diff options
| author | Stefan Agner <stefan.agner@toradex.com> | 2016-03-29 13:02:23 -0700 |
|---|---|---|
| committer | Stefan Agner <stefan.agner@toradex.com> | 2016-03-29 13:02:23 -0700 |
| commit | 1df133c0db64d633bbb9b238aa0e1588e2c5e7d6 (patch) | |
| tree | c68d76907c523e81b5d0e8a924728f9e1aed1844 /arch | |
| parent | 2b7d39d1a28cb478627fc22fdc8dd77ed89ffe92 (diff) | |
| parent | 62e21959dc6f25c5fce0c1a0934e4a9d982bf99b (diff) | |
Merge tag 'v4.4.5' into toradex_vf_4.4-next
This is the 4.4.5 stable release
Diffstat (limited to 'arch')
90 files changed, 937 insertions, 473 deletions
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 258b0e5ad332..68b6092349d7 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -112,6 +113,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index cbfec79137bf..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt @@ -211,7 +212,11 @@ debug_marker_syscall: ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig ; entry was via Exception in DS which got preempted in kernel). ; -; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling +; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround +; +; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline +; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly + .Lintr_ret_to_delay_slot: debug_marker_ds: @@ -222,18 +227,23 @@ debug_marker_ds: ld r2, [sp, PT_ret] ld r3, [sp, PT_status32] + ; STAT32 for Int return created from scratch + ; (No delay dlot, disable Further intr in trampoline) + bic r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK st r0, [sp, PT_status32] mov r1, .Lintr_ret_to_delay_slot_2 st r1, [sp, PT_ret] + ; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots st r2, [sp, 0] st r3, [sp, 4] b .Lisr_ret_fast_path .Lintr_ret_to_delay_slot_2: + ; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP sub sp, sp, SZ_PT_REGS st r9, [sp, -4] @@ -243,11 +253,19 @@ debug_marker_ds: ld r9, [sp, 4] sr r9, [erstatus] + ; restore AUX_USER_SP if returning to U mode + bbit0 r9, STATUS_U_BIT, 1f + ld r9, [sp, PT_sp] + sr r9, [AUX_USER_SP] + +1: ld r9, [sp, 8] sr r9, [erbta] ld r9, [sp, -4] add sp, sp, SZ_PT_REGS + + ; return from pure kernel mode to delay slot rtie END(ret_from_exception) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bd237acdf4f2..30d806ce0c78 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,12 @@ #include <linux/smp.h> #include <linux/irq.h> #include <linux/spinlock.h> +#include <asm/irqflags-arcv2.h> #include <asm/mcip.h> #include <asm/setup.h> +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + /* * NOTE: We must spin here if the other cpu hasn't yet * serviced a previous message. This can burn lots @@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq) unsigned long flags; unsigned int __maybe_unused copy; + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 259c0ca9c99a..ddbb361267d8 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -162,10 +162,9 @@ choice mobile SoCs in the Kona family of chips (e.g. bcm28155, bcm11351, etc...) - config DEBUG_BCM63XX + config DEBUG_BCM63XX_UART bool "Kernel low-level debugging on BCM63XX UART" depends on ARCH_BCM_63XX - select DEBUG_UART_BCM63XX config DEBUG_BERLIN_UART bool "Marvell Berlin SoC Debug UART" @@ -1348,7 +1347,7 @@ config DEBUG_LL_INCLUDE default "debug/vf.S" if DEBUG_VF_UART default "debug/vt8500.S" if DEBUG_VT8500_UART0 default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1 - default "debug/bcm63xx.S" if DEBUG_UART_BCM63XX + default "debug/bcm63xx.S" if DEBUG_BCM63XX_UART default "debug/digicolor.S" if DEBUG_DIGICOLOR_UA0 default "mach/debug-macro.S" @@ -1364,10 +1363,6 @@ config DEBUG_UART_8250 ARCH_IOP33X || ARCH_IXP4XX || \ ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC -# Compatibility options for BCM63xx -config DEBUG_UART_BCM63XX - def_bool ARCH_BCM_63XX - config DEBUG_UART_PHYS hex "Physical base address of debug UART" default 0x00100a00 if DEBUG_NETX_UART @@ -1462,7 +1457,7 @@ config DEBUG_UART_PHYS default 0xfffb0000 if DEBUG_OMAP1UART1 || DEBUG_OMAP7XXUART1 default 0xfffb0800 if DEBUG_OMAP1UART2 || DEBUG_OMAP7XXUART2 default 0xfffb9800 if DEBUG_OMAP1UART3 || DEBUG_OMAP7XXUART3 - default 0xfffe8600 if DEBUG_UART_BCM63XX + default 0xfffe8600 if DEBUG_BCM63XX_UART default 0xfffff700 if ARCH_IOP33X depends on ARCH_EP93XX || \ DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ @@ -1474,7 +1469,7 @@ config DEBUG_UART_PHYS DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF2 || \ DEBUG_RMOBILE_SCIFA0 || DEBUG_RMOBILE_SCIFA1 || \ DEBUG_RMOBILE_SCIFA4 || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 || \ DEBUG_AT91_UART @@ -1515,7 +1510,7 @@ config DEBUG_UART_VIRT default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT default 0xfc40ab00 if DEBUG_BRCMSTB_UART default 0xfc705000 if DEBUG_ZTE_ZX - default 0xfcfe8600 if DEBUG_UART_BCM63XX + default 0xfcfe8600 if DEBUG_BCM63XX_UART default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX default 0xfd000000 if ARCH_SPEAR13XX default 0xfd012000 if ARCH_MV78XX0 @@ -1566,7 +1561,7 @@ config DEBUG_UART_VIRT DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 config DEBUG_UART_8250_SHIFT diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index a633be3defda..cd316021d6ce 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -303,16 +303,6 @@ gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; }; - reg_usb2_1_vbus: v5-vbus1 { - compatible = "regulator-fixed"; - regulator-name = "v5.0-vbus1"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - enable-active-high; - regulator-always-on; - gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; - }; - reg_sata0: pwr-sata0 { compatible = "regulator-fixed"; regulator-name = "pwr_en_sata0"; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 131614f28e75..569026e8f96c 