diff options
author | Stefan Agner <stefan@agner.ch> | 2016-06-02 12:22:30 -0700 |
---|---|---|
committer | Max Krummenacher <max.krummenacher@toradex.com> | 2017-03-15 18:35:46 +0100 |
commit | 440ef98ad687b210dca17e5c5141b24738f04922 (patch) | |
tree | 036c3507db3d4250cff096e825fc90897e485a3c /arch | |
parent | de1c77640710e1cca36091c8e6d7947bff2397e7 (diff) | |
parent | 648d744eff1aedea4ffe49dfca07aa465669e1f4 (diff) |
Merge tag 'v4.1.24' into toradex_vf_4.1-next
Linux 4.1.24
Diffstat (limited to 'arch')
116 files changed, 818 insertions, 475 deletions
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 0c12ffb155a2..f775d7161ffb 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -161,10 +161,9 @@ 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" @@ -1304,7 +1303,7 @@ 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" @@ -1320,10 +1319,6 @@ 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 @@ -1415,7 +1410,7 @@ 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 || \ @@ -1427,7 +1422,7 @@ 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 config DEBUG_UART_VIRT @@ -1466,7 +1461,7 @@ config DEBUG_UART_VIRT default 0xfb009000 if DEBUG_REALVIEW_STD_PORT default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT default 0xfc40ab00 if DEBUG_BRCMSTB_UART - 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 @@ -1516,7 +1511,7 @@ 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-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index f076ff856d8b..07f61bb1697a 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -508,7 +508,7 @@ }; sata@a0000 { - compatible = "marvell,orion-sata"; + compatible = "marvell,armada-370-sata"; reg = <0xa0000 0x5000>; interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gateclk 14>, <&gateclk 20>; diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index 78514ab0b47a..757ac079e7f2 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -288,16 +288,6 @@ 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 c740e1a2a3a5..4f29968076ce 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -98,7 +98,7 @@ phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 45e7761b7a29..d4d24a081404 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -141,8 +141,15 @@ }; 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 { @@ -174,6 +181,10 @@ 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/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index dfcc0dd637e5..bc04b754fe36 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1411,6 +1411,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 9cf0ab62db7d..cf11660f35a1 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1219,7 +1219,7 @@ 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 f182f6538e90..89ed9b45d533 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -122,22 +122,14 @@ }; 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 c25ef3ec6d1f..e3789fb02c9c 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -37,7 +37,7 @@ struct psci_operations { extern struct psci_operations psci_ops; extern struct smp_operations psci_smp_ops; -#ifdef CONFIG_ARM_PSCI +#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI) int psci_init(void); bool psci_smp_available(void); #else diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index d503fbb787d3..88993cc95e8e 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/kvm/mmu.c b/arch/arm/kvm/mmu.c index 191dcfab9f60..da09ddcfcc00 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud) __kvm_flush_dcache_pud(pud); } +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + /** * stage2_dissolve_pmd() - clear and flush huge PMD entry * @kvm: pointer to kvm structure. @@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, kvm_tlb_flush_vmid_ipa(kvm, addr); /* No need to invalidate the cache for device mappings */ - if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!kvm_is_device_pfn(pte_pfn(old_pte))) kvm_flush_dcache_pte(old_pte); put_page(virt_to_page(pte)); @@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte) && - (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte))) kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) return kvm_vcpu_dabt_iswrite(vcpu); } -static bool kvm_is_device_pfn(unsigned long pfn) -{ - return !pfn_valid(pfn); -} - /** * stage2_wp_ptes - write protect PMD range * @pmd: pointer to pmd entry diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 5286e7773ed4..dee6831c0434 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -876,6 +876,36 @@ static int _init_opt_clks(struct omap_hwmod *oh) return ret; } +static void _enable_optional_clocks(struct omap_hwmod *oh) +{ + struct omap_hwmod_opt_clk *oc; + int i; + + pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name); + + for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) + if (oc->_clk) { + pr_debug("omap_hwmod: enable %s:%s\n", oc->role, + __clk_get_name(oc->_clk)); + clk_enable(oc->_clk); + } +} + +static void _disable_optional_clocks(struct omap_hwmod *oh) +{ + struct omap_hwmod_opt_clk *oc; + int i; + + pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name); + + for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) + if (oc->_clk) { + pr_debug("omap_hwmod: disable %s:%s\n", oc->role, + __clk_get_name(oc->_clk)); + clk_disable(oc->_clk); + } +} + /** * _enable_clocks - enable hwmod main clock and interface clocks * @oh: struct omap_hwmod * @@ -903,6 +933,9 @@ static int _enable_clocks(struct omap_hwmod *oh) clk_enable(os->_clk); } + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _enable_optional_clocks(oh); + /* The opt clocks are controlled by the device driver. */ return 0; @@ -934,41 +967,14 @@ static int _disable_clocks(struct omap_hwmod *oh) clk_disable(os->_clk); } + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _disable_optional_clocks(oh); + /* The opt clocks are controlled by the device driver. */ return 0; } -static void _enable_optional_clocks(struct omap_hwmod *oh) -{ - struct omap_hwmod_opt_clk *oc; - int i; - - pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name); - - for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) - if (oc->_clk) { - pr_debug("omap_hwmod: enable %s:%s\n", oc->role, - __clk_get_name(oc->_clk)); - clk_enable(oc->_clk); - } -} - -static