diff options
Diffstat (limited to 'arch')
393 files changed, 4375 insertions, 3291 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 98de654b79b3..516f2b05bd66 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -540,11 +540,17 @@ config HAVE_CONTEXT_TRACKING help Provide kernel/user boundaries probes necessary for subsystems that need it, such as userspace RCU extended quiescent state. - Syscalls need to be wrapped inside user_exit()-user_enter() through - the slow path using TIF_NOHZ flag. Exceptions handlers must be - wrapped as well. Irqs are already protected inside - rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on - irq exit still need to be protected. + Syscalls need to be wrapped inside user_exit()-user_enter(), either + optimized behind static key or through the slow path using TIF_NOHZ + flag. Exceptions handlers must be wrapped as well. Irqs are already + protected inside rcu_irq_enter/rcu_irq_exit() but preemption or signal + handling on irq exit still need to be protected. + +config HAVE_TIF_NOHZ + bool + help + Arch relies on TIF_NOHZ and syscall slow path to implement context + tracking calls to user_enter()/user_exit(). config HAVE_VIRT_CPU_ACCOUNTING bool @@ -738,8 +744,9 @@ config HAVE_STACK_VALIDATION config HAVE_RELIABLE_STACKTRACE bool help - Architecture has a save_stack_trace_tsk_reliable() function which - only returns a stack trace if it can guarantee the trace is reliable. + Architecture has either save_stack_trace_tsk_reliable() or + arch_stack_walk_reliable() function which only returns a stack trace + if it can guarantee the trace is reliable. config HAVE_ARCH_HASH bool diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h index bfd3c01038f8..da67afd578fd 100644 --- a/arch/alpha/include/asm/futex.h +++ b/arch/alpha/include/asm/futex.h @@ -31,7 +31,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -53,8 +54,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index da3e10d5f7fe..d17e44c99df9 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -213,32 +213,13 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr, * The special RTC interrupt type. The interrupt itself was * processed by PALcode, and comes in via entInt vector 1. */ - -struct irqaction timer_irqaction = { - .handler = rtc_timer_interrupt, - .name = "timer", -}; - void __init -init_rtc_irq(void) +init_rtc_irq(irq_handler_t handler) { irq_set_chip_and_handler_name(RTC_IRQ, &dummy_irq_chip, handle_percpu_irq, "RTC"); - setup_irq(RTC_IRQ, &timer_irqaction); + if (!handler) + handler = rtc_timer_interrupt; + if (request_irq(RTC_IRQ, handler, 0, "timer", NULL)) + pr_err("Failed to register timer interrupt\n"); } - -/* Dummy irqactions. */ -struct irqaction isa_cascade_irqaction = { - .handler = no_action, - .name = "isa-cascade" -}; - -struct irqaction timer_cascade_irqaction = { - .handler = no_action, - .name = "timer-cascade" -}; - -struct irqaction halt_switch_irqaction = { - .handler = no_action, - .name = "halt-switch" -}; diff --git a/arch/alpha/kernel/irq_i8259.c b/arch/alpha/kernel/irq_i8259.c index 5d54c076a8ae..1dcf0d9038fd 100644 --- a/arch/alpha/kernel/irq_i8259.c +++ b/arch/alpha/kernel/irq_i8259.c @@ -82,11 +82,6 @@ struct irq_chip i8259a_irq_type = { void __init init_i8259a_irqs(void) { - static struct irqaction cascade = { - .handler = no_action, - .name = "cascade", - }; - long i; outb(0xff, 0x21); /* mask all of 8259A-1 */ @@ -96,7 +91,8 @@ init_i8259a_irqs(void) irq_set_chip_and_handler(i, &i8259a_irq_type, handle_level_irq); } - setup_irq(2, &cascade); + if (request_irq(2, no_action, 0, "cascade", NULL)) + pr_err("Failed to request irq 2 (cascade)\n"); } diff --git a/arch/alpha/kernel/irq_impl.h b/arch/alpha/kernel/irq_impl.h index 16f2b0276f3a..fbf21892e66d 100644 --- a/arch/alpha/kernel/irq_impl.h +++ b/arch/alpha/kernel/irq_impl.h @@ -21,14 +21,9 @@ extern void isa_no_iack_sc_device_interrupt(unsigned long); extern void srm_device_interrupt(unsigned long); extern void pyxis_device_interrupt(unsigned long); -extern struct irqaction timer_irqaction; -extern struct irqaction isa_cascade_irqaction; -extern struct irqaction timer_cascade_irqaction; -extern struct irqaction halt_switch_irqaction; - extern void init_srm_irqs(long, unsigned long); extern void init_pyxis_irqs(unsigned long); -extern void init_rtc_irq(void); +extern void init_rtc_irq(irq_handler_t handler); extern void common_init_isa_dma(void); diff --git a/arch/alpha/kernel/irq_pyxis.c b/arch/alpha/kernel/irq_pyxis.c index a968b10e687d..27070b5bd33e 100644 --- a/arch/alpha/kernel/irq_pyxis.c +++ b/arch/alpha/kernel/irq_pyxis.c @@ -107,5 +107,6 @@ init_pyxis_irqs(unsigned long ignore_mask) irq_set_status_flags(i, IRQ_LEVEL); } - setup_irq(16+7, &isa_cascade_irqaction); + if (request_irq(16 + 7, no_action, 0, "isa-cascade", NULL)) + pr_err("Failed to register isa-cascade interrupt\n"); } diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index e56efd5b855f..ce5430056f65 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -133,7 +133,8 @@ alcor_init_irq(void) init_i8259a_irqs(); common_init_isa_dma(); - setup_irq(16+31, &isa_cascade_irqaction); + if (request_irq(16 + 31, no_action, 0, "isa-cascade", NULL)) + pr_err("Failed to register isa-cascade interrupt\n"); } diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index 10bc46a4ec40..0aa6a27d0e2f 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -112,7 +112,8 @@ common_init_irq(void (*srm_dev_int)(unsigned long v)) } common_init_isa_dma(); - setup_irq(16+4, &isa_cascade_irqaction); + if (request_irq(16 + 4, no_action, 0, "isa-cascade", NULL)) + pr_err("Failed to register isa-cascade interrupt\n"); } #ifndef CONFIG_ALPHA_PC164 diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index 5251937ec1b4..1cdfe55fb987 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -123,7 +123,8 @@ eb64p_init_irq(void) } common_init_isa_dma(); - setup_irq(16+5, &isa_cascade_irqaction); + if (request_irq(16 + 5, no_action, 0, "isa-cascade", NULL)) + pr_err("Failed to register isa-cascade interrupt\n"); } /* diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index 8d34cf6e002a..533899a4a1a1 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -397,7 +397,7 @@ marvel_init_pci(void) static void __init marvel_init_rtc(void) { - init_rtc_irq(); + init_rtc_irq(NULL); } static void diff --git a/arch/alpha/kernel/sys_miata.c b/arch/alpha/kernel/sys_miata.c index 6fa07dc5339d..702292af2225 100644 --- a/arch/alpha/kernel/sys_miata.c +++ b/arch/alpha/kernel/sys_miata.c @@ -81,8 +81,10 @@ miata_init_irq(void) init_pyxis_irqs(0x63b0000); common_init_isa_dma(); - setup_irq(16+2, &halt_switch_irqaction); /* SRM only? */ - setup_irq(16+6, &timer_cascade_irqaction); + if (request_irq(16 + 2, no_action, 0, "halt-switch", NULL)) + pr_err("Failed to register halt-switch interrupt\n"); + if (request_irq(16 + 6, no_action, 0, "timer-cascade", NULL)) + pr_err("Failed to register timer-cascade interrupt\n"); } diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index 07830cccabf9..d33074011960 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -82,7 +82,8 @@ ruffian_init_rtc(void) outb(0x31, 0x42); outb(0x13, 0x42); - setup_irq(0, &timer_irqaction); + if (request_irq(0, rtc_timer_interrupt, 0, "timer", NULL)) + pr_err("Failed to request irq 0 (timer)\n"); } static void diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index a3db719d3c38..4d85eaeb44aa 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -106,7 +106,8 @@ rx164_init_irq(void) init_i8259a_irqs(); common_init_isa_dma(); - setup_irq(16+20, &isa_cascade_irqaction); + if (request_irq(16 + 20, no_action, 0, "isa-cascade", NULL)) + pr_err("Failed to register isa-cascade interrupt\n"); } diff --git a/arch/alpha/kernel/sys_sx164.c b/arch/alpha/kernel/sys_sx164.c index 1ec638a2746a..17cc203176c8 100644 --- a/arch/alpha/kernel/sys_sx164.c +++ b/arch/alpha/kernel/sys_sx164.c @@ -54,7 +54,8 @@ sx164_init_irq(void) else init_pyxis_irqs(0xff00003f0000UL); - setup_irq(16+6, &timer_cascade_irqaction); + if (request_irq(16 + 6, no_action, 0, "timer-cascade", NULL)) + pr_err("Failed to register timer-cascade interrupt\n"); } /* diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index 8e64052811ab..2191bde161fd 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -156,10 +156,6 @@ static void __init wildfire_init_irq_per_pca(int qbbno, int pcano) { int i, irq_bias; - static struct irqaction isa_enable = { - .handler = no_action, - .name = "isa_enable", - }; irq_bias = qbbno * (WILDFIRE_PCA_PER_QBB * WILDFIRE_IRQ_PER_PCA) + pcano * WILDFIRE_IRQ_PER_PCA; @@ -198,7 +194,8 @@ wildfire_init_irq_per_pca(int qbbno, int pcano) irq_set_status_flags(i + irq_bias, IRQ_LEVEL); } - setup_irq(32+irq_bias, &isa_enable); + if (request_irq(32 + irq_bias, no_action, 0, "isa_enable", NULL)) + pr_err("Failed to register isa_enable interrupt\n"); } static void __init diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index 0069360697ee..4d01c392ab14 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -242,7 +242,7 @@ common_init_rtc(void) outb(0x31, 0x42); outb(0x13, 0x42); - init_rtc_irq(); + init_rtc_irq(NULL); } @@ -396,9 +396,7 @@ time_init(void) if (alpha_using_qemu) { clocksource_register_hz(&qemu_cs, NSEC_PER_SEC); init_qemu_clockevent(); - - timer_irqaction.handler = qemu_timer_interrupt; - init_rtc_irq(); + init_rtc_irq(qemu_timer_interrupt); return; } diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ff2a393b635c..7124ab82dfa3 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -154,7 +154,7 @@ config ARC_CPU_HS help Support for ARC HS38x Cores based on ARCv2 ISA The notable features are: - - SMP configurations of upto 4 core with coherency + - SMP configurations of up to 4 cores with coherency - Optional L2 Cache and IO-Coherency - Revised Interrupt Architecture (multiple priorites, reg banks, auto stack switch, auto regfile save/restore) @@ -192,7 +192,7 @@ config ARC_SMP_HALT_ON_RESET help In SMP configuration cores can be configured as Halt-on-reset or they could all start at same time. For Halt-on-reset, non - masters are parked until Master kicks them so they can start of + masters are parked until Master kicks them so they can start off at designated entry point. For other case, all jump to common entry point and spin wait for Master's signal. diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 07f26ed39f02..f7a978dfdf1d 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -21,8 +21,6 @@ CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_EZNPS=y CONFIG_SMP=y CONFIG_NR_CPUS=4096 diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 5dd470b6609e..bf39a0091679 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -20,8 +20,6 @@ CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 3532e86f7bff..7121bd71c543 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -19,8 +19,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index d90448bee064..f9863b294a70 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -14,8 +14,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set diff --git a/arch/arc/include/asm/fpu.h b/arch/arc/include/asm/fpu.h index 64347250fdf5..006bcf88a7a5 100644 --- a/arch/arc/include/asm/fpu.h +++ b/arch/arc/include/asm/fpu.h @@ -43,6 +43,8 @@ extern void fpu_init_task(struct pt_regs *regs); #endif /* !CONFIG_ISA_ARCOMPACT */ +struct task_struct; + extern void fpu_save_restore(struct task_struct *p, struct task_struct *n); #else /* !CONFIG_ARC_FPU_SAVE_RESTORE */ diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h index 9d0d070e6c22..607d1c16d4dd 100644 --- a/arch/arc/include/asm/futex.h +++ b/arch/arc/include/asm/futex.h @@ -75,10 +75,12 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; + #ifndef CONFIG_ARC_HAS_LLSC preempt_disable(); /* to guarantee atomic r-m-w of futex op */ #endif - pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -101,7 +103,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, ret = -ENOSYS; } - pagefault_enable(); #ifndef CONFIG_ARC_HAS_LLSC preempt_enable(); #endif diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index d9ee43c6b7db..fe19f1d412e7 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -29,6 +29,8 @@ .endm #define ASM_NL ` /* use '`' to mark new line in macro */ +#define __ALIGN .align 4 +#define __ALIGN_STR __stringify(__ALIGN) /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index e1c647490f00..aa41af6ef4ac 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -8,11 +8,11 @@ #include <linux/delay.h> #include <linux/root_dev.h> #include <linux/clk.h> -#include <linux/clk-provider.h> #include <linux/clocksource.h> #include <linux/console.h> #include <linux/module.h> #include <linux/cpu.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <linux/of.h> #include <linux/cache.h> diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index b79886a6cec8..d2999503fb8a 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -104,8 +104,7 @@ static void show_faulting_vma(unsigned long address) if (IS_ERR(nm)) nm = "?"; } - pr_info(" @off 0x%lx in [%s]\n" - " VMA: 0x%08lx to 0x%08lx\n", + pr_info(" @off 0x%lx in [%s] VMA: 0x%08lx to 0x%08lx\n", vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); @@ -120,8 +119,6 @@ static void show_ecr_verbose(struct pt_regs *regs) unsigned int vec, cause_code; unsigned long address; - pr_info("\n[ECR ]: 0x%08lx => ", regs->event); - /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; @@ -130,10 +127,10 @@ static void show_ecr_verbose(struct pt_regs *regs) /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + pr_cont("Invalid %s @ 0x%08lx by insn @ %pS\n", (cause_code == 0x01) ? "Read" : ((cause_code == 0x02) ? "Write" : "EX"), - address, regs->ret); + address, (void *)regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); } else if (vec == ECR_V_MACH_CHK) { @@ -191,31 +188,31 @@ void show_regs(struct pt_regs *regs) show_ecr_verbose(regs); - pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", - current->thread.fault_address, - (void *)regs->blink, (void *)regs->ret); - if (user_mode(regs)) show_faulting_vma(regs->ret); /* faulting code, not data */ - pr_info("[STAT32]: 0x%08lx", regs->status32); + pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n", + regs->event, current->thread.fault_address, regs->ret); + + pr_info("STAT32: 0x%08lx", regs->status32); #define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : "" #ifdef CONFIG_ISA_ARCOMPACT - pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s%2s%2s%2s]", (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" : %2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s]", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n", - regs->bta, regs->sp, regs->fp); + pr_cont(" BTA: 0x%08lx\n", regs->bta); + pr_info("BLK: %pS\n SP: 0x%08lx FP: 0x%08lx\n", + (void *)regs->blink, regs->sp, regs->fp); pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", regs->lp_start, regs->lp_end, regs->lp_count); diff --git a/arch/arm/Makefile b/arch/arm/Makefile index db857d07114f..1fc32b611f8a 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -307,13 +307,15 @@ endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) prepare: stack_protector_prepare stack_protector_prepare: prepare0 - $(eval KBUILD_CFLAGS += \ + $(eval SSP_PLUGIN_CFLAGS := \ -fplugin-arg-arm_ssp_per_task_plugin-tso=$(shell \ awk '{if ($$2 == "THREAD_SZ_ORDER") print $$3;}'\ include/generated/asm-offsets.h) \ -fplugin-arg-arm_ssp_per_task_plugin-offset=$(shell \ awk '{if ($$2 == "TI_STACK_CANARY") print $$3;}'\ include/generated/asm-offsets.h)) + $(eval KBUILD_CFLAGS += $(SSP_PLUGIN_CFLAGS)) + $(eval GCC_PLUGINS_CFLAGS += $(SSP_PLUGIN_CFLAGS)) endif all: $(notdir $(KBUILD_IMAGE)) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index da599c3a1193..9c11e7490292 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -101,7 +101,6 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S \ $(libfdt) $(libfdt_hdrs) hyp-stub.S KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS += $(DISABLE_ARM_SSP_PER_TASK_PLUGIN) ifeq ($(CONFIG_FUNCTION_TRACER),y) ORIG_CFLAGS := $(KBUILD_CFLAGS) @@ -117,7 +116,8 @@ CFLAGS_fdt_ro.o := $(nossp-flags-y) CFLAGS_fdt_rw.o := $(nossp-flags-y) CFLAGS_fdt_wip.o := $(nossp-flags-y) -ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj) +ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \ + -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN) asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S index a5983588f96b..62286da318e7 100644 --- a/arch/arm/boot/compressed/efi-header.S +++ b/arch/arm/boot/compressed/efi-header.S @@ -60,7 +60,7 @@ optional_header: .long __pecoff_code_size @ SizeOfCode .long __pecoff_data_size @ SizeOfInitializedData .long 0 @ SizeOfUninitializedData - .long efi_stub_entry - start @ AddressOfEntryPoint + .long efi_entry - start @ AddressOfEntryPoint .long start_offset @ BaseOfCode .long __pecoff_data_start - start @ BaseOfData @@ -70,8 +70,8 @@ extra_header_fields: .long SZ_512 @ FileAlignment .short 0 @ MajorOsVersion .short 0 @ MinorOsVersion - .short 0 @ MajorImageVersion - .short 0 @ MinorImageVersion + .short LINUX_EFISTUB_MAJOR_VERSION @ MajorImageVersion + .short LINUX_EFISTUB_MINOR_VERSION @ MinorImageVersion .short 0 @ MajorSubsystemVersion .short 0 @ MinorSubsystemVersion .long 0 @ Win32VersionValue diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 088b0a060876..04f77214f050 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1437,29 +1437,25 @@ __enter_kernel: reloc_code_end: #ifdef CONFIG_EFI_STUB - .align 2 -_start: .long start - . - -ENTRY(efi_stub_entry) - @ allocate space on stack for passing current zImage address - @ and for the EFI stub to return of new entry point of - @ zImage, as EFI stub may copy the kernel. Pointer address - @ is passed in r2. r0 and r1 are passed through from the - @ EFI firmware to efi_entry - adr ip, _start - ldr r3, [ip] - add r3, r3, ip - stmfd sp!, {r3, lr} - mov r2, sp @ pass zImage address in r2 - bl efi_entry - - @ Check for error return from EFI stub. r0 has FDT address - @ or error code. - cmn r0, #1 - beq efi_load_fail - - @ Preserve return value of efi_entry() in r4 - mov r4, r0 +ENTRY(efi_enter_kernel) + mov r7, r0 @ preserve image base + mov r4, r1 @ preserve DT pointer + + mov r0, r4 @ DT start + add r1, r4, r2 @ DT end + bl cache_clean_flush + + mov r0, r7 @ relocated zImage + ldr r1, =_edata @ size of zImage + add r1, r1, r0 @ end of zImage + bl cache_clean_flush + + @ The PE/COFF loader might not have cleaned the code we are + @ running beyond the PoU, and so calling cache_off below from + @ inside the PE/COFF loader allocated region is unsafe unless + @ we explicitly clean it to the PoC. + adr r0, call_cache_fn @ region of code we will + adr r1, 0f @ run with MMU off bl cache_clean_flush bl cache_off @@ -1469,18 +1465,10 @@ ENTRY(efi_stub_entry) mov r0, #0 mov r1, #0xFFFFFFFF mov r2, r4 - - @ Branch to (possibly) relocated zImage that is in [sp] - ldr lr, [sp] - ldr ip, =start_offset - add lr, lr, ip - mov pc, lr @ no mode switch - -efi_load_fail: - @ Return EFI_LOAD_ERROR to EFI firmware on error. - ldr r0, =0x80000001 - ldmfd sp!, {ip, pc} -ENDPROC(efi_stub_entry) + add r7, r7, #(__efi_start - start) + mov pc, r7 @ no mode switch +ENDPROC(efi_enter_kernel) +0: #endif .align diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts index f3ced6df0c9b..9f66f96d09c9 100644 --- a/arch/arm/boot/dts/am437x-idk-evm.dts +++ b/arch/arm/boot/dts/am437x-idk-evm.dts @@ -526,11 +526,11 @@ * Supply voltage supervisor on board will not allow opp50 so * disable it and set opp100 as suspend OPP. */ - opp50@300000000 { + opp50-300000000 { status = "disabled"; }; - opp100@600000000 { + opp100-600000000 { opp-suspend; }; }; diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi index 807a0fc20670..8e04303e8514 100644 --- a/arch/arm/boot/dts/aspeed-g4.dtsi +++ b/arch/arm/boot/dts/aspeed-g4.dtsi @@ -164,6 +164,8 @@ reg = <0x1e6a0000 0x300>; interrupts = <5>; clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; + aspeed,vhub-downstream-ports = <5>; + aspeed,vhub-generic-endpoints = <15>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb2d_default>; status = "disabled"; diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi index ebec0fa8baa7..f12ec04d3cbc 100644 --- a/arch/arm/boot/dts/aspeed-g5.dtsi +++ b/arch/arm/boot/dts/aspeed-g5.dtsi @@ -195,6 +195,8 @@ reg = <0x1e6a0000 0x300>; interrupts = <5>; clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; + aspeed,vhub-downstream-ports = <5>; + aspeed,vhub-generic-endpoints = <15>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb2ad_default>; status = "disabled"; diff --git a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi index 045ce66ca876..7028e21bdd98 100644 --- a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi +++ b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi @@ -1112,6 +1112,31 @@ groups = "UART9"; }; + pinctrl_usb2ah_default: usb2ah_default { + function = "USB2AH"; + groups = "USBA"; + }; + + pinctrl_usb2ad_default: usb2ad_default { + function = "USB2AD"; + groups = "USBA"; + }; + + pinctrl_usb2bh_default: usb2bh_default { + function = "USB2BH"; + groups = "USBB"; + }; + + pinctrl_usb2bd_default: usb2bd_default { + function = "USB2BD"; + groups = "USBB"; + }; + + pinctrl_usb11bhid_default: usb11bhid_default { + function = "USB11BHID"; + groups = "USBB"; + }; + pinctrl_vb_default: vb_default { function = "VB"; groups = "VB"; diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi index 796976d275e1..0a29b3b57a9d 100644 --- a/arch/arm/boot/dts/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed-g6.dtsi @@ -245,6 +245,51 @@ status = "disabled"; }; + ehci0: usb@1e6a1000 { + compatible = "aspeed,ast2600-ehci", "generic-ehci"; + reg = <0x1e6a1000 0x100>; + interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb2ah_default>; + status = "disabled"; + }; + + ehci1: usb@1e6a3000 { + compatible = "aspeed,ast2600-ehci", "generic-ehci"; + reg = <0x1e6a3000 0x100>; + interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon ASPEED_CLK_GATE_USBPORT2CLK>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb2bh_default>; + status = "disabled"; + }; + + uhci: usb@1e6b0000 { + compatible = "aspeed,ast2600-uhci", "generic-uhci"; + reg = <0x1e6b0000 0x100>; + interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; + #ports = <2>; + clocks = <&syscon ASPEED_CLK_GATE_USBUHCICLK>; + status = "disabled"; + /* + * No default pinmux, it will follow EHCI, use an + * explicit pinmux override if EHCI is not enabled. + */ + }; + + vhub: usb-vhub@1e6a0000 { + compatible = "aspeed,ast2600-usb-vhub"; + reg = <0x1e6a0000 0x350>; + interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>; + aspeed,vhub-downstream-ports = <7>; + aspeed,vhub-generic-endpoints = <21>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb2ad_default>; + status = "disabled"; + }; + apb { compatible = "simple-bus"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts index 1b5a835f66bd..efea891b1a76 100644 --- a/arch/arm/boot/dts/bcm2711-rpi-4-b.dts +++ b/arch/arm/boot/dts/bcm2711-rpi-4-b.dts @@ -21,6 +21,7 @@ aliases { ethernet0 = &genet; + pcie0 = &pcie0; }; leds { @@ -31,6 +32,8 @@ pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index b75af21069f9..4c3f606e5b8d 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -112,6 +112,7 @@ &sdhci { #address-cells = <1>; #size-cells = <0>; + pinctrl-names = "default"; pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>; bus-width = <4>; mmc-pwrseq = <&wifi_pwrseq>; diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index 394c8a71b13b..fd2c766e0f71 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -15,6 +15,7 @@ firmware: firmware { compatible = "raspberrypi,bcm2835-firmware", "simple-bus"; mboxes = <&mailbox>; + dma-ranges; }; power: power { diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts b/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts index 66ab35eccba7..28be0332c1c8 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-a-plus.dts @@ -26,6 +26,8 @@ pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; }; diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts index 74ed6d047807..37343148643d 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts @@ -27,6 +27,8 @@ pwr { label = "PWR"; gpios = <&expgpio 2 GPIO_ACTIVE_LOW>; + default-state = "keep"; + linux,default-trigger = "default-on"; }; }; diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts index 3931fb068ff0..91d1018ab75f 100644 --- a/arch/arm/boot/dts/dm8148-evm.dts +++ b/arch/arm/boot/dts/dm8148-evm.dts @@ -24,12 +24,12 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &davinci_mdio { diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts index 9e43d5ec0bb2..79ccdd4470f4 100644 --- a/arch/arm/boot/dts/dm8148-t410.dts +++ b/arch/arm/boot/dts/dm8148-t410.dts @@ -33,12 +33,12 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &davinci_mdio { diff --git a/arch/arm/boot/dts/dra62x-j5eco-evm.dts b/arch/arm/boot/dts/dra62x-j5eco-evm.dts index 861ab90a3f3a..c16e183822be 100644 --- a/arch/arm/boot/dts/dra62x-j5eco-evm.dts +++ b/arch/arm/boot/dts/dra62x-j5eco-evm.dts @@ -24,12 +24,12 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; }; &davinci_mdio { diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index de7f85efaa51..af06a55d1c5c 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -61,10 +61,10 @@ regulator-max-microvolt = <1800000>; }; - evm_3v3: fixedregulator-evm3v3 { + vsys_3v3: fixedregulator-vsys3v3 { /* Output of Cntlr A of TPS43351-Q1 on dra7-evm */ compatible = "regulator-fixed"; - regulator-name = "evm_3v3"; + regulator-name = "vsys_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; vin-supply = <&evm_12v0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index fc418834890d..2119a78e9c15 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -3474,6 +3474,7 @@ clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER13_CLKCTRL 24>; clock-names = "fck"; interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>; + ti,timer-pwm; }; }; @@ -3501,6 +3502,7 @@ clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>; clock-names = "fck"; interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>; + ti,timer-pwm; }; }; @@ -3528,6 +3530,7 @@ clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>; clock-names = "fck"; interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>; + ti,timer-pwm; }; }; @@ -3555,6 +3558,7 @@ clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>; clock-names = "fck"; interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>; + ti,timer-pwm; }; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index d78b684e7fca..5f5ee16f07a3 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -148,6 +148,7 @@ #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x0 0x0 0xc0000000>; + dma-ranges = <0x80000000 0x0 0x80000000 0x80000000>; ti,hwmods = "l3_main_1", "l3_main_2"; reg = <0x0 0x44000000 0x0 0x1000000>, <0x0 0x45000000 0x0 0x1000>; @@ -184,6 +185,7 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; @@ -238,6 +240,7 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index 2f7539afef2b..42b8a205b64f 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -128,3 +128,8 @@ &usb4_tm { status = "disabled"; }; + +&mmc3 { + /* dra76x is not affected by i887 */ + max-frequency = <96000000>; +}; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index 55cef4cac5f1..dc0a93bccbf1 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -796,16 +796,6 @@ clock-div = <1>; }; - ipu1_gfclk_mux: ipu1_gfclk_mux@520 { - #clock-cells = <0>; - compatible = "ti,mux-clock"; - clocks = <&dpll_abe_m2x2_ck>, <&dpll_core_h22x2_ck>; - ti,bit-shift = <24>; - reg = <0x0520>; - assigned-clocks = <&ipu1_gfclk_mux>; - assigned-clock-parents = <&dpll_core_h22x2_ck>; - }; - dummy_ck: dummy_ck { #clock-cells = <0>; compatible = "fixed-clock"; @@ -1564,6 +1554,8 @@ compatible = "ti,clkctrl"; reg = <0x20 0x4>; #clock-cells = <2>; + assigned-clocks = <&ipu1_clkctrl DRA7_IPU1_MMU_IPU1_CLKCTRL 24>; + assigned-clock-parents = <&dpll_core_h22x2_ck>; }; ipu_clkctrl: ipu-clkctrl@50 { diff --git a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi index 31719c079d67..44f97546dd0a 100644 --- a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi +++ b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi @@ -33,7 +33,7 @@ }; }; - lcd_vdd3_reg: voltage-regulator-6 { + lcd_vdd3_reg: voltage-regulator-7 { compatible = "regulator-fixed"; regulator-name = "LCD_VDD_2.2V"; regulator-min-microvolt = <2200000>; @@ -42,7 +42,7 @@ enable-active-high; }; - ps_als_reg: voltage-regulator-7 { + ps_als_reg: voltage-regulator-8 { compatible = "regulator-fixed"; regulator-name = "LED_A_3.0V"; regulator-min-microvolt = <3000000>; diff --git a/arch/arm/boot/dts/exynos4412-n710x.dts b/arch/arm/boot/dts/exynos4412-n710x.dts index 98cd1284cd90..4189e1fb204c 100644 --- a/arch/arm/boot/dts/exynos4412-n710x.dts +++ b/arch/arm/boot/dts/exynos4412-n710x.dts @@ -13,7 +13,7 @@ /* bootargs are passed in by bootloader */ - cam_vdda_reg: voltage-regulator-6 { + cam_vdda_reg: voltage-regulator-7 { compatible = "regulator-fixed"; regulator-name = "CAM_SENSOR_CORE_1.2V"; regulator-min-microvolt = <1200000>; diff --git a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts index cd075621de52..84fcc203a2e4 100644 --- a/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts +++ b/arch/arm/boot/dts/imx6dl-colibri-eval-v3.dts @@ -275,7 +275,7 @@ /* SRAM on Colibri nEXT_CS0 */ sram@0,0 { - compatible = "cypress,cy7c1019dv33-10zsxi, mtd-ram"; + compatible = "cypress,cy7c1019dv33-10zsxi", "mtd-ram"; reg = <0 0 0x00010000>; #address-cells = <1>; #size-cells = <1>; @@ -286,7 +286,7 @@ /* SRAM on Colibri nEXT_CS1 */ sram@1,0 { - compatible = "cypress,cy7c1019dv33-10zsxi, mtd-ram"; + compatible = "cypress,cy7c1019dv33-10zsxi", "mtd-ram"; reg = <1 0 0x00010000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi index 978dc1c2ff1b..77d871340eb7 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi @@ -112,7 +112,7 @@ regulators { vdd_arm: buck1 { regulator-name = "vdd_arm"; - regulator-min-microvolt = <730000>; + regulator-min-microvolt = <925000>; regulator-max-microvolt = <1380000>; regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-always-on; @@ -120,7 +120,7 @@ vdd_soc: buck2 { regulator-name = "vdd_soc"; - regulator-min-microvolt = <730000>; + regulator-min-microvolt = <1150000>; regulator-max-microvolt = <1380000>; regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-always-on; @@ -192,7 +192,6 @@ pinctrl-0 = <&pinctrl_usdhc4>; bus-width = <8>; non-removable; - vmmc-supply = <&vdd_emmc_1p8>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi index d05be3f0e2a7..04717cf69db0 100644 --- a/arch/arm/boot/dts/imx7-colibri.dtsi +++ b/arch/arm/boot/dts/imx7-colibri.dtsi @@ -336,7 +336,6 @@ assigned-clock-rates = <400000000>; bus-width = <8>; fsl,tuning-step = <2>; - max-frequency = <100000000>; vmmc-supply = <®_module_3v3>; vqmmc-supply = <®_DCDC3>; non-removable; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index 92f6d0c2a74f..4c22828df55f 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -44,7 +44,7 @@ opp-hz = /bits/ 64 <792000000>; opp-microvolt = <1000000>; clock-latency-ns = <150000>; - opp-supported-hw = <0xd>, <0xf>; + opp-supported-hw = <0xd>, <0x7>; opp-suspend; }; @@ -52,7 +52,7 @@ opp-hz = /bits/ 64 <996000000>; opp-microvolt = <1100000>; clock-latency-ns = <150000>; - opp-supported-hw = <0xc>, <0xf>; + opp-supported-hw = <0xc>, <0x7>; opp-suspend; }; @@ -60,7 +60,7 @@ opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1225000>; clock-latency-ns = <150000>; - opp-supported-hw = <0x8>, <0xf>; + opp-supported-hw = <0x8>, <0x3>; opp-suspend; }; }; diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi index 0855b1fe98e0..760a68c163c8 100644 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@ -747,7 +747,7 @@ }; mdio0: mdio@2d24000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>; @@ -756,7 +756,7 @@ }; mdio1: mdio@2d64000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index 85665506f4f8..9067e0ef4240 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -182,6 +182,14 @@ pwm-names = "enable", "direction"; direction-duty-cycle-ns = <10000000>; }; + + backlight: backlight { + compatible = "led-backlight"; + + leds = <&backlight_led>; + brightness-levels = <31 63 95 127 159 191 223 255>; + default-brightness-level = <6>; + }; }; &dss { @@ -205,6 +213,8 @@ vddi-supply = <&lcd_regulator>; reset-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>; /* gpio101 */ + backlight = <&backlight>; + width-mm = <50>; height-mm = <89>; @@ -393,12 +403,11 @@ ramp-up-us = <1024>; ramp-down-us = <8193>; - led@0 { + backlight_led: led@0 { reg = <0>; led-sources = <2>; ti,led-mode = <0>; label = ":backlight"; - linux,default-trigger = "backlight"; }; led@1 { @@ -420,7 +429,7 @@ reset-gpios = <&gpio6 13 GPIO_ACTIVE_HIGH>; /* gpio173 */ /* gpio_183 with sys_nirq2 pad as wakeup */ - interrupts-extended = <&gpio6 23 IRQ_TYPE_EDGE_FALLING>, + interrupts-extended = <&gpio6 23 IRQ_TYPE_LEVEL_LOW>, <&omap4_pmx_core 0x160>; interrupt-names = "irq", "wakeup"; wakeup-source; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index c3c6d7d04a76..4089d97405c9 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -854,34 +854,46 @@ compatible = "ti,omap2-onenand"; reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */ + /* + * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported + * bootloader set values when booted with v5.1 + * (OneNAND Manufacturer: Samsung): + * + * cs0 GPMC_CS_CONFIG1: 0xfb001202 + * cs0 GPMC_CS_CONFIG2: 0x00111100 + * cs0 GPMC_CS_CONFIG3: 0x00020200 + * cs0 GPMC_CS_CONFIG4: 0x11001102 + * cs0 GPMC_CS_CONFIG5: 0x03101616 + * cs0 GPMC_CS_CONFIG6: 0x90060000 + */ gpmc,sync-read; gpmc,sync-write; gpmc,burst-length = <16>; gpmc,burst-read; gpmc,burst-wrap; gpmc,burst-write; - gpmc,device-width = <2>; /* GPMC_DEVWIDTH_16BIT */ - gpmc,mux-add-data = <2>; /* GPMC_MUX_AD */ + gpmc,device-width = <2>; + gpmc,mux-add-data = <2>; gpmc,cs-on-ns = <0>; - gpmc,cs-rd-off-ns = <87>; - gpmc,cs-wr-off-ns = <87>; + gpmc,cs-rd-off-ns = <102>; + gpmc,cs-wr-off-ns = <102>; gpmc,adv-on-ns = <0>; - gpmc,adv-rd-off-ns = <10>; - gpmc,adv-wr-off-ns = <10>; - gpmc,oe-on-ns = <15>; - gpmc,oe-off-ns = <87>; + gpmc,adv-rd-off-ns = <12>; + gpmc,adv-wr-off-ns = <12>; + gpmc,oe-on-ns = <12>; + gpmc,oe-off-ns = <102>; gpmc,we-on-ns = <0>; - gpmc,we-off-ns = <87>; - gpmc,rd-cycle-ns = <112>; - gpmc,wr-cycle-ns = <112>; - gpmc,access-ns = <81>; - gpmc,page-burst-access-ns = <15>; + gpmc,we-off-ns = <102>; + gpmc,rd-cycle-ns = <132>; + gpmc,wr-cycle-ns = <132>; + gpmc,access-ns = <96>; + gpmc,page-burst-access-ns = <18>; gpmc,bus-turnaround-ns = <0>; gpmc,cycle2cycle-delay-ns = <0>; gpmc,wait-monitoring-ns = <0>; - gpmc,clk-activation-ns = <5>; - gpmc,wr-data-mux-bus-ns = <30>; - gpmc,wr-access-ns = <81>; + gpmc,clk-activation-ns = <6>; + gpmc,wr-data-mux-bus-ns = <36>; + gpmc,wr-access-ns = <96>; gpmc,sync-clk-ps = <15000>; /* diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index d0ecf54d5a23..a7562d3deb1a 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -143,6 +143,7 @@ #address-cells = <1>; #size-cells = <1>; ranges = <0 0 0 0xc0000000>; + dma-ranges = <0x80000000 0x0 0x80000000 0x80000000>; ti,hwmods = "l3_main_1", "l3_main_2", "l3_main_3"; reg = <0 0x44000000 0 0x2000>, <0 0x44800000 0 0x3000>, diff --git a/arch/arm/boot/dts/ox810se.dtsi b/arch/arm/boot/dts/ox810se.dtsi index 9f6c2b660ed3..0755e5864c4a 100644 --- a/arch/arm/boot/dts/ox810se.dtsi +++ b/arch/arm/boot/dts/ox810se.dtsi @@ -323,8 +323,8 @@ interrupt-controller; reg = <0 0x200>; #interrupt-cells = <1>; - valid-mask = <0xFFFFFFFF>; - clear-mask = <0>; + valid-mask = <0xffffffff>; + clear-mask = <0xffffffff>; }; timer0: timer@200 { diff --git a/arch/arm/boot/dts/ox820.dtsi b/arch/arm/boot/dts/ox820.dtsi index c9b327732063..90846a7655b4 100644 --- a/arch/arm/boot/dts/ox820.dtsi +++ b/arch/arm/boot/dts/ox820.dtsi @@ -240,8 +240,8 @@ reg = <0 0x200>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; #interrupt-cells = <1>; - valid-mask = <0xFFFFFFFF>; - clear-mask = <0>; + valid-mask = <0xffffffff>; + clear-mask = <0xffffffff>; }; timer0: timer@200 { diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi index beb9885e6ffc..c0999e27e9b1 100644 --- a/arch/arm/boot/dts/r8a7779.dtsi +++ b/arch/arm/boot/dts/r8a7779.dtsi @@ -377,7 +377,7 @@ }; sata: sata@fc600000 { - compatible = "renesas,sata-r8a7779", "renesas,rcar-sata"; + compatible = "renesas,sata-r8a7779"; reg = <0xfc600000 0x200000>; interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>; clocks = <&mstp1_clks R8A7779_CLK_SATA>; diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi index 1532a0e59af4..a2c37adacf77 100644 --- a/arch/arm/boot/dts/sun8i-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a33.dtsi @@ -215,7 +215,7 @@ }; crypto: crypto-engine@1c15000 { - compatible = "allwinner,sun4i-a10-crypto"; + compatible = "allwinner,sun8i-a33-crypto"; reg = <0x01c15000 0x1000>; interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_BUS_SS>, <&ccu CLK_SS>; diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts index 2fd31a0a0b34..e8b3669e0e5d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts +++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts @@ -374,8 +374,8 @@ }; ®_dldo3 { - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-name = "vdd-csi"; }; @@ -498,7 +498,8 @@ }; &usbphy { - usb0_id_det-gpios = <&pio 7 11 GPIO_ACTIVE_HIGH>; /* PH11 */ + usb0_id_det-gpios = <&pio 7 11 (GPIO_ACTIVE_HIGH | GPIO_PULL_UP)>; /* PH11 */ + usb0_vbus_power-supply = <&usb_power_supply>; usb0_vbus-supply = <®_drivevbus>; usb1_vbus-supply = <®_vmain>; usb2_vbus-supply = <®_vmain>; diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi index 74ac7ee9383c..e7b9bef1be6b 100644 --- a/arch/arm/boot/dts/sun8i-a83t.dtsi +++ b/arch/arm/boot/dts/sun8i-a83t.dtsi @@ -1006,10 +1006,10 @@ reg = <0x01c30000 0x104>; interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - resets = <&ccu CLK_BUS_EMAC>; - reset-names = "stmmaceth"; - clocks = <&ccu RST_BUS_EMAC>; + clocks = <&ccu CLK_BUS_EMAC>; clock-names = "stmmaceth"; + resets = <&ccu RST_BUS_EMAC>; + reset-names = "stmmaceth"; status = "disabled"; mdio: mdio { diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi index 8f09a24b36ec..a9d5d6ddbd71 100644 --- a/arch/arm/boot/dts/sun8i-r40.dtsi +++ b/arch/arm/boot/dts/sun8i-r40.dtsi @@ -181,6 +181,32 @@ interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; }; + spi0: spi@1c05000 { + compatible = "allwinner,sun8i-r40-spi", + "allwinner,sun8i-h3-spi"; + reg = <0x01c05000 0x1000>; + interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_SPI0>, <&ccu CLK_SPI0>; + clock-names = "ahb", "mod"; + resets = <&ccu RST_BUS_SPI0>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + spi1: spi@1c06000 { + compatible = "allwinner,sun8i-r40-spi", + "allwinner,sun8i-h3-spi"; + reg = <0x01c06000 0x1000>; + interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_SPI1>, <&ccu CLK_SPI1>; + clock-names = "ahb", "mod"; + resets = <&ccu RST_BUS_SPI1>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + csi0: csi@1c09000 { compatible = "allwinner,sun8i-r40-csi0", "allwinner,sun7i-a20-csi0"; @@ -290,6 +316,29 @@ resets = <&ccu RST_BUS_CE>; }; + spi2: spi@1c17000 { + compatible = "allwinner,sun8i-r40-spi", + "allwinner,sun8i-h3-spi"; + reg = <0x01c17000 0x1000>; + interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_SPI2>, <&ccu CLK_SPI2>; + clock-names = "ahb", "mod"; + resets = <&ccu RST_BUS_SPI2>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + ahci: sata@1c18000 { + compatible = "allwinner,sun8i-r40-ahci"; + reg = <0x01c18000 0x1000>; + interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_SATA>, <&ccu CLK_SATA>; + resets = <&ccu RST_BUS_SATA>; + reset-names = "ahci"; + status = "disabled"; + }; + ehci1: usb@1c19000 { compatible = "allwinner,sun8i-r40-ehci", "generic-ehci"; reg = <0x01c19000 0x100>; @@ -336,6 +385,19 @@ status = "disabled"; }; + spi3: spi@1c1f000 { + compatible = "allwinner,sun8i-r40-spi", + "allwinner,sun8i-h3-spi"; + reg = <0x01c1f000 0x1000>; + interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_SPI3>, <&ccu CLK_SPI3>; + clock-names = "ahb", "mod"; + resets = <&ccu RST_BUS_SPI3>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + ccu: clock@1c20000 { compatible = "allwinner,sun8i-r40-ccu"; reg = <0x01c20000 0x400>; @@ -653,69 +715,6 @@ #size-cells = <0>; }; - spi0: spi@1c05000 { - compatible = "allwinner,sun8i-r40-spi", - "allwinner,sun8i-h3-spi"; - reg = <0x01c05000 0x1000>; - interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_BUS_SPI0>, <&ccu CLK_SPI0>; - clock-names = "ahb", "mod"; - resets = <&ccu RST_BUS_SPI0>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <0>; - }; - - spi1: spi@1c06000 { - compatible = "allwinner,sun8i-r40-spi", - "allwinner,sun8i-h3-spi"; - reg = <0x01c06000 0x1000>; - interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_BUS_SPI1>, <&ccu CLK_SPI1>; - clock-names = "ahb", "mod"; - resets = <&ccu RST_BUS_SPI1>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <0>; - }; - - spi2: spi@1c07000 { - compatible = "allwinner,sun8i-r40-spi", - "allwinner,sun8i-h3-spi"; - reg = <0x01c07000 0x1000>; - interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_BUS_SPI2>, <&ccu CLK_SPI2>; - clock-names = "ahb", "mod"; - resets = <&ccu RST_BUS_SPI2>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <0>; - }; - - spi3: spi@1c0f000 { - compatible = "allwinner,sun8i-r40-spi", - "allwinner,sun8i-h3-spi"; - reg = <0x01c0f000 0x1000>; - interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_BUS_SPI3>, <&ccu CLK_SPI3>; - clock-names = "ahb", "mod"; - resets = <&ccu RST_BUS_SPI3>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <0>; - }; - - ahci: sata@1c18000 { - compatible = "allwinner,sun8i-r40-ahci"; - reg = <0x01c18000 0x1000>; - interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_BUS_SATA>, <&ccu CLK_SATA>; - resets = <&ccu RST_BUS_SATA>; - reset-names = "ahci"; - status = "disabled"; - - }; - gmac: ethernet@1c50000 { compatible = "allwinner,sun8i-r40-gmac"; syscon = <&ccu>; diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 947ef7981d92..c98ebae1aeac 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -302,10 +302,13 @@ static int sa1111_retrigger_irq(struct irq_data *d) break; } - if (i == 8) + if (i == 8) { pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n", d->irq); - return i == 8 ? -1 : 0; + return 0; + } + + return 1; } static int sa1111_type_irq(struct irq_data *d, unsigned int flags) diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig index 519ff58e67b3..0afcae9f7cf8 100644 --- a/arch/arm/configs/bcm2835_defconfig +++ b/arch/arm/configs/bcm2835_defconfig @@ -178,6 +178,7 @@ CONFIG_SCHED_TRACER=y CONFIG_STACK_TRACER=y CONFIG_FUNCTION_PROFILER=y CONFIG_TEST_KSTRTOX=y +CONFIG_DEBUG_FS=y CONFIG_KGDB=y CONFIG_KGDB_KDB=y CONFIG_STRICT_DEVMEM=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index c32c338f7704..847f9874ccc4 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -375,6 +375,7 @@ CONFIG_BACKLIGHT_GENERIC=m CONFIG_BACKLIGHT_PWM=m CONFIG_BACKLIGHT_PANDORA=m CONFIG_BACKLIGHT_GPIO=m +CONFIG_BACKLIGHT_LED=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig index fe2e1e82e233..e73c97b0f5b0 100644 --- a/arch/arm/configs/socfpga_defconfig +++ b/arch/arm/configs/socfpga_defconfig @@ -157,6 +157,7 @@ CONFIG_NLS_ISO8859_1=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set CONFIG_FUNCTION_TRACER=y diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h index f4fe4d02cef2..79fa327238e8 100644 --- a/arch/arm/include/asm/floppy.h +++ b/arch/arm/include/asm/floppy.h @@ -8,16 +8,18 @@ */ #ifndef __ASM_ARM_FLOPPY_H #define __ASM_ARM_FLOPPY_H -#if 0 -#include <mach/floppy.h> -#endif -#define fd_outb(val,port) \ - do { \ - if ((port) == (u32)FD_DOR) \ - fd_setdor((val)); \ - else \ - outb((val),(port)); \ +#define fd_outb(val,port) \ + do { \ + int new_val = (val); \ + if (((port) & 7) == FD_DOR) { \ + if (new_val & 0xf0) \ + new_val = (new_val & 0x0c) | \ + floppy_selects[new_val & 3]; \ + else \ + new_val &= 0x0c; \ + } \ + outb(new_val, (port)); \ } while(0) #define fd_inb(port) inb((port)) @@ -53,69 +55,7 @@ static inline int fd_dma_setup(void *data, unsigned int length, * to a non-zero track, and then restoring it to track 0. If an error occurs, * then there is no floppy drive present. [to be put back in again] */ -static unsigned char floppy_selects[2][4] = -{ - { 0x10, 0x21, 0x23, 0x33 }, - { 0x10, 0x21, 0x23, 0x33 } -}; - -#define fd_setdor(dor) \ -do { \ - int new_dor = (dor); \ - if (new_dor & 0xf0) \ - new_dor = (new_dor & 0x0c) | floppy_selects[fdc][new_dor & 3]; \ - else \ - new_dor &= 0x0c; \ - outb(new_dor, FD_DOR); \ -} while (0) - -/* - * Someday, we'll automatically detect which drives are present... - */ -static inline void fd_scandrives (void) -{ -#if 0 - int floppy, drive_count; - - fd_disable_irq(); - raw_cmd = &default_raw_cmd; - raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_SEEK; - raw_cmd->track = 0; - raw_cmd->rate = ?; - drive_count = 0; - for (floppy = 0; floppy < 4; floppy ++) { - current_drive = drive_count; - /* - * Turn on floppy motor - */ - if (start_motor(redo_fd_request)) - continue; - /* - * Set up FDC - */ - fdc_specify(); - /* - * Tell FDC to recalibrate - */ - output_byte(FD_RECALIBRATE); - LAST_OUT(UNIT(floppy)); - /* wait for command to complete */ - if (!successful) { - int i; - for (i = drive_count; i < 3; i--) - floppy_selects[fdc][i] = floppy_selects[fdc][i + 1]; - floppy_selects[fdc][3] = 0; - floppy -= 1; - } else - drive_count++; - } -#else - floppy_selects[0][0] = 0x10; - floppy_selects[0][1] = 0x21; - floppy_selects[0][2] = 0x23; - floppy_selects[0][3] = 0x33; -#endif -} +static unsigned char floppy_selects[4] = { 0x10, 0x21, 0x23, 0x33 }; #define FDC1 (0x3f0) @@ -135,9 +75,7 @@ static inline void fd_scandrives (void) */ static void driveswap(int *ints, int dummy, int dummy2) { - floppy_selects[0][0] ^= floppy_selects[0][1]; - floppy_selects[0][1] ^= floppy_selects[0][0]; - floppy_selects[0][0] ^= floppy_selects[0][1]; + swap(floppy_selects[0], floppy_selects[1]); } #define EXTRA_FLOPPY_PARAMS ,{ "driveswap", &driveswap, NULL, 0, 0 } diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 83c391b597d4..e133da303a98 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -134,10 +134,12 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret, tmp; + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; + #ifndef CONFIG_SMP preempt_disable(); #endif - pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -159,7 +161,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); #ifndef CONFIG_SMP preempt_enable(); #endif diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c3314b286a61..a827b4d60d38 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -392,9 +392,6 @@ static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_vhe_guest_enter(void) {} -static inline void kvm_arm_vhe_guest_exit(void) {} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 0d0d5178e2c3..3609a6980c34 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -141,7 +141,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SECCOMP 7 /* seccomp syscall filtering active */ -#define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 8a0fae94d45e..435aba289fc5 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -16,6 +16,9 @@ /* Enable topology flag updates */ #define arch_update_cpu_topology topology_update_cpu_topology +/* Replace task scheduler's default thermal pressure retrieve API */ +#define arch_scale_thermal_pressure topology_get_thermal_pressure + #else static inline void init_cpu_topology(void) { } diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c index bb18ed0539f4..0ce388f15422 100644 --- a/arch/arm/kernel/reboot.c +++ b/arch/arm/kernel/reboot.c @@ -88,11 +88,11 @@ void soft_restart(unsigned long addr) * to execute e.g. a RAM-based pin loop is not sufficient. This allows the * kexec'd kernel to use any and all RAM as it sees fit, without having to * avoid any code or data used by any SW CPU pin loop. The CPU hotplug - * functionality embodied in disable_nonboot_cpus() to achieve this. + * functionality embodied in smp_shutdown_nonboot_cpus() to achieve this. */ void machine_shutdown(void) { - disable_nonboot_cpus(); + smp_shutdown_nonboot_cpus(reboot_cpu); } /* diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index c89ac1b9d28b..e0330a25e1c6 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -95,6 +95,8 @@ static bool __init cntvct_functional(void) */ np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); if (!np) + np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer"); + if (!np) goto out_put; if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 95b2e1ce559c..f8016e3db65d 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -118,7 +118,7 @@ ENTRY(arm_copy_from_user) ENDPROC(arm_copy_from_user) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble ldmfd sp!, {r1, r2, r3} diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 35ff620537e6..03506ce46149 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -91,6 +91,8 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif +AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a +obj-$(CONFIG_SOC_IMX6) += resume-imx6.o obj-$(CONFIG_SOC_IMX6) += pm-imx6.o obj-$(CONFIG_SOC_IMX1) += mach-imx1.o diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 912aeceb4ff8..5aa5796cff0e 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -109,17 +109,17 @@ void imx_cpu_die(unsigned int cpu); int imx_cpu_kill(unsigned int cpu); #ifdef CONFIG_SUSPEND -void v7_cpu_resume(void); void imx53_suspend(void __iomem *ocram_vbase); extern const u32 imx53_suspend_sz; void imx6_suspend(void __iomem *ocram_vbase); #else -static inline void v7_cpu_resume(void) {} static inline void imx53_suspend(void __iomem *ocram_vbase) {} static const u32 imx53_suspend_sz; static inline void imx6_suspend(void __iomem *ocram_vbase) {} #endif +void v7_cpu_resume(void); + void imx6_pm_ccm_init(const char *ccm_compat); void imx6q_pm_init(void); void imx6dl_pm_init(void); diff --git a/arch/arm/mach-imx/resume-imx6.S b/arch/arm/mach-imx/resume-imx6.S new file mode 100644 index 000000000000..5bd1ba7ef15b --- /dev/null +++ b/arch/arm/mach-imx/resume-imx6.S @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright 2014 Freescale Semiconductor, Inc. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/hardware/cache-l2x0.h> +#include "hardware.h" + +/* + * The following code must assume it is running from physical address + * where absolute virtual addresses to the data section have to be + * turned into relative ones. + */ + +ENTRY(v7_cpu_resume) + bl v7_invalidate_l1 +#ifdef CONFIG_CACHE_L2X0 + bl l2c310_early_resume +#endif + b cpu_resume +ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 062391ff13da..1eabf2d2834b 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -327,17 +327,3 @@ resume: ret lr ENDPROC(imx6_suspend) - -/* - * The following code must assume it is running from physical address - * where absolute virtual addresses to the data section have to be - * turned into relative ones. - */ - -ENTRY(v7_cpu_resume) - bl v7_invalidate_l1 -#ifdef CONFIG_CACHE_L2X0 - bl l2c310_early_resume -#endif - b cpu_resume -ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-meson/Kconfig b/arch/arm/mach-meson/Kconfig index 01f0f4b765e0..75034fe197e3 100644 --- a/arch/arm/mach-meson/Kconfig +++ b/arch/arm/mach-meson/Kconfig @@ -9,7 +9,6 @@ menuconfig ARCH_MESON select CACHE_L2X0 select PINCTRL select PINCTRL_MESON - select COMMON_CLK select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD if SMP diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index e1135b9d67c6..5017a3be0ff0 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -16,7 +16,7 @@ hwmod-common = omap_hwmod.o omap_hwmod_reset.o \ clock-common = clock.o secure-common = omap-smc.o omap-secure.o -obj-$(CONFIG_ARCH_OMAP2) += $(omap-2-3-common) $(hwmod-common) $(secure-common) +obj-$(CONFIG_ARCH_OMAP2) += $(omap-2-3-common) $(hwmod-common) obj-$(CONFIG_ARCH_OMAP3) += $(omap-2-3-common) $(hwmod-common) $(secure-common) obj-$(CONFIG_ARCH_OMAP4) += $(hwmod-common) $(secure-common) obj-$(CONFIG_SOC_AM33XX) += $(hwmod-common) $(secure-common) diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index f28047233665..27608d1026cb 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -431,7 +431,6 @@ void __init omap2420_init_early(void) omap_hwmod_init_postsetup(); omap_clk_soc_init = omap2420_dt_clk_init; rate_table = omap2420_rate_table; - omap_secure_init(); } void __init omap2420_init_late(void) @@ -456,7 +455,6 @@ void __init omap2430_init_early(void) omap_hwmod_init_postsetup(); omap_clk_soc_init = omap2430_dt_clk_init; rate_table = omap2430_rate_table; - omap_secure_init(); } void __init omap2430_init_late(void) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts index 2f1f829450a2..6c9cc45fb417 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts @@ -76,3 +76,7 @@ }; }; }; + +&ir { + linux,rc-map-name = "rc-videostrong-kii-pro"; +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index f82f25c1a5f9..d5dc12878dfe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -327,7 +327,7 @@ #size-cells = <0>; bus-width = <4>; - max-frequency = <50000000>; + max-frequency = <60000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts index a8bb3fa9fec9..cb1b48f5b8b1 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts @@ -593,6 +593,7 @@ compatible = "brcm,bcm43438-bt"; interrupt-parent = <&gpio_intc>; interrupts = <95 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "host-wakeup"; shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>; max-speed = <2000000>; clocks = <&wifi32k>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 0bf375ec959b..55b71bb4baf8 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -53,7 +53,7 @@ * PSCI node is not added default, U-boot will add missing * parts if it determines to use PSCI. */ - entry-method = "arm,psci"; + entry-method = "psci"; CPU_PW20: cpu-pw20 { compatible = "arm,idle-state"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi index 6082ae022136..d237162a8744 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi @@ -20,6 +20,8 @@ }; &fman0 { + fsl,erratum-a050385; + /* these aliases provide the FMan ports mapping */ enet0: ethernet@e0000 { }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts index 4223a2352d45..dde50c88f5e3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts @@ -119,12 +119,12 @@ ethernet@e4000 { phy-handle = <&rgmii_phy1>; - phy-connection-type = "rgmii-txid"; + phy-connection-type = "rgmii-id"; }; ethernet@e6000 { phy-handle = <&rgmii_phy2>; - phy-connection-type = "rgmii-txid"; + phy-connection-type = "rgmii-id"; }; ethernet@e8000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts index dbc23d6cd3b4..d53ccc56bb63 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts @@ -131,12 +131,12 @@ &fman0 { ethernet@e4000 { phy-handle = <&rgmii_phy1>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-id"; }; ethernet@e6000 { phy-handle = <&rgmii_phy2>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-id"; }; ethernet@e8000 { diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts index d3d26cca7d52..13460a360c6a 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts @@ -52,11 +52,6 @@ compatible = "ethernet-phy-ieee802.3-c22"; reg = <0>; }; - - ethphy1: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; }; }; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi index e1d357eaad7c..d8c44d3ca15a 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi @@ -102,7 +102,7 @@ }; gmac0: ethernet@ff800000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff800000 0x2000>; interrupts = <0 90 4>; interrupt-names = "macirq"; @@ -118,7 +118,7 @@ }; gmac1: ethernet@ff802000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff802000 0x2000>; interrupts = <0 91 4>; interrupt-names = "macirq"; @@ -134,7 +134,7 @@ }; gmac2: ethernet@ff804000 { - compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac"; reg = <0xff804000 0x2000>; interrupts = <0 92 4>; interrupt-names = "macirq"; diff --git a/arch/arm64/boot/dts/sprd/sc9863a.dtsi b/arch/arm64/boot/dts/sprd/sc9863a.dtsi index cd80756c888d..2c590ca1d079 100644 --- a/arch/arm64/boot/dts/sprd/sc9863a.dtsi +++ b/arch/arm64/boot/dts/sprd/sc9863a.dtsi @@ -108,7 +108,7 @@ }; idle-states { - entry-method = "arm,psci"; + entry-method = "psci"; CORE_PD: core-pd { compatible = "arm,idle-state"; entry-latency-us = <4000>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 905109f6814f..e7573289a66f 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -62,6 +62,7 @@ CONFIG_ARCH_ZX=y CONFIG_ARCH_ZYNQMP=y CONFIG_ARM64_VA_BITS_48=y CONFIG_SCHED_MC=y +CONFIG_SCHED_SMT=y CONFIG_NUMA=y CONFIG_SECCOMP=y CONFIG_KEXEC=y @@ -773,7 +774,7 @@ CONFIG_ARCH_R8A774A1=y CONFIG_ARCH_R8A774B1=y CONFIG_ARCH_R8A774C0=y CONFIG_ARCH_R8A7795=y -CONFIG_ARCH_R8A7796=y +CONFIG_ARCH_R8A77960=y CONFIG_ARCH_R8A77961=y CONFIG_ARCH_R8A77965=y CONFIG_ARCH_R8A77970=y diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c index c1f9660d104c..37ca3e889848 100644 --- a/arch/arm64/crypto/chacha-neon-glue.c +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -55,10 +55,10 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, break; } chacha_4block_xor_neon(state, dst, src, nrounds, l); - bytes -= CHACHA_BLOCK_SIZE * 5; - src += CHACHA_BLOCK_SIZE * 5; - dst += CHACHA_BLOCK_SIZE * 5; - state[12] += 5; + bytes -= l; + src += l; + dst += l; + state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE); } } diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 324e7d5ab37e..5e5dc05d63a0 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -221,7 +221,7 @@ alternative_endif .macro user_alt, label, oldinstr, newinstr, cond 9999: alternative_insn "\oldinstr", "\newinstr", \cond - _ASM_EXTABLE 9999b, \label + _asm_extable 9999b, \label .endm /* diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 25fec4bde43a..a358e97572c1 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -32,7 +32,7 @@ static inline void gic_write_eoir(u32 irq) isb(); } -static inline void gic_write_dir(u32 irq) +static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); isb(); diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 806e9dc2a852..a4d1b5f771f6 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -69,7 +69,7 @@ static inline int icache_is_aliasing(void) return test_bit(ICACHEF_ALIASING, &__icache_flags); } -static inline int icache_is_vpipt(void) +static __always_inline int icache_is_vpipt(void) { return test_bit(ICACHEF_VPIPT, &__icache_flags); } diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 665c78e0665a..e6cca3d4acf7 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -145,7 +145,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -static inline void __flush_icache_all(void) +static __always_inline void __flush_icache_all(void) { if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) return; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 92ef9539874a..2a746b99e937 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -435,13 +435,13 @@ cpuid_feature_extract_signed_field(u64 features, int field) return cpuid_feature_extract_signed_field_width(features, field, 4); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); @@ -564,7 +564,7 @@ static inline bool system_supports_mixed_endian(void) return val == 0x1; } -static inline bool system_supports_fpsimd(void) +static __always_inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); } @@ -575,13 +575,13 @@ static inline bool system_uses_ttbr0_pan(void) !cpus_have_const_cap(ARM64_HAS_PAN); } -static inline bool system_supports_sve(void) +static __always_inline bool system_supports_sve(void) { return IS_ENABLED(CONFIG_ARM64_SVE) && cpus_have_const_cap(ARM64_SVE); } -static inline bool system_supports_cnp(void) +static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && cpus_have_const_cap(ARM64_HAS_CNP); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 44531a69d32b..45e821222774 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -58,13 +58,6 @@ efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); /* arch specific definitions used by the stub code */ /* - * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from - * start of kernel and may not cross a 2MiB boundary. We set alignment to - * 2MiB so we know it won't cross a 2MiB boundary. - */ -#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ - -/* * In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the * kernel need greater alignment than we require the segments to be padded to. */ @@ -107,9 +100,6 @@ static inline void free_screen_info(struct screen_info *si) { } -/* redeclare as 'hidden' so the compiler will generate relative references */ -extern struct screen_info screen_info __attribute__((__visibility__("hidden"))); - static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 6cc26a127819..97f6a63810ec 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -48,7 +48,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) int oldval = 0, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); - pagefault_disable(); + if (!access_ok(_uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -75,8 +76,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 4e531f57147d..6facd1308e7c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -34,7 +34,7 @@ static inline void __raw_writew(u16 val, volatile void __iomem *addr) } #define __raw_writel __raw_writel -static inline void __raw_writel(u32 val, volatile void __iomem *addr) +static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); } @@ -69,7 +69,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr) } #define __raw_readl __raw_readl -static inline u32 __raw_readl(const volatile void __iomem *addr) +static __always_inline u32 __raw_readl(const volatile void __iomem *addr) { u32 val; asm volatile(ALTERNATIVE("ldr %w0, [%1]", diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 688c63412cc2..f658dda12364 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -36,7 +36,7 @@ void kvm_inject_undef32(struct kvm_vcpu *vcpu); void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); -static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } @@ -127,7 +127,7 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) vcpu->arch.vsesr_el2 = vsesr; } -static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; } @@ -153,17 +153,17 @@ static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long *__vcpu_elr_el1(vcpu) = v; } -static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate; } -static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) { return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT); } -static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) return kvm_condition_valid32(vcpu); @@ -181,13 +181,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on * AArch32 with banked registers. */ -static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, +static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, +static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, unsigned long val) { if (reg_num != 31) @@ -264,12 +264,12 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) +static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } -static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); @@ -279,12 +279,12 @@ static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) return -1; } -static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.far_el2; } -static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) +static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) { return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8; } @@ -299,7 +299,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK; } -static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } @@ -319,17 +319,17 @@ static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF); } -static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) { return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } -static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ @@ -340,18 +340,18 @@ static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM); } -static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) +static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) { return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); } /* This one is not specific to Data Abort */ -static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL); } -static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); } @@ -361,17 +361,17 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; } -static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE; } -static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case FSC_SEA: @@ -390,7 +390,7 @@ static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) } } -static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); @@ -504,7 +504,7 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, return data; /* Leave LE untouched */ } -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) { if (vcpu_mode_is_32bit(vcpu)) kvm_skip_instr32(vcpu, is_wide_instr); @@ -519,7 +519,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ -static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) +static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d87aa609d2b6..57fd46acd058 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -626,38 +626,6 @@ static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} #endif -static inline void kvm_arm_vhe_guest_enter(void) -{ - local_daif_mask(); - - /* - * Having IRQs masked via PMR when entering the guest means the GIC - * will not signal the CPU of interrupts of lower priority, and the - * only way to get out will be via guest exceptions. - * Naturally, we want to avoid this. - * - * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a - * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. - */ - pmr_sync(); -} - -static inline void kvm_arm_vhe_guest_exit(void) -{ - /* - * local_daif_restore() takes care to properly restore PSTATE.DAIF - * and the GIC PMR if the host is using IRQ priorities. - */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - /* - * When we exit from the guest we change a number of CPU configuration - * parameters, such as traps. Make sure these changes take effect - * before running the host or additional guests. - */ - isb(); -} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index a3a6a2ba9a63..fe57f60f06a8 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,6 +47,13 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) +/* + * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the + * static inline can allow the compiler to out-of-line this. KVM always wants + * the macro version as its always inlined. + */ +#define __kvm_swab32(x) ___constant_swab32(x) + int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 53d846f1bfe7..785762860c63 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -93,7 +93,7 @@ void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_layout(void); -static inline unsigned long __kern_hyp_va(unsigned long v) +static __always_inline unsigned long __kern_hyp_va(unsigned long v) { asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" "ror %0, %0, #1\n" @@ -473,6 +473,7 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, extern void *__kvm_bp_vect_base; extern int __kvm_harden_el2_vector_slot; +/* This is only called on a VHE system */ static inline void *kvm_get_hyp_vector(void) { struct bp_hardening_data *data = arm64_get_bp_hardening_data(); diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index d429f7701c36..5d10051c3e62 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -6,7 +6,7 @@ #ifdef CONFIG_ARM64_LSE_ATOMICS -#define __LSE_PREAMBLE ".arch armv8-a+lse\n" +#define __LSE_PREAMBLE ".arch_extension lse\n" #include <linux/compiler_types.h> #include <linux/export.h> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a4f9ca5479b0..4d94676e5a8b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -213,7 +213,7 @@ static inline unsigned long kaslr_offset(void) ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ - u64 __addr = (__force u64)addr; \ + u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index e4d862420bb4..d79ce6df9e12 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -29,11 +29,9 @@ typedef struct { */ #define ASID(mm) ((mm)->context.id.counter & 0xffff) -extern bool arm64_use_ng_mappings; - static inline bool arm64_kernel_unmapped_at_el0(void) { - return arm64_use_ng_mappings; + return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); } typedef void (*bp_hardening_cb_t)(void); diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 6f87839f0249..1305e28225fc 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -23,11 +23,13 @@ #include <asm/pgtable-types.h> +extern bool arm64_use_ng_mappings; + #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0) -#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0) +#define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) +#define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index f0cec4160136..512174a8e789 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -63,7 +63,6 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ -#define TIF_NOHZ 7 #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ @@ -83,7 +82,6 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) -#define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -100,7 +98,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ - _TIF_NOHZ | _TIF_SYSCALL_EMU) + _TIF_SYSCALL_EMU) #define INIT_THREAD_INFO(tsk) \ { \ diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index a4d945db95a2..cbd70d78ef15 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -25,6 +25,9 @@ int pcibus_to_node(struct pci_bus *bus); /* Enable topology flag updates */ #define arch_update_cpu_topology topology_update_cpu_topology +/* Replace task scheduler's default thermal pressure retrieve API */ +#define arch_scale_thermal_pressure topology_get_thermal_pressure + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 1dd22da1c3a9..803039d504de 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -25,8 +25,8 @@ #define __NR_compat_gettimeofday 78 #define __NR_compat_sigreturn 119 #define __NR_compat_rt_sigreturn 173 -#define __NR_compat_clock_getres 247 #define __NR_compat_clock_gettime 263 +#define __NR_compat_clock_getres 264 #define __NR_compat_clock_gettime64 403 #define __NR_compat_clock_getres_time64 406 diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 0958ed6191aa..61fd26752adc 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -83,7 +83,7 @@ static inline bool is_kernel_in_hyp_mode(void) return read_sysreg(CurrentEL) == CurrentEL_EL2; } -static inline bool has_vhe(void) +static __always_inline bool has_vhe(void) { if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN)) return true; diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index 304d5b02ca67..1a03618df0df 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -10,81 +10,35 @@ #include <asm/assembler.h> -#define EFI_LOAD_ERROR 0x8000000000000001 - __INIT - /* - * We arrive here from the EFI boot manager with: - * - * * CPU in little-endian mode - * * MMU on with identity-mapped RAM - * * Icache and Dcache on - * - * We will most likely be running from some place other than where - * we want to be. The kernel image wants to be placed at TEXT_OFFSET - * from start of RAM. - */ -ENTRY(entry) - /* - * Create a stack frame to save FP/LR with extra space - * for image_addr variable passed to efi_entry(). - */ - stp x29, x30, [sp, #-32]! - mov x29, sp - - /* - * Call efi_entry to do the real work. - * x0 and x1 are already set up by firmware. Current runtime - * address of image is calculated and passed via *image_addr. - * - * unsigned long efi_entry(void *handle, - * efi_system_table_t *sys_table, - * unsigned long *image_addr) ; - */ - adr_l x8, _text - add x2, sp, 16 - str x8, [x2] - bl efi_entry - cmn x0, #1 - b.eq efi_load_fail - +SYM_CODE_START(efi_enter_kernel) /* * efi_entry() will have copied the kernel image if necessary and we - * return here with device tree address in x0 and the kernel entry - * point stored at *image_addr. Save those values in registers which - * are callee preserved. - */ - mov x20, x0 // DTB address - ldr x0, [sp, #16] // relocated _text address - ldr w21, =stext_offset - add x21, x0, x21 - - /* - * Calculate size of the kernel Image (same for original and copy). + * end up here with device tree address in x1 and the kernel entry + * point stored in x0. Save those values in registers which are + * callee preserved. */ - adr_l x1, _text - adr_l x2, _edata - sub x1, x2, x1 + ldr w2, =stext_offset + add x19, x0, x2 // relocated Image entrypoint + mov x20, x1 // DTB address /* - * Flush the copied Image to the PoC, and ensure it is not shadowed by + * Clean the copied Image to the PoC, and ensure it is not shadowed by * stale icache entries from before relocation. */ - bl __flush_dcache_area + ldr w1, =kernel_size + bl __clean_dcache_area_poc ic ialluis /* - * Ensure that the rest of this function (in the original Image) is - * visible when the caches are disabled. The I-cache can't have stale - * entries for the VA range of the current image, so no maintenance is - * necessary. + * Clean the remainder of this routine to the PoC + * so that we can safely disable the MMU and caches. */ - adr x0, entry - adr x1, entry_end - sub x1, x1, x0 - bl __flush_dcache_area - + adr x0, 0f + ldr w1, 3f + bl __clean_dcache_area_poc +0: /* Turn off Dcache and MMU */ mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 @@ -109,12 +63,6 @@ ENTRY(entry) mov x1, xzr mov x2, xzr mov x3, xzr - br x21 - -efi_load_fail: - mov x0, #EFI_LOAD_ERROR - ldp x29, x30, [sp], #32 - ret - -entry_end: -ENDPROC(entry) + br x19 +SYM_CODE_END(efi_enter_kernel) +3: .long . - 0b diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S index a7cfacce3e15..914999ccaf8a 100644 --- a/arch/arm64/kernel/efi-header.S +++ b/arch/arm64/kernel/efi-header.S @@ -27,7 +27,7 @@ optional_header: .long __initdata_begin - efi_header_end // SizeOfCode .long __pecoff_data_size // SizeOfInitializedData .long 0 // SizeOfUninitializedData - .long __efistub_entry - _head // AddressOfEntryPoint + .long __efistub_efi_entry - _head // AddressOfEntryPoint .long efi_header_end - _head // BaseOfCode extra_header_fields: @@ -36,8 +36,8 @@ extra_header_fields: .long PECOFF_FILE_ALIGNMENT // FileAlignment .short 0 // MajorOperatingSystemVersion .short 0 // MinorOperatingSystemVersion - .short 0 // MajorImageVersion - .short 0 // MinorImageVersion + .short LINUX_EFISTUB_MAJOR_VERSION // MajorImageVersion + .short LINUX_EFISTUB_MINOR_VERSION // MinorImageVersion .short 0 // MajorSubsystemVersion .short 0 // MinorSubsystemVersion .long 0 // Win32VersionValue diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 590963c9c609..5b73e92c99e3 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -166,14 +166,11 @@ int arch_hibernation_header_restore(void *addr) sleep_cpu = -EINVAL; return -EINVAL; } - if (!cpu_online(sleep_cpu)) { - pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); - ret = cpu_up(sleep_cpu); - if (ret) { - pr_err("Failed to bring hibernate-CPU up!\n"); - sleep_cpu = -EINVAL; - return ret; - } + + ret = bringup_hibernate_cpu(sleep_cpu); + if (ret) { + sleep_cpu = -EINVAL; + return ret; } resume_hdr = *hdr; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 25a2a9b479c2..7f06ad93fc95 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -12,7 +12,9 @@ #ifdef CONFIG_EFI -__efistub_stext_offset = stext - _text; +__efistub_kernel_size = _edata - _text; +__efistub_stext_offset = stext - _text; + /* * The EFI stub has its own symbol namespace prefixed by __efistub_, to @@ -33,7 +35,7 @@ __efistub_strnlen = __pi_strnlen; __efistub_strcmp = __pi_strcmp; __efistub_strncmp = __pi_strncmp; __efistub_strrchr = __pi_strrchr; -__efistub___flush_dcache_area = __pi___flush_dcache_area; +__efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc; #ifdef CONFIG_KASAN __efistub___memcpy = __pi_memcpy; @@ -45,6 +47,7 @@ __efistub__text = _text; __efistub__end = _end; __efistub__edata = _edata; __efistub_screen_info = screen_info; +__efistub__ctype = _ctype; #endif diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 00626057a384..3e5a6ad66cbe 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -141,11 +141,11 @@ void arch_cpu_idle_dead(void) * to execute e.g. a RAM-based pin loop is not sufficient. This allows the * kexec'd kernel to use any and all RAM as it sees fit, without having to * avoid any code or data used by any SW CPU pin loop. The CPU hotplug - * functionality embodied in disable_nonboot_cpus() to achieve this. + * functionality embodied in smpt_shutdown_nonboot_cpus() to achieve this. */ void machine_shutdown(void) { - disable_nonboot_cpus(); + smp_shutdown_nonboot_cpus(reboot_cpu); } /* diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d4ed9a19d8fe..5407bf5d98ac 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -958,11 +958,22 @@ void tick_broadcast(const struct cpumask *mask) } #endif +/* + * The number of CPUs online, not counting this CPU (which may not be + * fully online and so not counted in num_online_cpus()). + */ +static inline unsigned int num_other_online_cpus(void) +{ + unsigned int this_cpu_online = cpu_online(smp_processor_id()); + + return num_online_cpus() - this_cpu_online; +} + void smp_send_stop(void) { unsigned long timeout; - if (num_online_cpus() > 1) { + if (num_other_online_cpus()) { cpumask_t mask; cpumask_copy(&mask, cpu_online_mask); @@ -975,10 +986,10 @@ void smp_send_stop(void) /* Wait up to one second for other CPUs to stop */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && timeout--) + while (num_other_online_cpus() && timeout--) udelay(1); - if (num_online_cpus() > 1) + if (num_other_online_cpus()) pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(cpu_online_mask)); @@ -1001,7 +1012,11 @@ void crash_smp_send_stop(void) cpus_stopped = 1; - if (num_online_cpus() == 1) { + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) { sdei_mask_local_cpu(); return; } @@ -1009,7 +1024,7 @@ void crash_smp_send_stop(void) cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); pr_crit("SMP: stopping secondary CPUs\n"); smp_cross_call(&mask, IPI_CPU_CRASH_STOP); diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index dfe8dd172512..925086b46136 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -625,7 +625,7 @@ static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) } /* Switch to the guest for VHE systems running in EL2 */ -int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; @@ -678,7 +678,42 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } -NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); +NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); + +int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +{ + int ret; + + local_daif_mask(); + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. + */ + pmr_sync(); + + ret = __kvm_vcpu_run_vhe(vcpu); + + /* + * local_daif_restore() takes care to properly restore PSTATE.DAIF + * and the GIC PMR if the host is using IRQ priorities. + */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + /* + * When we exit from the guest we change a number of CPU configuration + * parameters, such as traps. Make sure these changes take effect + * before running the host or additional guests. + */ + isb(); + + return ret; +} /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 29ee1feba4eb..4f3a087e36d5 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -69,14 +69,14 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) u32 data = vcpu_get_reg(vcpu, rd); if (__is_be(vcpu)) { /* guest pre-swabbed data, undo this for writel() */ - data = swab32(data); + data = __kvm_swab32(data); } writel_relaxed(data, addr); } else { u32 data = readl_relaxed(addr); if (__is_be(vcpu)) { /* guest expects swabbed data */ - data = swab32(data); + data = __kvm_swab32(data); } vcpu_set_reg(vcpu, rd, data); } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 8ef73e89d514..d89bb22589f6 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -260,14 +260,26 @@ asmlinkage void post_ttbr_update_workaround(void) CONFIG_CAVIUM_ERRATUM_27456)); } -static int asids_init(void) +static int asids_update_limit(void) { - asid_bits = get_cpu_asid_bits(); + unsigned long num_available_asids = NUM_USER_ASIDS; + + if (arm64_kernel_unmapped_at_el0()) + num_available_asids /= 2; /* * Expect allocation after rollover to fail if we don't have at least * one more ASID than CPUs. ASID #0 is reserved for init_mm. */ - WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus()); + WARN_ON(num_available_asids - 1 <= num_possible_cpus()); + pr_info("ASID allocator initialised with %lu entries\n", + num_available_asids); + return 0; +} +arch_initcall(asids_update_limit); + +static int asids_init(void) +{ + asid_bits = get_cpu_asid_bits(); atomic64_set(&asid_generation, ASID_FIRST_VERSION); asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map), GFP_KERNEL); @@ -282,8 +294,6 @@ static int asids_init(void) */ if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) set_kpti_asid_bits(); - - pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); return 0; } early_initcall(asids_init); diff --git a/arch/c6x/platforms/timer64.c b/arch/c6x/platforms/timer64.c index d98d94303498..661f4c7c6ef6 100644 --- a/arch/c6x/platforms/timer64.c +++ b/arch/c6x/platforms/timer64.c @@ -165,13 +165,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction timer_iact = { - .name = "timer", - .flags = IRQF_TIMER, - .handler = timer_interrupt, - .dev_id = &t64_clockevent_device, -}; - void __init timer64_init(void) { struct clock_event_device *cd = &t64_clockevent_device; @@ -238,7 +231,9 @@ void __init timer64_init(void) cd->cpumask = cpumask_of(smp_processor_id()); clockevents_register_device(cd); - setup_irq(cd->irq, &timer_iact); + if (request_irq(cd->irq, timer_interrupt, IRQF_TIMER, "timer", + &t64_clockevent_device)) + pr_err("Failed to request irq %d (timer)\n", cd->irq); out: of_node_put(np); diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index da09c884cc30..047427f71d83 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -9,7 +9,6 @@ config CSKY select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2 select COMMON_CLK select CLKSRC_MMIO - select CLKSRC_OF select CSKY_MPINTC if CPU_CK860 select CSKY_MP_TIMER if CPU_CK860 select CSKY_APB_INTC @@ -37,6 +36,7 @@ config CSKY select GX6605S_TIMER if CPU_CK610 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_AUDITSYSCALL + select HAVE_COPY_THREAD_TLS select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -47,8 +47,8 @@ config CSKY select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS + select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES @@ -59,6 +59,11 @@ config CSKY select TIMER_OF select USB_ARCH_HAS_EHCI select USB_ARCH_HAS_OHCI + select GENERIC_PCI_IOMAP + select HAVE_PCI + select PCI_DOMAINS_GENERIC if PCI + select PCI_SYSCALL if PCI + select PCI_MSI if PCI config CPU_HAS_CACHEV2 bool @@ -75,7 +80,7 @@ config CPU_HAS_TLBI config CPU_HAS_LDSTEX bool help - For SMP, CPU needs "ldex&stex" instrcutions to atomic operations. + For SMP, CPU needs "ldex&stex" instructions for atomic operations. config CPU_NEED_TLBSYNC bool @@ -188,6 +193,40 @@ config CPU_PM_STOP bool "stop" endchoice +menuconfig HAVE_TCM + bool "Tightly-Coupled/Sram Memory" + select GENERIC_ALLOCATOR + help + The implementation are not only used by TCM (Tightly-Coupled Meory) + but also used by sram on SOC bus. It follow existed linux tcm + software interface, so that old tcm application codes could be + re-used directly. + +if HAVE_TCM +config ITCM_RAM_BASE + hex "ITCM ram base" + default 0xffffffff + +config ITCM_NR_PAGES + int "Page count of ITCM size: NR*4KB" + range 1 256 + default 32 + +config HAVE_DTCM + bool "DTCM Support" + +config DTCM_RAM_BASE + hex "DTCM ram base" + depends on HAVE_DTCM + default 0xffffffff + +config DTCM_NR_PAGES + int "Page count of DTCM size: NR*4KB" + depends on HAVE_DTCM + range 1 256 + default 32 +endif + config CPU_HAS_VDSP bool "CPU has VDSP coprocessor" depends on CPU_HAS_FPU && CPU_HAS_FPUV2 @@ -196,6 +235,10 @@ config CPU_HAS_FPU bool "CPU has FPU coprocessor" depends on CPU_CK807 || CPU_CK810 || CPU_CK860 +config CPU_HAS_ICACHE_INS + bool "CPU has Icache invalidate instructions" + depends on CPU_HAS_CACHEV2 + config CPU_HAS_TEE bool "CPU has Trusted Execution Environment" depends on CPU_CK810 @@ -235,4 +278,6 @@ config HOTPLUG_CPU Say N if you want to disable CPU hotplug. endmenu +source "arch/csky/Kconfig.platforms" + source "kernel/Kconfig.hz" diff --git a/arch/csky/Kconfig.platforms b/arch/csky/Kconfig.platforms new file mode 100644 index 000000000000..639e17f4eacb --- /dev/null +++ b/arch/csky/Kconfig.platforms @@ -0,0 +1,9 @@ +menu "Platform drivers selection" + +config ARCH_CSKY_DW_APB_ICTL + bool "Select dw-apb interrupt controller" + select DW_APB_ICTL + default y + help + This enables support for snps dw-apb-ictl +endmenu diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 79ef9e8c1afd..d3e04208d53c 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -48,9 +48,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, u #define flush_icache_page(vma, page) do {} while (0); #define flush_icache_range(start, end) cache_wbinv_range(start, end) - -#define flush_icache_user_range(vma,page,addr,len) \ - flush_dcache_page(page) +#define flush_icache_mm_range(mm, start, end) cache_wbinv_range(start, end) +#define flush_icache_deferred(mm) do {} while (0); #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ do { \ diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h index 7ab78bd0f3b1..f35a9f3315ee 100644 --- a/arch/csky/abiv1/inc/abi/entry.h +++ b/arch/csky/abiv1/inc/abi/entry.h @@ -16,14 +16,16 @@ #define LSAVE_A4 40 #define LSAVE_A5 44 +#define usp ss1 + .macro USPTOKSP - mtcr sp, ss1 + mtcr sp, usp mfcr sp, ss0 .endm .macro KSPTOUSP mtcr sp, ss0 - mfcr sp, ss1 + mfcr sp, usp .endm .macro SAVE_ALL epc_inc @@ -45,7 +47,13 @@ add lr, r13 stw lr, (sp, 8) + mov lr, sp + addi lr, 32 + addi lr, 32 + addi lr, 16 + bt 2f mfcr lr, ss1 +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -79,9 +87,10 @@ ldw a0, (sp, 12) mtcr a0, epsr btsti a0, 31 + bt 1f ldw a0, (sp, 16) mtcr a0, ss1 - +1: ldw a0, (sp, 24) ldw a1, (sp, 28) ldw a2, (sp, 32) @@ -102,9 +111,9 @@ addi sp, 32 addi sp, 8 - bt 1f + bt 2f KSPTOUSP -1: +2: rte .endm diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 5bb887b275e1..790f1ebfba44 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -6,46 +6,80 @@ #include <linux/mm.h> #include <asm/cache.h> -void flush_icache_page(struct vm_area_struct *vma, struct page *page) +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t *pte) { - unsigned long start; + unsigned long addr; + struct page *page; - start = (unsigned long) kmap_atomic(page); + page = pfn_to_page(pte_pfn(*pte)); + if (page == ZERO_PAGE(0)) + return; - cache_wbinv_range(start, start + PAGE_SIZE); + if (test_and_set_bit(PG_dcache_clean, &page->flags)) + return; - kunmap_atomic((void *)start); -} + addr = (unsigned long) kmap_atomic(page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len) -{ - unsigned long kaddr; + dcache_wb_range(addr, addr + PAGE_SIZE); - kaddr = (unsigned long) kmap_atomic(page) + (vaddr & ~PAGE_MASK); + if (vma->vm_flags & VM_EXEC) + icache_inv_range(addr, addr + PAGE_SIZE); + + kunmap_atomic((void *) addr); +} - cache_wbinv_range(kaddr, kaddr + len); +void flush_icache_deferred(struct mm_struct *mm) +{ + unsigned int cpu = smp_processor_id(); + cpumask_t *mask = &mm->context.icache_stale_mask; - kunmap_atomic((void *)kaddr); + if (cpumask_test_cpu(cpu, mask)) { + cpumask_clear_cpu(cpu, mask); + /* + * Ensure the remote hart's writes are visible to this hart. + * This pairs with a barrier in flush_icache_mm. + */ + smp_mb(); + local_icache_inv_all(NULL); + } } -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, - pte_t *pte) +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long addr, pfn; - struct page *page; + unsigned int cpu; + cpumask_t others, *mask; - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) - return; + preempt_disable(); - page = pfn_to_page(pfn); - if (page == ZERO_PAGE(0)) +#ifdef CONFIG_CPU_HAS_ICACHE_INS + if (mm == current->mm) { + icache_inv_range(start, end); + preempt_enable(); return; + } +#endif - addr = (unsigned long) kmap_atomic(page); + /* Mark every hart's icache as needing a flush for this MM. */ + mask = &mm->context.icache_stale_mask; + cpumask_setall(mask); - cache_wbinv_range(addr, addr + PAGE_SIZE); + /* Flush this hart's I$ now, and mark it as flushed. */ + cpu = smp_processor_id(); + cpumask_clear_cpu(cpu, mask); + local_icache_inv_all(NULL); - kunmap_atomic((void *) addr); + /* + * Flush the I$ of other harts concurrently executing, and mark them as + * flushed. + */ + cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu)); + + if (mm != current->active_mm || !cpumask_empty(&others)) { + on_each_cpu_mask(&others, local_icache_inv_all, NULL, 1); + cpumask_clear(mask); + } + + preempt_enable(); } diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index b8db5e0b2fe3..a565e00c3f70 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -13,24 +13,27 @@ #define flush_cache_all() do { } while (0) #define flush_cache_mm(mm) do { } while (0) #define flush_cache_dup_mm(mm) do { } while (0) +#define flush_cache_range(vma, start, end) do { } while (0) +#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_cache_range(vma, start, end) \ - do { \ - if (vma->vm_flags & VM_EXEC) \ - icache_inv_all(); \ - } while (0) +#define PG_dcache_clean PG_arch_1 + +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 +static inline void flush_dcache_page(struct page *page) +{ + if (test_bit(PG_dcache_clean, &page->flags)) + clear_bit(PG_dcache_clean, &page->flags); +} -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) +#define flush_icache_page(vma, page) do { } while (0) #define flush_icache_range(start, end) cache_wbinv_range(start, end) -void flush_icache_page(struct vm_area_struct *vma, struct page *page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len); +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end); +void flush_icache_deferred(struct mm_struct *mm); #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) @@ -38,7 +41,13 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ - cache_wbinv_range((unsigned long)dst, (unsigned long)dst + len); \ + if (vma->vm_flags & VM_EXEC) { \ + dcache_wb_range((unsigned long)dst, \ + (unsigned long)dst + len); \ + flush_icache_mm_range(current->mm, \ + (unsigned long)dst, \ + (unsigned long)dst + len); \ + } \ } while (0) #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h index 9897a16b45e5..94a7a58765df 100644 --- a/arch/csky/abiv2/inc/abi/entry.h +++ b/arch/csky/abiv2/inc/abi/entry.h @@ -31,7 +31,13 @@ mfcr lr, epsr stw lr, (sp, 12) + btsti lr, 31 + bf 1f + addi lr, sp, 152 + br 2f +1: mfcr lr, usp +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -64,8 +70,10 @@ mtcr a0, epc ldw a0, (sp, 12) mtcr a0, epsr + btsti a0, 31 ldw a0, (sp, 16) mtcr a0, usp + mtcr a0, ss0 #ifdef CONFIG_CPU_HAS_HILO ldw a0, (sp, 140) @@ -86,6 +94,9 @@ addi sp, 40 ldm r16-r30, (sp) addi sp, 72 + bf 1f + mfcr sp, ss0 +1: rte .endm diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig index 7ef42895dfb0..af722e4dfb47 100644 --- a/arch/csky/configs/defconfig +++ b/arch/csky/configs/defconfig @@ -10,9 +10,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_CPU_CK807=y -CONFIG_CPU_HAS_FPU=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -27,10 +24,7 @@ CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y -CONFIG_TTY_PRINTK=y # CONFIG_VGA_CONSOLE is not set -CONFIG_CSKY_MPTIMER=y -CONFIG_GX6605S_TIMER=y CONFIG_PM_DEVFREQ=y CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y CONFIG_DEVFREQ_GOV_PERFORMANCE=y @@ -56,6 +50,4 @@ CONFIG_CRAMFS=y CONFIG_ROMFS_FS=y CONFIG_NFS_FS=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index bc15a26c782f..4130e3eaa766 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -28,7 +28,6 @@ generic-y += local64.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h generic-y += module.h -generic-y += pci.h generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h diff --git a/arch/csky/include/asm/cache.h b/arch/csky/include/asm/cache.h index 1d5fc2f78fd7..4b5c09bf1d25 100644 --- a/arch/csky/include/asm/cache.h +++ b/arch/csky/include/asm/cache.h @@ -16,6 +16,7 @@ void dcache_wb_line(unsigned long start); void icache_inv_range(unsigned long start, unsigned long end); void icache_inv_all(void); +void local_icache_inv_all(void *priv); void dcache_wb_range(unsigned long start, unsigned long end); void dcache_wbinv_all(void); diff --git a/arch/csky/include/asm/cacheflush.h b/arch/csky/include/asm/cacheflush.h index a96da67261ae..f0b8f25429a2 100644 --- a/arch/csky/include/asm/cacheflush.h +++ b/arch/csky/include/asm/cacheflush.h @@ -4,6 +4,7 @@ #ifndef __ASM_CSKY_CACHEFLUSH_H #define __ASM_CSKY_CACHEFLUSH_H +#include <linux/mm.h> #include <abi/cacheflush.h> #endif /* __ASM_CSKY_CACHEFLUSH_H */ diff --git a/arch/csky/include/asm/fixmap.h b/arch/csky/include/asm/fixmap.h index 380ff0a307df..81f9477d5330 100644 --- a/arch/csky/include/asm/fixmap.h +++ b/arch/csky/include/asm/fixmap.h @@ -5,12 +5,16 @@ #define __ASM_CSKY_FIXMAP_H #include <asm/page.h> +#include <asm/memory.h> #ifdef CONFIG_HIGHMEM #include <linux/threads.h> #include <asm/kmap_types.h> #endif enum fixed_addresses { +#ifdef CONFIG_HAVE_TCM + FIX_TCM = TCM_NR_PAGES, +#endif #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1, @@ -18,10 +22,13 @@ enum fixed_addresses { __end_of_fixed_addresses }; -#define FIXADDR_TOP 0xffffc000 #define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) #include <asm-generic/fixmap.h> +extern void fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base); +extern void __init fixaddr_init(void); + #endif /* __ASM_CSKY_FIXMAP_H */ diff --git a/arch/csky/include/asm/memory.h b/arch/csky/include/asm/memory.h new file mode 100644 index 000000000000..a65c6759f537 --- /dev/null +++ b/arch/csky/include/asm/memory.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_MEMORY_H +#define __ASM_CSKY_MEMORY_H + +#include <linux/compiler.h> +#include <linux/const.h> +#include <linux/types.h> +#include <linux/sizes.h> + +#define FIXADDR_TOP _AC(0xffffc000, UL) +#define PKMAP_BASE _AC(0xff800000, UL) +#define VMALLOC_START _AC(0xc0008000, UL) +#define VMALLOC_END (PKMAP_BASE - (PAGE_SIZE * 2)) + +#ifdef CONFIG_HAVE_TCM +#ifdef CONFIG_HAVE_DTCM +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES + CONFIG_DTCM_NR_PAGES) +#else +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES) +#endif +#define FIXADDR_TCM _AC(FIXADDR_TOP - (TCM_NR_PAGES * PAGE_SIZE), UL) +#endif + +#endif diff --git a/arch/csky/include/asm/mmu.h b/arch/csky/include/asm/mmu.h index b382a14ea4ec..26fbb1d15df0 100644 --- a/arch/csky/include/asm/mmu.h +++ b/arch/csky/include/asm/mmu.h @@ -7,6 +7,7 @@ typedef struct { atomic64_t asid; void *vdso; + cpumask_t icache_stale_mask; } mm_context_t; #endif /* __ASM_CSKY_MMU_H */ diff --git a/arch/csky/include/asm/mmu_context.h b/arch/csky/include/asm/mmu_context.h index 0285b0ad18b6..abdf1f1cb6ec 100644 --- a/arch/csky/include/asm/mmu_context.h +++ b/arch/csky/include/asm/mmu_context.h @@ -43,5 +43,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, TLBMISS_HANDLER_SETUP_PGD(next->pgd); write_mmu_entryhi(next->context.asid.counter); + + flush_icache_deferred(next); } #endif /* __ASM_CSKY_MMU_CONTEXT_H */ diff --git a/arch/csky/include/asm/pci.h b/arch/csky/include/asm/pci.h new file mode 100644 index 000000000000..ebc765b1f78b --- /dev/null +++ b/arch/csky/include/asm/pci.