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -86,10 +86,12 @@ macb0: ethernet@f8020000 { phy-mode = "rmii"; status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; @@ -152,6 +154,10 @@ atmel,pins = <AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; + pinctrl_macb0_phy_irq: macb0_phy_irq_0 { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; + }; }; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 2d4a33100af6..4e98cda97403 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -160,8 +160,15 @@ }; macb0: ethernet@f8020000 { + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy-mode = "rmii"; status = "okay"; + + ethernet-phy@1 { + reg = <0x1>; + interrupt-parent = <&pioE>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + }; }; mmc1: mmc@fc000000 { @@ -193,6 +200,10 @@ pinctrl@fc06a000 { board { + pinctrl_macb0_phy_irq: macb0_phy_irq { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; + }; pinctrl_mmc0_cd: mmc0_cd { atmel,pins = <AT91_PIOE 5 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 36387b11451d..80f6c786a37e 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -122,6 +122,7 @@ interrupt-parent = <&gpio5>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ ref-clock-frequency = <26000000>; + tcxo-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 5cf76a1c5c75..41e80e7f20be 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -130,6 +130,16 @@ }; }; +&gpio8 { + /* TI trees use GPIO instead of msecure, see also muxing */ + p234 { + gpio-hog; + gpios = <10 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "gpio8_234/msecure"; + }; +}; + &omap5_pmx_core { pinctrl-names = "default"; pinctrl-0 = < @@ -213,6 +223,13 @@ >; }; + /* TI trees use GPIO mode; msecure mode does not work reliably? */ + palmas_msecure_pins: palmas_msecure_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */ + >; + }; + usbhost_pins: pinmux_usbhost_pins { pinctrl-single,pins = < 0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */ @@ -278,6 +295,12 @@ &usbhost_wkup_pins >; + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + >; + }; + usbhost_wkup_pins: pinmux_usbhost_wkup_pins { pinctrl-single,pins = < 0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ @@ -345,6 +368,8 @@ interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; + pinctrl-names = "default"; + pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>; extcon_usb3: palmas_usb { compatible = "ti,palmas-usb-vid"; @@ -358,6 +383,14 @@ #clock-cells = <0>; }; + rtc { + compatible = "ti,palmas-rtc"; + interrupt-parent = <&palmas>; + interrupts = <8 IRQ_TYPE_NONE>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + palmas_pmic { compatible = "ti,palmas-pmic"; interrupt-parent = <&palmas>; diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..b0c912feaa2f 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 2193637b9cd2..3daf8d5d7878 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1342,7 +1342,7 @@ dbgu: serial@fc069000 { compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; reg = <0xfc069000 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_dbgu>; clocks = <&dbgu_clk>; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index d0c743853318..27a333eb8987 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -127,22 +127,14 @@ }; mmcsd_default_mode: mmcsd_default { mmcsd_default_cfg1 { - /* MCCLK */ - pins = "GPIO8_B10"; - ste,output = <0>; - }; - mmcsd_default_cfg2 { - /* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */ - pins = "GPIO10_C11", "GPIO15_A12", - "GPIO16_C13", "GPIO23_D15"; - ste,output = <1>; - }; - mmcsd_default_cfg3 { - /* MCCMD, MCDAT3-0, MCMSFBCLK */ - pins = "GPIO9_A10", "GPIO11_B11", - "GPIO12_A11", "GPIO13_C12", - "GPIO14_B12", "GPIO24_C15"; - ste,input = <1>; + /* + * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 + * MCCMD, MCDAT3-0, MCMSFBCLK + */ + pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11", + "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12", + "GPIO16_C13", "GPIO23_D15", "GPIO24_C15"; + ste,output = <2>; }; }; }; @@ -802,10 +794,21 @@ clock-names = "mclk", "apb_pclk"; interrupt-parent = <&vica>; interrupts = <22>; - max-frequency = <48000000>; + max-frequency = <400000>; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + full-pwr-cycle; + /* + * The STw4811 circuit used with the Nomadik strictly + * requires that all of these signal direction pins be + * routed and used for its 4-bit levelshifter. + */ + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-dir-cmd; + st,sig-pin-fbclk; pinctrl-names = "default"; pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>; vmmc-supply = <&vmmc_regulator>; diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70ae59..d7ed252708c5 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> - +#include <asm/div64.h> #include <asm/hardware/icst.h> /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); @@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index 68ee3ce17b82..b4c6d99364f1 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -16,7 +16,7 @@ extern struct smp_operations psci_smp_ops; -#ifdef CONFIG_ARM_PSCI +#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI) bool psci_smp_available(void); #else static inline bool psci_smp_available(void) { return false; } diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<<compound_order(page)) * XEN_PFN_PER_PAGE; + bool local = (page_pfn <= dev_pfn) && + (dev_pfn - page_pfn < compound_pages); + /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. So if the first xen_pfn == mfn the page is local - * otherwise it's a foreign page grant-mapped in dom0. If the page is - * local we can safely call the native dma_ops function, otherwise we - * call the xen specific function. + * Dom0 is mapped 1:1, while the Linux page can span across + * multiple Xen pages, it's not possible for it to contain a + * mix of local and foreign Xen pages. So if the first xen_pfn + * == mfn the page is local otherwise it's a foreign page + * grant-mapped in dom0. If the page is local we can safely + * call the native dma_ops function, otherwise we call the xen + * specific function. */ if (local) __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 96e935bbc38c..3705fc2921c2 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -155,7 +155,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index eafd120b53f1..1b9f0520dea9 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) stmfd sp!, {lr} @ save registers on stack /* Setup so that we will disable and enable l2 */ mov r1, #0x1 - adrl r2, l2dis_3630 @ may be too distant for plain adr - str r1, [r2] + adrl r3, l2dis_3630_offset @ may be too distant for plain adr + ldr r2, [r3] @ value for offset + str r1, [r2, r3] @ write to l2dis_3630 ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) - .text -/* Function to call rom code to save secure ram context */ +/* + * Function to call rom code to save secure ram context. This gets + * relocated to SRAM, so it can be all in .data section. Otherwise + * we need to initialize api_params separately. + */ + .data .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack @@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context) ENTRY(save_secure_ram_context_sz) .word . - save_secure_ram_context + .text + /* * ====================== * == Idle entry point == @@ -289,12 +296,6 @@ wait_sdrc_ready: bic r5, r5, #0x40 str r5, [r4] -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - is_dll_in_lock_mode: /* Is dll in lock mode? */ ldr r4, sdrc_dlla_ctrl @@ -302,11 +303,7 @@ is_dll_in_lock_mode: tst r5, #0x4 bne exit_nonoff_modes @ Return if locked /* wait till dll locks */ - adr r7, kick_counter wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] ldr r4, sdrc_dlla_status /* Wait 20uS for lock */ mov r6, #8 @@ -330,9 +327,6 @@ kick_dll: orr r6, r6, #(1<<3) @ enable dll str r6, [r4] dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter b wait_dll_lock_timed exit_nonoff_modes: @@ -360,15 +354,6 @@ sdrc_dlla_status: .word SDRC_DLLA_STATUS_V sdrc_dlla_ctrl: .word SDRC_DLLA_CTRL_V - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 - ENTRY(omap3_do_wfi_sz) .word . - omap3_do_wfi @@ -437,7 +422,9 @@ ENTRY(omap3_restore) cmp r2, #0x0 @ Check if target power state was OFF or RET bne logic_l1_restore - ldr r0, l2dis_3630 + adr r1, l2dis_3630_offset @ address for offset + ldr r0, [r1] @ value for offset + ldr r0, [r1, r0] @ value at l2dis_3630 cmp r0, #0x1 @ should we disable L2 on 3630? bne skipl2dis mrc p15, 0, r0, c1, c0, 1 @@ -449,12 +436,14 @@ skipl2dis: and r1, #0x700 cmp r1, #0x300 beq l2_inv_gp + adr r0, l2_inv_api_params_offset + ldr r3, [r0] + add r3, r3, r0 @ r3 points to dummy parameters mov r0, #40 @ set service ID for PPA mov r12, r0 @ copy secure Service ID in r12 mov r1, #0 @ set task id for ROM code in r1 mov r2, #4 @ set some flags in r2, r6 mov r6, #0xff - adr r3, l2_inv_api_params @ r3 points to dummy parameters dsb @ data write barrier dmb @ data memory barrier smc #1 @ call SMI monitor (smi #1) @@ -488,8 +477,8 @@ skipl2dis: b logic_l1_restore .align -l2_inv_api_params: - .word 0x1, 0x00 +l2_inv_api_params_offset: + .long l2_inv_api_params - . l2_inv_gp: /* Execute smi to invalidate L2 cache */ mov r12, #0x1 @ set up to invalidate L2 @@ -506,7 +495,9 @@ l2_inv_gp: mov r12, #0x2 smc #0 @ Call SMI monitor (smieq) logic_l1_restore: - ldr r1, l2dis_3630 + adr r0, l2dis_3630_offset @ adress for offset + ldr r1, [r0] @ value for offset + ldr r1, [r0, r1] @ value at l2dis_3630 cmp r1, #0x1 @ Test if L2 re-enable needed on 3630 bne skipl2reen mrc p15, 0, r1, c1, c0, 1 @@ -535,9 +526,17 @@ control_stat: .word CONTROL_STAT control_mem_rta: .word CONTROL_MEM_RTA_CTRL +l2dis_3630_offset: + .long l2dis_3630 - . + + .data l2dis_3630: .word 0 + .data +l2_inv_api_params: + .word 0x1, 0x00 + /* * Internal functions */ diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9b09d85d811a..c7a3b4aab4b5 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -29,12 +29,6 @@ dsb .endm -ppa_zero_params: - .word 0x0 - -ppa_por_params: - .word 1, 0 - #ifdef CONFIG_ARCH_OMAP4 /* @@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume) beq skip_ns_smp_enable ppa_actrl_retry: mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX - adr r3, ppa_zero_params @ Pointer to parameters + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag mov r6, #0xff @@ -303,7 +299,9 @@ skip_ns_smp_enable: ldr r0, =OMAP4_PPA_L2_POR_INDEX ldr r1, =OMAP44XX_SAR_RAM_BASE ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] - adr r3, ppa_por_params + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params str r4, [r3, #0x04] mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag @@ -328,6 +326,8 @@ skip_l2en: #endif b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . ENDPROC(omap4_cpu_resume) #endif /* CONFIG_ARCH_OMAP4 */ @@ -380,4 +380,13 @@ ENTRY(omap_do_wfi) nop ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . ENDPROC(omap_do_wfi) + + .data +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index cd822d8454c0..b6c90e5006e4 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -27,6 +27,7 @@ $(warning LSE atomics not supported by binutils) endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 63f52b55defe..fc9f7ef2f4ab 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,13 +34,13 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -51,7 +51,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..b685257926f0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -512,9 +512,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 5b1897e8ca24..62d3dc60ca09 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -574,9 +574,6 @@ static void armv8pmu_reset(void *info) /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..ff7f13239515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d250160d32bc..3039f080e2d5 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -186,7 +186,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 7963aa4b5d28..354144e33218 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 17bf39ac83ba..4cb98aa8c27b 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -319,8 +319,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..116ad654dd59 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -456,6 +456,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..d69dffffaa89 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,15 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..b8f04b3f2786 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -155,6 +156,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5d70..a5ecef7188ba 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 2046c0230224..21ed7150fec3 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -33,7 +33,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) /* * This is used for calculating the real page sizes diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 8957f15e21ec..18826aa15a7c 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -353,7 +353,7 @@ static inline pte_t pte_mkdirty(pte_t pte) static inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pte_val(pte) & _PAGE_NO_READ)) pte_val(pte) |= _PAGE_SILENT_READ; else @@ -560,7 +560,7 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) { pmd_val(pmd) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pmd_val(pmd) & _PAGE_NO_READ)) pmd_val(pmd) |= _PAGE_SILENT_READ; else diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 6499d93ae68d..47bc45a67e9b 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task, /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ if ((config_enabled(CONFIG_32BIT) || test_tsk_thread_flag(task, TIF_32BIT_REGS)) && - (regs->regs[2] == __NR_syscall)) { + (regs->regs[2] == __NR_syscall)) i++; - n++; - } while (n--) ret |= mips_get_syscall_arg(args++, task, regs, i++); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 886cb1976e90..ca9a81007489 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ out: void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b9b803facdbf..2683d04fdda5 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index bf9f1a77f0e5..a2631a52ca99 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,6 +13,9 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 +#define HPET_MIN_CYCLES 64 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -161,8 +164,9 @@ static int hpet_next_event(unsigned long delta, cnt += delta; hpet_write(HPET_T0_CMP, cnt); - res = ((int)(hpet_read(HPET_COUNTER) - cnt) > 0) ? -ETIME : 0; - return res; + res = (int)(cnt - hpet_read(HPET_COUNTER)); + + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static irqreturn_t hpet_irq_handler(int irq, void *data) @@ -237,7 +241,7 @@ void __init setup_hpet_timer(void) cd->cpumask = cpumask_of(cpu); clockevent_set_clock(cd, HPET_FREQ); cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); - cd->min_delta_ns = 5000; + cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd); clockevents_register_device(cd); setup_irq(HPET_T0_IRQ, &hpet_irq); diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 1a4738a8f2d3..509832a9836c 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -30,13 +30,13 @@ #include "smp.h" DEFINE_PER_CPU(int, cpu_state); -DEFINE_PER_CPU(uint32_t, core0_c0count); static void *ipi_set0_regs[16]; static void *ipi_clear0_regs[16]; static void *ipi_status0_regs[16]; static void *ipi_en0_regs[16]; static void *ipi_mailbox_buf[16]; +static uint32_t core0_c0count[NR_CPUS]; /* read a 32bit value from ipi register */ #define loongson3_ipi_read32(addr) readl(addr) @@ -275,12 +275,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) if (action & SMP_ASK_C0COUNT) { BUG_ON(cpu != 0); c0count = read_c0_count(); - for (i = 1; i < num_possible_cpus(); i++) - per_cpu(core0_c0count, i) = c0count; + c0count = c0count ? c0count : 1; + for (i = 1; i < nr_cpu_ids; i++) + core0_c0count[i] = c0count; + __wbflush(); /* Let others see the result ASAP */ } } -#define MAX_LOOPS 1111 +#define MAX_LOOPS 800 /* * SMP init and finish on secondary CPUs */ @@ -305,16 +307,20 @@ static void loongson3_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; i = 0; - __this_cpu_write(core0_c0count, 0); + core0_c0count[cpu] = 0; loongson3_send_ipi_single(0, SMP_ASK_C0COUNT); - while (!__this_cpu_read(core0_c0count)) { + while (!core0_c0count[cpu]) { i++; cpu_relax(); } if (i > MAX_LOOPS) i = MAX_LOOPS; - initcount = __this_cpu_read(core0_c0count) + i; + if (cpu_data[cpu].package) + initcount = core0_c0count[cpu] + i; + else /* Local access is faster for loops */ + initcount = core0_c0count[cpu] + i/2; + write_c0_count(initcount); } diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 3bd0597d9c3d..ddb8154610cc 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } void __weak platform_early_l2_init(void) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 32e0be27673f..29f73e00253d 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -242,7 +242,7 @@ static void output_pgtable_bits_defines(void) pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT); pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT); #endif -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (cpu_has_rixi) { #ifdef _PAGE_NO_EXEC_SHIFT pr_define("_PAGE_NO_EXEC_SHIFT %d\n", _PAGE_NO_EXEC_SHIFT); diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 7d56a9ccb752..a65d888716c4 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -54,24 +54,12 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -} +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, +int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - int changed = !pte_same(*ptep, pte); - if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); - flush_tlb_page(vma, addr); - } - return changed; -} + pte_t pte, int dirty); static inline pte_t huge_ptep_get(pte_t *ptep) { diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h index d7034728f377..1c75565d984b 100644 --- a/arch/parisc/include/uapi/asm/siginfo.h +++ b/arch/parisc/include/uapi/asm/siginfo.h @@ -1,6 +1,10 @@ #ifndef _PARISC_SIGINFO_H #define _PARISC_SIGINFO_H +#if defined(__LP64__) +#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +#endif + #include <asm-generic/siginfo.h> #undef NSIGTRAP diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index f6fdc77a72bd..54ba39262b82 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -105,15 +105,13 @@ static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long ad addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { - mtsp(mm->context, 1); - pdtlb(addr); - if (unlikely(split_tlb)) - pitlb(addr); + purge_tlb_entries(mm, addr); addr += (1UL << REAL_HPAGE_SHIFT); } } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +/* __set_huge_pte_at() must be called holding the pa_tlb_lock. */ +static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned long addr_start; @@ -123,14 +121,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, addr_start = addr; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) - * instead, but then we get double locking on pa_tlb_lock. */ - *ptep = entry; + set_pte(ptep, entry); ptep++; - /* Drop the PAGE_SIZE/non-huge tlb entry */ - purge_tlb_entries(mm, addr); - addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } @@ -138,18 +131,61 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, purge_tlb_entries_huge(mm, addr_start); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long flags; + + purge_tlb_start(flags); + __set_huge_pte_at(mm, addr, ptep, entry); + purge_tlb_end(flags); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + unsigned long flags; pte_t entry; + purge_tlb_start(flags); entry = *ptep; - set_huge_pte_at(mm, addr, ptep, __pte(0)); + __set_huge_pte_at(mm, addr, ptep, __pte(0)); + purge_tlb_end(flags); return entry; } + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long flags; + pte_t old_pte; + + purge_tlb_start(flags); + old_pte = *ptep; + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + purge_tlb_end(flags); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + unsigned long flags; + int changed; + + purge_tlb_start(flags); + changed = !pte_same(*ptep, pte); + if (changed) { + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + } + purge_tlb_end(flags); + return changed; +} + + int pmd_huge(pmd_t pmd) { return 0; diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index ad6263cffb0f..d1a8d93cccfd 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) @@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d452..867c39b45df6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index e682a7143edb..c50868681f9e 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void isync(void) MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup); #define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER) #define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n" -#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n" +#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n" #define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n" #else #define PPC_ACQUIRE_BARRIER diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 59dad113897b..c2d21d11c2d2 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,6 +295,8 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_ENTRY 118 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40f12..52c1e273f8cd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } @@ -564,6 +563,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +803,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +887,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..98f81800e00c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); + if (loc) - goto out; + return loc; - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** @@ -931,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 68384514506b..59663af9315f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2(sechdrs, me) - (unsigned long)location; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + case R_PPC64_REL16_HA: /* Subtract location pointer */ value -= (unsigned long)location; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 646bf4d222c1..ef2ad2d682da 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -569,6 +569,24 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; + /* + * Use the current MSR TM suspended bit to track if we have + * checkpointed state outstanding. + * On signal delivery, we'd normally reclaim the checkpointed + * state to obtain stack pointer (see:get_tm_stackpointer()). + * This will then directly return to userspace without going + * through __switch_to(). However, if the stack frame is bad, + * we need to exit this thread which calls __switch_to() which + * will again attempt to reclaim the already saved tm state. + * Hence we need to check that we've not already reclaimed + * this state. + * We do this using the current MSR, rather tracking it in + * some specific thread_struct bit, as it has the additional + * benifit of checking for a potential TM bad thing exception. + */ + if (!MSR_TM_SUSPENDED(mfmsr())) + return; + tm_reclaim(thr, thr->regs->msr, cause); /* Having done the reclaim, we now have the checkpointed diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..e57cc383e5da 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..2ba602591a20 