45737a..8f8456816d83 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); static ssize_t show_idle_time(struct device *dev, struct device_attribute *attr, char *buf) { + unsigned long long now, idle_time, idle_enter, idle_exit, in_idle; struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); - unsigned long long now, idle_time, idle_enter, idle_exit; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_time = READ_ONCE(idle->idle_time); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + idle_time += in_idle; return sprintf(buf, "%llu\n", idle_time >> 12); } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; + unsigned long long now, idle_enter, idle_exit, in_idle; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - - return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + return cputime_to_nsecs(in_idle); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index d99155793c26..2e2fd9535f86 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1610,14 +1610,17 @@ static int __init init_cpum_sampling_pmu(void) } sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); - if (!sfdbg) + if (!sfdbg) { pr_err("Registering for s390dbf failed\n"); + return -ENOMEM; + } debug_register_view(sfdbg, &debug_sprintf_view); err = register_external_irq(EXT_IRQ_MEASURE_ALERT, cpumf_measurement_alert); if (err) { pr_cpumsf_err(RS_INIT_FAILURE_ALRT); + debug_unregister(sfdbg); goto out; } @@ -1626,6 +1629,7 @@ static int __init init_cpum_sampling_pmu(void) pr_cpumsf_err(RS_INIT_FAILURE_PERF); unregister_external_irq(EXT_IRQ_MEASURE_ALERT, cpumf_measurement_alert); + debug_unregister(sfdbg); goto out; } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 7d4c5500c6c2..1bb7ea6afcf9 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -185,20 +185,30 @@ unsigned long get_wchan(struct task_struct *p) if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p)) return 0; + + if (!try_get_task_stack(p)) + return 0; + low = task_stack_page(p); high = (struct stack_frame *) task_pt_regs(p); sf = (struct stack_frame *) p->thread.ksp; - if (sf <= low || sf > high) - return 0; + if (sf <= low || sf > high) { + return_address = 0; + goto out; + } for (count = 0; count < 16; count++) { sf = (struct stack_frame *) sf->back_chain; - if (sf <= low || sf > high) - return 0; + if (sf <= low || sf > high) { + return_address = 0; + goto out; + } return_address = sf->gprs[8]; if (!in_sched_functions(return_address)) - return return_address; + goto out; } - return 0; +out: + put_task_stack(p); + return return_address; } unsigned long arch_align_stack(unsigned long sp) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index ed0bdd220e1a..bd074acd0d1f 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -300,7 +300,8 @@ int arch_update_cpu_topology(void) rc = __arch_update_cpu_topology(); for_each_online_cpu(cpu) { dev = get_cpu_device(cpu); - kobject_uevent(&dev->kobj, KOBJ_CHANGE); + if (dev) + kobject_uevent(&dev->kobj, KOBJ_CHANGE); } return rc; } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 101cadabfc89..6d87f800b4f2 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -25,9 +25,10 @@ obj-y += vdso32_wrapper.o extra-y += vdso32.lds CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) -# Disable gcov profiling and ubsan for VDSO code +# Disable gcov profiling, ubsan and kasan for VDSO code GCOV_PROFILE := n UBSAN_SANITIZE := n +KASAN_SANITIZE := n # Force dependency (incbin is bad) $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 36bbafcf4a77..4bc166b8c0cb 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -25,9 +25,10 @@ obj-y += vdso64_wrapper.o extra-y += vdso64.lds CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) -# Disable gcov profiling and ubsan for VDSO code +# Disable gcov profiling, ubsan and kasan for VDSO code GCOV_PROFILE := n UBSAN_SANITIZE := n +KASAN_SANITIZE := n # Force dependency (incbin is bad) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 5185be314661..28f3796d23c8 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1701,6 +1701,16 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, case KVM_S390_MCHK: irq->u.mchk.mcic = s390int->parm64; break; + case KVM_S390_INT_PFAULT_INIT: + irq->u.ext.ext_params = s390int->parm; + irq->u.ext.ext_params2 = s390int->parm64; + break; + case KVM_S390_RESTART: + case KVM_S390_INT_CLOCK_COMP: + case KVM_S390_INT_CPU_TIMER: + break; + default: + return -EINVAL; } return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d6fe229ac20e..91c24e87fe10 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -361,19 +361,30 @@ static void kvm_s390_cpu_feat_init(void) int kvm_arch_init(void *opaque) { + int rc; + kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long)); if (!kvm_s390_dbf) return -ENOMEM; if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) { - debug_unregister(kvm_s390_dbf); - return -ENOMEM; + rc = -ENOMEM; + goto out_debug_unreg; } kvm_s390_cpu_feat_init(); /* Register floating interrupt controller interface. */ - return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); + rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); + if (rc) { + pr_err("Failed to register FLIC rc=%d\n", rc); + goto out_debug_unreg; + } + return 0; + +out_debug_unreg: + debug_unregister(kvm_s390_dbf); + return rc; } void kvm_arch_exit(void) @@ -1926,13 +1937,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags); if (!kvm->arch.sca) goto out_err; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); sca_offset += 16; if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE) sca_offset = 0; kvm->arch.sca = (struct bsca_block *) ((char *) kvm->arch.sca + sca_offset); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); sprintf(debug_name, "kvm-%u", current->pid); @@ -3658,7 +3669,7 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION | KVM_S390_MEMOP_F_CHECK_ONLY; - if (mop->flags & ~supported_flags) + if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) @@ -3730,7 +3741,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; - struct kvm_s390_irq s390irq; + struct kvm_s390_irq s390irq = {}; r = -EFAULT; if (copy_from_user(&s390int, argp, sizeof(s390int))) @@ -3913,21 +3924,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int rc; - - /* If the basics of the memslot do not change, we do not want - * to update the gmap. Every update causes several unnecessary - * segment translation exceptions. This is usually handled just - * fine by the normal fault handler + gmap, but it will also - * cause faults on the prefix page of running guest CPUs. - */ - if (old->userspace_addr == mem->userspace_addr && - old->base_gfn * PAGE_SIZE == mem->guest_phys_addr && - old->npages * PAGE_SIZE == mem->memory_size) - return; + int rc = 0; - rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + switch (change) { + case KVM_MR_DELETE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + break; + case KVM_MR_MOVE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + if (rc) + break; + /* FALLTHROUGH */ + case KVM_MR_CREATE: + rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, + mem->guest_phys_addr, mem->memory_size); + break; + case KVM_MR_FLAGS_ONLY: + break; + default: + WARN(1, "Unknown KVM MR CHANGE: %d\n", change); + } if (rc) pr_warn("failed to commit memory region\n"); return; diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 829c63dbc81a..c0e96bdac80a 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -307,16 +307,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, } if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) + len = min(*lenp, sizeof(buf)); + if (copy_from_user(buf, buffer, len)) return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; + buf[len - 1] = '\0'; cmm_skip_blanks(buf, &p); nr = simple_strtoul(p, &p, 0); cmm_skip_blanks(p, &p); seconds = simple_strtoul(p, &p, 0); cmm_set_timeout(nr, seconds); + *ppos += *lenp; } else { len = sprintf(buf, "%ld %ld\n", cmm_timeout_pages, cmm_timeout_seconds); @@ -324,9 +324,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, len = *lenp; if (copy_to_user(buffer, buf, len)) return -EFAULT; + *lenp = len; + *ppos += len; } - *lenp = len; - *ppos += len; return 0; } diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 05c8abd864f1..9bce54eac0b0 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -39,7 +39,8 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); head = compound_head(page); - if (!page_cache_get_speculative(head)) + if (unlikely(WARN_ON_ONCE(page_ref_count(head) < 0) + || !page_cache_get_speculative(head))) return 0; if (unlikely(pte_val(pte) != pte_val(*ptep))) { put_page(head); @@ -77,7 +78,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + if (unlikely(WARN_ON_ONCE(page_ref_count(head) < 0) + || !page_cache_add_speculative(head, refs))) { *nr -= refs; return 0; } @@ -151,7 +153,8 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - if (!page_cache_add_speculative(head, refs)) { + if (unlikely(WARN_ON_ONCE(page_ref_count(head) < 0) + || !page_cache_add_speculative(head, refs))) { *nr -= refs; return 0; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 6b1474fa99ab..b8bd84104843 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -30,8 +30,6 @@ #include <asm/set_memory.h> #include "bpf_jit.h" -int bpf_jit_enable __read_mostly; - struct bpf_jit { u32 seen; /* Flags to remember seen eBPF instructions */ u32 seen_reg[16]; /* Array to remember which registers are used */ @@ -884,7 +882,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i break; case BPF_ALU64 | BPF_NEG: /* dst = -dst */ /* lcgr %dst,%dst */ - EMIT4(0xb9130000, dst_reg, dst_reg); + EMIT4(0xb9030000, dst_reg, dst_reg); break; /* * BPF_FROM_BE/LE @@ -1065,8 +1063,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i /* llgf %w1,map.max_entries(%b2) */ EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2, offsetof(struct bpf_array, map.max_entries)); - /* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */ - EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3, + /* clrj %b3,%w1,0xa,label0: if (u32)%b3 >= (u32)%w1 goto out */ + EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3, REG_W1, 0, 0xa); /* @@ -1092,8 +1090,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i * goto out; */ - /* sllg %r1,%b3,3: %r1 = index * 8 */ - EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3); + /* llgfr %r1,%b3: %r1 = (u32) index */ + EMIT4(0xb9160000, REG_1, BPF_REG_3); + /* sllg %r1,%r1,3: %r1 *= 8 */ + EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, REG_1, REG_0, 3); /* lg %r1,prog(%b2,%r1) */ EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2, REG_1, offsetof(struct bpf_array, ptrs)); diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 6394b4f0a69b..f42feab25dcf 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -8,27 +8,19 @@ config SH_ALPHA_BOARD bool config SH_DEVICE_TREE - bool "Board Described by Device Tree" + bool select OF select OF_EARLY_FLATTREE select TIMER_OF select COMMON_CLK select GENERIC_CALIBRATE_DELAY - help - Select Board Described by Device Tree to build a kernel that - does not hard-code any board-specific knowledge but instead uses - a device tree blob provided by the boot-loader. You must enable - drivers for any hardware you want to use separately. At this - time, only boards based on the open-hardware J-Core processors - have sufficient driver coverage to use this option; do not - select it if you are using original SuperH hardware. config SH_JCORE_SOC bool "J-Core SoC" - depends on SH_DEVICE_TREE && (CPU_SH2 || CPU_J2) + select SH_DEVICE_TREE select CLKSRC_JCORE_PIT select JCORE_AIC - default y if CPU_J2 + depends on CPU_J2 help Select this option to include drivers core components of the J-Core SoC, including interrupt controllers and timers. diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 98cb8c802b1a..0ae60d680000 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -371,7 +371,11 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } #define ioremap_nocache ioremap #define ioremap_uc ioremap -#define iounmap __iounmap + +static inline void iounmap(void __iomem *addr) +{ + __iounmap(addr); +} /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index afe965712a69..dea2e23520e0 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -161,6 +161,7 @@ int arch_bp_generic_fields(int sh_len, int sh_type, switch (sh_type) { case SH_BREAKPOINT_READ: *gen_type = HW_BREAKPOINT_R; + break; case SH_BREAKPOINT_WRITE: *gen_type = HW_BREAKPOINT_W; break; diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index f71ef3729888..316faa0130ba 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -52,7 +52,12 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long return val; } -#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) +#define xchg(ptr,x) \ +({ __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __ret; \ +}) void __xchg_called_with_bad_pointer(void); diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index 05df5f043053..3c5a1c620f0f 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -21,6 +21,7 @@ */ #define HAS_DMA +#ifdef CONFIG_PARPORT_PC_FIFO static DEFINE_SPINLOCK(dma_spin_lock); #define claim_dma_lock() \ @@ -31,6 +32,7 @@ static DEFINE_SPINLOCK(dma_spin_lock); #define release_dma_lock(__flags) \ spin_unlock_irqrestore(&dma_spin_lock, __flags); +#endif static struct sparc_ebus_info { struct ebus_dma_info info; diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 1ef6156b1530..8f24f3d60b8c 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -355,6 +355,8 @@ static int get_vdev_port_node_info(struct mdesc_handle *md, u64 node, node_info->vdev_port.id = *idp; node_info->vdev_port.name = kstrdup_const(name, GFP_KERNEL); + if (!node_info->vdev_port.name) + return -1; node_info->vdev_port.parent_cfg_hdl = *parent_cfg_hdlp; return 0; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index eceb0215bdee..58ea64a29d5f 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -891,6 +891,10 @@ static int sparc_perf_event_set_period(struct perf_event *event, s64 period = hwc->sample_period; int ret = 0; + /* The period may have been changed by PERF_EVENT_IOC_PERIOD */ + if (unlikely(period != hwc->last_period)) + left = period - (hwc->last_period - left); + if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index 09e318eb34ee..3bd8ca95e521 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -11,8 +11,6 @@ #include "bpf_jit_32.h" -int bpf_jit_enable __read_mostly; - static inline bool is_simm13(unsigned int value) { return value + 0x1000 < 0x2000; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index ff5f9cb3039a..dfb1a62abe93 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -12,8 +12,6 @@ #include "bpf_jit_64.h" -int bpf_jit_enable __read_mostly; - static inline bool is_simm13(unsigned int value) { return value + 0x1000 < 0x2000; @@ -1328,6 +1326,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; u32 opcode = 0, rs2; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_2_used = true; emit_loadimm(imm, tmp2, ctx); @@ -1366,6 +1367,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp = bpf2sparc[TMP_REG_1]; u32 opcode = 0, rs2; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + switch (BPF_SIZE(code)) { case BPF_W: opcode = ST32; @@ -1398,6 +1402,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_1_used = true; ctx->tmp_2_used = true; ctx->tmp_3_used = true; @@ -1418,6 +1425,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_1_used = true; ctx->tmp_2_used = true; ctx->tmp_3_used = true; diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug index 967d3109689f..39d44bfb241d 100644 --- a/arch/um/Kconfig.debug +++ b/arch/um/Kconfig.debug @@ -19,6 +19,7 @@ config GPROF config GCOV bool "Enable gcov support" depends on DEBUG_INFO + depends on !KCOV help This option allows developers to retrieve coverage data from a UML session. diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 366e57f5e8d6..7e524efed584 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -261,7 +261,7 @@ static irqreturn_t line_write_interrupt(int irq, void *data) if (err == 0) { spin_unlock(&line->lock); return IRQ_NONE; - } else if (err < 0) { + } else if ((err < 0) && (err != -EAGAIN)) { line->head = line->buffer; line->tail = line->buffer; } diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h index fca34b2177e2..129fb1d1f1c5 100644 --- a/arch/um/include/asm/mmu_context.h +++ b/arch/um/include/asm/mmu_context.h @@ -53,7 +53,7 @@ static inline void activate_mm(struct mm_struct *old, struct mm_struct *new) * when the new ->mm is used for the first time. */ __switch_mm(&new->context.id); - down_write(&new->mmap_sem); + down_write_nested(&new->mmap_sem, 1); uml_setup_stubs(new); up_write(&new->mmap_sem); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8fec1585ac7a..c55870ac907e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1853,6 +1853,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI @@ -2671,8 +2716,7 @@ config OLPC config OLPC_XO1_PM bool "OLPC XO-1 Power Management" - depends on OLPC && MFD_CS5535 && PM_SLEEP - select MFD_CORE + depends on OLPC && MFD_CS5535=y && PM_SLEEP ---help--- Add support for poweroff and suspend of the OLPC XO-1 laptop. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b4c72da8a7ad..3dc54d2f79c4 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -39,6 +39,7 @@ REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) export REALMODE_CFLAGS @@ -248,7 +249,7 @@ ifdef CONFIG_RETPOLINE # retpoline builds, however, gcc does not for x86. This has # only been fixed starting from gcc stable version 8.4.0 and # onwards, but not for older ones. See gcc bug #86952. - ifndef CONFIG_CC_IS_CLANG + ifneq ($(cc-name), clang) KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables) endif endif diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 252fee320816..fb07cfa3f2f9 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -16,6 +16,7 @@ #include "error.h" #include "../string.h" #include "../voffset.h" +#include <asm/bootparam_utils.h> /* * WARNING!! diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 32d4ec2e0243..5380d45b1c6e 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -19,7 +19,6 @@ #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> -#include <asm/bootparam_utils.h> #define BOOT_BOOT_H #include "../ctype.h" diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 5d10b7a85cad..557c1bdda311 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -332,6 +332,23 @@ For 32-bit we have the following conventions - kernel is built with #endif +/* + * Mitigate Spectre v1 for conditional swapgs code paths. + * + * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to + * prevent a speculative swapgs when coming from kernel space. + * + * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path, + * to prevent the swapgs from getting speculatively skipped when coming from + * user space. + */ +.macro FENCE_SWAPGS_USER_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER +.endm +.macro FENCE_SWAPGS_KERNEL_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL +.endm + #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e09ba4bc8b98..5ec66fafde4e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -531,9 +531,12 @@ END(irq_entries_start) testb $3, CS-ORIG_RAX(%rsp) jz 1f SWAPGS + FENCE_SWAPGS_USER_ENTRY call switch_to_thread_stack + jmp 2f 1: - + FENCE_SWAPGS_KERNEL_ENTRY +2: PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER @@ -1113,7 +1116,6 @@ idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN idtentry xennmi do_nmi has_error_code=0 idtentry xendebug do_debug has_error_code=0 -idtentry xenint3 do_int3 has_error_code=0 #endif idtentry general_protection do_general_protection has_error_code=1 @@ -1147,6 +1149,12 @@ ENTRY(paranoid_entry) 1: SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + /* + * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an + * unconditional CR3 write, even in the PTI case. So do an lfence + * to prevent GS speculation, regardless of whether PTI is enabled. + */ + FENCE_SWAPGS_KERNEL_ENTRY ret END(paranoid_entry) @@ -1196,6 +1204,7 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1217,6 +1226,8 @@ ENTRY(error_entry) CALL_enter_from_user_mode ret +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY .Lerror_entry_done: TRACE_IRQS_OFF ret @@ -1235,7 +1246,7 @@ ENTRY(error_entry) cmpq %rax, RIP+8(%rsp) je .Lbstep_iret cmpq $.Lgs_change, RIP+8(%rsp) - jne .Lerror_entry_done + jne .Lerror_entry_done_lfence /* * hack: .Lgs_change can fail with user gsbase. If this happens, fix up @@ -1243,6 +1254,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done @@ -1257,6 +1269,7 @@ ENTRY(error_entry) * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* @@ -1348,6 +1361,7 @@ ENTRY(nmi) swapgs cld + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 9c35dc0a9d64..9f4b1081dee0 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); #ifdef CONFIG_PARAVIRT_CLOCK -extern u8 pvclock_page +extern u8 pvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif #ifdef CONFIG_HYPERV_TSCPAGE -extern u8 hvclock_page +extern u8 hvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif @@ -191,13 +191,24 @@ notrace static inline u64 vgetsns(int *mode) if (gtod->vclock_mode == VCLOCK_TSC) cycles = vread_tsc(); + + /* + * For any memory-mapped vclock type, we need to make sure that gcc + * doesn't cleverly hoist a load before the mode check. Otherwise we + * might end up touching the memory-mapped page even if the vclock in + * question isn't enabled, which will segfault. Hence the barriers. + */ #ifdef CONFIG_PARAVIRT_CLOCK - else if (gtod->vclock_mode == VCLOCK_PVCLOCK) + else if (gtod->vclock_mode == VCLOCK_PVCLOCK) { + barrier(); cycles = vread_pvclock(mode); + } #endif #ifdef CONFIG_HYPERV_TSCPAGE - else if (gtod->vclock_mode == VCLOCK_HVCLOCK) + else if (gtod->vclock_mode == VCLOCK_HVCLOCK) { + barrier(); cycles = vread_hvclock(mode); + } #endif else return 0; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 27ade3cb6482..defb536aebce 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -4,12 +4,14 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <asm/apicdef.h> #include <asm/nmi.h> #include "../perf_event.h" -static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); +static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); +static unsigned long perf_nmi_window; static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -640,11 +642,12 @@ static void amd_pmu_disable_event(struct perf_event *event) * handler when multiple PMCs are active or PMC overflow while handling some * other source of an NMI. * - * Attempt to mitigate this by using the number of active PMCs to determine - * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset - * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the - * number of active PMCs or 2. The value of 2 is used in case an NMI does not - * arrive at the LAPIC in time to be collapsed into an already pending NMI. + * Attempt to mitigate this by creating an NMI window in which un-handled NMIs + * received during this window will be claimed. This prevents extending the + * window past when it is possible that latent NMIs should be received. The + * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has + * handled a counter. When an un-handled NMI is received, it will be claimed + * only if arriving within that window. */ static int amd_pmu_handle_irq(struct pt_regs *regs) { @@ -662,21 +665,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) handled = x86_pmu_handle_irq(regs); /* - * If a counter was handled, record the number of possible remaining - * NMIs that can occur. + * If a counter was handled, record a timestamp such that un-handled + * NMIs will be claimed if arriving within that window. */ if (handled) { - this_cpu_write(perf_nmi_counter, - min_t(unsigned int, 2, active)); + this_cpu_write(perf_nmi_tstamp, + jiffies + perf_nmi_window); return handled; } - if (!this_cpu_read(perf_nmi_counter)) + if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp))) return NMI_DONE; - this_cpu_dec(perf_nmi_counter); - return NMI_HANDLED; } @@ -908,6 +909,9 @@ static int __init amd_core_pmu_init(void) if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; + /* Avoid calulating the value each time in the NMI handler */ + perf_nmi_window = msecs_to_jiffies(100); + switch (boot_cpu_data.x86) { case 0x15: pr_cont("Fam15h "); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 8c51844694e2..f24e9adaa316 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -389,7 +389,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -564,7 +565,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, @@ -625,7 +627,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { @@ -672,10 +674,17 @@ fail: throttle = perf_event_overflow(event, &data, ®s); out: - if (throttle) + if (throttle) { perf_ibs_stop(event, 0); - else - perf_ibs_enable_event(perf_ibs, hwc, period >> 4); + } else { + period >>= 4; + + if ((ibs_caps & IBS_CAPS_RDWROPCNT) && + (*config & IBS_OP_CNT_CTL)) + period |= *config & IBS_OP_CUR_CNT_RAND; + + perf_ibs_enable_event(perf_ibs, hwc, period); + } perf_event_update_userpage(event); diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 4e1d7483b78c..baa7e36073f9 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -19,6 +19,7 @@ #include <asm/cpufeature.h> #include <asm/perf_event.h> #include <asm/msr.h> +#include <asm/smp.h> #define NUM_COUNTERS_NB 4 #define NUM_COUNTERS_L2 4 @@ -209,15 +210,22 @@ static int amd_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; + if (event->cpu < 0) + return -EINVAL; + /* * SliceMask and ThreadMask need to be set for certain L3 events in * Family 17h. For other events, the two fields do not affect the count. */ - if (l3_mask) - hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK); + if (l3_mask && is_llc_event(event)) { + int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4); - if (event->cpu < 0) - return -EINVAL; + if (smp_num_siblings > 1) + thread += cpu_data(event->cpu).apicid & 1; + + hwc->config |= (1ULL << (AMD64_L3_THREAD_SHIFT + thread) & + AMD64_L3_THREAD_MASK) | AMD64_L3_SLICE_MASK; + } uncore = event_to_amd_uncore(event); if (!uncore) @@ -407,26 +415,8 @@ static int amd_uncore_cpu_starting(unsigned int cpu) } if (amd_uncore_llc) { - unsigned int apicid = cpu_data(cpu).apicid; - unsigned int nshared, subleaf, prev_eax = 0; - uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - /* - * Iterate over Cache Topology Definition leaves until no - * more cache descriptions are available. - */ - for (subleaf = 0; subleaf < 5; subleaf++) { - cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx); - - /* EAX[0:4] gives type of cache */ - if (!(eax & 0x1f)) - break; - - prev_eax = eax; - } - nshared = ((prev_eax >> 14) & 0xfff) + 1; - - uncore->id = apicid - (apicid % nshared); + uncore->id = per_cpu(cpu_llc_id, cpu); uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d44bb077c6cf..4a60ed8c4413 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3297,6 +3297,11 @@ static u64 bdw_limit_period(struct perf_event *event, u64 left) return left; } +static u64 nhm_limit_period(struct perf_event *event, u64 left) +{ + return max(left, 32ULL); +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -4092,6 +4097,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + x86_pmu.limit_period = nhm_limit_period; x86_pmu.cpu_events = nhm_events_attrs; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 25386be0d757..3310f9f6c3e1 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -681,7 +681,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -690,7 +690,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -698,7 +698,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { struct event_constraint intel_slm_pebs_event_constraints[] = { /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -729,7 +729,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -746,7 +746,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -755,7 +755,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -770,9 +770,9 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -786,9 +786,9 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -809,9 +809,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -832,9 +832,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 2e9d58cc371e..924fa9c07368 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -17,6 +17,7 @@ * */ +#include <linux/efi.h> #include <linux/types.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> @@ -101,6 +102,22 @@ static int hv_cpu_init(unsigned int cpu) return 0; } +static int __init hv_pci_init(void) +{ + int gen2vm = efi_enabled(EFI_BOOT); + + /* + * For Generation-2 VM, we exit from pci_arch_init() by returning 0. + * The purpose is to suppress the harmless warning: + * "PCI: Fatal: No config space access function found" + */ + if (gen2vm) + return 0; + + /* For Generation-1 VM, we'll proceed in pci_arch_init(). */ + return 1; +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -108,7 +125,7 @@ static int hv_cpu_init(unsigned int cpu) * 1. Setup the hypercall page. * 2. Register Hyper-V specific clocksource. */ -void hyperv_init(void) +void __init hyperv_init(void) { u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; @@ -154,6 +171,8 @@ void hyperv_init(void) hyper_alloc_mmu(); + x86_init.pci.arch_init = hv_pci_init; + /* * Register Hyper-V specific clocksource. */ diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 56c9ebac946f..47718fff0b79 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -57,12 +57,14 @@ static inline int fill_gva_list(u64 gva_list[], int offset, * Lower 12 bits encode the number of additional * pages to flush (in addition to the 'cur' page). */ - if (diff >= HV_TLB_FLUSH_UNIT) + if (diff >= HV_TLB_FLUSH_UNIT) { gva_list[gva_n] |= ~PAGE_MASK; - else if (diff) + cur += HV_TLB_FLUSH_UNIT; + } else if (diff) { gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT; + cur = end; + } - cur += HV_TLB_FLUSH_UNIT; gva_n++; } while (cur < end); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a1ed92aae12a..25a5a5c6ae90 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -48,7 +48,7 @@ static inline void generic_apic_probe(void) #ifdef CONFIG_X86_LOCAL_APIC -extern unsigned int apic_verbosity; +extern int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 72759f131cc5..d09dd91dd0b6 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -50,7 +50,7 @@ static __always_inline void atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) - : "ir" (i)); + : "ir" (i) : "memory"); } /** @@ -64,7 +64,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) - : "ir" (i)); + : "ir" (i) : "memory"); } /** @@ -90,7 +90,7 @@ static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) static __always_inline void atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" - : "+m" (v->counter)); + : "+m" (v->counter) :: "memory"); } /** @@ -102,7 +102,7 @@ static __always_inline void atomic_inc(atomic_t *v) static __always_inline void atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" - : "+m" (v->counter)); + : "+m" (v->counter) :: "memory"); } /** diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 738495caf05f..e6fad6bbb2ee 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -45,7 +45,7 @@ static __always_inline void atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) - : "er" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter) : "memory"); } /** @@ -59,7 +59,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) - : "er" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter) : "memory"); } /** @@ -86,7 +86,7 @@ static __always_inline void atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) - : "m" (v->counter)); + : "m" (v->counter) : "memory"); } /** @@ -99,7 +99,7 @@ static __always_inline void atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) - : "m" (v->counter)); + : "m" (v->counter) : "memory"); } /** diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index a04f0c242a28..bc88797cfa61 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -106,8 +106,8 @@ do { \ #endif /* Atomic operations are already serializing on x86 */ -#define __smp_mb__before_atomic() barrier() -#define __smp_mb__after_atomic() barrier() +#define __smp_mb__before_atomic() do { } while (0) +#define __smp_mb__after_atomic() do { } while (0) #include <asm-generic/barrier.h> diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index a07ffd23e4dd..8fa49cf1211d 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -18,6 +18,20 @@ * Note: efi_info is commonly left uninitialized, but that field has a * private magic, so it is better to leave it unchanged. */ + +#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); }) + +#define BOOT_PARAM_PRESERVE(struct_member) \ + { \ + .start = offsetof(struct boot_params, struct_member), \ + .len = sizeof_mbr(struct boot_params, struct_member), \ + } + +struct boot_params_to_save { + unsigned int start; + unsigned int len; +}; + static void sanitize_boot_params(struct boot_params *boot_params) { /* @@ -36,19 +50,41 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->ext_ramdisk_image, 0, - (char *)&boot_params->efi_info - - (char *)&boot_params->ext_ramdisk_image); - memset(&boot_params->kbd_status, 0, - (char *)&boot_params->hdr - - (char *)&boot_params->kbd_status); - memset(&boot_params->_pad7[0], 0, - (char *)&boot_params->edd_mbr_sig_buffer[0] - - (char *)&boot_params->_pad7[0]); - memset(&boot_params->_pad8[0], 0, - (char *)&boot_params->eddbuf[0] - - (char *)&boot_params->_pad8[0]); - memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + static struct boot_params scratch; + char *bp_base = (char *)boot_params; + char *save_base = (char *)&scratch; + int i; + + const struct boot_params_to_save to_save[] = { + BOOT_PARAM_PRESERVE(screen_info), + BOOT_PARAM_PRESERVE(apm_bios_info), + BOOT_PARAM_PRESERVE(tboot_addr), + BOOT_PARAM_PRESERVE(ist_info), + BOOT_PARAM_PRESERVE(hd0_info), + BOOT_PARAM_PRESERVE(hd1_info), + BOOT_PARAM_PRESERVE(sys_desc_table), + BOOT_PARAM_PRESERVE(olpc_ofw_header), + BOOT_PARAM_PRESERVE(efi_info), + BOOT_PARAM_PRESERVE(alt_mem_k), + BOOT_PARAM_PRESERVE(scratch), + BOOT_PARAM_PRESERVE(e820_entries), + BOOT_PARAM_PRESERVE(eddbuf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(secure_boot), + BOOT_PARAM_PRESERVE(hdr), + BOOT_PARAM_PRESERVE(e820_table), + BOOT_PARAM_PRESERVE(eddbuf), + }; + + memset(&scratch, 0, sizeof(scratch)); + + for (i = 0; i < ARRAY_SIZE(to_save); i++) { + memcpy(save_base + to_save[i].start, + bp_base + to_save[i].start, to_save[i].len); + } + + memcpy(boot_params, save_base, sizeof(*boot_params)); } } diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..4e2d03135854 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -22,8 +22,8 @@ enum cpuid_leafs CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, - CPUID_F_0_EDX, - CPUID_F_1_EDX, + CPUID_LNX_4, + CPUID_DUMMY, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 48ef9ed8226d..b4bef819d5d5 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -239,12 +239,14 @@ #define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ #define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ #define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */ #define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ #define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ #define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ #define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ #define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ @@ -269,13 +271,18 @@ #define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ #define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */ -#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0xf, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -380,5 +387,8 @@ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 038e4b63b56b..5cd7d4e1579d 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -6,7 +6,7 @@ * "Big Core" Processors (Branded as Core, Xeon, etc...) * * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E. + * "Extreme" ones, like Broadwell-E, or Atom microserver. * * Things ending in "2" are usually because we have no better * name for them. There's no processor called "SILVERMONT2". @@ -68,6 +68,7 @@ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ #define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ #define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ +#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index f327236f0fa7..5125fca472bb 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -67,7 +67,7 @@ struct kimage; /* Memory to backup during crash kdump */ #define KEXEC_BACKUP_SRC_START (0UL) -#define KEXEC_BACKUP_SRC_END (640 * 1024UL) /* 640K */ +#define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */ /* * CPU does not save ss and sp on stack if execution is already diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f9a4b85d7309..d0e17813a9b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -277,6 +277,7 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; /* * The following two entries are used to key the shadow page in the @@ -289,6 +290,7 @@ struct kvm_mmu_page { /* hold the gfn of each spte inside spt */ gfn_t *gfns; bool unsync; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ @@ -779,6 +781,7 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -854,6 +857,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -867,6 +872,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; @@ -973,7 +979,7 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - void (*tlb_flush)(struct kvm_vcpu *vcpu); + void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); @@ -998,7 +1004,7 @@ struct kvm_x86_ops { void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); - void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); + void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); @@ -1077,6 +1083,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); + bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc); void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); @@ -1353,25 +1360,29 @@ enum { #define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) #define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +asmlinkage void __noreturn kvm_spurious_fault(void); + /* * Hardware virtualization extension instructions may fault if a * reboot turns off virtualization while processes are running. - * Trap the fault and ignore the instruction if that happens. + * Usually after catching the fault we just panic; during reboot + * instead the instruction is ignored. */ -asmlinkage void kvm_spurious_fault(void); - -#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn) \ - "666: " insn "\n\t" \ - "668: \n\t" \ - ".pushsection .fixup, \"ax\" \n" \ - "667: \n\t" \ - cleanup_insn "\n\t" \ - "cmpb $0, kvm_rebooting \n\t" \ - "jne 668b \n\t" \ - __ASM_SIZE(push) " $666b \n\t" \ - "jmp kvm_spurious_fault \n\t" \ - ".popsection \n\t" \ - _ASM_EXTABLE(666b, 667b) +#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn) \ + "666: \n\t" \ + insn "\n\t" \ + "jmp 668f \n\t" \ + "667: \n\t" \ + "call kvm_spurious_fault \n\t" \ + "668: \n\t" \ + ".pushsection .fixup, \"ax\" \n\t" \ + "700: \n\t" \ + cleanup_insn "\n\t" \ + "cmpb $0, kvm_rebooting\n\t" \ + "je 667b \n\t" \ + "jmp 668b \n\t" \ + ".popsection \n\t" \ + _ASM_EXTABLE(666b, 700b) #define __kvm_handle_fault_on_reboot(insn) \ ____kvm_handle_fault_on_reboot(insn, "") diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 7f1c8448d595..5761a86b88e0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -84,6 +84,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -94,6 +106,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -334,6 +350,7 @@ #define MSR_AMD64_PATCH_LEVEL 0x0000008b #define MSR_AMD64_TSC_RATIO 0xc0000104 #define MSR_AMD64_NB_CFG 0xc001001f +#define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index eb0f80ce8524..3aa82deeab5a 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -21,7 +21,7 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 #define MWAITX_ECX_TIMER_ENABLE BIT(1) #define MWAITX_MAX_LOOPS ((u32)-1) -#define MWAITX_DISABLE_CSTATES 0xf +#define MWAITX_DISABLE_CSTATES 0xf0 static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f1ddf3a1f307..b73a16a56e4f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -202,7 +202,7 @@ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ - "903: addl $4, %%esp;\n" \ + "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ @@ -323,7 +323,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -346,7 +346,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c83a2f418cea..4471f0da6ed7 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -758,6 +758,7 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu) PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ "ret;" \ + ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 78241b736f2a..f6c4915a863e 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -209,16 +209,20 @@ struct x86_pmu_capability { #define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) #define IBSCTL_LVT_OFFSET_MASK 0x0F -/* ibs fetch bits/masks */ +/* IBS fetch bits/masks */ #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) #define IBS_FETCH_CNT 0xFFFF0000ULL #define IBS_FETCH_MAX_CNT 0x0000FFFFULL -/* ibs op bits/masks */ -/* lower 4 bits of the current count are ignored: */ -#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32) +/* + * IBS op bits/masks + * The lower 7 bits of the current count are random bits + * preloaded by hardware and ignored in software + */ +#define IBS_OP_CUR_CNT (0xFFF80ULL<<32) +#define IBS_OP_CUR_CNT_RAND (0x0007FULL<<32) #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index ef938583147e..3a33de4133d1 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -56,15 +56,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); -static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { - *ptep = native_make_pte(0); + WRITE_ONCE(*ptep, pte); } -static inline void native_set_pte(pte_t *ptep, pte_t pte) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -74,7 +74,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -110,7 +110,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -220,9 +220,9 @@ static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { #if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL) - p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd); + WRITE_ONCE(p4dp->pgd, pti_set_user_pgd(&p4dp->pgd, p4d.pgd)); #else - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); #endif } @@ -238,9 +238,9 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { #ifdef CONFIG_PAGE_TABLE_ISOLATION - *pgdp = pti_set_user_pgd(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgd(pgdp, pgd)); #else - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); #endif } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d55a0adbcf27..6a87eda9691e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -994,4 +994,11 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 14131dd06b29..8603d127f73c 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -232,23 +232,51 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs, } /** + * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns the address of the @n th entry of the + * kernel stack which is specified by @regs. If the @n th entry is NOT in + * the kernel stack, this returns NULL. + */ +static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return addr; + else + return NULL; +} + +/* To avoid include hell, we can't include uaccess.h */ +extern long probe_kernel_read(void *dst, const void *src, size_t size); + +/** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which - * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { - unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); - addr += n; - if (regs_within_kernel_stack(regs, (unsigned long)addr)) - return *addr; - else - return 0; + unsigned long *addr; + unsigned long val; + long ret; + + addr = regs_get_kernel_stack_nth_addr(regs, n); + if (addr) { + ret = probe_kernel_read(&val, addr, sizeof(val)); + if (!ret) + return val; + } + return 0; } #define arch_has_single_step() (1) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index fe2ee61880a8..a14730ca9d1e 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -175,16 +175,6 @@ static inline int wbinvd_on_all_cpus(void) extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC - -#ifndef CONFIG_X86_64 -static inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); -} - -#endif - extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index afbc87206886..b771bb3d159b 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -40,7 +40,7 @@ asmlinkage void simd_coprocessor_error(void); asmlinkage void xen_divide_error(void); asmlinkage void xen_xennmi(void); asmlinkage void xen_xendebug(void); -asmlinkage void xen_xenint3(void); +asmlinkage void xen_int3(void); asmlinkage void xen_overflow(void); asmlinkage void xen_bounds(void); asmlinkage void xen_invalid_op(void); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 4111edb3188e..971830341061 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -451,8 +451,10 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ + __typeof__(ptr) __gu_ptr = (ptr); \ + __typeof__(size) __gu_size = (size); \ __uaccess_begin_nospec(); \ - __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ + __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __builtin_expect(__gu_err, 0); \ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2e64178f284d..6415b4aead54 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -182,7 +182,7 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); /* * Debug level, exported for io_apic.c */ -unsigned int apic_verbosity; +int apic_verbosity; int pic_mode; @@ -723,7 +723,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2; static __initdata unsigned long lapic_cal_j1, lapic_cal_j2; /* - * Temporary interrupt handler. + * Temporary interrupt handler and polled calibration function. */ static void __init lapic_cal_handler(struct clock_event_device *dev) { @@ -807,7 +807,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init calibrate_APIC_clock(void) { struct clock_event_device *levt = this_cpu_ptr(&lapic_events); - void (*real_handler)(struct clock_event_device *dev); + u64 tsc_perj = 0, tsc_start = 0; + unsigned long jif_start; unsigned long deltaj; long delta, deltatsc; int pm_referenced = 0; @@ -838,28 +839,64 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" "calibrating APIC timer ...\n"); + /* + * There are platforms w/o global clockevent devices. Instead of + * making the calibration conditional on that, use a polling based + * approach everywhere. + */ local_irq_disable(); - /* Replace the global interrupt handler */ - real_handler = global_clock_event->event_handler; - global_clock_event->event_handler = lapic_cal_handler; - /* * Setup the APIC counter to maximum. There is no way the lapic * can underflow in the 100ms detection time frame */ __setup_APIC_LVTT(0xffffffff, 0, 0); - /* Let the interrupts run */ + /* + * Methods to terminate the calibration loop: + * 1) Global clockevent if available (jiffies) + * 2) TSC if available and frequency is known + */ + jif_start = READ_ONCE(jiffies); + + if (tsc_khz) { + tsc_start = rdtsc(); + tsc_perj = div_u64((u64)tsc_khz * 1000, HZ); + } + + /* + * Enable interrupts so the tick can fire, if a global + * clockevent device is available + */ local_irq_enable(); - while (lapic_cal_loops <= LAPIC_CAL_LOOPS) - cpu_relax(); + while (lapic_cal_loops <= LAPIC_CAL_LOOPS) { + /* Wait for a tick to elapse */ + while (1) { + if (tsc_khz) { + u64 tsc_now = rdtsc(); + if ((tsc_now - tsc_start) >= tsc_perj) { + tsc_start += tsc_perj; + break; + } + } else { + unsigned long jif_now = READ_ONCE(jiffies); - local_irq_disable(); + if (time_after(jif_now, jif_start)) { + jif_start = jif_now; + break; + } + } + cpu_relax(); + } - /* Restore the real event handler */ - global_clock_event->event_handler = real_handler; + /* Invoke the calibration routine */ + local_irq_disable(); + lapic_cal_handler(NULL); + local_irq_enable(); + } + + local_irq_disable(); /* Build delta t1-t2 as apic timer counts down */ delta = lapic_cal_t1 - lapic_cal_t2; @@ -912,10 +949,11 @@ static int __init calibrate_APIC_clock(void) levt->features &= ~CLOCK_EVT_FEAT_DUMMY; /* - * PM timer calibration failed or not turned on - * so lets try APIC timer based calibration + * PM timer calibration failed or not turned on so lets try APIC + * timer based calibration, if a global clockevent device is + * available. */ - if (!pm_referenced) { + if (!pm_referenced && global_clock_event) { apic_printk(APIC_VERBOSE, "... verify APIC timer\n"); /* @@ -1324,6 +1362,56 @@ static void lapic_setup_esr(void) oldvalue, value); } +static void apic_pending_intr_clear(void) +{ + long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned long long tsc = 0, ntsc; + unsigned int value, queued; + int i, j, acked = 0; + + if (boot_cpu_has(X86_FEATURE_TSC)) + tsc = rdtsc(); + /* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now CPU has serviced that pending interrupt and + * it might not have done the ack_APIC_irq() because it thought, + * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it + * does not clear the ISR bit and cpu thinks it has already serivced + * the interrupt. Hence a vector might get locked. It was noticed + * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + */ + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1<<j)) { + ack_APIC_irq(); + acked++; + } + } + } + if (acked > 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (queued) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { + ntsc = rdtsc(); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); +} + /** * setup_local_APIC - setup the local APIC * @@ -1333,19 +1421,22 @@ static void lapic_setup_esr(void) void setup_local_APIC(void) { int cpu = smp_processor_id(); - unsigned int value, queued; - int i, j, acked = 0; - unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned int value; - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); return; } + /* + * If this comes from kexec/kcrash the APIC might be enabled in + * SPIV. Soft disable it before doing further initialization. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_SPIV_APIC_ENABLED; + apic_write(APIC_SPIV, value); + #ifdef CONFIG_X86_32 /* Pound the ESR really hard over the head with a big hammer - mbligh */ if (lapic_is_integrated() && apic->disable_esr) { @@ -1371,16 +1462,21 @@ void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = - logical_smp_processor_id(); + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* @@ -1391,45 +1487,7 @@ void setup_local_APIC(void) value &= ~APIC_TPRI_MASK; apic_write(APIC_TASKPRI, value); - /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. - */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) { - ack_APIC_irq(); - acked++; - } - } - } - if (acked > 256) { - printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", - acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); - } else - max_loops--; - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + apic_pending_intr_clear(); /* * Now that we are all set up, enable the APIC diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index e12fbcfc9571..a527f2a712b4 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -38,32 +38,12 @@ static int bigsmp_early_logical_apicid(int cpu) return early_per_cpu(x86_cpu_to_apicid, cpu); } -static inline unsigned long calculate_ldr(int cpu) -{ - unsigned long val, id; - - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - id = per_cpu(x86_bios_cpu_apicid, cpu); - val |= SET_APIC_LOGICAL_ID(id); - - return val; -} - /* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... + * bigsmp enables physical destination mode + * and doesn't use LDR and DFR */ static void bigsmp_init_apic_ldr(void) { - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_FLAT); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); } static void bigsmp_setup_apic_routing(void) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 96a8a68f9c79..566b7bc5deaa 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2342,7 +2342,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use * gsi_top if ioapic_dynirq_base hasn't been initialized yet. */ - return ioapic_initialized ? ioapic_dynirq_base : gsi_top; + if (!ioapic_initialized) + return gsi_top; + /* + * For DT enabled machines ioapic_dynirq_base is irrelevant and not + * updated. So simply return @from if ioapic_dynirq_base == 0. + */ + return ioapic_dynirq_base ? : from; } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 570e8bb1f386..e13ddd19a76c 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,7 +28,7 @@ obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o tsx.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ecf82859f1c0..3914f9218a6b 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -772,6 +772,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c) msr_set_bit(MSR_AMD64_DE_CFG, 31); } +static bool rdrand_force; + +static int __init rdrand_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "force")) + rdrand_force = true; + else + return -EINVAL; + + return 0; +} +early_param("rdrand", rdrand_cmdline); + +static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c) +{ + /* + * Saving of the MSR used to hide the RDRAND support during + * suspend/resume is done by arch/x86/power/cpu.c, which is + * dependent on CONFIG_PM_SLEEP. + */ + if (!IS_ENABLED(CONFIG_PM_SLEEP)) + return; + + /* + * The nordrand option can clear X86_FEATURE_RDRAND, so check for + * RDRAND support using the CPUID function directly. + */ + if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force) + return; + + msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62); + + /* + * Verify that the CPUID change has occurred in case the kernel is + * running virtualized and the hypervisor doesn't support the MSR. + */ + if (cpuid_ecx(1) & BIT(30)) { + pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n"); + return; + } + + clear_cpu_cap(c, X86_FEATURE_RDRAND); + pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n"); +} + +static void init_amd_jg(struct cpuinfo_x86 *c) +{ + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -786,14 +844,24 @@ static void init_amd_bd(struct cpuinfo_x86 *c) wrmsrl_safe(MSR_F15H_IC_CFG, value); } } + + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); } static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); - /* Fix erratum 1076: CPB feature bit not being set in CPUID. */ - if (!cpu_has(c, X86_FEATURE_CPB)) + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. + * Always set it, except when running under a hypervisor. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -825,6 +893,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x16: init_amd_jg(c); break; case 0x17: init_amd_zn(c); break; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2769e0f5c686..7896a34f53b5 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -32,10 +32,15 @@ #include <asm/intel-family.h> #include <asm/e820/api.h> +#include "cpu.h" + +static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init mds_print_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -96,18 +101,19 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_STIBP)) x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper spectre mitigation before patching alternatives */ + /* Select the proper CPU mitigations before patching alternatives: */ + spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); - - /* - * Select proper mitigation for any exposure to the Speculative Store - * Bypass vulnerability. - */ ssb_select_mitigation(); - l1tf_select_mitigation(); - mds_select_mitigation(); + taa_select_mitigation(); + + /* + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. + */ + mds_print_mitigation(); arch_smt_update(); @@ -246,6 +252,12 @@ static void __init mds_select_mitigation(void) (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } +} + +static void __init mds_print_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) + return; pr_info("%s\n", mds_strings[mds_mitigation]); } @@ -272,6 +284,205 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* + * TAA mitigation via VERW is turned off if both + * tsx_async_abort=off and mds=off are specified. + */ + if (taa_mitigation == TAA_MITIGATION_OFF && + mds_mitigation == MDS_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + + /* + * Update MDS mitigation, if necessary, as the mds_user_clear is + * now enabled for TAA mitigation. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V1 : " fmt + +enum spectre_v1_mitigation { + SPECTRE_V1_MITIGATION_NONE, + SPECTRE_V1_MITIGATION_AUTO, +}; + +static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = + SPECTRE_V1_MITIGATION_AUTO; + +static const char * const spectre_v1_strings[] = { + [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", + [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", +}; + +/* + * Does SMAP provide full mitigation against speculative kernel access to + * userspace? + */ +static bool smap_works_speculatively(void) +{ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return false; + + /* + * On CPUs which are vulnerable to Meltdown, SMAP does not + * prevent speculative access to user data in the L1 cache. + * Consider SMAP to be non-functional as a mitigation on these + * CPUs. + */ + if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) + return false; + + return true; +} + +static void __init spectre_v1_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return; + } + + if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { + /* + * With Spectre v1, a user can speculatively control either + * path of a conditional swapgs with a user-controlled GS + * value. The mitigation is to add lfences to both code paths. + * + * If FSGSBASE is enabled, the user can put a kernel address in + * GS, in which case SMAP provides no protection. + * + * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the + * FSGSBASE enablement patches have been merged. ] + * + * If FSGSBASE is disabled, the user can only put a user space + * address in GS. That makes an attack harder, but still + * possible if there's no SMAP protection. + */ + if (!smap_works_speculatively()) { + /* + * Mitigation can be provided from SWAPGS itself or + * PTI as the CR3 write in the Meltdown mitigation + * is serializing. + * + * If neither is there, mitigate with an LFENCE to + * stop speculation through swapgs. + */ + if (boot_cpu_has_bug(X86_BUG_SWAPGS) && + !boot_cpu_has(X86_FEATURE_PTI)) + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); + + /* + * Enable lfences in the kernel entry (non-swapgs) + * paths, to prevent user entry from speculatively + * skipping swapgs. + */ + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); + } + } + + pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); +} + +static int __init nospectre_v1_cmdline(char *str) +{ + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return 0; +} +early_param("nospectre_v1", nospectre_v1_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = @@ -685,13 +896,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void arch_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -717,6 +925,17 @@ void arch_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -821,6 +1040,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* + * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper + * bit in the mask to allow guests to use the mitigation even in the + * case where the host does not enable it. + */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + } + + /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -837,7 +1066,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); } } @@ -1023,6 +1251,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1178,16 +1409,29 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) { - if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sprintf(buf, "%s; SMT Host state unknown\n", mds_strings[mds_mitigation]); } @@ -1202,6 +1446,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1246,7 +1505,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], @@ -1267,6 +1526,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1303,4 +1568,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ebe547b1ffce..3d805e8b3739 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -768,6 +768,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c) } } +static void init_cqm(struct cpuinfo_x86 *c) +{ + if (!cpu_has(c, X86_FEATURE_CQM_LLC)) { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + return; + } + + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = cpuid_ebx(0xf); + + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) || + cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) || + cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx); + + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -799,33 +823,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_D_1_EAX] = eax; } - /* Additional Intel-defined flags: level 0x0000000F */ - if (c->cpuid_level >= 0x0000000F) { - - /* QoS sub-leaf, EAX=0Fh, ECX=0 */ - cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[CPUID_F_0_EDX] = edx; - - if (cpu_has(c, X86_FEATURE_CQM_LLC)) { - /* will be overridden if occupancy monitoring exists */ - c->x86_cache_max_rmid = ebx; - - /* QoS sub-leaf, EAX=0Fh, ECX=1 */ - cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[CPUID_F_1_EDX] = edx; - - if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) || - ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) || - (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) { - c->x86_cache_max_rmid = ecx; - c->x86_cache_occ_scale = ebx; - } - } else { - c->x86_cache_max_rmid = -1; - c->x86_cache_occ_scale = -1; - } - } - /* AMD-defined flags: level 0x80000001 */ eax = cpuid_eax(0x80000000); c->extended_cpuid_level = eax; @@ -863,6 +860,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) init_scattered_cpuid_features(c); init_speculation_control(c); + init_cqm(c); /* * Clear/Set all flags overridden by options, after probe. @@ -899,12 +897,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) c->x86_cache_bits = c->x86_phys_bits; } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -922,35 +922,45 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_TREMONT_X, NO_ITLB_MULTIHIT), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; @@ -961,19 +971,30 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -987,6 +1008,24 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } + if (!cpu_matches(NO_SWAPGS)) + setup_force_cpu_bug(X86_BUG_SWAPGS); + + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1027,6 +1066,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); c->extended_cpuid_level = 0; + if (!have_cpuid_p()) + identify_cpu_without_cpuid(c); + /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); @@ -1043,7 +1085,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); } else { - identify_cpu_without_cpuid(c); setup_clear_cpu_cap(X86_FEATURE_CPUID); } @@ -1397,6 +1438,7 @@ void __init identify_boot_cpu(void) enable_sep_cpu(); #endif cpu_detect_tlb(&boot_cpu_data); + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index cca588407dca..db10a63687d3 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -45,6 +45,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); extern int detect_extended_topology_early(struct cpuinfo_x86 *c); @@ -54,4 +70,6 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 904b0a3c4e53..4c9fc6a4d1ea 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -59,6 +59,9 @@ const static struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, {} }; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index fa61c870ada9..1d9b8aaea06c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -437,7 +437,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) /* enable MAPEN */ setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable cpuid */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80); /* disable MAPEN */ setCx86(CX86_CCR3, ccr3); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 574dcdc092ab..3a5ea741701b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -695,6 +695,11 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index f6ea94f8954a..f892cb0b485e 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -313,6 +313,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 8fec687b3e44..f12141ba9a76 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -108,6 +108,9 @@ static void setup_inj_struct(struct mce *m) memset(m, 0, sizeof(struct mce)); m->cpuvendor = boot_cpu_data.x86_vendor; + m->time = ktime_get_real_seconds(); + m->cpuid = cpuid_eax(1); + m->microcode = boot_cpu_data.microcode; } /* Update fake mce registers on current CPU. */ @@ -576,6 +579,9 @@ static int inj_bank_set(void *data, u64 val) m->bank = val; do_inject(); + /* Reset injection struct */ + setup_inj_struct(&i_mce); + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 4f3be91f0b0b..c7bd2e549a6a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1660,36 +1660,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 hwcr; - bool need_toggle; - u32 msrs[] = { - 0x00000413, /* MC4_MISC0 */ - 0xc0000408, /* MC4_MISC1 */ - }; - - rdmsrl(MSR_K7_HWCR, hwcr); - - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); - - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - - /* Clear CntP bit safely */ - for (i = 0; i < ARRAY_SIZE(msrs); i++) - msr_clear_bit(msrs[i], 62); - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 4fa97a44e73f..b434780ae680 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -544,6 +544,40 @@ out: return offset; } +/* + * Turn off MC4_MISC thresholding banks on all family 0x15 models since + * they're not supported there. + */ +void disable_err_thresholding(struct cpuinfo_x86 *c) +{ + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { + 0x00000413, /* MC4_MISC0 */ + 0xc0000408, /* MC4_MISC1 */ + }; + + if (c->x86 != 0x15) + return; + + rdmsrl(MSR_K7_HWCR, hwcr); + + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); + + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); + + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -551,6 +585,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int bank, block, cpu = smp_processor_id(); int offset = -1; + disable_err_thresholding(c); + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) smca_configure(bank, cpu); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b6b44017cf16..93c22e7ee424 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -790,13 +790,16 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static int mc_cpu_online(unsigned int cpu) +static int mc_cpu_starting(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); microcode_update_cpu(cpu); pr_debug("CPU%d added\n", cpu); + return 0; +} + +static int mc_cpu_online(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); @@ -873,6 +876,8 @@ int __init microcode_init(void) goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); + cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", + mc_cpu_starting, NULL); cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", mc_cpu_online, mc_cpu_down_prep); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index d0dfb892c72f..aed45b8895d5 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -4,6 +4,8 @@ # Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # +set -e + IN=$1 OUT=$2 diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index df11f5d604be..ed7ce5184a77 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,6 +21,10 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, + { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, + { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, + { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..3e20d322bc98 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the + * RTM CPUID bit. Clear it here since it is now + * expected to be not set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the + * RTM CPUID bit. Force it here since it is now + * expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + } +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c020ba4b7eb6..ccc2b9d2956a 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -22,6 +22,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/module.h> +#include <linux/memory.h> #include <trace/syscall.h> @@ -36,6 +37,7 @@ int ftrace_arch_code_modify_prepare(void) { + mutex_lock(&text_mutex); set_kernel_text_rw(); set_all_modules_text_rw(); return 0; @@ -45,6 +47,7 @@ int ftrace_arch_code_modify_post_process(void) { set_all_modules_text_ro(); set_kernel_text_ro(); + mutex_unlock(&text_mutex); return 0; } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 45b5c6c4a55e..e00ccbcc2913 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -117,26 +117,27 @@ unsigned long __head __startup_64(unsigned long physaddr, pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; - i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + pgtable_flags; - p4d[i + 1] = (pgdval_t)pud + pgtable_flags; + i = physaddr >> P4D_SHIFT; + p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags; + p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags; } else { i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; pgd[i + 0] = (pgdval_t)pud + pgtable_flags; pgd[i + 1] = (pgdval_t)pud + pgtable_flags; } - i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + pgtable_flags; - pud[i + 1] = (pudval_t)pmd + pgtable_flags; + i = physaddr >> PUD_SHIFT; + pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags; + pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { - int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; - pmd[idx] = pmd_entry + i * PMD_SIZE; + int idx = i + (physaddr >> PMD_SHIFT); + + pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE; } /* @@ -144,13 +145,31 @@ unsigned long __head __startup_64(unsigned long physaddr, * we might write invalid pmds, when the kernel is relocated * cleanup_highmap() fixes this up along with the mappings * beyond _end. + * + * Only the region occupied by the kernel image has so far + * been checked against the table of usable memory regions + * provided by the firmware, so invalidate pages outside that + * region. A page table entry that maps to a reserved area of + * memory would allow processor speculation into that area, + * and on some hardware (particularly the UV platform) even + * speculative access to some reserved areas is caught as an + * error, causing the BIOS to halt the system. */ pmd = fixup_pointer(level2_kernel_pgt, physaddr); - for (i = 0; i < PTRS_PER_PMD; i++) { + + /* invalidate pages before the kernel image */ + for (i = 0; i < pmd_index((unsigned long)_text); i++) + pmd[i] &= ~_PAGE_PRESENT; + + /* fixup pages that are part of the kernel image */ + for (; i <= pmd_index((unsigned long)_end); i++) if (pmd[i] & _PAGE_PRESENT) pmd[i] += load_delta; - } + + /* invalidate pages after the kernel image */ + for (; i < PTRS_PER_PMD; i++) + pmd[i] &= ~_PAGE_PRESENT; /* * Fixup phys_base - remove the memory encryption mask to obtain diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 652bdd867782..5853eb50138e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -631,6 +631,7 @@ asm( "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" "setne %al;" "ret;" +".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;" ".popsection"); #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 1c52acaa5bec..236abf77994b 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -544,17 +544,15 @@ void __init default_get_smp_config(unsigned int early) * local APIC has default address */ mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - return; + goto out; } pr_info("Default MP configuration #%d\n", mpf->feature1); construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { - if (check_physptr(mpf, early)) { - early_memunmap(mpf, sizeof(*mpf)); - return; - } + if (check_physptr(mpf, early)) + goto out; } else BUG(); @@ -563,7 +561,7 @@ void __init default_get_smp_config(unsigned int early) /* * Only use the first configuration found. */ - +out: early_memunmap(mpf, sizeof(*mpf)); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index ed5c4cdf0a34..734549492a18 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,6 +24,7 @@ #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/context_tracking.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/pgtable.h> @@ -39,6 +40,7 @@ #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/syscall.h> +#include <asm/mmu_context.h> #include "tls.h" @@ -342,6 +344,49 @@ static int set_segment_reg(struct task_struct *task, return 0; } +static unsigned long task_seg_base(struct task_struct *task, + unsigned short selector) +{ + unsigned short idx = selector >> 3; + unsigned long base; + + if (likely((selector & SEGMENT_TI_MASK) == 0)) { + if (unlikely(idx >= GDT_ENTRIES)) + return 0; + + /* + * There are no user segments in the GDT with nonzero bases + * other than the TLS segments. + */ + if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) + return 0; + + idx -= GDT_ENTRY_TLS_MIN; + base = get_desc_base(&task->thread.tls_array[idx]); + } else { +#ifdef CONFIG_MODIFY_LDT_SYSCALL + struct ldt_struct *ldt; + + /* + * If performance here mattered, we could protect the LDT + * with RCU. This is a slow path, though, so we can just + * take the mutex. + */ + mutex_lock(&task->mm->context.lock); + ldt = task->mm->context.ldt; + if (unlikely(idx >= ldt->nr_entries)) + base = 0; + else + base = get_desc_base(ldt->entries + idx); + mutex_unlock(&task->mm->context.lock); +#else + base = 0; +#endif + } + + return base; +} + #endif /* CONFIG_X86_32 */ static unsigned long get_flags(struct task_struct *task) @@ -435,18 +480,16 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset) #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct, fs_base): { - /* - * XXX: This will not behave as expected if called on - * current or if fsindex != 0. - */ - return task->thread.fsbase; + if (task->thread.fsindex == 0) + return task->thread.fsbase; + else + return task_seg_base(task, task->thread.fsindex); } case offsetof(struct user_regs_struct, gs_base): { - /* - * XXX: This will not behave as expected if called on - * current or if fsindex != 0. - */ - return task->thread.gsbase; + if (task->thread.gsindex == 0) + return task->thread.gsbase; + else + return task_seg_base(task, task->thread.gsindex); } #endif } @@ -653,7 +696,8 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) unsigned long val = 0; if (n < HBP_NUM) { - struct perf_event *bp = thread->ptrace_bps[n]; + int index = array_index_nospec(n, HBP_NUM); + struct perf_event *bp = thread->ptrace_bps[index]; if (bp) val = bp->hw.info.address; diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 04adc8d60aed..b2b87b91f336 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -181,6 +181,12 @@ asmlinkage __visible void smp_reboot_interrupt(void) irq_exit(); } +static int register_stop_handler(void) +{ + return register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, + NMI_FLAG_FIRST, "smp_stop"); +} + static void native_stop_other_cpus(int wait) { unsigned long flags; @@ -214,39 +220,41 @@ static void native_stop_other_cpus(int wait) apic->send_IPI_allbutself(REBOOT_VECTOR); /* - * Don't wait longer than a second if the caller - * didn't ask us to wait. + * Don't wait longer than a second for IPI completion. The + * wait request is not checked here because that would + * prevent an NMI shutdown attempt in case that not all + * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && (wait || timeout--)) + while (num_online_cpus() > 1 && timeout--) udelay(1); } - - /* if the REBOOT_VECTOR didn't work, try with the NMI */ - if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi)) { - if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, - NMI_FLAG_FIRST, "smp_stop")) - /* Note: we ignore failures here */ - /* Hope the REBOOT_IRQ is good enough */ - goto finish; - - /* sync above data before sending IRQ */ - wmb(); - pr_emerg("Shutting down cpus with NMI\n"); + /* if the REBOOT_VECTOR didn't work, try with the NMI */ + if (num_online_cpus() > 1) { + /* + * If NMI IPI is enabled, try to register the stop handler + * and send the IPI. In any case try to wait for the other + * CPUs to stop. + */ + if (!smp_no_nmi_ipi && !register_stop_handler()) { + /* Sync above data before sending IRQ */ + wmb(); - apic->send_IPI_allbutself(NMI_VECTOR); + pr_emerg("Shutting down cpus with NMI\n"); + apic->send_IPI_allbutself(NMI_VECTOR); + } /* - * Don't wait longer than a 10 ms if the caller - * didn't ask us to wait. + * Don't wait longer than 10 ms if the caller didn't + * reqeust it. If wait is true, the machine hangs here if + * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; while (num_online_cpus() > 1 && (wait || timeout--)) udelay(1); } -finish: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 623965e86b65..897da526e40e 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -231,9 +231,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { {}, }; +/* + * Some devices have a portrait LCD but advertise a landscape resolution (and + * pitch). We simply swap width and height for these devices so that we can + * correctly deal with some of them coming with multiple resolutions. + */ +static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { + { + /* + * Lenovo MIIX310-10ICR, only some batches have the troublesome + * 800x1280 portrait screen. Luckily the portrait version has + * its own BIOS version, so we match on that. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), + }, + }, + { + /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo MIIX 320-10ICR"), + }, + }, + { + /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo ideapad D330-10IGM"), + }, + }, + {}, +}; + __init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) dmi_check_system(efifb_dmi_system_table); + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + dmi_check_system(efifb_dmi_swap_width_height)) { + u16 temp = screen_info.lfb_width; + + screen_info.lfb_width = screen_info.lfb_height; + screen_info.lfb_height = temp; + screen_info.lfb_linelength = 4 * screen_info.lfb_width; + } } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index a5b802a12212..71d3fef1edc9 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -5,6 +5,7 @@ #include <linux/user.h> #include <linux/regset.h> #include <linux/syscalls.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/desc.h> @@ -220,6 +221,7 @@ int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *u_info) { struct user_desc info; + int index; if (idx == -1 && get_user(idx, &u_info->entry_number)) return -EFAULT; @@ -227,8 +229,11 @@ int do_get_thread_area(struct task_struct *p, int idx, if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; - fill_user_desc(&info, idx, - &p->thread.tls_array[idx - GDT_ENTRY_TLS_MIN]); + index = idx - GDT_ENTRY_TLS_MIN; + index = array_index_nospec(index, + GDT_ENTRY_TLS_MAX - GDT_ENTRY_TLS_MIN + 1); + + fill_user_desc(&info, idx, &p->thread.tls_array[index]); if (copy_to_user(u_info, &info, sizeof(info))) return -EFAULT; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index b9a8f34b5e5a..73391c1bd2a9 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -518,9 +518,12 @@ struct uprobe_xol_ops { void (*abort)(struct arch_uprobe *, struct pt_regs *); }; -static inline int sizeof_long(void) +static inline int sizeof_long(struct pt_regs *regs) { - return in_ia32_syscall() ? 4 : 8; + /* + * Check registers for mode as in_xxx_syscall() does not apply here. + */ + return user_64bit_mode(regs) ? 8 : 4; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) @@ -531,9 +534,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) static int push_ret_address(struct pt_regs *regs, unsigned long ip) { - unsigned long new_sp = regs->sp - sizeof_long(); + unsigned long new_sp = regs->sp - sizeof_long(regs); - if (copy_to_user((void __user *)new_sp, &ip, sizeof_long())) + if (copy_to_user((void __user *)new_sp, &ip, sizeof_long(regs))) return -EFAULT; regs->sp = new_sp; @@ -566,7 +569,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs long correction = utask->vaddr - utask->xol_vaddr; regs->ip += correction; } else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) { - regs->sp += sizeof_long(); /* Pop incorrect return address */ + regs->sp += sizeof_long(regs); /* Pop incorrect return address */ if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen)) return -ERESTART; } @@ -675,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) * "call" insn was executed out-of-line. Just restore ->sp and restart. * We could also restore ->ip and try to call branch_emulate_op() again. */ - regs->sp += sizeof_long(); + regs->sp += sizeof_long(regs); return -ERESTART; } @@ -966,7 +969,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) { - int rasize = sizeof_long(), nleft; + int rasize = sizeof_long(regs), nleft; unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize)) @@ -984,7 +987,7 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); - force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); + force_sig(SIGSEGV, current); } return -1; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 5c82b4bc4a68..38959b173a42 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -404,7 +404,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_cpuid_1_ent(entry, function, index); @@ -481,8 +481,16 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); + entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. @@ -699,6 +707,9 @@ out: static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, u32 idx, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 9a327d5b6d1f..d78a61408243 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -47,8 +47,6 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX}, [CPUID_7_0_EBX] = { 7, 0, CPUID_EBX}, [CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX}, - [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX}, - [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX}, [CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX}, [CPUID_6_EAX] = { 6, 0, CPUID_EAX}, [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX}, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2bcadfc5b2f0..eb8b843325f4 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5298,6 +5298,8 @@ done_prefixes: ctxt->memopp->addr.mem.ea + ctxt->_eip); done: + if (rc == X86EMUL_PROPAGATE_FAULT) + ctxt->have_exception = true; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 053e4937af0c..2307f63efd20 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -209,6 +209,9 @@ static void recalculate_apic_map(struct kvm *kvm) if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) new->phys_map[xapic_id] = apic; + if (!kvm_apic_sw_enabled(apic)) + continue; + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { @@ -252,6 +255,8 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) recalculate_apic_map(apic->vcpu->kvm); } else static_key_slow_inc(&apic_sw_disabled.key); + + recalculate_apic_map(apic->vcpu->kvm); } } @@ -1962,13 +1967,11 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } } - if ((old_value ^ value) & X2APIC_ENABLE) { - if (value & X2APIC_ENABLE) { - kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); - kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); - } else - kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); - } + if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE)) + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + + if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) + kvm_x86_ops->set_virtual_apic_mode(vcpu); apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -2161,7 +2164,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!apic_enabled(apic)) + if (!kvm_apic_hw_enabled(apic)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 4b9935a38347..bc3446d3cfdf 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -16,6 +16,13 @@ #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) +enum lapic_mode { + LAPIC_MODE_DISABLED = 0, + LAPIC_MODE_INVALID = X2APIC_ENABLE, + LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE, + LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE, +}; + struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ @@ -89,6 +96,7 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); @@ -220,4 +228,10 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); + +static inline enum lapic_mode kvm_apic_mode(u64 apic_base) +{ + return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); +} + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f97b533bc6e6..c0b0135ef07f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -40,6 +40,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -48,6 +49,30 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -139,9 +164,6 @@ module_param(dbg, bool, 0644); #include <trace/events/kvm.h> -#define CREATE_TRACE_POINTS -#include "mmutrace.h" - #define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) @@ -244,6 +266,11 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); +static bool is_executable_pte(u64 spte); + +#define CREATE_TRACE_POINTS +#include "mmutrace.h" + void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { @@ -264,6 +291,11 @@ static inline bool spte_ad_enabled(u64 spte) return !(spte & shadow_acc_track_value); } +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + static inline u64 spte_shadow_accessed_mask(u64 spte) { MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); @@ -1008,10 +1040,16 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) { - if (sp->role.direct) - BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); - else + if (!sp->role.direct) { sp->gfns[index] = gfn; + return; + } + + if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index))) + pr_err_ratelimited("gfn mismatch under direct page %llx " + "(expected %llx, got %llx)\n", + sp->gfn, + kvm_mmu_page_get_gfn(sp, index), gfn); } /* @@ -1070,6 +1108,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1087,6 +1136,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -2634,6 +2690,9 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return ret; } @@ -2788,6 +2847,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -2903,10 +2967,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, ret = RET_PF_EMULATE; pgprintk("%s: setting spte %llx\n", __func__, *sptep); - pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", - is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn, - *sptep, sptep); + trace_kvm_mmu_set_spte(level, gfn, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -2918,8 +2979,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, } } - kvm_release_pfn_clean(pfn); - return ret; } @@ -2954,9 +3013,11 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, if (ret <= 0) return -1; - for (i = 0; i < ret; i++, gfn++, start++) + for (i = 0; i < ret; i++, gfn++, start++) { mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, page_to_pfn(pages[i]), true, true); + put_page(pages[i]); + } return 0; } @@ -3004,40 +3065,71 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { - struct kvm_shadow_walk_iterator iterator; + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, + int map_writable, int level, kvm_pfn_t pfn, + bool prefault, bool lpage_disallowed) +{ + struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int emulate = 0; - gfn_t pseudo_gfn; + int ret; + gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t base_gfn = gfn; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return 0; + return RET_PF_RETRY; - for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { - if (iterator.level == level) { - emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, level, gfn, pfn, prefault, - map_writable); - direct_pte_prefetch(vcpu, iterator.sptep); - ++vcpu->stat.pf_fixed; - break; - } + trace_kvm_mmu_spte_requested(gpa, level, pfn); + for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); - drop_large_spte(vcpu, iterator.sptep); - if (!is_shadow_present_pte(*iterator.sptep)) { - u64 base_addr = iterator.addr; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == level) + break; - base_addr &= PT64_LVL_ADDR_MASK(iterator.level); - pseudo_gfn = base_addr >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, 1, ACC_ALL); + drop_large_spte(vcpu, it.sptep); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, + it.level - 1, true, ACC_ALL); - link_shadow_page(vcpu, iterator.sptep, sp); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } - return emulate; + + ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, + write, level, base_gfn, pfn, prefault, + map_writable); + direct_pte_prefetch(vcpu, it.sptep); + ++vcpu->stat.pf_fixed; + return ret; } static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) @@ -3072,11 +3164,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, kvm_pfn_t *pfnp, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { kvm_pfn_t pfn = *pfnp; - gfn_t gfn = *gfnp; int level = *levelp; /* @@ -3086,7 +3177,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -3103,8 +3194,6 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, mask = KVM_PAGES_PER_HPAGE(level) - 1; VM_BUG_ON((gfn & mask) != (pfn & mask)); if (pfn & mask) { - gfn &= ~mask; - *gfnp = gfn; kvm_release_pfn_clean(pfn); pfn &= ~mask; kvm_get_pfn(pfn); @@ -3331,11 +3420,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3361,22 +3453,20 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } @@ -3922,6 +4012,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -3932,8 +4024,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -3954,22 +4047,20 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -4313,11 +4404,11 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, */ /* Faults from writes to non-writable pages */ - u8 wf = (pfec & PFERR_WRITE_MASK) ? ~w : 0; + u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0; /* Faults from user mode accesses to supervisor pages */ - u8 uf = (pfec & PFERR_USER_MASK) ? ~u : 0; + u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0; /* Faults from fetches of non-executable pages*/ - u8 ff = (pfec & PFERR_FETCH_MASK) ? ~x : 0; + u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0; /* Faults from kernel mode fetches of user pages */ u8 smepf = 0; /* Faults from kernel mode accesses of user pages */ @@ -5253,9 +5344,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { drop_spte(kvm, sptep); need_tlb_flush = 1; goto restart; @@ -5454,7 +5545,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -5504,7 +5595,7 @@ unlock: break; } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); return freed; } @@ -5528,8 +5619,58 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + int idx; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + idx = srcu_read_lock(&kvm->srcu); + kvm_mmu_invalidate_zap_all_pages(kvm); + srcu_read_unlock(&kvm->srcu, idx); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + kvm_mmu_reset_all_pte_masks(); pte_list_desc_cache = kmem_cache_create("pte_list_desc", @@ -5595,3 +5736,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index efc857615d8e..068feab64acf 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -195,4 +195,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index c73bf4e4988c..918b0d5bf272 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -325,6 +325,65 @@ TRACE_EVENT( __entry->kvm_gen == __entry->spte_gen ) ); + +TRACE_EVENT( + kvm_mmu_set_spte, + TP_PROTO(int level, gfn_t gfn, u64 *sptep), + TP_ARGS(level, gfn, sptep), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, spte) + __field(u64, sptep) + __field(u8, level) + /* These depend on page entry type, so compute them now. */ + __field(bool, r) + __field(bool, x) + __field(u8, u) + ), + + TP_fast_assign( + __entry->gfn = gfn; + __entry->spte = *sptep; + __entry->sptep = virt_to_phys(sptep); + __entry->level = level; + __entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK); + __entry->x = is_executable_pte(__entry->spte); + __entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1; + ), + + TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx", + __entry->gfn, __entry->spte, + __entry->r ? "r" : "-", + __entry->spte & PT_WRITABLE_MASK ? "w" : "-", + __entry->x ? "x" : "-", + __entry->u == -1 ? "" : (__entry->u ? "u" : "-"), + __entry->level, __entry->sptep + ) +); + +TRACE_EVENT( + kvm_mmu_spte_requested, + TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn), + TP_ARGS(addr, level, pfn), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, pfn) + __field(u8, level) + ), + + TP_fast_assign( + __entry->gfn = addr >> PAGE_SHIFT; + __entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + __entry->level = level; + ), + + TP_printk("gfn %llx pfn %llx level %d", + __entry->gfn, __entry->pfn, __entry->level + ) +); + #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6288e9d7068e..8cf7a09bdd73 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -522,6 +522,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + kvm_release_pfn_clean(pfn); return true; } @@ -595,12 +596,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -645,35 +648,48 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - for (; - shadow_walk_okay(&it) && it.level > hlevel; - shadow_walk_next(&it)) { - gfn_t direct_gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; + trace_kvm_mmu_spte_requested(addr, gw->level, pfn); + + for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - validate_direct_spte(vcpu, it.sptep, direct_access); - drop_large_spte(vcpu, it.sptep); + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); - if (is_shadow_present_pte(*it.sptep)) - continue; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == hlevel) + break; + + validate_direct_spte(vcpu, it.sptep, direct_access); - direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + drop_large_spte(vcpu, it.sptep); - sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access); - link_shadow_page(vcpu, it.sptep, sp); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, addr, + it.level - 1, true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); + } } - clear_sp_write_flooding_count(it.sptep); ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, gw->gfn, pfn, prefault, map_writable); + it.level, base_gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - + ++vcpu->stat.pf_fixed; return ret; out_gpte_changed: - kvm_release_pfn_clean(pfn); return RET_PF_RETRY; } @@ -740,9 +756,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -821,6 +839,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, walker.pte_access &= ~ACC_EXEC_MASK; } + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; @@ -829,19 +848,15 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (!force_pt_level) - transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); + transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); - ++vcpu->stat.pf_fixed; + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 026db42a86c3..1bca8016ee8a 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -131,8 +131,8 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm_pmu: event creation failed %ld\n", - PTR_ERR(event)); + pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", + PTR_ERR(event), pmc->idx); return; } diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 5ab4a364348e..2729131fe9bf 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -235,11 +235,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, msr))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { + if (msr_info->host_initiated) + pmc->counter = data; + else + pmc->counter = (s32)data; + return 0; + } else if ((pmc = get_fixed_pmc(pmu, msr))) { + pmc->counter = data; return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3a7e79f6cc77..52edb8cf1c40 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -299,7 +299,7 @@ static int vgif = true; module_param(vgif, int, 0444); static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); @@ -608,8 +608,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -2097,7 +2103,7 @@ static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); vcpu->arch.cr4 = cr4; if (!npt_enabled) @@ -2438,7 +2444,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, @@ -3111,7 +3117,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; svm->nested.intercept = nested_vmcb->control.intercept; - svm_flush_tlb(&svm->vcpu); + svm_flush_tlb(&svm->vcpu, true); svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; @@ -4589,7 +4595,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) set_cr_intercept(svm, INTERCEPT_CR8_WRITE); } -static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { return; } @@ -4637,6 +4643,11 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_vcpu_wake_up(vcpu); } +static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return false; +} + static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) { unsigned long flags; @@ -4942,7 +4953,7 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void svm_flush_tlb(struct kvm_vcpu *vcpu) +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5283,7 +5294,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) @@ -5297,7 +5308,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static int is_disabled(void) @@ -5708,7 +5719,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, - .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .set_virtual_apic_mode = svm_set_virtual_apic_mode, .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, @@ -5746,6 +5757,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .pmu_ops = &amd_pmu_ops, .deliver_posted_interrupt = svm_deliver_avic_intr, + .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, }; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9b2486e8ec00..c579cda1721e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -591,7 +591,8 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - bool change_vmcs01_virtual_x2apic_mode; + bool change_vmcs01_virtual_apic_mode; + /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; @@ -1601,7 +1602,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) return -1; } -static inline void __invvpid(int ext, u16 vpid, gva_t gva) +static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) { struct { u64 vpid : 16; @@ -1615,7 +1616,7 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva) : : "a"(&operand), "c"(ext) : "cc", "memory"); } -static inline void __invept(int ext, u64 eptp, gpa_t gpa) +static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) { struct { u64 eptp, gpa; @@ -2258,17 +2259,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -2825,9 +2818,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_CSTAR); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - move_msr_up(vmx, index, save_nmsrs++); /* * MSR_STAR is only needed on long mode guests, and only * if efer.sce is enabled. @@ -2840,6 +2830,9 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_EFER); if (index >= 0 && update_transition_efer(vmx, index)) move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_TSC_AUX); + if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) + move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; @@ -4427,9 +4420,10 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid, + bool invalidate_gpa) { - if (enable_ept) { + if (enable_ept && (invalidate_gpa || !enable_vpid)) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa)); @@ -4438,15 +4432,9 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) } } -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) -{ - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); -} - -static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) +static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { - if (enable_ept) - vmx_flush_tlb(vcpu); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -4480,7 +4468,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) (unsigned long *)&vcpu->arch.regs_dirty)) return; - if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (is_pae_paging(vcpu)) { vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); @@ -4492,7 +4480,7 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (is_pae_paging(vcpu)) { mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); @@ -4644,7 +4632,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) ept_load_pdptrs(vcpu); } - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); vmcs_writel(GUEST_CR3, guest_cr3); } @@ -7694,6 +7682,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmx->nested.sync_shadow_vmcs = false; } static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) @@ -7705,7 +7694,6 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); - vmx->nested.sync_shadow_vmcs = false; vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; @@ -7891,6 +7879,9 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) const unsigned long *fields = shadow_read_write_fields; const int num_fields = max_shadow_read_write_fields; + if (WARN_ON(!shadow_vmcs)) + return; + preempt_disable(); vmcs_load(shadow_vmcs); @@ -7938,6 +7929,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) u64 field_value = 0; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; + if (WARN_ON(!shadow_vmcs)) + return; + vmcs_load(shadow_vmcs); for (q = 0; q < ARRAY_SIZE(fields); q++) { @@ -7990,6 +7984,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gva_t gva = 0; + struct x86_exception e; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -8017,8 +8012,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu) vmx_instruction_info, true, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - kvm_write_guest_virt_system(vcpu, gva, &field_value, - (is_long_mode(vcpu) ? 8 : 4), NULL); + if (kvm_write_guest_virt_system(vcpu, gva, &field_value, + (is_long_mode(vcpu) ? 8 : 4), + &e)) + kvm_inject_page_fault(vcpu, &e); } nested_vmx_succeed(vcpu); @@ -8305,7 +8302,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } - __vmx_flush_tlb(vcpu, vmx->nested.vpid02); + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -9286,31 +9283,43 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) vmcs_write32(TPR_THRESHOLD, irr); } -static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { u32 sec_exec_control; + if (!lapic_in_kernel(vcpu)) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { - to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_has_vmx_virtualize_x2apic_mode()) - return; - if (!cpu_need_tpr_shadow(vcpu)) return; sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); - if (set) { - sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - } else { - sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb_ept_only(vcpu); + switch (kvm_get_apic_mode(vcpu)) { + case LAPIC_MODE_INVALID: + WARN_ONCE(true, "Invalid local APIC state"); + case LAPIC_MODE_DISABLED: + break; + case LAPIC_MODE_XAPIC: + if (flexpriority_enabled) { + sec_exec_control |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmx_flush_tlb(vcpu, true); + } + break; + case LAPIC_MODE_X2APIC: + if (cpu_has_vmx_virtualize_x2apic_mode()) + sec_exec_control |= + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + break; } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -9338,7 +9347,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) !nested_cpu_has2(get_vmcs12(&vmx->vcpu), SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } } @@ -9425,6 +9434,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } +static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return pi_test_on(vcpu_to_pi_desc(vcpu)); +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -10892,8 +10906,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * If PAE paging and EPT are both on, CR3 is not used by the CPU and * must not be dereferenced. */ - if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) && - !nested_ept) { + if (is_pae_paging(vcpu) && !nested_ept) { if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) { *entry_failure_code = ENTRY_FAIL_PDPTE; return 1; @@ -11200,11 +11213,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true); } } else { vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } } @@ -11228,7 +11241,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } } else if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* @@ -11907,7 +11920,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * L1's vpid. TODO: move to a more elaborate solution, giving * each L2 its own vpid and exposing the vpid feature to L1. */ - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } /* Restore posted intr vector. */ if (nested_cpu_has_posted_intr(vmcs12)) @@ -12176,14 +12189,13 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); - if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { - vmx->nested.change_vmcs01_virtual_x2apic_mode = false; - vmx_set_virtual_x2apic_mode(vcpu, - vcpu->arch.apic_base & X2APIC_ENABLE); + if (vmx->nested.change_vmcs01_virtual_apic_mode) { + vmx->nested.change_vmcs01_virtual_apic_mode = false; + vmx_set_virtual_apic_mode(vcpu); } else if (!nested_cpu_has_ept(vmcs12) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* This is needed for same reason as it was needed in prepare_vmcs02 */ @@ -12740,7 +12752,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, - .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, @@ -12750,6 +12762,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 858dd0d89b02..8a51442247c5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,8 +90,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -191,7 +191,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -275,13 +276,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -306,23 +308,27 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_apic_base); +enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) +{ + return kvm_apic_mode(kvm_get_apic_base(vcpu)); +} +EXPORT_SYMBOL_GPL(kvm_get_apic_mode); + int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 old_state = vcpu->arch.apic_base & - (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); - u64 new_state = msr_info->data & - (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); + enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff | (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); - if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE) - return 1; - if (!msr_info->host_initiated && - ((new_state == MSR_IA32_APICBASE_ENABLE && - old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) || - (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) && - old_state == 0))) + if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) return 1; + if (!msr_info->host_initiated) { + if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC) + return 1; + if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC) + return 1; + } kvm_lapic_set_base(vcpu, msr_info->data); return 0; @@ -563,8 +569,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, data, offset, len, access); } +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | + rsvd_bits(1, 2); +} + /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { @@ -583,8 +595,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { ret = 0; goto out; } @@ -610,7 +621,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (!is_pae_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -839,8 +850,8 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_long_mode(vcpu) && (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) return 1; - else if (is_pae(vcpu) && is_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + else if (is_pae_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; vcpu->arch.cr3 = cr3; @@ -1061,6 +1072,14 @@ u64 kvm_get_arch_capabilities(void) rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1072,8 +1091,40 @@ u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~ARCH_CAP_TAA_NO; + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; + else if (data & ARCH_CAP_TSX_CTRL_MSR) + data &= ~ARCH_CAP_MDS_NO; + + /* KVM does not emulate MSR_IA32_TSX_CTRL. */ + data &= ~ARCH_CAP_TSX_CTRL_MSR; return data; } + EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) @@ -1392,7 +1443,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) vcpu->arch.tsc_always_catchup = 1; return 0; } else { - WARN(1, "user requested TSC rate below hardware speed\n"); + pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } @@ -1402,8 +1453,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) user_tsc_khz, tsc_khz); if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { - WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); + pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); return -1; } @@ -4721,6 +4772,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, /* kvm_write_guest_virt_system can pull in tons of pages. */ vcpu->arch.l1tf_flush_l1d = true; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } @@ -5885,8 +5943,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, emulation_type)) return EMULATE_DONE; - if (ctxt->have_exception && inject_emulated_exception(vcpu)) + if (ctxt->have_exception) { + /* + * #UD should result in just EMULATION_FAILED, and trap-like + * exception should not be encountered during decode. + */ + WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || + exception_type(ctxt->exception.vector) == EXCPT_TRAP); + inject_emulated_exception(vcpu); return EMULATE_DONE; + } if (emulation_type & EMULTYPE_SKIP) return EMULATE_FAIL; return handle_emulation_failure(vcpu); @@ -5954,12 +6020,13 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) - kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || - exception_type(ctxt->exception.vector) == EXCPT_TRAP) + exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_rip_write(vcpu, ctxt->eip); + if (r == EMULATE_DONE && ctxt->tf) + kvm_vcpu_do_singlestep(vcpu, &r); __kvm_set_rflags(vcpu, ctxt->eflags); + } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will @@ -6104,17 +6171,17 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - if (vcpu->cpu != smp_processor_id()) + if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -6251,12 +6318,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -6922,10 +6989,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) +static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); + kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -6996,7 +7063,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - kvm_vcpu_flush_tlb(vcpu); + kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; @@ -7726,7 +7793,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (is_pae_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8309,6 +8376,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -8338,6 +8406,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { int r; @@ -8441,6 +8514,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { @@ -8711,6 +8789,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + kvm_test_request(KVM_REQ_SMI, vcpu) || + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu)) + return true; + + return false; +} + bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return vcpu->arch.preempted_in_kernel; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index c88305d997b0..68eb0d03e5fc 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -94,6 +94,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG)); } +static inline bool is_pae_paging(struct kvm_vcpu *vcpu) +{ + return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu); +} + static inline u32 bit(int bitno) { return 1 << (bitno & 31); diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index 2dd1fe13a37b..19f707992db2 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -1,5 +1,6 @@ #include <linux/types.h> #include <linux/export.h> +#include <asm/cpu.h> unsigned int x86_family(unsigned int sig) { diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 4846eff7e4c8..17a0d0f5a1bf 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops) __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* - * AMD, like Intel, supports the EAX hint and EAX=0xf - * means, do not enter any deep C-state and we use it + * AMD, like Intel's MWAIT version, supports the EAX hint and + * EAX=0xf0 means, do not enter any deep C-state and we use it * here in delay() to minimize wakeup latency. */ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h index a5a41ec58072..0c122226ca56 100644 --- a/arch/x86/math-emu/fpu_emu.h +++ b/arch/x86/math-emu/fpu_emu.h @@ -177,7 +177,7 @@ static inline void reg_copy(FPU_REG const *x, FPU_REG *y) #define setexponentpos(x,y) { (*(short *)&((x)->exp)) = \ ((y) + EXTENDED_Ebias) & 0x7fff; } #define exponent16(x) (*(short *)&((x)->exp)) -#define setexponent16(x,y) { (*(short *)&((x)->exp)) = (y); } +#define setexponent16(x,y) { (*(short *)&((x)->exp)) = (u16)(y); } #define addexponent(x,y) { (*(short *)&((x)->exp)) += (y); } #define stdexp(x) { (*(short *)&((x)->exp)) += EXTENDED_Ebias; } diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c index 8dc9095bab22..742619e94bdf 100644 --- a/arch/x86/math-emu/reg_constant.c +++ b/arch/x86/math-emu/reg_constant.c @@ -18,7 +18,7 @@ #include "control_w.h" #define MAKE_REG(s, e, l, h) { l, h, \ - ((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) } + (u16)((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) } FPU_REG const CONST_1 = MAKE_REG(POS, 0, 0x00000000, 0x80000000); #if 0 diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b162f92fd55c..27cab342a0b2 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -260,13 +260,14 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); - if (!pmd_present(*pmd_k)) - return NULL; - if (!pmd_present(*pmd)) + if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); + + if (!pmd_present(*pmd_k)) + return NULL; else - BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k)); + BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } @@ -286,17 +287,13 @@ void vmalloc_sync_all(void) spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; - pmd_t *ret; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - ret = vmalloc_sync_one(page_address(page), address); + vmalloc_sync_one(page_address(page), address); spin_unlock(pgt_lock); - - if (!ret) - break; } spin_unlock(&pgd_lock); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index af6f2f9c6a26..5813950b5877 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -194,7 +194,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr) if (!IS_ENABLED(CONFIG_X86_5LEVEL)) return (p4d_t *)pgd; - p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK; + p4d = pgd_val(*pgd) & PTE_PFN_MASK; p4d += __START_KERNEL_map - phys_base; return (p4d_t *)p4d + p4d_index(addr); } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index aafd4edfa2ac..b4fd36271f90 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -260,7 +260,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - pgdp[i] = native_make_pgd(0); + pgd_clear(&pgdp[i]); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -430,7 +430,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -445,7 +445,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -465,7 +465,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a9deb2b0397d..cdb386fa7101 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -16,8 +16,6 @@ #include <asm/nospec-branch.h> #include <linux/bpf.h> -int bpf_jit_enable __read_mostly; - /* * assembly code in arch/x86/net/bpf_jit.S */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 4210da7b44de..33e9b4f1ce20 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -589,6 +589,17 @@ static void pci_fixup_amd_ehci_pme(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme); /* + * Device [1022:7914] + * When in D0, PME# doesn't get asserted when plugging USB 2.0 device. + */ +static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PME# does not work under D0, disabling it\n"); + dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme); + +/* * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff] * * Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 9061babfbc83..335a62e74a2e 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -893,9 +893,6 @@ static void __init kexec_enter_virtual_mode(void) if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) runtime_code_page_mkexec(); - - /* clean DUMMY object */ - efi_delete_dummy_variable(); #endif } diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 513ce09e9950..3aa3149df07f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/tboot.h> +#include <linux/dmi.h> #include <asm/pgtable.h> #include <asm/proto.h> @@ -24,7 +25,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> -#include <linux/dmi.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -398,15 +399,14 @@ static int __init bsp_pm_check_init(void) core_initcall(bsp_pm_check_init); -static int msr_init_context(const u32 *msr_id, const int total_num) +static int msr_build_context(const u32 *msr_id, const int num) { - int i = 0; + struct saved_msrs *saved_msrs = &saved_context.saved_msrs; struct saved_msr *msr_array; + int total_num; + int i, j; - if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { - pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); - return -EINVAL; - } + total_num = saved_msrs->num + num; msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); if (!msr_array) { @@ -414,19 +414,30 @@ static int msr_init_context(const u32 *msr_id, const int total_num) return -ENOMEM; } - for (i = 0; i < total_num; i++) { - msr_array[i].info.msr_no = msr_id[i]; + if (saved_msrs->array) { + /* + * Multiple callbacks can invoke this function, so copy any + * MSR save requests from previous invocations. + */ + memcpy(msr_array, saved_msrs->array, + sizeof(struct saved_msr) * saved_msrs->num); + + kfree(saved_msrs->array); + } + + for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + msr_array[i].info.msr_no = msr_id[j]; msr_array[i].valid = false; msr_array[i].info.reg.q = 0; } - saved_context.saved_msrs.num = total_num; - saved_context.saved_msrs.array = msr_array; + saved_msrs->num = total_num; + saved_msrs->array = msr_array; return 0; } /* - * The following section is a quirk framework for problematic BIOSen: + * The following sections are a quirk framework for problematic BIOSen: * Sometimes MSRs are modified by the BIOSen after suspended to * RAM, this might cause unexpected behavior after wakeup. * Thus we save/restore these specified MSRs across suspend/resume @@ -441,7 +452,7 @@ static int msr_initialize_bdw(const struct dmi_system_id *d) u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); - return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); + return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); } static const struct dmi_system_id msr_save_dmi_table[] = { @@ -456,9 +467,58 @@ static const struct dmi_system_id msr_save_dmi_table[] = { {} }; +static int msr_save_cpuid_features(const struct x86_cpu_id *c) +{ + u32 cpuid_msr_id[] = { + MSR_AMD64_CPUID_FN_1, + }; + + pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n", + c->family); + + return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id)); +} + +static const struct x86_cpu_id msr_save_cpu_table[] = { + { + .vendor = X86_VENDOR_AMD, + .family = 0x15, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + { + .vendor = X86_VENDOR_AMD, + .family = 0x16, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + {} +}; + +typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *); +static int pm_cpu_check(const struct x86_cpu_id *c) +{ + const struct x86_cpu_id *m; + int ret = 0; + + m = x86_match_cpu(msr_save_cpu_table); + if (m) { + pm_cpu_match_t fn; + + fn = (pm_cpu_match_t)m->driver_data; + ret = fn(m); + } + + return ret; +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); + pm_cpu_check(msr_save_cpu_table); + return 0; } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 9c80966c80ba..692a179b1ba3 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -250,9 +250,9 @@ static int get_e820_md5(struct e820_table *table, void *buf) return ret; } -static void hibernation_e820_save(void *buf) +static int hibernation_e820_save(void *buf) { - get_e820_md5(e820_table_firmware, buf); + return get_e820_md5(e820_table_firmware, buf); } static bool hibernation_e820_mismatch(void *buf) @@ -272,8 +272,9 @@ static bool hibernation_e820_mismatch(void *buf) return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; } #else -static void hibernation_e820_save(void *buf) +static int hibernation_e820_save(void *buf) { + return 0; } static bool hibernation_e820_mismatch(void *buf) @@ -318,9 +319,7 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) rdr->magic = RESTORE_MAGIC; - hibernation_e820_save(rdr->e820_digest); - - return 0; + return hibernation_e820_save(rdr->e820_digest); } /** diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index a18703be9ead..4769a069d5bd 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -77,7 +77,9 @@ static efi_system_table_t __init *xen_efi_probe(void) efi.get_variable = xen_efi_get_variable; efi.get_next_variable = xen_efi_get_next_variable; efi.set_variable = xen_efi_set_variable; + efi.set_variable_nonblocking = xen_efi_set_variable; efi.query_variable_info = xen_efi_query_variable_info; + efi.query_variable_info_nonblocking = xen_efi_query_variable_info; efi.update_capsule = xen_efi_update_capsule; efi.query_capsule_caps = xen_efi_query_capsule_caps; efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 515d5e4414c2..00fc683a2011 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -259,19 +259,41 @@ void xen_reboot(int reason) BUG(); } +static int reboot_reason = SHUTDOWN_reboot; +static bool xen_legacy_crash; void xen_emergency_restart(void) { - xen_reboot(SHUTDOWN_reboot); + xen_reboot(reboot_reason); } static int xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - if (!kexec_crash_loaded()) - xen_reboot(SHUTDOWN_crash); + if (!kexec_crash_loaded()) { + if (xen_legacy_crash) + xen_reboot(SHUTDOWN_crash); + + reboot_reason = SHUTDOWN_crash; + + /* + * If panic_timeout==0 then we are supposed to wait forever. + * However, to preserve original dom0 behavior we have to drop + * into hypervisor. (domU behavior is controlled by its + * config file) + */ + if (panic_timeout == 0) + panic_timeout = -1; + } return NOTIFY_DONE; } +static int __init parse_xen_legacy_crash(char *arg) +{ + xen_legacy_crash = true; + return 0; +} +early_param("xen_legacy_crash", parse_xen_legacy_crash); + static struct notifier_block xen_panic_block = { .notifier_call = xen_panic_event, .priority = INT_MIN diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 481d7920ea24..f79a0cdc6b4e 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -598,12 +598,12 @@ struct trap_array_entry { static struct trap_array_entry trap_array[] = { { debug, xen_xendebug, true }, - { int3, xen_xenint3, true }, { double_fault, xen_double_fault, true }, #ifdef CONFIG_X86_MCE { machine_check, xen_machine_check, true }, #endif { nmi, xen_xennmi, true }, + { int3, xen_int3, false }, { overflow, xen_overflow, false }, #ifdef CONFIG_IA32_EMULATION { entry_INT80_compat, xen_entry_INT80_compat, false }, diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 417b339e5c8e..a93d8a7cef26 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -12,6 +12,7 @@ #include <asm/segment.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#include <asm/asm.h> #include <xen/interface/xen.h> @@ -24,13 +25,13 @@ ENTRY(xen_\name) pop %r11 jmp \name END(xen_\name) +_ASM_NOKPROBE(xen_\name) .endm xen_pv_trap divide_error xen_pv_trap debug xen_pv_trap xendebug xen_pv_trap int3 -xen_pv_trap xenint3 xen_pv_trap xennmi xen_pv_trap overflow xen_pv_trap bounds diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 08175df7a69e..92fb20777bb0 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -310,7 +310,8 @@ extern char _SecondaryResetVector_text_start; extern char _SecondaryResetVector_text_end; #endif -static inline int mem_reserve(unsigned long start, unsigned long end) +static inline int __init_memblock mem_reserve(unsigned long start, + unsigned long end) { return memblock_reserve(start, end - start); } @@ -507,6 +508,7 @@ void cpu_reset(void) "add %2, %2, %7\n\t" "addi %0, %0, -1\n\t" "bnez %0, 1b\n\t" + "isync\n\t" /* Jump to identity mapping */ "jx %3\n" "2:\n\t" diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 672391003e40..dc7b470a423a 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -114,13 +114,6 @@ EXPORT_SYMBOL(__invalidate_icache_range); // FIXME EXPORT_SYMBOL(screen_info); #endif -EXPORT_SYMBOL(outsb); -EXPORT_SYMBOL(outsw); -EXPORT_SYMBOL(outsl); -EXPORT_SYMBOL(insb); -EXPORT_SYMBOL(insw); -EXPORT_SYMBOL(insl); - extern long common_exception_return; EXPORT_SYMBOL(common_exception_return); |