diff options
Diffstat (limited to 'kernel/arch')
61 files changed, 561 insertions, 362 deletions
diff --git a/kernel/arch/arm/Kconfig b/kernel/arch/arm/Kconfig index bfaeed7a4..e16a25917 100644 --- a/kernel/arch/arm/Kconfig +++ b/kernel/arch/arm/Kconfig @@ -539,6 +539,7 @@ config ARCH_ORION5X select MVEBU_MBUS select PCI select PLAT_ORION_LEGACY + select MULTI_IRQ_HANDLER help Support for the following Marvell Orion 5x series SoCs: Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182), diff --git a/kernel/arch/arm/boot/compressed/decompress.c b/kernel/arch/arm/boot/compressed/decompress.c index bd245d349..a0765e7ed 100644 --- a/kernel/arch/arm/boot/compressed/decompress.c +++ b/kernel/arch/arm/boot/compressed/decompress.c @@ -57,5 +57,5 @@ extern char * strstr(const char * s1, const char *s2); int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x)) { - return decompress(input, len, NULL, NULL, output, NULL, error); + return __decompress(input, len, NULL, NULL, output, 0, NULL, error); } diff --git a/kernel/arch/arm/boot/dts/exynos3250-rinato.dts b/kernel/arch/arm/boot/dts/exynos3250-rinato.dts index 0b9906880..75aba40c6 100644 --- a/kernel/arch/arm/boot/dts/exynos3250-rinato.dts +++ b/kernel/arch/arm/boot/dts/exynos3250-rinato.dts @@ -181,7 +181,7 @@ display-timings { timing-0 { - clock-frequency = <0>; + clock-frequency = <4600000>; hactive = <320>; vactive = <320>; hfront-porch = <1>; diff --git a/kernel/arch/arm/boot/dts/rk3288.dtsi b/kernel/arch/arm/boot/dts/rk3288.dtsi index 165968d51..8eca5878a 100644 --- a/kernel/arch/arm/boot/dts/rk3288.dtsi +++ b/kernel/arch/arm/boot/dts/rk3288.dtsi @@ -584,7 +584,7 @@ compatible = "rockchip,rk3288-wdt", "snps,dw-wdt"; reg = <0xff800000 0x100>; clocks = <&cru PCLK_WDT>; - interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/kernel/arch/arm/kvm/arm.c b/kernel/arch/arm/kvm/arm.c index adb19885a..0c9014d7f 100644 --- a/kernel/arch/arm/kvm/arm.c +++ b/kernel/arch/arm/kvm/arm.c @@ -450,7 +450,7 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Map the VGIC hardware resources before running a vcpu the first * time on this VM. */ - if (unlikely(!vgic_ready(kvm))) { + if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) { ret = kvm_vgic_map_resources(kvm); if (ret) return ret; diff --git a/kernel/arch/arm/mach-omap2/clockdomains7xx_data.c b/kernel/arch/arm/mach-omap2/clockdomains7xx_data.c index 57d5df0c1..7581e036b 100644 --- a/kernel/arch/arm/mach-omap2/clockdomains7xx_data.c +++ b/kernel/arch/arm/mach-omap2/clockdomains7xx_data.c @@ -331,7 +331,7 @@ static struct clockdomain l4per2_7xx_clkdm = { .dep_bit = DRA7XX_L4PER2_STATDEP_SHIFT, .wkdep_srcs = l4per2_wkup_sleep_deps, .sleepdep_srcs = l4per2_wkup_sleep_deps, - .flags = CLKDM_CAN_HWSUP_SWSUP, + .flags = CLKDM_CAN_SWSUP, }; static struct clockdomain mpu0_7xx_clkdm = { diff --git a/kernel/arch/arm/mach-orion5x/include/mach/irqs.h b/kernel/arch/arm/mach-orion5x/include/mach/irqs.h index a6fa9d8f1..2431d9923 100644 --- a/kernel/arch/arm/mach-orion5x/include/mach/irqs.h +++ b/kernel/arch/arm/mach-orion5x/include/mach/irqs.h @@ -16,42 +16,42 @@ /* * Orion Main Interrupt Controller */ -#define IRQ_ORION5X_BRIDGE 0 -#define IRQ_ORION5X_DOORBELL_H2C 1 -#define IRQ_ORION5X_DOORBELL_C2H 2 -#define IRQ_ORION5X_UART0 3 -#define IRQ_ORION5X_UART1 4 -#define IRQ_ORION5X_I2C 5 -#define IRQ_ORION5X_GPIO_0_7 6 -#define IRQ_ORION5X_GPIO_8_15 7 -#define IRQ_ORION5X_GPIO_16_23 8 -#define IRQ_ORION5X_GPIO_24_31 9 -#define IRQ_ORION5X_PCIE0_ERR 10 -#define IRQ_ORION5X_PCIE0_INT 11 -#define IRQ_ORION5X_USB1_CTRL 12 -#define IRQ_ORION5X_DEV_BUS_ERR 14 -#define IRQ_ORION5X_PCI_ERR 15 -#define IRQ_ORION5X_USB_BR_ERR 16 -#define IRQ_ORION5X_USB0_CTRL 17 -#define IRQ_ORION5X_ETH_RX 18 -#define IRQ_ORION5X_ETH_TX 19 -#define IRQ_ORION5X_ETH_MISC 20 -#define IRQ_ORION5X_ETH_SUM 21 -#define IRQ_ORION5X_ETH_ERR 22 -#define IRQ_ORION5X_IDMA_ERR 23 -#define IRQ_ORION5X_IDMA_0 24 -#define IRQ_ORION5X_IDMA_1 25 -#define IRQ_ORION5X_IDMA_2 26 -#define IRQ_ORION5X_IDMA_3 27 -#define IRQ_ORION5X_CESA 28 -#define IRQ_ORION5X_SATA 29 -#define IRQ_ORION5X_XOR0 30 -#define IRQ_ORION5X_XOR1 31 +#define IRQ_ORION5X_BRIDGE (1 + 0) +#define IRQ_ORION5X_DOORBELL_H2C (1 + 1) +#define IRQ_ORION5X_DOORBELL_C2H (1 + 2) +#define IRQ_ORION5X_UART0 (1 + 3) +#define IRQ_ORION5X_UART1 (1 + 4) +#define IRQ_ORION5X_I2C (1 + 5) +#define IRQ_ORION5X_GPIO_0_7 (1 + 6) +#define IRQ_ORION5X_GPIO_8_15 (1 + 7) +#define IRQ_ORION5X_GPIO_16_23 (1 + 8) +#define IRQ_ORION5X_GPIO_24_31 (1 + 9) +#define IRQ_ORION5X_PCIE0_ERR (1 + 10) +#define IRQ_ORION5X_PCIE0_INT (1 + 11) +#define IRQ_ORION5X_USB1_CTRL (1 + 12) +#define IRQ_ORION5X_DEV_BUS_ERR (1 + 14) +#define IRQ_ORION5X_PCI_ERR (1 + 15) +#define IRQ_ORION5X_USB_BR_ERR (1 + 16) +#define IRQ_ORION5X_USB0_CTRL (1 + 17) +#define IRQ_ORION5X_ETH_RX (1 + 18) +#define IRQ_ORION5X_ETH_TX (1 + 19) +#define IRQ_ORION5X_ETH_MISC (1 + 20) +#define IRQ_ORION5X_ETH_SUM (1 + 21) +#define IRQ_ORION5X_ETH_ERR (1 + 22) +#define IRQ_ORION5X_IDMA_ERR (1 + 23) +#define IRQ_ORION5X_IDMA_0 (1 + 24) +#define IRQ_ORION5X_IDMA_1 (1 + 25) +#define IRQ_ORION5X_IDMA_2 (1 + 26) +#define IRQ_ORION5X_IDMA_3 (1 + 27) +#define IRQ_ORION5X_CESA (1 + 28) +#define IRQ_ORION5X_SATA (1 + 29) +#define IRQ_ORION5X_XOR0 (1 + 30) +#define IRQ_ORION5X_XOR1 (1 + 31) /* * Orion General Purpose Pins */ -#define IRQ_ORION5X_GPIO_START 32 +#define IRQ_ORION5X_GPIO_START 33 #define NR_GPIO_IRQS 32 #define NR_IRQS (IRQ_ORION5X_GPIO_START + NR_GPIO_IRQS) diff --git a/kernel/arch/arm/mach-orion5x/irq.c b/kernel/arch/arm/mach-orion5x/irq.c index cd4bac4d7..086ecb87d 100644 --- a/kernel/arch/arm/mach-orion5x/irq.c +++ b/kernel/arch/arm/mach-orion5x/irq.c @@ -42,7 +42,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs) stat = readl_relaxed(MAIN_IRQ_CAUSE); stat &= readl_relaxed(MAIN_IRQ_MASK); if (stat) { - unsigned int hwirq = __fls(stat); + unsigned int hwirq = 1 + __fls(stat); handle_IRQ(hwirq, regs); return; } @@ -51,7 +51,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs) void __init orion5x_init_irq(void) { - orion_irq_init(0, MAIN_IRQ_MASK); + orion_irq_init(1, MAIN_IRQ_MASK); #ifdef CONFIG_MULTI_IRQ_HANDLER set_handle_irq(orion5x_legacy_handle_irq); diff --git a/kernel/arch/arm/mach-rockchip/platsmp.c b/kernel/arch/arm/mach-rockchip/platsmp.c index 2e6ab67e2..611a5f96d 100644 --- a/kernel/arch/arm/mach-rockchip/platsmp.c +++ b/kernel/arch/arm/mach-rockchip/platsmp.c @@ -72,29 +72,22 @@ static struct reset_control *rockchip_get_core_reset(int cpu) static int pmu_set_power_domain(int pd, bool on) { u32 val = (on) ? 0 : BIT(pd); + struct reset_control *rstc = rockchip_get_core_reset(pd); int ret; + if (IS_ERR(rstc) && read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) { + pr_err("%s: could not get reset control for core %d\n", + __func__, pd); + return PTR_ERR(rstc); + } + /* * We need to soft reset the cpu when we turn off the cpu power domain, * or else the active processors might be stalled when the individual * processor is powered down. */ - if (read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) { - struct reset_control *rstc = rockchip_get_core_reset(pd); - - if (IS_ERR(rstc)) { - pr_err("%s: could not get reset control for core %d\n", - __func__, pd); - return PTR_ERR(rstc); - } - - if (on) - reset_control_deassert(rstc); - else - reset_control_assert(rstc); - - reset_control_put(rstc); - } + if (!IS_ERR(rstc) && !on) + reset_control_assert(rstc); ret = regmap_update_bits(pmu, PMU_PWRDN_CON, BIT(pd), val); if (ret < 0) { @@ -112,6 +105,12 @@ static int pmu_set_power_domain(int pd, bool on) } } + if (!IS_ERR(rstc)) { + if (on) + reset_control_deassert(rstc); + reset_control_put(rstc); + } + return 0; } @@ -147,8 +146,12 @@ static int __cpuinit rockchip_boot_secondary(unsigned int cpu, * the mailbox: * sram_base_addr + 4: 0xdeadbeaf * sram_base_addr + 8: start address for pc + * The cpu0 need to wait the other cpus other than cpu0 entering + * the wfe state.The wait time is affected by many aspects. + * (e.g: cpu frequency, bootrom frequency, sram frequency, ...) * */ - udelay(10); + mdelay(1); /* ensure the cpus other than cpu0 to startup */ + writel(virt_to_phys(secondary_startup), sram_base_addr + 8); writel(0xDEADBEAF, sram_base_addr + 4); dsb_sev(); diff --git a/kernel/arch/arm64/Kconfig b/kernel/arch/arm64/Kconfig index d555ed3a0..09a41259b 100644 --- a/kernel/arch/arm64/Kconfig +++ b/kernel/arch/arm64/Kconfig @@ -103,6 +103,10 @@ config NO_IOPORT_MAP config STACKTRACE_SUPPORT def_bool y +config ILLEGAL_POINTER_VALUE + hex + default 0xdead000000000000 + config LOCKDEP_SUPPORT def_bool y @@ -411,6 +415,22 @@ config ARM64_ERRATUM_845719 If unsure, say Y. +config ARM64_ERRATUM_843419 + bool "Cortex-A53: 843419: A load or store might access an incorrect address" + depends on MODULES + default y + help + This option builds kernel modules using the large memory model in + order to avoid the use of the ADRP instruction, which can cause + a subsequent memory access to use an incorrect address on Cortex-A53 + parts up to r0p4. + + Note that the kernel itself must be linked with a version of ld + which fixes potentially affected ADRP instructions through the + use of veneers. + + If unsure, say Y. + endmenu @@ -581,7 +601,7 @@ config XEN_DOM0 config XEN bool "Xen guest support on ARM64" - depends on ARM64 && OF + depends on ARM64 && OF && !PREEMPT_RT_FULL select SWIOTLB_XEN help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. diff --git a/kernel/arch/arm64/Makefile b/kernel/arch/arm64/Makefile index 4d2a92599..81151663e 100644 --- a/kernel/arch/arm64/Makefile +++ b/kernel/arch/arm64/Makefile @@ -30,6 +30,10 @@ endif CHECKFLAGS += -D__aarch64__ +ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) +CFLAGS_MODULE += -mcmodel=large +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/kernel/arch/arm64/include/asm/memory.h b/kernel/arch/arm64/include/asm/memory.h index f800d45ea..44a59c20e 100644 --- a/kernel/arch/arm64/include/asm/memory.h +++ b/kernel/arch/arm64/include/asm/memory.h @@ -114,6 +114,14 @@ extern phys_addr_t memstart_addr; #define PHYS_OFFSET ({ memstart_addr; }) /* + * The maximum physical address that the linear direct mapping + * of system RAM can cover. (PAGE_OFFSET can be interpreted as + * a 2's complement signed quantity and negated to derive the + * maximum size of the linear mapping.) + */ +#define MAX_MEMBLOCK_ADDR ({ memstart_addr - PAGE_OFFSET - 1; }) + +/* * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. * diff --git a/kernel/arch/arm64/kernel/debug-monitors.c b/kernel/arch/arm64/kernel/debug-monitors.c index b056369fd..70654d843 100644 --- a/kernel/arch/arm64/kernel/debug-monitors.c +++ b/kernel/arch/arm64/kernel/debug-monitors.c @@ -271,20 +271,21 @@ 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 +293,11 @@ 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/kernel/arch/arm64/kernel/fpsimd.c b/kernel/arch/arm64/kernel/fpsimd.c index 3dca15634..c31e59fe2 100644 --- a/kernel/arch/arm64/kernel/fpsimd.c +++ b/kernel/arch/arm64/kernel/fpsimd.c @@ -157,6 +157,7 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); + fpsimd_flush_task_state(current); set_thread_flag(TIF_FOREIGN_FPSTATE); } diff --git a/kernel/arch/arm64/kernel/head.S b/kernel/arch/arm64/kernel/head.S index 19f915e8f..36aa31ff2 100644 --- a/kernel/arch/arm64/kernel/head.S +++ b/kernel/arch/arm64/kernel/head.S @@ -565,6 +565,11 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems msr hstr_el2, xzr // Disable CP15 traps to EL2 #endif + /* EL2 debug */ + 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 + /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/kernel/arch/arm64/kernel/insn.c b/kernel/arch/arm64/kernel/insn.c index 924902083..30eb88e5b 100644 --- a/kernel/arch/arm64/kernel/insn.c +++ b/kernel/arch/arm64/kernel/insn.c @@ -77,7 +77,7 @@ bool __kprobes aarch64_insn_is_nop(u32 insn) } } -static DEFINE_SPINLOCK(patch_lock); +static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap) { @@ -124,13 +124,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn) unsigned long flags = 0; int ret; - spin_lock_irqsave(&patch_lock, flags); + raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); - spin_unlock_irqrestore(&patch_lock, flags); + raw_spin_unlock_irqrestore(&patch_lock, flags); return ret; } diff --git a/kernel/arch/arm64/kernel/module.c b/kernel/arch/arm64/kernel/module.c index 67bf4107f..876eb8df5 100644 --- a/kernel/arch/arm64/kernel/module.c +++ b/kernel/arch/arm64/kernel/module.c @@ -332,12 +332,14 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21, AARCH64_INSN_IMM_ADR); break; +#ifndef CONFIG_ARM64_ERRATUM_843419 case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21, AARCH64_INSN_IMM_ADR); break; +#endif case R_AARCH64_ADD_ABS_LO12_NC: case R_AARCH64_LDST8_ABS_LO12_NC: overflow_check = false; diff --git a/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c index c0cff3410..c58aee062 100644 --- a/kernel/arch/arm64/kernel/signal32.c +++ b/kernel/arch/arm64/kernel/signal32.c @@ -212,14 +212,32 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) /* * VFP save/restore code. + * + * We have to be careful with endianness, since the fpsimd context-switch + * code operates on 128-bit (Q) register values whereas the compat ABI + * uses an array of 64-bit (D) registers. Consequently, we need to swap + * the two halves of each Q register when running on a big-endian CPU. */ +union __fpsimd_vreg { + __uint128_t raw; + struct { +#ifdef __AARCH64EB__ + u64 hi; + u64 lo; +#else + u64 lo; + u64 hi; +#endif + }; +}; + static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) { struct fpsimd_state *fpsimd = ¤t->thread.fpsimd_state; compat_ulong_t magic = VFP_MAGIC; compat_ulong_t size = VFP_STORAGE_SIZE; compat_ulong_t fpscr, fpexc; - int err = 0; + int i, err = 0; /* * Save the hardware registers to the fpsimd_state structure. @@ -235,10 +253,15 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) /* * Now copy the FP registers. Since the registers are packed, * we can copy the prefix we want (V0-V15) as it is. - * FIXME: Won't work if big endian. */ - err |= __copy_to_user(&frame->ufp.fpregs, fpsimd->vregs, - sizeof(frame->ufp.fpregs)); + for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) { + union __fpsimd_vreg vreg = { + .raw = fpsimd->vregs[i >> 1], + }; + + __put_user_error(vreg.lo, &frame->ufp.fpregs[i], err); + __put_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err); + } /* Create an AArch32 fpscr from the fpsr and the fpcr. */ fpscr = (fpsimd->fpsr & VFP_FPSCR_STAT_MASK) | @@ -263,7 +286,7 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) compat_ulong_t magic = VFP_MAGIC; compat_ulong_t size = VFP_STORAGE_SIZE; compat_ulong_t fpscr; - int err = 0; + int i, err = 0; __get_user_error(magic, &frame->magic, err); __get_user_error(size, &frame->size, err); @@ -273,12 +296,14 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE) return -EINVAL; - /* - * Copy the FP registers into the start of the fpsimd_state. - * FIXME: Won't work if big endian. - */ - err |= __copy_from_user(fpsimd.vregs, frame->ufp.fpregs, - sizeof(frame->ufp.fpregs)); + /* Copy the FP registers into the start of the fpsimd_state. */ + for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) { + union __fpsimd_vreg vreg; + + __get_user_error(vreg.lo, &frame->ufp.fpregs[i], err); + __get_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err); + fpsimd.vregs[i >> 1] = vreg.raw; + } /* Extract the fpsr and the fpcr from the fpscr */ __get_user_error(fpscr, &frame->ufp.fpscr, err); diff --git a/kernel/arch/arm64/kvm/hyp.S b/kernel/arch/arm64/kvm/hyp.S index 5befd010e..64f9e60b3 100644 --- a/kernel/arch/arm64/kvm/hyp.S +++ b/kernel/arch/arm64/kvm/hyp.S @@ -844,8 +844,6 @@ mrs x3, cntv_ctl_el0 and x3, x3, #3 str w3, [x0, #VCPU_TIMER_CNTV_CTL] - bic x3, x3, #1 // Clear Enable - msr cntv_ctl_el0, x3 isb @@ -853,6 +851,9 @@ str x3, [x0, #VCPU_TIMER_CNTV_CVAL] 1: + // Disable the virtual timer + msr cntv_ctl_el0, xzr + // Allow physical timer/counter access for the host mrs x2, cnthctl_el2 orr x2, x2, #3 @@ -947,13 +948,15 @@ ENTRY(__kvm_vcpu_run) // Guest context add x2, x0, #VCPU_CONTEXT + // We must restore the 32-bit state before the sysregs, thanks + // to Cortex-A57 erratum #852523. + restore_guest_32bit_state bl __restore_sysregs bl __restore_fpsimd skip_debug_state x3, 1f bl __restore_debug 1: - restore_guest_32bit_state restore_guest_regs // That's it, no more messing around. diff --git a/kernel/arch/m32r/boot/compressed/misc.c b/kernel/arch/m32r/boot/compressed/misc.c index 28a09529f..3a7692745 100644 --- a/kernel/arch/m32r/boot/compressed/misc.c +++ b/kernel/arch/m32r/boot/compressed/misc.c @@ -86,6 +86,7 @@ decompress_kernel(int mmu_on, unsigned char *zimage_data, free_mem_end_ptr = free_mem_ptr + BOOT_HEAP_SIZE; puts("\nDecompressing Linux... "); - decompress(input_data, input_len, NULL, NULL, output_data, NULL, error); + __decompress(input_data, input_len, NULL, NULL, output_data, 0, + NULL, error); puts("done.\nBooting the kernel.\n"); } diff --git a/kernel/arch/mips/boot/compressed/decompress.c b/kernel/arch/mips/boot/compressed/decompress.c index 54831069a..080cd53ba 100644 --- a/kernel/arch/mips/boot/compressed/decompress.c +++ b/kernel/arch/mips/boot/compressed/decompress.c @@ -111,8 +111,8 @@ void decompress_kernel(unsigned long boot_heap_start) puts("\n"); /* Decompress the kernel with according algorithm */ - decompress((char *)zimage_start, zimage_size, 0, 0, - (void *)VMLINUX_LOAD_ADDRESS_ULL, 0, error); + __decompress((char *)zimage_start, zimage_size, 0, 0, + (void *)VMLINUX_LOAD_ADDRESS_ULL, 0, 0, error); /* FIXME: should we flush cache here? */ puts("Now, booting the kernel...\n"); diff --git a/kernel/arch/mips/math-emu/cp1emu.c b/kernel/arch/mips/math-emu/cp1emu.c index 6983fcd48..2b95e34fa 100644 --- a/kernel/arch/mips/math-emu/cp1emu.c +++ b/kernel/arch/mips/math-emu/cp1emu.c @@ -1137,7 +1137,7 @@ emul: break; case mfhc_op: - if (!cpu_has_mips_r2) + if (!cpu_has_mips_r2_r6) goto sigill; /* copregister rd -> gpr[rt] */ @@ -1148,7 +1148,7 @@ emul: break; case mthc_op: - if (!cpu_has_mips_r2) + if (!cpu_has_mips_r2_r6) goto sigill; /* copregister rd <- gpr[rt] */ @@ -1181,6 +1181,24 @@ emul: } break; + case bc1eqz_op: + case bc1nez_op: + if (!cpu_has_mips_r6 || delay_slot(xcp)) + return SIGILL; + + cond = likely = 0; + switch (MIPSInst_RS(ir)) { + case bc1eqz_op: + if (get_fpr32(¤t->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1) + cond = 1; + break; + case bc1nez_op: + if (!(get_fpr32(¤t->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1)) + cond = 1; + break; + } + goto branch_common; + case bc_op: if (delay_slot(xcp)) return SIGILL; @@ -1207,7 +1225,7 @@ emul: case bct_op: break; } - +branch_common: set_delay_slot(xcp); if (cond) { /* diff --git a/kernel/arch/parisc/kernel/irq.c b/kernel/arch/parisc/kernel/irq.c index f3191db6e..c0eab24f6 100644 --- a/kernel/arch/parisc/kernel/irq.c +++ b/kernel/arch/parisc/kernel/irq.c @@ -507,8 +507,8 @@ void do_cpu_irq_mask(struct pt_regs *regs) struct pt_regs *old_regs; unsigned long eirr_val; int irq, cpu = smp_processor_id(); -#ifdef CONFIG_SMP struct irq_desc *desc; +#ifdef CONFIG_SMP cpumask_t dest; #endif @@ -521,8 +521,12 @@ void do_cpu_irq_mask(struct pt_regs *regs) goto set_out; irq = eirr_to_irq(eirr_val); -#ifdef CONFIG_SMP + /* Filter out spurious interrupts, mostly from serial port at bootup */ desc = irq_to_desc(irq); + if (unlikely(!desc->action)) + goto set_out; + +#ifdef CONFIG_SMP cpumask_copy(&dest, desc->irq_data.affinity); if (irqd_is_per_cpu(&desc->irq_data) && !cpumask_test_cpu(smp_processor_id(), &dest)) { diff --git a/kernel/arch/parisc/kernel/syscall.S b/kernel/arch/parisc/kernel/syscall.S index 7ef22e338..0b8d26d3b 100644 --- a/kernel/arch/parisc/kernel/syscall.S +++ b/kernel/arch/parisc/kernel/syscall.S @@ -821,7 +821,7 @@ cas2_action: /* 64bit CAS */ #ifdef CONFIG_64BIT 19: ldd,ma 0(%sr3,%r26), %r29 - sub,= %r29, %r25, %r0 + sub,*= %r29, %r25, %r0 b,n cas2_end 20: std,ma %r24, 0(%sr3,%r26) copy %r0, %r28 diff --git a/kernel/arch/powerpc/boot/Makefile b/kernel/arch/powerpc/boot/Makefile index 73eddda53..4eec430d8 100644 --- a/kernel/arch/powerpc/boot/Makefile +++ b/kernel/arch/powerpc/boot/Makefile @@ -28,6 +28,9 @@ BOOTCFLAGS += -m64 endif ifdef CONFIG_CPU_BIG_ENDIAN BOOTCFLAGS += -mbig-endian +else +BOOTCFLAGS += -mlittle-endian +BOOTCFLAGS += $(call cc-option,-mabi=elfv2) endif BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc diff --git a/kernel/arch/powerpc/include/asm/pgtable-ppc64.h b/kernel/arch/powerpc/include/asm/pgtable-ppc64.h index 43e6ad424..88d27e325 100644 --- a/kernel/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/kernel/arch/powerpc/include/asm/pgtable-ppc64.h @@ -135,7 +135,19 @@ #define pte_iterate_hashed_end() } while(0) #ifdef CONFIG_PPC_HAS_HASH_64K -#define pte_pagesize_index(mm, addr, pte) get_slice_psize(mm, addr) +/* + * We expect this to be called only for user addresses or kernel virtual + * addresses other than the linear mapping. + */ +#define pte_pagesize_index(mm, addr, pte) \ + ({ \ + unsigned int psize; \ + if (is_kernel_addr(addr)) \ + psize = MMU_PAGE_4K; \ + else \ + psize = get_slice_psize(mm, addr); \ + psize; \ + }) #else #define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K #endif diff --git a/kernel/arch/powerpc/include/asm/rtas.h b/kernel/arch/powerpc/include/asm/rtas.h index 7a4ede16b..b77ef369c 100644 --- a/kernel/arch/powerpc/include/asm/rtas.h +++ b/kernel/arch/powerpc/include/asm/rtas.h @@ -343,6 +343,7 @@ extern void rtas_power_off(void); extern void rtas_halt(void); extern void rtas_os_term(char *str); extern int rtas_get_sensor(int sensor, int index, int *state); +extern int rtas_get_sensor_fast(int sensor, int index, int *state); extern int rtas_get_power_level(int powerdomain, int *level); extern int rtas_set_power_level(int powerdomain, int level, int *setlevel); extern bool rtas_indicator_present(int token, int *maxindex); diff --git a/kernel/arch/powerpc/include/asm/switch_to.h b/kernel/arch/powerpc/include/asm/switch_to.h index 58abeda64..15cca17cb 100644 --- a/kernel/arch/powerpc/include/asm/switch_to.h +++ b/kernel/arch/powerpc/include/asm/switch_to.h @@ -29,6 +29,7 @@ static inline void save_early_sprs(struct thread_struct *prev) {} extern void enable_kernel_fp(void); extern void enable_kernel_altivec(void); +extern void enable_kernel_vsx(void); extern int emulate_altivec(struct pt_regs *); extern void __giveup_vsx(struct task_struct *); extern void giveup_vsx(struct task_struct *); diff --git a/kernel/arch/powerpc/kernel/eeh.c b/kernel/arch/powerpc/kernel/eeh.c index 9ee61d156..cb565ad0a 100644 --- a/kernel/arch/powerpc/kernel/eeh.c +++ b/kernel/arch/powerpc/kernel/eeh.c @@ -310,11 +310,26 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) if (!(pe->type & EEH_PE_PHB)) { if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG)) eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + + /* + * The config space of some PCI devices can't be accessed + * when their PEs are in frozen state. Otherwise, fenced + * PHB might be seen. Those PEs are identified with flag + * EEH_PE_CFG_RESTRICTED, indicating EEH_PE_CFG_BLOCKED + * is set automatically when the PE is put to EEH_PE_ISOLATED. + * + * Restoring BARs possibly triggers PCI config access in + * (OPAL) firmware and then causes fenced PHB. If the + * PCI config is blocked with flag EEH_PE_CFG_BLOCKED, it's + * pointless to restore BARs and dump config space. + */ eeh_ops->configure_bridge(pe); - eeh_pe_restore_bars(pe); + if (!(pe->state & EEH_PE_CFG_BLOCKED)) { + eeh_pe_restore_bars(pe); - pci_regs_buf[0] = 0; - eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen); + pci_regs_buf[0] = 0; + eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen); + } } eeh_ops->get_log(pe, severity, pci_regs_buf, loglen); @@ -1118,9 +1133,6 @@ void eeh_add_device_late(struct pci_dev *dev) return; } - if (eeh_has_flag(EEH_PROBE_MODE_DEV)) - eeh_ops->probe(pdn, NULL); - /* * The EEH cache might not be removed correctly because of * unbalanced kref to the device during unplug time, which @@ -1144,6 +1156,9 @@ void eeh_add_device_late(struct pci_dev *dev) dev->dev.archdata.edev = NULL; } + if (eeh_has_flag(EEH_PROBE_MODE_DEV)) + eeh_ops->probe(pdn, NULL); + edev->pdev = dev; dev->dev.archdata.edev = edev; diff --git a/kernel/arch/powerpc/kernel/process.c b/kernel/arch/powerpc/kernel/process.c index febb50dd5..0596373cd 100644 --- a/kernel/arch/powerpc/kernel/process.c +++ b/kernel/arch/powerpc/kernel/process.c @@ -204,8 +204,6 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -#if 0 -/* not currently used, but some crazy RAID module might want to later */ void enable_kernel_vsx(void) { WARN_ON(preemptible()); @@ -220,7 +218,6 @@ void enable_kernel_vsx(void) #endif /* CONFIG_SMP */ } EXPORT_SYMBOL(enable_kernel_vsx); -#endif void giveup_vsx(struct task_struct *tsk) { diff --git a/kernel/arch/powerpc/kernel/rtas.c b/kernel/arch/powerpc/kernel/rtas.c index 7a488c108..caffb10e7 100644 --- a/kernel/arch/powerpc/kernel/rtas.c +++ b/kernel/arch/powerpc/kernel/rtas.c @@ -584,6 +584,23 @@ int rtas_get_sensor(int sensor, int index, int *state) } EXPORT_SYMBOL(rtas_get_sensor); +int rtas_get_sensor_fast(int sensor, int index, int *state) +{ + int token = rtas_token("get-sensor-state"); + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + rc = rtas_call(token, 2, 2, state, sensor, index); + WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN && + rc <= RTAS_EXTENDED_DELAY_MAX)); + + if (rc < 0) + return rtas_error_rc(rc); + return rc; +} + bool rtas_indicator_present(int token, int *maxindex) { int proplen, count, i; diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c index b027a8973..c6d601cc9 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -421,14 +421,20 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); v = pte & ~HPTE_V_HVLOCK; if (v & HPTE_V_VALID) { - u64 pte1; - - pte1 = be64_to_cpu(hpte[1]); hpte[0] &= ~cpu_to_be64(HPTE_V_VALID); - rb = compute_tlbie_rb(v, pte1, pte_index); + rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index); do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); - /* Read PTE low word after tlbie to get final R/C values */ - remove_revmap_chain(kvm, pte_index, rev, v, pte1); + /* + * The reference (R) and change (C) bits in a HPT + * entry can be set by hardware at any time up until + * the HPTE is invalidated and the TLB invalidation + * sequence has completed. This means that when + * removing a HPTE, we need to re-read the HPTE after + * the invalidation sequence has completed in order to + * obtain reliable values of R and C. + */ + remove_revmap_chain(kvm, pte_index, rev, v, + be64_to_cpu(hpte[1])); } r = rev->guest_rpte & ~HPTE_GR_RESERVED; note_hpte_modification(kvm, rev); diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 4d70df26c..3b2d2c5b6 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1127,6 +1127,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL bne 3f lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 beq 4f b guest_exit_cont 3: diff --git a/kernel/arch/powerpc/mm/hugepage-hash64.c b/kernel/arch/powerpc/mm/hugepage-hash64.c index 43dafb9d6..4d87122cf 100644 --- a/kernel/arch/powerpc/mm/hugepage-hash64.c +++ b/kernel/arch/powerpc/mm/hugepage-hash64.c @@ -85,7 +85,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, BUG_ON(index >= 4096); vpn = hpt_vpn(ea, vsid, ssize); - hash = hpt_hash(vpn, shift, ssize); hpte_slot_array = get_hpte_slot_array(pmdp); if (psize == MMU_PAGE_4K) { /* @@ -101,6 +100,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, valid = hpte_valid(hpte_slot_array, index); if (valid) { /* update the hpte bits */ + hash = hpt_hash(vpn, shift, ssize); hidx = hpte_hash_index(hpte_slot_array, index); if (hidx & _PTEIDX_SECONDARY) hash = ~hash; @@ -126,6 +126,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, if (!valid) { unsigned long hpte_group; + hash = hpt_hash(vpn, shift, ssize); /* insert new entry */ pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT; new_pmd |= _PAGE_HASHPTE; diff --git a/kernel/arch/powerpc/platforms/pseries/ras.c b/kernel/arch/powerpc/platforms/pseries/ras.c index 02e4a1745..3b6647e57 100644 --- a/kernel/arch/powerpc/platforms/pseries/ras.c +++ b/kernel/arch/powerpc/platforms/pseries/ras.c @@ -189,7 +189,8 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) int state; int critical; - status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state); + status = rtas_get_sensor_fast(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, + &state); if (state > 3) critical = 1; /* Time Critical */ diff --git a/kernel/arch/powerpc/platforms/pseries/setup.c b/kernel/arch/powerpc/platforms/pseries/setup.c index df6a70419..e6e8b241d 100644 --- a/kernel/arch/powerpc/platforms/pseries/setup.c +++ b/kernel/arch/powerpc/platforms/pseries/setup.c @@ -268,6 +268,11 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act eeh_dev_init(PCI_DN(np), pci->phb); } break; + case OF_RECONFIG_DETACH_NODE: + pci = PCI_DN(np); + if (pci) + list_del(&pci->list); + break; default: err = NOTIFY_DONE; break; diff --git a/kernel/arch/s390/boot/compressed/misc.c b/kernel/arch/s390/boot/compressed/misc.c index 42506b371..4da604ebf 100644 --- a/kernel/arch/s390/boot/compressed/misc.c +++ b/kernel/arch/s390/boot/compressed/misc.c @@ -167,7 +167,7 @@ unsigned long decompress_kernel(void) #endif puts("Uncompressing Linux... "); - decompress(input_data, input_len, NULL, NULL, output, NULL, error); + __decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error); puts("Ok, booting the kernel.\n"); return (unsigned long) output; } diff --git a/kernel/arch/s390/kernel/setup.c b/kernel/arch/s390/kernel/setup.c index 7262fe438..1942f22e6 100644 --- a/kernel/arch/s390/kernel/setup.c +++ b/kernel/arch/s390/kernel/setup.c @@ -683,7 +683,7 @@ static void __init setup_memory(void) /* * Setup hardware capabilities. */ -static void __init setup_hwcaps(void) +static int __init setup_hwcaps(void) { static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 }; struct cpuid cpu_id; @@ -749,9 +749,11 @@ static void __init setup_hwcaps(void) elf_hwcap |= HWCAP_S390_TE; /* - * Vector extension HWCAP_S390_VXRS is bit 11. + * Vector extension HWCAP_S390_VXRS is bit 11. The Vector extension + * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX + * instead of facility bit 129. */ - if (test_facility(129)) + if (MACHINE_HAS_VX) elf_hwcap |= HWCAP_S390_VXRS; get_cpu_id(&cpu_id); add_device_randomness(&cpu_id, sizeof(cpu_id)); @@ -788,7 +790,9 @@ static void __init setup_hwcaps(void) strcpy(elf_platform, "z13"); break; } + return 0; } +arch_initcall(setup_hwcaps); /* * Add system information as device randomness @@ -871,11 +875,6 @@ void __init setup_arch(char **cmdline_p) cpu_init(); /* - * Setup capabilities (ELF_HWCAP & ELF_PLATFORM). - */ - setup_hwcaps(); - - /* * Create kernel page tables and switch to virtual addressing. */ paging_init(); diff --git a/kernel/arch/sh/boot/compressed/misc.c b/kernel/arch/sh/boot/compressed/misc.c index 95470a472..208a9753a 100644 --- a/kernel/arch/sh/boot/compressed/misc.c +++ b/kernel/arch/sh/boot/compressed/misc.c @@ -132,7 +132,7 @@ void decompress_kernel(void) puts("Uncompressing Linux... "); cache_control(CACHE_ENABLE); - decompress(input_data, input_len, NULL, NULL, output, NULL, error); + __decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error); cache_control(CACHE_DISABLE); puts("Ok, booting the kernel.\n"); } diff --git a/kernel/arch/unicore32/boot/compressed/misc.c b/kernel/arch/unicore32/boot/compressed/misc.c index 176d5bda3..5c65dfee2 100644 --- a/kernel/arch/unicore32/boot/compressed/misc.c +++ b/kernel/arch/unicore32/boot/compressed/misc.c @@ -119,8 +119,8 @@ unsigned long decompress_kernel(unsigned long output_start, output_ptr = get_unaligned_le32(tmp); arch_decomp_puts("Uncompressing Linux..."); - decompress(input_data, input_data_end - input_data, NULL, NULL, - output_data, NULL, error); + __decompress(input_data, input_data_end - input_data, NULL, NULL, + output_data, 0, NULL, error); arch_decomp_puts(" done, booting the kernel.\n"); return output_ptr; } diff --git a/kernel/arch/x86/boot/compressed/misc.c b/kernel/arch/x86/boot/compressed/misc.c index a107b935e..e28437e0f 100644 --- a/kernel/arch/x86/boot/compressed/misc.c +++ b/kernel/arch/x86/boot/compressed/misc.c @@ -424,7 +424,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, #endif debug_putstr("\nDecompressing Linux... "); - decompress(input_data, input_len, NULL, NULL, output, NULL, error); + __decompress(input_data, input_len, NULL, NULL, output, output_len, + NULL, error); parse_elf(output); /* * 32-bit always performs relocations. 64-bit relocations are only diff --git a/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c b/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c index 2079baf06..daf8d2b9a 100644 --- a/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -294,6 +294,7 @@ static struct ahash_alg ghash_async_alg = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", .cra_priority = 400, + .cra_ctxsize = sizeof(struct ghash_async_ctx), .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_type = &crypto_ahash_type, diff --git a/kernel/arch/x86/include/asm/desc.h b/kernel/arch/x86/include/asm/desc.h index a0bf89fd2..4e10d73cf 100644 --- a/kernel/arch/x86/include/asm/desc.h +++ b/kernel/arch/x86/include/asm/desc.h @@ -280,21 +280,6 @@ static inline void clear_LDT(void) set_ldt(NULL, 0); } -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc) -{ - set_ldt(pc->ldt, pc->size); -} - -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} - static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); diff --git a/kernel/arch/x86/include/asm/mmu.h b/kernel/arch/x86/include/asm/mmu.h index 09b9620a7..364d27481 100644 --- a/kernel/arch/x86/include/asm/mmu.h +++ b/kernel/arch/x86/include/asm/mmu.h @@ -9,8 +9,7 @@ * we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/kernel/arch/x86/include/asm/mmu_context.h b/kernel/arch/x86/include/asm/mmu_context.h index e997f70f8..80d67dd80 100644 --- a/kernel/arch/x86/include/asm/mmu_context.h +++ b/kernel/arch/x86/include/asm/mmu_context.h @@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {} #endif /* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + int size; +}; + +static inline void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* lockless_dereference synchronizes with smp_store_release */ + ldt = lockless_dereference(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) + set_ldt(ldt->entries, ldt->size); + else + clear_LDT(); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} + +/* * Used for LDT copy/destruction. */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm); @@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * was called and then modify_ldt changed * prev->context.ldt but suppressed an IPI to this CPU. * In this case, prev->context.ldt != NULL, because we - * never free an LDT while the mm still exists. That - * means that next->context.ldt != prev->context.ldt, - * because mms never share an LDT. + * never set context.ldt to NULL while the mm still + * exists. That means that next->context.ldt != + * prev->context.ldt, because mms never share an LDT. */ if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); + load_mm_ldt(next); } #ifdef CONFIG_SMP else { @@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); - load_LDT_nolock(&next->context); + load_mm_ldt(next); } } #endif diff --git a/kernel/arch/x86/kernel/acpi/boot.c b/kernel/arch/x86/kernel/acpi/boot.c index dbe76a14c..07bea8022 100644 --- a/kernel/arch/x86/kernel/acpi/boot.c +++ b/kernel/arch/x86/kernel/acpi/boot.c @@ -489,6 +489,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here diff --git a/kernel/arch/x86/kernel/cpu/common.c b/kernel/arch/x86/kernel/cpu/common.c index a62cf04da..205e0f3df 100644 --- a/kernel/arch/x86/kernel/cpu/common.c +++ b/kernel/arch/x86/kernel/cpu/common.c @@ -1434,7 +1434,7 @@ void cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); @@ -1483,7 +1483,7 @@ void cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c b/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c index b4a41cf03..e166d833c 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -116,6 +116,27 @@ void mce_intel_hcpu_update(unsigned long cpu) per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; } +static void cmci_toggle_interrupt_mode(bool on) +{ + unsigned long flags, *owned; + int bank; + u64 val; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + owned = this_cpu_ptr(mce_banks_owned); + for_each_set_bit(bank, owned, MAX_NR_BANKS) { + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + + if (on) + val |= MCI_CTL2_CMCI_EN; + else + val &= ~MCI_CTL2_CMCI_EN; + + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + } + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + unsigned long cmci_intel_adjust_timer(unsigned long interval) { if ((this_cpu_read(cmci_backoff_cnt) > 0) && @@ -145,7 +166,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) */ if (!atomic_read(&cmci_storm_on_cpus)) { __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); - cmci_reenable(); + cmci_toggle_interrupt_mode(true); cmci_recheck(); } return CMCI_POLL_INTERVAL; @@ -156,22 +177,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) } } -static void cmci_storm_disable_banks(void) -{ - unsigned long flags, *owned; - int bank; - u64 val; - - raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = this_cpu_ptr(mce_banks_owned); - for_each_set_bit(bank, owned, MAX_NR_BANKS) { - rdmsrl(MSR_IA32_MCx_CTL2(bank), val); - val &= ~MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - } - raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); -} - static bool cmci_storm_detect(void) { unsigned int cnt = __this_cpu_read(cmci_storm_cnt); @@ -193,7 +198,7 @@ static bool cmci_storm_detect(void) if (cnt <= CMCI_STORM_THRESHOLD) return false; - cmci_storm_disable_banks(); + cmci_toggle_interrupt_mode(false); __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); r = atomic_add_return(1, &cmci_storm_on_cpus); mce_timer_kick(CMCI_STORM_INTERVAL); diff --git a/kernel/arch/x86/kernel/cpu/perf_event.c b/kernel/arch/x86/kernel/cpu/perf_event.c index aa4e3a74e..4cc98a4e8 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event.c +++ b/kernel/arch/x86/kernel/cpu/perf_event.c @@ -2170,21 +2170,25 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct ldt_struct *ldt; + if (idx > LDT_ENTRIES) return 0; - if (idx > current->active_mm->context.size) + /* IRQs are off, so this synchronizes with smp_store_release */ + ldt = lockless_dereference(current->active_mm->context.ldt); + if (!ldt || idx > ldt->size) return 0; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; } else { if (idx > GDT_ENTRIES) return 0; - desc = raw_cpu_ptr(gdt_page.gdt); + desc = raw_cpu_ptr(gdt_page.gdt) + idx; } - return get_desc_base(desc + idx); + return get_desc_base(desc); } #ifdef CONFIG_COMPAT diff --git a/kernel/arch/x86/kernel/ldt.c b/kernel/arch/x86/kernel/ldt.c index c37886d75..2bcc0525f 100644 --- a/kernel/arch/x86/kernel/ldt.c +++ b/kernel/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -20,82 +21,82 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + struct ldt_struct *new_ldt; + int alloc_size; + + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); - - if (!newldt) - return -ENOMEM; + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; + } - paravirt_alloc_ldt(newldt, mincount); + new_ldt->size = size; + return new_ldt; +} -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif - } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) +{ + paravirt_alloc_ldt(ldt->entries, ldt->size); } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + /* Synchronizes with lockless_dereference in load_mm_ldt. */ + smp_store_release(¤t_mm->context.ldt, ldt); + + /* Activate the LDT for all CPUs using current_mm. */ + on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); +} - if (err < 0) - return err; +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; + } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/kernel/arch/x86/kernel/process_64.c b/kernel/arch/x86/kernel/process_64.c index ddfdbf74f..5e0bf57d9 100644 --- a/kernel/arch/x86/kernel/process_64.c +++ b/kernel/arch/x86/kernel/process_64.c @@ -122,11 +122,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size); BUG(); } } diff --git a/kernel/arch/x86/kernel/step.c b/kernel/arch/x86/kernel/step.c index 9b4d51d0c..0ccb53a9f 100644 --- a/kernel/arch/x86/kernel/step.c +++ b/kernel/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/ptrace.h> #include <asm/desc.h> +#include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/kernel/arch/x86/kvm/mmu.c b/kernel/arch/x86/kvm/mmu.c index b73337634..554e877e0 100644 --- a/kernel/arch/x86/kvm/mmu.c +++ b/kernel/arch/x86/kvm/mmu.c @@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep) { return ACCESS_ONCE(*sptep); } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - /* It is valid if the spte is zapped. */ - return spte == 0ull; -} #else union split_spte { struct { @@ -478,23 +472,6 @@ retry: return spte.spte; } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - union split_spte sspte = (union split_spte)spte; - u32 high_mmio_mask = shadow_mmio_mask >> 32; - - /* It is valid if the spte is zapped. */ - if (spte == 0ull) - return true; - - /* It is valid if the spte is being zapped. */ - if (sspte.spte_low == 0ull && - (sspte.spte_high & high_mmio_mask) == high_mmio_mask) - return true; - - return false; -} #endif static bool spte_is_locklessly_modifiable(u64 spte) @@ -3343,21 +3320,6 @@ static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) return vcpu_match_mmio_gva(vcpu, addr); } - -/* - * On direct hosts, the last spte is only allows two states - * for mmio page fault: - * - It is the mmio spte - * - It is zapped or it is being zapped. - * - * This function completely checks the spte when the last spte - * is not the mmio spte. - */ -static bool check_direct_spte_mmio_pf(u64 spte) -{ - return __check_direct_spte_mmio_pf(spte); -} - static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) { struct kvm_shadow_walk_iterator iterator; @@ -3400,13 +3362,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) } /* - * It's ok if the gva is remapped by other cpus on shadow guest, - * it's a BUG if the gfn is not a mmio page. - */ - if (direct && !check_direct_spte_mmio_pf(spte)) - return RET_MMIO_PF_BUG; - - /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ diff --git a/kernel/arch/x86/kvm/x86.c b/kernel/arch/x86/kvm/x86.c index 6cceb2cb2..37d79a026 100644 --- a/kernel/arch/x86/kvm/x86.c +++ b/kernel/arch/x86/kvm/x86.c @@ -2192,7 +2192,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (guest_cpuid_has_tsc_adjust(vcpu)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; - kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + adjust_tsc_offset_guest(vcpu, adj); } vcpu->arch.ia32_tsc_adjust_msr = data; } diff --git a/kernel/arch/x86/math-emu/fpu_entry.c b/kernel/arch/x86/math-emu/fpu_entry.c index 9b8681241..274a52b11 100644 --- a/kernel/arch/x86/math-emu/fpu_entry.c +++ b/kernel/arch/x86/math-emu/fpu_entry.c @@ -29,7 +29,6 @@ #include <asm/uaccess.h> #include <asm/traps.h> -#include <asm/desc.h> #include <asm/user.h> #include <asm/i387.h> @@ -185,7 +184,7 @@ void math_emulate(struct math_emu_info *info) math_abort(FPU_info, SIGILL); } - code_descriptor = LDT_DESCRIPTOR(FPU_CS); + code_descriptor = FPU_get_ldt_descriptor(FPU_CS); if (SEG_D_SIZE(code_descriptor)) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ diff --git a/kernel/arch/x86/math-emu/fpu_system.h b/kernel/arch/x86/math-emu/fpu_system.h index 2c614410a..d342fce49 100644 --- a/kernel/arch/x86/math-emu/fpu_system.h +++ b/kernel/arch/x86/math-emu/fpu_system.h @@ -16,9 +16,24 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* s is always from a cpu register, and the cpu does bounds checking - * during register load --> no further bounds checks needed */ -#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) +#include <asm/desc.h> +#include <asm/mmu_context.h> + +static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) +{ + static struct desc_struct zero_desc; + struct desc_struct ret = zero_desc; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + seg >>= 3; + mutex_lock(¤t->mm->context.lock); + if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + ret = current->mm->context.ldt->entries[seg]; + mutex_unlock(¤t->mm->context.lock); +#endif + return ret; +} + #define SEG_D_SIZE(x) ((x).b & (3 << 21)) #define SEG_G_BIT(x) ((x).b & (1 << 23)) #define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) diff --git a/kernel/arch/x86/math-emu/get_address.c b/kernel/arch/x86/math-emu/get_address.c index 6ef5e9938..8300db71c 100644 --- a/kernel/arch/x86/math-emu/get_address.c +++ b/kernel/arch/x86/math-emu/get_address.c @@ -20,7 +20,6 @@ #include <linux/stddef.h> #include <asm/uaccess.h> -#include <asm/desc.h> #include "fpu_system.h" #include "exception.h" @@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, addr->selector = PM_REG_(segment); } - descriptor = LDT_DESCRIPTOR(PM_REG_(segment)); + descriptor = FPU_get_ldt_descriptor(addr->selector); base_address = SEG_BASE_ADDR(descriptor); address = base_address + offset; limit = base_address diff --git a/kernel/arch/x86/mm/init_32.c b/kernel/arch/x86/mm/init_32.c index c8140e128..c23ab1ee3 100644 --- a/kernel/arch/x86/mm/init_32.c +++ b/kernel/arch/x86/mm/init_32.c @@ -137,6 +137,7 @@ page_table_range_init_count(unsigned long start, unsigned long end) vaddr = start; pgd_idx = pgd_index(vaddr); + pmd_idx = pmd_index(vaddr); for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) { for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); diff --git a/kernel/arch/x86/power/cpu.c b/kernel/arch/x86/power/cpu.c index 757678fb2..bf9384488 100644 --- a/kernel/arch/x86/power/cpu.c +++ b/kernel/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/debugreg.h> #include <asm/fpu-internal.h> /* pcntxt_mask */ #include <asm/cpu.h> +#include <asm/mmu_context.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -154,7 +155,7 @@ static void fix_processor_context(void) syscall_init(); /* This sets MSR_*STAR and related */ #endif load_TR_desc(); /* This does ltr */ - load_LDT(¤t->active_mm->context); /* This does lldt */ + load_mm_ldt(current->active_mm); /* This does lldt */ } /** diff --git a/kernel/arch/xtensa/include/asm/traps.h b/kernel/arch/xtensa/include/asm/traps.h index 677bfcf4e..28f33a8b7 100644 --- a/kernel/arch/xtensa/include/asm/traps.h +++ b/kernel/arch/xtensa/include/asm/traps.h @@ -25,30 +25,39 @@ static inline void spill_registers(void) { #if XCHAL_NUM_AREGS > 16 __asm__ __volatile__ ( - " call12 1f\n" + " call8 1f\n" " _j 2f\n" " retw\n" " .align 4\n" "1:\n" +#if XCHAL_NUM_AREGS == 32 + " _entry a1, 32\n" + " addi a8, a0, 3\n" + " _entry a1, 16\n" + " mov a12, a12\n" + " retw\n" +#else " _entry a1, 48\n" - " addi a12, a0, 3\n" -#if XCHAL_NUM_AREGS > 32 - " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n" + " call12 1f\n" + " retw\n" + " .align 4\n" + "1:\n" + " .rept (" __stringify(XCHAL_NUM_AREGS) " - 16) / 12\n" " _entry a1, 48\n" " mov a12, a0\n" " .endr\n" -#endif - " _entry a1, 48\n" + " _entry a1, 16\n" #if XCHAL_NUM_AREGS % 12 == 0 - " mov a8, a8\n" -#elif XCHAL_NUM_AREGS % 12 == 4 " mov a12, a12\n" -#elif XCHAL_NUM_AREGS % 12 == 8 +#elif XCHAL_NUM_AREGS % 12 == 4 " mov a4, a4\n" +#elif XCHAL_NUM_AREGS % 12 == 8 + " mov a8, a8\n" #endif " retw\n" +#endif "2:\n" - : : : "a12", "a13", "memory"); + : : : "a8", "a9", "memory"); #else __asm__ __volatile__ ( " mov a12, a12\n" diff --git a/kernel/arch/xtensa/kernel/entry.S b/kernel/arch/xtensa/kernel/entry.S index 82bbfa5a0..a2a902140 100644 --- a/kernel/arch/xtensa/kernel/entry.S +++ b/kernel/arch/xtensa/kernel/entry.S @@ -568,12 +568,13 @@ user_exception_exit: * (if we have restored WSBITS-1 frames). */ +2: #if XCHAL_HAVE_THREADPTR l32i a3, a1, PT_THREADPTR wur a3, threadptr #endif -2: j common_exception_exit + j common_exception_exit /* This is the kernel exception exit. * We avoided to do a MOVSP when we entered the exception, but we @@ -1820,7 +1821,7 @@ ENDPROC(system_call) mov a12, a0 .endr #endif - _entry a1, 48 + _entry a1, 16 #if XCHAL_NUM_AREGS % 12 == 0 mov a8, a8 #elif XCHAL_NUM_AREGS % 12 == 4 @@ -1844,7 +1845,7 @@ ENDPROC(system_call) ENTRY(_switch_to) - entry a1, 16 + entry a1, 48 mov a11, a3 # and 'next' (a3) |