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..e40d0714679e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..ad8c3f4a5e0b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); @@ -762,6 +768,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..36a99feab7d8 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index 2559b16da525..17d9dcd29d45 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -48,6 +48,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -57,6 +58,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index efaac2c3bb77..e9a983f40a24 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -506,7 +506,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; unsigned int host_acrs[NUM_ACRS]; struct fpu host_fpregs; - struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 9cd248f637c7..dc6c9c604543 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -181,6 +181,7 @@ int main(void) OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area); OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area); OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area); + OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area); OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area); OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area); OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 846589281b04..a08d0afd5ff6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1268,44 +1268,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return 0; } -/* - * Backs up the current FP/VX register save area on a particular - * destination. Used to switch between different register save - * areas. - */ -static inline void save_fpu_to(struct fpu *dst) -{ - dst->fpc = current->thread.fpu.fpc; - dst->regs = current->thread.fpu.regs; -} - -/* - * Switches the FP/VX register save area from which to lazy - * restore register contents. - */ -static inline void load_fpu_from(struct fpu *from) -{ - current->thread.fpu.fpc = from->fpc; - current->thread.fpu.regs = from->regs; -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Save host register state */ save_fpu_regs(); - save_fpu_to(&vcpu->arch.host_fpregs); - - if (test_kvm_facility(vcpu->kvm, 129)) { - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - /* - * Use the register save area in the SIE-control block - * for register restore and save in kvm_arch_vcpu_put() - */ - current->thread.fpu.vxrs = - (__vector128 *)&vcpu->run->s.regs.vrs; - } else - load_fpu_from(&vcpu->arch.guest_fpregs); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + /* Depending on MACHINE_HAS_VX, data stored to vrs either + * has vector register or floating point register format. + */ + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; @@ -1321,19 +1295,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); + /* Save guest register state */ save_fpu_regs(); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - if (test_kvm_facility(vcpu->kvm, 129)) - /* - * kvm_arch_vcpu_load() set up the register save area to - * the &vcpu->run->s.regs.vrs and, thus, the vector registers - * are already saved. Only the floating-point control must be - * copied. - */ - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - else - save_fpu_to(&vcpu->arch.guest_fpregs); - load_fpu_from(&vcpu->arch.host_fpregs); + /* Restore host register state */ + current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; + current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); @@ -1351,8 +1319,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); vcpu->arch.sie_block->gcr[0] = 0xE0UL; vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; - vcpu->arch.guest_fpregs.fpc = 0; - asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + /* make sure the new fpc will be lazily loaded */ + save_fpu_regs(); + current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1501,19 +1470,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - /* - * Allocate a save area for floating-point registers. If the vector - * extension is available, register contents are saved in the SIE - * control block. The allocated save area is still required in - * particular places, for example, in kvm_s390_vcpu_store_status(). - */ - vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, - GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) { - rc = -ENOMEM; - goto out_free_sie_block; - } - rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; @@ -1734,19 +1690,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + /* make sure the new values will be lazily loaded */ + save_fpu_regs(); if (test_fp_ctl(fpu->fpc)) return -EINVAL; - memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc; - save_fpu_regs(); - load_fpu_from(&vcpu->arch.guest_fpregs); + current->thread.fpu.fpc = fpu->fpc; + if (MACHINE_HAS_VX) + convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + else + memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); - fpu->fpc = vcpu->arch.guest_fpregs.fpc; + /* make sure we have the latest values */ + save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + else + memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2266,41 +2230,50 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) { unsigned char archmode = 1; + freg_t fprs[NUM_FPRS]; unsigned int px; u64 clkcomp; int rc; + px = kvm_s390_get_prefix(vcpu); if (gpa == KVM_S390_STORE_STATUS_NOADDR) { if (write_guest_abs(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = SAVE_AREA_BASE; + gpa = 0; } else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) { if (write_guest_real(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE); + gpa = px; + } else + gpa -= __LC_FPREGS_SAVE_AREA; + + /* manually convert vector registers if necessary */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + fprs, 128); + } else { + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.vrs, 128); } - rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs), - vcpu->arch.guest_fpregs.fprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw), + rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA, &vcpu->arch.sie_block->gpsw, 16); - px = kvm_s390_get_prefix(vcpu); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA, &px, 4); - rc |= write_guest_abs(vcpu, - gpa + offsetof(struct save_area, fp_ctrl_reg), - &vcpu->arch.guest_fpregs.fpc, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA, + &vcpu->run->s.regs.fpc, 4); + rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA, &vcpu->arch.sie_block->todpr, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer), + rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA, &vcpu->arch.sie_block->cputm, 8); clkcomp = vcpu->arch.sie_block->ckc >> 8; - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp), + rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA, &clkcomp, 8); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA, &vcpu->run->s.regs.acrs, 64); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA, &vcpu->arch.sie_block->gcr, 128); return rc ? -EFAULT : 0; } @@ -2313,19 +2286,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * it into the save area */ save_fpu_regs(); - if (test_kvm_facility(vcpu->kvm, 129)) { - /* - * If the vector extension is available, the vector registers - * which overlaps with floating-point registers are saved in - * the SIE-control block. Hence, extract the floating-point - * registers and the FPC value and store them in the - * guest_fpregs structure. - */ - vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc; - convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs, - current->thread.fpu.vxrs); - } else - save_fpu_to(&vcpu->arch.guest_fpregs); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index 4d1ee88864e8..18c8b819b0aa 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -52,12 +52,16 @@ void sort_extable(struct exception_table_entry *start, int i; /* Normalize entries to being relative to the start of the section */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn += i; + p->fixup += i + 4; + } sort(start, finish - start, sizeof(*start), cmp_ex, NULL); /* Denormalize all entries */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn -= i; + p->fixup -= i + 4; + } } #ifdef CONFIG_MODULES diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 30e7ddb27a3a..c690c8e16a96 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -413,7 +413,7 @@ out: SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { - int ret; + long ret; if (personality(current->personality) == PER_LINUX32 && personality(personality) == PER_LINUX) diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 47f1ff056a54..22a358ef1b0c 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -94,6 +94,8 @@ static int start_ptraced_child(void) { int pid, n, status; + fflush(stdout); + pid = fork(); if (pid == 0) ptrace_child(); diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 6a1ae3751e82..15cfebaa7688 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -267,6 +267,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 881b4768644a..e7de5c9a4fbd 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM @@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -struct irq_desc; extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 379cd3658799..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -116,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -156,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..79c91853e50e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcdd..adb3eaf8fe2a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include <asm/cacheflush.h> #include <asm/realmode.h> +#include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f25321894ad2..fdb0fbfb1197 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; struct irq_chip *chip; @@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot @@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void) /* Might be lapic_chip for irq 0 */ if (chip->irq_set_affinity) chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..a35f6b5473f4 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -30,7 +30,7 @@ struct apic_chip_data { struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask; +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; static struct irq_chip lapic_controller; #ifdef CONFIG_X86_IO_APIC static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; @@ -116,35 +116,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; + int cpu, vector; - if (d->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + /* Get the possible target cpus for @mask/@cpu from the apic */ apic->vector_allocation_domain(cpu, vector_cpumask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; + if (cpumask_subset(vector_cpumask, d->domain)) { - err = 0; if (cpumask_equal(vector_cpumask, d->domain)) - break; + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(d->old_domain, d->domain, - vector_cpumask); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - cpumask_and(d->domain, d->domain, vector_cpumask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -156,45 +168,60 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(d->old_domain, d->old_domain, - vector_cpumask); - cpumask_andnot(vector_cpumask, mask, d->old_domain); - cpu = cpumask_first_and(vector_cpumask, - cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { + for_each_cpu(new_cpu, vector_searchmask) { if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (d->cfg.vector) { + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) cpumask_copy(d->old_domain, d->domain); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) + for_each_cpu(new_cpu, vector_searchmask) per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); - err = 