void _disable_optional_clocks(struct omap_hwmod *oh) -{ - struct omap_hwmod_opt_clk *oc; - int i; - - pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name); - - for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) - if (oc->_clk) { - pr_debug("omap_hwmod: disable %s:%s\n", oc->role, - __clk_get_name(oc->_clk)); - clk_disable(oc->_clk); - } -} - /** * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4 * @oh: struct omap_hwmod * @@ -1396,9 +1402,7 @@ static void _enable_sysc(struct omap_hwmod *oh) (sf & SYSC_HAS_CLOCKACTIVITY)) _set_clockactivity(oh, oh->class->sysc->clockact, &v); - /* If the cached value is the same as the new value, skip the write */ - if (oh->_sysc_cache != v) - _write_sysconfig(v, oh); + _write_sysconfig(v, oh); /* * Set the autoidle bit only after setting the smartidle bit @@ -1461,7 +1465,9 @@ static void _idle_sysc(struct omap_hwmod *oh) _set_master_standbymode(oh, idlemode, &v); } - _write_sysconfig(v, oh); + /* If the cached value is the same as the new value, skip the write */ + if (oh->_sysc_cache != v) + _write_sysconfig(v, oh); } /** @@ -2180,6 +2186,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2484,6 +2495,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2610,7 +2623,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 9611c91d9b82..ec289c5f099a 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -517,6 +517,10 @@ struct omap_hwmod_omap4_prcm { * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up * events by calling _reconfigure_io_chain() when a device is enabled * or idled. + * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to + * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -532,6 +536,8 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_FORCE_MSTANDBY (1 << 11) #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) +#define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions 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 ad1bb9431e94..5373a3281779 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 */ @@ -382,4 +382,13 @@ 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/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index e0e23582c8b4..5fe949b084ac 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -162,19 +162,6 @@ static inline int mem_words_used(struct jit_ctx *ctx) return fls(ctx->seen & SEEN_MEM); } -static inline bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void jit_fill_hole(void *area, unsigned int size) { u32 *ptr; @@ -186,7 +173,6 @@ static void jit_fill_hole(void *area, unsigned int size) static void build_prologue(struct jit_ctx *ctx) { u16 reg_set = saved_regs(ctx); - u16 first_inst = ctx->skf->insns[0].code; u16 off; #ifdef CONFIG_FRAME_POINTER @@ -216,7 +202,7 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 3258174e6152..f462e6e4ce07 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -18,6 +18,8 @@ GZFLAGS :=-9 KBUILD_DEFCONFIG := defconfig KBUILD_CFLAGS += -mgeneral-regs-only +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian AS += -EB diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 17e92f05b1fe..3ca894ecf699 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -99,11 +99,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; } +/* + * vcpu_reg should always be passed a register number coming from a + * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32 + * with banked registers. + */ static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_reg32(vcpu, reg_num); - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index cf7319422768..526a9cb218d3 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -33,7 +33,7 @@ /* * 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, @@ -43,7 +43,9 @@ #define VMALLOC_START (UL(0xffffffffffffffff) << VA_BITS) #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 - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index b056369fd47d..0d1d675f2cce 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -184,20 +184,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); -static DEFINE_RWLOCK(step_hook_lock); +static DEFINE_SPINLOCK(step_hook_lock); void register_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_add(&hook->node, &step_hook); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_add_rcu(&hook->node, &step_hook); + spin_unlock(&step_hook_lock); } void unregister_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_del(&hook->node); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&step_hook_lock); + synchronize_rcu(); } /* @@ -211,15 +212,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) struct step_hook *hook; int retval = DBG_HOOK_ERROR; - read_lock(&step_hook_lock); + rcu_read_lock(); - list_for_each_entry(hook, &step_hook, node) { + list_for_each_entry_rcu(hook, &step_hook, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - read_unlock(&step_hook_lock); + rcu_read_unlock(); return retval; } @@ -271,20 +272,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr, * Use reader/writer locks instead of plain spinlock. */ static LIST_HEAD(break_hook); -static DEFINE_RWLOCK(break_hook_lock); +static DEFINE_SPINLOCK(break_hook_lock); void register_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_add(&hook->node, &break_hook); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_add_rcu(&hook->node, &break_hook); + spin_unlock(&break_hook_lock); } void unregister_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_del(&hook->node); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&break_hook_lock); + synchronize_rcu(); } static int call_break_hook(struct pt_regs *regs, unsigned int esr) @@ -292,11 +294,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) struct break_hook *hook; int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL; - read_lock(&break_hook_lock); - list_for_each_entry(hook, &break_hook, node) + rcu_read_lock(); + list_for_each_entry_rcu(hook, &break_hook, node) if ((esr & hook->esr_mask) == hook->esr_val) fn = hook->fn; - read_unlock(&break_hook_lock); + rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 36aa31ff2c06..cc7435c9676e 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -566,9 +566,14 @@ 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 7778453762d8..b67b01cb5109 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1242,9 +1242,6 @@ 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 d882b833dbdb..608ac6aa497b 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/kernel/setup.c b/arch/arm64/kernel/setup.c index 74753132c3ac..bbdb53b87e13 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -523,6 +523,10 @@ static int c_show(struct seq_file *m, void *v) seq_printf(m, "processor\t: %d\n", i); #endif + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000UL/HZ), + loops_per_jiffy / (5000UL/HZ) % 100); + /* * Dump out the common processor features in a single line. * Userspace should read the hwcaps with getauxval(AT_HWCAP) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 53f1f8dccf6c..357418137db7 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -1,3 +1,4 @@ +#include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/slab.h> #include <asm/cacheflush.h> @@ -71,6 +72,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) local_dbg_save(flags); /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* * mm context saved on the stack, it will be restored when * the cpu comes out of reset through the identity mapped * page tables, so that the thread address space is properly @@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) hw_breakpoint_restore(NULL); } + unpause_graph_tracing(); + /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 9535bd555d1d..d4e04d2237c4 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -184,7 +184,7 @@ 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/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 85c57158dcd9..648112e90ed5 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) /* Note: These now point to the banked copies */ *vcpu_spsr(vcpu) = new_spsr_value; - *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ if (sctlr & (1 << 13)) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index ad87ce826cce..ae8f940152aa 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -312,8 +312,8 @@ void __init mem_init(void) " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", 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 5b8b664422d3..cb34eb8bbb9d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -450,6 +450,9 @@ 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 e47ed1c5dce1..545710f854f8 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 cdd754e19b9b..d253908a988d 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -165,6 +165,7 @@ 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 @@ -202,7 +203,9 @@ ENTRY(__cpu_setup) mov x0, #3 << 20 msr cpacr_el1, x0 // Enable FP/ASIMD - msr mdscr_el1, xzr // Reset mdscr_el1 + 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/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 98a26ce82d26..aee5637ea436 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com> + * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -35,6 +35,7 @@ aarch64_insn_gen_comp_branch_imm(0, offset, Rt, A64_VARIANT(sf), \ AARCH64_INSN_BRANCH_COMP_##type) #define A64_CBZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, ZERO) +#define A64_CBNZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, NONZERO) /* Conditional branch (immediate) */ #define A64_COND_BRANCH(cond, offset) \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c047598b09e0..6217f80702d2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com> + * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -225,6 +225,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 jmp_cond; s32 jmp_offset; +#define check_imm(bits, imm) do { \ + if ((((imm) > 0) && ((imm) >> (bits))) || \ + (((imm) < 0) && (~(imm) >> (bits)))) { \ + pr_info("[%2d] imm=%d(0x%x) out of range\n", \ + i, imm, imm); \ + return -EINVAL; \ + } \ +} while (0) +#define check_imm19(imm) check_imm(19, imm) +#define check_imm26(imm) check_imm(26, imm) + switch (code) { /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: @@ -258,15 +269,33 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: - emit(A64_UDIV(is64, dst, dst, src), ctx); - break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - ctx->tmp_used = 1; - emit(A64_UDIV(is64, tmp, dst, src), ctx); - emit(A64_MUL(is64, tmp, tmp, src), ctx); - emit(A64_SUB(is64, dst, dst, tmp), ctx); + { + const u8 r0 = bpf2a64[BPF_REG_0]; + + /* if (src == 0) return 0 */ + jmp_offset = 3; /* skip ahead to else path */ + check_imm19(jmp_offset); + emit(A64_CBNZ(is64, src, jmp_offset), ctx); + emit(A64_MOVZ(1, r0, 0, 0), ctx); + jmp_offset = epilogue_offset(ctx); + check_imm26(jmp_offset); + emit(A64_B(jmp_offset), ctx); + /* else */ + switch (BPF_OP(code)) { + case BPF_DIV: + emit(A64_UDIV(is64, dst, dst, src), ctx); + break; + case BPF_MOD: + ctx->tmp_used = 1; + emit(A64_UDIV(is64, tmp, dst, src), ctx); + emit(A64_MUL(is64, tmp, tmp, src), ctx); + emit(A64_SUB(is64, dst, dst, tmp), ctx); + break; + } break; + } case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: emit(A64_LSLV(is64, dst, dst, src), ctx); @@ -393,17 +422,6 @@ emit_bswap_uxt: emit(A64_ASR(is64, dst, dst, imm), ctx); break; -#define check_imm(bits, imm) do { \ - if ((((imm) > 0) && ((imm) >> (bits))) || \ - (((imm) < 0) && (~(imm) >> (bits)))) { \ - pr_info("[%2d] imm=%d(0x%x) out of range\n", \ - i, imm, imm); \ - return -EINVAL; \ - } \ -} while (0) -#define check_imm19(imm) check_imm(19, imm) -#define check_imm26(imm) check_imm(26, imm) - /* JUMP off */ case BPF_JMP | BPF_JA: jmp_offset = bpf2a64_offset(i + off, i, ctx); diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index 1d8b147282cf..bbf777c04cbf 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1328,6 +1328,21 @@ static struct clk atmel_mci0_pclk = { .index = 9, }; +static bool at32_mci_dma_filter(struct dma_chan *chan, void *pdata) +{ + struct mci_dma_data *sl = pdata; + + if (!sl) + return false; + + if (find_slave_dev(sl) == chan->device->dev) { + chan->private = slave_data_ptr(sl); + return true; + } + + return false; +} + struct platform_device *__init at32_add_device_mci(unsigned int id, struct mci_platform_data *data) { @@ -1362,6 +1377,7 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data) slave->sdata.dst_master = 0; data->dma_slave = slave; + data->dma_filter = at32_mci_dma_filter; if (platform_device_add_data(pdev, data, sizeof(struct mci_platform_data))) 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/Kconfig b/arch/mips/Kconfig index a3b1ffe50aa0..c99e8a32bea4 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2103,11 +2103,11 @@ config CPU_R4K_CACHE_TLB config MIPS_MT_SMP bool "MIPS MT SMP support (1 TC on each available VPE)" - depends on SYS_SUPPORTS_MULTITHREADING + depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6 select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2204,8 +2204,8 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" - depends on SYS_SUPPORTS_MIPS_CMP - select MIPS_GIC_IPI + depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2221,11 +2221,11 @@ config MIPS_CMP config MIPS_CPS bool "MIPS Coherent Processing System support" - depends on SYS_SUPPORTS_MIPS_CPS && !64BIT + depends on SYS_SUPPORTS_MIPS_CPS && !CPU_MIPSR6 select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2244,6 +2244,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 70f6e7f073b0..7fe24aef7fdc 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 @@ -558,7 +558,7 @@ 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/smp.c b/arch/mips/kernel/smp.c index d0744cc77ea7..3cef551908f4 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -120,6 +120,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 5f5f44edc77d..54923d6b7e16 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -693,15 +693,15 @@ 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); } @@ -877,7 +877,7 @@ 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 @@ -905,7 +905,6 @@ 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 22ee0afc7d5d..ace4ed7d41c6 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -700,7 +700,7 @@ 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; } @@ -730,7 +730,7 @@ 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/mm/tlbex.c b/arch/mips/mm/tlbex.c index 97c87027c17f..90b0e8316790 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/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index e23fdf2a9c80..d6d27d51d131 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -556,19 +556,6 @@ static inline u16 align_sp(unsigned int num) return num; } -static bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset) { int i = 0, real_off = 0; @@ -686,7 +673,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx) static void build_prologue(struct jit_ctx *ctx) { - u16 first_inst = ctx->skf->insns[0].code; int sp_off; /* Calculate the total offset for the stack pointer */ @@ -700,7 +686,7 @@ static void build_prologue(struct jit_ctx *ctx) emit_jit_reg_move(r_X, r_zero, ctx); /* Do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit_jit_reg_move(r_A, r_zero, ctx); } diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 4434b54e1d87..78ae5552fdb8 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -1,6 +1,7 @@ config MN10300 def_bool y select HAVE_OPROFILE + select HAVE_UID16 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select HAVE_ARCH_TRACEHOOK @@ -37,9 +38,6 @@ config HIGHMEM config NUMA def_bool n -config UID16 - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0abdd4c607ed..1960b87c1c8b 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -76,6 +76,7 @@ struct exception_table_entry { */ struct exception_data { unsigned long fault_ip; + unsigned long fault_gp; unsigned long fault_space; unsigned long fault_addr; }; 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/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 59001cea13f9..c972e6550f56 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -291,6 +291,7 @@ int main(void) DEFINE(ASM_PT_INITIAL, PT_INITIAL); BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); + DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); BLANK(); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 568b2c61ea02..3cad8aadc69e 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64); EXPORT_SYMBOL(lclear_user); EXPORT_SYMBOL(lstrnlen_user); -/* Global fixups */ -extern void fixup_get_user_skip_1(void); -extern void fixup_get_user_skip_2(void); -extern void fixup_put_user_skip_1(void); -extern void fixup_put_user_skip_2(void); +/* Global fixups - defined as int to avoid creation of function pointers */ +extern int fixup_get_user_skip_1; +extern int fixup_get_user_skip_2; +extern int fixup_put_user_skip_1; +extern int fixup_put_user_skip_2; EXPORT_SYMBOL(fixup_get_user_skip_1); EXPORT_SYMBOL(fixup_get_user_skip_2); EXPORT_SYMBOL(fixup_put_user_skip_1); 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 0b8d26d3ba43..02cf40c96fe3 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/kernel/traps.c b/arch/parisc/kernel/traps.c index 7f67c4c96a7a..bbf22658d1a3 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (fault_space == 0 && !in_atomic()) { + /* Clean up and return if in exception table. */ + if (fixup_exception(regs)) + return; pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); } diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S index 536ef66bb94b..1052b747e011 100644 --- a/arch/parisc/lib/fixup.S +++ b/arch/parisc/lib/fixup.S @@ -26,6 +26,7 @@ #ifdef CONFIG_SMP .macro get_fault_ip t1 t2 + loadgp addil LT%__per_cpu_offset,%r27 LDREG RT%__per_cpu_offset(%r1),\t1 /* t2 = smp_processor_id() */ @@ -40,14 +41,19 @@ LDREG RT%exception_data(%r1),\t1 /* t1 = this_cpu_ptr(&exception_data) */ add,l \t1,\t2,\t1 + /* %r27 = t1->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t1), %r27 /* t1 = t1->fault_ip */ LDREG EXCDATA_IP(\t1), \t1 .endm #else .macro get_fault_ip t1 t2 + loadgp /* t1 = this_cpu_ptr(&exception_data) */ addil LT%exception_data,%r27 LDREG RT%exception_data(%r1),\t2 + /* %r27 = t2->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t2), %r27 /* t1 = t2->fault_ip */ LDREG EXCDATA_IP(\t2), \t1 .endm diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index e5120e653240..50d64a7fc672 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs) struct exception_data *d; d = this_cpu_ptr(&exception_data); d->fault_ip = regs->iaoq[0]; + d->fault_gp = regs->gr[27]; d->fault_space = regs->isr; d->fault_addr = regs->ior; diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index d463c68fe7f0..99897f6645c1 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"); @@ -152,14 +152,14 @@ __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) @@ -198,13 +198,13 @@ __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 a52db28ecc1e..4457cb605356 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -79,6 +79,7 @@ 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 */ @@ -336,19 +337,13 @@ static inline int eeh_check_failure(const volatile void __iomem *token) #define eeh_dev_check_failure(x) (0) -static inline void eeh_addr_cache_build(void) { } - -static inline void eeh_add_device_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_late(struct pci_dev *dev) { } - -static inline void eeh_add_device_tree_late(struct pci_bus *bus) { } - -static inline void eeh_add_sysfs_files(struct pci_bus *bus) { } - -static inline void eeh_remove_device(struct pci_dev *dev) { } +#define eeh_addr_cache_build() +#define eeh_add_device_early(pdn) +#define eeh_add_device_tree_early(pdn) +#define eeh_add_device_late(pdev) +#define eeh_add_device_tree_late(pbus) +#define eeh_add_sysfs_files(pbus) +#define eeh_remove_device(pdev) #define EEH_POSSIBLE_ERROR(val, type) (0) #define EEH_IO_ERROR_VALUE(size) (-1UL) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index af56b5c6c81a..f4f99f01b746 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -108,6 +108,7 @@ #define MSR_TS_T __MASK(MSR_TS_T_LG) /* Transaction Transactional */ #define MSR_TS_MASK (MSR_TS_T | MSR_TS_S) /* Transaction State bits */ #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */ +#define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */ #define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T) #define MSR_TM_SUSPENDED(x) (((x) & MSR_TS_MASK) == MSR_TS_S) 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/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index de2c0e4ee1aa..67de80a8e178 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -31,6 +31,7 @@ #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \ 0x00000040 +/* Reserved - do not use 0x00000004 */ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 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 24768ff3cb73..90cc67904dc6 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -561,6 +561,7 @@ 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(); @@ -792,6 +793,7 @@ 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(); @@ -875,6 +877,7 @@ 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 35f0b62259bb..c3e0420b8a42 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -861,32 +861,29 @@ 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"; } /** @@ -909,7 +906,7 @@ 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..e4f7d4eed20c 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -335,7 +335,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; if (name[0] == '.') - memmove(name, name+1, strlen(name)); + syms[i].st_name++; } } } @@ -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 0596373cd1c3..c8c8275765e7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -551,6 +551,24 @@ static void tm_reclaim_thread(struct thread_struct *thr, msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; } + /* + * 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/kernel/prom.c b/arch/powerpc/kernel/prom.c index 308c5e15676b..abe9cdc390a5 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -149,23 +149,24 @@ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, + {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, /* * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP * which is 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, + {CPU_FTR_TM_COMP, 0, 0, 0, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -196,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index da50e0c9c57e..7356c33dc897 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -875,6 +875,15 @@ static long restore_tm_user_regs(struct pt_regs *regs, return 1; #endif /* CONFIG_SPE */ + /* Get the top half of the MSR from the user context */ + if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR])) + return 1; + msr_hi <<= 32; + /* If TM bits are set to the reserved value, it's an invalid context */ + if (MSR_TM_RESV(msr_hi)) + return 1; + /* Pull in the MSR TM bits from the user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK); /* Now, recheckpoint. This loads up all of the checkpointed (older) * registers, including FP and V[S]Rs. After recheckpointing, the * transactional versions should be loaded. @@ -884,11 +893,6 @@ static long restore_tm_user_regs(struct pt_regs *regs, current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); - /* Get the top half of the MSR */ - if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR])) - return 1; - /* Pull in MSR TM from user context */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK); /* This loads the speculative FP/VEC state, if used */ if (msr & MSR_FP) { diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c7c24d2e2bdb..164fd6474843 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -427,6 +427,10 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, /* get MSR separately, transfer the LE bit if doing signal return */ err |= __get_user(msr, &sc->gp_regs[PT_MSR]); + /* Don't allow reserved mode. */ + if (MSR_TM_RESV(msr)) + return -EINVAL; + /* pull in MSR TM from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index f1e0e5522e3a..f5b3de7f7fa2 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -210,6 +210,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ffd98b2bfa16..a34e43eec658 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1273,6 +1273,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ @@ -2047,7 +2061,7 @@ 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 ac3ddf115f3d..c8fe9ab10792 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -915,21 +915,17 @@ 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: @@ -970,17 +966,21 @@ 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/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 17cea18a09d3..264c473c1b3c 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, PPC_LI(r_X, 0); } - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* first instruction sets A register (or is RET 'constant') */ - break; - default: - /* make sure we dont leak kernel information to user */ + /* make sure we dont leak kernel information to user */ + if (bpf_needs_clear_a(&filter[0])) PPC_LI(r_A, 0); - } } static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index ce738ab3d5a9..abb396876b9a 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -455,9 +455,12 @@ 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/opal.c b/arch/powerpc/platforms/powernv/opal.c index 2241565b0739..b831a2ee32e9 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -358,7 +358,7 @@ static void opal_handle_message(void) /* Sanity check */ if (type >= OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Unknown message type: %u\n", __func__, type); + pr_warn_once("%s: Unknown message type: %u\n", __func__, type); return; } opal_message_do_notify(type, (void *)&msg); diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 11eae5f55b70..9787b61e0758 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -14,6 +14,7 @@ #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range free_pgd_range +#define hugepages_supported() (MACHINE_HAS_HPAGE) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3f..e485817f7b1a 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,25 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + if (mm->context.asce_limit == 0) { + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_bits = _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + mm->context.asce_limit = STACK_TOP_MAX; + } else if (mm->context.asce_limit == (1UL << 31)) { + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index a648338c434a..5b7153b34361 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -45,7 +45,8 @@ struct zpci_fmb { u64 rpcit_ops; u64 dma_rbytes; u64 dma_wbytes; -} __packed __aligned(16); + u64 pad[2]; +} __packed __aligned(128); enum zpci_state { ZPCI_FN_STATE_RESERVED, diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b4..d7cc79fb6191 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index c78ba51ae285..24b7e554db27 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -293,7 +293,7 @@ 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/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/s390/pci/pci.c b/arch/s390/pci/pci.c index 598f023cf8a6..50a79a5fc116 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -871,8 +871,11 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { + BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || + __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb)); + zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), - 16, 0, NULL); + __alignof__(struct zpci_fmb), 0, NULL); if (!zdev_fmb_cache) goto error_zdev; 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/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 7931eeeb649a..8109e92cd619 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp) } emit_reg_move(O7, r_saved_O7); - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* The first instruction sets the A register (or is - * a "RET 'constant'") - */ - break; - default: - /* Make sure we dont leak kernel information to the - * user. - */ + /* Make sure we dont leak kernel information to the user. */ + if (bpf_needs_clear_a(&filter[0])) emit_clear(r_A); /* A = 0 */ - } for (i = 0; i < flen; i++) { unsigned int K = filter[i].k; diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 29880c9b324e..e22e57298522 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); 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/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index e510b1c5d690..e5b79c1bb191 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -456,10 +456,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 72bf2680f819..27e54946ef35 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -511,6 +511,7 @@ ENTRY(ia32_syscall) * it is too small to ever cause noticeable irq latency. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS ENABLE_INTERRUPTS(CLBR_NONE) diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 976b86a325e5..a197e15a0e49 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -640,8 +640,8 @@ static inline void entering_irq(void) static inline void entering_ack_irq(void) { - ack_APIC_irq(); entering_irq(); + ack_APIC_irq(); } static inline void exiting_irq(void) 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/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 68c05398bba9..7aadd3cea843 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,6 +4,7 @@ #include <asm/page.h> #include <asm-generic/hugetlb.h> +#define hugepages_supported() cpu_has_pse static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 80d67dd80351..73e38f14ddeb 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -104,8 +104,36 @@ 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 */ @@ -142,10 +170,14 @@ 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/perf_event.h b/arch/x86/include/asm/perf_event.h index dc0f6ed35b08..5a2ed3ed2f26 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -159,6 +159,14 @@ struct x86_pmu_capability { */ #define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) +#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) +#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62) +#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) +#define GLOBAL_STATUS_ASIF BIT_ULL(60) +#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) + /* * IBS cpuid feature detection */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 78f0c8cbe316..74fcdf3f1534 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -337,20 +337,18 @@ 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/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index d866959e5685..d2ad00a42234 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -57,4 +57,6 @@ static inline bool xen_x2apic_para_available(void) } #endif +extern void xen_set_iopl_mask(unsigned mask); + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 3c6bb342a48f..06b407f79b24 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -72,6 +72,12 @@ #define MSR_LBR_CORE_FROM 0x00000040 #define MSR_LBR_CORE_TO 0x00000060 +#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */ +#define LBR_INFO_MISPRED BIT_ULL(63) +#define LBR_INFO_IN_TX BIT_ULL(62) +#define LBR_INFO_ABORT BIT_ULL(61) +#define LBR_INFO_CYCLES 0xffff + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 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/ioport.c b/arch/x86/kernel/ioport.c index 37dae792dbbe..589b3193f102 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) SYSCALL_DEFINE1(iopl, unsigned int, level) { struct pt_regs *regs = current_pt_regs(); - unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; + /* + * Careful: the IOPL bits in regs->flags are undefined under Xen PV + * and changing them has no effect. + */ + unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + if (level > 3) return -EINVAL; /* Trying to gain more privileges? */ @@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) if (!capable(CAP_SYS_RAWIO)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - t->iopl = level << 12; + regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | + (level << X86_EFLAGS_IOPL_BIT); + t->iopl = level << X86_EFLAGS_IOPL_BIT; set_iopl_mask(t->iopl); return 0; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 58e02d938218..f7724a1d7de1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,6 +49,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/xen/hypervisor.h> asmlinkage extern void ret_from_fork(void); @@ -419,6 +420,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); +#ifdef CONFIG_XEN + /* + * On Xen PV, IOPL bits in pt_regs->flags have no effect, and + * current_pt_regs()->flags may not match the current task's + * intended IOPL. We need to switch it manually. + */ + if (unlikely(xen_pv_domain() && + prev->iopl != next->iopl)) + xen_set_iopl_mask(next->iopl); +#endif + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 86db4bcd7ce5..0549ae3cb332 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/kernel/signal.c b/arch/x86/kernel/signal.c index e0fd5f47fbb9..5d2e2e9af1c4 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -667,12 +667,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(failed, ksig, stepping); } -#ifdef CONFIG_X86_32 -#define NR_restart_syscall __NR_restart_syscall -#else /* !CONFIG_X86_32 */ -#define NR_restart_syscall \ - test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall -#endif /* CONFIG_X86_32 */ +static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) + return __NR_restart_syscall; +#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ + return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : + __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +} /* * Note that 'init' is a special process: it doesn't get signals it doesn't @@ -701,7 +704,7 @@ static void do_signal(struct pt_regs *regs) break; case -ERESTART_RESTARTBLOCK: - regs->ax = NR_restart_syscall; + regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index f90952f64e79..e6a4c57100ea 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -244,7 +244,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) * PIC is being reset. Handle it gracefully here */ atomic_inc(&ps->pending); - else if (value > 0) + else if (value > 0 && ps->reinject) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ @@ -287,7 +287,9 @@ static void pit_do_work(struct kthread_work *work) * last one has been acked. */ spin_lock(&ps->inject_lock); - if (ps->irq_ack) { + if (!ps->reinject) + inject = 1; + else if (ps->irq_ack) { ps->irq_ack = 0; inject = 1; } @@ -316,10 +318,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); struct kvm_pit *pt = ps->kvm->arch.vpit; - if (ps->reinject || !atomic_read(&ps->pending)) { + if (ps->reinject) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6e6d115fe9b5..d537c9badeb6 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -257,7 +257,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; mark_page_dirty(vcpu->kvm, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 454ccb082e18..0d039cd268a8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1106,6 +1106,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_exception_intercept(svm, UD_VECTOR); set_exception_intercept(svm, MC_VECTOR); set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); set_intercept(svm, INTERCEPT_INTR); set_intercept(svm, INTERCEPT_NMI); @@ -1638,20 +1639,13 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_bp_intercept(struct kvm_vcpu *vcpu) +static void update_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - clr_exception_intercept(svm, DB_VECTOR); clr_exception_intercept(svm, BP_VECTOR); - if (svm->nmi_singlestep) - set_exception_intercept(svm, DB_VECTOR); - if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) set_exception_intercept(svm, BP_VECTOR); } else @@ -1757,7 +1751,6 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -3751,7 +3744,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -4367,7 +4359,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .update_db_bp_intercept = update_db_bp_intercept, + .update_db_bp_intercept = update_bp_intercept, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 7c7bc8bef21f..21dda139eb3a 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -250,7 +250,7 @@ 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 a243854c35d5..1274fac7c28f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1674,6 +1674,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1711,26 +1718,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1741,16 +1753,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -3652,20 +3669,21 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; - /* - * SMEP/SMAP is disabled if CPU is in non-paging mode - * in hardware. However KVM always uses paging mode to - * emulate guest non-paging mode with TDP. - * To emulate this behavior, SMEP/SMAP needs to be - * manually disabled when guest switches to non-paging - * mode. - */ - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } + if (!enable_unrestricted_guest && !is_paging(vcpu)) + /* + * SMEP/SMAP is disabled if CPU is in non-paging mode in + * hardware. However KVM always uses paging mode without + * unrestricted guest. + * To emulate this behavior, SMEP/SMAP needs to be manually + * disabled when guest switches to non-paging mode. + */ + hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); + vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); return 0; @@ -7192,6 +7210,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47a32f743a91..75eb9603ed29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -680,7 +680,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XSTATE_AVX512) != XSTATE_AVX512) return 1; } - kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK) @@ -940,7 +939,7 @@ 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; @@ -2117,6 +2116,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { + accumulate_steal_time(vcpu); + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -2262,12 +2263,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & KVM_MSR_ENABLED)) break; - vcpu->arch.st.last_steal = current->sched_info.run_delay; - - preempt_disable(); - accumulate_steal_time(vcpu); - preempt_enable(); - kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; @@ -2966,7 +2961,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; } - accumulate_steal_time(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } @@ -3737,13 +3731,13 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - int r = 0; - + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) @@ -3762,6 +3756,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int r = 0, start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3771,7 +3766,8 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return r; } @@ -4117,16 +4113,17 @@ 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; } @@ -6117,12 +6114,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending) { - if (kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } + if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -6292,10 +6287,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; /* enable NMI/IRQ window open exits if needed */ - else if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + else { + if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + } if (kvm_lapic_enabled(vcpu)) { /* @@ -6320,8 +6317,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); - kvm_load_guest_xcr0(vcpu); - vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -6344,6 +6339,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + kvm_load_guest_xcr0(vcpu); + if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6370,12 +6367,12 @@ 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; } /* @@ -6394,6 +6391,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_put_guest_xcr0(vcpu); + /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); @@ -7042,7 +7041,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) * and assume host would use all available bits. * Guest xcr0 would be loaded later. */ - kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); fpu_restore_checking(&vcpu->arch.guest_fpu); @@ -7051,8 +7049,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) return; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 181c53bac3a7..62855ac37ab7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -285,6 +285,9 @@ 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; @@ -356,8 +359,6 @@ 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) { @@ -399,17 +400,23 @@ 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 4d1c11c07fe1..6a3c774eaff6 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -120,19 +120,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; @@ -142,7 +142,7 @@ 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 89af288ec674..2dd9b3ad3bb5 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; @@ -1324,7 +1324,7 @@ 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 90b924acd982..061e0114005e 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -160,7 +160,10 @@ 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); @@ -187,17 +190,29 @@ 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); @@ -227,10 +242,18 @@ 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/pci/fixup.c b/arch/x86/pci/fixup.c index 9a2b7101ae8a..f16af96c60a2 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -553,3 +553,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); + +static void pci_bdwep_bar(struct pci_dev *dev) +{ + dev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a10ed8915bf4..1ecae556d4ed 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -959,7 +959,7 @@ static void xen_load_sp0(struct tss_struct *tss, tss->x86_tss.sp0 = thread->sp0; } -static void xen_set_iopl_mask(unsigned mask) +void xen_set_iopl_mask(unsigned mask) { struct physdev_set_iopl set_iopl; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 53b4c0811f4f..6d3415144dab 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -32,7 +32,8 @@ 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)) { diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 15a461e2a0ed..80eb62f853a7 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -128,7 +128,7 @@ ENTRY(_startup) wsr a0, icountlevel .set _index, 0 - .rept XCHAL_NUM_DBREAK - 1 + .rept XCHAL_NUM_DBREAK wsr a0, SREG_DBREAKC + _index .set _index, _index + 1 .endr diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index d75aa1476da7..1a804a2f9a5b 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr) unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(page, vaddr); set_bit(PG_arch_1, &page->flags); clear_page_alias(kvaddr, paddr); - pagefault_enable(); + preempt_enable(); } void copy_user_highpage(struct page *dst, struct page *src, @@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src, void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr, &src_paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(dst, vaddr); set_bit(PG_arch_1, &dst->flags); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); - pagefault_enable(); + preempt_enable(); } #endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 70cb408bc20d..92d785fefb6d 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv) { struct tty_port *port = (struct tty_port *)priv; int i = 0; + int rd = 1; unsigned char c; spin_lock(&timer_lock); while (simc_poll(0)) { - simc_read(0, &c, 1); + rd = simc_read(0, &c, 1); + if (rd <= 0) + break; tty_insert_flip_char(port, c, TTY_NORMAL); i++; } if (i) tty_flip_buffer_push(port); - - - mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); + if (rd) + mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); spin_unlock(&timer_lock); } |