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_CSKY_PCI_H +#define __ASM_CSKY_PCI_H + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> + +#include <asm/io.h> + +#define PCIBIOS_MIN_IO 0 +#define PCIBIOS_MIN_MEM 0 + +/* C-SKY shim does not initialize PCI bus */ +#define pcibios_assign_all_busses() 1 + +extern int isa_dma_bridge_buggy; + +#ifdef CONFIG_PCI +static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) +{ + /* no legacy IRQ on csky */ + return -ENODEV; +} + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + /* always show the domain in /proc */ + return 1; +} +#endif /* CONFIG_PCI */ + +#endif /* __ASM_CSKY_PCI_H */ diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index 4b2a41e15f2e..9b7764cb7645 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -5,6 +5,7 @@ #define __ASM_CSKY_PGTABLE_H #include <asm/fixmap.h> +#include <asm/memory.h> #include <asm/addrspace.h> #include <abi/pgtable-bits.h> #include <asm-generic/pgtable-nopmd.h> @@ -16,11 +17,6 @@ #define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE) #define FIRST_USER_ADDRESS 0UL -#define PKMAP_BASE (0xff800000) - -#define VMALLOC_START (0xc0008000) -#define VMALLOC_END (PKMAP_BASE - 2*PAGE_SIZE) - /* * C-SKY is two-level paging structure: */ diff --git a/arch/csky/include/asm/stackprotector.h b/arch/csky/include/asm/stackprotector.h new file mode 100644 index 000000000000..d7cd4e51edd9 --- /dev/null +++ b/arch/csky/include/asm/stackprotector.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H 1 + +#include <linux/random.h> +#include <linux/version.h> + +extern unsigned long __stack_chk_guard; + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary; + + /* Try to get a semi random initial value. */ + get_random_bytes(&canary, sizeof(canary)); + canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; + + current->stack_canary = canary; + __stack_chk_guard = current->stack_canary; +} + +#endif /* __ASM_SH_STACKPROTECTOR_H */ diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h new file mode 100644 index 000000000000..2b135cefb73f --- /dev/null +++ b/arch/csky/include/asm/tcm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_TCM_H +#define __ASM_CSKY_TCM_H + +#ifndef CONFIG_HAVE_TCM +#error "You should not be including tcm.h unless you have a TCM!" +#endif + +#include <linux/compiler.h> + +/* Tag variables with this */ +#define __tcmdata __section(.tcm.data) +/* Tag constants with this */ +#define __tcmconst __section(.tcm.rodata) +/* Tag functions inside TCM called from outside TCM with this */ +#define __tcmfunc __section(.tcm.text) noinline +/* Tag function inside TCM called from inside TCM with this */ +#define __tcmlocalfunc __section(.tcm.text) + +void *tcm_alloc(size_t len); +void tcm_free(void *addr, size_t len); + +#endif diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h index eaa1c3403a42..abefa125b93c 100644 --- a/arch/csky/include/asm/uaccess.h +++ b/arch/csky/include/asm/uaccess.h @@ -11,7 +11,6 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/sched.h> -#include <linux/mm.h> #include <linux/string.h> #include <linux/version.h> #include <asm/segment.h> diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index 211c983c7282..ba4018929733 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -1,7 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #include <asm-generic/unistd.h> diff --git a/arch/csky/kernel/atomic.S b/arch/csky/kernel/atomic.S index 5b84f11485ae..3821ef9b7567 100644 --- a/arch/csky/kernel/atomic.S +++ b/arch/csky/kernel/atomic.S @@ -17,10 +17,12 @@ ENTRY(csky_cmpxchg) mfcr a3, epc addi a3, TRAP0_SIZE - subi sp, 8 + subi sp, 16 stw a3, (sp, 0) mfcr a3, epsr stw a3, (sp, 4) + mfcr a3, usp + stw a3, (sp, 8) psrset ee #ifdef CONFIG_CPU_HAS_LDSTEX @@ -47,7 +49,9 @@ ENTRY(csky_cmpxchg) mtcr a3, epc ldw a3, (sp, 4) mtcr a3, epsr - addi sp, 8 + ldw a3, (sp, 8) + mtcr a3, usp + addi sp, 16 KSPTOUSP rte END(csky_cmpxchg) diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f320d9248a22..f7b231ca269a 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -16,6 +16,12 @@ struct cpuinfo_csky cpu_data[NR_CPUS]; +#ifdef CONFIG_STACKPROTECTOR +#include <linux/stackprotector.h> +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); @@ -34,10 +40,11 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sw->r15; } -int copy_thread(unsigned long clone_flags, +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, unsigned long kthread_arg, - struct task_struct *p) + struct task_struct *p, + unsigned long tls) { struct switch_stack *childstack; struct pt_regs *childregs = task_pt_regs(p); @@ -64,7 +71,7 @@ int copy_thread(unsigned long clone_flags, childregs->usp = usp; if (clone_flags & CLONE_SETTLS) task_thread_info(p)->tp_value = childregs->tls - = childregs->regs[0]; + = tls; childregs->a0 = 0; childstack->r15 = (unsigned long) ret_from_fork; diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index 52eaf31ba27f..3821e55742f4 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -47,9 +47,6 @@ static void __init csky_memblock_init(void) signed long size; memblock_reserve(__pa(_stext), _end - _stext); -#ifdef CONFIG_BLK_DEV_INITRD - memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); -#endif early_init_fdt_reserve_self(); early_init_fdt_scan_reserved_mem(); @@ -133,6 +130,8 @@ void __init setup_arch(char **cmdline_p) sparse_init(); + fixaddr_init(); + #ifdef CONFIG_HIGHMEM kmap_init(); #endif diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b753d382e4ce..0bb0954d5570 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -120,7 +120,7 @@ void __init setup_smp_ipi(void) int rc; if (ipi_irq == 0) - panic("%s IRQ mapping failed\n", __func__); + return; rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt", &ipi_dummy_dev); diff --git a/arch/csky/kernel/time.c b/arch/csky/kernel/time.c index b5fc9447d93f..52379d866fe4 100644 --- a/arch/csky/kernel/time.c +++ b/arch/csky/kernel/time.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. -#include <linux/clk-provider.h> #include <linux/clocksource.h> +#include <linux/of_clk.h> void __init time_init(void) { diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S index 2ff37beaf2bf..f05b413df328 100644 --- a/arch/csky/kernel/vmlinux.lds.S +++ b/arch/csky/kernel/vmlinux.lds.S @@ -2,6 +2,7 @@ #include <asm/vmlinux.lds.h> #include <asm/page.h> +#include <asm/memory.h> OUTPUT_ARCH(csky) ENTRY(_start) @@ -53,6 +54,54 @@ SECTIONS RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) _edata = .; +#ifdef CONFIG_HAVE_TCM + .tcm_start : { + . = ALIGN(PAGE_SIZE); + __tcm_start = .; + } + + .text_data_tcm FIXADDR_TCM : AT(__tcm_start) + { + . = ALIGN(4); + __stcm_text_data = .; + *(.tcm.text) + *(.tcm.rodata) +#ifndef CONFIG_HAVE_DTCM + *(.tcm.data) +#endif + . = ALIGN(4); + __etcm_text_data = .; + } + + . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_data_tcm); + +#ifdef CONFIG_HAVE_DTCM + #define ITCM_SIZE CONFIG_ITCM_NR_PAGES * PAGE_SIZE + + .dtcm_start : { + __dtcm_start = .; + } + + .data_tcm FIXADDR_TCM + ITCM_SIZE : AT(__dtcm_start) + { + . = ALIGN(4); + __stcm_data = .; + *(.tcm.data) + . = ALIGN(4); + __etcm_data = .; + } + + . = ADDR(.dtcm_start) + SIZEOF(.data_tcm); + + .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_tcm)) { +#else + .tcm_end : AT(ADDR(.tcm_start) + SIZEOF(.text_data_tcm)) { +#endif + . = ALIGN(PAGE_SIZE); + __tcm_end = .; + } +#endif + EXCEPTION_TABLE(L1_CACHE_BYTES) BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES) VBR_BASE diff --git a/arch/csky/mm/Makefile b/arch/csky/mm/Makefile index c94ef6481098..6e7696e55f71 100644 --- a/arch/csky/mm/Makefile +++ b/arch/csky/mm/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only ifeq ($(CONFIG_CPU_HAS_CACHEV2),y) obj-y += cachev2.o +CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE) else obj-y += cachev1.o +CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE) endif obj-y += dma-mapping.o @@ -14,3 +16,4 @@ obj-y += syscache.o obj-y += tlb.o obj-y += asid.o obj-y += context.o +obj-$(CONFIG_HAVE_TCM) += tcm.o diff --git a/arch/csky/mm/cachev1.c b/arch/csky/mm/cachev1.c index 494ec912abff..5a5a9804a0e3 100644 --- a/arch/csky/mm/cachev1.c +++ b/arch/csky/mm/cachev1.c @@ -94,6 +94,11 @@ void icache_inv_all(void) cache_op_all(INS_CACHE|CACHE_INV, 0); } +void local_icache_inv_all(void *priv) +{ + cache_op_all(INS_CACHE|CACHE_INV, 0); +} + void dcache_wb_range(unsigned long start, unsigned long end) { cache_op_range(start, end, DATA_CACHE|CACHE_CLR, 0); diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c index b61be6518e21..bc419f8039d3 100644 --- a/arch/csky/mm/cachev2.c +++ b/arch/csky/mm/cachev2.c @@ -3,15 +3,25 @@ #include <linux/spinlock.h> #include <linux/smp.h> +#include <linux/mm.h> #include <asm/cache.h> #include <asm/barrier.h> -inline void dcache_wb_line(unsigned long start) +#define INS_CACHE (1 << 0) +#define CACHE_INV (1 << 4) + +void local_icache_inv_all(void *priv) { - asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); + mtcr("cr17", INS_CACHE|CACHE_INV); sync_is(); } +void icache_inv_all(void) +{ + on_each_cpu(local_icache_inv_all, NULL, 1); +} + +#ifdef CONFIG_CPU_HAS_ICACHE_INS void icache_inv_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); @@ -20,43 +30,32 @@ void icache_inv_range(unsigned long start, unsigned long end) asm volatile("icache.iva %0\n"::"r"(i):"memory"); sync_is(); } - -void icache_inv_all(void) +#else +void icache_inv_range(unsigned long start, unsigned long end) { - asm volatile("icache.ialls\n":::"memory"); - sync_is(); + icache_inv_all(); } +#endif -void dcache_wb_range(unsigned long start, unsigned long end) +inline void dcache_wb_line(unsigned long start) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); sync_is(); } -void dcache_inv_range(unsigned long start, unsigned long end) +void dcache_wb_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.civa %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); sync_is(); } void cache_wbinv_range(unsigned long start, unsigned long end) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); - sync_is(); - - i = start & ~(L1_CACHE_BYTES - 1); - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("icache.iva %0\n"::"r"(i):"memory"); - sync_is(); + dcache_wb_range(start, end); + icache_inv_range(start, end); } EXPORT_SYMBOL(cache_wbinv_range); diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index 3317b774f6dc..813129145f3d 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -117,85 +117,29 @@ struct page *kmap_atomic_to_page(void *ptr) return pte_page(*pte); } -static void __init fixrange_init(unsigned long start, unsigned long end, - pgd_t *pgd_base) +static void __init kmap_pages_init(void) { -#ifdef CONFIG_HIGHMEM - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int i, j, k; unsigned long vaddr; - - vaddr = start; - i = __pgd_offset(vaddr); - j = __pud_offset(vaddr); - k = __pmd_offset(vaddr); - pgd = pgd_base + i; - - for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { - pud = (pud_t *)pgd; - for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { - pmd = (pmd_t *)pud; - for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { - if (pmd_none(*pmd)) { - pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate %lu bytes align=%lx\n", - __func__, PAGE_SIZE, - PAGE_SIZE); - - set_pmd(pmd, __pmd(__pa(pte))); - BUG_ON(pte != pte_offset_kernel(pmd, 0)); - } - vaddr += PMD_SIZE; - } - k = 0; - } - j = 0; - } -#endif -} - -void __init fixaddr_kmap_pages_init(void) -{ - unsigned long vaddr; - pgd_t *pgd_base; -#ifdef CONFIG_HIGHMEM pgd_t *pgd; pmd_t *pmd; pud_t *pud; pte_t *pte; -#endif - pgd_base = swapper_pg_dir; - - /* - * Fixed mappings: - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, 0, pgd_base); - -#ifdef CONFIG_HIGHMEM - /* - * Permanent kmaps: - */ + vaddr = PKMAP_BASE; - fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir); pgd = swapper_pg_dir + __pgd_offset(vaddr); pud = (pud_t *)pgd; pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; -#endif } void __init kmap_init(void) { unsigned long vaddr; - fixaddr_kmap_pages_init(); + kmap_pages_init(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index d4c2292ea46b..cb64d8647a78 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -19,6 +19,7 @@ #include <linux/swap.h> #include <linux/proc_fs.h> #include <linux/pfn.h> +#include <linux/initrd.h> #include <asm/setup.h> #include <asm/cachectl.h> @@ -31,10 +32,50 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pte_table); unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); +#ifdef CONFIG_BLK_DEV_INITRD +static void __init setup_initrd(void) +{ + unsigned long size; + + if (initrd_start >= initrd_end) { + pr_err("initrd not found or empty"); + goto disable; + } + + if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { + pr_err("initrd extends beyond end of memory"); + goto disable; + } + + size = initrd_end - initrd_start; + + if (memblock_is_region_reserved(__pa(initrd_start), size)) { + pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region", + __pa(initrd_start), size); + goto disable; + } + + memblock_reserve(__pa(initrd_start), size); + + pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), size); + + initrd_below_start_ok = 1; + + return; + +disable: + initrd_start = initrd_end = 0; + + pr_err(" - disabling initrd\n"); +} +#endif + void __init mem_init(void) { #ifdef CONFIG_HIGHMEM @@ -46,6 +87,10 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); +#ifdef CONFIG_BLK_DEV_INITRD + setup_initrd(); +#endif + memblock_free_all(); #ifdef CONFIG_HIGHMEM @@ -101,3 +146,50 @@ void __init pre_mmu_init(void) /* Setup page mask to 4k */ write_mmu_pagemask(0); } + +void __init fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, j, k; + unsigned long vaddr; + + vaddr = start; + i = __pgd_offset(vaddr); + j = __pud_offset(vaddr); + k = __pmd_offset(vaddr); + pgd = pgd_base + i; + + for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { + pud = (pud_t *)pgd; + for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { + pmd = (pmd_t *)pud; + for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { + if (pmd_none(*pmd)) { + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); + if (!pte) + panic("%s: Failed to allocate %lu bytes align=%lx\n", + __func__, PAGE_SIZE, + PAGE_SIZE); + + set_pmd(pmd, __pmd(__pa(pte))); + BUG_ON(pte != pte_offset_kernel(pmd, 0)); + } + vaddr += PMD_SIZE; + } + k = 0; + } + j = 0; + } +} + +void __init fixaddr_init(void) +{ + unsigned long vaddr; + + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; + fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir); +} diff --git a/arch/csky/mm/syscache.c b/arch/csky/mm/syscache.c index c4645e4e97f4..ffade2f9a4c8 100644 --- a/arch/csky/mm/syscache.c +++ b/arch/csky/mm/syscache.c @@ -3,7 +3,7 @@ #include <linux/syscalls.h> #include <asm/page.h> -#include <asm/cache.h> +#include <asm/cacheflush.h> #include <asm/cachectl.h> SYSCALL_DEFINE3(cacheflush, @@ -13,17 +13,14 @@ SYSCALL_DEFINE3(cacheflush, { switch (cache) { case ICACHE: - icache_inv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; + case BCACHE: + flush_icache_mm_range(current->mm, + (unsigned long)addr, + (unsigned long)addr + bytes); case DCACHE: dcache_wb_range((unsigned long)addr, (unsigned long)addr + bytes); break; - case BCACHE: - cache_wbinv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; default: return -EINVAL; } diff --git a/arch/csky/mm/tcm.c b/arch/csky/mm/tcm.c new file mode 100644 index 000000000000..ddeb36328819 --- /dev/null +++ b/arch/csky/mm/tcm.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/highmem.h> +#include <linux/genalloc.h> +#include <asm/tlbflush.h> +#include <asm/fixmap.h> + +#if (CONFIG_ITCM_RAM_BASE == 0xffffffff) +#error "You should define ITCM_RAM_BASE" +#endif + +#ifdef CONFIG_HAVE_DTCM +#if (CONFIG_DTCM_RAM_BASE == 0xffffffff) +#error "You should define DTCM_RAM_BASE" +#endif + +#if (CONFIG_DTCM_RAM_BASE == CONFIG_ITCM_RAM_BASE) +#error "You should define correct DTCM_RAM_BASE" +#endif +#endif + +extern char __tcm_start, __tcm_end, __dtcm_start; + +static struct gen_pool *tcm_pool; + +static void __init tcm_mapping_init(void) +{ + pte_t *tcm_pte; + unsigned long vaddr, paddr; + int i; + + paddr = CONFIG_ITCM_RAM_BASE; + + if (pfn_valid(PFN_DOWN(CONFIG_ITCM_RAM_BASE))) + goto panic; + +#ifndef CONFIG_HAVE_DTCM + for (i = 0; i < TCM_NR_PAGES; i++) { +#else + for (i = 0; i < CONFIG_ITCM_NR_PAGES; i++) { +#endif + vaddr = __fix_to_virt(FIX_TCM - i); + + tcm_pte = + pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } + +#ifdef CONFIG_HAVE_DTCM + if (pfn_valid(PFN_DOWN(CONFIG_DTCM_RAM_BASE))) + goto panic; + + paddr = CONFIG_DTCM_RAM_BASE; + + for (i = 0; i < CONFIG_DTCM_NR_PAGES; i++) { + vaddr = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES - i); + + tcm_pte = + pte_offset_kernel((pmd_t *) pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } +#endif + +#ifndef CONFIG_HAVE_DTCM + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__tcm_end - &__tcm_start); + + pr_info("%s: mapping tcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __tcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__tcm_end - &__tcm_start); +#else + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__dtcm_start - &__tcm_start); + + pr_info("%s: mapping itcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __itcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__dtcm_start - &__tcm_start); + + memcpy((void *)__fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + &__dtcm_start, &__tcm_end - &__dtcm_start); + + pr_info("%s: mapping dtcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + CONFIG_DTCM_RAM_BASE); + + pr_info("%s: __dtcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__dtcm_start, &__tcm_end - &__dtcm_start); + +#endif + return; +panic: + panic("TCM init error"); +} + +void *tcm_alloc(size_t len) +{ + unsigned long vaddr; + + if (!tcm_pool) + return NULL; + + vaddr = gen_pool_alloc(tcm_pool, len); + if (!vaddr) + return NULL; + + return (void *) vaddr; +} +EXPORT_SYMBOL(tcm_alloc); + +void tcm_free(void *addr, size_t len) +{ + gen_pool_free(tcm_pool, (unsigned long) addr, len); +} +EXPORT_SYMBOL(tcm_free); + +static int __init tcm_setup_pool(void) +{ +#ifndef CONFIG_HAVE_DTCM + u32 pool_size = (u32) (TCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__tcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM) + + (u32) (&__tcm_end - &__tcm_start); +#else + u32 pool_size = (u32) (CONFIG_DTCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__dtcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES) + + (u32) (&__tcm_end - &__dtcm_start); +#endif + int ret; + + tcm_pool = gen_pool_create(2, -1); + + ret = gen_pool_add(tcm_pool, tcm_pool_start, pool_size, -1); + if (ret) { + pr_err("%s: gen_pool add failed!\n", __func__); + return ret; + } + + pr_info("%s: Added %d bytes @ 0x%08x to memory pool\n", + __func__, pool_size, tcm_pool_start); + + return 0; +} + +static int __init tcm_init(void) +{ + tcm_mapping_init(); + + tcm_setup_pool(); + + return 0; +} +arch_initcall(tcm_init); diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h index 0191f7c7193e..6b9c554aee78 100644 --- a/arch/hexagon/include/asm/futex.h +++ b/arch/hexagon/include/asm/futex.h @@ -36,7 +36,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -62,8 +63,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h index 00cb38faad0c..c1019a736ff1 100644 --- a/arch/hexagon/include/asm/uaccess.h +++ b/arch/hexagon/include/asm/uaccess.h @@ -10,7 +10,6 @@ /* * User space memory access functions */ -#include <linux/mm.h> #include <asm/sections.h> /* diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index 0bbbe652a513..619c56420aa0 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -114,12 +114,6 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg) local_irq_restore(flags); } -static struct irqaction ipi_intdesc = { - .handler = handle_ipi, - .flags = IRQF_TRIGGER_RISING, - .name = "ipi_handler" -}; - void __init smp_prepare_boot_cpu(void) { } @@ -132,8 +126,8 @@ void __init smp_prepare_boot_cpu(void) void start_secondary(void) { - unsigned int cpu; unsigned long thread_ptr; + unsigned int cpu, irq; /* Calculate thread_info pointer from stack pointer */ __asm__ __volatile__( @@ -155,7 +149,10 @@ void start_secondary(void) cpu = smp_processor_id(); - setup_irq(BASE_IPI_IRQ + cpu, &ipi_intdesc); + irq = BASE_IPI_IRQ + cpu; + if (request_irq(irq, handle_ipi, IRQF_TRIGGER_RISING, "ipi_handler", + NULL)) + pr_err("Failed to request irq %u (ipi_handler)\n", irq); /* Register the clock_event dummy */ setup_percpu_clockdev(); @@ -201,7 +198,7 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_cpus(unsigned int max_cpus) { - int i; + int i, irq = BASE_IPI_IRQ; /* * should eventually have some sort of machine @@ -213,8 +210,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus) set_cpu_present(i, true); /* Also need to register the interrupts for IPI */ - if (max_cpus > 1) - setup_irq(BASE_IPI_IRQ, &ipi_intdesc); + if (max_cpus > 1) { + if (request_irq(irq, handle_ipi, IRQF_TRIGGER_RISING, + "ipi_handler", NULL)) + pr_err("Failed to request irq %d (ipi_handler)\n", irq); + } } void smp_send_reschedule(int cpu) diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c index f99e9257bed4..feffe527ac92 100644 --- a/arch/hexagon/kernel/time.c +++ b/arch/hexagon/kernel/time.c @@ -143,13 +143,6 @@ static irqreturn_t timer_interrupt(int irq, void *devid) return IRQ_HANDLED; } -/* This should also be pulled from devtree */ -static struct irqaction rtos_timer_intdesc = { - .handler = timer_interrupt, - .flags = IRQF_TIMER | IRQF_TRIGGER_RISING, - .name = "rtos_timer" -}; - /* * time_init_deferred - called by start_kernel to set up timer/clock source * @@ -163,6 +156,7 @@ void __init time_init_deferred(void) { struct resource *resource = NULL; struct clock_event_device *ce_dev = &hexagon_clockevent_dev; + unsigned long flag = IRQF_TIMER | IRQF_TRIGGER_RISING; ce_dev->cpumask = cpu_all_mask; @@ -195,7 +189,8 @@ void __init time_init_deferred(void) #endif clockevents_register_device(ce_dev); - setup_irq(ce_dev->irq, &rtos_timer_intdesc); + if (request_irq(ce_dev->irq, timer_interrupt, flag, "rtos_timer", NULL)) + pr_err("Failed to register rtos_timer interrupt\n"); } void __init time_init(void) diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index 2e106d462196..1db26b432d8c 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -50,7 +50,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -74,8 +75,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 89782ad3fb88..5c7e79eccaee 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -35,7 +35,6 @@ #include <linux/compiler.h> #include <linux/page-flags.h> -#include <linux/mm.h> #include <asm/intrinsics.h> #include <asm/pgtable.h> diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 0a34dcc435c6..f69f3fe0532e 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -45,11 +45,21 @@ #define EFI_DEBUG 0 +#define ESI_TABLE_GUID \ + EFI_GUID(0x43EA58DC, 0xCF28, 0x4b06, 0xB3, \ + 0x91, 0xB7, 0x50, 0x59, 0x34, 0x2B, 0xD4) + +static unsigned long mps_phys = EFI_INVALID_TABLE_ADDR; static __initdata unsigned long palo_phys; +unsigned long __initdata esi_phys = EFI_INVALID_TABLE_ADDR; +unsigned long hcdp_phys = EFI_INVALID_TABLE_ADDR; unsigned long sal_systab_phys = EFI_INVALID_TABLE_ADDR; -static __initdata efi_config_table_type_t arch_tables[] = { +static const efi_config_table_type_t arch_tables[] __initconst = { + {ESI_TABLE_GUID, "ESI", &esi_phys}, + {HCDP_TABLE_GUID, "HCDP", &hcdp_phys}, + {MPS_TABLE_GUID, "MPS", &mps_phys}, {PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys}, {SAL_SYSTEM_TABLE_GUID, "SALsystab", &sal_systab_phys}, {NULL_GUID, NULL, 0}, @@ -474,11 +484,10 @@ efi_map_pal_code (void) void __init efi_init (void) { + const efi_system_table_t *efi_systab; void *efi_map_start, *efi_map_end; - efi_char16_t *c16; u64 efi_desc_size; - char *cp, vendor[100] = "unknown"; - int i; + char *cp; set_bit(EFI_BOOT, &efi.flags); set_bit(EFI_64BIT, &efi.flags); @@ -508,42 +517,29 @@ efi_init (void) printk(KERN_INFO "Ignoring memory above %lluMB\n", max_addr >> 20); - efi.systab = __va(ia64_boot_param->efi_systab); + efi_systab = __va(ia64_boot_param->efi_systab); /* * Verify the EFI Table */ - if (efi.systab == NULL) + if (efi_systab == NULL) panic("Whoa! Can't find EFI system table.\n"); - if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + if (efi_systab_check_header(&efi_systab->hdr, 1)) panic("Whoa! EFI system table signature incorrect\n"); - if ((efi.systab->hdr.revision >> 16) == 0) - printk(KERN_WARNING "Warning: EFI system table version " - "%d.%02d, expected 1.00 or greater\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff); - - /* Show what we know for posterity */ - c16 = __va(efi.systab->fw_vendor); - if (c16) { - for (i = 0;i < (int) sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; - vendor[i] = '\0'; - } - printk(KERN_INFO "EFI v%u.%.02u by %s:", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff, vendor); + efi_systab_report_header(&efi_systab->hdr, efi_systab->fw_vendor); palo_phys = EFI_INVALID_TABLE_ADDR; - if (efi_config_init(arch_tables) != 0) + if (efi_config_parse_tables(__va(efi_systab->tables), + efi_systab->nr_tables, + arch_tables) != 0) return; if (palo_phys != EFI_INVALID_TABLE_ADDR) handle_palo(palo_phys); - runtime = __va(efi.systab->runtime); + runtime = __va(efi_systab->runtime); efi.get_time = phys_get_time; efi.set_time = phys_set_time; efi.get_wakeup_time = phys_get_wakeup_time; @@ -1351,3 +1347,12 @@ vmcore_find_descriptor_size (unsigned long address) return ret; } #endif + +char *efi_systab_show_arch(char *str) +{ + if (mps_phys != EFI_INVALID_TABLE_ADDR) + str += sprintf(str, "MPS=0x%lx\n", mps_phys); + if (hcdp_phys != EFI_INVALID_TABLE_ADDR) + str += sprintf(str, "HCDP=0x%lx\n", hcdp_phys); + return str; +} diff --git a/arch/ia64/kernel/esi.c b/arch/ia64/kernel/esi.c index cb514126ef7f..4df57c93e0a8 100644 --- a/arch/ia64/kernel/esi.c +++ b/arch/ia64/kernel/esi.c @@ -19,10 +19,6 @@ MODULE_LICENSE("GPL"); #define MODULE_NAME "esi" -#define ESI_TABLE_GUID \ - EFI_GUID(0x43EA58DC, 0xCF28, 0x4b06, 0xB3, \ - 0x91, 0xB7, 0x50, 0x59, 0x34, 0x2B, 0xD4) - enum esi_systab_entry_type { ESI_DESC_ENTRY_POINT = 0 }; @@ -48,27 +44,18 @@ struct pdesc { static struct ia64_sal_systab *esi_systab; +extern unsigned long esi_phys; + static int __init esi_init (void) { - efi_config_table_t *config_tables; struct ia64_sal_systab *systab; - unsigned long esi = 0; char *p; int i; - config_tables = __va(efi.systab->tables); - - for (i = 0; i < (int) efi.systab->nr_tables; ++i) { - if (efi_guidcmp(config_tables[i].guid, ESI_TABLE_GUID) == 0) { - esi = config_tables[i].table; - break; - } - } - - if (!esi) + if (esi_phys == EFI_INVALID_TABLE_ADDR) return -ENODEV; - systab = __va(esi); + systab = __va(esi_phys); if (strncmp(systab->signature, "ESIT", 4) != 0) { printk(KERN_ERR "bad signature in ESI system table!"); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 968b5f33e725..10cb9382ab76 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -646,14 +646,8 @@ cpu_halt (void) void machine_shutdown(void) { -#ifdef CONFIG_HOTPLUG_CPU - int cpu; + smp_shutdown_nonboot_cpus(reboot_cpu); - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) - cpu_down(cpu); - } -#endif #ifdef CONFIG_KEXEC kexec_disable_iosapic(); #endif @@ -681,3 +675,4 @@ machine_power_off (void) machine_halt(); } +EXPORT_SYMBOL(ia64_delay_loop); diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c index a09cfa064536..55fd3eb753ff 100644 --- a/arch/ia64/mm/ioremap.c +++ b/arch/ia64/mm/ioremap.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/efi.h> #include <linux/io.h> +#include <linux/mm.h> #include <linux/vmalloc.h> #include <asm/io.h> #include <asm/meminit.h> diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 40712e49381b..c3a630440512 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -118,12 +118,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->bsize = bsize; dev->bshift = ffs(bsize) - 10; - dev->queue = blk_alloc_queue(GFP_KERNEL); + dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE); if (dev->queue == NULL) goto free_dev; dev->queue->queuedata = dev; - blk_queue_make_request(dev->queue, nfhd_make_request); blk_queue_logical_block_size(dev->queue, bsize); dev->disk = alloc_disk(16); diff --git a/arch/m68k/include/asm/uaccess_no.h b/arch/m68k/include/asm/uaccess_no.h index 6bc80c35726d..a24cfe4a0d32 100644 --- a/arch/m68k/include/asm/uaccess_no.h +++ b/arch/m68k/include/asm/uaccess_no.h @@ -5,7 +5,6 @@ /* * User space memory access functions */ -#include <linux/mm.h> #include <linux/string.h> #include <asm/segment.h> diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 6a331bd57ea8..242f58ec086b 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -47,6 +47,8 @@ config MICROBLAZE select CPU_NO_EFFICIENT_FFS select MMU_GATHER_NO_RANGE if MMU select SPARSE_IRQ + select GENERIC_IRQ_MULTI_HANDLER + select HANDLE_DOMAIN_IRQ # Endianness selection choice diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h index 8c90357e5983..86131ed84c9a 100644 --- a/arch/microblaze/include/asm/futex.h +++ b/arch/microblaze/include/asm/futex.h @@ -34,7 +34,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -56,8 +57,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/microblaze/include/asm/irq.h b/arch/microblaze/include/asm/irq.h index eac2fb4b3fb9..5166f0893e2b 100644 --- a/arch/microblaze/include/asm/irq.h +++ b/arch/microblaze/include/asm/irq.h @@ -14,7 +14,4 @@ struct pt_regs; extern void do_IRQ(struct pt_regs *regs); -/* should be defined in each interrupt controller driver */ -extern unsigned int xintc_get_irq(void); - #endif /* _ASM_MICROBLAZE_IRQ_H */ diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index a1f206b90753..4916d5fbea5e 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -12,7 +12,6 @@ #define _ASM_MICROBLAZE_UACCESS_H #include <linux/kernel.h> -#include <linux/mm.h> #include <asm/mmu.h> #include <asm/page.h> diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c index 903dad822fad..0b37dde60a1e 100644 --- a/arch/microblaze/kernel/irq.c +++ b/arch/microblaze/kernel/irq.c @@ -20,29 +20,10 @@ #include <linux/irqchip.h> #include <linux/of_irq.h> -static u32 concurrent_irq; - void __irq_entry do_IRQ(struct pt_regs *regs) { - unsigned int irq; - struct pt_regs *old_regs = set_irq_regs(regs); trace_hardirqs_off(); - - irq_enter(); - irq = xintc_get_irq(); -next_irq: - BUG_ON(!irq); - generic_handle_irq(irq); - - irq = xintc_get_irq(); - if (irq != -1U) { - pr_debug("next irq: %d\n", irq); - ++concurrent_irq; - goto next_irq; - } - - irq_exit(); - set_irq_regs(old_regs); + handle_arch_irq(regs); trace_hardirqs_on(); } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 654369a7209d..66e94278bd10 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -50,6 +50,7 @@ config MIPS select HAVE_ASM_MODVERSIONS select HAVE_CBPF_JIT if !64BIT && !CPU_MICROMIPS select HAVE_CONTEXT_TRACKING + select HAVE_TIF_NOHZ select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 37b93166bf22..c340f947baa0 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -4,6 +4,8 @@ #include "jz4780.dtsi" #include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/regulator/active-semi,8865-regulator.h> / { compatible = "img,ci20", "ingenic,jz4780"; @@ -163,63 +165,71 @@ regulators { vddcore: SUDCDC1 { - regulator-name = "VDDCORE"; + regulator-name = "DCDC_REG1"; regulator-min-microvolt = <1100000>; regulator-max-microvolt = <1100000>; regulator-always-on; }; vddmem: SUDCDC2 { - regulator-name = "VDDMEM"; + regulator-name = "DCDC_REG2"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; vcc_33: SUDCDC3 { - regulator-name = "VCC33"; + regulator-name = "DCDC_REG3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_50: SUDCDC4 { - regulator-name = "VCC50"; + regulator-name = "SUDCDC_REG4"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; regulator-always-on; }; vcc_25: LDO_REG5 { - regulator-name = "VCC25"; + regulator-name = "LDO_REG5"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; wifi_io: LDO_REG6 { - regulator-name = "WIFIIO"; + regulator-name = "LDO_REG6"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; vcc_28: LDO_REG7 { - regulator-name = "VCC28"; + regulator-name = "LDO_REG7"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; regulator-always-on; }; vcc_15: LDO_REG8 { - regulator-name = "VCC15"; + regulator-name = "LDO_REG8"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; - vcc_18: LDO_REG9 { - regulator-name = "VCC18"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; + vrtc_18: LDO_REG9 { + regulator-name = "LDO_REG9"; + /* Despite the datasheet stating 3.3V + * for REG9 and the driver expecting that, + * REG9 outputs 1.8V. + * Likely the CI20 uses a proprietary + * factory programmed chip variant. + * Since this is a simple on/off LDO the + * exact values do not matter. + */ + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_11: LDO_REG10 { - regulator-name = "VCC11"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; + regulator-name = "LDO_REG10"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; regulator-always-on; }; }; @@ -261,7 +271,9 @@ rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; - interrupts = <110>; + + interrupt-parent = <&gpf>; + interrupts = <30 IRQ_TYPE_LEVEL_LOW>; }; }; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 5accda2767be..a3301bab9231 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4740-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> / { #address-cells = <1>; @@ -45,14 +46,6 @@ #clock-cells = <1>; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4740-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4740_CLK_RTC>; - clock-names = "rtc"; - }; - tcu: timer@10002000 { compatible = "ingenic,jz4740-tcu", "simple-mfd"; reg = <0x10002000 0x1000>; @@ -73,6 +66,14 @@ interrupt-parent = <&intc>; interrupts = <23 22 21>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4740-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index f928329b034b..bb89653d16a3 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4780-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/dma/jz4780-dma.h> / { @@ -67,6 +68,14 @@ interrupt-parent = <&intc>; interrupts = <27 26 25>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4780-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { @@ -348,14 +357,6 @@ status = "disabled"; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4780-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4780_CLK_RTCLK>; - clock-names = "rtc"; - }; - nemc: nemc@13410000 { compatible = "ingenic,jz4780-nemc"; reg = <0x13410000 0x10000>; diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index 4994c695a1a7..147f7d5c243a 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/clock/x1000-cgu.h> #include <dt-bindings/dma/x1000-dma.h> @@ -72,7 +73,7 @@ compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog"; reg = <0x0 0x10>; - clocks = <&cgu X1000_CLK_RTCLK>; + clocks = <&tcu TCU_CLK_WDT>; clock-names = "wdt"; }; }; @@ -158,7 +159,6 @@ i2c0: i2c-controller@10050000 { compatible = "ingenic,x1000-i2c"; reg = <0x10050000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -173,7 +173,6 @@ i2c1: i2c-controller@10051000 { compatible = "ingenic,x1000-i2c"; reg = <0x10051000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -188,7 +187,6 @@ i2c2: i2c-controller@10052000 { compatible = "ingenic,x1000-i2c"; reg = <0x10052000 0x1000>; - #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c index 2e2d45bc850d..abd11b7af22f 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c @@ -207,9 +207,9 @@ int cvmx_helper_board_get_mii_address(int ipd_port) * Returns The ports link status. If the link isn't fully resolved, this must * return zero. */ -cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port) +union cvmx_helper_link_info __cvmx_helper_board_link_get(int ipd_port) { - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; WARN(!octeon_is_simulation(), "Using deprecated link status - please update your DT"); diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c index e812ed9a03bb..c4b58598aa9d 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c @@ -261,7 +261,7 @@ int __cvmx_helper_rgmii_enable(int interface) * * Returns Link state */ -cvmx_helper_link_info_t __cvmx_helper_rgmii_link_get(int ipd_port) +union cvmx_helper_link_info __cvmx_helper_rgmii_link_get(int ipd_port) { int interface = cvmx_helper_get_interface_num(ipd_port); int index = cvmx_helper_get_interface_index_num(ipd_port); @@ -270,7 +270,7 @@ cvmx_helper_link_info_t __cvmx_helper_rgmii_link_get(int ipd_port) asxx_prt_loop.u64 = cvmx_read_csr(CVMX_ASXX_PRT_LOOP(interface)); if (asxx_prt_loop.s.int_loop & (1 << index)) { /* Force 1Gbps full duplex on internal loopback */ - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; result.u64 = 0; result.s.full_duplex = 1; result.s.link_up = 1; @@ -292,7 +292,7 @@ cvmx_helper_link_info_t __cvmx_helper_rgmii_link_get(int ipd_port) * Returns Zero on success, negative on failure */ int __cvmx_helper_rgmii_link_set(int ipd_port, - cvmx_helper_link_info_t link_info) + union cvmx_helper_link_info link_info) { int result = 0; int interface = cvmx_helper_get_interface_num(ipd_port); diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c index f6ebf63dc84c..e07d8f15efba 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c @@ -200,7 +200,7 @@ static int __cvmx_helper_sgmii_hardware_init_link(int interface, int index) */ static int __cvmx_helper_sgmii_hardware_init_link_speed(int interface, int index, - cvmx_helper_link_info_t + union cvmx_helper_link_info link_info) { int is_enabled; @@ -394,9 +394,9 @@ int __cvmx_helper_sgmii_enable(int interface) * * Returns Link state */ -cvmx_helper_link_info_t __cvmx_helper_sgmii_link_get(int ipd_port) +union cvmx_helper_link_info __cvmx_helper_sgmii_link_get(int ipd_port) { - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; union cvmx_pcsx_miscx_ctl_reg pcs_misc_ctl_reg; int interface = cvmx_helper_get_interface_num(ipd_port); int index = cvmx_helper_get_interface_index_num(ipd_port); @@ -505,7 +505,7 @@ cvmx_helper_link_info_t __cvmx_helper_sgmii_link_get(int ipd_port) * Returns Zero on success, negative on failure */ int __cvmx_helper_sgmii_link_set(int ipd_port, - cvmx_helper_link_info_t link_info) + union cvmx_helper_link_info link_info) { int interface = cvmx_helper_get_interface_num(ipd_port); int index = cvmx_helper_get_interface_index_num(ipd_port); diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c index 2a574d272671..525914e9b22d 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c @@ -140,9 +140,9 @@ int __cvmx_helper_spi_enable(int interface) * * Returns Link state */ -cvmx_helper_link_info_t __cvmx_helper_spi_link_get(int ipd_port) +union cvmx_helper_link_info __cvmx_helper_spi_link_get(int ipd_port) { - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; int interface = cvmx_helper_get_interface_num(ipd_port); int index = cvmx_helper_get_interface_index_num(ipd_port); result.u64 = 0; @@ -193,7 +193,7 @@ cvmx_helper_link_info_t __cvmx_helper_spi_link_get(int ipd_port) * * Returns Zero on success, negative on failure */ -int __cvmx_helper_spi_link_set(int ipd_port, cvmx_helper_link_info_t link_info) +int __cvmx_helper_spi_link_set(int ipd_port, union cvmx_helper_link_info link_info) { /* Nothing to do. If we have a SPI4000 then the setup was already performed by cvmx_spi4000_check_speed(). If not then there isn't any link diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c index 93a498d05184..842990e8404f 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c @@ -259,13 +259,13 @@ int __cvmx_helper_xaui_enable(int interface) * * Returns Link state */ -cvmx_helper_link_info_t __cvmx_helper_xaui_link_get(int ipd_port) +union cvmx_helper_link_info __cvmx_helper_xaui_link_get(int ipd_port) { int interface = cvmx_helper_get_interface_num(ipd_port); union cvmx_gmxx_tx_xaui_ctl gmxx_tx_xaui_ctl; union cvmx_gmxx_rx_xaui_ctl gmxx_rx_xaui_ctl; union cvmx_pcsxx_status1_reg pcsxx_status1_reg; - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; gmxx_tx_xaui_ctl.u64 = cvmx_read_csr(CVMX_GMXX_TX_XAUI_CTL(interface)); gmxx_rx_xaui_ctl.u64 = cvmx_read_csr(CVMX_GMXX_RX_XAUI_CTL(interface)); @@ -299,7 +299,7 @@ cvmx_helper_link_info_t __cvmx_helper_xaui_link_get(int ipd_port) * * Returns Zero on success, negative on failure */ -int __cvmx_helper_xaui_link_set(int ipd_port, cvmx_helper_link_info_t link_info) +int __cvmx_helper_xaui_link_set(int ipd_port, union cvmx_helper_link_info link_info) { int interface = cvmx_helper_get_interface_num(ipd_port); union cvmx_gmxx_tx_xaui_ctl gmxx_tx_xaui_ctl; diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index de391541d6f7..6044ff471002 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -782,9 +782,9 @@ static int __cvmx_helper_errata_fix_ipd_ptr_alignment(void) #define INTERFACE(port) (port >> 4) #define INDEX(port) (port & 0xf) uint64_t *p64; - cvmx_pko_command_word0_t pko_command; + union cvmx_pko_command_word0 pko_command; union cvmx_buf_ptr g_buffer, pkt_buffer; - cvmx_wqe_t *work; + struct cvmx_wqe *work; int size, num_segs = 0, wqe_pcnt, pkt_pcnt; union cvmx_gmxx_prtx_cfg gmx_cfg; int retry_cnt; @@ -1075,9 +1075,9 @@ int cvmx_helper_initialize_packet_io_local(void) * * Returns Link state */ -cvmx_helper_link_info_t cvmx_helper_link_get(int ipd_port) +union cvmx_helper_link_info cvmx_helper_link_get(int ipd_port) { - cvmx_helper_link_info_t result; + union cvmx_helper_link_info result; int interface = cvmx_helper_get_interface_num(ipd_port); int index = cvmx_helper_get_interface_index_num(ipd_port); @@ -1136,7 +1136,7 @@ EXPORT_SYMBOL_GPL(cvmx_helper_link_get); * * Returns Zero on success, negative on failure */ -int cvmx_helper_link_set(int ipd_port, cvmx_helper_link_info_t link_info) +int cvmx_helper_link_set(int ipd_port, union cvmx_helper_link_info link_info) { int result = -1; int interface = cvmx_helper_get_interface_num(ipd_port); diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index 110220705e97..2bf8f6014579 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -89,7 +89,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -116,8 +117,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/mips/include/asm/octeon/cvmx-helper-board.h b/arch/mips/include/asm/octeon/cvmx-helper-board.h index d7fdcf0a0088..ce52aafe7a8d 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-board.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-board.h @@ -93,7 +93,7 @@ extern int cvmx_helper_board_get_mii_address(int ipd_port); * Returns The ports link status. If the link isn't fully resolved, this must * return zero. */ -extern cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port); +extern union cvmx_helper_link_info __cvmx_helper_board_link_get(int ipd_port); /** * This function is called by cvmx_helper_interface_probe() after it diff --git a/arch/mips/include/asm/octeon/cvmx-helper-rgmii.h b/arch/mips/include/asm/octeon/cvmx-helper-rgmii.h index ac42b5066bd9..3e79a7f898b6 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-rgmii.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-rgmii.h @@ -74,7 +74,7 @@ extern int __cvmx_helper_rgmii_enable(int interface); * * Returns Link state */ -extern cvmx_helper_link_info_t __cvmx_helper_rgmii_link_get(int ipd_port); +extern union cvmx_helper_link_info __cvmx_helper_rgmii_link_get(int ipd_port); /** * Configure an IPD/PKO port for the specified link state. This @@ -88,6 +88,6 @@ extern cvmx_helper_link_info_t __cvmx_helper_rgmii_link_get(int ipd_port); * Returns Zero on success, negative on failure */ extern int __cvmx_helper_rgmii_link_set(int ipd_port, - cvmx_helper_link_info_t link_info); + union cvmx_helper_link_info link_info); #endif diff --git a/arch/mips/include/asm/octeon/cvmx-helper-sgmii.h b/arch/mips/include/asm/octeon/cvmx-helper-sgmii.h index 3a54dea58c0a..8aac90f1871f 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-sgmii.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-sgmii.h @@ -68,7 +68,7 @@ extern int __cvmx_helper_sgmii_enable(int interface); * * Returns Link state */ -extern cvmx_helper_link_info_t __cvmx_helper_sgmii_link_get(int ipd_port); +extern union cvmx_helper_link_info __cvmx_helper_sgmii_link_get(int ipd_port); /** * Configure an IPD/PKO port for the specified link state. This @@ -82,6 +82,6 @@ extern cvmx_helper_link_info_t __cvmx_helper_sgmii_link_get(int ipd_port); * Returns Zero on success, negative on failure */ extern int __cvmx_helper_sgmii_link_set(int ipd_port, - cvmx_helper_link_info_t link_info); + union cvmx_helper_link_info link_info); #endif diff --git a/arch/mips/include/asm/octeon/cvmx-helper-spi.h b/arch/mips/include/asm/octeon/cvmx-helper-spi.h index d5adf8592773..bc8cab9367b8 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-spi.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-spi.h @@ -65,7 +65,7 @@ extern int __cvmx_helper_spi_enable(int interface); * * Returns Link state */ -extern cvmx_helper_link_info_t __cvmx_helper_spi_link_get(int ipd_port); +extern union cvmx_helper_link_info __cvmx_helper_spi_link_get(int ipd_port); /** * Configure an IPD/PKO port for the specified link state. This @@ -79,6 +79,6 @@ extern cvmx_helper_link_info_t __cvmx_helper_spi_link_get(int ipd_port); * Returns Zero on success, negative on failure */ extern int __cvmx_helper_spi_link_set(int ipd_port, - cvmx_helper_link_info_t link_info); + union cvmx_helper_link_info link_info); #endif diff --git a/arch/mips/include/asm/octeon/cvmx-helper-util.h b/arch/mips/include/asm/octeon/cvmx-helper-util.h index e9a97e7ee604..97b27a07cfb0 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-util.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-util.h @@ -123,7 +123,7 @@ static inline int cvmx_helper_get_last_ipd_port(int interface) * * @work: Work queue entry with packet to free */ -static inline void cvmx_helper_free_packet_data(cvmx_wqe_t *work) +static inline void cvmx_helper_free_packet_data(struct cvmx_wqe *work) { uint64_t number_buffers; union cvmx_buf_ptr buffer_ptr; diff --git a/arch/mips/include/asm/octeon/cvmx-helper-xaui.h b/arch/mips/include/asm/octeon/cvmx-helper-xaui.h index 51f45b495680..c18da2eba78e 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper-xaui.h +++ b/arch/mips/include/asm/octeon/cvmx-helper-xaui.h @@ -68,7 +68,7 @@ extern int __cvmx_helper_xaui_enable(int interface); * * Returns Link state */ -extern cvmx_helper_link_info_t __cvmx_helper_xaui_link_get(int ipd_port); +extern union cvmx_helper_link_info __cvmx_helper_xaui_link_get(int ipd_port); /** * Configure an IPD/PKO port for the specified link state. This @@ -82,6 +82,6 @@ extern cvmx_helper_link_info_t __cvmx_helper_xaui_link_get(int ipd_port); * Returns Zero on success, negative on failure */ extern int __cvmx_helper_xaui_link_set(int ipd_port, - cvmx_helper_link_info_t link_info); + union cvmx_helper_link_info link_info); #endif diff --git a/arch/mips/include/asm/octeon/cvmx-helper.h b/arch/mips/include/asm/octeon/cvmx-helper.h index ba0e76f578e0..c6c99e28eefb 100644 --- a/arch/mips/include/asm/octeon/cvmx-helper.h +++ b/arch/mips/include/asm/octeon/cvmx-helper.h @@ -51,7 +51,7 @@ typedef enum { CVMX_HELPER_INTERFACE_MODE_LOOP, } cvmx_helper_interface_mode_t; -typedef union { +union cvmx_helper_link_info { uint64_t u64; struct { uint64_t reserved_20_63:44; @@ -59,7 +59,7 @@ typedef union { uint64_t full_duplex:1; /**< 1 if the link is full duplex */ uint64_t speed:18; /**< Speed of the link in Mbps */ } s; -} cvmx_helper_link_info_t; +}; #include <asm/octeon/cvmx-helper-errata.h> #include <asm/octeon/cvmx-helper-loop.h> @@ -145,7 +145,7 @@ extern cvmx_helper_interface_mode_t cvmx_helper_interface_get_mode(int * * Returns Link state */ -extern cvmx_helper_link_info_t cvmx_helper_link_get(int ipd_port); +extern union cvmx_helper_link_info cvmx_helper_link_get(int ipd_port); /** * Configure an IPD/PKO port for the specified link state. This @@ -159,7 +159,7 @@ extern cvmx_helper_link_info_t cvmx_helper_link_get(int ipd_port); * Returns Zero on success, negative on failure */ extern int cvmx_helper_link_set(int ipd_port, - cvmx_helper_link_info_t link_info); + union cvmx_helper_link_info link_info); /** * This function probes an interface to determine the actual diff --git a/arch/mips/include/asm/octeon/cvmx-pko.h b/arch/mips/include/asm/octeon/cvmx-pko.h index 20eb9c46a75a..5b0b982a36f7 100644 --- a/arch/mips/include/asm/octeon/cvmx-pko.h +++ b/arch/mips/include/asm/octeon/cvmx-pko.h @@ -169,7 +169,7 @@ typedef union { /** * Structure of the first packet output command word. */ -typedef union { +union cvmx_pko_command_word0 { uint64_t u64; struct { #ifdef __BIG_ENDIAN_BITFIELD @@ -261,7 +261,7 @@ typedef union { uint64_t size1:2; #endif } s; -} cvmx_pko_command_word0_t; +}; /* CSR typedefs have been moved to cvmx-csr-*.h */ @@ -394,7 +394,7 @@ static inline void cvmx_pko_send_packet_prepare(uint64_t port, uint64_t queue, CVMX_TAG_SW_BITS_INTERNAL << CVMX_TAG_SW_SHIFT | CVMX_TAG_SUBGROUP_PKO << CVMX_TAG_SUBGROUP_SHIFT | (CVMX_TAG_SUBGROUP_MASK & queue); - cvmx_pow_tag_sw_full((cvmx_wqe_t *) cvmx_phys_to_ptr(0x80), tag, + cvmx_pow_tag_sw_full((struct cvmx_wqe *) cvmx_phys_to_ptr(0x80), tag, CVMX_POW_TAG_TYPE_ATOMIC, 0); } } @@ -419,7 +419,7 @@ static inline void cvmx_pko_send_packet_prepare(uint64_t port, uint64_t queue, static inline cvmx_pko_status_t cvmx_pko_send_packet_finish( uint64_t port, uint64_t queue, - cvmx_pko_command_word0_t pko_command, + union cvmx_pko_command_word0 pko_command, union cvmx_buf_ptr packet, cvmx_pko_lock_t use_locking) { @@ -462,7 +462,7 @@ static inline cvmx_pko_status_t cvmx_pko_send_packet_finish( static inline cvmx_pko_status_t cvmx_pko_send_packet_finish3( uint64_t port, uint64_t queue, - cvmx_pko_command_word0_t pko_command, + union cvmx_pko_command_word0 pko_command, union cvmx_buf_ptr packet, uint64_t addr, cvmx_pko_lock_t use_locking) diff --git a/arch/mips/include/asm/octeon/cvmx-pow.h b/arch/mips/include/asm/octeon/cvmx-pow.h index 410bb70e5aac..ba366f4f3c3d 100644 --- a/arch/mips/include/asm/octeon/cvmx-pow.h +++ b/arch/mips/include/asm/octeon/cvmx-pow.h @@ -1283,7 +1283,7 @@ static inline cvmx_pow_tag_req_t cvmx_pow_get_current_tag(void) * * Returns WQE pointer */ -static inline cvmx_wqe_t *cvmx_pow_get_current_wqp(void) +static inline struct cvmx_wqe *cvmx_pow_get_current_wqp(void) { cvmx_pow_load_addr_t load_addr; cvmx_pow_tag_load_resp_t load_resp; @@ -1296,7 +1296,7 @@ static inline cvmx_wqe_t *cvmx_pow_get_current_wqp(void) load_addr.sstatus.get_cur = 1; load_addr.sstatus.get_wqp = 1; load_resp.u64 = cvmx_read_csr(load_addr.u64); - return (cvmx_wqe_t *) cvmx_phys_to_ptr(load_resp.s_sstatus4.wqp); + return (struct cvmx_wqe *) cvmx_phys_to_ptr(load_resp.s_sstatus4.wqp); } #ifndef CVMX_MF_CHORD @@ -1348,7 +1348,7 @@ static inline void cvmx_pow_tag_sw_wait(void) * Returns Returns the WQE pointer from POW. Returns NULL if no work * was available. */ -static inline cvmx_wqe_t *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_t +static inline struct cvmx_wqe *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_t wait) { cvmx_pow_load_addr_t ptr; @@ -1368,7 +1368,7 @@ static inline cvmx_wqe_t *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_t if (result.s_work.no_work) return NULL; else - return (cvmx_wqe_t *) cvmx_phys_to_ptr(result.s_work.addr); + return (struct cvmx_wqe *) cvmx_phys_to_ptr(result.s_work.addr); } /** @@ -1382,7 +1382,7 @@ static inline cvmx_wqe_t *cvmx_pow_work_request_sync_nocheck(cvmx_pow_wait_t * Returns Returns the WQE pointer from POW. Returns NULL if no work * was available. */ -static inline cvmx_wqe_t *cvmx_pow_work_request_sync(cvmx_pow_wait_t wait) +static inline struct cvmx_wqe *cvmx_pow_work_request_sync(cvmx_pow_wait_t wait) { if (CVMX_ENABLE_POW_CHECKS) __cvmx_pow_warn_if_pending_switch(__func__); @@ -1485,7 +1485,7 @@ static inline void cvmx_pow_work_request_async(int scr_addr, * Returns Returns the WQE from the scratch register, or NULL if no * work was available. */ -static inline cvmx_wqe_t *cvmx_pow_work_response_async(int scr_addr) +static inline struct cvmx_wqe *cvmx_pow_work_response_async(int scr_addr) { cvmx_pow_tag_load_resp_t result; @@ -1495,7 +1495,7 @@ static inline cvmx_wqe_t *cvmx_pow_work_response_async(int scr_addr) if (result.s_work.no_work) return NULL; else - return (cvmx_wqe_t *) cvmx_phys_to_ptr(result.s_work.addr); + return (struct cvmx_wqe *) cvmx_phys_to_ptr(result.s_work.addr); } /** @@ -1508,7 +1508,7 @@ static inline cvmx_wqe_t *cvmx_pow_work_response_async(int scr_addr) * Returns 0 if pointer is valid * 1 if invalid (no work was returned) */ -static inline uint64_t cvmx_pow_work_invalid(cvmx_wqe_t *wqe_ptr) +static inline uint64_t cvmx_pow_work_invalid(struct cvmx_wqe *wqe_ptr) { return wqe_ptr == NULL; } @@ -1638,7 +1638,7 @@ static inline void cvmx_pow_tag_sw(uint32_t tag, * @tag_type: type of tag * @group: group value for the work queue entry. */ -static inline void cvmx_pow_tag_sw_full_nocheck(cvmx_wqe_t *wqp, uint32_t tag, +static inline void cvmx_pow_tag_sw_full_nocheck(struct cvmx_wqe *wqp, uint32_t tag, enum cvmx_pow_tag_type tag_type, uint64_t group) { @@ -1712,7 +1712,7 @@ static inline void cvmx_pow_tag_sw_full_nocheck(cvmx_wqe_t *wqp, uint32_t tag, * @tag_type: type of tag * @group: group value for the work queue entry. */ -static inline void cvmx_pow_tag_sw_full(cvmx_wqe_t *wqp, uint32_t tag, +static inline void cvmx_pow_tag_sw_full(struct cvmx_wqe *wqp, uint32_t tag, enum cvmx_pow_tag_type tag_type, uint64_t group) { @@ -1803,7 +1803,7 @@ static inline void cvmx_pow_tag_sw_null(void) * @qos: Input queue to add to. * @grp: group value for the work queue entry. */ -static inline void cvmx_pow_work_submit(cvmx_wqe_t *wqp, uint32_t tag, +static inline void cvmx_pow_work_submit(struct cvmx_wqe *wqp, uint32_t tag, enum cvmx_pow_tag_type tag_type, uint64_t qos, uint64_t grp) { diff --git a/arch/mips/include/asm/octeon/cvmx-wqe.h b/arch/mips/include/asm/octeon/cvmx-wqe.h index 0d697aa786d4..9cec2299b81b 100644 --- a/arch/mips/include/asm/octeon/cvmx-wqe.h +++ b/arch/mips/include/asm/octeon/cvmx-wqe.h @@ -547,7 +547,7 @@ union cvmx_wqe_word1 { * * must be 8-byte aligned */ -typedef struct { +struct cvmx_wqe { /***************************************************************** * WORD 0 @@ -593,9 +593,9 @@ typedef struct { * */ -} CVMX_CACHE_LINE_ALIGNED cvmx_wqe_t; +} CVMX_CACHE_LINE_ALIGNED; -static inline int cvmx_wqe_get_port(cvmx_wqe_t *work) +static inline int cvmx_wqe_get_port(struct cvmx_wqe *work) { int port; @@ -607,7 +607,7 @@ static inline int cvmx_wqe_get_port(cvmx_wqe_t *work) return port; } -static inline void cvmx_wqe_set_port(cvmx_wqe_t *work, int port) +static inline void cvmx_wqe_set_port(struct cvmx_wqe *work, int port) { if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE)) work->word2.s_cn68xx.port = port; @@ -615,7 +615,7 @@ static inline void cvmx_wqe_set_port(cvmx_wqe_t *work, int port) work->word1.cn38xx.ipprt = port; } -static inline int cvmx_wqe_get_grp(cvmx_wqe_t *work) +static inline int cvmx_wqe_get_grp(struct cvmx_wqe *work) { int grp; @@ -627,7 +627,7 @@ static inline int cvmx_wqe_get_grp(cvmx_wqe_t *work) return grp; } -static inline void cvmx_wqe_set_grp(cvmx_wqe_t *work, int grp) +static inline void cvmx_wqe_set_grp(struct cvmx_wqe *work, int grp) { if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE)) work->word1.cn68xx.grp = grp; @@ -635,7 +635,7 @@ static inline void cvmx_wqe_set_grp(cvmx_wqe_t *work, int grp) work->word1.cn38xx.grp = grp; } -static inline int cvmx_wqe_get_qos(cvmx_wqe_t *work) +static inline int cvmx_wqe_get_qos(struct cvmx_wqe *work) { int qos; @@ -647,7 +647,7 @@ static inline int cvmx_wqe_get_qos(cvmx_wqe_t *work) return qos; } -static inline void cvmx_wqe_set_qos(cvmx_wqe_t *work, int qos) +static inline void cvmx_wqe_set_qos(struct cvmx_wqe *work, int qos) { if (octeon_has_feature(OCTEON_FEATURE_CN68XX_WQE)) work->word1.cn68xx.qos = qos; diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h index 7c6a1095f556..aabd097933fe 100644 --- a/arch/mips/include/asm/sync.h +++ b/arch/mips/include/asm/sync.h @@ -155,9 +155,11 @@ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use * optimized memory barrier primitives."). Here we specify that the affected * sync instructions should be emitted twice. + * Note that this expression is evaluated by the assembler (not the compiler), + * and that the assembler evaluates '==' as 0 or -1, not 0 or 1. */ #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb)) #else # define __SYNC_rpt(type) 1 #endif diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 1ac2752fb791..a7b469d89e2c 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -605,7 +605,8 @@ static void __init bootcmdline_init(char **cmdline_p) * If we're configured to take boot arguments from DT, look for those * now. */ - if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB)) + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB) || + IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND)) of_scan_flat_dt(bootcmdline_scan_chosen, &dt_bootargs); #endif diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f510c00bda88..0def6242b3ea 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -696,29 +696,22 @@ EXPORT_SYMBOL(flush_tlb_one); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -static DEFINE_PER_CPU(atomic_t, tick_broadcast_count); static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd); void tick_broadcast(const struct cpumask *mask) { - atomic_t *count; call_single_data_t *csd; int cpu; for_each_cpu(cpu, mask) { - count = &per_cpu(tick_broadcast_count, cpu); csd = &per_cpu(tick_broadcast_csd, cpu); - - if (atomic_inc_return(count) == 1) - smp_call_function_single_async(cpu, csd); + smp_call_function_single_async(cpu, csd); } } static void tick_broadcast_callee(void *info) { - int cpu = smp_processor_id(); tick_receive_broadcast(); - atomic_set(&per_cpu(tick_broadcast_count, cpu), 0); } static int __init tick_broadcast_init(void) diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6176b9acba95..d0d832ab3d3b 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index aa89a41dc5dd..d7fe8408603e 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -33,6 +33,7 @@ endif cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ + -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) @@ -51,6 +52,8 @@ endif CFLAGS_REMOVE_vgettimeofday.o = -pg +DISABLE_VDSO := n + # # For the pre-R6 code in arch/mips/vdso/vdso.h for locating # the base address of VDSO, the linker will emit a R_MIPS_PC32 @@ -64,11 +67,24 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) - ccflags-vdso += -DDISABLE_MIPS_VDSO + DISABLE_VDSO := y endif endif +# +# GCC (at least up to version 9.2) appears to emit function calls that make use +# of the GOT when targeting microMIPS, which we can't use in the VDSO due to +# the lack of relocations. As such, we disable the VDSO for microMIPS builds. +# +ifdef CONFIG_CPU_MICROMIPS + DISABLE_VDSO := y +endif + +ifeq ($(DISABLE_VDSO),y) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) + ccflags-vdso += -DDISABLE_MIPS_VDSO +endif + # VDSO linker flags. VDSO_LDFLAGS := \ -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \ @@ -81,12 +97,18 @@ GCOV_PROFILE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Check that we don't have PIC 'jalr t9' calls left +quiet_cmd_vdso_mips_check = VDSOCHK $@ + cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \ + then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \ + rm -f $@; /bin/false); fi + # # Shared build commands. # quiet_cmd_vdsold_and_vdso_check = LD $@ - cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check); $(cmd_vdso_mips_check) quiet_cmd_vdsold = VDSO $@ cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h index 5213c65c2e0b..4223f473bd36 100644 --- a/arch/nds32/include/asm/futex.h +++ b/arch/nds32/include/asm/futex.h @@ -66,8 +66,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: __futex_atomic_op("move %0, %3", ret, oldval, tmp, uaddr, @@ -93,8 +93,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 8916ad9f9f13..3a9219f53ee0 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -11,7 +11,6 @@ #include <asm/errno.h> #include <asm/memory.h> #include <asm/types.h> -#include <linux/mm.h> #define __asmeq(x, y) ".ifnc " x "," y " ; .err ; .endif\n\t" diff --git a/arch/openrisc/include/asm/futex.h b/arch/openrisc/include/asm/futex.h index fe894e6331ae..865e9cd0d97b 100644 --- a/arch/openrisc/include/asm/futex.h +++ b/arch/openrisc/include/asm/futex.h @@ -35,7 +35,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -57,8 +58,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 71034b54d74e..3801a2ef9bca 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -79,6 +79,11 @@ config MMU config STACK_GROWSUP def_bool y +config ARCH_DEFCONFIG + string + default "arch/parisc/configs/generic-32bit_defconfig" if !64BIT + default "arch/parisc/configs/generic-64bit_defconfig" if 64BIT + config GENERIC_LOCKBREAK bool default y diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index dca8f2de8cf5..628cd8bb7ad8 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -34,6 +34,13 @@ CC_ARCHES = hppa hppa2.0 hppa1.1 LD_BFD := elf32-hppa-linux endif +# select defconfig based on actual architecture +ifeq ($(shell uname -m),parisc64) + KBUILD_DEFCONFIG := generic-64bit_defconfig +else + KBUILD_DEFCONFIG := generic-32bit_defconfig +endif + export LD_BFD ifneq ($(SUBARCH),$(UTS_MACHINE)) diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h index d2c3e4106851..c459f656c8c3 100644 --- a/arch/parisc/include/asm/futex.h +++ b/arch/parisc/include/asm/futex.h @@ -40,7 +40,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) u32 tmp; _futex_spin_lock_irqsave(uaddr, &flags); - pagefault_disable(); ret = -EFAULT; if (unlikely(get_user(oldval, uaddr) != 0)) @@ -73,7 +72,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -EFAULT; out_pagefault_enable: - pagefault_enable(); _futex_spin_unlock_irqrestore(uaddr, &flags); if (!ret) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 13f771f74ee3..7f2d0c0ecc80 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -212,7 +212,7 @@ static int __init processor_probe(struct parisc_device *dev) #ifdef CONFIG_SMP if (cpuid) { set_cpu_present(cpuid, true); - cpu_up(cpuid); + add_cpu(cpuid); } #endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 497b7d0b2d7e..6f40af294685 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -182,6 +182,7 @@ config PPC select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13) select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2) select HAVE_CONTEXT_TRACKING if PPC64 + select HAVE_TIF_NOHZ if PPC64 select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index bc7d9d06a6d9..f187bb5e524e 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -35,8 +35,9 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; allow_read_write_user(uaddr, uaddr, sizeof(*uaddr)); - pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -58,8 +59,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, ret = -ENOSYS; } - pagefault_enable(); - *oval = oldval; prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr)); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 86332080399a..080a0bf8e54b 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -295,8 +295,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8387698bd5b6..eedcbfb9a6ff 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -168,6 +168,10 @@ struct thread_struct { unsigned long srr1; unsigned long dar; unsigned long dsisr; +#ifdef CONFIG_PPC_BOOK3S_32 + unsigned long r0, r3, r4, r5, r6, r8, r9, r11; + unsigned long lr, ctr; +#endif #endif /* Debug Registers */ struct debug_reg debug; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c25e562f1cd9..fcf24a365fc0 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -132,6 +132,18 @@ int main(void) OFFSET(SRR1, thread_struct, srr1); OFFSET(DAR, thread_struct, dar); OFFSET(DSISR, thread_struct, dsisr); +#ifdef CONFIG_PPC_BOOK3S_32 + OFFSET(THR0, thread_struct, r0); + OFFSET(THR3, thread_struct, r3); + OFFSET(THR4, thread_struct, r4); + OFFSET(THR5, thread_struct, r5); + OFFSET(THR6, thread_struct, r6); + OFFSET(THR8, thread_struct, r8); + OFFSET(THR9, thread_struct, r9); + OFFSET(THR11, thread_struct, r11); + OFFSET(THLR, thread_struct, lr); + OFFSET(THCTR, thread_struct, ctr); +#endif #endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index e745abc5457a..245be4fafe13 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2193,11 +2193,13 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, * oprofile_cpu_type already has a value, then we are * possibly overriding a real PVR with a logical one, * and, in that case, keep the current value for - * oprofile_cpu_type. + * oprofile_cpu_type. Futhermore, let's ensure that the + * fix for the PMAO bug is enabled on compatibility mode. */ if (old.oprofile_cpu_type != NULL) { t->oprofile_cpu_type = old.oprofile_cpu_type; t->oprofile_type = old.oprofile_type; + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a1eaffe868de..7b048cee767c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1184,6 +1184,17 @@ void eeh_handle_special_event(void) eeh_pe_state_mark(pe, EEH_PE_RECOVERING); eeh_handle_normal_event(pe); } else { + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) + edev->mode &= ~EEH_DEV_NO_HANDLER; + + /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_pe_report( + "error_detected(permanent failure)", pe, + eeh_report_failure, NULL); + pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -1192,16 +1203,6 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - eeh_for_each_pe(pe, tmp_pe) - eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) - edev->mode &= ~EEH_DEV_NO_HANDLER; - - /* Notify all devices to be down */ - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_pe_report( - "error_detected(permanent failure)", pe, - eeh_report_failure, NULL); bus = eeh_pe_bus_get(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0713daa651d9..16af0d8d90a8 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -783,7 +783,7 @@ fast_exception_return: 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 bge 2b #else bge 3f @@ -791,7 +791,7 @@ fast_exception_return: lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 blt 2b #else blt 3f @@ -1354,12 +1354,17 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 RFI -1: tophys(r9,r1) +1: tophys_novmstack r9, r1 +#ifdef CONFIG_VMAP_STACK + li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */ + mtmsr r0 + isync +#endif lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */ lwz r9,8(r9) /* original msr value */ addi r1,r1,INT_FRAME_SIZE li r0,0 - tophys(r7, r2) + tophys_novmstack r7, r2 stw r0, THREAD + RTAS_SP(r7) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 0493fcac6409..97c887950c3c 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -290,17 +290,55 @@ MachineCheck: 7: EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_CHRP - bne cr1,1f +#ifdef CONFIG_VMAP_STACK + mfspr r4, SPRN_SPRG_THREAD + tovirt(r4, r4) + lwz r4, RTAS_SP(r4) + cmpwi cr1, r4, 0 #endif - EXC_XFER_STD(0x200, machine_check_exception) -#ifdef CONFIG_PPC_CHRP -1: b machine_check_in_rtas + beq cr1, machine_check_tramp + b machine_check_in_rtas +#else + b machine_check_tramp #endif /* Data access exception. */ . = 0x300 DO_KVM 0x300 DataAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mfspr r10, SPRN_SPRG_THREAD +BEGIN_MMU_FTR_SECTION + stw r11, THR11(r10) + mfspr r10, SPRN_DSISR + mfcr r11 +#ifdef CONFIG_PPC_KUAP + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h +#else + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h +#endif + mfspr r10, SPRN_SPRG_THREAD + beq hash_page_dsi +.Lhash_page_dsi_cont: + mtcr r11 + lwz r11, THR11(r10) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r11, SPRN_DAR + stw r11, DAR(r10) + mfspr r11, SPRN_DSISR + stw r11, DSISR(r10) + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + b handle_page_fault_tramp_1 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 BEGIN_MMU_FTR_SECTION @@ -316,11 +354,32 @@ BEGIN_MMU_FTR_SECTION FTR_SECTION_ELSE b handle_page_fault_tramp_2 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ /* Instruction access exception. */ . = 0x400 DO_KVM 0x400 InstructionAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r10, SPRN_SPRG_THREAD + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 +BEGIN_MMU_FTR_SECTION + andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */ + bne hash_page_isi +.Lhash_page_isi_cont: + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */ beq 1f /* if so, try to put a PTE */ @@ -329,6 +388,7 @@ InstructionAccess: BEGIN_MMU_FTR_SECTION bl hash_page END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ stw r4, _DAR(r11) @@ -344,7 +404,7 @@ Alignment: EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x600, alignment_exception) + b alignment_exception_tramp /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) @@ -645,15 +705,100 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) . = 0x3000 +machine_check_tramp: + EXC_XFER_STD(0x200, machine_check_exception) + +alignment_exception_tramp: + EXC_XFER_STD(0x600, alignment_exception) + handle_page_fault_tramp_1: +#ifdef CONFIG_VMAP_STACK + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 +#endif lwz r4, _DAR(r11) lwz r5, _DSISR(r11) /* fall through */ handle_page_fault_tramp_2: EXC_XFER_LITE(0x300, handle_page_fault) +#ifdef CONFIG_VMAP_STACK +.macro save_regs_thread thread + stw r0, THR0(\thread) + stw r3, THR3(\thread) + stw r4, THR4(\thread) + stw r5, THR5(\thread) + stw r6, THR6(\thread) + stw r8, THR8(\thread) + stw r9, THR9(\thread) + mflr r0 + stw r0, THLR(\thread) + mfctr r0 + stw r0, THCTR(\thread) +.endm + +.macro restore_regs_thread thread + lwz r0, THLR(\thread) + mtlr r0 + lwz r0, THCTR(\thread) + mtctr r0 + lwz r0, THR0(\thread) + lwz r3, THR3(\thread) + lwz r4, THR4(\thread) + lwz r5, THR5(\thread) + lwz r6, THR6(\thread) + lwz r8, THR8(\thread) + lwz r9, THR9(\thread) +.endm + +hash_page_dsi: + save_regs_thread r10 + mfdsisr r3 + mfdar r4 + mfsrr0 r5 + mfsrr1 r9 + rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */ + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + b .Lhash_page_dsi_cont + +hash_page_isi: + mr r11, r10 + mfspr r10, SPRN_SPRG_THREAD + save_regs_thread r10 + li r3, 0 + lwz r4, SRR0(r10) + lwz r9, SRR1(r10) + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + mr r10, r11 + b .Lhash_page_isi_cont + + .globl fast_hash_page_return +fast_hash_page_return: + andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */ + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + bne 1f + + /* DSI */ + mtcr r11 + lwz r11, THR11(r10) + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + +1: /* ISI */ + mtcr r11 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + stack_overflow: vmap_stack_overflow_exception +#endif AltiVecUnavailable: EXCEPTION_PROLOG diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index a6a5fbbf8504..9db162f79fe6 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -64,11 +64,25 @@ .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mtcr r10 +FTR_SECTION_ELSE + stw r10, _CCR(r11) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#else stw r10,_CCR(r11) /* save registers */ +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 stw r12,GPR12(r11) stw r9,GPR9(r11) - mfspr r10,SPRN_SPRG_SCRATCH0 stw r10,GPR10(r11) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mfcr r10 + stw r10, _CCR(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) mflr r10 @@ -83,6 +97,11 @@ stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + andi. r10, r9, MSR_PR +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9922306ae512..073a651787df 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -256,7 +256,7 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 2462cd7c565c..d0854320bb50 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -331,11 +331,13 @@ int hw_breakpoint_handler(struct die_args *args) } info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (!dar_within_range(regs->dar, info)) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - - if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info)) - goto out; + if (IS_ENABLED(CONFIG_PPC_8xx)) { + if (!dar_within_range(regs->dar, info)) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + } else { + if (!stepping_handler(regs, bp, info)) + goto out; + } /* * As a policy, the callback is invoked in a 'trigger-after-execute' diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 0ffdd18b9f26..433d97bea1f3 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -166,7 +166,11 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_HID0 andis. r9,r9,HID0_NAP@h beq 1f +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_msscr0@ha +#else addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha +#endif lwz r9,nap_save_msscr0@l(r9) mtspr SPRN_MSSCR0, r9 sync @@ -174,7 +178,11 @@ BEGIN_FTR_SECTION 1: END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) BEGIN_FTR_SECTION +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_hid1@ha +#else addis r9,r11,(nap_save_hid1-KERNELBASE)@ha +#endif lwz r9,nap_save_hid1@l(r9) mtspr SPRN_HID1, r9 END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e6c30cee6abf..d215f9554553 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk) * normal/non-checkpointed stack pointer. */ + unsigned long ret = tsk->thread.regs->gpr[1]; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BUG_ON(tsk != current); if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { + preempt_disable(); tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) - return tsk->thread.ckpt_regs.gpr[1]; + ret = tsk->thread.ckpt_regs.gpr[1]; + + /* + * If we treclaim, we must clear the current thread's TM bits + * before re-enabling preemption. Otherwise we might be + * preempted and have the live MSR[TS] changed behind our back + * (tm_recheckpoint_new_task() would recheckpoint). Besides, we + * enter the signal handler in non-transactional state. + */ + tsk->thread.regs->msr &= ~MSR_TS_MASK; + preempt_enable(); } #endif - return tsk->thread.regs->gpr[1]; + return ret; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 98600b276f76..1b090a76b444 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, */ static int save_tm_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int sigret) + struct mcontext __user *tm_frame, int sigret, + unsigned long msr) { - unsigned long msr = regs->msr; - WARN_ON(tm_suspend_disabled); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; - if (save_tm_user_regs(regs, frame, tm_frame, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr)) goto badframe; } else @@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_mctx = &frame->mctx_transact; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, - sigret)) + sigret, msr)) goto badframe; } else diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 117515564ec7..84ed2e77ef9c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, struct task_struct *tsk, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + unsigned long msr) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); - BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + BUG_ON(!MSR_TM_ACTIVE(msr)); WARN_ON(tm_suspend_disabled); @@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); @@ -824,6 +817,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsigned long newsp = 0; long err = 0; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -841,7 +838,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= __put_user(0, &frame->uc.uc_flags); err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { /* The ucontext_t passed to userland points to the second * ucontext_t (for transactional state) with its uc_link ptr. */ @@ -849,7 +846,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, tsk, ksig->sig, NULL, - (unsigned long)ksig->ka.sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler, + msr); } else #endif { diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b4c89a1acebb..a32d478a7f41 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -303,6 +303,12 @@ SECTIONS *(.branch_lt) } +#ifdef CONFIG_DEBUG_INFO_BTF + .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { + *(.BTF) + } +#endif + .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 04a7cba58eff..b4184092172a 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -212,7 +212,7 @@ static void wake_offline_cpus(void) if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", cpu); - WARN_ON(cpu_up(cpu)); + WARN_ON(add_cpu(cpu)); } } } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 729a0f12a752..db3a87319642 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1817,6 +1817,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + kvmppc_mmu_destroy_pr(vcpu); free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kfree(vcpu->arch.shadow_vcpu); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1af96fb5dc6f..302e9dccdd6d 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -759,7 +759,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) return 0; out_vcpu_uninit: - kvmppc_mmu_destroy(vcpu); kvmppc_subarch_vcpu_uninit(vcpu); return err; } @@ -792,7 +791,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmppc_core_vcpu_free(vcpu); - kvmppc_mmu_destroy(vcpu); kvmppc_subarch_vcpu_uninit(vcpu); } diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index c11b0a005196..2015c4f96238 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -25,12 +25,6 @@ #include <asm/feature-fixups.h> #include <asm/code-patching-asm.h> -#ifdef CONFIG_VMAP_STACK -#define ADDR_OFFSET 0 -#else -#define ADDR_OFFSET PAGE_OFFSET -#endif - #ifdef CONFIG_SMP .section .bss .align 2 @@ -53,8 +47,8 @@ mmu_hash_lock: .text _GLOBAL(hash_page) #ifdef CONFIG_SMP - lis r8, (mmu_hash_lock - ADDR_OFFSET)@h - ori r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l + lis r8, (mmu_hash_lock - PAGE_OFFSET)@h + ori r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l lis r0,0x0fff b 10f 11: lwz r6,0(r8) @@ -72,12 +66,9 @@ _GLOBAL(hash_page) cmplw 0,r4,r0 ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */ -#ifdef CONFIG_VMAP_STACK - tovirt(r5, r5) -#endif blt+ 112f /* assume user more likely */ - lis r5, (swapper_pg_dir - ADDR_OFFSET)@ha /* if kernel address, use */ - addi r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l /* kernel page table */ + lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ + addi r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */ 112: #ifndef CONFIG_PTE_64BIT @@ -89,9 +80,6 @@ _GLOBAL(hash_page) lwzx r8,r8,r5 /* Get L1 entry */ rlwinm. r8,r8,0,0,20 /* extract pt base address */ #endif -#ifdef CONFIG_VMAP_STACK - tovirt(r8, r8) -#endif #ifdef CONFIG_SMP beq- hash_page_out /* return if no mapping */ #else @@ -143,30 +131,36 @@ retry: bne- retry /* retry if someone got there first */ mfsrin r3,r4 /* get segment reg for segment */ +#ifndef CONFIG_VMAP_STACK mfctr r0 stw r0,_CTR(r11) +#endif bl create_hpte /* add the hash table entry */ #ifdef CONFIG_SMP eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) #endif +#ifdef CONFIG_VMAP_STACK + b fast_hash_page_return +#else /* Return from the exception */ lwz r5,_CTR(r11) mtctr r5 lwz r0,GPR0(r11) lwz r8,GPR8(r11) b fast_exception_return +#endif #ifdef CONFIG_SMP hash_page_out: eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) blr #endif /* CONFIG_SMP */ @@ -341,7 +335,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) patch_site 1f, patch__hash_page_A1 patch_site 2f, patch__hash_page_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -0: lis r0, (Hash_base - ADDR_OFFSET)@h /* base address of hash table */ +0: lis r0, (Hash_base - PAGE_OFFSET)@h /* base address of hash table */ 1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ 2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r3,r3,r0 /* make primary hash */ @@ -355,10 +349,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ 10f /* no PTE: go look for an empty slot */ tlbie r4 - lis r4, (htab_hash_searches - ADDR_OFFSET)@ha - lwz r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + lis r4, (htab_hash_searches - PAGE_OFFSET)@ha + lwz r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) addi r6,r6,1 /* count how many searches we do */ - stw r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + stw r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) /* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */ mtctr r0 @@ -390,10 +384,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ found_empty /* update counter of times that the primary PTEG is full */ - lis r4, (primary_pteg_full - ADDR_OFFSET)@ha - lwz r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + lis r4, (primary_pteg_full - PAGE_OFFSET)@ha + lwz r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) addi r6,r6,1 - stw r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + stw r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) patch_site 0f, patch__hash_page_C /* Search the secondary PTEG for an empty slot */ @@ -427,8 +421,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) * lockup here but that shouldn't happen */ -1: lis r4, (next_slot - ADDR_OFFSET)@ha /* get next evict slot */ - lwz r6, (next_slot - ADDR_OFFSET)@l(r4) +1: lis r4, (next_slot - PAGE_OFFSET)@ha /* get next evict slot */ + lwz r6, (next_slot - PAGE_OFFSET)@l(r4) addi r6,r6,HPTE_SIZE /* search for candidate */ andi. r6,r6,7*HPTE_SIZE stw r6,next_slot@l(r4) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 0a1c65a2c565..f888cbb109b9 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -413,7 +413,7 @@ void __init MMU_init_hw(void) void __init MMU_init_hw_patch(void) { unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); - unsigned int hash; + unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); @@ -425,11 +425,6 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:create_hpte */ - if (IS_ENABLED(CONFIG_VMAP_STACK)) - hash = (unsigned int)Hash; - else - hash = (unsigned int)Hash - PAGE_OFFSET; - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6); @@ -439,8 +434,7 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:flush_hash_page */ - modify_instruction_site(&patch__flush_hash_A0, 0xffff, - ((unsigned int)Hash - PAGE_OFFSET) >> 16); + modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6); modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 73d4873fc7f8..33b3461d91e8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,20 +53,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (pshift >= pdshift) { cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + new = NULL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); + cachep = NULL; num_hugepd = 1; + new = pte_alloc_one(mm); } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; + new = NULL; } - if (!cachep) { + if (!cachep && !new) { WARN_ONCE(1, "No page table cache created for hugetlb tables"); return -ENOMEM; } - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + if (cachep) + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -97,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (i < num_hugepd) { for (i = i - 1 ; i >= 0; i--, hpdp--) *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); + if (cachep) + kmem_cache_free(cachep, new); + else + pte_free(mm, new); } else { kmemleak_ignore(new); } @@ -324,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); + pgtable_free_tlb(tlb, hugepte, 0); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -639,12 +645,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) + if (pdshift > shift) { + if (!IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(pdshift - shift); + } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); + } configured = true; } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 16dd95bd0749..d2bed3fcb719 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -120,12 +120,6 @@ static void __init kasan_unmap_early_shadow_vmalloc(void) unsigned long k_cur; phys_addr_t pa = __pa(kasan_early_shadow_page); - if (!early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { - int ret = kasan_init_shadow_page_tables(k_start, k_end); - - if (ret) - panic("kasan: kasan_init_shadow_page_tables() failed"); - } for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur); pte_t *ptep = pte_offset_kernel(pmd, k_cur); @@ -143,7 +137,8 @@ void __init kasan_mmu_init(void) int ret; struct memblock_region *reg; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || + IS_ENABLED(CONFIG_KASAN_VMALLOC)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -185,8 +180,7 @@ u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; static void __init kasan_early_hash_table(void) { - unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash : - __pa(early_hash); + unsigned int hash = __pa(early_hash); modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index ef7b1119b2e2..1c07d5a3f543 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -373,7 +373,9 @@ static inline bool flush_coherent_icache(unsigned long addr) */ if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { mb(); /* sync */ + allow_read_from_user((const void __user *)addr, L1_CACHE_BYTES); icbi((void *)addr); + prevent_read_from_user((const void __user *)addr, L1_CACHE_BYTES); mb(); /* sync */ isync(); return true; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 3086055bf681..3dcfecf858f3 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -518,6 +518,7 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events * } } cpuhw->bhrb_stack.nr = u_index; + cpuhw->bhrb_stack.hw_idx = -1ULL; return; } diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index 2735ec90414d..e87360a0fb40 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/reboot.h> +#include <linux/rcuwait.h> #include <asm/firmware.h> #include <asm/lv1call.h> @@ -670,7 +671,8 @@ struct ps3_notification_device { spinlock_t lock; u64 tag; u64 lv1_status; - struct completion done; + struct rcuwait wait; + bool done; }; enum ps3_notify_type { @@ -712,7 +714,8 @@ static irqreturn_t ps3_notification_interrupt(int irq, void *data) pr_debug("%s:%u: completed, status 0x%llx\n", __func__, __LINE__, status); dev->lv1_status = status; - complete(&dev->done); + dev->done = true; + rcuwait_wake_up(&dev->wait); } spin_unlock(&dev->lock); return IRQ_HANDLED; @@ -725,12 +728,12 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev, unsigned long flags; int res; - init_completion(&dev->done); spin_lock_irqsave(&dev->lock, flags); res = write ? lv1_storage_write(dev->sbd.dev_id, 0, 0, 1, 0, lpar, &dev->tag) : lv1_storage_read(dev->sbd.dev_id, 0, 0, 1, 0, lpar, &dev->tag); + dev->done = false; spin_unlock_irqrestore(&dev->lock, flags); if (res) { pr_err("%s:%u: %s failed %d\n", __func__, __LINE__, op, res); @@ -738,14 +741,10 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev, } pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); - res = wait_event_interruptible(dev->done.wait, - dev->done.done || kthread_should_stop()); + rcuwait_wait_event(&dev->wait, dev->done || kthread_should_stop(), TASK_IDLE); + if (kthread_should_stop()) res = -EINTR; - if (res) { - pr_debug("%s:%u: interrupted %s\n", __func__, __LINE__, op); - return res; - } if (dev->lv1_status) { pr_err("%s:%u: %s not completed, status 0x%llx\n", __func__, @@ -810,6 +809,7 @@ static int ps3_probe_thread(void *data) } spin_lock_init(&dev.lock); + rcuwait_init(&dev.wait); res = request_irq(irq, ps3_notification_interrupt, 0, "ps3_notification", &dev); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e8c84d265602..0ec9640335bb 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3435,6 +3435,11 @@ getstring(char *s, int size) int c; c = skipbl(); + if (c == '\n') { + *s = 0; + return; + } + do { if( size > 1 ){ *s++ = c; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 73f029eae0cc..cd5db57bfd41 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -50,7 +50,6 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_TIMER - select UACCESS_MEMCPY if !MMU select GENERIC_IRQ_MULTI_HANDLER select GENERIC_ARCH_TOPOLOGY if SMP select ARCH_HAS_PTE_SPECIAL @@ -121,6 +120,7 @@ config ARCH_FLATMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool y + depends on MMU select SPARSEMEM_VMEMMAP_ENABLE config ARCH_SELECT_MEMORY_MODEL diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index d325b67d00df..a131174a0a77 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -10,4 +10,14 @@ config SOC_SIFIVE help This enables support for SiFive SoC platform hardware. +config SOC_VIRT + bool "QEMU Virt Machine" + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH + select SIFIVE_PLIC + help + This enables support for QEMU Virt Machine. + endmenu diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index b9009a2fbaf5..259cb53d7f20 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -13,8 +13,10 @@ LDFLAGS_vmlinux := ifeq ($(CONFIG_DYNAMIC_FTRACE),y) LDFLAGS_vmlinux := --no-relax endif -KBUILD_AFLAGS_MODULE += -fPIC -KBUILD_CFLAGS_MODULE += -fPIC + +ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy) +KBUILD_CFLAGS_MODULE += -mcmodel=medany +endif export BITS ifeq ($(CONFIG_ARCH_RV64I),y) diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore index 8dab0bb6ae66..8a45a37d2af4 100644 --- a/arch/riscv/boot/.gitignore +++ b/arch/riscv/boot/.gitignore @@ -1,2 +1,4 @@ Image Image.gz +loader +loader.lds diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 609198cb1163..4a2729f5ca3f 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -2,6 +2,7 @@ /* Copyright (c) 2018-2019 SiFive, Inc */ #include "fu540-c000.dtsi" +#include <dt-bindings/gpio/gpio.h> /* Clock frequency (in Hz) of the PCB crystal for rtcclk */ #define RTCCLK_FREQ 1000000 @@ -41,6 +42,10 @@ clock-frequency = <RTCCLK_FREQ>; clock-output-names = "rtcclk"; }; + gpio-restart { + compatible = "gpio-restart"; + gpios = <&gpio 10 GPIO_ACTIVE_LOW>; + }; }; &uart0 { diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index e2ff95cb3390..2557c5372a25 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -15,6 +15,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y CONFIG_SOC_SIFIVE=y +CONFIG_SOC_VIRT=y CONFIG_SMP=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -63,6 +64,7 @@ CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set +CONFIG_POWER_RESET=y CONFIG_DRM=y CONFIG_DRM_RADEON=y CONFIG_DRM_VIRTIO_GPU=y @@ -78,6 +80,7 @@ CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_MMC=y CONFIG_MMC_SPI=y +CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y @@ -102,13 +105,13 @@ CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_VM=y CONFIG_DEBUG_VM_PGFLAGS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_WQ_WATCHDOG=y -CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index eb519407c841..0292879a9690 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y CONFIG_MODULES=y @@ -61,6 +62,7 @@ CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y # CONFIG_PTP_1588_CLOCK is not set +CONFIG_POWER_RESET=y CONFIG_DRM=y CONFIG_DRM_RADEON=y CONFIG_DRM_VIRTIO_GPU=y @@ -74,13 +76,13 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y CONFIG_RPMSG_VIRTIO=y -CONFIG_SIFIVE_PLIC=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -99,13 +101,13 @@ CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_VM=y CONFIG_DEBUG_VM_PGFLAGS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_WQ_WATCHDOG=y -CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h index 6eaa2eedd694..a279b17a6aad 100644 --- a/arch/riscv/include/asm/clint.h +++ b/arch/riscv/include/asm/clint.h @@ -15,12 +15,12 @@ static inline void clint_send_ipi_single(unsigned long hartid) writel(1, clint_ipi_base + hartid); } -static inline void clint_send_ipi_mask(const struct cpumask *hartid_mask) +static inline void clint_send_ipi_mask(const struct cpumask *mask) { - int hartid; + int cpu; - for_each_cpu(hartid, hartid_mask) - clint_send_ipi_single(hartid); + for_each_cpu(cpu, mask) + clint_send_ipi_single(cpuid_to_hartid_map(cpu)); } static inline void clint_clear_ipi(unsigned long hartid) diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 435b65532e29..8e18d2c64399 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -72,6 +72,16 @@ #define EXC_LOAD_PAGE_FAULT 13 #define EXC_STORE_PAGE_FAULT 15 +/* PMP configuration */ +#define PMP_R 0x01 +#define PMP_W 0x02 +#define PMP_X 0x04 +#define PMP_A 0x18 +#define PMP_A_TOR 0x08 +#define PMP_A_NA4 0x10 +#define PMP_A_NAPOT 0x18 +#define PMP_L 0x80 + /* symbolic CSR names: */ #define CSR_CYCLE 0xc00 #define CSR_TIME 0xc01 @@ -100,6 +110,8 @@ #define CSR_MCAUSE 0x342 #define CSR_MTVAL 0x343 #define CSR_MIP 0x344 +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPADDR0 0x3b0 #define CSR_MHARTID 0xf14 #ifdef CONFIG_RISCV_M_MODE diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fdfaf7f3df7c..1b00badb9f87 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -46,7 +46,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret = 0; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -73,8 +74,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index e43041519edd..393f2014dfee 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -19,6 +19,47 @@ #include <asm/tlbflush.h> #include <linux/mm_types.h> +#ifdef CONFIG_MMU + +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#define VMALLOC_END (PAGE_OFFSET - 1) +#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) + +#define BPF_JIT_REGION_SIZE (SZ_128M) +#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) +#define BPF_JIT_REGION_END (VMALLOC_END) + +/* + * Roughly size the vmemmap space to be large enough to fit enough + * struct pages to map half the virtual address space. Then + * position vmemmap directly below the VMALLOC region. + */ +#define VMEMMAP_SHIFT \ + (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) +#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) +#define VMEMMAP_END (VMALLOC_START - 1) +#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) + +/* + * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel + * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. + */ +#define vmemmap ((struct page *)VMEMMAP_START) + +#define PCI_IO_SIZE SZ_16M +#define PCI_IO_END VMEMMAP_START +#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) + +#define FIXADDR_TOP PCI_IO_START +#ifdef CONFIG_64BIT +#define FIXADDR_SIZE PMD_SIZE +#else +#define FIXADDR_SIZE PGDIR_SIZE +#endif +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + +#endif + #ifdef CONFIG_64BIT #include <asm/pgtable-64.h> #else @@ -90,31 +131,6 @@ extern pgd_t swapper_pg_dir[]; #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC -#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) -#define VMALLOC_END (PAGE_OFFSET - 1) -#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) - -#define BPF_JIT_REGION_SIZE (SZ_128M) -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) -#define BPF_JIT_REGION_END (VMALLOC_END) - -/* - * Roughly size the vmemmap space to be large enough to fit enough - * struct pages to map half the virtual address space. Then - * position vmemmap directly below the VMALLOC region. - */ -#define VMEMMAP_SHIFT \ - (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) -#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) -#define VMEMMAP_END (VMALLOC_START - 1) -#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) - -/* - * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel - * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. - */ -#define vmemmap ((struct page *)VMEMMAP_START) - static inline int pmd_present(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); @@ -432,18 +448,6 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define PCI_IO_SIZE SZ_16M -#define PCI_IO_END VMEMMAP_START -#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) - -#define FIXADDR_TOP PCI_IO_START -#ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE -#else -#define FIXADDR_SIZE PGDIR_SIZE -#endif -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - /* * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32. * Note that PGDIR_SIZE must evenly divide TASK_SIZE. diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 42347d0981e7..49350c8bd7b0 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -28,13 +28,6 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->a7; } -static inline void syscall_set_nr(struct task_struct *task, - struct pt_regs *regs, - int sysno) -{ - regs->a7 = sysno; -} - static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index f462a183a9c2..8ce9d607b53d 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -11,6 +11,24 @@ /* * User space memory access functions */ + +extern unsigned long __must_check __asm_copy_to_user(void __user *to, + const void *from, unsigned long n); +extern unsigned long __must_check __asm_copy_from_user(void *to, + const void __user *from, unsigned long n); + +static inline unsigned long +raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return __asm_copy_from_user(to, from, n); +} + +static inline unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return __asm_copy_to_user(to, from, n); +} + #ifdef CONFIG_MMU #include <linux/errno.h> #include <linux/compiler.h> @@ -367,24 +385,6 @@ do { \ -EFAULT; \ }) - -extern unsigned long __must_check __asm_copy_to_user(void __user *to, - const void *from, unsigned long n); -extern unsigned long __must_check __asm_copy_from_user(void *to, - const void __user *from, unsigned long n); - -static inline unsigned long -raw_copy_from_user(void *to, const void __user *from, unsigned long n) -{ - return __asm_copy_from_user(to, from, n); -} - -static inline unsigned long -raw_copy_to_user(void __user *to, const void *from, unsigned long n) -{ - return __asm_copy_to_user(to, from, n); -} - extern long strncpy_from_user(char *dest, const char __user *src, long count); extern long __must_check strlen_user(const char __user *str); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index bad4d85b5e91..208702d8c18e 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -229,19 +229,12 @@ check_syscall_nr: li t0, __NR_syscalls la s0, sys_ni_syscall /* - * The tracer can change syscall number to valid/invalid value. - * We use syscall_set_nr helper in syscall_trace_enter thus we - * cannot trust the current value in a7 and have to reload from - * the current task pt_regs. - */ - REG_L a7, PT_A7(sp) - /* * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ bge a7, t0, 1f /* - * Check if syscall is rejected by tracer or seccomp, i.e., a7 == -1. + * Check if syscall is rejected by tracer, i.e., a7 == -1. * If yes, we pretend it was executed. */ li t1, -1 @@ -334,6 +327,7 @@ work_resched: handle_syscall_trace_enter: move a0, sp call do_syscall_trace_enter + move t0, a0 REG_L a0, PT_A0(sp) REG_L a1, PT_A1(sp) REG_L a2, PT_A2(sp) @@ -342,6 +336,7 @@ handle_syscall_trace_enter: REG_L a5, PT_A5(sp) REG_L a6, PT_A6(sp) REG_L a7, PT_A7(sp) + bnez t0, ret_from_syscall_rejected j check_syscall_nr handle_syscall_trace_exit: move a0, sp diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 271860fc2c3f..85f2073e7fe4 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -58,6 +58,12 @@ _start_kernel: /* Reset all registers except ra, a0, a1 */ call reset_regs + /* Setup a PMP to permit access to all of memory. */ + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 + /* * The hartid in a0 is expected later on, and we have no firmware * to hand it to us. diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index b7401858d872..8bbe5dbe1341 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -8,6 +8,10 @@ #include <linux/err.h> #include <linux/errno.h> #include <linux/moduleloader.h> +#include <linux/vmalloc.h> +#include <linux/sizes.h> +#include <asm/pgtable.h> +#include <asm/sections.h> static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) { @@ -386,3 +390,15 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, return 0; } + +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) +#define VMALLOC_MODULE_START \ + max(PFN_ALIGN((unsigned long)&_end - SZ_2G), VMALLOC_START) +void *module_alloc(unsigned long size) +{ + return __vmalloc_node_range(size, 1, VMALLOC_MODULE_START, + VMALLOC_END, GFP_KERNEL, + PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 407464201b91..444dc7b0fd78 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -148,21 +148,19 @@ long arch_ptrace(struct task_struct *child, long request, * Allows PTRACE_SYSCALL to work. These are called from entry.S in * {handle,ret_from}_syscall. */ -__visible void do_syscall_trace_enter(struct pt_regs *regs) +__visible int do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) if (tracehook_report_syscall_entry(regs)) - syscall_set_nr(current, regs, -1); + return -1; /* * Do the secure computing after ptrace; failures should be fast. * If this fails we might have return value in a0 from seccomp * (via SECCOMP_RET_ERRNO/TRACE). */ - if (secure_computing() == -1) { - syscall_set_nr(current, regs, -1); - return; - } + if (secure_computing() == -1) + return -1; #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) @@ -170,6 +168,7 @@ __visible void do_syscall_trace_enter(struct pt_regs *regs) #endif audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); + return 0; } __visible void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index eb878abcaaf8..e0a6293093f1 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -96,7 +96,7 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) if (IS_ENABLED(CONFIG_RISCV_SBI)) sbi_send_ipi(cpumask_bits(&hartid_mask)); else - clint_send_ipi_mask(&hartid_mask); + clint_send_ipi_mask(mask); } static void send_ipi_single(int cpu, enum ipi_message_type op) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2..55ea614d89bf 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -156,6 +156,6 @@ void __init trap_init(void) csr_write(CSR_SCRATCH, 0); /* Set the exception vector address */ csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + /* Enable interrupts */ + csr_write(CSR_IE, IE_SIE); } diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 47e7a8204460..0d0db80800c4 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -2,5 +2,5 @@ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o -lib-$(CONFIG_MMU) += uaccess.o +lib-y += uaccess.o lib-$(CONFIG_64BIT) += tishift.o diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 965a8cf4829c..fab855963c73 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -131,7 +131,7 @@ void __init setup_bootmem(void) for_each_memblock(memory, reg) { phys_addr_t end = reg->base + reg->size; - if (reg->base <= vmlinux_end && vmlinux_end <= end) { + if (reg->base <= vmlinux_start && vmlinux_end <= end) { mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); /* diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f0cc86040587..ec0ca90dd900 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -19,18 +19,20 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, - pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)), - __pgprot(_PAGE_TABLE))); + pfn_pmd(PFN_DOWN + (__pa((uintptr_t) kasan_early_shadow_pte)), + __pgprot(_PAGE_TABLE))); for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); /* init for swapper_pg_dir */ pgd = pgd_offset_k(KASAN_SHADOW_START); @@ -38,37 +40,43 @@ asmlinkage void __init kasan_early_init(void) for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); flush_tlb_all(); } static void __init populate(void *start, void *end) { - unsigned long i; + unsigned long i, offset; unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); unsigned long n_pages = (vend - vaddr) / PAGE_SIZE; + unsigned long n_ptes = + ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE; unsigned long n_pmds = - (n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 : - n_pages / PTRS_PER_PTE; + ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD; + + pte_t *pte = + memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + pmd_t *pmd = + memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); pgd_t *pgd = pgd_offset_k(vaddr); - pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE); - pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); for (i = 0; i < n_pages; i++) { phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); - - set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); + set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); } - for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))), + for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE) + set_pmd(&pmd[i], + pfn_pmd(PFN_DOWN(__pa(&pte[offset])), __pgprot(_PAGE_TABLE))); - for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE) - set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))), + for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD) + set_pgd(&pgd[i], + pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); flush_tlb_all(); @@ -81,7 +89,8 @@ void __init kasan_init(void) unsigned long i; kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + (void *)kasan_mem_to_shadow((void *) + VMALLOC_END)); for_each_memblock(memory, reg) { void *start = (void *)__va(reg->base); @@ -90,14 +99,14 @@ void __init kasan_init(void) if (start >= end) break; - populate(kasan_mem_to_shadow(start), - kasan_mem_to_shadow(end)); + populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); }; for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], mk_pte(virt_to_page(kasan_early_shadow_page), - __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED))); + __pgprot(_PAGE_PRESENT | _PAGE_READ | + _PAGE_ACCESSED))); memset(kasan_early_shadow_page, 0, PAGE_SIZE); init_task.kasan_depth = 0; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e0e3a465bbfd..8dfa2cf1f05c 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -146,7 +146,7 @@ all: bzImage #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg... KBUILD_IMAGE := $(boot)/bzImage -install: vmlinux +install: $(Q)$(MAKE) $(build)=$(boot) $@ bzImage: vmlinux diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index e2c47d3a1c89..0ff9261c915e 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -70,7 +70,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE $(obj)/startup.a: $(OBJECTS) FORCE $(call if_changed,ar) -install: $(CONFIGURE) $(obj)/bzImage +install: sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 5d12352545c5..5591243d673e 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -75,7 +75,7 @@ static unsigned long get_random(unsigned long limit) *(unsigned long *) prng.parm_block ^= seed; for (i = 0; i < 16; i++) { cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, - (char *) entropy, (char *) entropy, + (u8 *) entropy, (u8 *) entropy, sizeof(entropy)); memcpy(prng.parm_block, entropy, sizeof(entropy)); } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 2e60c80395ab..0c86ba19fa2b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -474,7 +475,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -684,7 +684,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -748,7 +747,6 @@ CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y @@ -772,9 +770,9 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y +CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y -CONFIG_PANIC_ON_OOPS=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -783,9 +781,20 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_PREEMPT_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y @@ -796,15 +805,6 @@ CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y -CONFIG_IRQSOFF_TRACER=y -CONFIG_PREEMPT_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -814,5 +814,3 @@ CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 25f799849582..6b27d861a9a3 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -470,7 +471,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -677,7 +677,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -739,18 +738,18 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 5e97a4353147..26f9144562c9 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -29,7 +29,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, mm_segment_t old_fs; old_fs = enable_sacf_uaccess(); - pagefault_disable(); switch (op) { case FUTEX_OP_SET: __futex_atomic_op("lr %2,%5\n", @@ -54,7 +53,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, default: ret = -ENOSYS; } - pagefault_enable(); disable_sacf_uaccess(old_fs); if (!ret) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 85e944f04c70..1019efd85b9d 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -42,7 +42,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end); static inline void storage_key_init_range(unsigned long start, unsigned long end) { - if (PAGE_DEFAULT_KEY) + if (PAGE_DEFAULT_KEY != 0) __storage_key_init_range(start, end); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 137a3920ca36..6d7c3b7e9281 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -752,6 +752,12 @@ static inline int pmd_write(pmd_t pmd) return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0; } +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0; +} + static inline int pmd_dirty(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 361ef5eda468..aadb3d0e2adc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -84,7 +84,6 @@ void s390_update_cpu_mhz(void); void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; -extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); extern void __bpon(void); diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 71e3f0146cda..1e3517b0518b 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -201,7 +201,7 @@ struct slib { * @scount: SBAL count * @sflags: whole SBAL flags * @length: length - * @addr: address + * @addr: absolute data address */ struct qdio_buffer_element { u8 eflags; @@ -211,7 +211,7 @@ struct qdio_buffer_element { u8 scount; u8 sflags; u32 length; - void *addr; + u64 addr; } __attribute__ ((packed, aligned(16))); /** @@ -227,7 +227,7 @@ struct qdio_buffer { * @sbal: absolute SBAL address */ struct sl_element { - unsigned long sbal; + u64 sbal; } __attribute__ ((packed)); /** diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d7ff30e45589..c2e6d4ba4e23 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3268,7 +3268,10 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) /* Initial reset is a superset of the normal reset */ kvm_arch_vcpu_ioctl_normal_reset(vcpu); - /* this equals initial cpu reset in pop, but we don't switch to ESA */ + /* + * This equals initial cpu reset in pop, but we don't switch to ESA. + * We do not only reset the internal data, but also ... + */ vcpu->arch.sie_block->gpsw.mask = 0; vcpu->arch.sie_block->gpsw.addr = 0; kvm_s390_set_prefix(vcpu, 0); @@ -3278,6 +3281,19 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; + + /* ... the data in sync regs */ + memset(vcpu->run->s.regs.crs, 0, sizeof(vcpu->run->s.regs.crs)); + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.crs[0] = CR0_INITIAL_MASK; + vcpu->run->s.regs.crs[14] = CR14_INITIAL_MASK; + vcpu->run->psw_addr = 0; + vcpu->run->psw_mask = 0; + vcpu->run->s.regs.todpr = 0; + vcpu->run->s.regs.cputm = 0; + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.pp = 0; + vcpu->run->s.regs.gbea = 1; vcpu->run->s.regs.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index bc61ea18e88d..60716d18ce5a 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -424,7 +424,7 @@ static void zpci_map_resources(struct pci_dev *pdev) if (zpci_use_mio(zdev)) pdev->resource[i].start = - (resource_size_t __force) zdev->bars[i].mio_wb; + (resource_size_t __force) zdev->bars[i].mio_wt; else pdev->resource[i].start = (resource_size_t __force) pci_iomap_range_fh(pdev, i, 0, 0); @@ -531,7 +531,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, flags |= IORESOURCE_MEM_64; if (zpci_use_mio(zdev)) - addr = (unsigned long) zdev->bars[i].mio_wb; + addr = (unsigned long) zdev->bars[i].mio_wt; else addr = ZPCI_ADDR(entry); size = 1UL << zdev->bars[i].size; diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c index 3b6ea2d99013..0305d0b51730 100644 --- a/arch/sh/boards/mach-cayman/irq.c +++ b/arch/sh/boards/mach-cayman/irq.c @@ -40,16 +40,6 @@ static irqreturn_t cayman_interrupt_pci2(int irq, void *dev_id) return IRQ_NONE; } -static struct irqaction cayman_action_smsc = { - .name = "Cayman SMSC Mux", - .handler = cayman_interrupt_smsc, -}; - -static struct irqaction cayman_action_pci2 = { - .name = "Cayman PCI2 Mux", - .handler = cayman_interrupt_pci2, -}; - static void enable_cayman_irq(struct irq_data *data) { unsigned int irq = data->irq; @@ -149,6 +139,10 @@ void init_cayman_irq(void) } /* Setup the SMSC interrupt */ - setup_irq(SMSC_IRQ, &cayman_action_smsc); - setup_irq(PCI2_IRQ, &cayman_action_pci2); + if (request_irq(SMSC_IRQ, cayman_interrupt_smsc, 0, "Cayman SMSC Mux", + NULL)) + pr_err("Failed to register Cayman SMSC Mux interrupt\n"); + if (request_irq(PCI2_IRQ, cayman_interrupt_pci2, 0, "Cayman PCI2 Mux", + NULL)) + pr_err("Failed to register Cayman PCI2 Mux interrupt\n"); } diff --git a/arch/sh/drivers/dma/dma-pvr2.c b/arch/sh/drivers/dma/dma-pvr2.c index b5dbd1f75768..21c347543e19 100644 --- a/arch/sh/drivers/dma/dma-pvr2.c +++ b/arch/sh/drivers/dma/dma-pvr2.c @@ -64,11 +64,6 @@ static int pvr2_xfer_dma(struct dma_channel *chan) return 0; } -static struct irqaction pvr2_dma_irq = { - .name = "pvr2 DMA handler", - .handler = pvr2_dma_interrupt, -}; - static struct dma_ops pvr2_dma_ops = { .request = pvr2_request_dma, .get_residue = pvr2_get_dma_residue, @@ -84,7 +79,9 @@ static struct dma_info pvr2_dma_info = { static int __init pvr2_dma_init(void) { - setup_irq(HW_EVENT_PVR2_DMA, &pvr2_dma_irq); + if (request_irq(HW_EVENT_PVR2_DMA, pvr2_dma_interrupt, 0, + "pvr2 DMA handler", NULL)) + pr_err("Failed to register pvr2 DMA handler interrupt\n"); request_dma(PVR2_CASCADE_CHAN, "pvr2 cascade"); return register_dmac(&pvr2_dma_info); diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h index 3190ec89df81..b39cda09fb95 100644 --- a/arch/sh/include/asm/futex.h +++ b/arch/sh/include/asm/futex.h @@ -34,8 +34,6 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 oldval, newval, prev; int ret; - pagefault_disable(); - do { ret = get_user(oldval, uaddr); @@ -67,8 +65,6 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, ret = futex_atomic_cmpxchg_inatomic(&prev, uaddr, oldval, newval); } while (!ret && prev != oldval); - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c1dd6dd642f4..9cc9ab04bd99 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -71,6 +71,7 @@ config SPARC64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_SYSCALL_TRACEPOINTS select HAVE_CONTEXT_TRACKING + select HAVE_TIF_NOHZ select HAVE_DEBUG_KMEMLEAK select IOMMU_HELPER select SPARSE_IRQ diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h index 0865ce77ec00..72de967318d7 100644 --- a/arch/sparc/include/asm/futex_64.h +++ b/arch/sparc/include/asm/futex_64.h @@ -38,8 +38,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, if (unlikely((((unsigned long) uaddr) & 0x3UL))) return -EINVAL; - pagefault_disable(); - switch (op) { case FUTEX_OP_SET: __futex_cas_op("mov\t%4, %1", ret, oldval, uaddr, oparg); @@ -60,8 +58,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index bbf59b3b4af8..75232cbd58bf 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -555,7 +555,7 @@ static int dr_cpu_configure(struct ds_info *dp, struct ds_cap_state *cp, printk(KERN_INFO "ds-%llu: Starting cpu %d...\n", dp->id, cpu); - err = cpu_up(cpu); + err = add_cpu(cpu); if (err) { __u32 res = DR_CPU_RES_FAILURE; __u32 stat = DR_CPU_STAT_UNCONFIGURED; @@ -611,7 +611,7 @@ static int dr_cpu_unconfigure(struct ds_info *dp, printk(KERN_INFO "ds-%llu: Shutting down cpu %d...\n", dp->id, cpu); - err = cpu_down(cpu); + err = remove_cpu(cpu); if (err) dr_cpu_mark(resp, cpu, ncpus, DR_CPU_RES_FAILURE, diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h index 3ca74e1cde7d..bd4e7c332f85 100644 --- a/arch/unicore32/include/asm/io.h +++ b/arch/unicore32/include/asm/io.h @@ -27,7 +27,7 @@ extern void __uc32_iounmap(volatile void __iomem *addr); * ioremap and friends. * * ioremap takes a PCI memory address, as specified in - * Documentation/io-mapping.txt. + * Documentation/driver-api/io-mapping.rst. * */ #define ioremap(cookie, size) __uc32_ioremap(cookie, size) diff --git a/arch/unicore32/kernel/time.c b/arch/unicore32/kernel/time.c index 8b217a761bf0..c3a37edf4d40 100644 --- a/arch/unicore32/kernel/time.c +++ b/arch/unicore32/kernel/time.c @@ -72,13 +72,6 @@ static struct clocksource cksrc_puv3_oscr = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static struct irqaction puv3_timer_irq = { - .name = "ost0", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = puv3_ost0_interrupt, - .dev_id = &ckevt_puv3_osmr0, -}; - void __init time_init(void) { writel(0, OST_OIER); /* disable any timer interrupts */ @@ -94,7 +87,9 @@ void __init time_init(void) ckevt_puv3_osmr0.min_delta_ticks = MIN_OSCR_DELTA * 2; ckevt_puv3_osmr0.cpumask = cpumask_of(0); - setup_irq(IRQ_TIMER0, &puv3_timer_irq); + if (request_irq(IRQ_TIMER0, puv3_ost0_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, "ost0", &ckevt_puv3_osmr0)) + pr_err("Failed to register ost0 interrupt\n"); clocksource_register_hz(&cksrc_puv3_oscr, CLOCK_TICK_RATE); clockevents_register_device(&ckevt_puv3_osmr0); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8b995db3d10f..e2e326a96788 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -127,6 +127,7 @@ config X86 select GENERIC_GETTIMEOFDAY select GENERIC_VDSO_TIME_NS select GUP_GET_PTE_LOW_HIGH if X86_PAE + select HARDIRQS_SW_RESEND select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI @@ -1874,7 +1875,6 @@ config X86_SMAP config X86_UMIP def_bool y - depends on CPU_SUP_INTEL || CPU_SUP_AMD prompt "User Mode Instruction Prevention" if EXPERT ---help--- User Mode Instruction Prevention (UMIP) is a security feature in diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94df0868804b..513a55562d75 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -194,9 +194,10 @@ avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) +adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 012b82fc8617..ef9e1f2c836c 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -88,7 +88,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 26050ae0b27e..e51879bdc51c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -87,10 +87,7 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o -$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone - -vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o \ - $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o # The compressed kernel is built with -fPIC/-fPIE so that a boot loader diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c deleted file mode 100644 index 287393d725f0..000000000000 --- a/arch/x86/boot/compressed/eboot.c +++ /dev/null @@ -1,889 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -/* ----------------------------------------------------------------------- - * - * Copyright 2011 Intel Corporation; author Matt Fleming - * - * ----------------------------------------------------------------------- */ - -#pragma GCC visibility push(hidden) - -#include <linux/efi.h> -#include <linux/pci.h> - -#include <asm/efi.h> -#include <asm/e820/types.h> -#include <asm/setup.h> -#include <asm/desc.h> -#include <asm/boot.h> - -#include "../string.h" -#include "eboot.h" - -static efi_system_table_t *sys_table; -extern const bool efi_is64; - -__pure efi_system_table_t *efi_system_table(void) -{ - return sys_table; -} - -__attribute_const__ bool efi_is_64bit(void) -{ - if (IS_ENABLED(CONFIG_EFI_MIXED)) - return efi_is64; - return IS_ENABLED(CONFIG_X86_64); -} - -static efi_status_t -preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) -{ - struct pci_setup_rom *rom = NULL; - efi_status_t status; - unsigned long size; - uint64_t romsize; - void *romimage; - - /* - * Some firmware images contain EFI function pointers at the place where - * the romimage and romsize fields are supposed to be. Typically the EFI - * code is mapped at high addresses, translating to an unrealistically - * large romsize. The UEFI spec limits the size of option ROMs to 16 - * MiB so we reject any ROMs over 16 MiB in size to catch this. - */ - romimage = efi_table_attr(pci, romimage); - romsize = efi_table_attr(pci, romsize); - if (!romimage || !romsize || romsize > SZ_16M) - return EFI_INVALID_PARAMETER; - - size = romsize + sizeof(*rom); - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&rom); - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate memory for 'rom'\n"); - return status; - } - - memset(rom, 0, sizeof(*rom)); - - rom->data.type = SETUP_PCI; - rom->data.len = size - sizeof(struct setup_data); - rom->data.next = 0; - rom->pcilen = pci->romsize; - *__rom = rom; - - status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, - PCI_VENDOR_ID, 1, &rom->vendor); - - if (status != EFI_SUCCESS) { - efi_printk("Failed to read rom->vendor\n"); - goto free_struct; - } - - status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, - PCI_DEVICE_ID, 1, &rom->devid); - - if (status != EFI_SUCCESS) { - efi_printk("Failed to read rom->devid\n"); - goto free_struct; - } - - status = efi_call_proto(pci, get_location, &rom->segment, &rom->bus, - &rom->device, &rom->function); - - if (status != EFI_SUCCESS) - goto free_struct; - - memcpy(rom->romdata, romimage, romsize); - return status; - -free_struct: - efi_bs_call(free_pool, rom); - return status; -} - -/* - * There's no way to return an informative status from this function, - * because any analysis (and printing of error messages) needs to be - * done directly at the EFI function call-site. - * - * For example, EFI_INVALID_PARAMETER could indicate a bug or maybe we - * just didn't find any PCI devices, but there's no way to tell outside - * the context of the call. - */ -static void setup_efi_pci(struct boot_params *params) -{ - efi_status_t status; - void **pci_handle = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - unsigned long size = 0; - struct setup_data *data; - efi_handle_t h; - int i; - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); - - if (status == EFI_BUFFER_TOO_SMALL) { - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&pci_handle); - - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate memory for 'pci_handle'\n"); - return; - } - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); - } - - if (status != EFI_SUCCESS) - goto free_handle; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - for_each_efi_handle(h, pci_handle, size, i) { - efi_pci_io_protocol_t *pci = NULL; - struct pci_setup_rom *rom; - - status = efi_bs_call(handle_protocol, h, &pci_proto, - (void **)&pci); - if (status != EFI_SUCCESS || !pci) - continue; - - status = preserve_pci_rom_image(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - } - -free_handle: - efi_bs_call(free_pool, pci_handle); -} - -static void retrieve_apple_device_properties(struct boot_params *boot_params) -{ - efi_guid_t guid = APPLE_PROPERTIES_PROTOCOL_GUID; - struct setup_data *data, *new; - efi_status_t status; - u32 size = 0; - apple_properties_protocol_t *p; - - status = efi_bs_call(locate_protocol, &guid, NULL, (void **)&p); - if (status != EFI_SUCCESS) - return; - - if (efi_table_attr(p, version) != 0x10000) { - efi_printk("Unsupported properties proto version\n"); - return; - } - - efi_call_proto(p, get_all, NULL, &size); - if (!size) - return; - - do { - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, - size + sizeof(struct setup_data), - (void **)&new); - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate memory for 'properties'\n"); - return; - } - - status = efi_call_proto(p, get_all, new->data, &size); - - if (status == EFI_BUFFER_TOO_SMALL) - efi_bs_call(free_pool, new); - } while (status == EFI_BUFFER_TOO_SMALL); - - new->type = SETUP_APPLE_PROPERTIES; - new->len = size; - new->next = 0; - - data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; - if (!data) { - boot_params->hdr.setup_data = (unsigned long)new; - } else { - while (data->next) - data = (struct setup_data *)(unsigned long)data->next; - data->next = (unsigned long)new; - } -} - -static const efi_char16_t apple[] = L"Apple"; - -static void setup_quirks(struct boot_params *boot_params) -{ - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table(), fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } -} - -/* - * See if we have Universal Graphics Adapter (UGA) protocol - */ -static efi_status_t -setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) -{ - efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - efi_uga_draw_protocol_t *uga = NULL, *first_uga; - efi_handle_t handle; - int i; - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&uga_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - height = 0; - width = 0; - - first_uga = NULL; - for_each_efi_handle(handle, uga_handle, size, i) { - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 w, h, depth, refresh; - void *pciio; - - status = efi_bs_call(handle_protocol, handle, uga_proto, - (void **)&uga); - if (status != EFI_SUCCESS) - continue; - - pciio = NULL; - efi_bs_call(handle_protocol, handle, &pciio_proto, &pciio); - - status = efi_call_proto(uga, get_mode, &w, &h, &depth, &refresh); - if (status == EFI_SUCCESS && (!first_uga || pciio)) { - width = w; - height = h; - - /* - * Once we've found a UGA supporting PCIIO, - * don't bother looking any further. - */ - if (pciio) - break; - - first_uga = uga; - } - } - - if (!width && !height) - goto free_handle; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_depth = 32; - si->lfb_width = width; - si->lfb_height = height; - - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; - -free_handle: - efi_bs_call(free_pool, uga_handle); - - return status; -} - -void setup_graphics(struct boot_params *boot_params) -{ - efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID; - struct screen_info *si; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; - efi_status_t status; - unsigned long size; - void **gop_handle = NULL; - void **uga_handle = NULL; - - si = &boot_params->screen_info; - memset(si, 0, sizeof(*si)); - - size = 0; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &graphics_proto, NULL, &size, gop_handle); - if (status == EFI_BUFFER_TOO_SMALL) - status = efi_setup_gop(si, &graphics_proto, size); - - if (status != EFI_SUCCESS) { - size = 0; - status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, - &uga_proto, NULL, &size, uga_handle); - if (status == EFI_BUFFER_TOO_SMALL) - setup_uga(si, &uga_proto, size); - } -} - -void startup_32(struct boot_params *boot_params); - -void __noreturn efi_stub_entry(efi_handle_t handle, - efi_system_table_t *sys_table_arg, - struct boot_params *boot_params); - -/* - * Because the x86 boot code expects to be passed a boot_params we - * need to create one ourselves (usually the bootloader would create - * one for us). - */ -efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, - efi_system_table_t *sys_table_arg) -{ - struct boot_params *boot_params; - struct apm_bios_info *bi; - struct setup_header *hdr; - efi_loaded_image_t *image; - efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; - int options_size = 0; - efi_status_t status; - char *cmdline_ptr; - unsigned long ramdisk_addr; - unsigned long ramdisk_size; - - sys_table = sys_table_arg; - - /* Check if we were booted by the EFI firmware */ - if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) - return EFI_INVALID_PARAMETER; - - status = efi_bs_call(handle_protocol, handle, &proto, (void *)&image); - if (status != EFI_SUCCESS) { - efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); - return status; - } - - status = efi_low_alloc(0x4000, 1, (unsigned long *)&boot_params); - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate lowmem for boot params\n"); - return status; - } - - memset(boot_params, 0x0, 0x4000); - - hdr = &boot_params->hdr; - bi = &boot_params->apm_bios_info; - - /* Copy the second sector to boot_params */ - memcpy(&hdr->jump, image->image_base + 512, 512); - - /* - * Fill out some of the header fields ourselves because the - * EFI firmware loader doesn't load the first sector. - */ - hdr->root_flags = 1; - hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; - - hdr->type_of_loader = 0x21; - - /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline(image, &options_size); - if (!cmdline_ptr) - goto fail; - - hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; - /* Fill in upper bits of command line address, NOP on 32 bit */ - boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32; - - hdr->ramdisk_image = 0; - hdr->ramdisk_size = 0; - - /* Clear APM BIOS info */ - memset(bi, 0, sizeof(*bi)); - - status = efi_parse_options(cmdline_ptr); - if (status != EFI_SUCCESS) - goto fail2; - - status = handle_cmdline_files(image, - (char *)(unsigned long)hdr->cmd_line_ptr, - "initrd=", hdr->initrd_addr_max, - &ramdisk_addr, &ramdisk_size); - - if (status != EFI_SUCCESS && - hdr->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G) { - efi_printk("Trying to load files to higher address\n"); - status = handle_cmdline_files(image, - (char *)(unsigned long)hdr->cmd_line_ptr, - "initrd=", -1UL, - &ramdisk_addr, &ramdisk_size); - } - - if (status != EFI_SUCCESS) - goto fail2; - hdr->ramdisk_image = ramdisk_addr & 0xffffffff; - hdr->ramdisk_size = ramdisk_size & 0xffffffff; - boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32; - boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; - - hdr->code32_start = (u32)(unsigned long)startup_32; - - efi_stub_entry(handle, sys_table, boot_params); - /* not reached */ - -fail2: - efi_free(options_size, hdr->cmd_line_ptr); -fail: - efi_free(0x4000, (unsigned long)boot_params); - - return status; -} - -static void add_e820ext(struct boot_params *params, - struct setup_data *e820ext, u32 nr_entries) -{ - struct setup_data *data; - - e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct boot_e820_entry); - e820ext->next = 0; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - if (data) - data->next = (unsigned long)e820ext; - else - params->hdr.setup_data = (unsigned long)e820ext; -} - -static efi_status_t -setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) -{ - struct boot_e820_entry *entry = params->e820_table; - struct efi_info *efi = ¶ms->efi_info; - struct boot_e820_entry *prev = NULL; - u32 nr_entries; - u32 nr_desc; - int i; - - nr_entries = 0; - nr_desc = efi->efi_memmap_size / efi->efi_memdesc_size; - - for (i = 0; i < nr_desc; i++) { - efi_memory_desc_t *d; - unsigned int e820_type = 0; - unsigned long m = efi->efi_memmap; - -#ifdef CONFIG_X86_64 - m |= (u64)efi->efi_memmap_hi << 32; -#endif - - d = efi_early_memdesc_ptr(m, efi->efi_memdesc_size, i); - switch (d->type) { - case EFI_RESERVED_TYPE: - case EFI_RUNTIME_SERVICES_CODE: - case EFI_RUNTIME_SERVICES_DATA: - case EFI_MEMORY_MAPPED_IO: - case EFI_MEMORY_MAPPED_IO_PORT_SPACE: - case EFI_PAL_CODE: - e820_type = E820_TYPE_RESERVED; - break; - - case EFI_UNUSABLE_MEMORY: - e820_type = E820_TYPE_UNUSABLE; - break; - - case EFI_ACPI_RECLAIM_MEMORY: - e820_type = E820_TYPE_ACPI; - break; - - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: - case EFI_BOOT_SERVICES_CODE: - case EFI_BOOT_SERVICES_DATA: - case EFI_CONVENTIONAL_MEMORY: - if (efi_soft_reserve_enabled() && - (d->attribute & EFI_MEMORY_SP)) - e820_type = E820_TYPE_SOFT_RESERVED; - else - e820_type = E820_TYPE_RAM; - break; - - case EFI_ACPI_MEMORY_NVS: - e820_type = E820_TYPE_NVS; - break; - - case EFI_PERSISTENT_MEMORY: - e820_type = E820_TYPE_PMEM; - break; - - default: - continue; - } - - /* Merge adjacent mappings */ - if (prev && prev->type == e820_type && - (prev->addr + prev->size) == d->phys_addr) { - prev->size += d->num_pages << 12; - continue; - } - - if (nr_entries == ARRAY_SIZE(params->e820_table)) { - u32 need = (nr_desc - i) * sizeof(struct e820_entry) + - sizeof(struct setup_data); - - if (!e820ext || e820ext_size < need) - return EFI_BUFFER_TOO_SMALL; - - /* boot_params map full, switch to e820 extended */ - entry = (struct boot_e820_entry *)e820ext->data; - } - - entry->addr = d->phys_addr; - entry->size = d->num_pages << PAGE_SHIFT; - entry->type = e820_type; - prev = entry++; - nr_entries++; - } - - if (nr_entries > ARRAY_SIZE(params->e820_table)) { - u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_table); - - add_e820ext(params, e820ext, nr_e820ext); - nr_entries -= nr_e820ext; - } - - params->e820_entries = (u8)nr_entries; - - return EFI_SUCCESS; -} - -static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, - u32 *e820ext_size) -{ - efi_status_t status; - unsigned long size; - - size = sizeof(struct setup_data) + - sizeof(struct e820_entry) * nr_desc; - - if (*e820ext) { - efi_bs_call(free_pool, *e820ext); - *e820ext = NULL; - *e820ext_size = 0; - } - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)e820ext); - if (status == EFI_SUCCESS) - *e820ext_size = size; - - return status; -} - -static efi_status_t allocate_e820(struct boot_params *params, - struct setup_data **e820ext, - u32 *e820ext_size) -{ - unsigned long map_size, desc_size, buff_size; - struct efi_boot_memmap boot_map; - efi_memory_desc_t *map; - efi_status_t status; - __u32 nr_desc; - - boot_map.map = ↦ - boot_map.map_size = &map_size; - boot_map.desc_size = &desc_size; - boot_map.desc_ver = NULL; - boot_map.key_ptr = NULL; - boot_map.buff_size = &buff_size; - - status = efi_get_memory_map(&boot_map); - if (status != EFI_SUCCESS) - return status; - - nr_desc = buff_size / desc_size; - - if (nr_desc > ARRAY_SIZE(params->e820_table)) { - u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table); - - status = alloc_e820ext(nr_e820ext, e820ext, e820ext_size); - if (status != EFI_SUCCESS) - return status; - } - - return EFI_SUCCESS; -} - -struct exit_boot_struct { - struct boot_params *boot_params; - struct efi_info *efi; -}; - -static efi_status_t exit_boot_func(struct efi_boot_memmap *map, - void *priv) -{ - const char *signature; - struct exit_boot_struct *p = priv; - - signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE - : EFI32_LOADER_SIGNATURE; - memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - - p->efi->efi_systab = (unsigned long)efi_system_table(); - p->efi->efi_memdesc_size = *map->desc_size; - p->efi->efi_memdesc_version = *map->desc_ver; - p->efi->efi_memmap = (unsigned long)*map->map; - p->efi->efi_memmap_size = *map->map_size; - -#ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)efi_system_table() >> 32; - p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; -#endif - - return EFI_SUCCESS; -} - -static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) -{ - unsigned long map_sz, key, desc_size, buff_size; - efi_memory_desc_t *mem_map; - struct setup_data *e820ext = NULL; - __u32 e820ext_size = 0; - efi_status_t status; - __u32 desc_version; - struct efi_boot_memmap map; - struct exit_boot_struct priv; - - map.map = &mem_map; - map.map_size = &map_sz; - map.desc_size = &desc_size; - map.desc_ver = &desc_version; - map.key_ptr = &key; - map.buff_size = &buff_size; - priv.boot_params = boot_params; - priv.efi = &boot_params->efi_info; - - status = allocate_e820(boot_params, &e820ext, &e820ext_size); - if (status != EFI_SUCCESS) - return status; - - /* Might as well exit boot services now */ - status = efi_exit_boot_services(handle, &map, &priv, exit_boot_func); - if (status != EFI_SUCCESS) - return status; - - /* Historic? */ - boot_params->alt_mem_k = 32 * 1024; - - status = setup_e820(boot_params, e820ext, e820ext_size); - if (status != EFI_SUCCESS) - return status; - - return EFI_SUCCESS; -} - -/* - * On success we return a pointer to a boot_params structure, and NULL - * on failure. - */ -struct boot_params *efi_main(efi_handle_t handle, - efi_system_table_t *sys_table_arg, - struct boot_params *boot_params) -{ - struct desc_ptr *gdt = NULL; - struct setup_header *hdr = &boot_params->hdr; - efi_status_t status; - struct desc_struct *desc; - unsigned long cmdline_paddr; - - sys_table = sys_table_arg; - - /* Check if we were booted by the EFI firmware */ - if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) - goto fail; - - /* - * make_boot_params() may have been called before efi_main(), in which - * case this is the second time we parse the cmdline. This is ok, - * parsing the cmdline multiple times does not have side-effects. - */ - cmdline_paddr = ((u64)hdr->cmd_line_ptr | - ((u64)boot_params->ext_cmd_line_ptr << 32)); - efi_parse_options((char *)cmdline_paddr); - - /* - * If the boot loader gave us a value for secure_boot then we use that, - * otherwise we ask the BIOS. - */ - if (boot_params->secure_boot == efi_secureboot_mode_unset) - boot_params->secure_boot = efi_get_secureboot(); - - /* Ask the firmware to clear memory on unclean shutdown */ - efi_enable_reset_attack_mitigation(); - - efi_random_get_seed(); - - efi_retrieve_tpm2_eventlog(); - - setup_graphics(boot_params); - - setup_efi_pci(boot_params); - - setup_quirks(boot_params); - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), - (void **)&gdt); - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate memory for 'gdt' structure\n"); - goto fail; - } - - gdt->size = 0x800; - status = efi_low_alloc(gdt->size, 8, (unsigned long *)&gdt->address); - if (status != EFI_SUCCESS) { - efi_printk("Failed to allocate memory for 'gdt'\n"); - goto fail; - } - - /* - * If the kernel isn't already loaded at the preferred load - * address, relocate it. - */ - if (hdr->pref_address != hdr->code32_start) { - unsigned long bzimage_addr = hdr->code32_start; - status = efi_relocate_kernel(&bzimage_addr, - hdr->init_size, hdr->init_size, - hdr->pref_address, - hdr->kernel_alignment, - LOAD_PHYSICAL_ADDR); - if (status != EFI_SUCCESS) { - efi_printk("efi_relocate_kernel() failed!\n"); - goto fail; - } - - hdr->pref_address = hdr->code32_start; - hdr->code32_start = bzimage_addr; - } - - status = exit_boot(boot_params, handle); - if (status != EFI_SUCCESS) { - efi_printk("exit_boot() failed!\n"); - goto fail; - } - - memset((char *)gdt->address, 0x0, gdt->size); - desc = (struct desc_struct *)gdt->address; - - /* The first GDT is a dummy. */ - desc++; - - if (IS_ENABLED(CONFIG_X86_64)) { - /* __KERNEL32_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; - - desc++; - } else { - /* Second entry is unused on 32-bit */ - desc++; - } - - /* __KERNEL_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - - if (IS_ENABLED(CONFIG_X86_64)) { - desc->l = 1; - desc->d = 0; - } else { - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - } - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; - desc++; - - /* __KERNEL_DS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; - desc++; - - if (IS_ENABLED(CONFIG_X86_64)) { - /* Task segment value */ - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; - desc++; - } - - asm volatile("cli"); - asm volatile ("lgdt %0" : : "m" (*gdt)); - - return boot_params; -fail: - efi_printk("efi_main() failed!\n"); - - for (;;) - asm("hlt"); -} diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h deleted file mode 100644 index 99f35343d443..000000000000 --- a/arch/x86/boot/compressed/eboot.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BOOT_COMPRESSED_EBOOT_H -#define BOOT_COMPRESSED_EBOOT_H - -#define SEG_TYPE_DATA (0 << 3) -#define SEG_TYPE_READ_WRITE (1 << 1) -#define SEG_TYPE_CODE (1 << 3) -#define SEG_TYPE_EXEC_READ (1 << 1) -#define SEG_TYPE_TSS ((1 << 3) | (1 << 0)) -#define SEG_OP_SIZE_32BIT (1 << 0) -#define SEG_GRANULARITY_4KB (1 << 0) - -#define DESC_TYPE_CODE_DATA (1 << 0) - -typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; - -union efi_uga_draw_protocol { - struct { - efi_status_t (__efiapi *get_mode)(efi_uga_draw_protocol_t *, - u32*, u32*, u32*, u32*); - void *set_mode; - void *blt; - }; - struct { - u32 get_mode; - u32 set_mode; - u32 blt; - } mixed_mode; -}; - -#endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index 8fb7f6799c52..2b2049259619 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -54,11 +54,16 @@ SYM_FUNC_START(__efi64_thunk) * Switch to gdt with 32-bit segments. This is the firmware GDT * that was installed when the kernel started executing. This * pointer was saved at the EFI stub entry point in head_64.S. + * + * Pass the saved DS selector to the 32-bit code, and use far return to + * restore the saved CS selector. */ leaq efi32_boot_gdt(%rip), %rax lgdt (%rax) - pushq $__KERNEL_CS + movzwl efi32_boot_ds(%rip), %edx + movzwq efi32_boot_cs(%rip), %rax + pushq %rax leaq efi_enter32(%rip), %rax pushq %rax lretq @@ -73,6 +78,10 @@ SYM_FUNC_START(__efi64_thunk) movl %ebx, %es pop %rbx movl %ebx, %ds + /* Clear out 32-bit selector from FS and GS */ + xorl %ebx, %ebx + movl %ebx, %fs + movl %ebx, %gs /* * Convert 32-bit status code into 64-bit. @@ -92,10 +101,12 @@ SYM_FUNC_END(__efi64_thunk) * The stack should represent the 32-bit calling convention. */ SYM_FUNC_START_LOCAL(efi_enter32) - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss + /* Load firmware selector into data and stack segment registers */ + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + movl %edx, %ss /* Reload pgtables */ movl %cr3, %eax @@ -157,6 +168,14 @@ SYM_DATA_START(efi32_boot_gdt) .quad 0 SYM_DATA_END(efi32_boot_gdt) +SYM_DATA_START(efi32_boot_cs) + .word 0 +SYM_DATA_END(efi32_boot_cs) + +SYM_DATA_START(efi32_boot_ds) + .word 0 +SYM_DATA_END(efi32_boot_ds) + SYM_DATA_START(efi_gdt64) .word efi_gdt64_end - efi_gdt64 .long 0 /* Filled out by user */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 73f17d0544dd..ab3307036ba4 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -63,21 +63,7 @@ __HEAD SYM_FUNC_START(startup_32) cld - /* - * Test KEEP_SEGMENTS flag to see if the bootloader is asking - * us to not reload segments - */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 1f - cli - movl $__BOOT_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %fs - movl %eax, %gs - movl %eax, %ss -1: /* * Calculate the delta between where we were compiled to run @@ -89,32 +75,59 @@ SYM_FUNC_START(startup_32) */ leal (BP_scratch+4)(%esi), %esp call 1f -1: popl %ebp - subl $1b, %ebp +1: popl %edx + subl $1b, %edx + + /* Load new GDT */ + leal gdt(%edx), %eax + movl %eax, 2(%eax) + lgdt (%eax) + + /* Load segment registers with our descriptors */ + movl $__BOOT_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %fs + movl %eax, %gs + movl %eax, %ss /* - * %ebp contains the address we are loaded at by the boot loader and %ebx + * %edx contains the address we are loaded at by the boot loader and %ebx * contains the address where we should move the kernel image temporarily - * for safe in-place decompression. + * for safe in-place decompression. %ebp contains the address that the kernel + * will be decompressed to. */ #ifdef CONFIG_RELOCATABLE - movl %ebp, %ebx + movl %edx, %ebx + +#ifdef CONFIG_EFI_STUB +/* + * If we were loaded via the EFI LoadImage service, startup_32() will be at an + * offset to the start of the space allocated for the image. efi_pe_entry() will + * set up image_offset to tell us where the image actually starts, so that we + * can use the full available buffer. + * image_offset = startup_32 - image_base + * Otherwise image_offset will be zero and has no effect on the calculations. + */ + subl image_offset(%edx), %ebx +#endif + movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: + movl %ebx, %ebp // Save the output address for later /* Target address to relocate to for decompression */ - movl BP_init_size(%esi), %eax - subl $_end, %eax - addl %eax, %ebx + addl BP_init_size(%esi), %ebx + subl $_end, %ebx /* Set up the stack */ leal boot_stack_end(%ebx), %esp @@ -128,7 +141,7 @@ SYM_FUNC_START(startup_32) * where decompression in place becomes safe. */ pushl %esi - leal (_bss-4)(%ebp), %esi + leal (_bss-4)(%edx), %esi leal (_bss-4)(%ebx), %edi movl $(_bss - startup_32), %ecx shrl $2, %ecx @@ -137,6 +150,15 @@ SYM_FUNC_START(startup_32) cld popl %esi + /* + * The GDT may get overwritten either during the copy we just did or + * during extract_kernel below. To avoid any issues, repoint the GDTR + * to the new copy of the GDT. + */ + leal gdt(%ebx), %eax + movl %eax, 2(%eax) + lgdt (%eax) + /* * Jump to the relocated address. */ @@ -148,9 +170,8 @@ SYM_FUNC_END(startup_32) SYM_FUNC_START(efi32_stub_entry) SYM_FUNC_START_ALIAS(efi_stub_entry) add $0x4, %esp + movl 8(%esp), %esi /* save boot_params pointer */ call efi_main - movl %eax, %esi - movl BP_code32_start(%esi), %eax leal startup_32(%eax), %eax jmp *%eax SYM_FUNC_END(efi32_stub_entry) @@ -189,9 +210,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) /* push arguments for extract_kernel: */ pushl $z_output_len /* decompressed length, end of relocs */ - leal _end(%ebx), %eax - subl BP_init_size(%esi), %eax - pushl %eax /* output address */ + pushl %ebp /* output address */ pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax @@ -209,6 +228,21 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) jmp *%eax SYM_FUNC_END(.Lrelocated) + .data + .balign 8 +SYM_DATA_START_LOCAL(gdt) + .word gdt_end - gdt - 1 + .long 0 + .word 0 + .quad 0x0000000000000000 /* Reserved */ + .quad 0x00cf9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf92000000ffff /* __KERNEL_DS */ +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) + +#ifdef CONFIG_EFI_STUB +SYM_DATA(image_offset, .long 0) +#endif + /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 1f1f6c8139b3..d4657d38e884 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -53,19 +53,7 @@ SYM_FUNC_START(startup_32) * all need to be under the 4G limit. */ cld - /* - * Test KEEP_SEGMENTS flag to see if the bootloader is asking - * us to not reload segments - */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 1f - cli - movl $(__BOOT_DS), %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss -1: /* * Calculate the delta between where we were compiled to run @@ -80,10 +68,21 @@ SYM_FUNC_START(startup_32) 1: popl %ebp subl $1b, %ebp + /* Load new GDT with the 64bit segments using 32bit descriptor */ + leal gdt(%ebp), %eax + movl %eax, 2(%eax) + lgdt (%eax) + + /* Load segment registers with our descriptors */ + movl $__BOOT_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %fs + movl %eax, %gs + movl %eax, %ss + /* setup a stack and make sure cpu supports long mode. */ - movl $boot_stack_end, %eax - addl %ebp, %eax - movl %eax, %esp + leal boot_stack_end(%ebp), %esp call verify_cpu testl %eax, %eax @@ -100,30 +99,38 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE movl %ebp, %ebx + +#ifdef CONFIG_EFI_STUB +/* + * If we were loaded via the EFI LoadImage service, startup_32 will be at an + * offset to the start of the space allocated for the image. efi_pe_entry will + * set up image_offset to tell us where the image actually starts, so that we + * can use the full available buffer. + * image_offset = startup_32 - image_base + * Otherwise image_offset will be zero and has no effect on the calculations. + */ + subl image_offset(%ebp), %ebx +#endif + movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: /* Target address to relocate to for decompression */ - movl BP_init_size(%esi), %eax - subl $_end, %eax - addl %eax, %ebx + addl BP_init_size(%esi), %ebx + subl $_end, %ebx /* * Prepare for entering 64 bit mode */ - /* Load new GDT with the 64bit segments using 32bit descriptor */ - addl %ebp, gdt+2(%ebp) - lgdt gdt(%ebp) - /* Enable PAE mode */ movl %cr4, %eax orl $X86_CR4_PAE, %eax @@ -212,8 +219,13 @@ SYM_FUNC_START(startup_32) cmp $0, %edi jz 1f leal efi64_stub_entry(%ebp), %eax - movl %esi, %edx movl efi32_boot_args+4(%ebp), %esi + movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer + cmpl $0, %edx + jnz 1f + leal efi_pe_entry(%ebp), %eax + movl %edi, %ecx // MS calling convention + movl %esi, %edx 1: #endif pushl %eax @@ -238,11 +250,17 @@ SYM_FUNC_START(efi32_stub_entry) 1: pop %ebp subl $1b, %ebp + movl %esi, efi32_boot_args+8(%ebp) +SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) movl %ecx, efi32_boot_args(%ebp) movl %edx, efi32_boot_args+4(%ebp) - sgdtl efi32_boot_gdt(%ebp) movb $0, efi_is64(%ebp) + /* Save firmware GDTR and code/data selectors */ + sgdtl efi32_boot_gdt(%ebp) + movw %cs, efi32_boot_cs(%ebp) + movw %ds, efi32_boot_ds(%ebp) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -266,6 +284,9 @@ SYM_CODE_START(startup_64) * and command line. */ + cld + cli + /* Setup data segments. */ xorl %eax, %eax movl %eax, %ds @@ -290,13 +311,27 @@ SYM_CODE_START(startup_64) /* Start with the delta to where the kernel will run at. */ #ifdef CONFIG_RELOCATABLE leaq startup_32(%rip) /* - $startup_32 */, %rbp + +#ifdef CONFIG_EFI_STUB +/* + * If we were loaded via the EFI LoadImage service, startup_32 will be at an + * offset to the start of the space allocated for the image. efi_pe_entry will + * set up image_offset to tell us where the image actually starts, so that we + * can use the full available buffer. + * image_offset = startup_32 - image_base + * Otherwise image_offset will be zero and has no effect on the calculations. + */ + movl image_offset(%rip), %eax + subq %rax, %rbp +#endif + movl BP_kernel_alignment(%rsi), %eax decl %eax addq %rax, %rbp notq %rax andq %rax, %rbp cmpq $LOAD_PHYSICAL_ADDR, %rbp - jge 1f + jae 1f #endif movq $LOAD_PHYSICAL_ADDR, %rbp 1: @@ -354,9 +389,9 @@ SYM_CODE_START(startup_64) */ /* Make sure we have GDT with 32-bit code segment */ - leaq gdt(%rip), %rax - movq %rax, gdt64+2(%rip) - lgdt gdt64(%rip) + leaq gdt64(%rip), %rax + addq %rax, 2(%rax) + lgdt (%rax) /* * paging_prepare() sets up the trampoline and checks if we need to @@ -441,6 +476,16 @@ trampoline_return: cld popq %rsi + /* + * The GDT may get overwritten either during the copy we just did or + * during extract_kernel below. To avoid any issues, repoint the GDTR + * to the new copy of the GDT. + */ + leaq gdt64(%rbx), %rax + leaq gdt(%rbx), %rdx + movq %rdx, 2(%rax) + lgdt (%rax) + /* * Jump to the relocated address. */ @@ -453,9 +498,9 @@ SYM_CODE_END(startup_64) SYM_FUNC_START(efi64_stub_entry) SYM_FUNC_START_ALIAS(efi_stub_entry) and $~0xf, %rsp /* realign the stack */ + movq %rdx, %rbx /* save boot_params pointer */ call efi_main - movq %rax,%rsi - movl BP_code32_start(%esi), %eax + movq %rbx,%rsi leaq startup_64(%rax), %rax jmp *%rax SYM_FUNC_END(efi64_stub_entry) @@ -613,13 +658,13 @@ SYM_FUNC_END(.Lno_longmode) .data SYM_DATA_START_LOCAL(gdt64) - .word gdt_end - gdt - .quad 0 + .word gdt_end - gdt - 1 + .quad gdt - gdt64 SYM_DATA_END(gdt64) .balign 8 SYM_DATA_START_LOCAL(gdt) - .word gdt_end - gdt - .long gdt + .word gdt_end - gdt - 1 + .long 0 .word 0 .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ .quad 0x00af9a000000ffff /* __KERNEL_CS */ @@ -628,9 +673,97 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x0000000000000000 /* TS continued */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) +#ifdef CONFIG_EFI_STUB +SYM_DATA(image_offset, .long 0) +#endif + #ifdef CONFIG_EFI_MIXED -SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0) +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) SYM_DATA(efi_is64, .byte 1) + +#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) +#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) +#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) + + .text + .code32 +SYM_FUNC_START(efi32_pe_entry) +/* + * efi_status_t efi32_pe_entry(efi_handle_t image_handle, + * efi_system_table_32_t *sys_table) + */ + + pushl %ebp + movl %esp, %ebp + pushl %eax // dummy push to allocate loaded_image + + pushl %ebx // save callee-save registers + pushl %edi + + call verify_cpu // check for long mode support + testl %eax, %eax + movl $0x80000003, %eax // EFI_UNSUPPORTED + jnz 2f + + call 1f +1: pop %ebx + subl $1b, %ebx + + /* Get the loaded image protocol pointer from the image handle */ + leal -4(%ebp), %eax + pushl %eax // &loaded_image + leal loaded_image_proto(%ebx), %eax + pushl %eax // pass the GUID address + pushl 8(%ebp) // pass the image handle + + /* + * Note the alignment of the stack frame. + * sys_table + * handle <-- 16-byte aligned on entry by ABI + * return address + * frame pointer + * loaded_image <-- local variable + * saved %ebx <-- 16-byte aligned here + * saved %edi + * &loaded_image + * &loaded_image_proto + * handle <-- 16-byte aligned for call to handle_protocol + */ + + movl 12(%ebp), %eax // sys_table + movl ST32_boottime(%eax), %eax // sys_table->boottime + call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol + addl $12, %esp // restore argument space + testl %eax, %eax + jnz 2f + + movl 8(%ebp), %ecx // image_handle + movl 12(%ebp), %edx // sys_table + movl -4(%ebp), %esi // loaded_image + movl LI32_image_base(%esi), %esi // loaded_image->image_base + movl %ebx, %ebp // startup_32 for efi32_pe_stub_entry + /* + * We need to set the image_offset variable here since startup_32() will + * use it before we get to the 64-bit efi_pe_entry() in C code. + */ + subl %esi, %ebx + movl %ebx, image_offset(%ebp) // save image_offset + jmp efi32_pe_stub_entry + +2: popl %edi // restore callee-save registers + popl %ebx + leave + ret +SYM_FUNC_END(efi32_pe_entry) + + .section ".rodata" + /* EFI loaded image protocol GUID */ + .balign 4 +SYM_DATA_START_LOCAL(loaded_image_proto) + .long 0x5b1b31a1 + .word 0x9562, 0x11d2 + .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b +SYM_DATA_END(loaded_image_proto) #endif /* diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c index 748456c365f4..9557c5a15b91 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/kaslr_64.c @@ -29,9 +29,6 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" -/* Used by pgtable.h asm code to force instruction serialization. */ -unsigned long __force_order; - /* Used to track our page table allocation area. */ struct alloc_pgt_data { unsigned char *pgt_buf; diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 97d9b6d6c1af..735ad7f21ab0 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -15,7 +15,7 @@ * hex while segment addresses are written as segment:offset. * */ - +#include <linux/pe.h> #include <asm/segment.h> #include <asm/boot.h> #include <asm/page_types.h> @@ -43,8 +43,7 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header - .byte 0x4d - .byte 0x5a + .word MZ_MAGIC #endif # Normalize the start address @@ -97,39 +96,30 @@ bugger_off_msg: #ifdef CONFIG_EFI_STUB pe_header: - .ascii "PE" - .word 0 + .long PE_MAGIC coff_header: #ifdef CONFIG_X86_32 - .word 0x14c # i386 + .set image_file_add_flags, IMAGE_FILE_32BIT_MACHINE + .set pe_opt_magic, PE_OPT_MAGIC_PE32 + .word IMAGE_FILE_MACHINE_I386 #else - .word 0x8664 # x86-64 + .set image_file_add_flags, 0 + .set pe_opt_magic, PE_OPT_MAGIC_PE32PLUS + .word IMAGE_FILE_MACHINE_AMD64 #endif - .word 4 # nr_sections + .word section_count # nr_sections .long 0 # TimeDateStamp .long 0 # PointerToSymbolTable .long 1 # NumberOfSymbols .word section_table - optional_header # SizeOfOptionalHeader -#ifdef CONFIG_X86_32 - .word 0x306 # Characteristics. - # IMAGE_FILE_32BIT_MACHINE | - # IMAGE_FILE_DEBUG_STRIPPED | - # IMAGE_FILE_EXECUTABLE_IMAGE | - # IMAGE_FILE_LINE_NUMS_STRIPPED -#else - .word 0x206 # Characteristics - # IMAGE_FILE_DEBUG_STRIPPED | - # IMAGE_FILE_EXECUTABLE_IMAGE | - # IMAGE_FILE_LINE_NUMS_STRIPPED -#endif + .word IMAGE_FILE_EXECUTABLE_IMAGE | \ + image_file_add_flags | \ + IMAGE_FILE_DEBUG_STRIPPED | \ + IMAGE_FILE_LINE_NUMS_STRIPPED # Characteristics optional_header: -#ifdef CONFIG_X86_32 - .word 0x10b # PE32 format -#else - .word 0x20b # PE32+ format -#endif + .word pe_opt_magic .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion @@ -148,17 +138,19 @@ optional_header: #endif extra_header_fields: + # PE specification requires ImageBase to be 64k aligned + .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long 0 # ImageBase + .long image_base # ImageBase #else - .quad 0 # ImageBase + .quad image_base # ImageBase #endif .long 0x20 # SectionAlignment .long 0x20 # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion - .word 0 # MajorImageVersion - .word 0 # MinorImageVersion + .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion + .word LINUX_EFISTUB_MINOR_VERSION # MinorImageVersion .word 0 # MajorSubsystemVersion .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue @@ -170,7 +162,7 @@ extra_header_fields: .long 0x200 # SizeOfHeaders .long 0 # CheckSum - .word 0xa # Subsystem (EFI application) + .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) .word 0 # DllCharacteristics #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve @@ -184,7 +176,7 @@ extra_header_fields: .quad 0 # SizeOfHeapCommit #endif .long 0 # LoaderFlags - .long 0x6 # NumberOfRvaAndSizes + .long (section_table - .) / 8 # NumberOfRvaAndSizes .quad 0 # ExportTable .quad 0 # ImportTable @@ -210,7 +202,10 @@ section_table: .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers - .long 0x60500020 # Characteristics (section flags) + .long IMAGE_SCN_CNT_CODE | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_EXECUTE | \ + IMAGE_SCN_ALIGN_16BYTES # Characteristics # # The EFI application loader requires a relocation section @@ -228,45 +223,53 @@ section_table: .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers - .long 0x42100040 # Characteristics (section flags) + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_DISCARDABLE | \ + IMAGE_SCN_ALIGN_1BYTES # Characteristics +#ifdef CONFIG_EFI_MIXED # # The offset & size fields are filled in by build.c. # - .ascii ".text" - .byte 0 - .byte 0 - .byte 0 + .asciz ".compat" .long 0 - .long 0x0 # startup_{32,64} + .long 0x0 .long 0 # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long 0x0 .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers - .long 0x60500020 # Characteristics (section flags) + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_DISCARDABLE | \ + IMAGE_SCN_ALIGN_1BYTES # Characteristics +#endif # # The offset & size fields are filled in by build.c. # - .ascii ".bss" - .byte 0 + .ascii ".text" .byte 0 .byte 0 .byte 0 .long 0 - .long 0x0 + .long 0x0 # startup_{32,64} .long 0 # Size of initialized data # on disk - .long 0x0 + .long 0x0 # startup_{32,64} .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers - .long 0xc8000080 # Characteristics (section flags) + .long IMAGE_SCN_CNT_CODE | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_EXECUTE | \ + IMAGE_SCN_ALIGN_16BYTES # Characteristics + .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 55e669d29e54..8f8c8e386cea 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -53,11 +53,20 @@ u8 buf[SETUP_SECT_MAX*512]; #define PECOFF_RELOC_RESERVE 0x20 +#ifdef CONFIG_EFI_MIXED +#define PECOFF_COMPAT_RESERVE 0x20 +#else +#define PECOFF_COMPAT_RESERVE 0x0 +#endif + unsigned long efi32_stub_entry; unsigned long efi64_stub_entry; unsigned long efi_pe_entry; +unsigned long efi32_pe_entry; unsigned long kernel_info; unsigned long startup_64; +unsigned long _ehead; +unsigned long _end; /*----------------------------------------------------------------------*/ @@ -189,7 +198,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz static void update_pecoff_setup_and_reloc(unsigned int size) { u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE; + u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; +#ifdef CONFIG_EFI_MIXED + u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; +#endif u32 setup_size = reloc_offset - setup_offset; update_pecoff_section_header(".setup", setup_offset, setup_size); @@ -201,43 +213,59 @@ static void update_pecoff_setup_and_reloc(unsigned int size) */ put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); put_unaligned_le32(10, &buf[reloc_offset + 4]); + +#ifdef CONFIG_EFI_MIXED + update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); + + /* + * Put the IA-32 machine type (0x14c) and the associated entry point + * address in the .compat section, so loaders can figure out which other + * execution modes this image supports. + */ + buf[compat_offset] = 0x1; + buf[compat_offset + 1] = 0x8; + put_unaligned_le16(0x14c, &buf[compat_offset + 2]); + put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); +#endif } -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) +static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, + unsigned int init_sz) { unsigned int pe_header; unsigned int text_sz = file_sz - text_start; + unsigned int bss_sz = init_sz - file_sz; pe_header = get_unaligned_le32(&buf[0x3c]); /* + * The PE/COFF loader may load the image at an address which is + * misaligned with respect to the kernel_alignment field in the setup + * header. + * + * In order to avoid relocating the kernel to correct the misalignment, + * add slack to allow the buffer to be aligned within the declared size + * of the image. + */ + bss_sz += CONFIG_PHYSICAL_ALIGN; + init_sz += CONFIG_PHYSICAL_ALIGN; + + /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. */ - put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]); + put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); + + /* Size of image */ + put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); /* * Address of entry point for PE/COFF executable */ put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - update_pecoff_section_header(".text", text_start, text_sz); -} - -static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz) -{ - unsigned int pe_header; - unsigned int bss_sz = init_sz - file_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* Size of uninitialized data */ - put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]); - - /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); - - update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0); + update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, + text_sz, text_start); } static int reserve_pecoff_reloc_section(int c) @@ -278,9 +306,8 @@ static void efi_stub_entry_update(void) static inline void update_pecoff_setup_and_reloc(unsigned int size) {} static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz) {} -static inline void update_pecoff_bss(unsigned int file_sz, - unsigned int init_sz) {} + unsigned int file_sz, + unsigned int init_sz) {} static inline void efi_stub_defaults(void) {} static inline void efi_stub_entry_update(void) {} @@ -290,6 +317,12 @@ static inline int reserve_pecoff_reloc_section(int c) } #endif /* CONFIG_EFI_STUB */ +static int reserve_pecoff_compat_section(int c) +{ + /* Reserve 0x20 bytes for .compat section */ + memset(buf+c, 0, PECOFF_COMPAT_RESERVE); + return PECOFF_COMPAT_RESERVE; +} /* * Parse zoffset.h and find the entry points. We could just #include zoffset.h @@ -322,8 +355,11 @@ static void parse_zoffset(char *fname) PARSE_ZOFS(p, efi32_stub_entry); PARSE_ZOFS(p, efi64_stub_entry); PARSE_ZOFS(p, efi_pe_entry); + PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, kernel_info); PARSE_ZOFS(p, startup_64); + PARSE_ZOFS(p, _ehead); + PARSE_ZOFS(p, _end); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -365,6 +401,7 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); + c += reserve_pecoff_compat_section(c); c += reserve_pecoff_reloc_section(c); /* Pad unused space with zeros */ @@ -406,9 +443,28 @@ int main(int argc, char ** argv) buf[0x1f1] = setup_sectors-1; put_unaligned_le32(sys_size, &buf[0x1f4]); - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); init_sz = get_unaligned_le32(&buf[0x260]); - update_pecoff_bss(i + (sys_size * 16), init_sz); +#ifdef CONFIG_EFI_STUB + /* + * The decompression buffer will start at ImageBase. When relocating + * the compressed kernel to its end, we must ensure that the head + * section does not get overwritten. The head section occupies + * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). + * + * At present these should never overlap, because 'i' is at most 32k + * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the + * calculation of INIT_SIZE in boot/header.S ensures that + * 'init_sz - _end' is at least 64k. + * + * For future-proofing, increase init_sz if necessary. + */ + + if (init_sz - _end < i + _ehead) { + init_sz = (i + _ehead + _end + 4095) & ~4095; + put_unaligned_le32(init_sz, &buf[0x260]); + } +#endif + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); efi_stub_entry_update(); diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index b69e00bf20b8..8c2e9eadee8a 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -11,6 +11,7 @@ avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) +adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o @@ -39,7 +40,11 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o -obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + +# These modules require the assembler to support ADX. +ifeq ($(adx_supported),yes) + obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o +endif # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index bbbebbd35b5d..75b6ea20491e 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1064,7 +1064,7 @@ static struct aead_alg aesni_aeads[0]; static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)]; static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), + X86_MATCH_FEATURE(X86_FEATURE_AES, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 418bd88acac8..7c4c7b2fbf05 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -170,7 +170,7 @@ static struct shash_alg alg = { }; static const struct x86_cpu_id crc32pclmul_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), + X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index c20d1b8a82c3..d2d069bd459b 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -221,7 +221,7 @@ static struct shash_alg alg = { }; static const struct x86_cpu_id crc32c_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM4_2), + X86_MATCH_FEATURE(X86_FEATURE_XMM4_2, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id); diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index 3c81e15b0873..71291d5af9f4 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -114,7 +114,7 @@ static struct shash_alg alg = { }; static const struct x86_cpu_id crct10dif_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), + X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id); diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index a4b728518e28..1f1a95f3dd0c 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -313,7 +313,7 @@ static struct ahash_alg ghash_async_alg = { }; static const struct x86_cpu_id pcmul_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), /* Pickle-Mickle-Duck */ + X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), /* Pickle-Mickle-Duck */ {} }; MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id); diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index abef51320e3a..43b09e9c93a2 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -259,7 +259,7 @@ static int power_cpu_init(unsigned int cpu) } static const struct x86_cpu_id cpu_match[] = { - { .vendor = X86_VENDOR_AMD, .family = 0x15 }, + X86_MATCH_VENDOR_FAM(AMD, 0x15, NULL), {}, }; diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a6ea07f2aa84..76400c052b0e 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -180,6 +180,31 @@ static void amd_uncore_del(struct perf_event *event, int flags) hwc->idx = -1; } +/* + * Convert logical CPU number to L3 PMC Config ThreadMask format + */ +static u64 l3_thread_slice_mask(int cpu) +{ + u64 thread_mask, core = topology_core_id(cpu); + unsigned int shift, thread = 0; + + if (topology_smt_supported() && !topology_is_primary_thread(cpu)) + thread = 1; + + if (boot_cpu_data.x86 <= 0x18) { + shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread; + thread_mask = BIT_ULL(shift); + + return AMD64_L3_SLICE_MASK | thread_mask; + } + + core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK; + shift = AMD64_L3_THREAD_SHIFT + thread; + thread_mask = BIT_ULL(shift); + + return AMD64_L3_EN_ALL_SLICES | core | thread_mask; +} + static int amd_uncore_event_init(struct perf_event *event) { struct amd_uncore *uncore; @@ -190,15 +215,12 @@ static int amd_uncore_event_init(struct perf_event *event) /* * NB and Last level cache counters (MSRs) are shared across all cores - * that share the same NB / Last level cache. Interrupts can be directed - * to a single target core, however, event counts generated by processes - * running on other cores cannot be masked out. So we do not support - * sampling and per-thread events. + * that share the same NB / Last level cache. On family 16h and below, + * Interrupts can be directed to a single target core, however, event + * counts generated by processes running on other cores cannot be masked + * out. So we do not support sampling and per-thread events via + * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - /* and we do not enable counter overflow interrupts */ hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; @@ -206,18 +228,11 @@ static int amd_uncore_event_init(struct perf_event *event) return -EINVAL; /* - * SliceMask and ThreadMask need to be set for certain L3 events in - * Family 17h. For other events, the two fields do not affect the count. + * SliceMask and ThreadMask need to be set for certain L3 events. + * For other events, the two fields do not affect the count. */ - if (l3_mask && is_llc_event(event)) { - int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4); - - if (smp_num_siblings > 1) - thread += cpu_data(event->cpu).apicid & 1; - - hwc->config |= (1ULL << (AMD64_L3_THREAD_SHIFT + thread) & - AMD64_L3_THREAD_MASK) | AMD64_L3_SLICE_MASK; - } + if (l3_mask && is_llc_event(event)) + hwc->config |= l3_thread_slice_mask(event->cpu); uncore = event_to_amd_uncore(event); if (!uncore) @@ -306,7 +321,7 @@ static struct pmu amd_nb_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct pmu amd_llc_pmu = { @@ -317,7 +332,7 @@ static struct pmu amd_llc_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) @@ -523,9 +538,9 @@ static int __init amd_uncore_init(void) if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) return -ENODEV; - if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) { + if (boot_cpu_data.x86 >= 0x17) { /* - * For F17h or F18h, the Northbridge counters are + * For F17h and above, the Northbridge counters are * repurposed as Data Fabric counters. Also, L3 * counters are supported too. The PMUs are exported * based on family as either L2 or L3 and NB or DF. diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index dff6623804c2..332954cccece 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1945,6 +1945,14 @@ static __initconst const u64 knl_hw_cache_extra_regs * intel_bts events don't coexist with intel PMU's BTS events because of * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them * disabled around intel PMU's event batching etc, only inside the PMI handler. + * + * Avoid PEBS_ENABLE MSR access in PMIs. + * The GLOBAL_CTRL has been disabled. All the counters do not count anymore. + * It doesn't matter if the PEBS is enabled or not. + * Usually, the PEBS status are not changed in PMIs. It's unnecessary to + * access PEBS_ENABLE MSR in disable_all()/enable_all(). + * However, there are some cases which may change PEBS status, e.g. PMI + * throttle. The PEBS_ENABLE should be updated where the status changes. */ static void __intel_pmu_disable_all(void) { @@ -1954,13 +1962,12 @@ static void __intel_pmu_disable_all(void) if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); - - intel_pmu_pebs_disable_all(); } static void intel_pmu_disable_all(void) { __intel_pmu_disable_all(); + intel_pmu_pebs_disable_all(); intel_pmu_lbr_disable_all(); } @@ -1968,7 +1975,6 @@ static void __intel_pmu_enable_all(int added, bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - intel_pmu_pebs_enable_all(); intel_pmu_lbr_enable_all(pmi); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); @@ -1986,6 +1992,7 @@ static void __intel_pmu_enable_all(int added, bool pmi) static void intel_pmu_enable_all(int added) { + intel_pmu_pebs_enable_all(); __intel_pmu_enable_all(added, false); } @@ -2374,9 +2381,21 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) * PEBS overflow sets bit 62 in the global status register */ if (__test_and_clear_bit(62, (unsigned long *)&status)) { + u64 pebs_enabled = cpuc->pebs_enabled; + handled++; x86_pmu.drain_pebs(regs); status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; + + /* + * PMI throttle may be triggered, which stops the PEBS event. + * Although cpuc->pebs_enabled is updated accordingly, the + * MSR_IA32_PEBS_ENABLE is not updated. Because the + * cpuc->enabled has been forced to 0 in PMI. + * Update the MSR if pebs_enabled is changed. + */ + if (pebs_enabled != cpuc->pebs_enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } /* diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4814c964692c..e4aa20c0426f 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -594,63 +594,60 @@ static const struct cstate_model glm_cstates __initconst = { }; -#define X86_CSTATES_MODEL(model, states) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } - static const struct x86_cpu_id intel_cstates_match[] __initconst = { - X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM, nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EP, nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EX, nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE, nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EP, nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EX, nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_G, snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_cstates), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_D, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &slm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D, &slm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_D, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_G, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_L, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &snb_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &hswult_cstates), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &hswult_cstates), + X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &hswult_cstates), + X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &cnl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 534c76606049..65113b16804a 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -585,6 +585,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; + cpuc->lbr_stack.hw_idx = tos; } /* @@ -680,6 +681,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) out++; } cpuc->lbr_stack.nr = out; + cpuc->lbr_stack.hw_idx = tos; } void intel_pmu_lbr_read(void) @@ -1120,6 +1122,13 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr) int i; cpuc->lbr_stack.nr = x86_pmu.lbr_nr; + + /* Cannot get TOS for large PEBS */ + if (cpuc->n_pebs == cpuc->n_large_pebs) + cpuc->lbr_stack.hw_idx = -1ULL; + else + cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos(); + for (i = 0; i < x86_pmu.lbr_nr; i++) { u64 info = lbr->lbr[i].info; struct perf_branch_entry *e = &cpuc->lbr_entries[i]; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 09913121e726..a5dbd25852cb 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -668,9 +668,6 @@ static int __init init_rapl_pmus(void) return 0; } -#define X86_RAPL_MODEL_MATCH(model, init) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } - static struct rapl_model model_snb = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | @@ -716,36 +713,35 @@ static struct rapl_model model_skl = { }; static const struct x86_cpu_id rapl_model_match[] __initconst = { - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE, model_skl), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), {}, }; - MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 86467f85c383..1ba72c563313 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1392,10 +1392,6 @@ err: return ret; } - -#define X86_UNCORE_MODEL_MATCH(model, init) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } - struct intel_uncore_init_fun { void (*cpu_init)(void); int (*pci_init)(void); @@ -1470,6 +1466,16 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = { .pci_init = skl_uncore_pci_init, }; +static const struct intel_uncore_init_fun tgl_uncore_init __initconst = { + .cpu_init = icl_uncore_cpu_init, + .mmio_init = tgl_uncore_mmio_init, +}; + +static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = { + .cpu_init = icl_uncore_cpu_init, + .mmio_init = tgl_l_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun snr_uncore_init __initconst = { .cpu_init = snr_uncore_cpu_init, .pci_init = snr_uncore_pci_init, @@ -1477,38 +1483,39 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = { }; static const struct x86_cpu_id intel_uncore_match[] __initconst = { - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE, nhm_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP, nhm_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, ivb_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_L, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_G, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL, bdw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, bdw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX, nhmex_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX, nhmex_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, ivbep_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hswep_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, bdx_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, bdx_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_D, snr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &ivb_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &hsw_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hsw_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &hsw_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &bdw_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &bdw_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snbep_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhmex_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhmex_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ivbep_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &hswep_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &bdx_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &bdx_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &skl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &skl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &skx_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &skl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &skl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; - MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); static int __init intel_uncore_init(void) diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index bbfdaa720b45..b30429f8a53a 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -154,6 +154,7 @@ struct freerunning_counters { unsigned int box_offset; unsigned int num_counters; unsigned int bits; + unsigned *box_offsets; }; struct pci2phy_map { @@ -310,7 +311,9 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box, return pmu->type->freerunning[type].counter_base + pmu->type->freerunning[type].counter_offset * idx + - pmu->type->freerunning[type].box_offset * pmu->pmu_idx; + (pmu->type->freerunning[type].box_offsets ? + pmu->type->freerunning[type].box_offsets[pmu->pmu_idx] : + pmu->type->freerunning[type].box_offset * pmu->pmu_idx); } static inline @@ -527,6 +530,8 @@ void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); +void tgl_uncore_mmio_init(void); +void tgl_l_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index c37cb12d0ef6..3de1065eefc4 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -44,6 +44,11 @@ #define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35 #define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02 #define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12 +#define PCI_DEVICE_ID_INTEL_TGL_U1_IMC 0x9a02 +#define PCI_DEVICE_ID_INTEL_TGL_U2_IMC 0x9a04 +#define PCI_DEVICE_ID_INTEL_TGL_U3_IMC 0x9a12 +#define PCI_DEVICE_ID_INTEL_TGL_U4_IMC 0x9a14 +#define PCI_DEVICE_ID_INTEL_TGL_H_IMC 0x9a36 /* SNB event control */ @@ -1002,3 +1007,157 @@ void nhm_uncore_cpu_init(void) } /* end of Nehalem uncore support */ + +/* Tiger Lake MMIO uncore support */ + +static const struct pci_device_id tgl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ } +}; + +enum perf_tgl_uncore_imc_freerunning_types { + TGL_MMIO_UNCORE_IMC_DATA_TOTAL, + TGL_MMIO_UNCORE_IMC_DATA_READ, + TGL_MMIO_UNCORE_IMC_DATA_WRITE, + TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX +}; + +static struct freerunning_counters tgl_l_uncore_imc_freerunning[] = { + [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x5040, 0x0, 0x0, 1, 64 }, + [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0x5058, 0x0, 0x0, 1, 64 }, + [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0x50A0, 0x0, 0x0, 1, 64 }, +}; + +static struct freerunning_counters tgl_uncore_imc_freerunning[] = { + [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0xd840, 0x0, 0x0, 1, 64 }, + [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0xd858, 0x0, 0x0, 1, 64 }, + [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xd8A0, 0x0, 0x0, 1, 64 }, +}; + +static struct uncore_event_desc tgl_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(data_total, "event=0xff,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(data_total.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_total.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_read, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(data_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_read.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_write, "event=0xff,umask=0x30"), + INTEL_UNCORE_EVENT_DESC(data_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_write.unit, "MiB"), + + { /* end: all zeroes */ } +}; + +static struct pci_dev *tgl_uncore_get_mc_dev(void) +{ + const struct pci_device_id *ids = tgl_uncore_pci_ids; + struct pci_dev *mc_dev = NULL; + + while (ids && ids->vendor) { + mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, ids->device, NULL); + if (mc_dev) + return mc_dev; + ids++; + } + + return mc_dev; +} + +#define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 + +static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = tgl_uncore_get_mc_dev(); + struct intel_uncore_pmu *pmu = box->pmu; + resource_size_t addr; + u32 mch_bar; + + if (!pdev) { + pr_warn("perf uncore: Cannot find matched IMC device.\n"); + return; + } + + pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar); + /* MCHBAR is disabled */ + if (!(mch_bar & BIT(0))) { + pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n"); + return; + } + mch_bar &= ~BIT(0); + addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx); + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar); + addr |= ((resource_size_t)mch_bar << 32); +#endif + + box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); +} + +static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = { + .init_box = tgl_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct attribute *tgl_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + NULL +}; + +static const struct attribute_group tgl_uncore_imc_format_group = { + .name = "format", + .attrs = tgl_uncore_imc_formats_attr, +}; + +static struct intel_uncore_type tgl_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 3, + .num_boxes = 2, + .num_freerunning_types = TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX, + .freerunning = tgl_uncore_imc_freerunning, + .ops = &tgl_uncore_imc_freerunning_ops, + .event_descs = tgl_uncore_imc_events, + .format_group = &tgl_uncore_imc_format_group, +}; + +static struct intel_uncore_type *tgl_mmio_uncores[] = { + &tgl_uncore_imc_free_running, + NULL +}; + +void tgl_l_uncore_mmio_init(void) +{ + tgl_uncore_imc_free_running.freerunning = tgl_l_uncore_imc_freerunning; + uncore_mmio_uncores = tgl_mmio_uncores; +} + +void tgl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = tgl_mmio_uncores; +} + +/* end of Tiger Lake MMIO uncore support */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ad20220af303..01023f0d935b 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4380,10 +4380,10 @@ static struct pci_dev *snr_uncore_get_mc_dev(int id) return mc_dev; } -static void snr_uncore_mmio_init_box(struct intel_uncore_box *box) +static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box, + unsigned int box_ctl, int mem_offset) { struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid); - unsigned int box_ctl = uncore_mmio_box_ctl(box); resource_size_t addr; u32 pci_dword; @@ -4393,7 +4393,7 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box) pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword); addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23; - pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword); + pci_read_config_dword(pdev, mem_offset, &pci_dword); addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12; addr += box_ctl; @@ -4405,6 +4405,12 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box) writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr); } +static void snr_uncore_mmio_init_box(struct intel_uncore_box *box) +{ + __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), + SNR_IMC_MMIO_MEM0_OFFSET); +} + static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box) { u32 config; diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 1ae4e5791afa..c7df20e78b09 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -12,7 +12,6 @@ struct amd_nb_bus_dev_range { u8 dev_limit; }; -extern const struct pci_device_id amd_nb_misc_ids[]; extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; extern bool early_is_amd_nb(u32 value); diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 31c379c1da41..cf3d621c6892 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -5,9 +5,139 @@ /* * Declare drivers belonging to specific x86 CPUs * Similar in spirit to pci_device_id and related PCI functions + * + * The wildcard initializers are in mod_devicetable.h because + * file2alias needs them. Sigh. */ - #include <linux/mod_devicetable.h> +/* Get the INTEL_FAM* model defines */ +#include <asm/intel-family.h> +/* And the X86_VENDOR_* ones */ +#include <asm/processor.h> + +/* Centaur FAM6 models */ +#define X86_CENTAUR_FAM6_C7_A 0xa +#define X86_CENTAUR_FAM6_C7_D 0xd +#define X86_CENTAUR_FAM6_NANO 0xf + +/** + * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching + * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Use only if you need all selectors. Otherwise use one of the shorter + * macros of the X86_MATCH_* family. If there is no matching shorthand + * macro, consider to add one. If you really need to wrap one of the macros + * into another macro at the usage site for good reasons, then please + * start this local macro with X86_MATCH to allow easy grepping. + */ +#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model, \ + _feature, _data) { \ + .vendor = X86_VENDOR_##_vendor, \ + .family = _family, \ + .model = _model, \ + .feature = _feature, \ + .driver_data = (unsigned long) _data \ +} + +/** + * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, \ + X86_MODEL_ANY, feature, data) + +/** + * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data) \ + X86_MATCH_VENDOR_FAM_FEATURE(vendor, X86_FAMILY_ANY, feature, data) + +/** + * X86_MATCH_FEATURE - Macro for matching a CPU feature + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_FEATURE(feature, data) \ + X86_MATCH_VENDOR_FEATURE(ANY, feature, data) + +/** + * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @model: The model number, model constant or X86_MODEL_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, \ + X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VENDOR_FAM - Match vendor and family + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments to X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set of wildcards. + */ +#define X86_MATCH_VENDOR_FAM(vendor, family, data) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data) + +/** + * X86_MATCH_INTEL_FAM6_MODEL - Match vendor INTEL, family 6 and model + * @model: The model name without the INTEL_FAM6_ prefix or ANY + * The model name is expanded to INTEL_FAM6_@model internally + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * The vendor is set to INTEL, the family to 6 and all other missing + * arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are set to wildcards. + * + * See X86_MATCH_VENDOR_FAM_MODEL_FEATURE() for further information. + */ +#define X86_MATCH_INTEL_FAM6_MODEL(model, data) \ + X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data) /* * Match specific microcode revisions. diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f3327cb56edf..242f7e872080 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -217,7 +217,7 @@ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -299,6 +299,7 @@ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 86169a24b0d8..cdcf48d52a12 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -10,6 +10,8 @@ #include <asm/mmu_context.h> #include <linux/build_bug.h> +extern unsigned long efi_fw_vendor, efi_config_table; + /* * We map the EFI regions needed for runtime services non-contiguously, * with preserved alignment on virtual addresses starting from -4G down @@ -34,8 +36,6 @@ static inline bool efi_have_uv1_memmap(void) #define EFI32_LOADER_SIGNATURE "EL32" #define EFI64_LOADER_SIGNATURE "EL64" -#define MAX_CMDLINE_ADDRESS UINT_MAX - #define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF /* @@ -180,7 +180,6 @@ extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); struct efi_setup_data { u64 fw_vendor; - u64 runtime; u64 tables; u64 smbios; u64 reserved[8]; @@ -219,7 +218,8 @@ extern void efi_thunk_runtime_setup(void); efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, unsigned long descriptor_size, u32 descriptor_version, - efi_memory_desc_t *virtual_map); + efi_memory_desc_t *virtual_map, + unsigned long systab_phys); /* arch specific definitions used by the stub code */ @@ -270,6 +270,11 @@ static inline void *efi64_zero_upper(void *p) return p; } +static inline u32 efi64_convert_status(efi_status_t status) +{ + return (u32)(status | (u64)status >> 32); +} + #define __efi64_argmap_free_pages(addr, size) \ ((addr), 0, (size)) @@ -285,11 +290,21 @@ static inline void *efi64_zero_upper(void *p) #define __efi64_argmap_locate_protocol(protocol, reg, interface) \ ((protocol), (reg), efi64_zero_upper(interface)) +#define __efi64_argmap_locate_device_path(protocol, path, handle) \ + ((protocol), (path), efi64_zero_upper(handle)) + +#define __efi64_argmap_exit(handle, status, size, data) \ + ((handle), efi64_convert_status(status), (size), (data)) + /* PCI I/O */ #define __efi64_argmap_get_location(protocol, seg, bus, dev, func) \ ((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus), \ efi64_zero_upper(dev), efi64_zero_upper(func)) +/* LoadFile */ +#define __efi64_argmap_load_file(protocol, path, policy, bufsize, buf) \ + ((protocol), (path), (policy), efi64_zero_upper(bufsize), (buf)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index 13c83fe97988..f9c00110a69a 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -12,76 +12,103 @@ #include <asm/processor.h> #include <asm/smap.h> -#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ - asm volatile("\t" ASM_STAC "\n" \ - "1:\t" insn "\n" \ - "2:\t" ASM_CLAC "\n" \ +#define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \ +do { \ + int oldval = 0, ret; \ + asm volatile("1:\t" insn "\n" \ + "2:\n" \ "\t.section .fixup,\"ax\"\n" \ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ - : "i" (-EFAULT), "0" (oparg), "1" (0)) + : "i" (-EFAULT), "0" (oparg), "1" (0)); \ + if (ret) \ + goto label; \ + *oval = oldval; \ +} while(0) -#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \ - asm volatile("\t" ASM_STAC "\n" \ - "1:\tmovl %2, %0\n" \ - "\tmovl\t%0, %3\n" \ + +#define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \ +do { \ + int oldval = 0, ret, tem; \ + asm volatile("1:\tmovl %2, %0\n" \ + "2:\tmovl\t%0, %3\n" \ "\t" insn "\n" \ - "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ - "\tjnz\t1b\n" \ - "3:\t" ASM_CLAC "\n" \ + "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ + "\tjnz\t2b\n" \ + "4:\n" \ "\t.section .fixup,\"ax\"\n" \ - "4:\tmov\t%5, %1\n" \ - "\tjmp\t3b\n" \ + "5:\tmov\t%5, %1\n" \ + "\tjmp\t4b\n" \ "\t.previous\n" \ - _ASM_EXTABLE_UA(1b, 4b) \ - _ASM_EXTABLE_UA(2b, 4b) \ + _ASM_EXTABLE_UA(1b, 5b) \ + _ASM_EXTABLE_UA(3b, 5b) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ - : "r" (oparg), "i" (-EFAULT), "1" (0)) + : "r" (oparg), "i" (-EFAULT), "1" (0)); \ + if (ret) \ + goto label; \ + *oval = oldval; \ +} while(0) -static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, +static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int oldval = 0, ret, tem; - - pagefault_disable(); + if (!user_access_begin(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: - __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg); + unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ADD: - __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval, - uaddr, oparg); + unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval, + uaddr, oparg, Efault); break; case FUTEX_OP_OR: - __futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg); + unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ANDN: - __futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg); + unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault); break; case FUTEX_OP_XOR: - __futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg); + unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault); break; default: - ret = -ENOSYS; + user_access_end(); + return -ENOSYS; } - - pagefault_enable(); - - if (!ret) - *oval = oldval; - - return ret; + user_access_end(); + return 0; +Efault: + user_access_end(); + return -EFAULT; } static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { - return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval); + int ret = 0; + + if (!user_access_begin(uaddr, sizeof(u32))) + return -EFAULT; + asm volatile("\n" + "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" + "2:\n" + "\t.section .fixup, \"ax\"\n" + "3:\tmov %3, %0\n" + "\tjmp 2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "i" (-EFAULT), "r" (newval), "1" (oldval) + : "memory" + ); + user_access_end(); + *uval = oldval; + return ret; } #endif diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 4981c293f926..8f1e94f29a16 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -35,6 +35,9 @@ * The #define line may optionally include a comment including platform names. */ +/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */ +#define INTEL_FAM6_ANY X86_MODEL_ANY + #define INTEL_FAM6_CORE_YONAH 0x0E #define INTEL_FAM6_CORE2_MEROM 0x0F @@ -118,17 +121,7 @@ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ #define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */ -/* Useful macros */ -#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data) \ -{ \ - .vendor = X86_VENDOR_INTEL, \ - .family = _family, \ - .model = _model, \ - .feature = X86_FEATURE_ANY, \ - .driver_data = (kernel_ulong_t)&_driver_data \ -} - -#define INTEL_CPU_FAM6(_model, _driver_data) \ - INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data) +/* Family 5 */ +#define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 02c6ef8f7667..07344d82e88e 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,7 +19,14 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(void); -void tss_update_io_bitmap(void); +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include <asm/paravirt.h> +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#endif + #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(void) { } diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 95b1f053bd96..073eb7ad2f56 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -36,6 +36,7 @@ typedef u8 kprobe_opcode_t; /* optinsn template addresses */ extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_clac[]; extern __visible kprobe_opcode_t optprobe_template_val[]; extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 03946eb3e2b9..c06e8353efd3 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -292,6 +292,14 @@ enum x86emul_mode { #define X86EMUL_SMM_MASK (1 << 6) #define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) +/* + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ +struct fastop; + +typedef void (*fastop_t)(struct fastop *); + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -324,7 +332,10 @@ struct x86_emulate_ctxt { struct operand src; struct operand src2; struct operand dst; - int (*execute)(struct x86_emulate_ctxt *ctxt); + union { + int (*execute)(struct x86_emulate_ctxt *ctxt); + fastop_t fop; + }; int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* * The following six fields are cleared together, @@ -349,7 +360,6 @@ struct x86_emulate_ctxt { u64 d; unsigned long _eip; struct operand memop; - /* Fields above regs are cleared together. */ unsigned long _regs[NR_VCPU_REGS]; struct operand *memopp; struct fetch_cache fetch; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 40a0c0fd95ca..98959e8cd448 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1122,6 +1122,7 @@ struct kvm_x86_ops { int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1146,7 +1147,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4359b955e0b7..9d5b09913ef3 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -102,7 +102,7 @@ #define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ -#define MCE_LOG_LEN 32 +#define MCE_LOG_MIN_LEN 32U #define MCE_LOG_SIGNATURE "MACHINECHECK" /* AMD Scalable MCA */ @@ -135,11 +135,11 @@ */ struct mce_log_buffer { char signature[12]; /* "MACHINECHECK" */ - unsigned len; /* = MCE_LOG_LEN */ + unsigned len; /* = elements in .mce_entry[] */ unsigned next; unsigned flags; unsigned recordlen; /* length of struct mce */ - struct mce entry[MCE_LOG_LEN]; + struct mce entry[]; }; enum mce_notifier_prios { diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dd..d5e517d1c3dd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 86e7317eb31f..694d8daf4983 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -295,6 +295,13 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(cpu.update_io_bitmap); +} +#endif + static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 84812964d3dd..732f62e04ddb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -140,6 +140,10 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); +#ifdef CONFIG_X86_IOPL_IOPERM + void (*update_io_bitmap)(void); +#endif + void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 29964b0e1075..e855e9cf2c37 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -50,11 +50,22 @@ #define AMD64_L3_SLICE_SHIFT 48 #define AMD64_L3_SLICE_MASK \ - ((0xFULL) << AMD64_L3_SLICE_SHIFT) + (0xFULL << AMD64_L3_SLICE_SHIFT) +#define AMD64_L3_SLICEID_MASK \ + (0x7ULL << AMD64_L3_SLICE_SHIFT) #define AMD64_L3_THREAD_SHIFT 56 #define AMD64_L3_THREAD_MASK \ - ((0xFFULL) << AMD64_L3_THREAD_SHIFT) + (0xFFULL << AMD64_L3_THREAD_SHIFT) +#define AMD64_L3_F19H_THREAD_MASK \ + (0x3ULL << AMD64_L3_THREAD_SHIFT) + +#define AMD64_L3_EN_ALL_CORES BIT_ULL(47) +#define AMD64_L3_EN_ALL_SLICES BIT_ULL(46) + +#define AMD64_L3_COREID_SHIFT 42 +#define AMD64_L3_COREID_MASK \ + (0x7ULL << AMD64_L3_COREID_SHIFT) #define X86_RAW_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_EVENT | \ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index cf4327986e98..384cdde10680 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,7 +92,6 @@ struct thread_info { #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ -#define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -122,7 +121,6 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) -#define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -133,14 +131,10 @@ struct thread_info { #define _TIF_X32 (1 << TIF_X32) #define _TIF_FSCHECK (1 << TIF_FSCHECK) -/* - * work to do in syscall_trace_enter(). Also includes TIF_NOHZ for - * enter_from_user_mode() - */ +/* Work to do before invoking the actual syscall. */ #define _TIF_WORK_SYSCALL_ENTRY \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ - _TIF_NOHZ) + _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW_BASE \ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 4b14d2318251..79d8d5496330 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -193,4 +193,29 @@ static inline void sched_clear_itmt_support(void) } #endif /* CONFIG_SCHED_MC_PRIO */ +#ifdef CONFIG_SMP +#include <asm/cpufeature.h> + +DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key); + +#define arch_scale_freq_invariant() static_branch_likely(&arch_scale_freq_key) + +DECLARE_PER_CPU(unsigned long, arch_freq_scale); + +static inline long arch_scale_freq_capacity(int cpu) +{ + return per_cpu(arch_freq_scale, cpu); +} +#define arch_scale_freq_capacity arch_scale_freq_capacity + +extern void arch_scale_freq_tick(void); +#define arch_scale_freq_tick arch_scale_freq_tick + +extern void arch_set_max_freq_ratio(bool turbo_disabled); +#else +static inline void arch_set_max_freq_ratio(bool turbo_disabled) +{ +} +#endif + #endif /* _ASM_X86_TOPOLOGY_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 61d93f062a36..ea6fc643ccfe 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -584,99 +584,6 @@ extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); -extern void __cmpxchg_wrong_size(void) - __compiletime_error("Bad argument size for cmpxchg"); - -#define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \ -({ \ - int __ret = 0; \ - __typeof__(*(ptr)) __old = (old); \ - __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin_nospec(); \ - switch (size) { \ - case 1: \ - { \ - asm volatile("\n" \ - "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \ - "2:\n" \ - "\t.section .fixup, \"ax\"\n" \ - "3:\tmov %3, %0\n" \ - "\tjmp 2b\n" \ - "\t.previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ - : "i" (-EFAULT), "q" (__new), "1" (__old) \ - : "memory" \ - ); \ - break; \ - } \ - case 2: \ - { \ - asm volatile("\n" \ - "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \ - "2:\n" \ - "\t.section .fixup, \"ax\"\n" \ - "3:\tmov %3, %0\n" \ - "\tjmp 2b\n" \ - "\t.previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ - : "i" (-EFAULT), "r" (__new), "1" (__old) \ - : "memory" \ - ); \ - break; \ - } \ - case 4: \ - { \ - asm volatile("\n" \ - "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \ - "2:\n" \ - "\t.section .fixup, \"ax\"\n" \ - "3:\tmov %3, %0\n" \ - "\tjmp 2b\n" \ - "\t.previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ - : "i" (-EFAULT), "r" (__new), "1" (__old) \ - : "memory" \ - ); \ - break; \ - } \ - case 8: \ - { \ - if (!IS_ENABLED(CONFIG_X86_64)) \ - __cmpxchg_wrong_size(); \ - \ - asm volatile("\n" \ - "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \ - "2:\n" \ - "\t.section .fixup, \"ax\"\n" \ - "3:\tmov %3, %0\n" \ - "\tjmp 2b\n" \ - "\t.previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ - : "i" (-EFAULT), "r" (__new), "1" (__old) \ - : "memory" \ - ); \ - break; \ - } \ - default: \ - __cmpxchg_wrong_size(); \ - } \ - __uaccess_end(); \ - *(uval) = __old; \ - __ret; \ -}) - -#define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \ -({ \ - access_ok((ptr), sizeof(*(ptr))) ? \ - __user_atomic_cmpxchg_inatomic((uval), (ptr), \ - (old), (new), sizeof(*(ptr))) : \ - -EFAULT; \ -}) - /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b3685..8521af3fef27 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -72,7 +72,7 @@ #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) -#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index a50e4a0de315..9915990fd8cf 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -81,6 +81,7 @@ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ #define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 503d3f42da16..3f3f780c8c65 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9b294c13809a..8be5926cce51 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,7 +28,6 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n -OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 04205ce127a1..1ae5439a9a85 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -45,6 +45,7 @@ EXPORT_SYMBOL(acpi_disabled); #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ +int acpi_nobgrt; /* skip ACPI BGRT */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); @@ -1619,7 +1620,7 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); - if (IS_ENABLED(CONFIG_ACPI_BGRT)) + if (IS_ENABLED(CONFIG_ACPI_BGRT) && !acpi_nobgrt) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) @@ -1671,6 +1672,13 @@ static int __init parse_acpi(char *arg) } early_param("acpi", parse_acpi); +static int __init parse_acpi_bgrt(char *arg) +{ + acpi_nobgrt = true; + return 0; +} +early_param("bgrt_disable", parse_acpi_bgrt); + /* FIXME: Using pci= for an ACPI parameter is a travesty. */ static int __init parse_pci(char *arg) { @@ -1740,7 +1748,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 26b7256f590f..ed3b04483972 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -43,7 +43,7 @@ unsigned long acpi_get_wakeup_address(void) * * Wrapper around acpi_enter_sleep_state() to be called by assmebly. */ -acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state) +asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state) { return acpi_enter_sleep_state(state); } diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index d06c2079b6c1..171a40c74db6 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -19,4 +19,4 @@ extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); -acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); +asmlinkage acpi_status x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 69aed0ebbdfc..b6b3297851f3 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -36,10 +36,9 @@ static const struct pci_device_id amd_root_ids[] = { {} }; - #define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 -const struct pci_device_id amd_nb_misc_ids[] = { +static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, @@ -56,7 +55,6 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; -EXPORT_SYMBOL_GPL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5f973fed3c9f..81b9c63dae1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,12 +546,6 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -#define DEADLINE_MODEL_MATCH_FUNC(model, func) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&func } - -#define DEADLINE_MODEL_MATCH_REV(model, rev) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } - static u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { @@ -588,23 +582,23 @@ static u32 skx_deadline_rev(void) } static const struct x86_cpu_id deadline_match[] = { - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X, &skx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL, 0x22), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L, 0x20), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G, 0x17), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL, 0x22), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L, 0x20), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL, 0x25), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G, 0x17), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL, 0x25), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE, 0xb2), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_L, 0xb2), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L, 0x52), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE, 0x52), + X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE_L, 0x52), + X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE, 0x52), {}, }; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..67768e54438b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -557,6 +557,12 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->hwirq = virq + i; irqd_set_single_target(irqd); /* + * Prevent that any of these interrupts is invoked in + * non interrupt context via e.g. generic_handle_irq() + * as that can corrupt the affinity move state. + */ + irqd_set_handle_enforce_irqctx(irqd); + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is * required for check_timer() to work correctly as it might @@ -838,13 +844,15 @@ static void free_moved_vector(struct apic_chip_data *apicd) bool managed = apicd->is_managed; /* - * This should never happen. Managed interrupts are not - * migrated except on CPU down, which does not involve the - * cleanup vector. But try to keep the accounting correct - * nevertheless. + * Managed interrupts are usually not migrated away + * from an online CPU, but CPU isolation 'managed_irq' + * can make that happen. + * 1) Activation does not take the isolation into account + * to keep the code simple + * 2) Migration away from an isolated CPU can happen when + * a non-isolated CPU which is in the calculated + * affinity mask comes online. */ - WARN_ON_ONCE(managed); - trace_vector_free_moved(apicd->irq, cpu, vector, managed); irq_matrix_free(vector_matrix, cpu, vector, managed); per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 5c7ee3df4d0b..3ca07ad552ae 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -88,7 +88,6 @@ static void __used common(void) OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); OFFSET(BP_init_size, boot_params, hdr.init_size); OFFSET(BP_pref_address, boot_params, hdr.pref_address); - OFFSET(BP_code32_start, boot_params, hdr.code32_start); BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 82826f2275cc..2b4256ebe86e 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -3,6 +3,8 @@ # error "Please do not build this file directly, build asm-offsets.c instead" #endif +#include <linux/efi.h> + #include <asm/ucontext.h> #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, @@ -64,4 +66,7 @@ void foo(void) BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); DEFINE(NR_syscalls, sizeof(syscalls)); + + BLANK(); + DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map)); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ac83a0fef628..547ad7bbf0e0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -28,6 +28,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -393,6 +394,35 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; } +static void amd_detect_ppin(struct cpuinfo_x86 *c) +{ + unsigned long long val; + + if (!cpu_has(c, X86_FEATURE_AMD_PPIN)) + return; + + /* When PPIN is defined in CPUID, still need to check PPIN_CTL MSR */ + if (rdmsrl_safe(MSR_AMD_PPIN_CTL, &val)) + goto clear_ppin; + + /* PPIN is locked in disabled mode, clear feature bit */ + if ((val & 3UL) == 1UL) + goto clear_ppin; + + /* If PPIN is disabled, try to enable it */ + if (!(val & 2UL)) { + wrmsrl_safe(MSR_AMD_PPIN_CTL, val | 2UL); + rdmsrl_safe(MSR_AMD_PPIN_CTL, &val); + } + + /* If PPIN_EN bit is 1, return from here; otherwise fall through */ + if (val & 2UL) + return; + +clear_ppin: + clear_cpu_cap(c, X86_FEATURE_AMD_PPIN); +} + u16 amd_get_nb_id(int cpu) { return per_cpu(cpu_llc_id, cpu); @@ -925,7 +955,8 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: init_amd_zn(c); break; + case 0x17: fallthrough; + case 0x19: init_amd_zn(c); break; } /* @@ -940,6 +971,7 @@ static void init_amd(struct cpuinfo_x86 *c) amd_detect_cmp(c); amd_get_topology(c); srat_detect_node(c); + amd_detect_ppin(c); init_amd_cacheinfo(c); @@ -972,6 +1004,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1099,6 +1140,10 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 52c9bfbbdb2a..137644a52716 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -445,7 +445,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -1008,8 +1008,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) -#define VULNWL(_vendor, _family, _model, _whitelist) \ - { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } +#define VULNWL(vendor, family, model, whitelist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) #define VULNWL_INTEL(model, whitelist) \ VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist) diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 6dd78d8235e4..d3482eb43ff3 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -16,12 +16,17 @@ * respective wildcard entries. * * A typical table entry would be to match a specific CPU - * { X86_VENDOR_INTEL, 6, 0x12 } - * or to match a specific CPU feature - * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) } + * + * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL, + * X86_FEATURE_ANY, NULL); * * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY, - * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor) + * %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor) + * + * asm/cpu_device_id.h contains a set of useful macros which are shortcuts + * for various common selections. The above can be shortened to: + * + * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL); * * Arrays used to match for this should also be declared using * MODULE_DEVICE_TABLE(x86cpu, ...) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index b3a50d962851..52de616a8065 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1260,7 +1260,7 @@ recurse: if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2c4f949611e4..dd06fce537fc 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -142,6 +142,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + else if (this_cpu_has(X86_FEATURE_AMD_PPIN)) + rdmsrl(MSR_AMD_PPIN, m->ppin); m->microcode = boot_cpu_data.microcode; } @@ -1877,6 +1879,8 @@ bool filter_mce(struct mce *m) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return amd_filter_mce(m); + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return intel_filter_mce(m); return false; } diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 7c8958dee103..d089567a9ce8 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -29,11 +29,7 @@ static char *mce_helper_argv[2] = { mce_helper, NULL }; * separate MCEs from kernel messages to avoid bogus bug reports. */ -static struct mce_log_buffer mcelog = { - .signature = MCE_LOG_SIGNATURE, - .len = MCE_LOG_LEN, - .recordlen = sizeof(struct mce), -}; +static struct mce_log_buffer *mcelog; static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); @@ -45,21 +41,21 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, mutex_lock(&mce_chrdev_read_mutex); - entry = mcelog.next; + entry = mcelog->next; /* * When the buffer fills up discard new entries. Assume that the * earlier errors are the more interesting ones: */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags); + if (entry >= mcelog->len) { + set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog->flags); goto unlock; } - mcelog.next = entry + 1; + mcelog->next = entry + 1; - memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - mcelog.entry[entry].finished = 1; + memcpy(mcelog->entry + entry, mce, sizeof(struct mce)); + mcelog->entry[entry].finished = 1; /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); @@ -214,21 +210,21 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, /* Only supports full reads right now */ err = -EINVAL; - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) + if (*off != 0 || usize < mcelog->len * sizeof(struct mce)) goto out; - next = mcelog.next; + next = mcelog->next; err = 0; for (i = 0; i < next; i++) { - struct mce *m = &mcelog.entry[i]; + struct mce *m = &mcelog->entry[i]; err |= copy_to_user(buf, m, sizeof(*m)); buf += sizeof(*m); } - memset(mcelog.entry, 0, next * sizeof(struct mce)); - mcelog.next = 0; + memset(mcelog->entry, 0, next * sizeof(struct mce)); + mcelog->next = 0; if (err) err = -EFAULT; @@ -242,7 +238,7 @@ out: static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (READ_ONCE(mcelog.next)) + if (READ_ONCE(mcelog->next)) return EPOLLIN | EPOLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return EPOLLIN | EPOLLRDNORM; @@ -261,13 +257,13 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, case MCE_GET_RECORD_LEN: return put_user(sizeof(struct mce), p); case MCE_GET_LOG_LEN: - return put_user(MCE_LOG_LEN, p); + return put_user(mcelog->len, p); case MCE_GETCLEAR_FLAGS: { unsigned flags; do { - flags = mcelog.flags; - } while (cmpxchg(&mcelog.flags, flags, 0) != flags); + flags = mcelog->flags; + } while (cmpxchg(&mcelog->flags, flags, 0) != flags); return put_user(flags, p); } @@ -339,8 +335,18 @@ static struct miscdevice mce_chrdev_device = { static __init int dev_mcelog_init_device(void) { + int mce_log_len; int err; + mce_log_len = max(MCE_LOG_MIN_LEN, num_online_cpus()); + mcelog = kzalloc(sizeof(*mcelog) + mce_log_len * sizeof(struct mce), GFP_KERNEL); + if (!mcelog) + return -ENOMEM; + + strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); + mcelog->len = mce_log_len; + mcelog->recordlen = sizeof(struct mce); + /* register character device /dev/mcelog */ err = misc_register(&mce_chrdev_device); if (err) { @@ -350,6 +356,7 @@ static __init int dev_mcelog_init_device(void) else pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + kfree(mcelog); return err; } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 5627b1091b85..d8f9230d2034 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -493,17 +493,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } @@ -520,3 +521,20 @@ void mce_intel_feature_clear(struct cpuinfo_x86 *c) { intel_clear_lmce(); } + +bool intel_filter_mce(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */ + if ((c->x86 == 6) && + ((c->x86_model == INTEL_FAM6_HASWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_L) || + (c->x86_model == INTEL_FAM6_BROADWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_G)) && + (m->bank == 0) && + ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) + return true; + + return false; +} diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index b785c0d0b590..97db18441d2c 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -48,6 +48,7 @@ void cmci_disable_bank(int bank); void intel_init_cmci(void); void intel_init_lmce(void); void intel_clear_lmce(void); +bool intel_filter_mce(struct mce *m); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } @@ -56,6 +57,7 @@ static inline void cmci_disable_bank(int bank) { } static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } static inline void intel_clear_lmce(void) { } +static inline bool intel_filter_mce(struct mce *m) { return false; }; #endif void mce_timer_kick(unsigned long interval); diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 58b4ee3cda77..f36dc0742085 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -486,9 +486,14 @@ static int thermal_throttle_offline(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; + + /* Mask the thermal vector before draining evtl. pending work */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); - cancel_delayed_work(&state->package_throttle.therm_work); - cancel_delayed_work(&state->core_throttle.therm_work); + cancel_delayed_work_sync(&state->package_throttle.therm_work); + cancel_delayed_work_sync(&state->core_throttle.therm_work); state->package_throttle.rate_control_active = false; state->core_throttle.rate_control_active = false; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 3923ab4630d7..f66a6b90f954 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -67,11 +67,6 @@ __HEAD SYM_CODE_START(startup_32) movl pa(initial_stack),%ecx - /* test KEEP_SEGMENTS flag to see if the bootloader is asking - us to not reload segments */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 2f - /* * Set segments to known values. */ @@ -82,7 +77,6 @@ SYM_CODE_START(startup_32) movl %eax,%fs movl %eax,%gs movl %eax,%ss -2: leal -__PAGE_OFFSET(%ecx),%esp /* diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4d4f5d9faac3..7dfb1e808928 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -19,13 +17,13 @@ static enum efi_secureboot_mode get_sb_mode(void) size = sizeof(secboot); - if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) { pr_info("ima: secureboot mode unknown, no efi\n"); return efi_secureboot_mode_unknown; } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index f293d872602a..db6578d45157 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -141,9 +141,8 @@ prepare_add_efi_setup_data(struct boot_params *params, struct setup_data *sd = (void *)params + efi_setup_data_offset; struct efi_setup_data *esd = (void *)sd + sizeof(struct setup_data); - esd->fw_vendor = efi.fw_vendor; - esd->runtime = efi.runtime; - esd->tables = efi.config_table; + esd->fw_vendor = efi_fw_vendor; + esd->tables = efi_config_table; esd->smbios = efi.smbios; sd->type = SETUP_EFI; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3f45b5c43a71..ea13f6888284 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -71,6 +71,21 @@ found: return (unsigned long)buf; } +static void synthesize_clac(kprobe_opcode_t *addr) +{ + /* + * Can't be static_cpu_has() due to how objtool treats this feature bit. + * This isn't a fast path anyway. + */ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return; + + /* Replace the NOP3 with CLAC */ + addr[0] = 0x0f; + addr[1] = 0x01; + addr[2] = 0xca; +} + /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) { @@ -92,6 +107,9 @@ asm ( /* We don't bother saving the ss register */ " pushq %rsp\n" " pushfq\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 SAVE_REGS_STRING " movq %rsp, %rsi\n" ".global optprobe_template_val\n" @@ -111,6 +129,9 @@ asm ( #else /* CONFIG_X86_32 */ " pushl %esp\n" " pushfl\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 SAVE_REGS_STRING " movl %esp, %edx\n" ".global optprobe_template_val\n" @@ -134,6 +155,8 @@ asm ( void optprobe_template_func(void); STACK_FRAME_NON_STANDARD(optprobe_template_func); +#define TMPL_CLAC_IDX \ + ((long)optprobe_template_clac - (long)optprobe_template_entry) #define TMPL_MOVE_IDX \ ((long)optprobe_template_val - (long)optprobe_template_entry) #define TMPL_CALL_IDX \ @@ -389,6 +412,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, op->optinsn.size = ret; len = TMPL_END_IDX + op->optinsn.size; + synthesize_clac(buf + TMPL_CLAC_IDX); + /* Set probe information */ synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d817f255aed8..6efe0410fb72 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -425,7 +425,29 @@ static void __init sev_map_percpu_data(void) } } +static bool pv_tlb_flush_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); + #ifdef CONFIG_SMP + +static bool pv_ipi_supported(void) +{ + return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); +} + +static bool pv_sched_yield_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) static void __send_ipi_mask(const struct cpumask *mask, int vector) @@ -490,12 +512,12 @@ static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); const struct cpumask *local_mask; - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; + cpumask_copy(new_mask, mask); + cpumask_clear_cpu(this_cpu, new_mask); + local_mask = new_mask; __send_ipi_mask(local_mask, vector); } @@ -575,7 +597,6 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) @@ -583,7 +604,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask, u8 state; int cpu; struct kvm_steal_time *src; - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); cpumask_copy(flushmask, cpumask); /* @@ -619,11 +640,10 @@ static void __init kvm_guest_init(void) pv_ops.time.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) { pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; pv_ops.mmu.tlb_remove_table = tlb_remove_table; + pr_info("KVM setup pv remote TLB flush\n"); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -632,9 +652,7 @@ static void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_sched_yield_supported()) { smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; pr_info("KVM setup pv sched yield\n"); } @@ -700,7 +718,7 @@ static uint32_t __init kvm_detect(void) static void __init kvm_apic_init(void) { #if defined(CONFIG_SMP) - if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI)) + if (pv_ipi_supported()) kvm_setup_pv_ipi(); #endif } @@ -732,26 +750,31 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); -static __init int kvm_setup_pv_tlb_flush(void) +static __init int kvm_alloc_cpumask(void) { int cpu; + bool alloc = false; if (!kvm_para_available() || nopv) return 0; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) + alloc = true; + +#if defined(CONFIG_SMP) + if (pv_ipi_supported()) + alloc = true; +#endif + + if (alloc) for_each_possible_cpu(cpu) { - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); } - pr_info("KVM setup pv remote TLB flush\n"); - } return 0; } -arch_initcall(kvm_setup_pv_tlb_flush); +arch_initcall(kvm_alloc_cpumask); #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89de..c131ba4e70ef 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include <asm/timer.h> #include <asm/special_insns.h> #include <asm/tlb.h> +#include <asm/io_bitmap.h> /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7..3053c85e0e42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index ef3ba99068d3..a4d9a261425b 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -9,6 +9,8 @@ #include <asm/kexec.h> #include <asm/processor-flags.h> #include <asm/pgtable_types.h> +#include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> /* * Must be relocatable PIC code callable as a C function @@ -39,6 +41,7 @@ .align PAGE_SIZE .code64 SYM_CODE_START_NOALIGN(relocate_kernel) + UNWIND_HINT_EMPTY /* * %rdi indirection_page * %rsi page_list @@ -105,6 +108,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) + UNWIND_HINT_EMPTY /* set return address to 0 if not preserving context */ pushq $0 /* store the start address on the stack */ @@ -192,14 +196,12 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) 1: popq %rdx leaq PAGE_SIZE(%r10), %rsp + ANNOTATE_RETPOLINE_SAFE call *%rdx /* get the re-entry point of the peer system */ movq 0(%rsp), %rbp - call 1f -1: - popq %r8 - subq $(1b - relocate_kernel), %r8 + leaq relocate_kernel(%rip), %r8 movq CP_PA_SWAP_PAGE(%r8), %r10 movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi movq CP_PA_TABLE_PAGE(%r8), %rax @@ -212,6 +214,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) + UNWIND_HINT_EMPTY movq RSP(%r8), %rsp movq CR4(%r8), %rax movq %rax, %cr4 @@ -233,6 +236,7 @@ SYM_CODE_END(virtual_mapped) /* Do the copies */ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) + UNWIND_HINT_EMPTY movq %rdi, %rcx /* Put the page_list in %rcx */ xorl %edi, %edi xorl %esi, %esi diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 69881b2d446c..d59525d2ead3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -147,6 +147,8 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } +static void init_freq_invariance(void); + /* * Report back to the Boot Processor during boot time or to the caller processor * during CPU online. @@ -183,6 +185,8 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); + init_freq_invariance(); + /* * Get our bogomips. * Update loops_per_jiffy in cpu_data. Previous call to @@ -466,7 +470,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) */ static const struct x86_cpu_id snc_cpu[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL), {} }; @@ -1337,7 +1341,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - + init_freq_invariance(); smp_sanity_check(); switch (apic_intr_mode) { @@ -1764,3 +1768,287 @@ void native_play_dead(void) } #endif + +/* + * APERF/MPERF frequency ratio computation. + * + * The scheduler wants to do frequency invariant accounting and needs a <1 + * ratio to account for the 'current' frequency, corresponding to + * freq_curr / freq_max. + * + * Since the frequency freq_curr on x86 is controlled by micro-controller and + * our P-state setting is little more than a request/hint, we need to observe + * the effective frequency 'BusyMHz', i.e. the average frequency over a time + * interval after discarding idle time. This is given by: + * + * BusyMHz = delta_APERF / delta_MPERF * freq_base + * + * where freq_base is the max non-turbo P-state. + * + * The freq_max term has to be set to a somewhat arbitrary value, because we + * can't know which turbo states will be available at a given point in time: + * it all depends on the thermal headroom of the entire package. We set it to + * the turbo level with 4 cores active. + * + * Benchmarks show that's a good compromise between the 1C turbo ratio + * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, + * which would ignore the entire turbo range (a conspicuous part, making + * freq_curr/freq_max always maxed out). + * + * An exception to the heuristic above is the Atom uarch, where we choose the + * highest turbo level for freq_max since Atom's are generally oriented towards + * power efficiency. + * + * Setting freq_max to anything less than the 1C turbo ratio makes the ratio + * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. + */ + +DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); + +static DEFINE_PER_CPU(u64, arch_prev_aperf); +static DEFINE_PER_CPU(u64, arch_prev_mperf); +static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; +static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; + +void arch_set_max_freq_ratio(bool turbo_disabled) +{ + arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : + arch_turbo_freq_ratio; +} + +static bool turbo_disabled(void) +{ + u64 misc_en; + int err; + + err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); + if (err) + return false; + + return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); +} + +static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ + *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ + + return true; +} + +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +#define ICPU(model) \ + {X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0} + +static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_XEON_PHI_KNL), + ICPU(INTEL_FAM6_XEON_PHI_KNM), + {} +}; + +static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_SKYLAKE_X), + {} +}; + +static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_ATOM_GOLDMONT), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_D), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS), + {} +}; + +static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, + int num_delta_fratio) +{ + int fratio, delta_fratio, found; + int err, i; + u64 msr; + + if (!x86_match_cpu(has_knl_turbo_ratio_limits)) + return false; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + fratio = (msr >> 8) & 0xFF; + i = 16; + found = 0; + do { + if (found >= num_delta_fratio) { + *turbo_freq = fratio; + return true; + } + + delta_fratio = (msr >> (i + 5)) & 0x7; + + if (delta_fratio) { + found += 1; + fratio -= delta_fratio; + } + + i += 8; + } while (i < 64); + + return true; +} + +static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) +{ + u64 ratios, counts; + u32 group_size; + int err, i; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); + if (err) + return false; + + for (i = 0; i < 64; i += 8) { + group_size = (counts >> i) & 0xFF; + if (group_size >= size) { + *turbo_freq = (ratios >> i) & 0xFF; + return true; + } + } + + return false; +} + +static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */ + + return true; +} + +static bool intel_set_max_freq_ratio(void) +{ + u64 base_freq, turbo_freq; + + if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + if (x86_match_cpu(has_glm_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_skx_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) + goto out; + + if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + return false; + +out: + arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, + base_freq); + arch_set_max_freq_ratio(turbo_disabled()); + return true; +} + +static void init_counter_refs(void *arg) +{ + u64 aperf, mperf; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + + this_cpu_write(arch_prev_aperf, aperf); + this_cpu_write(arch_prev_mperf, mperf); +} + +static void init_freq_invariance(void) +{ + bool ret = false; + + if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF)) + return; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + ret = intel_set_max_freq_ratio(); + + if (ret) { + on_each_cpu(init_counter_refs, NULL, 1); + static_branch_enable(&arch_scale_freq_key); + } else { + pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); + } +} + +DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; + +void arch_scale_freq_tick(void) +{ + u64 freq_scale; + u64 aperf, mperf; + u64 acnt, mcnt; + + if (!arch_scale_freq_invariant()) + return; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + + acnt = aperf - this_cpu_read(arch_prev_aperf); + mcnt = mperf - this_cpu_read(arch_prev_mperf); + if (!mcnt) + return; + + this_cpu_write(arch_prev_aperf, aperf); + this_cpu_write(arch_prev_mperf, mperf); + + acnt <<= 2*SCHED_CAPACITY_SHIFT; + mcnt *= arch_max_freq_ratio; + + freq_scale = div64_u64(acnt, mcnt); + + if (freq_scale > SCHED_CAPACITY_SCALE) + freq_scale = SCHED_CAPACITY_SCALE; + + this_cpu_write(arch_freq_scale, freq_scale); +} diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index be5bc2e47c71..b8810ebbc8ae 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -59,39 +59,29 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug); */ int _debug_hotplug_cpu(int cpu, int action) { - struct device *dev = get_cpu_device(cpu); int ret; if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - lock_device_hotplug(); - switch (action) { case 0: - ret = cpu_down(cpu); - if (!ret) { + ret = remove_cpu(cpu); + if (!ret) pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu); - dev->offline = true; - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); - } else + else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: - ret = cpu_up(cpu); - if (!ret) { - dev->offline = false; - kobject_uevent(&dev->kobj, KOBJ_ONLINE); - } else { + ret = add_cpu(cpu); + if (ret) pr_debug("Can't online CPU%d.\n", cpu); - } + break; default: ret = -EINVAL; } - unlock_device_hotplug(); - return ret; } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index e0cbe4f2af49..bf528aae8ece 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -63,13 +63,13 @@ static const struct freq_desc freq_desc_lgm = { }; static const struct x86_cpu_id tsc_msr_cpu_ids[] = { - INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw), - INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv), - INTEL_CPU_FAM6(ATOM_SILVERMONT, freq_desc_byt), - INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng), - INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht), - INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann), - INTEL_CPU_FAM6(ATOM_AIRMONT_NP, freq_desc_lgm), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID, &freq_desc_pnw), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_TABLET,&freq_desc_clv), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &freq_desc_byt), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &freq_desc_tng), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &freq_desc_cht), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID, &freq_desc_ann), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_NP, &freq_desc_lgm), {} }; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 991019d5eee1..9fea0757db92 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -59,6 +59,19 @@ config KVM If unsure, say N. +config KVM_WERROR + bool "Compile KVM with -Werror" + # KASAN may cause the build to fail due to larger frames + default y if X86_64 && !KASAN + # We use the dependency on !COMPILE_TEST to not be enabled + # blindly in allmodconfig or allyesconfig configurations + depends on (X86_64 && !KASAN) || !COMPILE_TEST + depends on EXPERT + help + Add -Werror to the build flags for KVM. + + If in doubt, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b19ef421084d..e553f0fdd87d 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y += -Iarch/x86/kvm +ccflags-$(CONFIG_KVM_WERROR) += -Werror KVM := ../../../virt/kvm diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227..bc00642e5d3b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -191,25 +191,6 @@ #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * fastop functions are declared as taking a never-defined fastop parameter, - * so they can't be called from C directly. - */ - -struct fastop; - struct opcode { u64 flags : 56; u64 intercept : 8; @@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -typedef void (*fastop_t)(struct fastop *); - +/* + * fastop functions have a special calling convention: + * + * dst: rax (in/out) + * src: rdx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ @@ -5181,6 +5173,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { @@ -5683,7 +5676,7 @@ special_insn: if (ctxt->execute) { if (ctxt->d & Fastop) - rc = fastop(ctxt, (fastop_t)ctxt->execute); + rc = fastop(ctxt, ctxt->fop); else rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 7668fed1ce65..750ff0b29404 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -378,12 +378,15 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; - irq.shorthand = APIC_DEST_NOSHORT; irq.vector = e->fields.vector; irq.delivery_mode = e->fields.delivery_mode << 8; - irq.dest_id = e->fields.dest_id; irq.dest_mode = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + irq.level = false; + irq.trig_mode = e->fields.trig_mode; + irq.shorthand = APIC_DEST_NOSHORT; + irq.dest_id = e->fields.dest_id; + irq.msi_redir_hint = false; bitmap_zero(&vcpu_bitmap, 16); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, &vcpu_bitmap); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 79afa0bb5f41..c47d2acec529 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afcd30d44cbb..7356a56e6282 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1446,6 +1445,8 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) } } +static void cancel_hv_timer(struct kvm_lapic *apic); + static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & @@ -1455,6 +1456,10 @@ static void apic_update_lvtt(struct kvm_lapic *apic) if (apic_lvtt_tscdeadline(apic) != (timer_mode == APIC_LVT_TIMER_TSCDEADLINE)) { hrtimer_cancel(&apic->lapic_timer.timer); + preempt_disable(); + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + preempt_enable(); kvm_lapic_set_reg(apic, APIC_TMICT, 0); apic->lapic_timer.period = 0; apic->lapic_timer.tscdeadline = 0; @@ -1716,7 +1721,7 @@ static void start_sw_period(struct kvm_lapic *apic) hrtimer_start(&apic->lapic_timer.timer, apic->lapic_timer.target_expiration, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1..ffcd96fc02d0 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index bef0ba35f121..216364cb65a3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -48,6 +48,7 @@ #include <asm/kvm_para.h> #include <asm/irq_remapping.h> #include <asm/spec-ctrl.h> +#include <asm/cpu_device_id.h> #include <asm/virtext.h> #include "trace.h" @@ -57,11 +58,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id svm_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_SVM), + X86_MATCH_FEATURE(X86_FEATURE_SVM, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); +#endif #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 @@ -1005,33 +1008,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1350,6 +1352,24 @@ static __init void svm_adjust_mmio_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } +static void svm_hardware_teardown(void) +{ + int cpu; + + if (svm_sev_enabled()) { + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } + + for_each_possible_cpu(cpu) + svm_cpu_uninit(cpu); + + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1463,29 +1483,10 @@ static __init int svm_hardware_setup(void) return 0; err: - __free_pages(iopm_pages, IOPM_ALLOC_ORDER); - iopm_base = 0; + svm_hardware_teardown(); return r; } -static __exit void svm_hardware_unsetup(void) -{ - int cpu; - - if (svm_sev_enabled()) { - bitmap_free(sev_asid_bitmap); - bitmap_free(sev_reclaim_asid_bitmap); - - sev_flush_asids(); - } - - for_each_possible_cpu(cpu) - svm_cpu_uninit(cpu); - - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = 0; -} - static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; @@ -1933,14 +1934,6 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) static void __unregister_enc_region_locked(struct kvm *kvm, struct enc_region *region) { - /* - * The guest may change the memory encryption attribute from C=0 -> C=1 - * or vice versa for this memory range. Lets make sure caches are - * flushed to ensure that guest data gets written into memory with - * correct C-bit. - */ - sev_clflush_pages(region->pages, region->npages); - sev_unpin_memory(kvm, region->pages, region->npages); list_del(®ion->list); kfree(region); @@ -1971,6 +1964,13 @@ static void sev_vm_destroy(struct kvm *kvm) mutex_lock(&kvm->lock); /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + + /* * if userspace was terminated before unregistering the memory regions * then lets unpin all the registered memory. */ @@ -2196,8 +2196,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static int avic_init_vcpu(struct vcpu_svm *svm) { int ret; + struct kvm_vcpu *vcpu = &svm->vcpu; - if (!kvm_vcpu_apicv_active(&svm->vcpu)) + if (!avic || !irqchip_in_kernel(vcpu->kvm)) return 0; ret = avic_init_backing_page(&svm->vcpu); @@ -5232,6 +5233,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); + if (!avic) + return; + if (activated) { /** * During AVIC temporary deactivation, guest could update @@ -5255,8 +5259,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5268,6 +5275,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) put_cpu(); } else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -6303,7 +6312,8 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, enum exit_fastpath_completion *exit_fastpath) { if (!is_guest_mode(vcpu) && - to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && + to_svm(vcpu)->vmcb->control.exit_info_1) *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } @@ -7148,6 +7158,9 @@ static int svm_mem_enc_op(struct kvm *kvm, void __user *argp) if (!svm_sev_enabled()) return -ENOTTY; + if (!argp) + return 0; + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) return -EFAULT; @@ -7275,6 +7288,13 @@ static int svm_unregister_enc_region(struct kvm *kvm, goto failed; } + /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + __unregister_enc_region_locked(kvm, region); mutex_unlock(&kvm->lock); @@ -7378,7 +7398,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .hardware_unsetup = svm_hardware_unsetup, + .hardware_unsetup = svm_hardware_teardown, .check_processor_compatibility = svm_check_processor_compat, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, @@ -7433,6 +7453,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .run = svm_vcpu_run, .handle_exit = handle_exit, .skip_emulated_instruction = skip_emulated_instruction, + .update_emulated_instruction = NULL, .set_interrupt_shadow = svm_set_interrupt_shadow, .get_interrupt_shadow = svm_get_interrupt_shadow, .patch_hypercall = svm_patch_hypercall, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 283bdb7071af..f486e2606247 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 3589cd3c0fcc..9750e590c89d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -224,7 +224,7 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) return; kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs_vmptr = -1ull; + vmx->nested.hv_evmcs_vmptr = 0; vmx->nested.hv_evmcs = NULL; } @@ -1923,7 +1923,8 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) return 1; - if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { + if (unlikely(!vmx->nested.hv_evmcs || + evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { if (!vmx->nested.hv_evmcs) vmx->nested.current_vmptr = -1ull; @@ -3161,10 +3162,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. * * Returns: - * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode - * NVMX_ENTRY_VMFAIL: Consistency check VMFail - * NVMX_ENTRY_VMEXIT: Consistency check VMExit - * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error + * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_VMENTRY_VMFAIL: Consistency check VMFail + * NVMX_VMENTRY_VMEXIT: Consistency check VMExit + * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error */ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) @@ -3609,8 +3610,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; + /* + * Clear the MTF state. If a higher priority VM-exit is delivered first, + * this state is discarded. + */ + vmx->nested.mtf_pending = false; + if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) @@ -3621,8 +3629,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ + if (vcpu->arch.exception.pending && + !vmx_pending_dbg_trap(vcpu) && + nested_vmx_check_exception(vcpu, &exit_qual)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 0; + } + + if (mtf_pending) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); + return 0; + } + if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + nested_vmx_check_exception(vcpu, &exit_qual)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -5285,24 +5313,17 @@ fail: return 1; } - -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -5329,8 +5350,26 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an MSR access access, + * Return 1 if we should exit from L2 to L1 to handle an MSR access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed * disinterest in the current event (read or write a specific MSR) by using an * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. @@ -5712,6 +5751,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + + if (vmx->nested.mtf_pending) + kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; } } @@ -5892,6 +5934,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + vmx->nested.mtf_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); + ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != -1ull) { @@ -5949,8 +5994,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5977,7 +6021,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index fc874d4ead0f..9aeda46f473e 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,8 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); @@ -34,6 +33,8 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -175,6 +176,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12) +{ + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3be25ecae145..22aac046a8df 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -31,6 +31,7 @@ #include <asm/apic.h> #include <asm/asm.h> #include <asm/cpu.h> +#include <asm/cpu_device_id.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/internal.h> @@ -64,11 +65,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id vmx_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_VMX), + X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); +#endif bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); @@ -95,7 +98,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -1175,6 +1178,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1599,6 +1606,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 1; } + +/* + * Recognizes a pending MTF VM-exit and records the nested state for later + * delivery. + */ +static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!is_guest_mode(vcpu)) + return; + + /* + * Per the SDM, MTF takes priority over debug-trap exceptions besides + * T-bit traps. As instruction emulation is completed (i.e. at the + * instruction boundary), any #DB exception pending delivery must be a + * debug-trap. Record the pending MTF state to be delivered in + * vmx_check_nested_events(). + */ + if (nested_cpu_has_mtf(vmcs12) && + (!vcpu->arch.exception.pending || + vcpu->arch.exception.nr == DB_VECTOR)) + vmx->nested.mtf_pending = true; + else + vmx->nested.mtf_pending = false; +} + +static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + vmx_update_emulated_instruction(vcpu); + return skip_emulated_instruction(vcpu); +} + static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* @@ -2298,6 +2339,17 @@ static void hardware_disable(void) kvm_cpu_vmxoff(); } +/* + * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID + * directly instead of going through cpu_has(), to ensure KVM is trapping + * ENCLS whenever it's supported in hardware. It does not matter whether + * the host OS supports or has enabled SGX. + */ +static bool cpu_has_sgx(void) +{ + return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); +} + static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { @@ -2378,8 +2430,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_ENCLS_EXITING; + SECONDARY_EXEC_ENABLE_VMFUNC; + if (cpu_has_sgx()) + opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -3818,24 +3871,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -6230,7 +6288,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) #endif ASM_CALL_CONSTRAINT : - THUNK_TARGET(entry), + [thunk_target]"r"(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -6482,8 +6540,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -6757,8 +6818,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6839,8 +6899,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -7101,6 +7160,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -7108,19 +7201,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + switch (info->intercept) { /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7702,7 +7821,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7786,7 +7905,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd70..e64da06c7009 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -150,6 +150,9 @@ struct nested_vmx { /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + /* Pending MTF VM-exit into L1. */ + bool mtf_pending; + struct loaded_vmcs vmcs02; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0e7ef2955db3..bf8564d73fc3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1554,7 +1554,10 @@ EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); */ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) { - if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) && + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic)) + return 1; + + if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) && ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { @@ -2444,7 +2447,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; - WARN_ON((s64)vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -6891,6 +6893,8 @@ restart: kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); + if (kvm_x86_ops->update_emulated_instruction) + kvm_x86_ops->update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -7188,14 +7192,16 @@ static void kvm_timer_init(void) if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { #ifdef CONFIG_CPU_FREQ - struct cpufreq_policy policy; + struct cpufreq_policy *policy; int cpu; - memset(&policy, 0, sizeof(policy)); cpu = get_cpu(); - cpufreq_get_policy(&policy, cpu); - if (policy.cpuinfo.max_freq) - max_tsc_khz = policy.cpuinfo.max_freq; + policy = cpufreq_cpu_get(cpu); + if (policy) { + if (policy->cpuinfo.max_freq) + max_tsc_khz = policy->cpuinfo.max_freq; + cpufreq_cpu_put(policy); + } put_cpu(); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, @@ -7306,12 +7312,12 @@ int kvm_arch_init(void *opaque) } if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); + pr_err_ratelimited("kvm: no hardware support\n"); r = -EOPNOTSUPP; goto out; } if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); + pr_err_ratelimited("kvm: disabled by bios\n"); r = -EOPNOTSUPP; goto out; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 64229dad7eab..69309cd56fdf 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -363,13 +363,8 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, { const struct ptdump_range ptdump_ranges[] = { #ifdef CONFIG_X86_64 - -#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1)) -#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \ - normalize_addr_shift) - {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2}, - {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL}, + {GUARD_HOLE_END_ADDR, ~0UL}, #else {0, ~0UL}, #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa4ea09593ab..629fdf13f846 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,7 +190,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } -void vmalloc_sync_all(void) +static void vmalloc_sync(void) { unsigned long address; @@ -217,6 +217,16 @@ void vmalloc_sync_all(void) } } +void vmalloc_sync_mappings(void) +{ + vmalloc_sync(); +} + +void vmalloc_sync_unmappings(void) +{ + vmalloc_sync(); +} + /* * 32-bit: * @@ -319,11 +329,23 @@ out: #else /* CONFIG_X86_64: */ -void vmalloc_sync_all(void) +void vmalloc_sync_mappings(void) { + /* + * 64-bit mappings might allocate new p4d/pud pages + * that need to be propagated to all tasks' PGDs. + */ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); } +void vmalloc_sync_unmappings(void) +{ + /* + * Unmappings never allocate or free p4d/pud pages. + * No work is required here. + */ +} + /* * 64-bit: * diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 44e4beb4239f..18c637c0dc6f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -106,6 +106,22 @@ static unsigned int __ioremap_check_encrypted(struct resource *res) return 0; } +/* + * The EFI runtime services data area is not covered by walk_mem_res(), but must + * be mapped encrypted when SEV is active. + */ +static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc) +{ + if (!sev_active()) + return; + + if (!IS_ENABLED(CONFIG_EFI)) + return; + + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + desc->flags |= IORES_MAP_ENCRYPTED; +} + static int __ioremap_collect_map_flags(struct resource *res, void *arg) { struct ioremap_desc *desc = arg; @@ -124,6 +140,9 @@ static int __ioremap_collect_map_flags(struct resource *res, void *arg) * To avoid multiple resource walks, this function walks resources marked as * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES). + * + * After that, deal with misc other ranges in __ioremap_check_other() which do + * not fall into the above category. */ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, struct ioremap_desc *desc) @@ -135,6 +154,8 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, memset(desc, 0, sizeof(struct ioremap_desc)); walk_mem_res(start, end, desc, __ioremap_collect_map_flags); + + __ioremap_check_other(addr, desc); } /* diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 673de6063345..109325d77b3e 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -386,7 +386,7 @@ static void enter_uniprocessor(void) put_online_cpus(); for_each_cpu(cpu, downed_cpus) { - err = cpu_down(cpu); + err = remove_cpu(cpu); if (!err) pr_info("CPU%d is down.\n", cpu); else @@ -406,7 +406,7 @@ static void leave_uniprocessor(void) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { - err = cpu_up(cpu); + err = add_cpu(cpu); if (!err) pr_info("enabled CPU%d.\n", cpu); else diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 393d251798c0..4d2a7a764602 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2039,10 +2039,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } /* and dreg_lo,sreg_lo */ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); - /* and dreg_hi,sreg_hi */ - EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); - /* or dreg_lo,dreg_hi */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + if (is_jmp64) { + /* and dreg_hi,sreg_hi */ + EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); + /* or dreg_lo,dreg_hi */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + } goto emit_cond_jmp; } case BPF_JMP | BPF_JSET | BPF_K: diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index ee6b0780bea1..f8ed5f66cd20 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -117,17 +117,16 @@ static void punit_dbgfs_unregister(void) debugfs_remove_recursive(punit_dbg_file); } -#define ICPU(model, drv_data) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\ - (kernel_ulong_t)&drv_data } +#define X86_MATCH(model, data) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ + X86_FEATURE_MWAIT, data) static const struct x86_cpu_id intel_punit_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt), - ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, punit_device_tng), - ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht), + X86_MATCH(ATOM_SILVERMONT, &punit_device_byt), + X86_MATCH(ATOM_SILVERMONT_MID, &punit_device_tng), + X86_MATCH(ATOM_AIRMONT, &punit_device_cht), {} }; - MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids); static int __init punit_atom_debug_init(void) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index ae923ee8e2b4..1aae5302501d 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,10 +54,16 @@ #include <asm/x86_init.h> #include <asm/uv/uv.h> -static efi_system_table_t efi_systab __initdata; -static u64 efi_systab_phys __initdata; +static unsigned long efi_systab_phys __initdata; +static unsigned long prop_phys = EFI_INVALID_TABLE_ADDR; +static unsigned long uga_phys = EFI_INVALID_TABLE_ADDR; +static unsigned long efi_runtime, efi_nr_tables; -static efi_config_table_type_t arch_tables[] __initdata = { +unsigned long efi_fw_vendor, efi_config_table; + +static const efi_config_table_type_t arch_tables[] __initconst = { + {EFI_PROPERTIES_TABLE_GUID, "PROP", &prop_phys}, + {UGA_IO_PROTOCOL_GUID, "UGA", &uga_phys}, #ifdef CONFIG_X86_UV {UV_SYSTEM_TABLE_GUID, "UVsystab", &uv_systab_phys}, #endif @@ -65,26 +71,26 @@ static efi_config_table_type_t arch_tables[] __initdata = { }; static const unsigned long * const efi_tables[] = { - &efi.mps, &efi.acpi, &efi.acpi20, &efi.smbios, &efi.smbios3, - &efi.boot_info, - &efi.hcdp, - &efi.uga, + &uga_phys, #ifdef CONFIG_X86_UV &uv_systab_phys, #endif - &efi.fw_vendor, - &efi.runtime, - &efi.config_table, + &efi_fw_vendor, + &efi_runtime, + &efi_config_table, &efi.esrt, - &efi.properties_table, - &efi.mem_attr_table, + &prop_phys, + &efi_mem_attr_table, #ifdef CONFIG_EFI_RCI2_TABLE &rci2_table_phys, #endif + &efi.tpm_log, + &efi.tpm_final_log, + &efi_rng_seed, }; u64 efi_setup; /* efi setup_data physical address */ @@ -214,16 +220,13 @@ int __init efi_memblock_x86_reserve_range(void) if (efi_enabled(EFI_PARAVIRT)) return 0; -#ifdef CONFIG_X86_32 - /* Can't handle data above 4GB at this time */ - if (e->efi_memmap_hi) { + /* Can't handle firmware tables above 4GB on i386 */ + if (IS_ENABLED(CONFIG_X86_32) && e->efi_memmap_hi > 0) { pr_err("Memory map is above 4GB, disabling EFI.\n"); return -EINVAL; } - pmap = e->efi_memmap; -#else - pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); -#endif + pmap = (phys_addr_t)(e->efi_memmap | ((u64)e->efi_memmap_hi << 32)); + data.phys_map = pmap; data.size = e->efi_memmap_size; data.desc_size = e->efi_memdesc_size; @@ -243,6 +246,7 @@ int __init efi_memblock_x86_reserve_range(void) efi.memmap.desc_version); memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size); + set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags); return 0; } @@ -305,11 +309,11 @@ static void __init efi_clean_memmap(void) if (n_removal > 0) { struct efi_memory_map_data data = { - .phys_map = efi.memmap.phys_map, - .desc_version = efi.memmap.desc_version, - .desc_size = efi.memmap.desc_size, - .size = efi.memmap.desc_size * (efi.memmap.nr_map - n_removal), - .flags = 0, + .phys_map = efi.memmap.phys_map, + .desc_version = efi.memmap.desc_version, + .desc_size = efi.memmap.desc_size, + .size = efi.memmap.desc_size * (efi.memmap.nr_map - n_removal), + .flags = 0, }; pr_warn("Removing %d invalid memory map entries.\n", n_removal); @@ -333,43 +337,32 @@ void __init efi_print_memmap(void) } } -static int __init efi_systab_init(u64 phys) +static int __init efi_systab_init(unsigned long phys) { int size = efi_enabled(EFI_64BIT) ? sizeof(efi_system_table_64_t) : sizeof(efi_system_table_32_t); + const efi_table_hdr_t *hdr; bool over4g = false; void *p; + int ret; - p = early_memremap_ro(phys, size); + hdr = p = early_memremap_ro(phys, size); if (p == NULL) { pr_err("Couldn't map the system table!\n"); return -ENOMEM; } + ret = efi_systab_check_header(hdr, 1); + if (ret) { + early_memunmap(p, size); + return ret; + } + if (efi_enabled(EFI_64BIT)) { const efi_system_table_64_t *systab64 = p; - efi_systab.hdr = systab64->hdr; - efi_systab.fw_vendor = systab64->fw_vendor; - efi_systab.fw_revision = systab64->fw_revision; - efi_systab.con_in_handle = systab64->con_in_handle; - efi_systab.con_in = systab64->con_in; - efi_systab.con_out_handle = systab64->con_out_handle; - efi_systab.con_out = (void *)(unsigned long)systab64->con_out; - efi_systab.stderr_handle = systab64->stderr_handle; - efi_systab.stderr = systab64->stderr; - efi_systab.runtime = (void *)(unsigned long)systab64->runtime; - efi_systab.boottime = (void *)(unsigned long)systab64->boottime; - efi_systab.nr_tables = systab64->nr_tables; - efi_systab.tables = systab64->tables; - - over4g = systab64->con_in_handle > U32_MAX || - systab64->con_in > U32_MAX || - systab64->con_out_handle > U32_MAX || - systab64->con_out > U32_MAX || - systab64->stderr_handle > U32_MAX || - systab64->stderr > U32_MAX || - systab64->boottime > U32_MAX; + efi_runtime = systab64->runtime; + over4g = systab64->runtime > U32_MAX; if (efi_setup) { struct efi_setup_data *data; @@ -380,38 +373,33 @@ static int __init efi_systab_init(u64 phys) return -ENOMEM; } - efi_systab.fw_vendor = (unsigned long)data->fw_vendor; - efi_systab.runtime = (void *)(unsigned long)data->runtime; - efi_systab.tables = (unsigned long)data->tables; + efi_fw_vendor = (unsigned long)data->fw_vendor; + efi_config_table = (unsigned long)data->tables; over4g |= data->fw_vendor > U32_MAX || - data->runtime > U32_MAX || data->tables > U32_MAX; early_memunmap(data, sizeof(*data)); } else { + efi_fw_vendor = systab64->fw_vendor; + efi_config_table = systab64->tables; + over4g |= systab64->fw_vendor > U32_MAX || - systab64->runtime > U32_MAX || systab64->tables > U32_MAX; } + efi_nr_tables = systab64->nr_tables; } else { const efi_system_table_32_t *systab32 = p; - efi_systab.hdr = systab32->hdr; - efi_systab.fw_vendor = systab32->fw_vendor; - efi_systab.fw_revision = systab32->fw_revision; - efi_systab.con_in_handle = systab32->con_in_handle; - efi_systab.con_in = systab32->con_in; - efi_systab.con_out_handle = systab32->con_out_handle; - efi_systab.con_out = (void *)(unsigned long)systab32->con_out; - efi_systab.stderr_handle = systab32->stderr_handle; - efi_systab.stderr = systab32->stderr; - efi_systab.runtime = (void *)(unsigned long)systab32->runtime; - efi_systab.boottime = (void *)(unsigned long)systab32->boottime; - efi_systab.nr_tables = systab32->nr_tables; - efi_systab.tables = systab32->tables; + efi_fw_vendor = systab32->fw_vendor; + efi_runtime = systab32->runtime; + efi_config_table = systab32->tables; + efi_nr_tables = systab32->nr_tables; } + efi.runtime_version = hdr->revision; + + efi_systab_report_header(hdr, efi_fw_vendor); early_memunmap(p, size); if (IS_ENABLED(CONFIG_X86_32) && over4g) { @@ -419,29 +407,40 @@ static int __init efi_systab_init(u64 phys) return -EINVAL; } - efi.systab = &efi_systab; + return 0; +} + +static int __init efi_config_init(const efi_config_table_type_t *arch_tables) +{ + void *config_tables; + int sz, ret; + + if (efi_nr_tables == 0) + return 0; + + if (efi_enabled(EFI_64BIT)) + sz = sizeof(efi_config_table_64_t); + else + sz = sizeof(efi_config_table_32_t); /* - * Verify the EFI Table + * Let's see what config tables the firmware passed to us. */ - if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { - pr_err("System table signature incorrect!\n"); - return -EINVAL; + config_tables = early_memremap(efi_config_table, efi_nr_tables * sz); + if (config_tables == NULL) { + pr_err("Could not map Configuration table!\n"); + return -ENOMEM; } - if ((efi.systab->hdr.revision >> 16) == 0) - pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff); - return 0; + ret = efi_config_parse_tables(config_tables, efi_nr_tables, + arch_tables); + + early_memunmap(config_tables, efi_nr_tables * sz); + return ret; } void __init efi_init(void) { - efi_char16_t *c16; - char vendor[100] = "unknown"; - int i = 0; - if (IS_ENABLED(CONFIG_X86_32) && (boot_params.efi_info.efi_systab_hi || boot_params.efi_info.efi_memmap_hi)) { @@ -455,29 +454,7 @@ void __init efi_init(void) if (efi_systab_init(efi_systab_phys)) return; - efi.config_table = (unsigned long)efi.systab->tables; - efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; - efi.runtime = (unsigned long)efi.systab->runtime; - - /* - * Show what we know for posterity - */ - c16 = early_memremap_ro(efi.systab->fw_vendor, - sizeof(vendor) * sizeof(efi_char16_t)); - if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i) - vendor[i] = c16[i]; - vendor[i] = '\0'; - early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); - } else { - pr_err("Could not map the firmware vendor!\n"); - } - - pr_info("EFI v%u.%.02u by %s\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff, vendor); - - if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables)) + if (efi_reuse_config(efi_config_table, efi_nr_tables)) return; if (efi_config_init(arch_tables)) @@ -496,6 +473,22 @@ void __init efi_init(void) return; } + /* Parse the EFI Properties table if it exists */ + if (prop_phys != EFI_INVALID_TABLE_ADDR) { + efi_properties_table_t *tbl; + + tbl = early_memremap_ro(prop_phys, sizeof(*tbl)); + if (tbl == NULL) { + pr_err("Could not map Properties table!\n"); + } else { + if (tbl->memory_protection_attribute & + EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA) + set_bit(EFI_NX_PE_DATA, &efi.flags); + + early_memunmap(tbl, sizeof(*tbl)); + } + } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi_clean_memmap(); @@ -602,20 +595,6 @@ static void __init efi_merge_regions(void) } } -static void __init get_systab_virt_addr(efi_memory_desc_t *md) -{ - unsigned long size; - u64 end, systab; - - size = md->num_pages << EFI_PAGE_SHIFT; - end = md->phys_addr + size; - systab = efi_systab_phys; - if (md->phys_addr <= systab && systab < end) { - systab += md->virt_addr - md->phys_addr; - efi.systab = (efi_system_table_t *)(unsigned long)systab; - } -} - static void *realloc_pages(void *old_memmap, int old_shift) { void *ret; @@ -771,7 +750,6 @@ static void * __init efi_map_regions(int *count, int *pg_shift) continue; efi_map_region(md); - get_systab_virt_addr(md); if (left < desc_size) { new_memmap = realloc_pages(new_memmap, *pg_shift); @@ -797,8 +775,6 @@ static void __init kexec_enter_virtual_mode(void) efi_memory_desc_t *md; unsigned int num_pages; - efi.systab = NULL; - /* * We don't do virtual mode, since we don't do runtime services, on * non-native EFI. With the UV1 memmap, we don't do runtime services in @@ -821,10 +797,8 @@ static void __init kexec_enter_virtual_mode(void) * Map efi regions which were passed via setup_data. The virt_addr is a * fixed addr which was used in first kernel of a kexec boot. */ - for_each_efi_memory_desc(md) { + for_each_efi_memory_desc(md) efi_map_region_fixed(md); /* FIXME: add error handling */ - get_systab_virt_addr(md); - } /* * Unregister the early EFI memmap from efi_init() and install @@ -839,8 +813,6 @@ static void __init kexec_enter_virtual_mode(void) return; } - BUG_ON(!efi.systab); - num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE); num_pages >>= PAGE_SHIFT; @@ -850,15 +822,6 @@ static void __init kexec_enter_virtual_mode(void) } efi_sync_low_kernel_mappings(); - - /* - * Now that EFI is in virtual mode, update the function - * pointers in the runtime service table to the new virtual addresses. - * - * Call EFI services through wrapper functions. - */ - efi.runtime_version = efi_systab.hdr.revision; - efi_native_runtime_setup(); #endif } @@ -892,8 +855,6 @@ static void __init __efi_enter_virtual_mode(void) efi_status_t status; unsigned long pa; - efi.systab = NULL; - if (efi_alloc_page_tables()) { pr_err("Failed to allocate EFI page tables\n"); goto err; @@ -925,9 +886,6 @@ static void __init __efi_enter_virtual_mode(void) efi_print_memmap(); } - if (WARN_ON(!efi.systab)) - goto err; - if (efi_setup_page_tables(pa, 1 << pg_shift)) goto err; @@ -936,23 +894,17 @@ static void __init __efi_enter_virtual_mode(void) status = efi_set_virtual_address_map(efi.memmap.desc_size * count, efi.memmap.desc_size, efi.memmap.desc_version, - (efi_memory_desc_t *)pa); + (efi_memory_desc_t *)pa, + efi_systab_phys); if (status != EFI_SUCCESS) { pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n", status); goto err; } + efi_check_for_embedded_firmwares(); efi_free_boot_services(); - /* - * Now that EFI is in virtual mode, update the function - * pointers in the runtime service table to the new virtual addresses. - * - * Call EFI services through wrapper functions. - */ - efi.runtime_version = efi_systab.hdr.revision; - if (!efi_is_mixed()) efi_native_runtime_setup(); else @@ -978,6 +930,8 @@ void __init efi_enter_virtual_mode(void) if (efi_enabled(EFI_PARAVIRT)) return; + efi.runtime = (efi_runtime_services_t *)efi_runtime; + if (efi_setup) kexec_enter_virtual_mode(); else @@ -999,3 +953,43 @@ bool efi_is_table_address(unsigned long phys_addr) return false; } + +char *efi_systab_show_arch(char *str) +{ + if (uga_phys != EFI_INVALID_TABLE_ADDR) + str += sprintf(str, "UGA=0x%lx\n", uga_phys); + return str; +} + +#define EFI_FIELD(var) efi_ ## var + +#define EFI_ATTR_SHOW(name) \ +static ssize_t name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + return sprintf(buf, "0x%lx\n", EFI_FIELD(name)); \ +} + +EFI_ATTR_SHOW(fw_vendor); +EFI_ATTR_SHOW(runtime); +EFI_ATTR_SHOW(config_table); + +struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor); +struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime); +struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table); + +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) +{ + if (attr == &efi_attr_fw_vendor.attr) { + if (efi_enabled(EFI_PARAVIRT) || + efi_fw_vendor == EFI_INVALID_TABLE_ADDR) + return 0; + } else if (attr == &efi_attr_runtime.attr) { + if (efi_runtime == EFI_INVALID_TABLE_ADDR) + return 0; + } else if (attr == &efi_attr_config_table.attr) { + if (efi_config_table == EFI_INVALID_TABLE_ADDR) + return 0; + } + return attr->mode; +} diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 081d466002c9..c049c432745d 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -66,14 +66,16 @@ void __init efi_map_region(efi_memory_desc_t *md) void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} -efi_status_t efi_call_svam(efi_set_virtual_address_map_t *__efiapi *, - u32, u32, u32, void *); +efi_status_t efi_call_svam(efi_runtime_services_t * const *, + u32, u32, u32, void *, u32); efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, unsigned long descriptor_size, u32 descriptor_version, - efi_memory_desc_t *virtual_map) + efi_memory_desc_t *virtual_map, + unsigned long systab_phys) { + const efi_system_table_t *systab = (efi_system_table_t *)systab_phys; struct desc_ptr gdt_descr; efi_status_t status; unsigned long flags; @@ -90,9 +92,10 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, /* Disable interrupts around EFI calls: */ local_irq_save(flags); - status = efi_call_svam(&efi.systab->runtime->set_virtual_address_map, + status = efi_call_svam(&systab->runtime, memory_map_size, descriptor_size, - descriptor_version, virtual_map); + descriptor_version, virtual_map, + __pa(&efi.runtime)); local_irq_restore(flags); load_fixmap_gdt(0); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index fa8506e76bbe..211bb9358b73 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -180,7 +180,7 @@ void efi_sync_low_kernel_mappings(void) static inline phys_addr_t virt_to_phys_or_null_size(void *va, unsigned long size) { - bool bad_size; + phys_addr_t pa; if (!va) return 0; @@ -188,16 +188,13 @@ virt_to_phys_or_null_size(void *va, unsigned long size) if (virt_addr_valid(va)) return virt_to_phys(va); - /* - * A fully aligned variable on the stack is guaranteed not to - * cross a page bounary. Try to catch strings on the stack by - * checking that 'size' is a power of two. - */ - bad_size = size > PAGE_SIZE || !is_power_of_2(size); + pa = slow_virt_to_phys(va); - WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size); + /* check if the object crosses a page boundary */ + if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK)) + return 0; - return slow_virt_to_phys(va); + return pa; } #define virt_to_phys_or_null(addr) \ @@ -500,12 +497,9 @@ static DEFINE_SPINLOCK(efi_runtime_lock); */ #define __efi_thunk(func, ...) \ ({ \ - efi_runtime_services_32_t *__rt; \ unsigned short __ds, __es; \ efi_status_t ____s; \ \ - __rt = (void *)(unsigned long)efi.systab->mixed_mode.runtime; \ - \ savesegment(ds, __ds); \ savesegment(es, __es); \ \ @@ -513,7 +507,7 @@ static DEFINE_SPINLOCK(efi_runtime_lock); loadsegment(ds, __KERNEL_DS); \ loadsegment(es, __KERNEL_DS); \ \ - ____s = efi64_thunk(__rt->func, __VA_ARGS__); \ + ____s = efi64_thunk(efi.runtime->mixed_mode.func, __VA_ARGS__); \ \ loadsegment(ds, __ds); \ loadsegment(es, __es); \ @@ -568,85 +562,25 @@ efi_thunk_set_virtual_address_map(unsigned long memory_map_size, static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { - efi_status_t status; - u32 phys_tm, phys_tc; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - phys_tc = virt_to_phys_or_null(tc); - - status = efi_thunk(get_time, phys_tm, phys_tc); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_time(efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_time, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm) { - efi_status_t status; - u32 phys_enabled, phys_pending, phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_enabled = virt_to_phys_or_null(enabled); - phys_pending = virt_to_phys_or_null(pending); - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(get_wakeup_time, phys_enabled, - phys_pending, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_wakeup_time, enabled, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static unsigned long efi_name_size(efi_char16_t *name) @@ -658,6 +592,8 @@ static efi_status_t efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; @@ -665,14 +601,19 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_data_size = virt_to_phys_or_null(data_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_attr = virt_to_phys_or_null(attr); phys_data = virt_to_phys_or_null_size(data, *data_size); - status = efi_thunk(get_variable, phys_name, phys_vendor, - phys_attr, phys_data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -683,19 +624,25 @@ static efi_status_t efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -707,6 +654,8 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; @@ -714,13 +663,17 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) return EFI_NOT_READY; + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -732,39 +685,36 @@ efi_thunk_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name_size = virt_to_phys_or_null(name_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, *name_size); - status = efi_thunk(get_next_variable, phys_name_size, - phys_name, phys_vendor); + if (!phys_name) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); spin_unlock_irqrestore(&efi_runtime_lock, flags); + *vendor = *vnd; return status; } static efi_status_t efi_thunk_get_next_high_mono_count(u32 *count) { - efi_status_t status; - u32 phys_count; - unsigned long flags; - - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_count = virt_to_phys_or_null(count); - status = efi_thunk(get_next_high_mono_count, phys_count); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - - return status; + return EFI_UNSUPPORTED; } static void @@ -886,8 +836,10 @@ efi_status_t __init __no_sanitize_address efi_set_virtual_address_map(unsigned long memory_map_size, unsigned long descriptor_size, u32 descriptor_version, - efi_memory_desc_t *virtual_map) + efi_memory_desc_t *virtual_map, + unsigned long systab_phys) { + const efi_system_table_t *systab = (efi_system_table_t *)systab_phys; efi_status_t status; unsigned long flags; pgd_t *save_pgd = NULL; @@ -910,13 +862,16 @@ efi_set_virtual_address_map(unsigned long memory_map_size, /* Disable interrupts around EFI calls: */ local_irq_save(flags); - status = efi_call(efi.systab->runtime->set_virtual_address_map, + status = efi_call(efi.runtime->set_virtual_address_map, memory_map_size, descriptor_size, descriptor_version, virtual_map); local_irq_restore(flags); kernel_fpu_end(); + /* grab the virtually remapped EFI runtime services table pointer */ + efi.runtime = READ_ONCE(systab->runtime); + if (save_pgd) efi_uv1_memmap_phys_epilog(save_pgd); else diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index 75c46e7a809f..09ec84f6ef51 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -8,14 +8,20 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/asm-offsets.h> #include <asm/page_types.h> __INIT SYM_FUNC_START(efi_call_svam) - push 8(%esp) - push 8(%esp) + push %ebp + movl %esp, %ebp + push %ebx + + push 16(%esp) + push 16(%esp) push %ecx push %edx + movl %eax, %ebx // &systab_phys->runtime /* * Switch to the flat mapped alias of this routine, by jumping to the @@ -35,15 +41,20 @@ SYM_FUNC_START(efi_call_svam) subl $__PAGE_OFFSET, %esp /* call the EFI routine */ - call *(%eax) + movl (%eax), %eax + call *EFI_svam(%eax) - /* convert ESP back to a kernel VA, and pop the outgoing args */ - addl $__PAGE_OFFSET + 16, %esp + /* grab the virtually remapped EFI runtime services table pointer */ + movl (%ebx), %ecx + movl 36(%esp), %edx // &efi.runtime + movl %ecx, (%edx) /* re-enable paging */ movl %cr0, %edx orl $0x80000000, %edx movl %edx, %cr0 + movl 16(%esp), %ebx + leave ret SYM_FUNC_END(efi_call_svam) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 88d32c06cffa..a5a469cdf5bf 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -410,6 +410,10 @@ void __init efi_free_boot_services(void) int num_entries = 0; void *new, *new_md; + /* Keep all regions for /sys/kernel/debug/efi */ + if (efi_enabled(EFI_DBG)) + return; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -537,7 +541,7 @@ int __init efi_reuse_config(u64 tables, int nr_tables) goto out_memremap; } - for (i = 0; i < efi.systab->nr_tables; i++) { + for (i = 0; i < nr_tables; i++) { efi_guid_t guid; guid = ((efi_config_table_64_t *)p)->guid; @@ -659,12 +663,9 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff, return 1; } -#define ICPU(family, model, quirk_handler) \ - { X86_VENDOR_INTEL, family, model, X86_FEATURE_ANY, \ - (unsigned long)&quirk_handler } - static const struct x86_cpu_id efi_capsule_quirk_ids[] = { - ICPU(5, 9, qrk_capsule_setup_info), /* Intel Quark X1000 */ + X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, + &qrk_capsule_setup_info), { } }; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c index e3f4bfc08f78..31dda18bb370 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -60,11 +60,8 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = { .setup = tng_bt_sfi_setup, }; -#define ICPU(model, ddata) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata } - static const struct x86_cpu_id bt_sfi_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &tng_bt_sfi_data), {} }; diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index e9d97d52475e..0286fe1b14b5 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -569,7 +569,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) } static const struct x86_cpu_id imr_ids[] __initconst = { - { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */ + X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL), {} }; diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 4307830e1b6f..570e3062faac 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -105,7 +105,7 @@ static void __init imr_self_test(void) } static const struct x86_cpu_id imr_ids[] __initconst = { - { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */ + X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL), {} }; diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index 9e2444500428..526f70f27c1c 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -265,7 +265,7 @@ static void iosf_mbi_reset_semaphore(void) iosf_mbi_sem_address, 0, PUNIT_SEMAPHORE_BIT)) dev_err(&mbi_pdev->dev, "Error P-Unit semaphore reset failed\n"); - pm_qos_update_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE); blocking_notifier_call_chain(&iosf_mbi_pmic_bus_access_notifier, MBI_PMIC_BUS_ACCESS_END, NULL); @@ -301,8 +301,8 @@ static void iosf_mbi_reset_semaphore(void) * 4) When CPU cores enter C6 or C7 the P-Unit needs to talk to the PMIC * if this happens while the kernel itself is accessing the PMIC I2C bus * the SoC hangs. - * As the third step we call pm_qos_update_request() to disallow the CPU - * to enter C6 or C7. + * As the third step we call cpu_latency_qos_update_request() to disallow the + * CPU to enter C6 or C7. * * 5) The P-Unit has a PMIC bus semaphore which we can request to stop * autonomous P-Unit tasks from accessing the PMIC I2C bus while we hold it. @@ -338,7 +338,7 @@ int iosf_mbi_block_punit_i2c_access(void) * requires the P-Unit to talk to the PMIC and if this happens while * we're holding the semaphore, the SoC hangs. */ - pm_qos_update_request(&iosf_mbi_pm_qos, 0); + cpu_latency_qos_update_request(&iosf_mbi_pm_qos, 0); /* host driver writes to side band semaphore register */ ret = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE, @@ -547,8 +547,7 @@ static int __init iosf_mbi_init(void) { iosf_debugfs_init(); - pm_qos_add_request(&iosf_mbi_pm_qos, PM_QOS_CPU_DMA_LATENCY, - PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_add_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE); return pci_register_driver(&iosf_mbi_pci_driver); } @@ -561,7 +560,7 @@ static void __exit iosf_mbi_exit(void) pci_dev_put(mbi_pdev); mbi_pdev = NULL; - pm_qos_remove_request(&iosf_mbi_pm_qos); + cpu_latency_qos_remove_request(&iosf_mbi_pm_qos); } module_init(iosf_mbi_init); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 915bb1639763..aaff9ed7ff45 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -475,20 +475,8 @@ static int msr_save_cpuid_features(const struct x86_cpu_id *c) } static const struct x86_cpu_id msr_save_cpu_table[] = { - { - .vendor = X86_VENDOR_AMD, - .family = 0x15, - .model = X86_MODEL_ANY, - .feature = X86_FEATURE_ANY, - .driver_data = (kernel_ulong_t)msr_save_cpuid_features, - }, - { - .vendor = X86_VENDOR_AMD, - .family = 0x16, - .model = X86_MODEL_ANY, - .feature = X86_FEATURE_ANY, - .driver_data = (kernel_ulong_t)msr_save_cpuid_features, - }, + X86_MATCH_VENDOR_FAM(AMD, 0x15, &msr_save_cpuid_features), + X86_MATCH_VENDOR_FAM(AMD, 0x16, &msr_save_cpuid_features), {} }; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 1f756ffffe8b..507f4fb88fa7 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -72,6 +72,9 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/cpu.h> +#ifdef CONFIG_X86_IOPL_IOPERM +#include <asm/io_bitmap.h> +#endif #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -837,6 +840,25 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } +#ifdef CONFIG_X86_IOPL_IOPERM +static void xen_update_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap; + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + + native_tss_update_io_bitmap(); + + iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + + tss->x86_tss.io_bitmap_base; + if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) + iobitmap.nr_ports = 0; + else + iobitmap.nr_ports = IO_BITMAP_BITS; + + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} +#endif + static void xen_io_delay(void) { } @@ -896,14 +918,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; +#ifdef CONFIG_X86_64 + unsigned int which; + u64 base; +#endif ret = 0; switch (msr) { #ifdef CONFIG_X86_64 - unsigned which; - u64 base; - case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; @@ -1046,6 +1069,9 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, +#ifdef CONFIG_X86_IOPL_IOPERM + .update_io_bitmap = xen_update_io_bitmap, +#endif .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 7a43b2ae19f1..2097fa0ebdb5 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -132,7 +132,7 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) continue; - rc = cpu_down(cpu); + rc = remove_cpu(cpu); if (rc == 0) { /* diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h index 964611083224..a1a27b2ea460 100644 --- a/arch/xtensa/include/asm/futex.h +++ b/arch/xtensa/include/asm/futex.h @@ -72,7 +72,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, #if XCHAL_HAVE_S32C1I || XCHAL_HAVE_EXCLUSIVE int oldval = 0, ret; - pagefault_disable(); + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; switch (op) { case FUTEX_OP_SET: @@ -99,8 +100,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, ret = -ENOSYS; } - pagefault_enable(); - if (!ret) *oval = oldval; diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 833109880165..49322b66cda9 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -267,13 +267,12 @@ static int __init simdisk_setup(struct simdisk *dev, int which, spin_lock_init(&dev->lock); dev->users = 0; - dev->queue = blk_alloc_queue(GFP_KERNEL); + dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE); if (dev->queue == NULL) { pr_err("blk_alloc_queue failed\n"); goto out_alloc_queue; } - blk_queue_make_request(dev->queue, simdisk_make_request); dev->queue->queuedata = dev; dev->gd = alloc_disk(SIMDISK_MINORS); |