0; - break; - } + goto update; - if (!err) { - /* cache destination APIC IDs into cfg->dest_apicid */ - err = apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid); +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, @@ -224,10 +251,8 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { struct irq_desc *desc; - unsigned long flags; int cpu, vector; - raw_spin_lock_irqsave(&vector_lock, flags); BUG_ON(!data->cfg.vector); vector = data->cfg.vector; @@ -237,10 +262,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) data->cfg.vector = 0; cpumask_clear(data->domain); - if (likely(!data->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } desc = irq_to_desc(irq); for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { @@ -253,7 +281,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) } } data->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); } void init_irq_alloc_info(struct irq_alloc_info *info, @@ -274,19 +301,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { + struct apic_chip_data *apic_data; struct irq_data *irq_data; + unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); clear_irq_vector(virq + i, irq_data->chip_data); - free_apic_chip_data(irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); #ifdef CONFIG_X86_IO_APIC if (virq + i < nr_legacy_irqs()) legacy_irq_data[virq + i] = NULL; #endif - irq_domain_reset_irq_data(irq_data); } } } @@ -404,6 +436,8 @@ int __init arch_early_irq_init(void) arch_init_htirq_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); return arch_early_ioapic_init(); } @@ -492,14 +526,7 @@ static int apic_set_affinity(struct irq_data *irq_data, return -EINVAL; err = assign_irq_vector(irq, data, dest); - if (err) { - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(irq_data))) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - return IRQ_SET_MASK_OK; + return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { @@ -511,20 +538,12 @@ static struct irq_chip lapic_controller = { #ifdef CONFIG_SMP static void __send_cleanup_vector(struct apic_chip_data *data) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - - for_each_cpu_and(i, data->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } void send_cleanup_vector(struct irq_cfg *cfg) @@ -568,12 +587,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (data->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) goto unlock; @@ -591,6 +623,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; } __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } @@ -619,12 +652,48 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) +/* + * Called with @desc->lock held and interrupts disabled. + */ +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; - if (cfg) - __irq_complete_move(cfg, cfg->vector); + if (!cfg) + return; + + __irq_complete_move(cfg, cfg->vector); + + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * The cleanup cannot make progress because we hold @desc->lock. So in + * case @data->old_domain is not yet cleaned up, we need to drop the + * lock and acquire it again. @desc cannot go away, because the + * hotplug code holds the sparse irq lock. + */ + raw_spin_lock(&vector_lock); + /* Clean out all offline cpus (including ourself) first. */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + while (!cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + raw_spin_unlock(&desc->lock); + cpu_relax(); + raw_spin_lock(&desc->lock); + /* + * Reevaluate apic_chip_data. It might have been cleared after + * we dropped @desc->lock. + */ + data = apic_chip_data(irqdata); + if (!data) + return; + raw_spin_lock(&vector_lock); + } + raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f8062aaf5df9..61521dc19c10 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -462,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -470,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..f660d63f40fe 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 3058a22a658d..7be8a251363e 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 120302511802..ab9ae67a80e4 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -268,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44976a596fa6..5fd846cd6e0e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -595,6 +595,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -2062,14 +2064,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } @@ -8932,7 +8936,8 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) best->ebx &= ~bit(X86_FEATURE_INVPCID); } - vmcs_set_secondary_exec_control(secondary_exec_ctl); + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { if (guest_cpuid_has_pcommit(vcpu)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97592e190413..d2945024ed33 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -951,7 +951,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -4006,16 +4006,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -6543,12 +6544,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4a9b..27f89c79a44b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_4b_nocache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: + movl %edx,%ecx +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index eef44d9a3f77..e830c71a1323 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -360,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..db20ee9a413a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -1345,7 +1345,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8ddb5d0d66fb..8f4cc3dfac32 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -161,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -188,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -228,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index df0c40559583..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -34,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { |